Validation of an instrument to measure tutor performance in promoting self-directed learning by using confirmatory factor analysis.

PubMed

Amador Fierros, Genoveva; Montesinos-López, Osval Antonio; Alcaráz Moreno, Noemí

2016-04-01

This work sought to validate and propose an instrument to measure the performance of tutors in promoting self-directed learning in students involved in processes of problem-based learning. Confirmatory factor analysis (CFA) was applied to validate the instrument composed of 60 items and six factors (self-assessment of learning gaps within the United Nations specific context: self-assessment, reflexion, critical thinking, administration of information, group skills), using a sample of 207 students from a total of 279, which comprise the student population of the Faculty of Nursing at Universidad de Colima in Mexico. (2007). The CFA results demonstrated that the instrument is acceptable to measure performance of tutors in promoting self-directed learning, given that all the indicators, variances, covariances, and thresholds are statistically significant. The instrument permits obtaining students' opinions on how much professors contribute for them to develop each of the 60 skills described in the scale. Lastly, the results could report if professors are placing more emphasis in some areas than in other areas they should address during the problem-based learning (PBL) process, or if definitely their actions are removed from the premises of PBL, information that will be useful for school management in decision making on the direction of teaching as a whole.

Empirical Validation of the Importance of Employees' Learning Motivation for Workplace E-Learning in Taiwanese Organisations

ERIC Educational Resources Information Center

Chen, Hsiu-Ju; Kao, Chia-Hung

2012-01-01

E-learning systems, adopted by organisations for employee training to enhance employees' performance, are characterised by self-directed, autonomous learning. Learning motivation is then of importance in the design of e-learning practices in workplace. However, empirical study of the alignment of e-learning with individual learning needs and…

Blended Learning Improves Science Education.

PubMed

Stockwell, Brent R; Stockwell, Melissa S; Cennamo, Michael; Jiang, Elise

2015-08-27

Blended learning is an emerging paradigm for science education but has not been rigorously assessed. We performed a randomized controlled trial of blended learning. We found that in-class problem solving improved exam performance, and video assignments increased attendance and satisfaction. This validates a new model for science communication and education. Copyright © 2015 Elsevier Inc. All rights reserved.

Validation of the three web quality dimensions of a minimally invasive surgery e-learning platform.

PubMed

Ortega-Morán, Juan Francisco; Pagador, J Blas; Sánchez-Peralta, Luisa Fernanda; Sánchez-González, Patricia; Noguera, José; Burgos, Daniel; Gómez, Enrique J; Sánchez-Margallo, Francisco M

2017-11-01

E-learning web environments, including the new TELMA platform, are increasingly being used to provide cognitive training in minimally invasive surgery (MIS) to surgeons. A complete validation of this MIS e-learning platform has been performed to determine whether it complies with the three web quality dimensions: usability, content and functionality. 21 Surgeons participated in the validation trials. They performed a set of tasks in the TELMA platform, where an e-MIS validity approach was followed. Subjective (questionnaires and checklists) and objective (web analytics) metrics were analysed to achieve the complete validation of usability, content and functionality. The TELMA platform allowed access to didactic content with easy and intuitive navigation. Surgeons performed all tasks with a close-to-ideal number of clicks and amount of time. They considered the design of the website to be consistent (95.24%), organised (90.48%) and attractive (85.71%). Moreover, they gave the content a high score (4.06 out of 5) and considered it adequate for teaching purposes. The surgeons scored the professional language and content (4.35), logo (4.24) and recommendations (4.20) the highest. Regarding functionality, the TELMA platform received an acceptance of 95.24% for navigation and 90.48% for interactivity. According to the study, it seems that TELMA had an attractive design, innovative content and interactive navigation, which are three key features of an e-learning platform. TELMA successfully met the three criteria necessary for consideration as a website of quality by achieving more than 70% of agreements regarding all usability, content and functionality items validated; this constitutes a preliminary requirement for an effective e-learning platform. However, the content completeness, authoring tool and registration process required improvement. Finally, the e-MIS validity methodology used to measure the three dimensions of web quality in this work can be applied to other clinical areas or training fields. Copyright © 2017 Elsevier B.V. All rights reserved.

Educational Technology-Related Performance of Teaching Faculty in Higher Education: Implications for eLearning Management

ERIC Educational Resources Information Center

Larbi-Apau, Josephine A.; Guerra-Lopez, Ingrid; Moseley, James L.; Spannaus, Timothy; Yaprak, Attila

2017-01-01

The study examined teaching faculty's educational technology-related performances (ETRP) as a measure for predicting eLearning management in Ghana. A total of valid data (n = 164) were collected and analyzed on applied ISTE-NETS-T Performance Standards using descriptive and ANOVA statistics. Results showed an overall moderate performance with the…

Concussion classification via deep learning using whole-brain white matter fiber strains

PubMed Central

Cai, Yunliang; Wu, Shaoju; Zhao, Wei; Li, Zhigang; Wu, Zheyang

2018-01-01

Developing an accurate and reliable injury predictor is central to the biomechanical studies of traumatic brain injury. State-of-the-art efforts continue to rely on empirical, scalar metrics based on kinematics or model-estimated tissue responses explicitly pre-defined in a specific brain region of interest. They could suffer from loss of information. A single training dataset has also been used to evaluate performance but without cross-validation. In this study, we developed a deep learning approach for concussion classification using implicit features of the entire voxel-wise white matter fiber strains. Using reconstructed American National Football League (NFL) injury cases, leave-one-out cross-validation was employed to objectively compare injury prediction performances against two baseline machine learning classifiers (support vector machine (SVM) and random forest (RF)) and four scalar metrics via univariate logistic regression (Brain Injury Criterion (BrIC), cumulative strain damage measure of the whole brain (CSDM-WB) and the corpus callosum (CSDM-CC), and peak fiber strain in the CC). Feature-based machine learning classifiers including deep learning, SVM, and RF consistently outperformed all scalar injury metrics across all performance categories (e.g., leave-one-out accuracy of 0.828–0.862 vs. 0.690–0.776, and .632+ error of 0.148–0.176 vs. 0.207–0.292). Further, deep learning achieved the best cross-validation accuracy, sensitivity, AUC, and .632+ error. These findings demonstrate the superior performances of deep learning in concussion prediction and suggest its promise for future applications in biomechanical investigations of traumatic brain injury. PMID:29795640

Concussion classification via deep learning using whole-brain white matter fiber strains.

PubMed

Cai, Yunliang; Wu, Shaoju; Zhao, Wei; Li, Zhigang; Wu, Zheyang; Ji, Songbai

2018-01-01

Developing an accurate and reliable injury predictor is central to the biomechanical studies of traumatic brain injury. State-of-the-art efforts continue to rely on empirical, scalar metrics based on kinematics or model-estimated tissue responses explicitly pre-defined in a specific brain region of interest. They could suffer from loss of information. A single training dataset has also been used to evaluate performance but without cross-validation. In this study, we developed a deep learning approach for concussion classification using implicit features of the entire voxel-wise white matter fiber strains. Using reconstructed American National Football League (NFL) injury cases, leave-one-out cross-validation was employed to objectively compare injury prediction performances against two baseline machine learning classifiers (support vector machine (SVM) and random forest (RF)) and four scalar metrics via univariate logistic regression (Brain Injury Criterion (BrIC), cumulative strain damage measure of the whole brain (CSDM-WB) and the corpus callosum (CSDM-CC), and peak fiber strain in the CC). Feature-based machine learning classifiers including deep learning, SVM, and RF consistently outperformed all scalar injury metrics across all performance categories (e.g., leave-one-out accuracy of 0.828-0.862 vs. 0.690-0.776, and .632+ error of 0.148-0.176 vs. 0.207-0.292). Further, deep learning achieved the best cross-validation accuracy, sensitivity, AUC, and .632+ error. These findings demonstrate the superior performances of deep learning in concussion prediction and suggest its promise for future applications in biomechanical investigations of traumatic brain injury.

Motivation, learning strategies, participation and medical school performance.

PubMed

Stegers-Jager, Karen M; Cohen-Schotanus, Janke; Themmen, Axel P N

2012-07-01

Medical schools wish to better understand why some students excel academically and others have difficulty in passing medical courses. Components of self-regulated learning (SRL), such as motivational beliefs and learning strategies, as well as participation in scheduled learning activities, have been found to relate to student performance. Although participation may be a form of SRL, little is known about the relationships among motivational beliefs, learning strategies, participation and medical school performance. This study aimed to test and cross-validate a hypothesised model of relationships among motivational beliefs (value and self-efficacy), learning strategies (deep learning and resource management), participation (lecture attendance, skills training attendance and completion of optional study assignments) and Year 1 performance at medical school. Year 1 medical students in the cohorts of 2008 (n = 303) and 2009 (n = 369) completed a questionnaire on motivational beliefs and learning strategies (sourced from the Motivated Strategies for Learning Questionnaire) and participation. Year 1 performance was operationalised as students' average Year 1 course examination grades. Structural equation modelling was used to analyse the data. Participation and self-efficacy beliefs were positively associated with Year 1 performance (β = 0.78 and β = 0.19, respectively). Deep learning strategies were negatively associated with Year 1 performance (β =- 0.31), but positively related to resource management strategies (β = 0.77), which, in turn, were positively related to participation (β = 0.79). Value beliefs were positively related to deep learning strategies only (β = 0.71). The overall structural model for the 2008 cohort accounted for 47% of the variance in Year 1 grade point average and was cross-validated in the 2009 cohort. This study suggests that participation mediates the relationships between motivation and learning strategies, and medical school performance. However, participation and self-efficacy beliefs also made unique contributions towards performance. Encouraging participation and strengthening self-efficacy may help to enhance medical student performance. © Blackwell Publishing Ltd 2012.

Validating Teacher Performativity through Lifelong School-University Collaboration

ERIC Educational Resources Information Center

Lewis, Theodore

2013-01-01

The main point of this article is that more credence should be given in teacher education to performative dimensions of teaching. I agree with David Carr (1999) that the requisite capabilities are probably best learned in actual schools. I employ Turnbull's (2000) conception of performativity, which speaks of tacit cultural learning. Following…

Development of Advanced Verification and Validation Procedures and Tools for the Certification of Learning Systems in Aerospace Applications

NASA Technical Reports Server (NTRS)

Jacklin, Stephen; Schumann, Johann; Gupta, Pramod; Richard, Michael; Guenther, Kurt; Soares, Fola

2005-01-01

Adaptive control technologies that incorporate learning algorithms have been proposed to enable automatic flight control and vehicle recovery, autonomous flight, and to maintain vehicle performance in the face of unknown, changing, or poorly defined operating environments. In order for adaptive control systems to be used in safety-critical aerospace applications, they must be proven to be highly safe and reliable. Rigorous methods for adaptive software verification and validation must be developed to ensure that control system software failures will not occur. Of central importance in this regard is the need to establish reliable methods that guarantee convergent learning, rapid convergence (learning) rate, and algorithm stability. This paper presents the major problems of adaptive control systems that use learning to improve performance. The paper then presents the major procedures and tools presently developed or currently being developed to enable the verification, validation, and ultimate certification of these adaptive control systems. These technologies include the application of automated program analysis methods, techniques to improve the learning process, analytical methods to verify stability, methods to automatically synthesize code, simulation and test methods, and tools to provide on-line software assurance.

Social Cues Alter Implicit Motor Learning in a Serial Reaction Time Task.

PubMed

Geiger, Alexander; Cleeremans, Axel; Bente, Gary; Vogeley, Kai

2018-01-01

Learning is a central ability for human development. Many skills we learn, such as language, are learned through observation or imitation in social contexts. Likewise, many skills are learned implicitly, that is, without an explicit intent to learn and without full awareness of the acquired knowledge. Here, we asked whether performance in a motor learning task is modulated by social vs. object cues of varying validity. To address this question, we asked participants to carry out a serial reaction time (SRT) task in which, on each trial, people have to respond as fast and as accurately as possible to the appearance of a stimulus at one of four possible locations. Unbeknownst to participants, the sequence of successive locations was sequentially structured, so that knowledge of the sequence facilitates anticipation of the next stimulus and hence faster motor responses. Crucially, each trial also contained a cue pointing to the next stimulus location. Participants could thus learn based on the cue, or on learning about the sequence of successive locations, or on a combination of both. Results show an interaction between cue type and cue validity for the motor responses: social cues (vs. object cues) led to faster responses in the low validity (LV) condition only. Concerning the extent to which learning was implicit, results show that in the cued blocks only, the highly valid social cue led to implicit learning. In the uncued blocks, participants showed no implicit learning in the highly valid social cue condition, but did in all other combinations of stimulus type and cueing validity. In conclusion, our results suggest that implicit learning is context-dependent and can be influenced by the cue type, e.g., social and object cues.

Beyond Objectivity: The Performance Impact of the Perceived Ability to Learn and Solve Problems

ERIC Educational Resources Information Center

Tews, Michael J.; Michel, John W.; Noe, Raymond A.

2011-01-01

The purpose of this research was to develop and provide initial validation evidence for the performance impact of a measure of an individual's perceived ability to learn and solve problems (PALS). Building on the self-efficacy literature and the importance of learning and problem solving, the fundamental premise of this research was that PALS…

An Efficient Data Partitioning to Improve Classification Performance While Keeping Parameters Interpretable

PubMed Central

Korjus, Kristjan; Hebart, Martin N.; Vicente, Raul

2016-01-01

Supervised machine learning methods typically require splitting data into multiple chunks for training, validating, and finally testing classifiers. For finding the best parameters of a classifier, training and validation are usually carried out with cross-validation. This is followed by application of the classifier with optimized parameters to a separate test set for estimating the classifier’s generalization performance. With limited data, this separation of test data creates a difficult trade-off between having more statistical power in estimating generalization performance versus choosing better parameters and fitting a better model. We propose a novel approach that we term “Cross-validation and cross-testing” improving this trade-off by re-using test data without biasing classifier performance. The novel approach is validated using simulated data and electrophysiological recordings in humans and rodents. The results demonstrate that the approach has a higher probability of discovering significant results than the standard approach of cross-validation and testing, while maintaining the nominal alpha level. In contrast to nested cross-validation, which is maximally efficient in re-using data, the proposed approach additionally maintains the interpretability of individual parameters. Taken together, we suggest an addition to currently used machine learning approaches which may be particularly useful in cases where model weights do not require interpretation, but parameters do. PMID:27564393

An Efficient Data Partitioning to Improve Classification Performance While Keeping Parameters Interpretable.

PubMed

Korjus, Kristjan; Hebart, Martin N; Vicente, Raul

2016-01-01

Supervised machine learning methods typically require splitting data into multiple chunks for training, validating, and finally testing classifiers. For finding the best parameters of a classifier, training and validation are usually carried out with cross-validation. This is followed by application of the classifier with optimized parameters to a separate test set for estimating the classifier's generalization performance. With limited data, this separation of test data creates a difficult trade-off between having more statistical power in estimating generalization performance versus choosing better parameters and fitting a better model. We propose a novel approach that we term "Cross-validation and cross-testing" improving this trade-off by re-using test data without biasing classifier performance. The novel approach is validated using simulated data and electrophysiological recordings in humans and rodents. The results demonstrate that the approach has a higher probability of discovering significant results than the standard approach of cross-validation and testing, while maintaining the nominal alpha level. In contrast to nested cross-validation, which is maximally efficient in re-using data, the proposed approach additionally maintains the interpretability of individual parameters. Taken together, we suggest an addition to currently used machine learning approaches which may be particularly useful in cases where model weights do not require interpretation, but parameters do.

Incidental Learning: A Brief, Valid Measure of Memory Based on the WAIS-IV Vocabulary and Similarities Subtests.

PubMed

Spencer, Robert J; Reckow, Jaclyn; Drag, Lauren L; Bieliauskas, Linas A

2016-12-01

We assessed the validity of a brief incidental learning measure based on the Similarities and Vocabulary subtests of the Wechsler Adult Intelligence Scale-Fourth Edition (WAIS-IV). Most neuropsychological assessments for memory require intentional learning, but incidental learning occurs without explicit instruction. Incidental memory tests such as the WAIS-III Symbol Digit Coding subtest have existed for many years, but few memory studies have used a semantically processed incidental learning model. We conducted a retrospective analysis of 37 veterans with traumatic brain injury, referred for outpatient neuropsychological testing at a Veterans Affairs hospital. As part of their evaluation, the participants completed the incidental learning tasks. We compared their incidental learning performance to their performance on traditional memory measures. Incidental learning scores correlated strongly with scores on the California Verbal Learning Test-Second Edition (CVLT-II) and Brief Visuospatial Memory Test-Revised (BVMT-R). After we conducted a partial correlation that controlled for the effects of age, incidental learning correlated significantly with the CVLT-II Immediate Free Recall, CVLT-II Short-Delay Recall, CVLT-II Long-Delay Recall, and CVLT-II Yes/No Recognition Hits, and with the BVMT-R Delayed Recall and BVMT-R Recognition Discrimination Index. Our incidental learning procedures derived from subtests of the WAIS-IV Edition are an efficient and valid way of measuring memory. These tasks add minimally to testing time and capitalize on the semantic encoding that is inherent in completing the Similarities and Vocabulary subtests.

Learning with Multiple Representations: Extending Multimedia Learning beyond the Lab

ERIC Educational Resources Information Center

Eilam, Billie; Poyas, Yael

2008-01-01

The present study extended multimedia learning principles beyond the lab to an ecologically valid setting (homework). Eighteen information cards were used to perform three homework tasks. The control group students learned from single representation (SR) cards that presented all information as printed text. The multiple representation (MR) group…

Development and Validation of a Learning Analytics Framework: Two Case Studies Using Support Vector Machines

ERIC Educational Resources Information Center

Ifenthaler, Dirk; Widanapathirana, Chathuranga

2014-01-01

Interest in collecting and mining large sets of educational data on student background and performance to conduct research on learning and instruction has developed as an area generally referred to as learning analytics. Higher education leaders are recognizing the value of learning analytics for improving not only learning and teaching but also…

Estimating learning outcomes from pre- and posttest student self-assessments: a longitudinal study.

PubMed

Schiekirka, Sarah; Reinhardt, Deborah; Beißbarth, Tim; Anders, Sven; Pukrop, Tobias; Raupach, Tobias

2013-03-01

Learning outcome is an important measure for overall teaching quality and should be addressed by comprehensive evaluation tools. The authors evaluated the validity of a novel evaluation tool based on student self-assessments, which may help identify specific strengths and weaknesses of a particular course. In 2011, the authors asked 145 fourth-year students at Göttingen Medical School to self-assess their knowledge on 33 specific learning objectives in a pretest and posttest as part of a cardiorespiratory module. The authors compared performance gain calculated from self-assessments with performance gain derived from formative examinations that were closely matched to these 33 learning objectives. Eighty-three students (57.2%) completed the assessment. There was good agreement between performance gain derived from subjective data and performance gain derived from objective examinations (Pearson r=0.78; P<.0001) on the group level. The association between the two measures was much weaker when data were analyzed on the individual level. Further analysis determined a quality cutoff for performance gain derived from aggregated student self-assessments. When using this cutoff, the evaluation tool was highly sensitive in identifying specific learning objectives with favorable or suboptimal objective performance gains. The tool is easy to implement, takes initial performance levels into account, and does not require extensive pre-post testing. By providing valid estimates of actual performance gain obtained during a teaching module, it may assist medical teachers in identifying strengths and weaknesses of a particular course on the level of specific learning objectives.

The Impact of Preceptor and Student Learning Styles on Experiential Performance Measures

PubMed Central

Cox, Craig D.; Seifert, Charles F.

2012-01-01

Objectives. To identify preceptors’ and students’ learning styles to determine how these impact students’ performance on pharmacy practice experience assessments. Methods. Students and preceptors were asked to complete a validated Pharmacist’s Inventory of Learning Styles (PILS) questionnaire to identify dominant and secondary learning styles. The significance of “matched” and “unmatched” learning styles between students and preceptors was evaluated based on performance on both subjective and objective practice experience assessments. Results. Sixty-one percent of 67 preceptors and 57% of 72 students who participated reported “assimilator” as their dominant learning style. No differences were found between student and preceptor performance on evaluations, regardless of learning style match. Conclusion. Determination of learning styles may encourage preceptors to use teaching methods to challenge students during pharmacy practice experiences; however, this does not appear to impact student or preceptor performance. PMID:23049100

Development and validation of a Clinical Assessment Tool for Nursing Education (CAT-NE).

PubMed

Skúladóttir, Hafdís; Svavarsdóttir, Margrét Hrönn

2016-09-01

The aim of this study was to develop a valid assessment tool to guide clinical education and evaluate students' performance in clinical nursing education. The development of the Clinical Assessment Tool for Nursing Education (CAT-NE) was based on the theory of nursing as professional caring and the Bologna learning outcomes. Benson and Clark's four steps of instrument development and validation guided the development and assessment of the tool. A mixed-methods approach with individual structured cognitive interviewing and quantitative assessments was used to validate the tool. Supervisory teachers, a pedagogical consultant, clinical expert teachers, clinical teachers, and nursing students at the University of Akureyri in Iceland participated in the process. This assessment tool is valid to assess the clinical performance of nursing students; it consists of rubrics that list the criteria for the students' expected performance. According to the students and their clinical teachers, the assessment tool clarified learning objectives, enhanced the focus of the assessment process, and made evaluation more objective. Training clinical teachers on how to assess students' performances in clinical studies and use the tool enhanced the quality of clinical assessment in nursing education. Copyright © 2016 Elsevier Ltd. All rights reserved.

The Learning Loss Scale as an Assessment Tool: An Empirical Examination of Convergent Validity with Performative Measures

ERIC Educational Resources Information Center

Hooker, John; Denker, Katherine

2014-01-01

Higher education has placed an increasingly greater value on assessment. The Learning Loss Scale may be an appropriate tool to assess learning across disciplines. In this paper, we review the culture of assessment, conceptualizations of cognitive learning, the Learning Loss Scale, and a theoretical explanation, and then we test this measure to…

Development of simulation-based learning programme for improving adherence to time-out protocol on high-risk invasive procedures outside of operating room.

PubMed

Jeong, Eun Ju; Chung, Hyun Soo; Choi, Jeong Yun; Kim, In Sook; Hong, Seong Hee; Yoo, Kyung Sook; Kim, Mi Kyoung; Won, Mi Yeol; Eum, So Yeon; Cho, Young Soon

2017-06-01

The aim of this study was to develop a simulation-based time-out learning programme targeted to nurses participating in high-risk invasive procedures and to figure out the effects of application of the new programme on acceptance of nurses. This study was performed using a simulation-based learning predesign and postdesign to figure out the effects of implementation of this programme. It was targeted to 48 registered nurses working in the general ward and the emergency department in a tertiary teaching hospital. Difference between acceptance and performance rates has been figured out by using mean, standard deviation, and Wilcoxon-signed rank test. The perception survey and score sheet have been validated through content validation index, and the reliability of evaluator has been verified by using intraclass correlation coefficient. Results showed high level of acceptance of high-risk invasive procedure (P<.01). Further, improvement was consistent regardless of clinical experience, workplace, or experience in simulation-based learning. The face validity of the programme showed over 4.0 out of 5.0. This simulation-based learning programme was effective in improving the recognition of time-out protocol and has given the participants the opportunity to become proactive in cases of high-risk invasive procedures performed outside of operating room. © 2017 John Wiley & Sons Australia, Ltd.

The development of performance-based practical assessment model at civil engineering workshop in state polytechnic

NASA Astrophysics Data System (ADS)

Kristinayanti, W. S.; Mas Pertiwi, I. G. A. I.; Evin Yudhi, S.; Lokantara, W. D.

2018-01-01

Assessment is an important element in education that shall oversees students’ competence not only in terms of cognitive aspect, but alsothe students’ psychomotorin a comprehensive way. Civil Engineering Department at Bali State Polytechnic,as a vocational education institution, emphasizes on not only the theoretical foundation of the study, but also the application throughpracticum in workshop-based learning. We are aware of a need for performance-based assessment for these students, which would be essential for the student’s all-round performance in their studies.We try to develop a performance-based practicum assessment model that is needed to assess student’s ability in workshop-based learning. This research was conducted in three stages, 1) learning needs analysis, 2) instruments development, and 3) testing of instruments. The study uses rubrics set-up to test students’ competence in the workshop and test the validity. We obtained 34-point valid statement out of 35, and resulted in value of Cronbach’s alpha equal to 0.977. In expert test we obtained a value of CVI = 0.75 which means that the drafted assessment is empirically valid within thetrial group.

Replication of elite music performance enhancement following alpha/theta neurofeedback and application to novice performance and improvisation with SMR benefits.

PubMed

Gruzelier, J H; Holmes, P; Hirst, L; Bulpin, K; Rahman, S; van Run, C; Leach, J

2014-01-01

Alpha/theta (A/T) and sensory-motor rhythm (SMR) neurofeedback were compared in university instrumentalists who were novice singers with regard to prepared and improvised instrumental and vocal performance in three music domains: creativity/musicality, technique and communication/presentation. Only A/T training enhanced advanced playing seen in all three domains by expert assessors and validated by correlations with learning indices, strongest with Creativity/Musicality as shown by Egner and Gruzelier (2003). Here A/T gains extended to novice performance - prepared vocal, improvised vocal and instrumental - and were recognised by a lay audience who judged the prepared folk songs. SMR learning correlated positively with Technical Competence and Communication in novice performance, in keeping with SMR neurofeedback's known impact on lower-order processes such as attention, working memory and psychomotor skills. The importance of validation through learning indices was emphasised in the interpretation of neurofeedback outcome. Copyright © 2013 Elsevier B.V. All rights reserved.

Value-Added Models for Teacher Preparation Programs: Validity and Reliability Threats, and a Manageable Alternative

ERIC Educational Resources Information Center

Brady, Michael P.; Heiser, Lawrence A.; McCormick, Jazarae K.; Forgan, James

2016-01-01

High-stakes standardized student assessments are increasingly used in value-added evaluation models to connect teacher performance to P-12 student learning. These assessments are also being used to evaluate teacher preparation programs, despite validity and reliability threats. A more rational model linking student performance to candidates who…

Leveraging MSLQ Data for Predicting Student Achievement Goal Orientations

ERIC Educational Resources Information Center

Ali, Liaqat; Hatala, Marek; Winne, Phil; Gaševic, Dragan

2014-01-01

This study aims to investigate how the learning strategies and achievement goal orientations of students relate to their academic behaviours and performance in the context of an online learning system. The study also develops and validates a relational model between student learning strategies and achievement goals.

The development and validation of the On-the-job Learning Styles Questionnaire for the Nursing Profession.

PubMed

Berings, Marjolein G M C; Poell, Rob F; Simons, P Robert-Jan; van Veldhoven, Marc J P M

2007-06-01

This paper is a report of a study to develop and test the psychometric properties of the On-the-job Learning Style Questionnaire for the Nursing Profession. Although numerous questionnaires measuring learning styles have been developed, none are suitable for working environments. Existing instruments do not meet the requirements for use in workplace settings and tend to ignore the influence of different learning situations. The questionnaire was constructed using a situation-response design, measuring learning activities in different on-the-job learning situations. Content validity was ensured by basing the questionnaire on interview studies. The questionnaire was distributed to 912 Registered Nurses working in different departments of 13 general hospitals in the Netherlands at the end of 2005. The response rate was 41% (372 questionnaires). The internal factor structure of the questionnaire was partly based on the learning activities in which nurses participate and partly on the learning situation in which they are performed. The internal consistency was good. The situation-response design of the questionnaire demonstrated its added value. Construct validity was estimated using intercorrelations between the scales, and criterion validity was estimated based on the relationships of the scales with perceived professional competence. The On-the-job Learning Styles Questionnaire for the Nursing Profession is well suited to describing nurses' learning styles in on-the-job settings and has satisfactory psychometric properties.

Implementation and Use of Simulated Students for Test and Validation of New Adaptive Educational Systems: A Practical Insight

ERIC Educational Resources Information Center

Dorça, Fabiano

2015-01-01

Studies attest that learning is facilitated if teaching strategies are in accordance with students learning styles, making learning process more effective and considerably improving students performances. In this context, one major research point--and a challenge--is to efficiently discover students' learning styles. But, the test and validation…

The Impact of Summer Learning Loss on Measures of School Performance

ERIC Educational Resources Information Center

McEachin, Andrew; Atteberry, Allison

2017-01-01

State and federal accountability policies are predicated on the ability to estimate valid and reliable measures of school impacts on student learning. The typical spring-to-spring testing window potentially conflates the amount of learning that occurs during the school year with learning that occurs during the summer. We use a unique dataset to…

Influence of feedback characteristics on perceived learning value of feedback in clerkships: does culture matter?

PubMed

Suhoyo, Yoyo; Van Hell, Elisabeth A; Kerdijk, Wouter; Emilia, Ova; Schönrock-Adema, Johanna; Kuks, Jan B M; Cohen-Schotanus, Janke

2017-04-05

Various feedback characteristics have been suggested to positively influence student learning. It is not clear how these feedback characteristics contribute to students' perceived learning value of feedback in cultures classified low on the cultural dimension of individualism and high on power distance. This study was conducted to validate the influence of five feedback characteristics on students' perceived learning value of feedback in an Indonesian clerkship context. We asked clerks in Neurology (n = 169) and Internal Medicine (n = 132) to assess on a 5-point Likert scale the learning value of the feedback they received. We asked them to record whether the feedback provider (1) informed the student what went well, (2) mentioned which aspects of performance needed improvement, (3) compared the student's performance to a standard, (4) further explained or demonstrated the correct performance, and (5) prepared an action plan with the student to improve performance. Data were analyzed using multilevel regression. A total of 250 students participated in this study, 131 from Internal Medicine (response rate 99%) and 119 from Neurology (response rate 70%). Of these participants, 225 respondents (44% males, 56% females) completed the form and reported 889 feedback moments. Students perceived feedback as more valuable when the feedback provider mentioned their weaknesses (β = 0.153, p < 0.01), compared their performance to a standard (β = 0.159, p < 0.01), explained or demonstrated the correct performance (β = 0.324, p < 0.001) and prepared an action plan with the student (β =0.496, p < 0.001). Appraisal of good performance did not influence the perceived learning value of feedback. No gender differences were found for perceived learning value. In Indonesia, we could validate four out of the five characteristics for effective feedback. We argue that our findings relate to culture, in particular to the levels of individualism and power distance. The recognized characteristics of what constitutes effective feedback should be validated across cultures.

New Zealand and Queensland Teachers' Conceptions of Learning: Transforming More than Reproducing

ERIC Educational Resources Information Center

Brown, Gavin T. L.; Lake, Robert; Matters, Gabrielle

2008-01-01

Background: Two major conceptions of learning exist: reproducing new material and transforming material to make meaning. Teachers' understandings of what learning is probably influence their teaching practices and student academic performance. Aims: To validate a short scale derived from Tait, Entwistle, & McCune's (1998) ASSIST inventory and…

Measuring striving for understanding and learning value of geometry: a validity study

NASA Astrophysics Data System (ADS)

Ubuz, Behiye; Aydınyer, Yurdagül

2017-11-01

The current study aimed to construct a questionnaire that measures students' personality traits related to striving for understanding and learning value of geometry and then examine its psychometric properties. Through the use of multiple methods on two independent samples of 402 and 521 middle school students, two studies were performed to address this issue to provide support for its validity. In Study 1, exploratory factor analysis indicated the two-factor model. In Study 2, confirmatory factor analysis indicated the better fit of two-factor model compared to one or three-factor model. Convergent and discriminant validity evidence provided insight into the distinctiveness of the two factors. Subgroup validity evidence revealed gender differences for striving for understanding geometry trait favouring girls and grade level differences for learning value of geometry trait favouring the sixth- and seventh-grade students. Predictive validity evidence demonstrated that the striving for understanding geometry trait but not learning value of geometry trait was significantly correlated with prior mathematics achievement. In both studies, each factor and the entire questionnaire showed satisfactory reliability. In conclusion, the questionnaire was psychometrically sound.

Novel Breast Imaging and Machine Learning: Predicting Breast Lesion Malignancy at Cone-Beam CT Using Machine Learning Techniques.

PubMed

Uhlig, Johannes; Uhlig, Annemarie; Kunze, Meike; Beissbarth, Tim; Fischer, Uwe; Lotz, Joachim; Wienbeck, Susanne

2018-05-24

The purpose of this study is to evaluate the diagnostic performance of machine learning techniques for malignancy prediction at breast cone-beam CT (CBCT) and to compare them to human readers. Five machine learning techniques, including random forests, back propagation neural networks (BPN), extreme learning machines, support vector machines, and K-nearest neighbors, were used to train diagnostic models on a clinical breast CBCT dataset with internal validation by repeated 10-fold cross-validation. Two independent blinded human readers with profound experience in breast imaging and breast CBCT analyzed the same CBCT dataset. Diagnostic performance was compared using AUC, sensitivity, and specificity. The clinical dataset comprised 35 patients (American College of Radiology density type C and D breasts) with 81 suspicious breast lesions examined with contrast-enhanced breast CBCT. Forty-five lesions were histopathologically proven to be malignant. Among the machine learning techniques, BPNs provided the best diagnostic performance, with AUC of 0.91, sensitivity of 0.85, and specificity of 0.82. The diagnostic performance of the human readers was AUC of 0.84, sensitivity of 0.89, and specificity of 0.72 for reader 1 and AUC of 0.72, sensitivity of 0.71, and specificity of 0.67 for reader 2. AUC was significantly higher for BPN when compared with both reader 1 (p = 0.01) and reader 2 (p < 0.001). Machine learning techniques provide a high and robust diagnostic performance in the prediction of malignancy in breast lesions identified at CBCT. BPNs showed the best diagnostic performance, surpassing human readers in terms of AUC and specificity.

Incidental Learning of Melodic Structure of North Indian Music.

PubMed

Rohrmeier, Martin; Widdess, Richard

2017-07-01

Musical knowledge is largely implicit. It is acquired without awareness of its complex rules, through interaction with a large number of samples during musical enculturation. Whereas several studies explored implicit learning of mostly abstract and less ecologically valid features of Western music, very little work has been done with respect to ecologically valid stimuli as well as non-Western music. The present study investigated implicit learning of modal melodic features in North Indian classical music in a realistic and ecologically valid way. It employed a cross-grammar design, using melodic materials from two modes (rāgas) that use the same scale. Findings indicated that Western participants unfamiliar with Indian music incidentally learned to identify distinctive features of each mode. Confidence ratings suggest that participants' performance was consistently correlated with confidence, indicating that they became aware of whether they were right in their responses; that is, they possessed explicit judgment knowledge. Altogether our findings show incidental learning in a realistic ecologically valid context during only a very short exposure, they provide evidence that incidental learning constitutes a powerful mechanism that plays a fundamental role in musical acquisition. Copyright © 2016 Cognitive Science Society, Inc.

Developing instruments concerning scientific epistemic beliefs and goal orientations in learning science: a validation study

NASA Astrophysics Data System (ADS)

Lin, Tzung-Jin; Tsai, Chin-Chung

2017-11-01

The purpose of this study was to develop and validate two survey instruments to evaluate high school students' scientific epistemic beliefs and goal orientations in learning science. The initial relationships between the sampled students' scientific epistemic beliefs and goal orientations in learning science were also investigated. A final valid sample of 600 volunteer Taiwanese high school students participated in this survey by responding to the Scientific Epistemic Beliefs Instrument (SEBI) and the Goal Orientations in Learning Science Instrument (GOLSI). Through both exploratory and confirmatory factor analyses, the SEBI and GOLSI were proven to be valid and reliable for assessing the participants' scientific epistemic beliefs and goal orientations in learning science. The path analysis results indicated that, by and large, the students with more sophisticated epistemic beliefs in various dimensions such as Development of Knowledge, Justification for Knowing, and Purpose of Knowing tended to adopt both Mastery-approach and Mastery-avoidance goals. Some interesting results were also found. For example, the students tended to set a learning goal to outperform others or merely demonstrate competence (Performance-approach) if they had more informed epistemic beliefs in the dimensions of Multiplicity of Knowledge, Uncertainty of Knowledge, and Purpose of Knowing.

Teaching Quality, Learning Satisfaction, and Academic Performance among Hospitality Students in Taiwan

ERIC Educational Resources Information Center

Ko, Wen-Hwa; Chung, Feng-Ming

2014-01-01

The purpose of this study is to examine the effect of the teaching quality of culinary arts teachers and student learning satisfaction on the academic performance of hospitality students. This study surveys the students in hospitality departments at universities in Taiwan. A total of 406 (81.2%) valid questionnaires were received. Research results…

Assessing student engagement and self-regulated learning in a medical gross anatomy course.

PubMed

Pizzimenti, Marc A; Axelson, Rick D

2015-01-01

In courses with large enrollment, faculty members sometimes struggle with an understanding of how individual students are engaging in their courses. Information about the level of student engagement that instructors would likely find most useful can be linked to: (1) the learning strategies that students are using; (2) the barriers to learning that students are encountering; and (3) whether the course materials and activities are yielding the intended learning outcomes. This study drew upon self-regulated learning theory (SRL) to specify relevant information about learning engagement, and how the measures of particular scales might prove useful for student/faculty reflection. We tested the quality of such information as collected via the Motivated Strategies for Learning Questionnaire (MSLQ). MSLQ items were administered through a web-based survey to 150 students in a first-year medical gross anatomy course. The resulting 66 responses (44% response rate) were examined for information quality (internal reliability and predictive validity) and usefulness of the results to the course instructor. Students' final grades in the course were correlated with their MSLQ scale scores to assess the predictive validity of the measures. These results were consistent with the course design and expectations, showing that greater use of learning strategies such as elaboration and critical thinking was associated with higher levels of performance in the course. Motivation subscales for learning were also correlated with the higher levels of performance in the course. The extent to which these scales capture valid and reliable information in other institutional settings and courses needs further investigation. © 2014 American Association of Anatomists.

Validating the Learning Cycle Models of Business Simulation Games via Student Perceived Gains in Skills and Knowledge

ERIC Educational Resources Information Center

Tao, Yu-Hui; Yeh, C. Rosa; Hung, Kung Chin

2015-01-01

Several theoretical models have been constructed to determine the effects of buisness simulation games (BSGs) on learning performance. Although these models agree on the concept of learning-cycle effect, no empirical evidence supports the claim that the use of learning cycle activities with BSGs produces an effect on incremental gains in knowledge…

Predicting ionizing radiation exposure using biochemically-inspired genomic machine learning.

PubMed

Zhao, Jonathan Z L; Mucaki, Eliseos J; Rogan, Peter K

2018-01-01

Background: Gene signatures derived from transcriptomic data using machine learning methods have shown promise for biodosimetry testing. These signatures may not be sufficiently robust for large scale testing, as their performance has not been adequately validated on external, independent datasets. The present study develops human and murine signatures with biochemically-inspired machine learning that are strictly validated using k-fold and traditional approaches. Methods: Gene Expression Omnibus (GEO) datasets of exposed human and murine lymphocytes were preprocessed via nearest neighbor imputation and expression of genes implicated in the literature to be responsive to radiation exposure (n=998) were then ranked by Minimum Redundancy Maximum Relevance (mRMR). Optimal signatures were derived by backward, complete, and forward sequential feature selection using Support Vector Machines (SVM), and validated using k-fold or traditional validation on independent datasets. Results: The best human signatures we derived exhibit k-fold validation accuracies of up to 98% ( DDB2 ,  PRKDC , TPP2 , PTPRE , and GADD45A ) when validated over 209 samples and traditional validation accuracies of up to 92% ( DDB2 ,  CD8A ,  TALDO1 ,  PCNA ,  EIF4G2 ,  LCN2 ,  CDKN1A ,  PRKCH ,  ENO1 ,  and PPM1D ) when validated over 85 samples. Some human signatures are specific enough to differentiate between chemotherapy and radiotherapy. Certain multi-class murine signatures have sufficient granularity in dose estimation to inform eligibility for cytokine therapy (assuming these signatures could be translated to humans). We compiled a list of the most frequently appearing genes in the top 20 human and mouse signatures. More frequently appearing genes among an ensemble of signatures may indicate greater impact of these genes on the performance of individual signatures. Several genes in the signatures we derived are present in previously proposed signatures. Conclusions: Gene signatures for ionizing radiation exposure derived by machine learning have low error rates in externally validated, independent datasets, and exhibit high specificity and granularity for dose estimation.

Measuring Assurance of Learning at the Degree Program and Academic Major Levels

ERIC Educational Resources Information Center

Marshall, Leisa Lynn

2007-01-01

In this article, the author examines the validity of performing assurance of learning (AOL) activities at the degree program level (e.g., bachelor's level) and the major level (e.g., accounting, finance). She examines 3 learning goals: management-specific knowledge, problem solving, and communication. The results strongly suggest that the AOL…

Assessment in Immersive Virtual Environments: Cases for Learning, of Learning, and as Learning

ERIC Educational Resources Information Center

Code, Jillianne; Zap, Nick

2017-01-01

The key to education reform lies in exploring alternative forms of assessment. Alternative performance assessments provide a more valid measure than multiple-choice tests of students' conceptual understanding and higher-level skills such as problem solving and inquiry. Advances in game-based and virtual environment technologies are creating new…

Supporting Interaction among Participants of Online Learning Using the Knowledge Sharing Concept

ERIC Educational Resources Information Center

Chao, Chih-Yang; Hwu, Shiow-Lin; Chang, Chi-Cheng

2011-01-01

In education business, proper interaction is a crucial factor for learning effectiveness. However, it is difficult to successfully guide the participants to achieve the appropriate interaction in an online learning environment. That is, the interaction as well as internal dialogue should be systemically performed under a valid control. In this…

Exploring geo-tagged photos for land cover validation with deep learning

NASA Astrophysics Data System (ADS)

Xing, Hanfa; Meng, Yuan; Wang, Zixuan; Fan, Kaixuan; Hou, Dongyang

2018-07-01

Land cover validation plays an important role in the process of generating and distributing land cover thematic maps, which is usually implemented by high cost of sample interpretation with remotely sensed images or field survey. With an increasing availability of geo-tagged landscape photos, the automatic photo recognition methodologies, e.g., deep learning, can be effectively utilised for land cover applications. However, they have hardly been utilised in validation processes, as challenges remain in sample selection and classification for highly heterogeneous photos. This study proposed an approach to employ geo-tagged photos for land cover validation by using the deep learning technology. The approach first identified photos automatically based on the VGG-16 network. Then, samples for validation were selected and further classified by considering photos distribution and classification probabilities. The implementations were conducted for the validation of the GlobeLand30 land cover product in a heterogeneous area, western California. Experimental results represented promises in land cover validation, given that GlobeLand30 showed an overall accuracy of 83.80% with classified samples, which was close to the validation result of 80.45% based on visual interpretation. Additionally, the performances of deep learning based on ResNet-50 and AlexNet were also quantified, revealing no substantial differences in final validation results. The proposed approach ensures geo-tagged photo quality, and supports the sample classification strategy by considering photo distribution, with accuracy improvement from 72.07% to 79.33% compared with solely considering the single nearest photo. Consequently, the presented approach proves the feasibility of deep learning technology on land cover information identification of geo-tagged photos, and has a great potential to support and improve the efficiency of land cover validation.

Deep Learning to Classify Radiology Free-Text Reports.

PubMed

Chen, Matthew C; Ball, Robyn L; Yang, Lingyao; Moradzadeh, Nathaniel; Chapman, Brian E; Larson, David B; Langlotz, Curtis P; Amrhein, Timothy J; Lungren, Matthew P

2018-03-01

Purpose To evaluate the performance of a deep learning convolutional neural network (CNN) model compared with a traditional natural language processing (NLP) model in extracting pulmonary embolism (PE) findings from thoracic computed tomography (CT) reports from two institutions. Materials and Methods Contrast material-enhanced CT examinations of the chest performed between January 1, 1998, and January 1, 2016, were selected. Annotations by two human radiologists were made for three categories: the presence, chronicity, and location of PE. Classification of performance of a CNN model with an unsupervised learning algorithm for obtaining vector representations of words was compared with the open-source application PeFinder. Sensitivity, specificity, accuracy, and F1 scores for both the CNN model and PeFinder in the internal and external validation sets were determined. Results The CNN model demonstrated an accuracy of 99% and an area under the curve value of 0.97. For internal validation report data, the CNN model had a statistically significant larger F1 score (0.938) than did PeFinder (0.867) when classifying findings as either PE positive or PE negative, but no significant difference in sensitivity, specificity, or accuracy was found. For external validation report data, no statistical difference between the performance of the CNN model and PeFinder was found. Conclusion A deep learning CNN model can classify radiology free-text reports with accuracy equivalent to or beyond that of an existing traditional NLP model. © RSNA, 2017 Online supplemental material is available for this article.

Validation of an instrument to measure students' motivation and self-regulation towards technology learning

NASA Astrophysics Data System (ADS)

Liou, Pey-Yan; Kuo, Pei-Jung

2014-05-01

Background:Few studies have examined students' attitudinal perceptions of technology. There is no appropriate instrument to measure senior high school students' motivation and self-regulation toward technology learning among the current existing instruments in the field of technology education. Purpose:The present study is to validate an instrument for assessing senior high school students' motivation and self-regulation towards technology learning. Sample:A total of 1822 Taiwanese senior high school students (1020 males and 802 females) responded to the newly developed instrument. Design and method:The Motivation and Self-regulation towards Technology Learning (MSRTL) instrument was developed based on the previous instruments measuring students' motivation and self-regulation towards science learning. Exploratory and confirmatory factor analyses were utilized to investigate the structure of the items. Cronbach's alpha was applied for measuring the internal consistency of each scale. Furthermore, multivariate analysis of variance was used to examine gender differences. Results:Seven scales, including 'Technology learning self-efficacy,' 'Technology learning value,' 'Technology active learning strategies,' 'Technology learning environment stimulation,' 'Technology learning goal-orientation,' 'Technology learning self-regulation-triggering,' and 'Technology learning self-regulation-implementing' were confirmed for the MSRTL instrument. Moreover, the results also showed that male and female students did not present the same degree of preference in all of the scales. Conclusions:The MSRTL instrument composed of seven scales corresponding to 39 items was shown to be valid based on validity and reliability analyses. While male students tended to express more positive and active performance in the motivation scales, no gender differences were found in the self-regulation scales.

A Machine Learning Framework for Plan Payment Risk Adjustment.

PubMed

Rose, Sherri

2016-12-01

To introduce cross-validation and a nonparametric machine learning framework for plan payment risk adjustment and then assess whether they have the potential to improve risk adjustment. 2011-2012 Truven MarketScan database. We compare the performance of multiple statistical approaches within a broad machine learning framework for estimation of risk adjustment formulas. Total annual expenditure was predicted using age, sex, geography, inpatient diagnoses, and hierarchical condition category variables. The methods included regression, penalized regression, decision trees, neural networks, and an ensemble super learner, all in concert with screening algorithms that reduce the set of variables considered. The performance of these methods was compared based on cross-validated R 2 . Our results indicate that a simplified risk adjustment formula selected via this nonparametric framework maintains much of the efficiency of a traditional larger formula. The ensemble approach also outperformed classical regression and all other algorithms studied. The implementation of cross-validated machine learning techniques provides novel insight into risk adjustment estimation, possibly allowing for a simplified formula, thereby reducing incentives for increased coding intensity as well as the ability of insurers to "game" the system with aggressive diagnostic upcoding. © Health Research and Educational Trust.

Embedded performance validity testing in neuropsychological assessment: Potential clinical tools.

PubMed

Rickards, Tyler A; Cranston, Christopher C; Touradji, Pegah; Bechtold, Kathleen T

2018-01-01

The article aims to suggest clinically-useful tools in neuropsychological assessment for efficient use of embedded measures of performance validity. To accomplish this, we integrated available validity-related and statistical research from the literature, consensus statements, and survey-based data from practicing neuropsychologists. We provide recommendations for use of 1) Cutoffs for embedded performance validity tests including Reliable Digit Span, California Verbal Learning Test (Second Edition) Forced Choice Recognition, Rey-Osterrieth Complex Figure Test Combination Score, Wisconsin Card Sorting Test Failure to Maintain Set, and the Finger Tapping Test; 2) Selecting number of performance validity measures to administer in an assessment; and 3) Hypothetical clinical decision-making models for use of performance validity testing in a neuropsychological assessment collectively considering behavior, patient reporting, and data indicating invalid or noncredible performance. Performance validity testing helps inform the clinician about an individual's general approach to tasks: response to failure, task engagement and persistence, compliance with task demands. Data-driven clinical suggestions provide a resource to clinicians and to instigate conversation within the field to make more uniform, testable decisions to further the discussion, and guide future research in this area.

Learning to Write: Progress-Monitoring Tools for Beginning and at-Risk Writers

ERIC Educational Resources Information Center

Ritchey, Kristen D.

2006-01-01

Teachers now have a wide range of tools to help assess the beginning reading performance of kindergarten and first-grade children. However, validated procedures for assessing the beginning writing skills of kindergarten and first-grade children are less widely available. Learning to write, like learning to read, is a complex task. The ability to…

Validation of the GreenLight™ Simulator and development of a training curriculum for photoselective vaporisation of the prostate.

PubMed

Aydin, Abdullatif; Muir, Gordon H; Graziano, Manuela E; Khan, Muhammad Shamim; Dasgupta, Prokar; Ahmed, Kamran

2015-06-01

To assess face, content and construct validity, and feasibility and acceptability of the GreenLight™ Simulator as a training tool for photoselective vaporisation of the prostate (PVP), and to establish learning curves and develop an evidence-based training curriculum. This prospective, observational and comparative study, recruited novice (25 participants), intermediate (14) and expert-level urologists (seven) from the UK and Europe at the 28th European Association of Urological Surgeons Annual Meeting 2013. A group of novices (12 participants) performed 10 sessions of subtask training modules followed by a long operative case, whereas a second group (13) performed five sessions of a given case module. Intermediate and expert groups performed all training modules once, followed by one operative case. The outcome measures for learning curves and construct validity were time to task, coagulation time, vaporisation time, average sweep speed, average laser distance, blood loss, operative errors, and instrument cost. Face and content validity, feasibility and acceptability were addressed through a quantitative survey. Construct validity was demonstrated in two of five training modules (P = 0.038; P = 0.018) and in a considerable number of case metrics (P = 0.034). Learning curves were seen in all five training modules (P < 0.001) and significant reduction in case operative time (P < 0.001) and error (P = 0.017) were seen. An evidence-based training curriculum, to help trainees acquire transferable skills, was produced using the results. This study has shown the GreenLight Simulator to be a valid and useful training tool for PVP. It is hoped that by using the training curriculum for the GreenLight Simulator, novice trainees can acquire skills and knowledge to a predetermined level of proficiency. © 2014 The Authors. BJU International © 2014 BJU International.

Assessing Procedural Competence: Validity Considerations.

PubMed

Pugh, Debra M; Wood, Timothy J; Boulet, John R

2015-10-01

Simulation-based medical education (SBME) offers opportunities for trainees to learn how to perform procedures and to be assessed in a safe environment. However, SBME research studies often lack robust evidence to support the validity of the interpretation of the results obtained from tools used to assess trainees' skills. The purpose of this paper is to describe how a validity framework can be applied when reporting and interpreting the results of a simulation-based assessment of skills related to performing procedures. The authors discuss various sources of validity evidence because they relate to SBME. A case study is presented.

Stressors, academic performance, and learned resourcefulness in baccalaureate nursing students.

PubMed

Goff, Anne-Marie

2011-01-01

High stress levels in nursing students may affect memory, concentration, and problem-solving ability, and may lead to decreased learning, coping, academic performance, and retention. College students with higher levels of learned resourcefulness develop greater self-confidence, motivation, and academic persistence, and are less likely to become anxious, depressed, and frustrated, but no studies specifically involve nursing students. This explanatory correlational study used Gadzella's Student-life Stress Inventory (SSI) and Rosenbaum's Self Control Scale (SCS) to explore learned resourcefulness, stressors, and academic performance in 53 baccalaureate nursing students. High levels of personal and academic stressors were evident, but not significant predictors of academic performance (p = .90). Age was a significant predictor of academic performance (p = < .01) and males and African-American/Black participants had higher learned resourcefulness scores than females and Caucasians. Studies in larger, more diverse samples are necessary to validate these findings.

The development of guided inquiry-based learning devices on photosynthesis and respiration matter to train science literacy skills

NASA Astrophysics Data System (ADS)

Choirunnisak; Ibrahim, M.; Yuliani

2018-01-01

The purpose of this research was to develop a guided inquiry-based learning devices on photosynthesis and respiration matter that are feasible (valid, practical, and effective) to train students’ science literacy. This research used 4D development model and tested on 15 students of biology education 2016 the State University of Surabaya with using one group pretest-posttest design. Learning devices developed include (a) Semester Lesson Plan (b) Lecture Schedule, (c) Student Activity Sheet, (d) Student Textbook, and (e) testability of science literacy. Research data obtained through validation method, observation, test, and questionnaire. The results were analyzed descriptively quantitative and qualitative. The ability of science literacy was analyzed by n-gain. The results of this research showed that (a) learning devices that developed was categorically very valid, (b) learning activities performed very well, (c) student’s science literacy skills improved that was a category as moderate, and (d) students responses were very positively to the learning that already held. Based on the results of the analysis and discussion, it is concluded that the development of guided inquiry-based learning devices on photosynthesis and respiration matter was feasible to train students literacy science skills.

Learning to recognize rat social behavior: Novel dataset and cross-dataset application.

PubMed

Lorbach, Malte; Kyriakou, Elisavet I; Poppe, Ronald; van Dam, Elsbeth A; Noldus, Lucas P J J; Veltkamp, Remco C

2018-04-15

Social behavior is an important aspect of rodent models. Automated measuring tools that make use of video analysis and machine learning are an increasingly attractive alternative to manual annotation. Because machine learning-based methods need to be trained, it is important that they are validated using data from different experiment settings. To develop and validate automated measuring tools, there is a need for annotated rodent interaction datasets. Currently, the availability of such datasets is limited to two mouse datasets. We introduce the first, publicly available rat social interaction dataset, RatSI. We demonstrate the practical value of the novel dataset by using it as the training set for a rat interaction recognition method. We show that behavior variations induced by the experiment setting can lead to reduced performance, which illustrates the importance of cross-dataset validation. Consequently, we add a simple adaptation step to our method and improve the recognition performance. Most existing methods are trained and evaluated in one experimental setting, which limits the predictive power of the evaluation to that particular setting. We demonstrate that cross-dataset experiments provide more insight in the performance of classifiers. With our novel, public dataset we encourage the development and validation of automated recognition methods. We are convinced that cross-dataset validation enhances our understanding of rodent interactions and facilitates the development of more sophisticated recognition methods. Combining them with adaptation techniques may enable us to apply automated recognition methods to a variety of animals and experiment settings. Copyright © 2017 Elsevier B.V. All rights reserved.

Validating the ACE Model for Evaluating Student Performance Using a Teaching-Learning Process Based on Computational Modeling Systems

ERIC Educational Resources Information Center

Louzada, Alexandre Neves; Elia, Marcos da Fonseca; Sampaio, Fábio Ferrentini; Vidal, Andre Luiz Pestana

2014-01-01

The aim of this work is to adapt and test, in a Brazilian public school, the ACE model proposed by Borkulo for evaluating student performance as a teaching-learning process based on computational modeling systems. The ACE model is based on different types of reasoning involving three dimensions. In addition to adapting the model and introducing…

Validity of Cognitive Load Measures in Simulation-Based Training: A Systematic Review.

PubMed

Naismith, Laura M; Cavalcanti, Rodrigo B

2015-11-01

Cognitive load theory (CLT) provides a rich framework to inform instructional design. Despite the applicability of CLT to simulation-based medical training, findings from multimedia learning have not been consistently replicated in this context. This lack of transferability may be related to issues in measuring cognitive load (CL) during simulation. The authors conducted a review of CLT studies across simulation training contexts to assess the validity evidence for different CL measures. PRISMA standards were followed. For 48 studies selected from a search of MEDLINE, EMBASE, PsycInfo, CINAHL, and ERIC databases, information was extracted about study aims, methods, validity evidence of measures, and findings. Studies were categorized on the basis of findings and prevalence of validity evidence collected, and statistical comparisons between measurement types and research domains were pursued. CL during simulation training has been measured in diverse populations including medical trainees, pilots, and university students. Most studies (71%; 34) used self-report measures; others included secondary task performance, physiological indices, and observer ratings. Correlations between CL and learning varied from positive to negative. Overall validity evidence for CL measures was low (mean score 1.55/5). Studies reporting greater validity evidence were more likely to report that high CL impaired learning. The authors found evidence that inconsistent correlations between CL and learning may be related to issues of validity in CL measures. Further research would benefit from rigorous documentation of validity and from triangulating measures of CL. This can better inform CLT instructional design for simulation-based medical training.

Simulation-driven machine learning: Bearing fault classification

NASA Astrophysics Data System (ADS)

Sobie, Cameron; Freitas, Carina; Nicolai, Mike

2018-01-01

Increasing the accuracy of mechanical fault detection has the potential to improve system safety and economic performance by minimizing scheduled maintenance and the probability of unexpected system failure. Advances in computational performance have enabled the application of machine learning algorithms across numerous applications including condition monitoring and failure detection. Past applications of machine learning to physical failure have relied explicitly on historical data, which limits the feasibility of this approach to in-service components with extended service histories. Furthermore, recorded failure data is often only valid for the specific circumstances and components for which it was collected. This work directly addresses these challenges for roller bearings with race faults by generating training data using information gained from high resolution simulations of roller bearing dynamics, which is used to train machine learning algorithms that are then validated against four experimental datasets. Several different machine learning methodologies are compared starting from well-established statistical feature-based methods to convolutional neural networks, and a novel application of dynamic time warping (DTW) to bearing fault classification is proposed as a robust, parameter free method for race fault detection.

Development of a proficiency-based virtual reality simulation training curriculum for laparoscopic appendicectomy.

PubMed

Sirimanna, Pramudith; Gladman, Marc A

2017-10-01

Proficiency-based virtual reality (VR) training curricula improve intraoperative performance, but have not been developed for laparoscopic appendicectomy (LA). This study aimed to develop an evidence-based training curriculum for LA. A total of 10 experienced (>50 LAs), eight intermediate (10-30 LAs) and 20 inexperienced (<10 LAs) operators performed guided and unguided LA tasks on a high-fidelity VR simulator using internationally relevant techniques. The ability to differentiate levels of experience (construct validity) was measured using simulator-derived metrics. Learning curves were analysed. Proficiency benchmarks were defined by the performance of the experienced group. Intermediate and experienced participants completed a questionnaire to evaluate the realism (face validity) and relevance (content validity). Of 18 surgeons, 16 (89%) considered the VR model to be visually realistic and 17 (95%) believed that it was representative of actual practice. All 'guided' modules demonstrated construct validity (P < 0.05), with learning curves that plateaued between sessions 6 and 9 (P < 0.01). When comparing inexperienced to intermediates to experienced, the 'unguided' LA module demonstrated construct validity for economy of motion (5.00 versus 7.17 versus 7.84, respectively; P < 0.01) and task time (864.5 s versus 477.2 s versus 352.1 s, respectively, P < 0.01). Construct validity was also confirmed for number of movements, path length and idle time. Validated modules were used for curriculum construction, with proficiency benchmarks used as performance goals. A VR LA model was realistic and representative of actual practice and was validated as a training and assessment tool. Consequently, the first evidence-based internationally applicable training curriculum for LA was constructed, which facilitates skill acquisition to proficiency. © 2017 Royal Australasian College of Surgeons.

Tandem internal models execute motor learning in the cerebellum.

PubMed

Honda, Takeru; Nagao, Soichi; Hashimoto, Yuji; Ishikawa, Kinya; Yokota, Takanori; Mizusawa, Hidehiro; Ito, Masao

2018-06-25

In performing skillful movement, humans use predictions from internal models formed by repetition learning. However, the computational organization of internal models in the brain remains unknown. Here, we demonstrate that a computational architecture employing a tandem configuration of forward and inverse internal models enables efficient motor learning in the cerebellum. The model predicted learning adaptations observed in hand-reaching experiments in humans wearing a prism lens and explained the kinetic components of these behavioral adaptations. The tandem system also predicted a form of subliminal motor learning that was experimentally validated after training intentional misses of hand targets. Patients with cerebellar degeneration disease showed behavioral impairments consistent with tandemly arranged internal models. These findings validate computational tandemization of internal models in motor control and its potential uses in more complex forms of learning and cognition. Copyright © 2018 the Author(s). Published by PNAS.

[Information technology in learning sign language].

PubMed

Hernández, Cesar; Pulido, Jose L; Arias, Jorge E

2015-01-01

To develop a technological tool that improves the initial learning of sign language in hearing impaired children. The development of this research was conducted in three phases: the lifting of requirements, design and development of the proposed device, and validation and evaluation device. Through the use of information technology and with the advice of special education professionals, we were able to develop an electronic device that facilitates the learning of sign language in deaf children. This is formed mainly by a graphic touch screen, a voice synthesizer, and a voice recognition system. Validation was performed with the deaf children in the Filadelfia School of the city of Bogotá. A learning methodology was established that improves learning times through a small, portable, lightweight, and educational technological prototype. Tests showed the effectiveness of this prototype, achieving a 32 % reduction in the initial learning time for sign language in deaf children.

Mortality risk score prediction in an elderly population using machine learning.

PubMed

Rose, Sherri

2013-03-01

Standard practice for prediction often relies on parametric regression methods. Interesting new methods from the machine learning literature have been introduced in epidemiologic studies, such as random forest and neural networks. However, a priori, an investigator will not know which algorithm to select and may wish to try several. Here I apply the super learner, an ensembling machine learning approach that combines multiple algorithms into a single algorithm and returns a prediction function with the best cross-validated mean squared error. Super learning is a generalization of stacking methods. I used super learning in the Study of Physical Performance and Age-Related Changes in Sonomans (SPPARCS) to predict death among 2,066 residents of Sonoma, California, aged 54 years or more during the period 1993-1999. The super learner for predicting death (risk score) improved upon all single algorithms in the collection of algorithms, although its performance was similar to that of several algorithms. Super learner outperformed the worst algorithm (neural networks) by 44% with respect to estimated cross-validated mean squared error and had an R2 value of 0.201. The improvement of super learner over random forest with respect to R2 was approximately 2-fold. Alternatives for risk score prediction include the super learner, which can provide improved performance.

A Machine Learning and Cross-Validation Approach for the Discrimination of Vegetation Physiognomic Types Using Satellite Based Multispectral and Multitemporal Data.

PubMed

Sharma, Ram C; Hara, Keitarou; Hirayama, Hidetake

2017-01-01

This paper presents the performance and evaluation of a number of machine learning classifiers for the discrimination between the vegetation physiognomic classes using the satellite based time-series of the surface reflectance data. Discrimination of six vegetation physiognomic classes, Evergreen Coniferous Forest, Evergreen Broadleaf Forest, Deciduous Coniferous Forest, Deciduous Broadleaf Forest, Shrubs, and Herbs, was dealt with in the research. Rich-feature data were prepared from time-series of the satellite data for the discrimination and cross-validation of the vegetation physiognomic types using machine learning approach. A set of machine learning experiments comprised of a number of supervised classifiers with different model parameters was conducted to assess how the discrimination of vegetation physiognomic classes varies with classifiers, input features, and ground truth data size. The performance of each experiment was evaluated by using the 10-fold cross-validation method. Experiment using the Random Forests classifier provided highest overall accuracy (0.81) and kappa coefficient (0.78). However, accuracy metrics did not vary much with experiments. Accuracy metrics were found to be very sensitive to input features and size of ground truth data. The results obtained in the research are expected to be useful for improving the vegetation physiognomic mapping in Japan.

Developing an instrument to measure effective factors on Clinical Learning.

PubMed

Dadgaran, Ideh; Shirazi, Mandana; Mohammadi, Aeen; Ravari, Ali

2016-07-01

Although nursing students spend a large part of their learning period in the clinical environment, clinical learning has not been perceived by its nature yet. To develop an instrument to measure effective factors on clinical learning in nursing students. This is a mixed methods study performed in 2 steps. First, the researchers defined "clinical learning" in nursing students through qualitative content analysis and designed items of the questionnaire based on semi-structured individual interviews with nursing students. Then, as the second step, psychometric properties of the questionnaire were evaluated using the face validity, content validity, construct validity, and internal consistency evaluated on 227 students from fourth or higher semesters. All the interviews were recorded and transcribed, and then, they were analyzed using Max Qualitative Data Analysis and all of qualitative data were analyzed using SPSS 14. To do the study, we constructed the preliminary questionnaire containing 102 expressions. After determination of face and content validities by qualitative and quantitative approaches, the expressions of the questionnaire were reduced to 45. To determine the construct validity, exploratory factor analysis was applied. The results indicated that the maximum variance percentage (40.55%) was defined by the first 3 factors while the rest of the total variance percentage (59.45%) was determined by the other 42 factors. Results of exploratory factor analysis of this questionnaire indicated the presence of 3 instructor-staff, students, and educational related factors. Finally, 41 expressions were kept in 3 factor groups. The α-Cronbach coefficient (0.93) confirmed the high internal consistency of the questionnaire. Results indicated that the prepared questionnaire was an efficient instrument in the study of the effective factors on clinical learning as viewed by nursing students since it involves 41 expressions and properties such as instrument design based on perception and experiences of the nursing students about effective factors on clinical learning, definition of facilitator and preventive factors of the clinical learning, simple scoring, suitable validity and reliability, and applicability in different occasions.

An evidence-based virtual reality training program for novice laparoscopic surgeons.

PubMed

Aggarwal, Rajesh; Grantcharov, Teodor P; Eriksen, Jens R; Blirup, Dorthe; Kristiansen, Viggo B; Funch-Jensen, Peter; Darzi, Ara

2006-08-01

To develop an evidence-based virtual reality laparoscopic training curriculum for novice laparoscopic surgeons to achieve a proficient level of skill prior to participating in live cases. Technical skills for laparoscopic surgery must be acquired within a competency-based curriculum that begins in the surgical skills laboratory. Implementation of this program necessitates the definition of the validity, learning curves and proficiency criteria on the training tool. The study recruited 40 surgeons, classified into experienced (performed >100 laparoscopic cholecystectomies) or novice groups (<10 laparoscopic cholecystectomies). Ten novices and 10 experienced surgeons were tested on basic tasks, and 11 novices and 9 experienced surgeons on a procedural module for dissection of Calot triangle. Performance of the 2 groups was assessed using time, error, and economy of movement parameters. All basic tasks demonstrated construct validity (Mann-Whitney U test, P < 0.05), and learning curves for novices plateaued at a median of 7 repetitions (Friedman's test, P < 0.05). Expert surgeons demonstrated a learning rate at a median of 2 repetitions (P < 0.05). Performance on the dissection module demonstrated significant differences between experts and novices (P < 0.002); learning curves for novice subjects plateaued at the fourth repetition (P < 0.05). Expert benchmark criteria were defined for validated parameters on each task. A competency-based training curriculum for novice laparoscopic surgeons has been defined. This can serve to ensure that junior trainees have acquired prerequisite levels of skill prior to entering the operating room, and put them directly into practice.

Measuring Emotions in Students' Learning and Performance: The Achievement Emotions Questionnaire (AEQ)

ERIC Educational Resources Information Center

Pekrun, Reinhard; Goetz, Thomas; Frenzel, Anne C.; Barchfeld, Petra; Perry, Raymond P.

2011-01-01

Aside from test anxiety scales, measurement instruments assessing students' achievement emotions are largely lacking. This article reports on the construction, reliability, internal validity, and external validity of the Achievement Emotions Questionnaire (AEQ) which is designed to assess various achievement emotions experienced by students in…

EL_PSSM-RT: DNA-binding residue prediction by integrating ensemble learning with PSSM Relation Transformation.

PubMed

Zhou, Jiyun; Lu, Qin; Xu, Ruifeng; He, Yulan; Wang, Hongpeng

2017-08-29

Prediction of DNA-binding residue is important for understanding the protein-DNA recognition mechanism. Many computational methods have been proposed for the prediction, but most of them do not consider the relationships of evolutionary information between residues. In this paper, we first propose a novel residue encoding method, referred to as the Position Specific Score Matrix (PSSM) Relation Transformation (PSSM-RT), to encode residues by utilizing the relationships of evolutionary information between residues. PDNA-62 and PDNA-224 are used to evaluate PSSM-RT and two existing PSSM encoding methods by five-fold cross-validation. Performance evaluations indicate that PSSM-RT is more effective than previous methods. This validates the point that the relationship of evolutionary information between residues is indeed useful in DNA-binding residue prediction. An ensemble learning classifier (EL_PSSM-RT) is also proposed by combining ensemble learning model and PSSM-RT to better handle the imbalance between binding and non-binding residues in datasets. EL_PSSM-RT is evaluated by five-fold cross-validation using PDNA-62 and PDNA-224 as well as two independent datasets TS-72 and TS-61. Performance comparisons with existing predictors on the four datasets demonstrate that EL_PSSM-RT is the best-performing method among all the predicting methods with improvement between 0.02-0.07 for MCC, 4.18-21.47% for ST and 0.013-0.131 for AUC. Furthermore, we analyze the importance of the pair-relationships extracted by PSSM-RT and the results validates the usefulness of PSSM-RT for encoding DNA-binding residues. We propose a novel prediction method for the prediction of DNA-binding residue with the inclusion of relationship of evolutionary information and ensemble learning. Performance evaluation shows that the relationship of evolutionary information between residues is indeed useful in DNA-binding residue prediction and ensemble learning can be used to address the data imbalance issue between binding and non-binding residues. A web service of EL_PSSM-RT ( http://hlt.hitsz.edu.cn:8080/PSSM-RT_SVM/ ) is provided for free access to the biological research community.

Application of Machine-Learning Models to Predict Tacrolimus Stable Dose in Renal Transplant Recipients

NASA Astrophysics Data System (ADS)

Tang, Jie; Liu, Rong; Zhang, Yue-Li; Liu, Mou-Ze; Hu, Yong-Fang; Shao, Ming-Jie; Zhu, Li-Jun; Xin, Hua-Wen; Feng, Gui-Wen; Shang, Wen-Jun; Meng, Xiang-Guang; Zhang, Li-Rong; Ming, Ying-Zi; Zhang, Wei

2017-02-01

Tacrolimus has a narrow therapeutic window and considerable variability in clinical use. Our goal was to compare the performance of multiple linear regression (MLR) and eight machine learning techniques in pharmacogenetic algorithm-based prediction of tacrolimus stable dose (TSD) in a large Chinese cohort. A total of 1,045 renal transplant patients were recruited, 80% of which were randomly selected as the “derivation cohort” to develop dose-prediction algorithm, while the remaining 20% constituted the “validation cohort” to test the final selected algorithm. MLR, artificial neural network (ANN), regression tree (RT), multivariate adaptive regression splines (MARS), boosted regression tree (BRT), support vector regression (SVR), random forest regression (RFR), lasso regression (LAR) and Bayesian additive regression trees (BART) were applied and their performances were compared in this work. Among all the machine learning models, RT performed best in both derivation [0.71 (0.67-0.76)] and validation cohorts [0.73 (0.63-0.82)]. In addition, the ideal rate of RT was 4% higher than that of MLR. To our knowledge, this is the first study to use machine learning models to predict TSD, which will further facilitate personalized medicine in tacrolimus administration in the future.

Evaluating Inquiry-Based Learning as a Means to Advance Individual Student Achievement

ERIC Educational Resources Information Center

Ziemer, Cherilyn G.

2013-01-01

Although inquiry-based learning has been debated throughout the greater educational community and demonstrated with some effect in modern classrooms, little quantitative analysis has been performed to empirically validate sustained benefits. This quantitative study focused on whether inquiry-based pedagogy actually brought about sustained and…

Goal orientation and self-efficacy in relation to memory in adulthood

PubMed Central

Hastings, Erin C.; West, Robin L.

2011-01-01

The achievement goal framework (Dweck, 1986) has been well-established in children and college-students, but has rarely been examined empirically with older adults. The current study, including younger and older adults, examined the effects of memory self-efficacy, learning goals (focusing on skill mastery over time) and performance goals (focusing on performance outcome evaluations) on memory performance. Questionnaires measured memory self-efficacy and general orientation toward learning and performance goals; free and cued recall was assessed in a subsequent telephone interview. As expected, age was negatively related and education was positively related to memory self-efficacy, and memory self-efficacy was positively related to memory, in a structural equation model. Age was also negatively related to memory performance. Results supported the positive impact of learning goals and the negative impact of performance goals on memory self-efficacy. There was no significant direct effect of learning or performance goals on memory performance; their impact occurred via their effect on memory self-efficacy. The present study supports past research suggesting that learning goals are beneficial, and performance goals are maladaptive, for self-efficacy and learning, and validates the achievement goal framework in a sample including older adults. PMID:21728891

The Validity of ITBS Reading Comprehension Test Scores for Learning Disabled and Non Learning Disabled Students under Extended-Time Conditions.

ERIC Educational Resources Information Center

Huesman, Ronald L., Jr.; Frisbie, David A.

This study investigated the effect of extended-time limits in terms of performance levels and score comparability for reading comprehension scores on the Iowa Tests of Basic Skills (ITBS). The first part of the study compared the average reading comprehension scores on the ITBS of 61 sixth-graders with learning disabilities and 397 non learning…

Measuring student learning using initial and final concept test in an STEM course

NASA Astrophysics Data System (ADS)

Kaw, Autar; Yalcin, Ali

2012-06-01

Effective assessment is a cornerstone in measuring student learning in higher education. For a course in Numerical Methods, a concept test was used as an assessment tool to measure student learning and its improvement during the course. The concept test comprised 16 multiple choice questions and was given in the beginning and end of the class for three semesters. Hake's gain index, a measure of learning gains from pre- to post-tests, of 0.36 to 0.41 were recorded. The validity and reliability of the concept test was checked via standard measures such as Cronbach's alpha, content and criterion-related validity, item characteristic curves and difficulty and discrimination indices. The performance of various subgroups such as pre-requisite grades, transfer students, gender and age were also studied.

The Relationship Between Artificial and Second Language Learning.

PubMed

Ettlinger, Marc; Morgan-Short, Kara; Faretta-Stutenberg, Mandy; Wong, Patrick C M

2016-05-01

Artificial language learning (ALL) experiments have become an important tool in exploring principles of language and language learning. A persistent question in all of this work, however, is whether ALL engages the linguistic system and whether ALL studies are ecologically valid assessments of natural language ability. In the present study, we considered these questions by examining the relationship between performance in an ALL task and second language learning ability. Participants enrolled in a Spanish language class were evaluated using a number of different measures of Spanish ability and classroom performance, which was compared to IQ and a number of different measures of ALL performance. The results show that success in ALL experiments, particularly more complex artificial languages, correlates positively with indices of L2 learning even after controlling for IQ. These findings provide a key link between studies involving ALL and our understanding of second language learning in the classroom. Copyright © 2015 Cognitive Science Society, Inc.

Diabetic retinopathy risk prediction for fundus examination using sparse learning: a cross-sectional study.

PubMed

Oh, Ein; Yoo, Tae Keun; Park, Eun-Cheol

2013-09-13

Blindness due to diabetic retinopathy (DR) is the major disability in diabetic patients. Although early management has shown to prevent vision loss, diabetic patients have a low rate of routine ophthalmologic examination. Hence, we developed and validated sparse learning models with the aim of identifying the risk of DR in diabetic patients. Health records from the Korea National Health and Nutrition Examination Surveys (KNHANES) V-1 were used. The prediction models for DR were constructed using data from 327 diabetic patients, and were validated internally on 163 patients in the KNHANES V-1. External validation was performed using 562 diabetic patients in the KNHANES V-2. The learning models, including ridge, elastic net, and LASSO, were compared to the traditional indicators of DR. Considering the Bayesian information criterion, LASSO predicted DR most efficiently. In the internal and external validation, LASSO was significantly superior to the traditional indicators by calculating the area under the curve (AUC) of the receiver operating characteristic. LASSO showed an AUC of 0.81 and an accuracy of 73.6% in the internal validation, and an AUC of 0.82 and an accuracy of 75.2% in the external validation. The sparse learning model using LASSO was effective in analyzing the epidemiological underlying patterns of DR. This is the first study to develop a machine learning model to predict DR risk using health records. LASSO can be an excellent choice when both discriminative power and variable selection are important in the analysis of high-dimensional electronic health records.

Measuring preschool learning engagement in the laboratory.

PubMed

Halliday, Simone E; Calkins, Susan D; Leerkes, Esther M

2018-03-01

Learning engagement is a critical factor for academic achievement and successful school transitioning. However, current methods of assessing learning engagement in young children are limited to teacher report or classroom observation, which may limit the types of research questions one could assess about this construct. The current study investigated the validity of a novel assessment designed to measure behavioral learning engagement among young children in a standardized laboratory setting and examined how learning engagement in the laboratory relates to future classroom adjustment. Preschool-aged children (N = 278) participated in a learning-based Tangrams task and Story sequencing task and were observed based on seven behavioral indicators of engagement. Confirmatory factor analysis supported the construct validity for a behavioral engagement factor composed of six of the original behavioral indicators: attention to instructions, on-task behavior, enthusiasm/energy, persistence, monitoring progress/strategy use, and negative affect. Concurrent validity for this behavioral engagement factor was established through its associations with parent-reported mastery motivation and pre-academic skills in math and literacy measured in the laboratory, and predictive validity was demonstrated through its associations with teacher-reported classroom learning behaviors and performance in math and reading in kindergarten. These associations were found when behavioral engagement was observed during both the nonverbal task and the verbal story sequencing tasks and persisted even after controlling for child minority status, gender, and maternal education. Learning engagement in preschool appears to be successfully measurable in a laboratory setting. This finding has implications for future research on the mechanisms that support successful academic development. Copyright © 2017 Elsevier Inc. All rights reserved.

Operational Test and Evaluation Handbook for Aircrew Training Devices. Volume II. Operational Effectiveness Evaluation

DTIC Science & Technology

1982-02-01

should also convey an understanding of the differ- ences in learning behavior between initial learning activity and later skill maintenance and...refinement might then be, ATTACK MANEUVERS * Pop-up attack # Loft/ LADO type attack * Level/laydown attack Figure 5-4 showe diagrammatically the...sensitive to differ- ences in performance. Severai criteria should be used to guide the selection/development of performance measures, i.e., measure validity

Validation of the tool assessment of clinical education (AssCE): A study using Delphi method and clinical experts.

PubMed

Löfmark, Anna; Mårtensson, Gunilla

2017-03-01

The aim of the present study was to establish the validity of the tool Assessment of Clinical Education (AssCE). The tool is widely used in Sweden and some Nordic countries for assessing nursing students' performance in clinical education. It is important that the tools in use be subjected to regular audit and critical reviews. The validation process, performed in two stages, was concluded with a high level of congruence. In the first stage, Delphi technique was used to elaborate the AssCE tool using a group of 35 clinical nurse lecturers. After three rounds, we reached consensus. In the second stage, a group of 46 clinical nurse lecturers representing 12 universities in Sweden and Norway audited the revised version of the AssCE in relation to learning outcomes from the last clinical course at their respective institutions. Validation of the revised AssCE was established with high congruence between the factors in the AssCE and examined learning outcomes. The revised AssCE tool seems to meet its objective to be a validated assessment tool for use in clinical nursing education. Copyright © 2016 Elsevier Ltd. All rights reserved.

Place and direction learning in a spatial T-maze task by neonatal piglets

PubMed Central

Elmore, Monica R. P.; Dilger, Ryan N.; Johnson, Rodney W.

2013-01-01

Pigs are a valuable animal model for studying neurodevelopment in humans due to similarities in brain structure and growth. The development and validation of behavioral tests to assess learning and memory in neonatal piglets are needed. The present study evaluated the capability of 2-wk old piglets to acquire a novel place and direction learning spatial T-maze task. Validity of the task was assessed by the administration of scopolamine, an anti-cholinergic drug that acts on the hippocampus and other related structures, to impair spatial memory. During acquisition, piglets were trained to locate a milk reward in a constant place in space, as well as direction (east or west), in a plus-shaped maze using extra-maze visual cues. Following acquisition, reward location was reversed and piglets were re-tested to assess learning and working memory. The performance of control piglets in the maze improved over time (P < 0.0001), reaching performance criterion (80% correct) on day 5 of acquisition. Correct choices decreased in the reversal phase (P < 0.0001), but improved over time. In a separate study, piglets were injected daily with either phosphate buffered saline (PBS; control) or scopolamine prior to testing. Piglets administered scopolamine showed impaired performance in the maze compared to controls (P = 0.03), failing to reach performance criterion after 6 days of acquisition testing. Collectively, these data demonstrate that neonatal piglets can be tested in a spatial T-maze task to assess hippocampal-dependent learning and memory. PMID:22526690

Normative data and discriminant validity of Rey's Verbal Learning Test for the Greek adult population.

PubMed

Messinis, Lambros; Tsakona, Ioanna; Malefaki, Sonia; Papathanasopoulos, Panagiotis

2007-08-01

The present study sought to establish normative and discriminant validity data for Rey's Auditory Verbal Learning Test [Rey, A. (1964). L 'examen clinique en psychologie [Clinical tests in psychology]. Paris: Presses Universitaires de France; Schmidt, M. (1996). Rey auditory verbal learning test: A handbook. Los Angeles, CA: Western Psychological Services] using newly adapted learning lists for the Greek adult population. Applying the procedure suggested by Geffen et al. [Geffen, G., Moar, K. J., O'Hanlon, A. P., Clark, C. R., & Geffen, L. N. (1990). Performance measures of 16-86-year-old males and females on the auditory verbal learning test. The Clinical Neuropsychologist, 4, 45-63] we administered the test to 205 healthy participants, aged 18-78 years and two adult patient groups (long-term cannabis users and HIV symptomatic patients). Stepwise linear regression analyses showed that the variables age, education and gender contributed significantly to most trials of the RAVLT. Performance decreased in an age-dependent manner from young adulthood. Women, young adults and higher educated participants outperformed men, older adults and less educated individuals. The test appears to discriminate adequately between the performance of long-term heavy cannabis users and HIV seropositive symptomatic patients and matched healthy controls, as both patient groups performed more poorly than their respective control group. Normative data stratified by age, gender and education for the Greek adult population is presented for use in research and clinical settings.

Validity and Generalizability of Measuring Student Engaged Time in Physical Education.

ERIC Educational Resources Information Center

Silverman, Stephen; Zotos, Connee

The validity of interval and time sampling methods of measuring student engaged time was investigated in a study estimating the actual time students spent engaged in relevant motor performance in physical education classes. Two versions of the interval Academic Learning Time in Physical Education (ALT-PE) instrument and an equivalent time sampling…

Dynamic testing in schizophrenia: does training change the construct validity of a test?

PubMed

Wiedl, Karl H; Schöttke, Henning; Green, Michael F; Nuechterlein, Keith H

2004-01-01

Dynamic testing typically involves specific interventions for a test to assess the extent to which test performance can be modified, beyond level of baseline (static) performance. This study used a dynamic version of the Wisconsin Card Sorting Test (WCST) that is based on cognitive remediation techniques within a test-training-test procedure. From results of previous studies with schizophrenia patients, we concluded that the dynamic and static versions of the WCST should have different construct validity. This hypothesis was tested by examining the patterns of correlations with measures of executive functioning, secondary verbal memory, and verbal intelligence. Results demonstrated a specific construct validity of WCST dynamic (i.e., posttest) scores as an index of problem solving (Tower of Hanoi) and secondary verbal memory and learning (Auditory Verbal Learning Test), whereas the impact of general verbal capacity and selective attention (Verbal IQ, Stroop Test) was reduced. It is concluded that the construct validity of the test changes with dynamic administration and that this difference helps to explain why the dynamic version of the WCST predicts functional outcome better than the static version.

Comparison effectiveness of cooperative learning type STAD with cooperative learning type TPS in terms of mathematical method of Junior High School students

NASA Astrophysics Data System (ADS)

Wahyuni, A.

2018-05-01

This research is aimed to find out whether the model of cooperative learning type Student Team Achievement Division (STAD) is more effective than cooperative learning type Think-Pair-Share in SMP Negeri 7 Yogyakarta. This research was a quasi-experimental research, using two experimental groups. The population of research was all students of 7thclass in SMP Negeri 7 Yogyakarta that consists of 5 Classes. From the population were taken 2 classes randomly which used as sample. The instrument to collect data was a description test. Measurement of instrument validity use content validity and construct validity, while measuring instrument reliability use Cronbach Alpha formula. To investigate the effectiveness of cooperative learning type STAD and cooperative learning type TPS on the aspect of student’s mathematical method, the datas were analyzed by one sample test. Comparing the effectiveness of cooperative learning type STAD and TPS in terms of mathematical communication skills by using t-test. Normality test was not conducted because the sample of research more than 30 students, while homogeneity tested by using Kolmogorov Smirnov test. The analysis was performed at 5% confidence level.The results show as follows : 1) The model of cooperative learning type STAD and TPS are effective in terms of mathematical method of junior high school students. 2). STAD type cooperative learning model is more effective than TPS type cooperative learning model in terms of mathematical methods of junior high school students.

WISC-R Factor Structures for Diagnosed Learning Disabled Navajo and Papago Children.

ERIC Educational Resources Information Center

Zarske, John A.; And Others

1981-01-01

Wechsler Intelligence Scale for Children (Revised) (WISC-R) factor structures were compared for learning disabled Navajo and Papago children. Results support the validity of the WISC-R as a measure of general intellectual functioning, and verbal and performance aspects for both groups, indicating its appropriateness for diverse groups of children.…

Effect of the learning climate of residency programs on faculty's teaching performance as evaluated by residents.

PubMed

Lombarts, Kiki M J M H; Heineman, Maas Jan; Scherpbier, Albert J J A; Arah, Onyebuchi A

2014-01-01

To understand teaching performance of individual faculty, the climate in which residents' learning takes place, the learning climate, may be important. There is emerging evidence that specific climates do predict specific outcomes. Until now, the effect of learning climate on the performance of the individual faculty who actually do the teaching was unknown. THIS STUDY: (i) tested the hypothesis that a positive learning climate was associated with better teaching performance of individual faculty as evaluated by residents, and (ii) explored which dimensions of learning climate were associated with faculty's teaching performance. We conducted two cross-sectional questionnaire surveys amongst residents from 45 residency training programs and multiple specialties in 17 hospitals in the Netherlands. Residents evaluated the teaching performance of individual faculty using the robust System for Evaluating Teaching Qualities (SETQ) and evaluated the learning climate of residency programs using the Dutch Residency Educational Climate Test (D-RECT). The validated D-RECT questionnaire consisted of 11 subscales of learning climate. Main outcome measure was faculty's overall teaching (SETQ) score. We used multivariable adjusted linear mixed models to estimate the separate associations of overall learning climate and each of its subscales with faculty's teaching performance. In total 451 residents completed 3569 SETQ evaluations of 502 faculty. Residents also evaluated the learning climate of 45 residency programs in 17 hospitals in the Netherlands. Overall learning climate was positively associated with faculty's teaching performance (regression coefficient 0.54, 95% confidence interval: 0.37 to 0.71; P<0.001). Three out of 11 learning climate subscales were substantially associated with better teaching performance: 'coaching and assessment', 'work is adapted to residents' competence', and 'formal education'. Individual faculty's teaching performance evaluations are positively affected by better learning climate of residency programs.

Beyond the hype: deep neural networks outperform established methods using a ChEMBL bioactivity benchmark set.

PubMed

Lenselink, Eelke B; Ten Dijke, Niels; Bongers, Brandon; Papadatos, George; van Vlijmen, Herman W T; Kowalczyk, Wojtek; IJzerman, Adriaan P; van Westen, Gerard J P

2017-08-14

The increase of publicly available bioactivity data in recent years has fueled and catalyzed research in chemogenomics, data mining, and modeling approaches. As a direct result, over the past few years a multitude of different methods have been reported and evaluated, such as target fishing, nearest neighbor similarity-based methods, and Quantitative Structure Activity Relationship (QSAR)-based protocols. However, such studies are typically conducted on different datasets, using different validation strategies, and different metrics. In this study, different methods were compared using one single standardized dataset obtained from ChEMBL, which is made available to the public, using standardized metrics (BEDROC and Matthews Correlation Coefficient). Specifically, the performance of Naïve Bayes, Random Forests, Support Vector Machines, Logistic Regression, and Deep Neural Networks was assessed using QSAR and proteochemometric (PCM) methods. All methods were validated using both a random split validation and a temporal validation, with the latter being a more realistic benchmark of expected prospective execution. Deep Neural Networks are the top performing classifiers, highlighting the added value of Deep Neural Networks over other more conventional methods. Moreover, the best method ('DNN_PCM') performed significantly better at almost one standard deviation higher than the mean performance. Furthermore, Multi-task and PCM implementations were shown to improve performance over single task Deep Neural Networks. Conversely, target prediction performed almost two standard deviations under the mean performance. Random Forests, Support Vector Machines, and Logistic Regression performed around mean performance. Finally, using an ensemble of DNNs, alongside additional tuning, enhanced the relative performance by another 27% (compared with unoptimized 'DNN_PCM'). Here, a standardized set to test and evaluate different machine learning algorithms in the context of multi-task learning is offered by providing the data and the protocols. Graphical Abstract .

Osteoporosis risk prediction using machine learning and conventional methods.

PubMed

Kim, Sung Kean; Yoo, Tae Keun; Oh, Ein; Kim, Deok Won

2013-01-01

A number of clinical decision tools for osteoporosis risk assessment have been developed to select postmenopausal women for the measurement of bone mineral density. We developed and validated machine learning models with the aim of more accurately identifying the risk of osteoporosis in postmenopausal women, and compared with the ability of a conventional clinical decision tool, osteoporosis self-assessment tool (OST). We collected medical records from Korean postmenopausal women based on the Korea National Health and Nutrition Surveys (KNHANES V-1). The training data set was used to construct models based on popular machine learning algorithms such as support vector machines (SVM), random forests (RF), artificial neural networks (ANN), and logistic regression (LR) based on various predictors associated with low bone density. The learning models were compared with OST. SVM had significantly better area under the curve (AUC) of the receiver operating characteristic (ROC) than ANN, LR, and OST. Validation on the test set showed that SVM predicted osteoporosis risk with an AUC of 0.827, accuracy of 76.7%, sensitivity of 77.8%, and specificity of 76.0%. We were the first to perform comparisons of the performance of osteoporosis prediction between the machine learning and conventional methods using population-based epidemiological data. The machine learning methods may be effective tools for identifying postmenopausal women at high risk for osteoporosis.

Automatic detection of hemorrhagic pericardial effusion on PMCT using deep learning - a feasibility study.

PubMed

Ebert, Lars C; Heimer, Jakob; Schweitzer, Wolf; Sieberth, Till; Leipner, Anja; Thali, Michael; Ampanozi, Garyfalia

2017-12-01

Post mortem computed tomography (PMCT) can be used as a triage tool to better identify cases with a possibly non-natural cause of death, especially when high caseloads make it impossible to perform autopsies on all cases. Substantial data can be generated by modern medical scanners, especially in a forensic setting where the entire body is documented at high resolution. A solution for the resulting issues could be the use of deep learning techniques for automatic analysis of radiological images. In this article, we wanted to test the feasibility of such methods for forensic imaging by hypothesizing that deep learning methods can detect and segment a hemopericardium in PMCT. For deep learning image analysis software, we used the ViDi Suite 2.0. We retrospectively selected 28 cases with, and 24 cases without, hemopericardium. Based on these data, we trained two separate deep learning networks. The first one classified images into hemopericardium/not hemopericardium, and the second one segmented the blood content. We randomly selected 50% of the data for training and 50% for validation. This process was repeated 20 times. The best performing classification network classified all cases of hemopericardium from the validation images correctly with only a few false positives. The best performing segmentation network would tend to underestimate the amount of blood in the pericardium, which is the case for most networks. This is the first study that shows that deep learning has potential for automated image analysis of radiological images in forensic medicine.

Development Instrument’s Learning of Physics Through Scientific Inquiry Model Based Batak Culture to Improve Science Process Skill and Student’s Curiosity

NASA Astrophysics Data System (ADS)

Nasution, Derlina; Syahreni Harahap, Putri; Harahap, Marabangun

2018-03-01

This research aims to: (1) developed a instrument’s learning (lesson plan, worksheet, student’s book, teacher’s guide book, and instrument test) of physics learning through scientific inquiry learning model based Batak culture to achieve skills improvement process of science students and the students’ curiosity; (2) describe the quality of the result of develop instrument’s learning in high school using scientific inquiry learning model based Batak culture (lesson plan, worksheet, student’s book, teacher’s guide book, and instrument test) to achieve the science process skill improvement of students and the student curiosity. This research is research development. This research developed a instrument’s learning of physics by using a development model that is adapted from the development model Thiagarajan, Semmel, and Semmel. The stages are traversed until retrieved a valid physics instrument’s learning, practical, and effective includes :(1) definition phase, (2) the planning phase, and (3) stages of development. Test performed include expert test/validation testing experts, small groups, and test classes is limited. Test classes are limited to do in SMAN 1 Padang Bolak alternating on a class X MIA. This research resulted in: 1) the learning of physics static fluid material specially for high school grade 10th consisted of (lesson plan, worksheet, student’s book, teacher’s guide book, and instrument test) and quality worthy of use in the learning process; 2) each component of the instrument’s learning meet the criteria have valid learning, practical, and effective way to reach the science process skill improvement and curiosity in students.

A Cross-Correlated Delay Shift Supervised Learning Method for Spiking Neurons with Application to Interictal Spike Detection in Epilepsy.

PubMed

Guo, Lilin; Wang, Zhenzhong; Cabrerizo, Mercedes; Adjouadi, Malek

2017-05-01

This study introduces a novel learning algorithm for spiking neurons, called CCDS, which is able to learn and reproduce arbitrary spike patterns in a supervised fashion allowing the processing of spatiotemporal information encoded in the precise timing of spikes. Unlike the Remote Supervised Method (ReSuMe), synapse delays and axonal delays in CCDS are variants which are modulated together with weights during learning. The CCDS rule is both biologically plausible and computationally efficient. The properties of this learning rule are investigated extensively through experimental evaluations in terms of reliability, adaptive learning performance, generality to different neuron models, learning in the presence of noise, effects of its learning parameters and classification performance. Results presented show that the CCDS learning method achieves learning accuracy and learning speed comparable with ReSuMe, but improves classification accuracy when compared to both the Spike Pattern Association Neuron (SPAN) learning rule and the Tempotron learning rule. The merit of CCDS rule is further validated on a practical example involving the automated detection of interictal spikes in EEG records of patients with epilepsy. Results again show that with proper encoding, the CCDS rule achieves good recognition performance.

Computer-assisted teaching of skin flap surgery: validation of a mobile platform software for medical students.

PubMed

de Sena, David P; Fabricio, Daniela D; Lopes, Maria Helena I; da Silva, Vinicius D

2013-01-01

The purpose of this study was to develop and validate a multimedia software application for mobile platforms to assist in the teaching and learning process of design and construction of a skin flap. Traditional training in surgery is based on learning by doing. Initially, the use of cadavers and animal models appeared to be a valid alternative for training. However, many conflicts with these training models prompted progression to synthetic and virtual reality models. Fifty volunteer fifth- and sixth-year medical students completed a pretest and were randomly allocated into two groups of 25 students each. The control group was exposed for 5 minutes to a standard text-based print article, while the test group used multimedia software describing how to fashion a rhomboid flap. Each group then performed a cutaneous flap on a training bench model while being evaluated by three blinded BSPS (Brazilian Society of Plastic Surgery) board-certified surgeons using the OSATS (Objective Structured Assessment of Technical Skill) protocol and answered a post-test. The text-based group was then tested again using the software. The computer-assisted learning (CAL) group had superior performance as confirmed by checklist scores (p<0.002), overall global assessment (p = 0.017) and post-test results (p<0.001). All participants ranked the multimedia method as the best study tool. CAL learners exhibited better subjective and objective performance when fashioning rhomboid flaps as compared to those taught with standard print material. These findings indicate that students preferred to learn using the multimedia method.

Plaque Tissue Morphology-Based Stroke Risk Stratification Using Carotid Ultrasound: A Polling-Based PCA Learning Paradigm.

PubMed

Saba, Luca; Jain, Pankaj K; Suri, Harman S; Ikeda, Nobutaka; Araki, Tadashi; Singh, Bikesh K; Nicolaides, Andrew; Shafique, Shoaib; Gupta, Ajay; Laird, John R; Suri, Jasjit S

2017-06-01

Severe atherosclerosis disease in carotid arteries causes stenosis which in turn leads to stroke. Machine learning systems have been previously developed for plaque wall risk assessment using morphology-based characterization. The fundamental assumption in such systems is the extraction of the grayscale features of the plaque region. Even though these systems have the ability to perform risk stratification, they lack the ability to achieve higher performance due their inability to select and retain dominant features. This paper introduces a polling-based principal component analysis (PCA) strategy embedded in the machine learning framework to select and retain dominant features, resulting in superior performance. This leads to more stability and reliability. The automated system uses offline image data along with the ground truth labels to generate the parameters, which are then used to transform the online grayscale features to predict the risk of stroke. A set of sixteen grayscale plaque features is computed. Utilizing the cross-validation protocol (K = 10), and the PCA cutoff of 0.995, the machine learning system is able to achieve an accuracy of 98.55 and 98.83%corresponding to the carotidfar wall and near wall plaques, respectively. The corresponding reliability of the system was 94.56 and 95.63%, respectively. The automated system was validated against the manual risk assessment system and the precision of merit for same cross-validation settings and PCA cutoffs are 98.28 and 93.92%for the far and the near wall, respectively.PCA-embedded morphology-based plaque characterization shows a powerful strategy for risk assessment and can be adapted in clinical settings.

The Effect of Instructional Method on Cardiopulmonary Resuscitation Skill Performance: A Comparison Between Instructor-Led Basic Life Support and Computer-Based Basic Life Support With Voice-Activated Manikin.

PubMed

Wilson-Sands, Cathy; Brahn, Pamela; Graves, Kristal

2015-01-01

Validating participants' ability to correctly perform cardiopulmonary resuscitation (CPR) skills during basic life support courses can be a challenge for nursing professional development specialists. This study compares two methods of basic life support training, instructor-led and computer-based learning with voice-activated manikins, to identify if one method is more effective for performance of CPR skills. The findings suggest that a computer-based learning course with voice-activated manikins is a more effective method of training for improved CPR performance.

Framework for e-learning assessment in dental education: a global model for the future.

PubMed

Arevalo, Carolina R; Bayne, Stephen C; Beeley, Josie A; Brayshaw, Christine J; Cox, Margaret J; Donaldson, Nora H; Elson, Bruce S; Grayden, Sharon K; Hatzipanagos, Stylianos; Johnson, Lynn A; Reynolds, Patricia A; Schönwetter, Dieter J

2013-05-01

The framework presented in this article demonstrates strategies for a global approach to e-curricula in dental education by considering a collection of outcome assessment tools. By combining the outcomes for overall assessment, a global model for a pilot project that applies e-assessment tools to virtual learning environments (VLE), including haptics, is presented. Assessment strategies from two projects, HapTEL (Haptics in Technology Enhanced Learning) and UDENTE (Universal Dental E-learning), act as case-user studies that have helped develop the proposed global framework. They incorporate additional assessment tools and include evaluations from questionnaires and stakeholders' focus groups. These measure each of the factors affecting the classical teaching/learning theory framework as defined by Entwistle in a standardized manner. A mathematical combinatorial approach is proposed to join these results together as a global assessment. With the use of haptic-based simulation learning, exercises for tooth preparation assessing enamel and dentine were compared to plastic teeth in manikins. Equivalence for student performance for haptic versus traditional preparation methods was established, thus establishing the validity of the haptic solution for performing these exercises. Further data collected from HapTEL are still being analyzed, and pilots are being conducted to validate the proposed test measures. Initial results have been encouraging, but clearly the need persists to develop additional e-assessment methods for new learning domains.

Validation of electronic medical record-based phenotyping algorithms: results and lessons learned from the eMERGE network.

PubMed

Newton, Katherine M; Peissig, Peggy L; Kho, Abel Ngo; Bielinski, Suzette J; Berg, Richard L; Choudhary, Vidhu; Basford, Melissa; Chute, Christopher G; Kullo, Iftikhar J; Li, Rongling; Pacheco, Jennifer A; Rasmussen, Luke V; Spangler, Leslie; Denny, Joshua C

2013-06-01

Genetic studies require precise phenotype definitions, but electronic medical record (EMR) phenotype data are recorded inconsistently and in a variety of formats. To present lessons learned about validation of EMR-based phenotypes from the Electronic Medical Records and Genomics (eMERGE) studies. The eMERGE network created and validated 13 EMR-derived phenotype algorithms. Network sites are Group Health, Marshfield Clinic, Mayo Clinic, Northwestern University, and Vanderbilt University. By validating EMR-derived phenotypes we learned that: (1) multisite validation improves phenotype algorithm accuracy; (2) targets for validation should be carefully considered and defined; (3) specifying time frames for review of variables eases validation time and improves accuracy; (4) using repeated measures requires defining the relevant time period and specifying the most meaningful value to be studied; (5) patient movement in and out of the health plan (transience) can result in incomplete or fragmented data; (6) the review scope should be defined carefully; (7) particular care is required in combining EMR and research data; (8) medication data can be assessed using claims, medications dispensed, or medications prescribed; (9) algorithm development and validation work best as an iterative process; and (10) validation by content experts or structured chart review can provide accurate results. Despite the diverse structure of the five EMRs of the eMERGE sites, we developed, validated, and successfully deployed 13 electronic phenotype algorithms. Validation is a worthwhile process that not only measures phenotype performance but also strengthens phenotype algorithm definitions and enhances their inter-institutional sharing.

Comparison and validation of injury risk classifiers for advanced automated crash notification systems.

PubMed

Kusano, Kristofer; Gabler, Hampton C

2014-01-01

The odds of death for a seriously injured crash victim are drastically reduced if he or she received care at a trauma center. Advanced automated crash notification (AACN) algorithms are postcrash safety systems that use data measured by the vehicles during the crash to predict the likelihood of occupants being seriously injured. The accuracy of these models are crucial to the success of an AACN. The objective of this study was to compare the predictive performance of competing injury risk models and algorithms: logistic regression, random forest, AdaBoost, naïve Bayes, support vector machine, and classification k-nearest neighbors. This study compared machine learning algorithms to the widely adopted logistic regression modeling approach. Machine learning algorithms have not been commonly studied in the motor vehicle injury literature. Machine learning algorithms may have higher predictive power than logistic regression, despite the drawback of lacking the ability to perform statistical inference. To evaluate the performance of these algorithms, data on 16,398 vehicles involved in non-rollover collisions were extracted from the NASS-CDS. Vehicles with any occupants having an Injury Severity Score (ISS) of 15 or greater were defined as those requiring victims to be treated at a trauma center. The performance of each model was evaluated using cross-validation. Cross-validation assesses how a model will perform in the future given new data not used for model training. The crash ΔV (change in velocity during the crash), damage side (struck side of the vehicle), seat belt use, vehicle body type, number of events, occupant age, and occupant sex were used as predictors in each model. Logistic regression slightly outperformed the machine learning algorithms based on sensitivity and specificity of the models. Previous studies on AACN risk curves used the same data to train and test the power of the models and as a result had higher sensitivity compared to the cross-validated results from this study. Future studies should account for future data; for example, by using cross-validation or risk presenting optimistic predictions of field performance. Past algorithms have been criticized for relying on age and sex, being difficult to measure by vehicle sensors, and inaccuracies in classifying damage side. The models with accurate damage side and including age/sex did outperform models with less accurate damage side and without age/sex, but the differences were small, suggesting that the success of AACN is not reliant on these predictors.

Infrastructure and distributed learning methodology for privacy-preserving multi-centric rapid learning health care: euroCAT.

PubMed

Deist, Timo M; Jochems, A; van Soest, Johan; Nalbantov, Georgi; Oberije, Cary; Walsh, Seán; Eble, Michael; Bulens, Paul; Coucke, Philippe; Dries, Wim; Dekker, Andre; Lambin, Philippe

2017-06-01

Machine learning applications for personalized medicine are highly dependent on access to sufficient data. For personalized radiation oncology, datasets representing the variation in the entire cancer patient population need to be acquired and used to learn prediction models. Ethical and legal boundaries to ensure data privacy hamper collaboration between research institutes. We hypothesize that data sharing is possible without identifiable patient data leaving the radiation clinics and that building machine learning applications on distributed datasets is feasible. We developed and implemented an IT infrastructure in five radiation clinics across three countries (Belgium, Germany, and The Netherlands). We present here a proof-of-principle for future 'big data' infrastructures and distributed learning studies. Lung cancer patient data was collected in all five locations and stored in local databases. Exemplary support vector machine (SVM) models were learned using the Alternating Direction Method of Multipliers (ADMM) from the distributed databases to predict post-radiotherapy dyspnea grade [Formula: see text]. The discriminative performance was assessed by the area under the curve (AUC) in a five-fold cross-validation (learning on four sites and validating on the fifth). The performance of the distributed learning algorithm was compared to centralized learning where datasets of all institutes are jointly analyzed. The euroCAT infrastructure has been successfully implemented in five radiation clinics across three countries. SVM models can be learned on data distributed over all five clinics. Furthermore, the infrastructure provides a general framework to execute learning algorithms on distributed data. The ongoing expansion of the euroCAT network will facilitate machine learning in radiation oncology. The resulting access to larger datasets with sufficient variation will pave the way for generalizable prediction models and personalized medicine.

[Comparison of the Wechsler Memory Scale-III and the Spain-Complutense Verbal Learning Test in acquired brain injury: construct validity and ecological validity].

PubMed

Luna-Lario, P; Pena, J; Ojeda, N

2017-04-16

To perform an in-depth examination of the construct validity and the ecological validity of the Wechsler Memory Scale-III (WMS-III) and the Spain-Complutense Verbal Learning Test (TAVEC). The sample consists of 106 adults with acquired brain injury who were treated in the Area of Neuropsychology and Neuropsychiatry of the Complejo Hospitalario de Navarra and displayed memory deficit as the main sequela, measured by means of specific memory tests. The construct validity is determined by examining the tasks required in each test over the basic theoretical models, comparing the performance according to the parameters offered by the tests, contrasting the severity indices of each test and analysing their convergence. The external validity is explored through the correlation between the tests and by using regression models. According to the results obtained, both the WMS-III and the TAVEC have construct validity. The TAVEC is more sensitive and captures not only the deficits in mnemonic consolidation, but also in the executive functions involved in memory. The working memory index of the WMS-III is useful for predicting the return to work at two years after the acquired brain injury, but none of the instruments anticipates the disability and dependence at least six months after the injury. We reflect upon the construct validity of the tests and their insufficient capacity to predict functionality when the sequelae become chronic.

Conceptualization of Approaches and Thought Processes Emerging in Validating of Model in Mathematical Modeling in Technology Aided Environment

ERIC Educational Resources Information Center

Hidiroglu, Çaglar Naci; Bukova Güzel, Esra

2013-01-01

The aim of the present study is to conceptualize the approaches displayed for validation of model and thought processes provided in mathematical modeling process performed in technology-aided learning environment. The participants of this grounded theory study were nineteen secondary school mathematics student teachers. The data gathered from the…

Is Learner Self-Assessment Reliable and Valid in a Web-Based Portfolio Environment for High School Students?

ERIC Educational Resources Information Center

Chang, Chi-Cheng; Liang, Chaoyun; Chen, Yi-Hui

2013-01-01

This study explored the reliability and validity of Web-based portfolio self-assessment. Participants were 72 senior high school students enrolled in a computer application course. The students created learning portfolios, viewed peers' work, and performed self-assessment on the Web-based portfolio assessment system. The results indicated: 1)…

Validating the Heirarchy of the iStartSmart® Academic Content

ERIC Educational Resources Information Center

McManis, Perry, W.; McManis, Mark, H.

2016-01-01

The purpose of this analysis was to investigate the validity of skill groupings in an instructional technology learning system designed for use by children in early childhood education classrooms. A Principal Component Analysis was performed to measure the fit of 18 skill games to their 5 assigned groupings in the system, covering a range of…

The Professionalism Assessment of Clinical Teachers (PACT): The Reliability and Validity of a Novel Tool to Evaluate Professional and Clinical Teaching Behaviors

ERIC Educational Resources Information Center

Young, Meredith E.; Cruess, Sylvia R.; Cruess, Richard L.; Steinert, Yvonne

2014-01-01

Physicians function as clinicians, teachers, and role models within the clinical environment. Negative learning environments have been shown to be due to many factors, including the presence of unprofessional behaviors among clinical teachers. Reliable and valid assessments of clinical teacher performance, including professional behaviors, may…

Design of a multiple kernel learning algorithm for LS-SVM by convex programming.

PubMed

Jian, Ling; Xia, Zhonghang; Liang, Xijun; Gao, Chuanhou

2011-06-01

As a kernel based method, the performance of least squares support vector machine (LS-SVM) depends on the selection of the kernel as well as the regularization parameter (Duan, Keerthi, & Poo, 2003). Cross-validation is efficient in selecting a single kernel and the regularization parameter; however, it suffers from heavy computational cost and is not flexible to deal with multiple kernels. In this paper, we address the issue of multiple kernel learning for LS-SVM by formulating it as semidefinite programming (SDP). Furthermore, we show that the regularization parameter can be optimized in a unified framework with the kernel, which leads to an automatic process for model selection. Extensive experimental validations are performed and analyzed. Copyright © 2011 Elsevier Ltd. All rights reserved.

Typical Intellectual Engagement, Big Five Personality Traits, Approaches to Learning and Cognitive Ability Predictors of Academic Performance

ERIC Educational Resources Information Center

Furnham, Adrian; Monsen, Jeremy; Ahmetoglu, Gorkan

2009-01-01

Background: Both ability (measured by power tests) and non-ability (measured by preference tests) individual difference measures predict academic school outcomes. These include fluid as well as crystalized intelligence, personality traits, and learning styles. This paper examines the incremental validity of five psychometric tests and the sex and…

Effects of Extended Time Allotments on Reading Comprehension Performance of College Students with and without Learning Disabilities

ERIC Educational Resources Information Center

Lewandowski, Lawrence; Cohen, Justin; Lovett, Benjamin J.

2013-01-01

Students with disabilities often receive test accommodations in schools and on high-stakes tests. Students with learning disabilities (LD) represent the largest disability group in schools, and extended time the most common test accommodation requested by such students. This pairing persists despite controversy over the validity of extended time…

Teacher Performance and Student Learning: Linking Evidence from Two National Assessment Programmes

ERIC Educational Resources Information Center

Taut, Sandy; Valencia, Edgar; Palacios, Diego; Santelices, Maria V.; Jiménez, Daniela; Manzi, Jorge

2016-01-01

This paper investigates the validity of a national, standards-based teacher evaluation programme by examining the relationship between teachers' evaluation results and their students' learning progress. We used census achievement data that assessed the same cohort of students at the end of 8th and 10th grade. We applied multilevel modelling and…

Evaluation of the Motivated Strategies for Learning Questionnaire for Predicting Academic Performance in College Students of Varying Scholastic Aptitude

ERIC Educational Resources Information Center

Burlison, Jonathan D.; Murphy, Chanda S.; Dwyer, William O.

2009-01-01

All 15 subscales of the Motivated Strategies for Learning Questionnaire (Pintrich, Smith, Garcia, & McKeachie, 1993) were administered to 352 undergraduate students taking Introductory Psychology. Their scores were evaluated with respect to incremental validity (in addition to ACT scores) they provided for predicting course grades. Results…

Measuring Student Variables Useful in the Study of Performance in an Online Learning Environment.

ERIC Educational Resources Information Center

Kennedy, Cathleen A.

This paper discusses the measurement of unobservable or latent variables of students and how they contribute to learning in an online environment. It also examines the construct validity of two questionnaires: the College Experience Survey and the Computer Experience Study, which both measure different aspects of student attitudes and behavior…

Electrotactile Feedback Improves Performance and Facilitates Learning in the Routine Grasping Task.

PubMed

Isaković, Milica; Belić, Minja; Štrbac, Matija; Popović, Igor; Došen, Strahinja; Farina, Dario; Keller, Thierry

2016-06-13

Aim of this study was to investigate the feasibility of electrotactile feedback in closed loop training of force control during the routine grasping task. The feedback was provided using an array electrode and a simple six-level spatial coding, and the experiment was conducted in three amputee subjects. The psychometric tests confirmed that the subjects could perceive and interpret the electrotactile feedback with a high success rate. The subjects performed the routine grasping task comprising 4 blocks of 60 grasping trials. In each trial, the subjects employed feedforward control to close the hand and produce the desired grasping force (four levels). First (baseline) and the last (validation) session were performed in open loop, while the second and the third session (training) included electrotactile feedback. The obtained results confirmed that using the feedback improved the accuracy and precision of the force control. In addition, the subjects performed significantly better in the validation vs. baseline session, therefore suggesting that electrotactile feedback can be used for learning and training of myoelectric control.

Comparison of machine-learning algorithms to build a predictive model for detecting undiagnosed diabetes - ELSA-Brasil: accuracy study.

PubMed

Olivera, André Rodrigues; Roesler, Valter; Iochpe, Cirano; Schmidt, Maria Inês; Vigo, Álvaro; Barreto, Sandhi Maria; Duncan, Bruce Bartholow

2017-01-01

Type 2 diabetes is a chronic disease associated with a wide range of serious health complications that have a major impact on overall health. The aims here were to develop and validate predictive models for detecting undiagnosed diabetes using data from the Longitudinal Study of Adult Health (ELSA-Brasil) and to compare the performance of different machine-learning algorithms in this task. Comparison of machine-learning algorithms to develop predictive models using data from ELSA-Brasil. After selecting a subset of 27 candidate variables from the literature, models were built and validated in four sequential steps: (i) parameter tuning with tenfold cross-validation, repeated three times; (ii) automatic variable selection using forward selection, a wrapper strategy with four different machine-learning algorithms and tenfold cross-validation (repeated three times), to evaluate each subset of variables; (iii) error estimation of model parameters with tenfold cross-validation, repeated ten times; and (iv) generalization testing on an independent dataset. The models were created with the following machine-learning algorithms: logistic regression, artificial neural network, naïve Bayes, K-nearest neighbor and random forest. The best models were created using artificial neural networks and logistic regression. -These achieved mean areas under the curve of, respectively, 75.24% and 74.98% in the error estimation step and 74.17% and 74.41% in the generalization testing step. Most of the predictive models produced similar results, and demonstrated the feasibility of identifying individuals with highest probability of having undiagnosed diabetes, through easily-obtained clinical data.

Development, validation and operating room-transfer of a six-step laparoscopic training program for the vesicourethral anastomosis.

PubMed

Klein, Jan; Teber, Dogu; Frede, Tom; Stock, Christian; Hruza, Marcel; Gözen, Ali; Seemann, Othmar; Schulze, Michael; Rassweiler, Jens

2013-03-01

Development and full validation of a laparoscopic training program for stepwise learning of a reproducible application of a standardized laparoscopic anastomosis technique and integration into the clinical course. The training of vesicourethral anastomosis (VUA) was divided into six simple standardized steps. To fix the objective criteria, four experienced surgeons performed the stepwise training protocol. Thirty-eight participants with no previous laparoscopic experience were investigated in their training performance. The times needed to manage each training step and the total training time were recorded. The integration into the clinical course was investigated. The training results and the corresponding steps during laparoscopic radical prostatectomy (LRP) were analyzed. Data analysis of corresponding operating room (OR) sections of 793 LRP was performed. Based on the validity, criteria were determined. In the laboratory section, a significant reduction of OR time for every step was seen in all participants. Coordination: 62%; longitudinal incision: 52%; inverted U-shape incision: 43%; plexus: 47%. Anastomosis catheter model: 38%. VUA: 38%. The laboratory section required a total time of 29 hours (minimum: 16 hours; maximum: 42 hours). All participants had shorter execution times in the laboratory than under real conditions. The best match was found within the VUA model. To perform an anastomosis under real conditions, 25% more time was needed. By using the training protocol, the performance of the VUA is comparable to that of an surgeon with experience of about 50 laparoscopic VUA. Data analysis proved content, construct, and prognostic validity. The use of stepwise training approaches enables a surgeon to learn and reproduce complex reconstructive surgical tasks: eg, the VUA in a safe environment. The validity of the designed system is given at all levels and should be used as a standard in the clinical surgical training in laparoscopic reconstructive urology.

A Novel Unsupervised Adaptive Learning Method for Long-Term Electromyography (EMG) Pattern Recognition

PubMed Central

Huang, Qi; Yang, Dapeng; Jiang, Li; Zhang, Huajie; Liu, Hong; Kotani, Kiyoshi

2017-01-01

Performance degradation will be caused by a variety of interfering factors for pattern recognition-based myoelectric control methods in the long term. This paper proposes an adaptive learning method with low computational cost to mitigate the effect in unsupervised adaptive learning scenarios. We presents a particle adaptive classifier (PAC), by constructing a particle adaptive learning strategy and universal incremental least square support vector classifier (LS-SVC). We compared PAC performance with incremental support vector classifier (ISVC) and non-adapting SVC (NSVC) in a long-term pattern recognition task in both unsupervised and supervised adaptive learning scenarios. Retraining time cost and recognition accuracy were compared by validating the classification performance on both simulated and realistic long-term EMG data. The classification results of realistic long-term EMG data showed that the PAC significantly decreased the performance degradation in unsupervised adaptive learning scenarios compared with NSVC (9.03% ± 2.23%, p < 0.05) and ISVC (13.38% ± 2.62%, p = 0.001), and reduced the retraining time cost compared with ISVC (2 ms per updating cycle vs. 50 ms per updating cycle). PMID:28608824

A Novel Unsupervised Adaptive Learning Method for Long-Term Electromyography (EMG) Pattern Recognition.

PubMed

Huang, Qi; Yang, Dapeng; Jiang, Li; Zhang, Huajie; Liu, Hong; Kotani, Kiyoshi

2017-06-13

Performance degradation will be caused by a variety of interfering factors for pattern recognition-based myoelectric control methods in the long term. This paper proposes an adaptive learning method with low computational cost to mitigate the effect in unsupervised adaptive learning scenarios. We presents a particle adaptive classifier (PAC), by constructing a particle adaptive learning strategy and universal incremental least square support vector classifier (LS-SVC). We compared PAC performance with incremental support vector classifier (ISVC) and non-adapting SVC (NSVC) in a long-term pattern recognition task in both unsupervised and supervised adaptive learning scenarios. Retraining time cost and recognition accuracy were compared by validating the classification performance on both simulated and realistic long-term EMG data. The classification results of realistic long-term EMG data showed that the PAC significantly decreased the performance degradation in unsupervised adaptive learning scenarios compared with NSVC (9.03% ± 2.23%, p < 0.05) and ISVC (13.38% ± 2.62%, p = 0.001), and reduced the retraining time cost compared with ISVC (2 ms per updating cycle vs. 50 ms per updating cycle).

Critical validation studies of neurofeedback.

PubMed

Gruzelier, John; Egner, Tobias

2005-01-01

The field of neurofeedback training has proceeded largely without validation. In this article the authors review studies directed at validating sensory motor rhythm, beta and alpha-theta protocols for improving attention, memory, and music performance in healthy participants. Importantly, benefits were demonstrable with cognitive and neurophysiologic measures that were predicted on the basis of regression models of learning to enhance sensory motor rhythm and beta activity. The first evidence of operant control over the alpha-theta ratio is provided, together with remarkable improvements in artistic aspects of music performance equivalent to two class grades in conservatory students. These are initial steps in providing a much needed scientific basis to neurofeedback.

Teaching and learning in out-patient clinics.

PubMed

Williamson, James

2012-10-01

Out-patient clinics offer trainees one of the most varied clinical experiences within the hospital setting, but they are often chaotic and over-stretched, with limited time for teaching. An awareness of how to improve this learning environment by both trainers and trainees may enhance learning opportunities. Clinical supervisors need to balance educational and service commitments, while maintaining a high quality of patient care. Supervision features observation and the sharing of clinical and continual feedback, which can improve clinical performance. Trainers must closely monitor the abilities of the trainee and gradually increase their responsibility and clinical load. The application of learning theory to the workplace can improve learning opportunities. Trainers should have some control over the environment, both the physical attributes (room availability, staffing levels and allocated consultation time) and the harder to measure aspects, such as the ethos of the department and attitudes to teaching. The creation of a community of practice within out-patient clinics can strengthen both the collective knowledge of the team and its role in treating patients. The active involvement of trainees within this social environment (for example, by performing independent consultations) validates their role in the care of patients and enhances their learning. To maximise the learning opportunities within out-patient clinics there needs to be a shift in culture to promote learning in a safe and non-threatening environment. The establishment of a community of practice may validate the role of trainees in the management of patients and facilitate social learning by all members of the clinical team. © Blackwell Publishing Ltd 2012.

Improving machine learning reproducibility in genetic association studies with proportional instance cross validation (PICV).

PubMed

Piette, Elizabeth R; Moore, Jason H

2018-01-01

Machine learning methods and conventions are increasingly employed for the analysis of large, complex biomedical data sets, including genome-wide association studies (GWAS). Reproducibility of machine learning analyses of GWAS can be hampered by biological and statistical factors, particularly so for the investigation of non-additive genetic interactions. Application of traditional cross validation to a GWAS data set may result in poor consistency between the training and testing data set splits due to an imbalance of the interaction genotypes relative to the data as a whole. We propose a new cross validation method, proportional instance cross validation (PICV), that preserves the original distribution of an independent variable when splitting the data set into training and testing partitions. We apply PICV to simulated GWAS data with epistatic interactions of varying minor allele frequencies and prevalences and compare performance to that of a traditional cross validation procedure in which individuals are randomly allocated to training and testing partitions. Sensitivity and positive predictive value are significantly improved across all tested scenarios for PICV compared to traditional cross validation. We also apply PICV to GWAS data from a study of primary open-angle glaucoma to investigate a previously-reported interaction, which fails to significantly replicate; PICV however improves the consistency of testing and training results. Application of traditional machine learning procedures to biomedical data may require modifications to better suit intrinsic characteristics of the data, such as the potential for highly imbalanced genotype distributions in the case of epistasis detection. The reproducibility of genetic interaction findings can be improved by considering this variable imbalance in cross validation implementation, such as with PICV. This approach may be extended to problems in other domains in which imbalanced variable distributions are a concern.

Infinite hidden conditional random fields for human behavior analysis.

PubMed

Bousmalis, Konstantinos; Zafeiriou, Stefanos; Morency, Louis-Philippe; Pantic, Maja

2013-01-01

Hidden conditional random fields (HCRFs) are discriminative latent variable models that have been shown to successfully learn the hidden structure of a given classification problem (provided an appropriate validation of the number of hidden states). In this brief, we present the infinite HCRF (iHCRF), which is a nonparametric model based on hierarchical Dirichlet processes and is capable of automatically learning the optimal number of hidden states for a classification task. We show how we learn the model hyperparameters with an effective Markov-chain Monte Carlo sampling technique, and we explain the process that underlines our iHCRF model with the Restaurant Franchise Rating Agencies analogy. We show that the iHCRF is able to converge to a correct number of represented hidden states, and outperforms the best finite HCRFs--chosen via cross-validation--for the difficult tasks of recognizing instances of agreement, disagreement, and pain. Moreover, the iHCRF manages to achieve this performance in significantly less total training, validation, and testing time.

What motivates professionals to learn and use hypnosis in clinical practice?

PubMed

Meyerson, Joseph; Gelkopf, Marc; Golan, Gaby; Shahamorov, Ewa

2013-01-01

The authors devised and validated a questionnaire assessing the various possible motivations for learning and using hypnosis and administered it to 125 Israeli psychologists, physicians, and dentists who study and/or use hypnosis in their clinical work. The results suggest that most professionals were motivated by a desire to improve their professional performance and that a majority of professionals were primarily influenced in their desire to learn hypnosis by colleagues in academically or clinically oriented settings.

Profiling Perceptual Learning Styles of Chinese as a Second Language Learners in University Settings.

PubMed

Sun, Peijian Paul; Teng, Lin Sophie

2017-12-01

This study revisited Reid's (1987) perceptual learning style preference questionnaire (PLSPQ) in an attempt to answer whether the PLSPQ fits in the Chinese-as-a-second-language (CSL) context. If not, what are CSL learners' learning styles drawing on the PLSPQ? The PLSPQ was first re-examined through reliability analysis and confirmatory factor analysis (CFA) with 224 CSL learners. The results showed that Reid's six-factor PLSPQ could not satisfactorily explain the CSL learners' learning styles. Exploratory factor analyses were, therefore, performed to explore the dimensionality of the PLSPQ in the CSL context. A four-factor PLSPQ was successfully constructed including auditory/visual, kinaesthetic/tactile, group, and individual styles. Such a measurement model was cross-validated through CFAs with 118 CSL learners. The study not only lends evidence to the literature that Reid's PLSPQ lacks construct validity, but also provides CSL teachers and learners with insightful and practical guidance concerning learning styles. Implications and limitations of the present study are discussed.

Punishment sensitivity modulates the processing of negative feedback but not error-induced learning.

PubMed

Unger, Kerstin; Heintz, Sonja; Kray, Jutta

2012-01-01

Accumulating evidence suggests that individual differences in punishment and reward sensitivity are associated with functional alterations in neural systems underlying error and feedback processing. In particular, individuals highly sensitive to punishment have been found to be characterized by larger mediofrontal error signals as reflected in the error negativity/error-related negativity (Ne/ERN) and the feedback-related negativity (FRN). By contrast, reward sensitivity has been shown to relate to the error positivity (Pe). Given that Ne/ERN, FRN, and Pe have been functionally linked to flexible behavioral adaptation, the aim of the present research was to examine how these electrophysiological reflections of error and feedback processing vary as a function of punishment and reward sensitivity during reinforcement learning. We applied a probabilistic learning task that involved three different conditions of feedback validity (100%, 80%, and 50%). In contrast to prior studies using response competition tasks, we did not find reliable correlations between punishment sensitivity and the Ne/ERN. Instead, higher punishment sensitivity predicted larger FRN amplitudes, irrespective of feedback validity. Moreover, higher reward sensitivity was associated with a larger Pe. However, only reward sensitivity was related to better overall learning performance and higher post-error accuracy, whereas highly punishment sensitive participants showed impaired learning performance, suggesting that larger negative feedback-related error signals were not beneficial for learning or even reflected maladaptive information processing in these individuals. Thus, although our findings indicate that individual differences in reward and punishment sensitivity are related to electrophysiological correlates of error and feedback processing, we found less evidence for influences of these personality characteristics on the relation between performance monitoring and feedback-based learning.

Measuring students' self-regulated learning in professional education: bridging the gap between event and aptitude measurements.

PubMed

Endedijk, Maaike D; Brekelmans, Mieke; Sleegers, Peter; Vermunt, Jan D

Self-regulated learning has benefits for students' academic performance in school, but also for expertise development during their professional career. This study examined the validity of an instrument to measure student teachers' regulation of their learning to teach across multiple and different kinds of learning events in the context of a postgraduate professional teacher education programme. Based on an analysis of the literature, we developed a log with structured questions that could be used as a multiple-event instrument to determine the quality of student teachers' regulation of learning by combining data from multiple learning experiences. The findings showed that this structured version of the instrument measured student teachers' regulation of their learning in a valid and reliable way. Furthermore, with the aid of the Structured Learning Report individual differences in student teachers' regulation of learning could be discerned. Together the findings indicate that a multiple-event instrument can be used to measure regulation of learning in multiple contexts for various learning experiences at the same time, without the necessity of relying on students' ability to rate themselves across all these different experiences. In this way, this instrument can make an important contribution to bridging the gap between two dominant approaches to measure SRL, the traditional aptitude and event measurement approach.

Conative aptitudes in science learning

NASA Astrophysics Data System (ADS)

Jackson, Douglas Northrop, III

2000-09-01

The conative domain of aptitude constructs spans the domains of individual differences in motivation and volition. This research sampled a broad range of conative constructs, including achievement motivation, anxiety, goal orientations, and interest, among others. The purpose was threefold: (a) to explore relationships among conative constructs hypothesized to affect student commitment to learning and subsequent performance, (b) to determine whether or not individual differences in conative constructs were associated with the learning activities and time-on-task of students learning science, and (c) to ascertain whether or not the conative constructs and the time and activity variables were associated with performance differences in a paper-and-pencil science recall measure. This research consisted of three separate studies. Study I involved 60 U.S. college students. In Study II, 234 Canadian high school students participated. These two studies investigated the construct validity of a selection of conative constructs. A principal components analysis of the measures was undertaken and yielded seven components: Pursuit of Excellence, Evaluation Anxiety, Self-Reported Grades, Science Confidence, Science Interest vs. Science Ambivalence, Performance Orientation, and Verbal Ability. For Study III, 82 Canadian high school students completed the same conative questionnaires as were administered in Study II. A computerized environment patterned after an internet browser allowed students to learn about disease-causing microbes. The environment yielded aggregate measures of the time spent learning science, the time spent playing games, the number of games played, and the number of science-related learning activities engaged in by each student. Following administration of the computerized learning environment, students were administered a paper-and pencil science recall measure. Study III found support for the educational importance of the conative variables. Among the principal components, the strongest positive relationship was found between Science Interest vs. Science Ambivalence and performance on the recall measure. Scores on the conative variables were also correlated with both the time and activity variables from the computerized learning task. The implications of the findings are discussed with regard to the construct validation of conative constructs, the use of conative constructs for future educational research, and the design of computerized learning environments for both educational research and applied use.

Validity of Peer Evaluation for Team-Based Learning in a Dental School in Japan.

PubMed

Nishigawa, Keisuke; Hayama, Rika; Omoto, Katsuhiro; Okura, Kazuo; Tajima, Toyoko; Suzuki, Yoshitaka; Hosoki, Maki; Ueda, Mayu; Inoue, Miho; Rodis, Omar Marianito Maningo; Matsuka, Yoshizo

2017-12-01

The aim of this study was to determine the validity of peer evaluation for team-based learning (TBL) classes in dental education in comparison with the term-end examination records and TBL class scores. Examination and TBL class records of 256 third- and fourth-year dental students in six fixed prosthodontics courses from 2013 to 2015 in one dental school in Japan were investigated. Results of the term-end examination during those courses, individual readiness assurance test (IRAT), group readiness assurance test (GRAT), group assignment projects (GAP), and peer evaluation of group members in TBL classes were collected. Significant positive correlations were found between all combinations of peer evaluation, IRAT, and term-end examination. Individual scores also showed a positive correlation with group score (total of GRAT and GAP). From the investigation of the correlations in the six courses, significant positive correlations between peer evaluation and individual score were found in four of the six courses. In this study, peer evaluation seemed to be a valid index for learning performance in TBL classes. To verify the effectiveness of peer evaluation, all students have to realize the significance of scoring the team member's performance. Clear criteria and detailed instruction for appropriate evaluation are also required.

A hypothesis-driven physical examination learning and assessment procedure for medical students: initial validity evidence.

PubMed

Yudkowsky, Rachel; Otaki, Junji; Lowenstein, Tali; Riddle, Janet; Nishigori, Hiroshi; Bordage, Georges

2009-08-01

Diagnostic accuracy is maximised by having clinical signs and diagnostic hypotheses in mind during the physical examination (PE). This diagnostic reasoning approach contrasts with the rote, hypothesis-free screening PE learned by many medical students. A hypothesis-driven PE (HDPE) learning and assessment procedure was developed to provide targeted practice and assessment in anticipating, eliciting and interpreting critical aspects of the PE in the context of diagnostic challenges. This study was designed to obtain initial content validity evidence, performance and reliability estimates, and impact data for the HDPE procedure. Nineteen clinical scenarios were developed, covering 160 PE manoeuvres. A total of 66 Year 3 medical students prepared for and encountered three clinical scenarios during required formative assessments. For each case, students listed anticipated positive PE findings for two plausible diagnoses before examining the patient; examined a standardised patient (SP) simulating one of the diagnoses; received immediate feedback from the SP, and documented their findings and working diagnosis. The same students later encountered some of the scenarios during their Year 4 clinical skills examination. On average, Year 3 students anticipated 65% of the positive findings, correctly performed 88% of the PE manoeuvres and documented 61% of the findings. Year 4 students anticipated and elicited fewer findings overall, but achieved proportionally more discriminating findings, thereby more efficiently achieving a diagnostic accuracy equivalent to that of students in Year 3. Year 4 students performed better on cases on which they had received feedback as Year 3 students. Twelve cases would provide a reliability of 0.80, based on discriminating checklist items only. The HDPE provided medical students with a thoughtful, deliberate approach to learning and assessing PE skills in a valid and reliable manner.

Curriculum-Based Measurement in the Content Areas: Vocabulary Matching as an Indicator of Progress in Social Studies Learning

ERIC Educational Resources Information Center

Espin, Christine A.; Shin, Jongho; Busch, Todd W.

2005-01-01

The purpose of this study was to examine the reliability and validity of curriculum-based measures as indicator of growth in content-area learning. Participants were 58 students in 2 seventh-grade social studies classes. CBM measures were student- and administrator-read vocabulary-matching probes. Criterion measures were performance on a knowledge…

Construct Validity of the California Verbal Learning Test--Children's Version (CVLT-C) after Pediatric Traumatic Brain Injury

ERIC Educational Resources Information Center

Mottram, Lisa; Donders, Jacobus

2005-01-01

The purpose of this study was to determine the latent structure of the California Verbal Learning Test--Children's Version (CVLT-C; D. Delis, J. Kramer, E.Kaplan, & B. Ober, 1994) in a sample of 175 children with traumatic brain injury (TBI). Maximum-likelihood confirmatory factor analyses were performed to test 6 competing hypothetical models…

Using deep learning for detecting gender in adult chest radiographs

NASA Astrophysics Data System (ADS)

Xue, Zhiyun; Antani, Sameer; Long, L. Rodney; Thoma, George R.

2018-03-01

In this paper, we present a method for automatically identifying the gender of an imaged person using their frontal chest x-ray images. Our work is motivated by the need to determine missing gender information in some datasets. The proposed method employs the technique of convolutional neural network (CNN) based deep learning and transfer learning to overcome the challenge of developing handcrafted features in limited data. Specifically, the method consists of four main steps: pre-processing, CNN feature extractor, feature selection, and classifier. The method is tested on a combined dataset obtained from several sources with varying acquisition quality resulting in different pre-processing steps that are applied for each. For feature extraction, we tested and compared four CNN architectures, viz., AlexNet, VggNet, GoogLeNet, and ResNet. We applied a feature selection technique, since the feature length is larger than the number of images. Two popular classifiers: SVM and Random Forest, are used and compared. We evaluated the classification performance by cross-validation and used seven performance measures. The best performer is the VggNet-16 feature extractor with the SVM classifier, with accuracy of 86.6% and ROC Area being 0.932 for 5-fold cross validation. We also discuss several misclassified cases and describe future work for performance improvement.

Validity of a verbal incidental learning measure from the WAIS-IV in older adults.

PubMed

Hammers, Dustin B; Kucera, Amanda M; Card, Stephanie J; Tolle, Kathryn A; Atkinson, Taylor J; Duff, Kevin; Spencer, Robert J

2018-01-01

Incidental memory may reflect a form of learning in everyday life, although it is not consistently evaluated during standard neuropsychological evaluations. Further validation of a recently created measure of verbal Incidental Learning (IL) from the Wechsler Adult Intelligence Scale-IV is necessary to understand the utility of such a measure in clinical settings. Sixty-eight adults aged 50 to 89 were recruited from a Cognitive Disorders Clinic while receiving a standard neuropsychological assessment, along with two additional measures of IL. IL-Total Score was significantly correlated with immediate and delayed memory trials from standard neuropsychological tests (rs = .43 to .73, ps < .001, ds = 0.94-2.14), with worse IL performance being associated with lower memory abilities. Participants with probable Alzheimer's disease performed worse on the IL-Total Score than participants with Mild Cognitive Impairment, t(39.997) = 5.46, p < .001, d = 1.13. Given the strong relationships between this IL task and traditional memory measures in our sample, and the discrimination of IL-Total Score performance among diagnostic groups despite its short administration time, this IL task may play a role as a measure of memory in brief cognitive evaluations.

Developing an instrument to measure effective factors on Clinical Learning

PubMed Central

DADGARAN, IDEH; SHIRAZI, MANDANA; MOHAMMADI, AEEN; RAVARI, ALI

2016-01-01

Introduction Although nursing students spend a large part of their learning period in the clinical environment, clinical learning has not been perceived by its nature yet. To develop an instrument to measure effective factors on clinical learning in nursing students. Methods This is a mixed methods study performed in 2 steps. First, the researchers defined “clinical learning” in nursing students through qualitative content analysis and designed items of the questionnaire based on semi-structured individual interviews with nursing students. Then, as the second step, psychometric properties of the questionnaire were evaluated using the face validity, content validity, construct validity, and internal consistency evaluated on 227 students from fourth or higher semesters. All the interviews were recorded and transcribed, and then, they were analyzed using Max Qualitative Data Analysis and all of qualitative data were analyzed using SPSS 14. Results To do the study, we constructed the preliminary questionnaire containing 102 expressions. After determination of face and content validities by qualitative and quantitative approaches, the expressions of the questionnaire were reduced to 45. To determine the construct validity, exploratory factor analysis was applied. The results indicated that the maximum variance percentage (40.55%) was defined by the first 3 factors while the rest of the total variance percentage (59.45%) was determined by the other 42 factors. Results of exploratory factor analysis of this questionnaire indicated the presence of 3 instructor-staff, students, and educational related factors. Finally, 41 expressions were kept in 3 factor groups. The α-Cronbach coefficient (0.93) confirmed the high internal consistency of the questionnaire. Conclusion Results indicated that the prepared questionnaire was an efficient instrument in the study of the effective factors on clinical learning as viewed by nursing students since it involves 41 expressions and properties such as instrument design based on perception and experiences of the nursing students about effective factors on clinical learning, definition of facilitator and preventive factors of the clinical learning, simple scoring, suitable validity and reliability, and applicability in different occasions. PMID:27382579

Phonological and Non-Phonological Language Skills as Predictors of Early Reading Performance

ERIC Educational Resources Information Center

Batson-Magnuson, LuAnn

2010-01-01

Accurate prediction of early childhood reading performance could help identify at-risk students, aid in the development of evidence-based intervention strategies, and further our theoretical understanding of reading development. This study assessed the validity of the Developmental Indicator for the Assessment of Learning (DIAL) language-based…

Scene recognition based on integrating active learning with dictionary learning

NASA Astrophysics Data System (ADS)

Wang, Chengxi; Yin, Xueyan; Yang, Lin; Gong, Chengrong; Zheng, Caixia; Yi, Yugen

2018-04-01

Scene recognition is a significant topic in the field of computer vision. Most of the existing scene recognition models require a large amount of labeled training samples to achieve a good performance. However, labeling image manually is a time consuming task and often unrealistic in practice. In order to gain satisfying recognition results when labeled samples are insufficient, this paper proposed a scene recognition algorithm named Integrating Active Learning and Dictionary Leaning (IALDL). IALDL adopts projective dictionary pair learning (DPL) as classifier and introduces active learning mechanism into DPL for improving its performance. When constructing sampling criterion in active learning, IALDL considers both the uncertainty and representativeness as the sampling criteria to effectively select the useful unlabeled samples from a given sample set for expanding the training dataset. Experiment results on three standard databases demonstrate the feasibility and validity of the proposed IALDL.

The role of critical thinking skills and learning styles of university students in their academic performance.

PubMed

Ghazivakili, Zohre; Norouzi Nia, Roohangiz; Panahi, Faride; Karimi, Mehrdad; Gholsorkhi, Hayede; Ahmadi, Zarrin

2014-07-01

The Current world needs people who have a lot of different abilities such as cognition and application of different ways of thinking, research, problem solving, critical thinking skills and creativity. In addition to critical thinking, learning styles is another key factor which has an essential role in the process of problem solving. This study aimed to determine the relationship between learning styles and critical thinking of students and their academic performance in Alborz University of Medical Science. This cross-correlation study was performed in 2012, on 216 students of Alborz University who were selected randomly by the stratified random sampling. The data was obtained via a three-part questionnaire included demographic data, Kolb standardized questionnaire of learning style and California critical thinking standardized questionnaire. The academic performance of the students was extracted by the school records. The validity of the instruments was determined in terms of content validity, and the reliability was gained through internal consistency methods. Cronbach's alpha coefficient was found to be 0.78 for the California critical thinking questionnaire. The Chi Square test, Independent t-test, one way ANOVA and Pearson correlation test were used to determine relationship between variables. The Package SPSS14 statistical software was used to analyze data with a significant level of p<0.05. Our findings indicated the significant difference of mean score in four learning style, suggesting university students with convergent learning style have better performance than other groups. Also learning style had a relationship with age, gender, field of study, semester and job. The results about the critical thinking of the students showed that the mean of deductive reasoning and evaluation skills were higher than that of other skills and analytical skills had the lowest mean and there was a positive significant relationship between the students' performance with inferential skill and the total score of critical thinking skills (p<0.05). Furthermore, evaluation skills and deductive reasoning had significant relationship. On the other hand, the mean total score of critical thinking had significant difference between different learning styles. The results of this study showed that the learning styles, critical thinking and academic performance are significantly associated with one another. Considering the growing importance of critical thinking in enhancing the professional competence of individuals, it's recommended to use teaching methods consistent with the learning style because it would be more effective in this context.

The role of critical thinking skills and learning styles of university students in their academic performance

PubMed Central

GHAZIVAKILI, ZOHRE; NOROUZI NIA, ROOHANGIZ; PANAHI, FARIDE; KARIMI, MEHRDAD; GHOLSORKHI, HAYEDE; AHMADI, ZARRIN

2014-01-01

Introduction: The Current world needs people who have a lot of different abilities such as cognition and application of different ways of thinking, research, problem solving, critical thinking skills and creativity. In addition to critical thinking, learning styles is another key factor which has an essential role in the process of problem solving. This study aimed to determine the relationship between learning styles and critical thinking of students and their academic performance in Alborz University of Medical Science. Methods: This cross-correlation study was performed in 2012, on 216 students of Alborz University who were selected randomly by the stratified random sampling. The data was obtained via a three-part questionnaire included demographic data, Kolb standardized questionnaire of learning style and California critical thinking standardized questionnaire. The academic performance of the students was extracted by the school records. The validity of the instruments was determined in terms of content validity, and the reliability was gained through internal consistency methods. Cronbach's alpha coefficient was found to be 0.78 for the California critical thinking questionnaire. The Chi Square test, Independent t-test, one way ANOVA and Pearson correlation test were used to determine relationship between variables. The Package SPSS14 statistical software was used to analyze data with a significant level of p<0.05. Results: Our findings indicated the significant difference of mean score in four learning style, suggesting university students with convergent learning style have better performance than other groups. Also learning style had a relationship with age, gender, field of study, semester and job. The results about the critical thinking of the students showed that the mean of deductive reasoning and evaluation skills were higher than that of other skills and analytical skills had the lowest mean and there was a positive significant relationship between the students’ performance with inferential skill and the total score of critical thinking skills (p<0.05). Furthermore, evaluation skills and deductive reasoning had significant relationship. On the other hand, the mean total score of critical thinking had significant difference between different learning styles. Conclusion: The results of this study showed that the learning styles, critical thinking and academic performance are significantly associated with one another. Considering the growing importance of critical thinking in enhancing the professional competence of individuals, it's recommended to use teaching methods consistent with the learning style because it would be more effective in this context. PMID:25512928

A Slovenian version of the "clinical learning environment, supervision and nurse teacher scale (Cles+T)" and its comparison with the Croatian version.

PubMed

Žvanut, Boštjan; Lovrić, Robert; Kolnik, Tamara Štemberger; Šavle, Majda; Pucer, Patrik

2018-05-01

Nursing clinical learning environments are particularly important for the achievement of good practice in clinical training of student nurses, and thus, for the nursing competence development. Hence, it is important to have an instrument consisting of reliable and valid criteria for assessing the clinical learning environment, applicable in different contexts, and translated in the respondents mother tongue. The goal of the present research was to test the reliability and validity of the Slovenian version of the "Clinical Learning Environment, Supervision and Nurse Teacher evaluation scale", and to compare it with the Croatian version. The data was collected between 10 March and 10 June 2015 at four Slovenian institutions, where nursing BSc study programmes are performed. The final sample consisted of 232 students (response rate 68.8%): 81.9% were females and 18.1% males, average age was 23. The translated instrument in Slovenian language resulted as reliable and valid, it reflects the expected five factors of the original version despite some minor problems in the factor structure and in test-retest. The most important difference between the Slovenian and Croatian version is in the factor structure regarding the implementation of roles in clinical learning environment. Copyright © 2018 Elsevier Ltd. All rights reserved.

Efficacy of a Deep Learning System for Detecting Glaucomatous Optic Neuropathy Based on Color Fundus Photographs.

PubMed

Li, Zhixi; He, Yifan; Keel, Stuart; Meng, Wei; Chang, Robert T; He, Mingguang

2018-03-02

To assess the performance of a deep learning algorithm for detecting referable glaucomatous optic neuropathy (GON) based on color fundus photographs. A deep learning system for the classification of GON was developed for automated classification of GON on color fundus photographs. We retrospectively included 48 116 fundus photographs for the development and validation of a deep learning algorithm. This study recruited 21 trained ophthalmologists to classify the photographs. Referable GON was defined as vertical cup-to-disc ratio of 0.7 or more and other typical changes of GON. The reference standard was made until 3 graders achieved agreement. A separate validation dataset of 8000 fully gradable fundus photographs was used to assess the performance of this algorithm. The area under receiver operator characteristic curve (AUC) with sensitivity and specificity was applied to evaluate the efficacy of the deep learning algorithm detecting referable GON. In the validation dataset, this deep learning system achieved an AUC of 0.986 with sensitivity of 95.6% and specificity of 92.0%. The most common reasons for false-negative grading (n = 87) were GON with coexisting eye conditions (n = 44 [50.6%]), including pathologic or high myopia (n = 37 [42.6%]), diabetic retinopathy (n = 4 [4.6%]), and age-related macular degeneration (n = 3 [3.4%]). The leading reason for false-positive results (n = 480) was having other eye conditions (n = 458 [95.4%]), mainly including physiologic cupping (n = 267 [55.6%]). Misclassification as false-positive results amidst a normal-appearing fundus occurred in only 22 eyes (4.6%). A deep learning system can detect referable GON with high sensitivity and specificity. Coexistence of high or pathologic myopia is the most common cause resulting in false-negative results. Physiologic cupping and pathologic myopia were the most common reasons for false-positive results. Copyright © 2018 American Academy of Ophthalmology. Published by Elsevier Inc. All rights reserved.

Model-Free control performance improvement using virtual reference feedback tuning and reinforcement Q-learning

NASA Astrophysics Data System (ADS)

Radac, Mircea-Bogdan; Precup, Radu-Emil; Roman, Raul-Cristian

2017-04-01

This paper proposes the combination of two model-free controller tuning techniques, namely linear virtual reference feedback tuning (VRFT) and nonlinear state-feedback Q-learning, referred to as a new mixed VRFT-Q learning approach. VRFT is first used to find stabilising feedback controller using input-output experimental data from the process in a model reference tracking setting. Reinforcement Q-learning is next applied in the same setting using input-state experimental data collected under perturbed VRFT to ensure good exploration. The Q-learning controller learned with a batch fitted Q iteration algorithm uses two neural networks, one for the Q-function estimator and one for the controller, respectively. The VRFT-Q learning approach is validated on position control of a two-degrees-of-motion open-loop stable multi input-multi output (MIMO) aerodynamic system (AS). Extensive simulations for the two independent control channels of the MIMO AS show that the Q-learning controllers clearly improve performance over the VRFT controllers.

Embedded performance validity tests within the Hopkins Verbal Learning Test - Revised and the Brief Visuospatial Memory Test - Revised.

PubMed

Sawyer, R John; Testa, S Marc; Dux, Moira

2017-01-01

Various research studies and neuropsychology practice organizations have reiterated the importance of developing embedded performance validity tests (PVTs) to detect potentially invalid neurocognitive test data. This study investigated whether measures within the Hopkins Verbal Learning Test - Revised (HVLT-R) and the Brief Visuospatial Memory Test - Revised (BVMT-R) could accurately classify individuals who fail two or more PVTs during routine clinical assessment. The present sample of 109 United States military veterans (Mean age = 52.4, SD = 13.3), all consisted of clinically referred patients and received a battery of neuropsychological tests. Based on performance validity findings, veterans were assigned to valid (n = 86) or invalid (n = 23) groups. Of the 109 patients in the overall sample, 77 were administered the HLVT-R and 75 were administered the BVMT-R, which were examined for classification accuracy. The HVLT-R Recognition Discrimination Index and the BVMT-R Retention Percentage showed good to adequate discrimination with an area under the curve of .78 and .70, respectively. The HVLT-R Recognition Discrimination Index showed sensitivity of .53 with specificity of .93. The BVMT-R Retention Percentage demonstrated sensitivity of .31 with specificity of .92. When used in conjunction with other PVTs, these new embedded PVTs may be effective in the detection of invalid test data, although they are not intended for use in patients with dementia.

Prediction of Protein-Protein Interaction Sites with Machine-Learning-Based Data-Cleaning and Post-Filtering Procedures.

PubMed

Liu, Guang-Hui; Shen, Hong-Bin; Yu, Dong-Jun

2016-04-01

Accurately predicting protein-protein interaction sites (PPIs) is currently a hot topic because it has been demonstrated to be very useful for understanding disease mechanisms and designing drugs. Machine-learning-based computational approaches have been broadly utilized and demonstrated to be useful for PPI prediction. However, directly applying traditional machine learning algorithms, which often assume that samples in different classes are balanced, often leads to poor performance because of the severe class imbalance that exists in the PPI prediction problem. In this study, we propose a novel method for improving PPI prediction performance by relieving the severity of class imbalance using a data-cleaning procedure and reducing predicted false positives with a post-filtering procedure: First, a machine-learning-based data-cleaning procedure is applied to remove those marginal targets, which may potentially have a negative effect on training a model with a clear classification boundary, from the majority samples to relieve the severity of class imbalance in the original training dataset; then, a prediction model is trained on the cleaned dataset; finally, an effective post-filtering procedure is further used to reduce potential false positive predictions. Stringent cross-validation and independent validation tests on benchmark datasets demonstrated the efficacy of the proposed method, which exhibits highly competitive performance compared with existing state-of-the-art sequence-based PPIs predictors and should supplement existing PPI prediction methods.

A comparative study of machine learning methods for time-to-event survival data for radiomics risk modelling.

PubMed

Leger, Stefan; Zwanenburg, Alex; Pilz, Karoline; Lohaus, Fabian; Linge, Annett; Zöphel, Klaus; Kotzerke, Jörg; Schreiber, Andreas; Tinhofer, Inge; Budach, Volker; Sak, Ali; Stuschke, Martin; Balermpas, Panagiotis; Rödel, Claus; Ganswindt, Ute; Belka, Claus; Pigorsch, Steffi; Combs, Stephanie E; Mönnich, David; Zips, Daniel; Krause, Mechthild; Baumann, Michael; Troost, Esther G C; Löck, Steffen; Richter, Christian

2017-10-16

Radiomics applies machine learning algorithms to quantitative imaging data to characterise the tumour phenotype and predict clinical outcome. For the development of radiomics risk models, a variety of different algorithms is available and it is not clear which one gives optimal results. Therefore, we assessed the performance of 11 machine learning algorithms combined with 12 feature selection methods by the concordance index (C-Index), to predict loco-regional tumour control (LRC) and overall survival for patients with head and neck squamous cell carcinoma. The considered algorithms are able to deal with continuous time-to-event survival data. Feature selection and model building were performed on a multicentre cohort (213 patients) and validated using an independent cohort (80 patients). We found several combinations of machine learning algorithms and feature selection methods which achieve similar results, e.g. C-Index = 0.71 and BT-COX: C-Index = 0.70 in combination with Spearman feature selection. Using the best performing models, patients were stratified into groups of low and high risk of recurrence. Significant differences in LRC were obtained between both groups on the validation cohort. Based on the presented analysis, we identified a subset of algorithms which should be considered in future radiomics studies to develop stable and clinically relevant predictive models for time-to-event endpoints.

The R package "sperrorest" : Parallelized spatial error estimation and variable importance assessment for geospatial machine learning

NASA Astrophysics Data System (ADS)

Schratz, Patrick; Herrmann, Tobias; Brenning, Alexander

2017-04-01

Computational and statistical prediction methods such as the support vector machine have gained popularity in remote-sensing applications in recent years and are often compared to more traditional approaches like maximum-likelihood classification. However, the accuracy assessment of such predictive models in a spatial context needs to account for the presence of spatial autocorrelation in geospatial data by using spatial cross-validation and bootstrap strategies instead of their now more widely used non-spatial equivalent. The R package sperrorest by A. Brenning [IEEE International Geoscience and Remote Sensing Symposium, 1, 374 (2012)] provides a generic interface for performing (spatial) cross-validation of any statistical or machine-learning technique available in R. Since spatial statistical models as well as flexible machine-learning algorithms can be computationally expensive, parallel computing strategies are required to perform cross-validation efficiently. The most recent major release of sperrorest therefore comes with two new features (aside from improved documentation): The first one is the parallelized version of sperrorest(), parsperrorest(). This function features two parallel modes to greatly speed up cross-validation runs. Both parallel modes are platform independent and provide progress information. par.mode = 1 relies on the pbapply package and calls interactively (depending on the platform) parallel::mclapply() or parallel::parApply() in the background. While forking is used on Unix-Systems, Windows systems use a cluster approach for parallel execution. par.mode = 2 uses the foreach package to perform parallelization. This method uses a different way of cluster parallelization than the parallel package does. In summary, the robustness of parsperrorest() is increased with the implementation of two independent parallel modes. A new way of partitioning the data in sperrorest is provided by partition.factor.cv(). This function gives the user the possibility to perform cross-validation at the level of some grouping structure. As an example, in remote sensing of agricultural land uses, pixels from the same field contain nearly identical information and will thus be jointly placed in either the test set or the training set. Other spatial sampling resampling strategies are already available and can be extended by the user.

Validation of learning style measures: implications for medical education practice.

PubMed

Chapman, Dane M; Calhoun, Judith G

2006-06-01

It is unclear which learners would most benefit from the more individualised, student-structured, interactive approaches characteristic of problem-based and computer-assisted learning. The validity of learning style measures is uncertain, and there is no unifying learning style construct identified to predict such learners. This study was conducted to validate learning style constructs and to identify the learners most likely to benefit from problem-based and computer-assisted curricula. Using a cross-sectional design, 3 established learning style inventories were administered to 97 post-Year 2 medical students. Cognitive personality was measured by the Group Embedded Figures Test, information processing by the Learning Styles Inventory, and instructional preference by the Learning Preference Inventory. The 11 subscales from the 3 inventories were factor-analysed to identify common learning constructs and to verify construct validity. Concurrent validity was determined by intercorrelations of the 11 subscales. A total of 94 pre-clinical medical students completed all 3 inventories. Five meaningful learning style constructs were derived from the 11 subscales: student- versus teacher-structured learning; concrete versus abstract learning; passive versus active learning; individual versus group learning, and field-dependence versus field-independence. The concurrent validity of 10 of 11 subscales was supported by correlation analysis. Medical students most likely to thrive in a problem-based or computer-assisted learning environment would be expected to score highly on abstract, active and individual learning constructs and would be more field-independent. Learning style measures were validated in a medical student population and learning constructs were established for identifying learners who would most likely benefit from a problem-based or computer-assisted curriculum.

Cross-domain and multi-task transfer learning of deep convolutional neural network for breast cancer diagnosis in digital breast tomosynthesis

NASA Astrophysics Data System (ADS)

Samala, Ravi K.; Chan, Heang-Ping; Hadjiiski, Lubomir; Helvie, Mark A.; Richter, Caleb; Cha, Kenny

2018-02-01

We propose a cross-domain, multi-task transfer learning framework to transfer knowledge learned from non-medical images by a deep convolutional neural network (DCNN) to medical image recognition task while improving the generalization by multi-task learning of auxiliary tasks. A first stage cross-domain transfer learning was initiated from ImageNet trained DCNN to mammography trained DCNN. 19,632 regions-of-interest (ROI) from 2,454 mass lesions were collected from two imaging modalities: digitized-screen film mammography (SFM) and full-field digital mammography (DM), and split into training and test sets. In the multi-task transfer learning, the DCNN learned the mass classification task simultaneously from the training set of SFM and DM. The best transfer network for mammography was selected from three transfer networks with different number of convolutional layers frozen. The performance of single-task and multitask transfer learning on an independent SFM test set in terms of the area under the receiver operating characteristic curve (AUC) was 0.78+/-0.02 and 0.82+/-0.02, respectively. In the second stage cross-domain transfer learning, a set of 12,680 ROIs from 317 mass lesions on DBT were split into validation and independent test sets. We first studied the data requirements for the first stage mammography trained DCNN by varying the mammography training data from 1% to 100% and evaluated its learning on the DBT validation set in inference mode. We found that the entire available mammography set provided the best generalization. The DBT validation set was then used to train only the last four fully connected layers, resulting in an AUC of 0.90+/-0.04 on the independent DBT test set.

Validation of a structured training and assessment curriculum for technical skill acquisition in minimally invasive surgery: a randomized controlled trial.

PubMed

Palter, Vanessa N; Orzech, Neil; Reznick, Richard K; Grantcharov, Teodor P

2013-02-01

: To develop and validate an ex vivo comprehensive curriculum for a basic laparoscopic procedure. : Although simulators have been well validated as tools to teach technical skills, their integration into comprehensive curricula is lacking. Moreover, neither the effect of ex vivo training on learning curves in the operating room (OR), nor the effect on nontechnical proficiency has been investigated. : This randomized single-blinded prospective trial allocated 20 surgical trainees to a structured training and assessment curriculum (STAC) group or conventional residency training. The STAC consisted of case-based learning, proficiency-based virtual reality training, laparoscopic box training, and OR participation. After completion of the intervention, all participants performed 5 sequential laparoscopic cholecystectomies in the OR. The primary outcome measure was the difference in technical performance between the 2 groups during the first laparoscopic cholecystectomy. Secondary outcome measures included differences with respect to learning curves in the OR, technical proficiency of each sequential laparoscopic cholecystectomy, and nontechnical skills. : Residents in the STAC group outperformed residents in the conventional group in the first (P = 0.004), second (P = 0.036), third (P = 0.021), and fourth (P = 0.023) laparoscopic cholecystectomies. The conventional group demonstrated a significant learning curve in the OR (P = 0.015) in contrast to the STAC group (P = 0.032). Residents in the STAC group also had significantly higher nontechnical skills (P = 0.027). : Participating in the STAC shifted the learning curve for a basic laparoscopic procedure from the operating room into the simulation laboratory. STAC-trained residents had superior technical proficiency in the OR and nontechnical skills compared with conventionally trained residents. (The study registration ID is NCT01560494.).

The Validity of Value-Added Estimates from Low-Stakes Testing Contexts: The Impact of Change in Test-Taking Motivation and Test Consequences

ERIC Educational Resources Information Center

Finney, Sara J.; Sundre, Donna L.; Swain, Matthew S.; Williams, Laura M.

2016-01-01

Accountability mandates often prompt assessment of student learning gains (e.g., value-added estimates) via achievement tests. The validity of these estimates have been questioned when performance on tests is low stakes for students. To assess the effects of motivation on value-added estimates, we assigned students to one of three test consequence…

SSME fault monitoring and diagnosis expert system

NASA Technical Reports Server (NTRS)

Ali, Moonis; Norman, Arnold M.; Gupta, U. K.

1989-01-01

An expert system, called LEADER, has been designed and implemented for automatic learning, detection, identification, verification, and correction of anomalous propulsion system operations in real time. LEADER employs a set of sensors to monitor engine component performance and to detect, identify, and validate abnormalities with respect to varying engine dynamics and behavior. Two diagnostic approaches are adopted in the architecture of LEADER. In the first approach fault diagnosis is performed through learning and identifying engine behavior patterns. LEADER, utilizing this approach, generates few hypotheses about the possible abnormalities. These hypotheses are then validated based on the SSME design and functional knowledge. The second approach directs the processing of engine sensory data and performs reasoning based on the SSME design, functional knowledge, and the deep-level knowledge, i.e., the first principles (physics and mechanics) of SSME subsystems and components. This paper describes LEADER's architecture which integrates a design based reasoning approach with neural network-based fault pattern matching techniques. The fault diagnosis results obtained through the analyses of SSME ground test data are presented and discussed.

The Benefits of Peer Review and a Multisemester Capstone Writing Series on Inquiry and Analysis Skills in an Undergraduate Thesis

ERIC Educational Resources Information Center

Weaver, K. F.; Morales, V.; Nelson, M.; Weaver, P. F.; Toledo, A.; Godde, K.

2016-01-01

This study examines the relationship between the introduction of a four-course writing-intensive capstone series and improvement in inquiry and analysis skills of biology senior undergraduates. To measure the impact of the multicourse write-to-learn and peer-review pedagogy on student performance, we used a modified Valid Assessment of Learning in…

Separating the Signal from the Noise: An Examination of Student and Teacher Scores Based on Student Learning Objectives (SLOs) in One State

ERIC Educational Resources Information Center

Buckley, Katie Hills

2015-01-01

Despite the prevalence of student learning objectives (SLOs) in teacher evaluation systems throughout the United States, research on the validity of student and teacher SLO scores used for high-stakes decisions is lacking. For this reason, this dissertation is comprised of two chapters that examine student and teacher-level SLO performance data…

Redefining "Learning" in Statistical Learning: What Does an Online Measure Reveal About the Assimilation of Visual Regularities?

PubMed

Siegelman, Noam; Bogaerts, Louisa; Kronenfeld, Ofer; Frost, Ram

2017-10-07

From a theoretical perspective, most discussions of statistical learning (SL) have focused on the possible "statistical" properties that are the object of learning. Much less attention has been given to defining what "learning" is in the context of "statistical learning." One major difficulty is that SL research has been monitoring participants' performance in laboratory settings with a strikingly narrow set of tasks, where learning is typically assessed offline, through a set of two-alternative-forced-choice questions, which follow a brief visual or auditory familiarization stream. Is that all there is to characterizing SL abilities? Here we adopt a novel perspective for investigating the processing of regularities in the visual modality. By tracking online performance in a self-paced SL paradigm, we focus on the trajectory of learning. In a set of three experiments we show that this paradigm provides a reliable and valid signature of SL performance, and it offers important insights for understanding how statistical regularities are perceived and assimilated in the visual modality. This demonstrates the promise of integrating different operational measures to our theory of SL. © 2017 Cognitive Science Society, Inc.

Online Feature Transformation Learning for Cross-Domain Object Category Recognition.

PubMed

Zhang, Xuesong; Zhuang, Yan; Wang, Wei; Pedrycz, Witold

2017-06-09

In this paper, we introduce a new research problem termed online feature transformation learning in the context of multiclass object category recognition. The learning of a feature transformation is viewed as learning a global similarity metric function in an online manner. We first consider the problem of online learning a feature transformation matrix expressed in the original feature space and propose an online passive aggressive feature transformation algorithm. Then these original features are mapped to kernel space and an online single kernel feature transformation (OSKFT) algorithm is developed to learn a nonlinear feature transformation. Based on the OSKFT and the existing Hedge algorithm, a novel online multiple kernel feature transformation algorithm is also proposed, which can further improve the performance of online feature transformation learning in large-scale application. The classifier is trained with k nearest neighbor algorithm together with the learned similarity metric function. Finally, we experimentally examined the effect of setting different parameter values in the proposed algorithms and evaluate the model performance on several multiclass object recognition data sets. The experimental results demonstrate the validity and good performance of our methods on cross-domain and multiclass object recognition application.

Design and Validation of MAPS for Educators: A Performance Support System to Guide Media Selection for Lesson Design

ERIC Educational Resources Information Center

Hung, Wei-Chen; Kalota, Faisal

2013-01-01

The importance of adopting technology-supported performance systems for on-the-job learning and training is well-recognized in a networked economy. In this study, we present a performance support system (PSS) designed to support technology integration for lesson design. The goal is to support educators in the development of appropriate and…

Multidimensional assessment of homework: an analysis of students with ADHD.

PubMed

Mautone, Jennifer A; Marshall, Stephen A; Costigan, Tracy E; Clarke, Angela T; Power, Thomas J

2012-10-01

Homework can have beneficial effects for students; however, it presents challenges, particularly for students with attention problems. Although effective homework interventions exist, intervention development and evaluation has been hampered by the lack of psychometrically sound measures. The primary purpose of this study was to evaluate the construct validity of the Homework Performance Questionnaire (HPQ), Parent and Teacher Versions, in a sample of children with ADHD. A secondary purpose was to examine variations in homework performance as a function of individual characteristics, such as academic achievement, quality of the family-school relationship, and child's diagnostic status. The sample included 91 children (34% female) with ADHD in Grades 2 to 6. Measures included parent and teacher ratings of homework performance and the quality of the parent-teacher relationship as well as direct assessment of child academic achievement and homework performance (i.e., samples of completed assignments). Correlational analyses were used to examine construct validity, and ANOVAs were used to evaluate group differences. Each factor of the HPQ had a significant relationship with other measures of relevant constructs. There were no significant differences in homework performance between groups for ADHD subtype, medication status, or comorbidity, with the exception of learning disability. Children with ADHD and learning disabilities had significantly lower teacher ratings of academic competence. Results of the present study suggest that HPQ scores may be used to make valid inferences about the homework performance of children with attention problems. These rating scales may be helpful in progress monitoring and evaluating intervention effectiveness.

Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies.

PubMed

Hansen, Katja; Montavon, Grégoire; Biegler, Franziska; Fazli, Siamac; Rupp, Matthias; Scheffler, Matthias; von Lilienfeld, O Anatole; Tkatchenko, Alexandre; Müller, Klaus-Robert

2013-08-13

The accurate and reliable prediction of properties of molecules typically requires computationally intensive quantum-chemical calculations. Recently, machine learning techniques applied to ab initio calculations have been proposed as an efficient approach for describing the energies of molecules in their given ground-state structure throughout chemical compound space (Rupp et al. Phys. Rev. Lett. 2012, 108, 058301). In this paper we outline a number of established machine learning techniques and investigate the influence of the molecular representation on the methods performance. The best methods achieve prediction errors of 3 kcal/mol for the atomization energies of a wide variety of molecules. Rationales for this performance improvement are given together with pitfalls and challenges when applying machine learning approaches to the prediction of quantum-mechanical observables.

Development of models for classification of action between heat-clearing herbs and blood-activating stasis-resolving herbs based on theory of traditional Chinese medicine.

PubMed

Chen, Zhao; Cao, Yanfeng; He, Shuaibing; Qiao, Yanjiang

2018-01-01

Action (" gongxiao " in Chinese) of traditional Chinese medicine (TCM) is the high recapitulation for therapeutic and health-preserving effects under the guidance of TCM theory. TCM-defined herbal properties (" yaoxing " in Chinese) had been used in this research. TCM herbal property (TCM-HP) is the high generalization and summary for actions, both of which come from long-term effective clinical practice in two thousands of years in China. However, the specific relationship between TCM-HP and action of TCM is complex and unclear from a scientific perspective. The research about this is conducive to expound the connotation of TCM-HP theory and is of important significance for the development of the TCM-HP theory. One hundred and thirty-three herbs including 88 heat-clearing herbs (HCHs) and 45 blood-activating stasis-resolving herbs (BAHRHs) were collected from reputable TCM literatures, and their corresponding TCM-HPs/actions information were collected from Chinese pharmacopoeia (2015 edition). The Kennard-Stone (K-S) algorithm was used to split 133 herbs into 100 calibration samples and 33 validation samples. Then, machine learning methods including supported vector machine (SVM), k-nearest neighbor (kNN) and deep learning methods including deep belief network (DBN), convolutional neutral network (CNN) were adopted to develop action classification models based on TCM-HP theory, respectively. In order to ensure robustness, these four classification methods were evaluated by using the method of tenfold cross validation and 20 external validation samples for prediction. As results, 72.7-100% of 33 validation samples including 17 HCHs and 16 BASRHs were correctly predicted by these four types of methods. Both of the DBN and CNN methods gave out the best results and their sensitivity, specificity, precision, accuracy were all 100.00%. Especially, the predicted results of external validation set showed that the performance of deep learning methods (DBN, CNN) were better than traditional machine learning methods (kNN, SVM) in terms of their sensitivity, specificity, precision, accuracy. Moreover, the distribution patterns of TCM-HPs of HCHs and BASRHs were also analyzed to detect the featured TCM-HPs of these two types of herbs. The result showed that the featured TCM-HPs of HCHs were cold, bitter, liver and stomach meridians entered, while those of BASRHs were warm, bitter and pungent, liver meridian entered. The performance on validation set and external validation set of deep learning methods (DBN, CNN) were better than machine learning models (kNN, SVM) in sensitivity, specificity, precision, accuracy when predicting the actions of heat-clearing and blood-activating stasis-resolving based on TCM-HP theory. The deep learning classification methods owned better generalization ability and accuracy when predicting the actions of heat-clearing and blood-activating stasis-resolving based on TCM-HP theory. Besides, the methods of deep learning would help us to improve our understanding about the relationship between herbal property and action, as well as to enrich and develop the theory of TCM-HP scientifically.

A cross-validation package driving Netica with python

USGS Publications Warehouse

Fienen, Michael N.; Plant, Nathaniel G.

2014-01-01

Bayesian networks (BNs) are powerful tools for probabilistically simulating natural systems and emulating process models. Cross validation is a technique to avoid overfitting resulting from overly complex BNs. Overfitting reduces predictive skill. Cross-validation for BNs is known but rarely implemented due partly to a lack of software tools designed to work with available BN packages. CVNetica is open-source, written in Python, and extends the Netica software package to perform cross-validation and read, rebuild, and learn BNs from data. Insights gained from cross-validation and implications on prediction versus description are illustrated with: a data-driven oceanographic application; and a model-emulation application. These examples show that overfitting occurs when BNs become more complex than allowed by supporting data and overfitting incurs computational costs as well as causing a reduction in prediction skill. CVNetica evaluates overfitting using several complexity metrics (we used level of discretization) and its impact on performance metrics (we used skill).

The Relationship Between Fidelity and Learning in Aviation Training and Assessment

NASA Technical Reports Server (NTRS)

Noble, Cliff

2002-01-01

Flight simulators can be designed to train pilots or assess their flight performance. Low-Fidelity simulators maximize the initial learning rate of novice pilots and minimize initial costs; whereas, expensive, high-fidelity simulators predict the realworld in-flight performance of expert pilots (Fink & Shriver, 1978 Hays & Singer 1989; Kinkade & Wheaton. 1972). Although intuitively appealing and intellectually convenient to generalize concepts of learning and assessment, what holds true for the role of fidelity in assessment may not always hold true for learning, and vice versa. To bring clarity to this issue, the author distinguishes the role of fidelity in learning from its role in assessment as a function of skill level by applying the hypothesis of Alessi (1988) and reviewing the Laughery, Ditzian, and Houtman (1982) study on simulator validity. Alessi hypothesized that there is it point beyond which one additional unit of flight-simulator fidelity results in a diminished rate of learning. The author of this current paper also suggests the existence of an optimal point beyond which one additional unit of flight-simulator fidelity results in a diminished rate of practical assessment of nonexpert pilot performance.

Development of Learning Models Based on Problem Solving and Meaningful Learning Standards by Expert Validity for Animal Development Course

NASA Astrophysics Data System (ADS)

Lufri, L.; Fitri, R.; Yogica, R.

2018-04-01

The purpose of this study is to produce a learning model based on problem solving and meaningful learning standards by expert assessment or validation for the course of Animal Development. This research is a development research that produce the product in the form of learning model, which consist of sub product, namely: the syntax of learning model and student worksheets. All of these products are standardized through expert validation. The research data is the level of validity of all sub products obtained using questionnaire, filled by validators from various field of expertise (field of study, learning strategy, Bahasa). Data were analysed using descriptive statistics. The result of the research shows that the problem solving and meaningful learning model has been produced. Sub products declared appropriate by expert include the syntax of learning model and student worksheet.

Automated pixel-wise brain tissue segmentation of diffusion-weighted images via machine learning.

PubMed

Ciritsis, Alexander; Boss, Andreas; Rossi, Cristina

2018-04-26

The diffusion-weighted (DW) MR signal sampled over a wide range of b-values potentially allows for tissue differentiation in terms of cellularity, microstructure, perfusion, and T 2 relaxivity. This study aimed to implement a machine learning algorithm for automatic brain tissue segmentation from DW-MRI datasets, and to determine the optimal sub-set of features for accurate segmentation. DWI was performed at 3 T in eight healthy volunteers using 15 b-values and 20 diffusion-encoding directions. The pixel-wise signal attenuation, as well as the trace and fractional anisotropy (FA) of the diffusion tensor, were used as features to train a support vector machine classifier for gray matter, white matter, and cerebrospinal fluid classes. The datasets of two volunteers were used for validation. For each subject, tissue classification was also performed on 3D T 1 -weighted data sets with a probabilistic framework. Confusion matrices were generated for quantitative assessment of image classification accuracy in comparison with the reference method. DWI-based tissue segmentation resulted in an accuracy of 82.1% on the validation dataset and of 82.2% on the training dataset, excluding relevant model over-fitting. A mean Dice coefficient (DSC) of 0.79 ± 0.08 was found. About 50% of the classification performance was attributable to five features (i.e. signal measured at b-values of 5/10/500/1200 s/mm 2 and the FA). This reduced set of features led to almost identical performances for the validation (82.2%) and the training (81.4%) datasets (DSC = 0.79 ± 0.08). Machine learning techniques applied to DWI data allow for accurate brain tissue segmentation based on both morphological and functional information. Copyright © 2018 John Wiley & Sons, Ltd.

Values taught, values learned, attitude and performance in mathematics

NASA Astrophysics Data System (ADS)

Limbaco, K. S. A.

2015-03-01

The purpose of the study was to identify, describe and find the relationship among values taught, values learned, attitude and performance in mathematics. The researcher used descriptive-correlational method of research to gather information and to describe the nature of situation. The following instruments were used in this study: Math Attitude Inventory, Inventory of Values Taught and Learned which were content validated by experts in the field of Mathematics, Values and Education. Generally, most of the values were taught by the teachers. All of the values were learned by the students. The following got the highest mean ratings for values taught: moral strength, sharing, charity, valuing life, love of God, truth and honesty, reason, alternativism and articulation. The following got highest mean ratings for values learned: patience/tolerance, sharing, charity, valuing life, faith, love of God, truth and honesty, analogical thinking, confidence and individual liberty. Majority of the respondents have moderately positive attitude towards mathematics. Positive statements in the Mathematics Attitude Inventory are "Generally true" while negative statements are "Neutral." In conclusion, values were taught by mathematics teacher, thus, learned by the students. Therefore, mathematics is very much related to life. Values can be learned and strengthened through mathematics; there is a significant relationship between values taught by the teachers and values learned by the students and attitude towards mathematics and performance in mathematics; values taught does not affect attitude towards mathematics and performance in mathematics. A student may have a positive attitude towards mathematics or have an exemplary performance in mathematics even if the mathematics teacher did not teach values; values learned does not affect attitude towards mathematics and performance in mathematics. A student may have a positive attitude towards mathematics or have an exemplary performance in mathematics even he/she did not learned values in his/her mathematics class.

A Novel Local Learning based Approach With Application to Breast Cancer Diagnosis

DOE Office of Scientific and Technical Information (OSTI.GOV)

Xu, Songhua; Tourassi, Georgia

2012-01-01

The purpose of this study is to develop and evaluate a novel local learning-based approach for computer-assisted diagnosis of breast cancer. Our new local learning based algorithm using the linear logistic regression method as its base learner is described. Overall, our algorithm will perform its stochastic searching process until the total allowed computing time is used up by our random walk process in identifying the most suitable population subdivision scheme and their corresponding individual base learners. The proposed local learning-based approach was applied for the prediction of breast cancer given 11 mammographic and clinical findings reported by physicians using themore » BI-RADS lexicon. Our database consisted of 850 patients with biopsy confirmed diagnosis (290 malignant and 560 benign). We also compared the performance of our method with a collection of publicly available state-of-the-art machine learning methods. Predictive performance for all classifiers was evaluated using 10-fold cross validation and Receiver Operating Characteristics (ROC) analysis. Figure 1 reports the performance of 54 machine learning methods implemented in the machine learning toolkit Weka (version 3.0). We introduced a novel local learning-based classifier and compared it with an extensive list of other classifiers for the problem of breast cancer diagnosis. Our experiments show that the algorithm superior prediction performance outperforming a wide range of other well established machine learning techniques. Our conclusion complements the existing understanding in the machine learning field that local learning may capture complicated, non-linear relationships exhibited by real-world datasets.« less

Clinical validation of the NANDA-I diagnosis of impaired memory in elderly patients.

PubMed

Montoril, Michelle H; Lopes, Marcos Venícios O; Santana, Rosimere F; Sousa, Vanessa Emille C; Carvalho, Priscilla Magalhães O; Diniz, Camila M; Alves, Naiana P; Ferreira, Gabriele L; Fróes, Nathaly Bianka M; Menezes, Angélica P

2016-05-01

The aim of this study was to perform a clinical validation of the defining characteristics of impaired memory (IM) in elderly patients at a long-term care institution. A sample of 123 elderly patients was evaluated with a questionnaire designed to identify IM according to the NANDA-I taxonomy. Accuracy measures were calculated for the total sample and for males and females separately. Sensitivity and specificity values indicated that: (1) inability to learn new skills is useful in screening IM, and (2) forgets to perform a behavior at a scheduled time, forgetfulness, inability to learn new information, inability to recall events, and inability to recall factual information are confirmatory indicators. Specific factors can affect the manifestation of IM by elderly patients. The results may be useful in improving diagnostic accuracy and efficiency of the IM nursing diagnosis. Copyright © 2015 Elsevier Inc. All rights reserved.

Test validity and performance validity: considerations in providing a framework for development of an ability-focused neuropsychological test battery.

PubMed

Larrabee, Glenn J

2014-11-01

Literature on test validity and performance validity is reviewed to propose a framework for specification of an ability-focused battery (AFB). Factor analysis supports six domains of ability: first, verbal symbolic; secondly, visuoperceptual and visuospatial judgment and problem solving; thirdly, sensorimotor skills; fourthly, attention/working memory; fifthly, processing speed; finally, learning and memory (which can be divided into verbal and visual subdomains). The AFB should include at least three measures for each of the six domains, selected based on various criteria for validity including sensitivity to presence of disorder, sensitivity to severity of disorder, correlation with important activities of daily living, and containing embedded/derived measures of performance validity. Criterion groups should include moderate and severe traumatic brain injury, and Alzheimer's disease. Validation groups should also include patients with left and right hemisphere stroke, to determine measures sensitive to lateralized cognitive impairment and so that the moderating effects of auditory comprehension impairment and neglect can be analyzed on AFB measures. © The Author 2014. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

EEG-neurofeedback for optimising performance. II: creativity, the performing arts and ecological validity.

PubMed

Gruzelier, John H

2014-07-01

As a continuation of a review of evidence of the validity of cognitive/affective gains following neurofeedback in healthy participants, including correlations in support of the gains being mediated by feedback learning (Gruzelier, 2014a), the focus here is on the impact on creativity, especially in the performing arts including music, dance and acting. The majority of research involves alpha/theta (A/T), sensory-motor rhythm (SMR) and heart rate variability (HRV) protocols. There is evidence of reliable benefits from A/T training with advanced musicians especially for creative performance, and reliable benefits from both A/T and SMR training for novice music performance in adults and in a school study with children with impact on creativity, communication/presentation and technique. Making the SMR ratio training context ecologically relevant for actors enhanced creativity in stage performance, with added benefits from the more immersive training context. A/T and HRV training have benefitted dancers. The neurofeedback evidence adds to the rapidly accumulating validation of neurofeedback, while performing arts studies offer an opportunity for ecological validity in creativity research for both creative process and product. Copyright © 2013 Elsevier Ltd. All rights reserved.

Novel-word learning deficits in Mandarin-speaking preschool children with specific language impairments.

PubMed

Chen, Yuchun; Liu, Huei-Mei

2014-01-01

Children with SLI exhibit overall deficits in novel word learning compared to their age-matched peers. However, the manifestation of the word learning difficulty in SLI was not consistent across tasks and the factors affecting the learning performance were not yet determined. Our aim is to examine the extent of word learning difficulties in Mandarin-speaking preschool children with SLI, and to explore the potent influence of existing lexical knowledge on to the word learning process. Preschool children with SLI (n=37) and typical language development (n=33) were exposed to novel words for unfamiliar objects embedded in stories. Word learning tasks including the initial mapping and short-term repetitive learning were designed. Results revealed that Mandarin-speaking preschool children with SLI performed as well as their age-peers in the initial form-meaning mapping task. Their word learning difficulty was only evidently shown in the short-term repetitive learning task under a production demand, and their learning speed was slower than the control group. Children with SLI learned the novel words with a semantic head better in both the initial mapping and repetitive learning tasks. Moderate correlations between stand word learning performances and scores on standardized vocabulary were found after controlling for children's age and nonverbal IQ. The results suggested that the word learning difficulty in children with SLI occurred in the process of establishing a robust phonological representation at the beginning stage of word learning. Also, implicit compound knowledge is applied to aid word learning process for children with and without SLI. We also provide the empirical data to validate the relationship between preschool children's word learning performance and their existing receptive vocabulary ability. Copyright © 2013 Elsevier Ltd. All rights reserved.

Validation of the NASA-TLX Score in Ongoing Assessment of Mental Workload During a Laparoscopic Learning Curve in Bariatric Surgery.

PubMed

Ruiz-Rabelo, Juan Francisco; Navarro-Rodriguez, Elena; Di-Stasi, Leandro Luigi; Diaz-Jimenez, Nelida; Cabrera-Bermon, Juan; Diaz-Iglesias, Carlos; Gomez-Alvarez, Manuel; Briceño-Delgado, Javier

2015-12-01

Fatigue and mental workload are directly associated with high-complexity tasks. In general, difficult tasks produce a higher mental workload, leaving little opportunity to deal with new/unexpected events and increasing the likelihood of performance errors. The laparoscopic Roux-en-Y gastric bypass (LRYGB) learning curve is considered to be one of the most difficult to complete in laparoscopic surgery. We wished to validate the National Aeronautics and Space Administration Task Load Index (NASA-TLX) in LRYGB and identify factors that could provoke a higher mental workload for surgeons during the learning curve. A single surgeon was enrolled to undertake 70 consecutive LRYGB procedures with two internal surgeons mentoring the first 35 cases. Patients were consecutive and ranked from case 35 to case 105 according to the date of the surgical procedure ("case rank"). Self-ratings of satisfaction, performance, and fatigue were measured at the end of surgery using a validated NASA-TLX questionnaire. The procedure was recorded for later viewing by two external evaluators. General data for patients and surgical variables were collected prospectively. A moderate correlation between the NASA-TLX score, BMI, operative time, and volumes of blood drainage was observed. There was no correlation between the NASA-TLX score and duration of hospital stay or time of drain removal. BMI ≥50 kg/m(2), male sex, inexperienced first assistant, and type 2 diabetes mellitus were identified as independent predictive factors of a higher NASA-TLX score. The NASA-TLX is a valid tool to gauge mental workload in LRYGB.

Measuring strategies for learning regulation in medical education: scale reliability and dimensionality in a Swedish sample.

PubMed

Edelbring, Samuel

2012-08-15

The degree of learners' self-regulated learning and dependence on external regulation influence learning processes in higher education. These regulation strategies are commonly measured by questionnaires developed in other settings than in which they are being used, thereby requiring renewed validation. The aim of this study was to psychometrically evaluate the learning regulation strategy scales from the Inventory of Learning Styles with Swedish medical students (N = 206). The regulation scales were evaluated regarding their reliability, scale dimensionality and interrelations. The primary evaluation focused on dimensionality and was performed with Mokken scale analysis. To assist future scale refinement, additional item analysis, such as item-to-scale correlations, was performed. Scale scores in the Swedish sample displayed good reliability in relation to published results: Cronbach's alpha: 0.82, 0.72, and 0.65 for self-regulation, external regulation and lack of regulation scales respectively. The dimensionalities in scales were adequate for self-regulation and its subscales, whereas external regulation and lack of regulation displayed less unidimensionality. The established theoretical scales were largely replicated in the exploratory analysis. The item analysis identified two items that contributed little to their respective scales. The results indicate that these scales have an adequate capacity for detecting the three theoretically proposed learning regulation strategies in the medical education sample. Further construct validity should be sought by interpreting scale scores in relation to specific learning activities. Using established scales for measuring students' regulation strategies enables a broad empirical base for increasing knowledge on regulation strategies in relation to different disciplinary settings and contributes to theoretical development.

Consensus on Quality Indicators of Postgraduate Medical E-Learning: Delphi Study

PubMed Central

Walsh, Kieran; Westerman, Michiel; Scheele, Fedde

2018-01-01

Background The progressive use of e-learning in postgraduate medical education calls for useful quality indicators. Many evaluation tools exist. However, these are diversely used and their empirical foundation is often lacking. Objective We aimed to identify an empirically founded set of quality indicators to set the bar for “good enough” e-learning. Methods We performed a Delphi procedure with a group of 13 international education experts and 10 experienced users of e-learning. The questionnaire started with 57 items. These items were the result of a previous literature review and focus group study performed with experts and users. Consensus was met when a rate of agreement of more than two-thirds was achieved. Results In the first round, the participants accepted 37 items of the 57 as important, reached no consensus on 20, and added 15 new items. In the second round, we added the comments from the first round to the items on which there was no consensus and added the 15 new items. After this round, a total of 72 items were addressed and, of these, 37 items were accepted and 34 were rejected due to lack of consensus. Conclusions This study produced a list of 37 items that can form the basis of an evaluation tool to evaluate postgraduate medical e-learning. This is, to our knowledge, the first time that quality indicators for postgraduate medical e-learning have been defined and validated. The next step is to create and validate an e-learning evaluation tool from these items. PMID:29699970

Normal tissue complication probability (NTCP) modelling using spatial dose metrics and machine learning methods for severe acute oral mucositis resulting from head and neck radiotherapy.

PubMed

Dean, Jamie A; Wong, Kee H; Welsh, Liam C; Jones, Ann-Britt; Schick, Ulrike; Newbold, Kate L; Bhide, Shreerang A; Harrington, Kevin J; Nutting, Christopher M; Gulliford, Sarah L

2016-07-01

Severe acute mucositis commonly results from head and neck (chemo)radiotherapy. A predictive model of mucositis could guide clinical decision-making and inform treatment planning. We aimed to generate such a model using spatial dose metrics and machine learning. Predictive models of severe acute mucositis were generated using radiotherapy dose (dose-volume and spatial dose metrics) and clinical data. Penalised logistic regression, support vector classification and random forest classification (RFC) models were generated and compared. Internal validation was performed (with 100-iteration cross-validation), using multiple metrics, including area under the receiver operating characteristic curve (AUC) and calibration slope, to assess performance. Associations between covariates and severe mucositis were explored using the models. The dose-volume-based models (standard) performed equally to those incorporating spatial information. Discrimination was similar between models, but the RFCstandard had the best calibration. The mean AUC and calibration slope for this model were 0.71 (s.d.=0.09) and 3.9 (s.d.=2.2), respectively. The volumes of oral cavity receiving intermediate and high doses were associated with severe mucositis. The RFCstandard model performance is modest-to-good, but should be improved, and requires external validation. Reducing the volumes of oral cavity receiving intermediate and high doses may reduce mucositis incidence. Copyright © 2016 The Author(s). Published by Elsevier Ireland Ltd.. All rights reserved.

Young Children's Understanding of Teaching and Learning and Their Theory of Mind Development: A Causal Analysis from a Cross-Cultural Perspective

PubMed Central

Wang, Zhenlin; Wang, X. Christine; Chui, Wai Yip

2017-01-01

Children's understanding of the concepts of teaching and learning is closely associated with their theory of mind (ToM) ability and vital for school readiness. This study aimed to develop and validate a Preschool Teaching and Learning Comprehension Index (PTLCI) across cultures and examine the causal relationship between children's comprehension of teaching and learning and their mental state understanding. Two hundred and twelve children from 3 to 6 years of age from Hong Kong and the United States participated in study. The results suggested strong construct validity of the PTLCI, and its measurement and structural equivalence within and across cultures. ToM and PTLCI were significantly correlated with a medium effect size, even after controlling for age, and language ability. Hong Kong children outperformed their American counterparts in both ToM and PTLCI. Competing structural equation models suggested that children's performance on the PTLCI causally predicted their ToM across countries. PMID:28559863

Sub-processes of motor learning revealed by a robotic manipulandum for rodents.

PubMed

Lambercy, O; Schubring-Giese, M; Vigaru, B; Gassert, R; Luft, A R; Hosp, J A

2015-02-01

Rodent models are widely used to investigate neural changes in response to motor learning. Usually, the behavioral readout of motor learning tasks used for this purpose is restricted to a binary measure of performance (i.e. "successful" movement vs. "failure"). Thus, the assignability of research in rodents to concepts gained in human research - implying diverse internal models that constitute motor learning - is still limited. To solve this problem, we recently introduced a three-degree-of-freedom robotic platform designed for rats (the ETH-Pattus) that combines an accurate behavioral readout (in the form of kinematics) with the possibility to invasively assess learning related changes within the brain (e.g. by performing immunohistochemistry or electrophysiology in acute slice preparations). Here, we validate this platform as a tool to study motor learning by establishing two forelimb-reaching paradigms that differ in degree of skill. Both conditions can be precisely differentiated in terms of their temporal pattern and performance levels. Based on behavioral data, we hypothesize the presence of several sub-processes contributing to motor learning. These share close similarities with concepts gained in humans or primates. Copyright © 2014 Elsevier B.V. All rights reserved.

Cooperative Learning: Improving University Instruction by Basing Practice on Validated Theory

ERIC Educational Resources Information Center

Johnson, David W.; Johnson, Roger T.; Smith, Karl A.

2014-01-01

Cooperative learning is an example of how theory validated by research may be applied to instructional practice. The major theoretical base for cooperative learning is social interdependence theory. It provides clear definitions of cooperative, competitive, and individualistic learning. Hundreds of research studies have validated its basic…

Probability machines: consistent probability estimation using nonparametric learning machines.

PubMed

Malley, J D; Kruppa, J; Dasgupta, A; Malley, K G; Ziegler, A

2012-01-01

Most machine learning approaches only provide a classification for binary responses. However, probabilities are required for risk estimation using individual patient characteristics. It has been shown recently that every statistical learning machine known to be consistent for a nonparametric regression problem is a probability machine that is provably consistent for this estimation problem. The aim of this paper is to show how random forests and nearest neighbors can be used for consistent estimation of individual probabilities. Two random forest algorithms and two nearest neighbor algorithms are described in detail for estimation of individual probabilities. We discuss the consistency of random forests, nearest neighbors and other learning machines in detail. We conduct a simulation study to illustrate the validity of the methods. We exemplify the algorithms by analyzing two well-known data sets on the diagnosis of appendicitis and the diagnosis of diabetes in Pima Indians. Simulations demonstrate the validity of the method. With the real data application, we show the accuracy and practicality of this approach. We provide sample code from R packages in which the probability estimation is already available. This means that all calculations can be performed using existing software. Random forest algorithms as well as nearest neighbor approaches are valid machine learning methods for estimating individual probabilities for binary responses. Freely available implementations are available in R and may be used for applications.

A closer look at cross-validation for assessing the accuracy of gene regulatory networks and models.

PubMed

Tabe-Bordbar, Shayan; Emad, Amin; Zhao, Sihai Dave; Sinha, Saurabh

2018-04-26

Cross-validation (CV) is a technique to assess the generalizability of a model to unseen data. This technique relies on assumptions that may not be satisfied when studying genomics datasets. For example, random CV (RCV) assumes that a randomly selected set of samples, the test set, well represents unseen data. This assumption doesn't hold true where samples are obtained from different experimental conditions, and the goal is to learn regulatory relationships among the genes that generalize beyond the observed conditions. In this study, we investigated how the CV procedure affects the assessment of supervised learning methods used to learn gene regulatory networks (or in other applications). We compared the performance of a regression-based method for gene expression prediction estimated using RCV with that estimated using a clustering-based CV (CCV) procedure. Our analysis illustrates that RCV can produce over-optimistic estimates of the model's generalizability compared to CCV. Next, we defined the 'distinctness' of test set from training set and showed that this measure is predictive of performance of the regression method. Finally, we introduced a simulated annealing method to construct partitions with gradually increasing distinctness and showed that performance of different gene expression prediction methods can be better evaluated using this method.

Enabling multi-level relevance feedback on PubMed by integrating rank learning into DBMS.

PubMed

Yu, Hwanjo; Kim, Taehoon; Oh, Jinoh; Ko, Ilhwan; Kim, Sungchul; Han, Wook-Shin

2010-04-16

Finding relevant articles from PubMed is challenging because it is hard to express the user's specific intention in the given query interface, and a keyword query typically retrieves a large number of results. Researchers have applied machine learning techniques to find relevant articles by ranking the articles according to the learned relevance function. However, the process of learning and ranking is usually done offline without integrated with the keyword queries, and the users have to provide a large amount of training documents to get a reasonable learning accuracy. This paper proposes a novel multi-level relevance feedback system for PubMed, called RefMed, which supports both ad-hoc keyword queries and a multi-level relevance feedback in real time on PubMed. RefMed supports a multi-level relevance feedback by using the RankSVM as the learning method, and thus it achieves higher accuracy with less feedback. RefMed "tightly" integrates the RankSVM into RDBMS to support both keyword queries and the multi-level relevance feedback in real time; the tight coupling of the RankSVM and DBMS substantially improves the processing time. An efficient parameter selection method for the RankSVM is also proposed, which tunes the RankSVM parameter without performing validation. Thereby, RefMed achieves a high learning accuracy in real time without performing a validation process. RefMed is accessible at http://dm.postech.ac.kr/refmed. RefMed is the first multi-level relevance feedback system for PubMed, which achieves a high accuracy with less feedback. It effectively learns an accurate relevance function from the user's feedback and efficiently processes the function to return relevant articles in real time.

Enabling multi-level relevance feedback on PubMed by integrating rank learning into DBMS

PubMed Central

2010-01-01

Background Finding relevant articles from PubMed is challenging because it is hard to express the user's specific intention in the given query interface, and a keyword query typically retrieves a large number of results. Researchers have applied machine learning techniques to find relevant articles by ranking the articles according to the learned relevance function. However, the process of learning and ranking is usually done offline without integrated with the keyword queries, and the users have to provide a large amount of training documents to get a reasonable learning accuracy. This paper proposes a novel multi-level relevance feedback system for PubMed, called RefMed, which supports both ad-hoc keyword queries and a multi-level relevance feedback in real time on PubMed. Results RefMed supports a multi-level relevance feedback by using the RankSVM as the learning method, and thus it achieves higher accuracy with less feedback. RefMed "tightly" integrates the RankSVM into RDBMS to support both keyword queries and the multi-level relevance feedback in real time; the tight coupling of the RankSVM and DBMS substantially improves the processing time. An efficient parameter selection method for the RankSVM is also proposed, which tunes the RankSVM parameter without performing validation. Thereby, RefMed achieves a high learning accuracy in real time without performing a validation process. RefMed is accessible at http://dm.postech.ac.kr/refmed. Conclusions RefMed is the first multi-level relevance feedback system for PubMed, which achieves a high accuracy with less feedback. It effectively learns an accurate relevance function from the user’s feedback and efficiently processes the function to return relevant articles in real time. PMID:20406504

Validation of the VBLaST: A Virtual Peg Transfer Task in Gynecologic Surgeons.

PubMed

Awtrey, Christopher; Chellali, Amine; Schwaitzberg, Steven; De, Suvranu; Jones, Daniel; Cao, Caroline

2015-01-01

To validate the Virtual Basic Laparoscopic Skill Trainer (VBLaST-PT; the peg transfer task) for concurrent validity based on its ability to differentiate between novice, intermediate, and expert groups of gynecologists, and the gynecologists' subjective preference between the physical Fundamentals of Laparoscopic Surgery (FLS) system and the virtual reality system. Prospective study (Canadian Task Force II-2). Academic medical center. Obstetrics and gynecology residents (n = 18) and attending gynecologists (n = 9). Twenty-seven subjects were divided into 3 groups: novices (n = 9), intermediates (n = 9), and experts (n = 9). All subjects performed 10 trials of the peg transfer on each simulator. Assessment of laparoscopic performance was based on FLS scoring, whereas a questionnaire was used for subjective evaluation. The performance scores in the 2 simulators were nearly identical. Experts performed better than intermediates and novices in both the FLS trainer and the VBLAST, and intermediates performed better than novices in both simulators. The results also show a significant learning effect on both trainers for all subgroups; however, the greatest learning effect was in the novice group for both trainers. Subjectively, 74% participants preferred the FLS over the VBLaST for training laparoscopic surgical skills. This study demonstrates that the peg transfer task was reproduced well in the VBLaST in gynecologic surgeons and trainees. The VBLaST has the potential to be a valuable tool in laparoscopic training for gynecologic surgeons. Copyright © 2015 AAGL. Published by Elsevier Inc. All rights reserved.

Studying Different Tasks of Implicit Learning across Multiple Test Sessions Conducted on the Web

PubMed Central

Sævland, Werner; Norman, Elisabeth

2016-01-01

Implicit learning is usually studied through individual performance on a single task, with the most common tasks being the Serial Reaction Time (SRT) task, the Dynamic System Control (DSC) task, and Artificial Grammar Learning (AGL). Few attempts have been made to compare performance across different implicit learning tasks within the same study. The current study was designed to explore the relationship between performance on the DSC Sugar factory task and the Alternating Serial Reaction Time (ASRT) task. We also addressed another limitation of traditional implicit learning experiments, namely that implicit learning is usually studied in laboratory settings over a restricted time span lasting for less than an hour. In everyday situations, implicit learning is assumed to involve a gradual accumulation of knowledge across several learning episodes over a longer time span. One way to increase the ecological validity of implicit learning experiments could be to present the learning material repeatedly across shorter test sessions. This can most easily be done by using a web-based setup in which participants can access the material from home. We therefore created an online web-based system for measuring implicit learning that could be administered in either single or multiple sessions. Participants (n = 66) were assigned to either a single session or a multiple session condition. Learning occurred on both tasks, and awareness measures suggested that acquired knowledge was not fully conscious on either of the tasks. Learning and the degree of conscious awareness of the learned regularities were compared across conditions and tasks. On the DSC task, performance was not affected by whether learning had taken place in one or over multiple sessions. On the ASRT task, RT improvement across blocks was larger in the multiple-session condition. Learning in the two tasks was not related. PMID:27375512

AZOrange - High performance open source machine learning for QSAR modeling in a graphical programming environment

PubMed Central

2011-01-01

Background Machine learning has a vast range of applications. In particular, advanced machine learning methods are routinely and increasingly used in quantitative structure activity relationship (QSAR) modeling. QSAR data sets often encompass tens of thousands of compounds and the size of proprietary, as well as public data sets, is rapidly growing. Hence, there is a demand for computationally efficient machine learning algorithms, easily available to researchers without extensive machine learning knowledge. In granting the scientific principles of transparency and reproducibility, Open Source solutions are increasingly acknowledged by regulatory authorities. Thus, an Open Source state-of-the-art high performance machine learning platform, interfacing multiple, customized machine learning algorithms for both graphical programming and scripting, to be used for large scale development of QSAR models of regulatory quality, is of great value to the QSAR community. Results This paper describes the implementation of the Open Source machine learning package AZOrange. AZOrange is specially developed to support batch generation of QSAR models in providing the full work flow of QSAR modeling, from descriptor calculation to automated model building, validation and selection. The automated work flow relies upon the customization of the machine learning algorithms and a generalized, automated model hyper-parameter selection process. Several high performance machine learning algorithms are interfaced for efficient data set specific selection of the statistical method, promoting model accuracy. Using the high performance machine learning algorithms of AZOrange does not require programming knowledge as flexible applications can be created, not only at a scripting level, but also in a graphical programming environment. Conclusions AZOrange is a step towards meeting the needs for an Open Source high performance machine learning platform, supporting the efficient development of highly accurate QSAR models fulfilling regulatory requirements. PMID:21798025

AZOrange - High performance open source machine learning for QSAR modeling in a graphical programming environment.

PubMed

Stålring, Jonna C; Carlsson, Lars A; Almeida, Pedro; Boyer, Scott

2011-07-28

Machine learning has a vast range of applications. In particular, advanced machine learning methods are routinely and increasingly used in quantitative structure activity relationship (QSAR) modeling. QSAR data sets often encompass tens of thousands of compounds and the size of proprietary, as well as public data sets, is rapidly growing. Hence, there is a demand for computationally efficient machine learning algorithms, easily available to researchers without extensive machine learning knowledge. In granting the scientific principles of transparency and reproducibility, Open Source solutions are increasingly acknowledged by regulatory authorities. Thus, an Open Source state-of-the-art high performance machine learning platform, interfacing multiple, customized machine learning algorithms for both graphical programming and scripting, to be used for large scale development of QSAR models of regulatory quality, is of great value to the QSAR community. This paper describes the implementation of the Open Source machine learning package AZOrange. AZOrange is specially developed to support batch generation of QSAR models in providing the full work flow of QSAR modeling, from descriptor calculation to automated model building, validation and selection. The automated work flow relies upon the customization of the machine learning algorithms and a generalized, automated model hyper-parameter selection process. Several high performance machine learning algorithms are interfaced for efficient data set specific selection of the statistical method, promoting model accuracy. Using the high performance machine learning algorithms of AZOrange does not require programming knowledge as flexible applications can be created, not only at a scripting level, but also in a graphical programming environment. AZOrange is a step towards meeting the needs for an Open Source high performance machine learning platform, supporting the efficient development of highly accurate QSAR models fulfilling regulatory requirements.

WORMHOLE: Novel Least Diverged Ortholog Prediction through Machine Learning

PubMed Central

Sutphin, George L.; Mahoney, J. Matthew; Sheppard, Keith; Walton, David O.; Korstanje, Ron

2016-01-01

The rapid advancement of technology in genomics and targeted genetic manipulation has made comparative biology an increasingly prominent strategy to model human disease processes. Predicting orthology relationships between species is a vital component of comparative biology. Dozens of strategies for predicting orthologs have been developed using combinations of gene and protein sequence, phylogenetic history, and functional interaction with progressively increasing accuracy. A relatively new class of orthology prediction strategies combines aspects of multiple methods into meta-tools, resulting in improved prediction performance. Here we present WORMHOLE, a novel ortholog prediction meta-tool that applies machine learning to integrate 17 distinct ortholog prediction algorithms to identify novel least diverged orthologs (LDOs) between 6 eukaryotic species—humans, mice, zebrafish, fruit flies, nematodes, and budding yeast. Machine learning allows WORMHOLE to intelligently incorporate predictions from a wide-spectrum of strategies in order to form aggregate predictions of LDOs with high confidence. In this study we demonstrate the performance of WORMHOLE across each combination of query and target species. We show that WORMHOLE is particularly adept at improving LDO prediction performance between distantly related species, expanding the pool of LDOs while maintaining low evolutionary distance and a high level of functional relatedness between genes in LDO pairs. We present extensive validation, including cross-validated prediction of PANTHER LDOs and evaluation of evolutionary divergence and functional similarity, and discuss future applications of machine learning in ortholog prediction. A WORMHOLE web tool has been developed and is available at http://wormhole.jax.org/. PMID:27812085

WORMHOLE: Novel Least Diverged Ortholog Prediction through Machine Learning.

PubMed

Sutphin, George L; Mahoney, J Matthew; Sheppard, Keith; Walton, David O; Korstanje, Ron

2016-11-01

The rapid advancement of technology in genomics and targeted genetic manipulation has made comparative biology an increasingly prominent strategy to model human disease processes. Predicting orthology relationships between species is a vital component of comparative biology. Dozens of strategies for predicting orthologs have been developed using combinations of gene and protein sequence, phylogenetic history, and functional interaction with progressively increasing accuracy. A relatively new class of orthology prediction strategies combines aspects of multiple methods into meta-tools, resulting in improved prediction performance. Here we present WORMHOLE, a novel ortholog prediction meta-tool that applies machine learning to integrate 17 distinct ortholog prediction algorithms to identify novel least diverged orthologs (LDOs) between 6 eukaryotic species-humans, mice, zebrafish, fruit flies, nematodes, and budding yeast. Machine learning allows WORMHOLE to intelligently incorporate predictions from a wide-spectrum of strategies in order to form aggregate predictions of LDOs with high confidence. In this study we demonstrate the performance of WORMHOLE across each combination of query and target species. We show that WORMHOLE is particularly adept at improving LDO prediction performance between distantly related species, expanding the pool of LDOs while maintaining low evolutionary distance and a high level of functional relatedness between genes in LDO pairs. We present extensive validation, including cross-validated prediction of PANTHER LDOs and evaluation of evolutionary divergence and functional similarity, and discuss future applications of machine learning in ortholog prediction. A WORMHOLE web tool has been developed and is available at http://wormhole.jax.org/.

The Validation Challenge: How Close Is Europe to Recognising All Learning? Briefing Note

ERIC Educational Resources Information Center

Cedefop - European Centre for the Development of Vocational Training, 2014

2014-01-01

The European inventory on validation of non-formal and informal learning provides an unrivaled source of information detailing how validation of prior learning is developing across Europe. It shows that validation strategies and legislation, despite complexity of the task before them, have been developing slowly but steadily. However, there is…

Assessing Learning Styles of Graduate Entry Nursing Students as a Classroom Research Activity: A quantitative research study.

PubMed

Gonzales, Lucia K; Glaser, Dale; Howland, Lois; Clark, Mary Jo; Hutchins, Susie; Macauley, Karen; Close, Jacqueline F; Leveque, Noelle Lipkin; Failla, Kim Reina; Brooks, Raelene; Ward, Jillian

2017-01-01

A number of studies across different disciplines have investigated students' learning styles. Differences are known to exist between graduate and baccalaureate nursing students. However, few studies have investigated the learning styles of students in graduate entry nursing programs. . Study objective was to describe graduate entry nursing students' learning styles. A descriptive design was used for this study. The Index of Learning Styles (ILS) was administered to 202 graduate entry nursing student volunteers at a southwestern university. Descriptive statistics, tests of association, reliability, and validity were performed. Graduate nursing students and faculty participated in data collection, analysis, and dissemination of the results. Predominant learning styles were: sensing - 82.7%, visual - 78.7%, sequential - 65.8%, and active - 59.9%. Inter-item reliabilities for the postulated subscales were: sensing/intuitive (α=0.70), visual/verbal (α=0.694), sequential/global (α=0.599), and active/reflective (α=0.572). Confirmatory factor analysis for results of validity were: χ 2 (896)=1110.25, p<0.001, CFI=0.779, TLI=0.766, WRMR=1.14, and RMSEA =0.034. Predominant learning styles described students as being concrete thinkers oriented toward facts (sensing); preferring pictures, diagrams, flow charts, demonstrations (visual); being linear thinkers (sequencing); and enjoying working in groups and trying things out (active),. The predominant learning styles suggest educators teach concepts through simulation, discussion, and application of knowledge. Multiple studies, including this one, provided similar psychometric results. Similar reliability and validity results for the ILS have been noted in previous studies and therefore provide sufficient evidence to use the ILS with graduate entry nursing students. This study provided faculty with numerous opportunities for actively engaging students in data collection, analysis, and dissemination of results. Copyright © 2016 Elsevier Ltd. All rights reserved.

Reliable and valid tools for measuring surgeons' teaching performance: residents' vs. self evaluation.

PubMed

Boerebach, Benjamin C M; Arah, Onyebuchi A; Busch, Olivier R C; Lombarts, Kiki M J M H

2012-01-01

In surgical education, there is a need for educational performance evaluation tools that yield reliable and valid data. This paper describes the development and validation of robust evaluation tools that provide surgeons with insight into their clinical teaching performance. We investigated (1) the reliability and validity of 2 tools for evaluating the teaching performance of attending surgeons in residency training programs, and (2) whether surgeons' self evaluation correlated with the residents' evaluation of those surgeons. We surveyed 343 surgeons and 320 residents as part of a multicenter prospective cohort study of faculty teaching performance in residency training programs. The reliability and validity of the SETQ (System for Evaluation Teaching Qualities) tools were studied using standard psychometric techniques. We then estimated the correlations between residents' and surgeons' evaluations. The response rate was 87% among surgeons and 84% among residents, yielding 2625 residents' evaluations and 302 self evaluations. The SETQ tools yielded reliable and valid data on 5 domains of surgical teaching performance, namely, learning climate, professional attitude towards residents, communication of goals, evaluation of residents, and feedback. The correlations between surgeons' self and residents' evaluations were low, with coefficients ranging from 0.03 for evaluation of residents to 0.18 for communication of goals. The SETQ tools for the evaluation of surgeons' teaching performance appear to yield reliable and valid data. The lack of strong correlations between surgeons' self and residents' evaluations suggest the need for using external feedback sources in informed self evaluation of surgeons. Copyright © 2012 Association of Program Directors in Surgery. Published by Elsevier Inc. All rights reserved.

Validation of an Evaluation Model for Learning Management Systems

ERIC Educational Resources Information Center

Kim, S. W.; Lee, M. G.

2008-01-01

This study aims to validate a model for evaluating learning management systems (LMS) used in e-learning fields. A survey of 163 e-learning experts, regarding 81 validation items developed through literature review, was used to ascertain the importance of the criteria. A concise list of explanatory constructs, including two principle factors, was…

Validation of "Teaching and Learning Guiding Principles Instrument" for Malaysian Higher Learning Institutions

ERIC Educational Resources Information Center

Rahman, Nurulhuda Abd; Masuwai, Azwani; Tajudin, Nor'ain Mohd; Tek, Ong Eng; Adnan, Mazlini

2016-01-01

Purpose: This study was aimed at establishing, through the validation of the "Teaching and Learning Guiding Principles Instrument" (TLGPI), the validity and reliability of the underlying factor structure of the Teaching and Learning Guiding Principles (TLGP) generated by a previous study. Method: A survey method was used to collect data…

Active Learning Using Hint Information.

PubMed

Li, Chun-Liang; Ferng, Chun-Sung; Lin, Hsuan-Tien

2015-08-01

The abundance of real-world data and limited labeling budget calls for active learning, an important learning paradigm for reducing human labeling efforts. Many recently developed active learning algorithms consider both uncertainty and representativeness when making querying decisions. However, exploiting representativeness with uncertainty concurrently usually requires tackling sophisticated and challenging learning tasks, such as clustering. In this letter, we propose a new active learning framework, called hinted sampling, which takes both uncertainty and representativeness into account in a simpler way. We design a novel active learning algorithm within the hinted sampling framework with an extended support vector machine. Experimental results validate that the novel active learning algorithm can result in a better and more stable performance than that achieved by state-of-the-art algorithms. We also show that the hinted sampling framework allows improving another active learning algorithm designed from the transductive support vector machine.

Automated Deep Learning-Based System to Identify Endothelial Cells Derived from Induced Pluripotent Stem Cells.

PubMed

Kusumoto, Dai; Lachmann, Mark; Kunihiro, Takeshi; Yuasa, Shinsuke; Kishino, Yoshikazu; Kimura, Mai; Katsuki, Toshiomi; Itoh, Shogo; Seki, Tomohisa; Fukuda, Keiichi

2018-06-05

Deep learning technology is rapidly advancing and is now used to solve complex problems. Here, we used deep learning in convolutional neural networks to establish an automated method to identify endothelial cells derived from induced pluripotent stem cells (iPSCs), without the need for immunostaining or lineage tracing. Networks were trained to predict whether phase-contrast images contain endothelial cells based on morphology only. Predictions were validated by comparison to immunofluorescence staining for CD31, a marker of endothelial cells. Method parameters were then automatically and iteratively optimized to increase prediction accuracy. We found that prediction accuracy was correlated with network depth and pixel size of images to be analyzed. Finally, K-fold cross-validation confirmed that optimized convolutional neural networks can identify endothelial cells with high performance, based only on morphology. Copyright © 2018 The Author(s). Published by Elsevier Inc. All rights reserved.

Quality of Life in Children and Adolescents With Learning Problems: Development and Validation of the LD/QOL15 Scale.

PubMed

Waber, Deborah P; Boiselle, Ellen C; Forbes, Peter W; Girard, Jonathan M; Sideridis, Georgios D

2018-05-01

Learning problems (LP) can have wider implications than the academic deficits per se. The goal of the present series of studies was to develop a reliable and valid quality-of-life measure targeted to children and adolescents with LP. In Study 1, using a 35-item questionnaire, we surveyed 151 parents/guardians of children referred for assessment of learning disorders. Exploratory factor analysis identified a three-factor model: Academic Performance, School Understanding, and Child/Family Psychological. These factors were validated against standardized measures of academic achievement and psychosocial functioning. The questionnaire was then reduced to 15 items-the LD/QOL15 -and administered to a community sample of 325 parents/guardians of children in Grades 1 to 8 (Study 2). The three-factor model was verified with confirmatory factor analysis. Comparison of general education ( n = 232) and LP ( n = 93) groups within the community sample documented substantial group differences ( p < .0001), with the LP group having higher mean scores. These differences were larger for older students (Grades 5-8) than younger students (Grades 1-4; p < .01). The LD/QOL15 is a brief and reliable measure that is valid to assess quality of life and, potentially, outcomes in children and adolescents with LP.

First year medical students' learning style preferences and their correlation with performance in different subjects within the medical course.

PubMed

Hernández-Torrano, Daniel; Ali, Syed; Chan, Chee-Kai

2017-08-08

Students commencing their medical training arrive with different educational backgrounds and a diverse range of learning experiences. Consequently, students would have developed preferred approaches to acquiring and processing information or learning style preferences. Understanding first-year students' learning style preferences is important to success in learning. However, little is understood about how learning styles impact learning and performance across different subjects within the medical curriculum. Greater understanding of the relationship between students' learning style preferences and academic performance in specific medical subjects would be valuable. This cross-sectional study examined the learning style preferences of first-year medical students and how they differ across gender. This research also analyzed the effect of learning styles on academic performance across different subjects within a medical education program in a Central Asian university. A total of 52 students (57.7% females) from two batches of first-year medical school completed the Index of Learning Styles Questionnaire, which measures four dimensions of learning styles: sensing-intuitive; visual-verbal; active-reflective; sequential-global. First-year medical students reported preferences for visual (80.8%) and sequential (60.5%) learning styles, suggesting that these students preferred to learn through demonstrations and diagrams and in a linear and sequential way. Our results indicate that male medical students have higher preference for visual learning style over verbal, while females seemed to have a higher preference for sequential learning style over global. Significant associations were found between sensing-intuitive learning styles and performance in Genetics [β = -0.46, B = -0.44, p < 0.01] and Anatomy [β = -0.41, B = -0.61, p < 0.05] and between sequential-global styles and performance in Genetics [β = 0.36, B = 0.43, p < 0.05]. More specifically, sensing learners were more likely to perform better than intuitive learners in the two subjects and global learners were more likely to perform better than sequential learners in Genetics. This knowledge will be helpful to individual students to improve their performance in these subjects by adopting new sensing learning techniques. Instructors can also benefit by modifying and adapting more appropriate teaching approaches in these subjects. Future studies to validate this observation will be valuable.

Joint fMRI analysis and subject clustering using sparse dictionary learning

NASA Astrophysics Data System (ADS)

Kim, Seung-Jun; Dontaraju, Krishna K.

2017-08-01

Multi-subject fMRI data analysis methods based on sparse dictionary learning are proposed. In addition to identifying the component spatial maps by exploiting the sparsity of the maps, clusters of the subjects are learned by postulating that the fMRI volumes admit a subspace clustering structure. Furthermore, in order to tune the associated hyper-parameters systematically, a cross-validation strategy is developed based on entry-wise sampling of the fMRI dataset. Efficient algorithms for solving the proposed constrained dictionary learning formulations are developed. Numerical tests performed on synthetic fMRI data show promising results and provides insights into the proposed technique.

Diagnosing Breast Cancer with Microwave Technology: remaining challenges and potential solutions with machine learning.

PubMed

Oliveira, Bárbara L; Godinho, Daniela; O'Halloran, Martin; Glavin, Martin; Jones, Edward; Conceição, Raquel C

2018-05-19

Currently, breast cancer often requires invasive biopsies for diagnosis, motivating researchers to design and develop non-invasive and automated diagnosis systems. Recent microwave breast imaging studies have shown how backscattered signals carry relevant information about the shape of a tumour, and tumour shape is often used with current imaging modalities to assess malignancy. This paper presents a comprehensive analysis of microwave breast diagnosis systems which use machine learning to learn characteristics of benign and malignant tumours. The state-of-the-art, the main challenges still to overcome and potential solutions are outlined. Specifically, this work investigates the benefit of signal pre-processing on diagnostic performance, and proposes a new set of extracted features that capture the tumour shape information embedded in a signal. This work also investigates if a relationship exists between the antenna topology in a microwave system and diagnostic performance. Finally, a careful machine learning validation methodology is implemented to guarantee the robustness of the results and the accuracy of performance evaluation.

Cross-platform normalization of microarray and RNA-seq data for machine learning applications

PubMed Central

Thompson, Jeffrey A.; Tan, Jie

2016-01-01

Large, publicly available gene expression datasets are often analyzed with the aid of machine learning algorithms. Although RNA-seq is increasingly the technology of choice, a wealth of expression data already exist in the form of microarray data. If machine learning models built from legacy data can be applied to RNA-seq data, larger, more diverse training datasets can be created and validation can be performed on newly generated data. We developed Training Distribution Matching (TDM), which transforms RNA-seq data for use with models constructed from legacy platforms. We evaluated TDM, as well as quantile normalization, nonparanormal transformation, and a simple log2 transformation, on both simulated and biological datasets of gene expression. Our evaluation included both supervised and unsupervised machine learning approaches. We found that TDM exhibited consistently strong performance across settings and that quantile normalization also performed well in many circumstances. We also provide a TDM package for the R programming language. PMID:26844019

Usefulness of video-laryngoscopy with the Airway Scope for intubation performance and learning: an experimental manikin controlled study.

PubMed

Declercq, Pierre-Louis; Bubenheim, Michael; Gelinotte, Stéphanie; Guernon, Kévin; Michot, Jean-Baptiste; Royon, Vincent; Carpentier, Dorothée; Béduneau, Gaëtan; Tamion, Fabienne; Girault, Christophe

2016-12-01

Different video-laryngoscopes (VDLs) for endotracheal intubation (ETI) have recently been developed. We compared the performance of the VDL Airway Scope (AWS) with the direct laryngoscopy by Macintosh (DLM) for ETI success, time and learning. We performed an experimental manikin controlled study. Twenty experienced (experts) and 40 inexperienced operators (novices) for DLM-ETI were enrolled. None of them had experience with the use of AWS-VDL. Novices were assigned to start learning with DLM or AWS, and two sub-groups of 20 novices were formed. Experts group constituted the control group. Each participant performed 10 ETI attempts with each device on the same standard manikin. The primary endpoint was the ETI success probability. Secondary endpoints were ETI time, technical validity and qualitative evaluation for each technique. We also assessed the learning order and the successive attempts effects for these parameters. Overall, 1200 ETI attempts were performed. ETI success probability was higher with the AWS than with the DLM for all operators (98 vs. 81 %; p < 0.0001) and for experts compared to novices using devices in the same order (97 vs. 83 %; p = 0.0002). Overall ETI time was shorter with the AWS than with the DLM (13 vs. 20 s; p < 0.0001) and for experts compared to novices using devices in the same order (11 vs. 21 s; p < 0.0001). Among novices, those starting learning with AWS had higher ETI success probability (89 vs. 83 %; p = 0.03) and shorter ETI time (18 vs. 21 s; p = 0.02). Technical validity was found better with the AWS than DLM for all operators. Novices expressed global satisfaction and device preference for the AWS, whereas experts were indifferent. AWS-VDL permits faster, easier and more reliable ETI compared to the DLM whatever the previous airway ETI experience and could be a useful device for DLM-ETI learning.

Association between exposure to work stressors and cognitive performance.

PubMed

Vuori, Marko; Akila, Ritva; Kalakoski, Virpi; Pentti, Jaana; Kivimäki, Mika; Vahtera, Jussi; Härmä, Mikko; Puttonen, Sampsa

2014-04-01

To examine the association between work stress and cognitive performance. Cognitive performance of a total of 99 women (mean age = 47.3 years) working in hospital wards at either the top or bottom quartiles of job strain was assessed using validated tests that measured learning, short-term memory, and speed of memory retrieval. The high job strain group (n = 43) had lower performance than the low job strain group (n = 56) in learning (P = 0.025), short-term memory (P = 0.027), and speed of memory retrieval (P = 0.003). After controlling for education level, only the difference in speed of memory retrieval remained statistically significant (P = 0.010). The association found between job strain and speed of memory retrieval might be one important factor explaining the effect of stress on work performance.

The development of thematic materials using project based learning for elementary school

NASA Astrophysics Data System (ADS)

Yuliana, M.; Wiryawan, S. A.; Riyadi

2018-05-01

Teaching materials is one of the important factors in supporting on learning process. This paper discussed about developing thematic materials using project based learning. Thematic materials are designed to make students to be active, creative, cooperative, easy in thinking to solve the problem. The purpose of the research was to develop thematic material using project based learning which used valid variables. The method of research which used in this research was four stages of research and development proposed by Thiagarajan consisting of 4 stages, namely: (1) definition stage, (2) design stage, (3) development stage, and (4) stage of dissemination. The first stage was research and information collection, it was in form of need analysis with questionnaire, observation, interview, and document analysis. Design stage was based on the competencies and indicator. The third was development stage, this stage was used to product validation from expert. The validity of research development involved media validator, material validator, and linguistic validator. The result from the validation of thematic material by expert showed that the overall result had a very good rating which ranged from 1 to 5 likert scale, media validation showed a mean score 4,83, the material validation showed mean score 4,68, and the mean of linguistic validation was e 4,74. It showed that the thematic material using project based learning was valid and feasible to be implemented in the context thematic learning.

Classifier ensemble construction with rotation forest to improve medical diagnosis performance of machine learning algorithms.

PubMed

Ozcift, Akin; Gulten, Arif

2011-12-01

Improving accuracies of machine learning algorithms is vital in designing high performance computer-aided diagnosis (CADx) systems. Researches have shown that a base classifier performance might be enhanced by ensemble classification strategies. In this study, we construct rotation forest (RF) ensemble classifiers of 30 machine learning algorithms to evaluate their classification performances using Parkinson's, diabetes and heart diseases from literature. While making experiments, first the feature dimension of three datasets is reduced using correlation based feature selection (CFS) algorithm. Second, classification performances of 30 machine learning algorithms are calculated for three datasets. Third, 30 classifier ensembles are constructed based on RF algorithm to assess performances of respective classifiers with the same disease data. All the experiments are carried out with leave-one-out validation strategy and the performances of the 60 algorithms are evaluated using three metrics; classification accuracy (ACC), kappa error (KE) and area under the receiver operating characteristic (ROC) curve (AUC). Base classifiers succeeded 72.15%, 77.52% and 84.43% average accuracies for diabetes, heart and Parkinson's datasets, respectively. As for RF classifier ensembles, they produced average accuracies of 74.47%, 80.49% and 87.13% for respective diseases. RF, a newly proposed classifier ensemble algorithm, might be used to improve accuracy of miscellaneous machine learning algorithms to design advanced CADx systems. Copyright © 2011 Elsevier Ireland Ltd. All rights reserved.

Incorporating High-Frequency Physiologic Data Using Computational Dictionary Learning Improves Prediction of Delayed Cerebral Ischemia Compared to Existing Methods.

PubMed

Megjhani, Murad; Terilli, Kalijah; Frey, Hans-Peter; Velazquez, Angela G; Doyle, Kevin William; Connolly, Edward Sander; Roh, David Jinou; Agarwal, Sachin; Claassen, Jan; Elhadad, Noemie; Park, Soojin

2018-01-01

Accurate prediction of delayed cerebral ischemia (DCI) after subarachnoid hemorrhage (SAH) can be critical for planning interventions to prevent poor neurological outcome. This paper presents a model using convolution dictionary learning to extract features from physiological data available from bedside monitors. We develop and validate a prediction model for DCI after SAH, demonstrating improved precision over standard methods alone. 488 consecutive SAH admissions from 2006 to 2014 to a tertiary care hospital were included. Models were trained on 80%, while 20% were set aside for validation testing. Modified Fisher Scale was considered the standard grading scale in clinical use; baseline features also analyzed included age, sex, Hunt-Hess, and Glasgow Coma Scales. An unsupervised approach using convolution dictionary learning was used to extract features from physiological time series (systolic blood pressure and diastolic blood pressure, heart rate, respiratory rate, and oxygen saturation). Classifiers (partial least squares and linear and kernel support vector machines) were trained on feature subsets of the derivation dataset. Models were applied to the validation dataset. The performances of the best classifiers on the validation dataset are reported by feature subset. Standard grading scale (mFS): AUC 0.54. Combined demographics and grading scales (baseline features): AUC 0.63. Kernel derived physiologic features: AUC 0.66. Combined baseline and physiologic features with redundant feature reduction: AUC 0.71 on derivation dataset and 0.78 on validation dataset. Current DCI prediction tools rely on admission imaging and are advantageously simple to employ. However, using an agnostic and computationally inexpensive learning approach for high-frequency physiologic time series data, we demonstrated that we could incorporate individual physiologic data to achieve higher classification accuracy.

A New Semantic List Learning Task to Probe Functioning of the Papez Circuit

PubMed Central

Schallmo, Michael-Paul; Kassel, Michelle T.; Weisenbach, Sara L.; Walker, Sara J.; Guidotti-Breting, Leslie M.; Rao, Julia A.; Hazlett, Kathleen E.; Considine, Ciaran M.; Sethi, Gurpriya; Vats, Naalti; Pecina, Marta; Welsh, Robert C.; Starkman, Monica N.; Giordani, Bruno; Langenecker, Scott A.

2016-01-01

Introduction List learning tasks are powerful clinical tools for studying memory, yet have been relatively underutilized within the functional imaging literature. This limits understanding of regions such as the Papez circuit which support memory performance in healthy, non-demented adults. Method The current study characterized list learning performance in 40 adults who completed a Semantic List Learning Task (SLLT) with a Brown-Peterson manipulation during functional MRI (fMRI). Cued recall with semantic cues, and recognition memory were assessed after imaging. Internal reliability and convergent and discriminant validity were evaluated. Results Subjects averaged 38% accuracy in recall (62% for recognition), with primacy but no recency effects observed. Validity and reliability were demonstrated by showing that the SLLT was correlated with the California Verbal Learning test (CVLT), but not with executive functioning tests, and high intraclass correlation coefficient across lists for recall (.91). fMRI measurements during Encoding (vs. Silent Rehearsal) revealed significant activation in bilateral hippocampus, parahippocampus, and bilateral anterior and posterior cingulate cortex. Post-hoc analyses showed increased activation in anterior and middle hippocampus, subgenual cingulate, and mammillary bodies specific to Encoding. In addition, increasing age was positively associated with increased activation in a diffuse network, particularly frontal cortex and specific Papez regions for correctly recalled words. Gender differences were specific to left inferior and superior frontal cortex. Conclusions This is a clinically relevant list learning task that can be used in studies of groups for which the Papez circuit is damaged or disrupted, in mixed or crossover studies at imaging and clinical sites. PMID:26313512

Stability of the guinea pigs personality - cognition - linkage over time.

PubMed

Brust, Vera; Guenther, Anja

2017-01-01

In human psychological research, personality traits as well as cognitive traits are usually validated for both, their stability over time and contexts. While stability over time gives an estimate on how genetically fixated a trait can be, correlations across traits have the power to reveal linkages or trade - offs. In animals, these validations have widely been done for personality but not for cognitive traits. We tested guinea pigs in four consecutive discrimination tasks using four unique pairs of objects with two objects of the same form but different size in each pair. The same animals were tested twice each for three personality traits, i.e. boldness, aggression and sociopositive behaviour. The animals did not learn to "always choose the larger item" in the cognitive task but learned to discriminate the two objects of each stimulus pair anew, so that we did test for learning speed in four slightly different task setups. Performance over the four tasks was significantly repeatable as well as all tested personality traits. A stable linkage over time was found between sociopositive behaviour and learning performance, probably indicating an ecological relevance for a correlation between these two traits. Still, not all traits seem to be connected amongst each other, as in our case boldness and aggression are both not linked to individual learning performance. Future studies will hopefully further investigate the repeatability of various cognitive traits in several species and thus lead to a better understanding of the interdependence of personality and cognition. This will help to unravel which suites of traits facilitate individual life histories and hence improve our understanding of the emergence and maintenance of individual differences. Copyright © 2016 Elsevier B.V. All rights reserved.

Stereotype threat prevents perceptual learning

PubMed Central

Shiffrin, Richard M.; Boucher, Kathryn L.; Van Loo, Katie; Rydell, Michael T.

2010-01-01

Stereotype threat (ST) refers to a situation in which a member of a group fears that her or his performance will validate an existing negative performance stereotype, causing a decrease in performance. For example, reminding women of the stereotype “women are bad at math” causes them to perform more poorly on math questions from the SAT and GRE. Performance deficits can be of several types and be produced by several mechanisms. We show that ST prevents perceptual learning, defined in our task as an increasing rate of search for a target Chinese character in a display of such characters. Displays contained two or four characters and half of these contained a target. Search rate increased across a session of training for a control group of women, but not women under ST. Speeding of search is typically explained in terms of learned “popout” (automatic attraction of attention to a target). Did women under ST learn popout but fail to express it? Following training, the women were shown two colored squares and asked to choose the one with the greater color saturation. Superimposed on the squares were task-irrelevant Chinese characters. For women not trained under ST, the presence of a trained target on one square slowed responding, indicating that training had caused the learning of an attention response to targets. Women trained under ST showed no slowing, indicating that they had not learned such an attention response. PMID:20660737

Consensus on Quality Indicators of Postgraduate Medical E-Learning: Delphi Study.

PubMed

de Leeuw, Robert Adrianus; Walsh, Kieran; Westerman, Michiel; Scheele, Fedde

2018-04-26

The progressive use of e-learning in postgraduate medical education calls for useful quality indicators. Many evaluation tools exist. However, these are diversely used and their empirical foundation is often lacking. We aimed to identify an empirically founded set of quality indicators to set the bar for “good enough” e-learning. We performed a Delphi procedure with a group of 13 international education experts and 10 experienced users of e-learning. The questionnaire started with 57 items. These items were the result of a previous literature review and focus group study performed with experts and users. Consensus was met when a rate of agreement of more than two-thirds was achieved. In the first round, the participants accepted 37 items of the 57 as important, reached no consensus on 20, and added 15 new items. In the second round, we added the comments from the first round to the items on which there was no consensus and added the 15 new items. After this round, a total of 72 items were addressed and, of these, 37 items were accepted and 34 were rejected due to lack of consensus. This study produced a list of 37 items that can form the basis of an evaluation tool to evaluate postgraduate medical e-learning. This is, to our knowledge, the first time that quality indicators for postgraduate medical e-learning have been defined and validated. The next step is to create and validate an e-learning evaluation tool from these items. ©Robert Adrianus de Leeuw, Kieran Walsh, Michiel Westerman, Fedde Scheele. Originally published in JMIR Medical Education (http://mededu.jmir.org), 26.04.2018.

Computerized Hammer Sounding Interpretation for Concrete Assessment with Online Machine Learning.

PubMed

Ye, Jiaxing; Kobayashi, Takumi; Iwata, Masaya; Tsuda, Hiroshi; Murakawa, Masahiro

2018-03-09

Developing efficient Artificial Intelligence (AI)-enabled systems to substitute the human role in non-destructive testing is an emerging topic of considerable interest. In this study, we propose a novel hammering response analysis system using online machine learning, which aims at achieving near-human performance in assessment of concrete structures. Current computerized hammer sounding systems commonly employ lab-scale data to validate the models. In practice, however, the response signal patterns can be far more complicated due to varying geometric shapes and materials of structures. To deal with a large variety of unseen data, we propose a sequential treatment for response characterization. More specifically, the proposed system can adaptively update itself to approach human performance in hammering sounding data interpretation. To this end, a two-stage framework has been introduced, including feature extraction and the model updating scheme. Various state-of-the-art online learning algorithms have been reviewed and evaluated for the task. To conduct experimental validation, we collected 10,940 response instances from multiple inspection sites; each sample was annotated by human experts with healthy/defective condition labels. The results demonstrated that the proposed scheme achieved favorable assessment accuracy with high efficiency and low computation load.

Developing physics learning media using 3D cartoon

NASA Astrophysics Data System (ADS)

Wati, M.; Hartini, S.; Hikmah, N.; Mahtari, S.

2018-03-01

This study focuses on developing physics learning media using 3D cartoon on the static fluid topic. The purpose of this study is to describe: (1) the validity of the learning media, (2) the practicality of the learning media, and (3) the effectiveness of the learning media. This study is a research and development using ADDIE model. The subject of the implementation of media used class XI Science of SMAN 1 Pulau Laut Timur. The data were obtained from the validation sheet of the learning media, questionnaire, and the test of learning outcomes. The results showed that: (1) the validity of the media category is valid, (2) the practicality of the media category is practice, and (3) the effectiveness of the media category is effective. It is concluded that the learning using 3D cartoon on the static fluid topic is eligible to use in learning.

Quantum-state anomaly detection for arbitrary errors using a machine-learning technique

NASA Astrophysics Data System (ADS)

Hara, Satoshi; Ono, Takafumi; Okamoto, Ryo; Washio, Takashi; Takeuchi, Shigeki

2016-10-01

The accurate detection of small deviations in given density matrice is important for quantum information processing, which is a difficult task because of the intrinsic fluctuation in density matrices reconstructed using a limited number of experiments. We previously proposed a method for decoherence error detection using a machine-learning technique [S. Hara, T. Ono, R. Okamoto, T. Washio, and S. Takeuchi, Phys. Rev. A 89, 022104 (2014), 10.1103/PhysRevA.89.022104]. However, the previous method is not valid when the errors are just changes in phase. Here, we propose a method that is valid for arbitrary errors in density matrices. The performance of the proposed method is verified using both numerical simulation data and real experimental data.

Group Performing in a Problem-Based Curriculum: The Development and Evaluation of an Instrument.

ERIC Educational Resources Information Center

van Berkel, Henk J. M.; van Til, Cita T.

In a problem-based curriculum, emphasis is placed on the groups in which students learn to analyze problems and to contribute to the solution of a problem. This paper describes an instrument that aims to measure individual group performing and presents some psychometric results. Reliability and validity were studied with 240 students in groups of…

Challenges in Implementing National Systems of Competency Validation with Regard to Adult Learning Professionals: Perspectives from Romania and India

ERIC Educational Resources Information Center

Sava, Simona Lidia; Shah, S. Y.

2015-01-01

Validation of prior learning (VPL), also referred to as recognition, validation and accreditation of prior learning (RVA), is becoming an increasingly important political issue at both European and international levels. In 2012, the European Council, the UNESCO Institute for Lifelong Learning (UIL) and the Organisation for Economic Co-operation…

Factor Validity of the Motivated Strategies for Learning Questionnaire (MSLQ) in Asynchronous Online Learning Environments (AOLE)

ERIC Educational Resources Information Center

Cho, Moon-Heum; Summers, Jessica

2012-01-01

The purpose of this study was to investigate the factor validity of the Motivated Strategies for Learning Questionnaire (MSLQ) in asynchronous online learning environments. In order to check the factor validity, confirmatory factor analysis (CFA) was conducted with 193 cases. Using CFA, it was found that the original measurement model fit for…

Short- and Long-Term Learning of Feedforward Control of a Myoelectric Prosthesis with Sensory Feedback by Amputees.

PubMed

Strbac, Matija; Isakovic, Milica; Belic, Minja; Popovic, Igor; Simanic, Igor; Farina, Dario; Keller, Thierry; Dosen, Strahinja

2017-11-01

Human motor control relies on a combination of feedback and feedforward strategies. The aim of this study was to longitudinally investigate artificial somatosensory feedback and feedforward control in the context of grasping with myoelectric prosthesis. Nine amputee subjects performed routine grasping trials, with the aim to produce four levels of force during four blocks of 60 trials across five days. The electrotactile force feedback was provided in the second and third block using multipad electrode and spatial coding. The first baseline and last validation block (open-loop control) evaluated the effects of long- (across sessions) and short-term (within session) learning, respectively. The outcome measures were the absolute error between the generated and target force, and the number of force saturations. The results demonstrated that the electrotactile feedback improved the performance both within and across sessions. In the validation block, the performance did not significantly decrease and the quality of open-loop control (baseline) improved across days, converging to the performance characterizing closed-loop control. This paper provides important insights into the feedback and feedforward processes in prosthesis control, contributing to the better understanding of the role and design of feedback in prosthetic systems.

End-to-end learning for digital hologram reconstruction

NASA Astrophysics Data System (ADS)

Xu, Zhimin; Zuo, Si; Lam, Edmund Y.

2018-02-01

Digital holography is a well-known method to perform three-dimensional imaging by recording the light wavefront information originating from the object. Not only the intensity, but also the phase distribution of the wavefront can then be computed from the recorded hologram in the numerical reconstruction process. However, the reconstructions via the traditional methods suffer from various artifacts caused by twin-image, zero-order term, and noise from image sensors. Here we demonstrate that an end-to-end deep neural network (DNN) can learn to perform both intensity and phase recovery directly from an intensity-only hologram. We experimentally show that the artifacts can be effectively suppressed. Meanwhile, our network doesn't need any preprocessing for initialization, and is comparably fast to train and test, in comparison with the recently published learning-based method. In addition, we validate that the performance improvement can be achieved by introducing a prior on sparsity.

Complex scenes and situations visualization in hierarchical learning algorithm with dynamic 3D NeoAxis engine

NASA Astrophysics Data System (ADS)

Graham, James; Ternovskiy, Igor V.

2013-06-01

We applied a two stage unsupervised hierarchical learning system to model complex dynamic surveillance and cyber space monitoring systems using a non-commercial version of the NeoAxis visualization software. The hierarchical scene learning and recognition approach is based on hierarchical expectation maximization, and was linked to a 3D graphics engine for validation of learning and classification results and understanding the human - autonomous system relationship. Scene recognition is performed by taking synthetically generated data and feeding it to a dynamic logic algorithm. The algorithm performs hierarchical recognition of the scene by first examining the features of the objects to determine which objects are present, and then determines the scene based on the objects present. This paper presents a framework within which low level data linked to higher-level visualization can provide support to a human operator and be evaluated in a detailed and systematic way.

A Supervised Learning Process to Validate Online Disease Reports for Use in Predictive Models.

PubMed

Patching, Helena M M; Hudson, Laurence M; Cooke, Warrick; Garcia, Andres J; Hay, Simon I; Roberts, Mark; Moyes, Catherine L

2015-12-01

Pathogen distribution models that predict spatial variation in disease occurrence require data from a large number of geographic locations to generate disease risk maps. Traditionally, this process has used data from public health reporting systems; however, using online reports of new infections could speed up the process dramatically. Data from both public health systems and online sources must be validated before they can be used, but no mechanisms exist to validate data from online media reports. We have developed a supervised learning process to validate geolocated disease outbreak data in a timely manner. The process uses three input features, the data source and two metrics derived from the location of each disease occurrence. The location of disease occurrence provides information on the probability of disease occurrence at that location based on environmental and socioeconomic factors and the distance within or outside the current known disease extent. The process also uses validation scores, generated by disease experts who review a subset of the data, to build a training data set. The aim of the supervised learning process is to generate validation scores that can be used as weights going into the pathogen distribution model. After analyzing the three input features and testing the performance of alternative processes, we selected a cascade of ensembles comprising logistic regressors. Parameter values for the training data subset size, number of predictors, and number of layers in the cascade were tested before the process was deployed. The final configuration was tested using data for two contrasting diseases (dengue and cholera), and 66%-79% of data points were assigned a validation score. The remaining data points are scored by the experts, and the results inform the training data set for the next set of predictors, as well as going to the pathogen distribution model. The new supervised learning process has been implemented within our live site and is being used to validate the data that our system uses to produce updated predictive disease maps on a weekly basis.

Concurrent Validity Between a Shared Curriculum, the Internal Medicine In-Training Examination, and the American Board of Internal Medicine Certifying Examination.

PubMed

Sisson, Stephen D; Bertram, Amanda; Yeh, Hsin-Chieh

2015-03-01

A core objective of residency education is to facilitate learning, and programs need more curricula and assessment tools with demonstrated validity evidence. We sought to demonstrate concurrent validity between performance on a widely shared, ambulatory curriculum (the Johns Hopkins Internal Medicine Curriculum), the Internal Medicine In-Training Examination (IM-ITE), and the American Board of Internal Medicine Certifying Examination (ABIM-CE). A cohort study of 443 postgraduate year (PGY)-3 residents at 22 academic and community hospital internal medicine residency programs using the curriculum through the Johns Hopkins Internet Learning Center (ILC). Total and percentile rank scores on ILC didactic modules were compared with total and percentile rank scores on the IM-ITE and total scores on the ABIM-CE. The average score on didactic modules was 80.1%; the percentile rank was 53.8. The average IM-ITE score was 64.1% with a percentile rank of 54.8. The average score on the ABIM-CE was 464. Scores on the didactic modules, IM-ITE, and ABIM-CE correlated with each other (P < .05). Residents completing greater numbers of didactic modules, regardless of scores, had higher IM-ITE total and percentile rank scores (P < .05). Resident performance on modules covering back pain, hypertension, preoperative evaluation, and upper respiratory tract infection was associated with IM-ITE percentile rank. Performance on a widely shared ambulatory curriculum is associated with performance on the IM-ITE and the ABIM-CE.

Validation of the VBLaST: A Virtual Peg Transfer Task in Gynecologic Surgeons

PubMed Central

Awtrey, CS; Chellali, A; Schwaitzberg, SD; De, S; Jones, DB; Cao, CGL

2016-01-01

Study Objective To validate the virtual reality VBLaST-PT (the peg transfer task) for concurrent validity based on its ability to differentiate between novice, intermediate and expert groups of gynecologists, and the gynecologists’ subjective preference between the physical FLS system and the virtual reality system. Design Prospective study (Canadian Task Force II-2) Setting Academic medical center. Participants Obstetrics and gynecology residents (n = 18), and attending gynecologists (n = 9) Interventions Twenty-seven subjects were divided into three groups: novices (PGY1-2, n = 9), intermediates (PGY3-4, n = 9), and experts (attendings, n = 9). All subjects performed ten trials of the peg transfer on each simulator. Assessment of laparoscopic performance was based on FLS scoring while a questionnaire was used for subjective evaluation. Measurements and Main Results The results show that the performance scores in the two simulators were nearly identical. Experts performed better than intermediates and novices in both the FLS trainer and the VBLAST© and intermediates performed better than novices in both simulators as well. The results also show a significant learning effect on both trainers for all subgroups however the greatest learning effect was in the novice group for both trainers. Subjectively 74% participants preferred the FLS over the VBLaST© for training laparoscopic surgical skills. Conclusion This study demonstrates that the peg transfer task was reproduced well in the VBLaST in gynecologic surgeons and trainee’s. The VBLaST© has the potential to be a valuable tool in laparoscopic training for gynecologic surgeons. PMID:26216094

Innovative learning model for improving students’ argumentation skill and concept understanding on science

NASA Astrophysics Data System (ADS)

Nafsiati Astuti, Rini

2018-04-01

Argumentation skill is the ability to compose and maintain arguments consisting of claims, supports for evidence, and strengthened-reasons. Argumentation is an important skill student needs to face the challenges of globalization in the 21st century. It is not an ability that can be developed by itself along with the physical development of human, but it must be developed under nerve like process, giving stimulus so as to require a person to be able to argue. Therefore, teachers should develop students’ skill of arguing in science learning in the classroom. The purpose of this study is to obtain an innovative learning model that are valid in terms of content and construct in improving the skills of argumentation and concept understanding of junior high school students. The assessment of content validity and construct validity was done through Focus Group Discussion (FGD), using the content and construct validation sheet, book model, learning video, and a set of learning aids for one meeting. Assessment results from 3 (three) experts showed that the learning model developed in the category was valid. The validity itself shows that the developed learning model has met the content requirement, the student needs, state of the art, strong theoretical and empirical foundation and construct validity, which has a connection of syntax stages and components of learning model so that it can be applied in the classroom activities

Learning from samples of one or fewer*

PubMed Central

March, J; Sproull, L; Tamuz, M

2003-01-01



 Organizations learn from experience. Sometimes, however, history is not generous with experience. We explore how organizations convert infrequent events into interpretations of history, and how they balance the need to achieve agreement on interpretations with the need to interpret history correctly. We ask what methods are used, what problems are involved, and what improvements might be made. Although the methods we observe are not guaranteed to lead to consistent agreement on interpretations, valid knowledge, improved organizational performance, or organizational survival, they provide possible insights into the possibilities for and problems of learning from fragments of history. PMID:14645764

Classroom Research and Experiential Learning: Three Successful Experiences--Outcomes of Writing Competency.

ERIC Educational Resources Information Center

Mizell, Kay

1991-01-01

Describes a study conducted at Collin County Community College to assess the writing performance of different student populations. Offers observations about writing assessment for external validity. Suggests simple procedures for quantifying writing competency. Includes a proposal for portfolio assessment. (DMM)

Objective assessment of gynecologic laparoscopic skills using the LapSimGyn virtual reality simulator.

PubMed

Larsen, C R; Grantcharov, T; Aggarwal, R; Tully, A; Sørensen, J L; Dalsgaard, T; Ottesen, B

2006-09-01

Safe realistic training and unbiased quantitative assessment of technical skills are required for laparoscopy. Virtual reality (VR) simulators may be useful tools for training and assessing basic and advanced surgical skills and procedures. This study aimed to investigate the construct validity of the LapSimGyn VR simulator, and to determine the learning curves of gynecologists with different levels of experience. For this study, 32 gynecologic trainees and consultants (juniors or seniors) were allocated into three groups: novices (0 advanced laparoscopic procedures), intermediate level (>20 and <60 procedures), and experts (>100 procedures). All performed 10 sets of simulations consisting of three basic skill tasks and an ectopic pregnancy program. The simulations were carried out on 3 days within a maximum period of 2 weeks. Assessment of skills was based on time, economy of movement, and error parameters measured by the simulator. The data showed that expert gynecologists performed significantly and consistently better than intermediate and novice gynecologists. The learning curves differed significantly between the groups, showing that experts start at a higher level and more rapidly reach the plateau of their learning curve than do intermediate and novice groups of surgeons. The LapSimGyn VR simulator package demonstrates construct validity on both the basic skills module and the procedural gynecologic module for ectopic pregnancy. Learning curves can be obtained, but to reach the maximum performance for the more complex tasks, 10 repetitions do not seem sufficient at the given task level and settings. LapSimGyn also seems to be flexible and widely accepted by the users.

Validating module network learning algorithms using simulated data.

PubMed

Michoel, Tom; Maere, Steven; Bonnet, Eric; Joshi, Anagha; Saeys, Yvan; Van den Bulcke, Tim; Van Leemput, Koenraad; van Remortel, Piet; Kuiper, Martin; Marchal, Kathleen; Van de Peer, Yves

2007-05-03

In recent years, several authors have used probabilistic graphical models to learn expression modules and their regulatory programs from gene expression data. Despite the demonstrated success of such algorithms in uncovering biologically relevant regulatory relations, further developments in the area are hampered by a lack of tools to compare the performance of alternative module network learning strategies. Here, we demonstrate the use of the synthetic data generator SynTReN for the purpose of testing and comparing module network learning algorithms. We introduce a software package for learning module networks, called LeMoNe, which incorporates a novel strategy for learning regulatory programs. Novelties include the use of a bottom-up Bayesian hierarchical clustering to construct the regulatory programs, and the use of a conditional entropy measure to assign regulators to the regulation program nodes. Using SynTReN data, we test the performance of LeMoNe in a completely controlled situation and assess the effect of the methodological changes we made with respect to an existing software package, namely Genomica. Additionally, we assess the effect of various parameters, such as the size of the data set and the amount of noise, on the inference performance. Overall, application of Genomica and LeMoNe to simulated data sets gave comparable results. However, LeMoNe offers some advantages, one of them being that the learning process is considerably faster for larger data sets. Additionally, we show that the location of the regulators in the LeMoNe regulation programs and their conditional entropy may be used to prioritize regulators for functional validation, and that the combination of the bottom-up clustering strategy with the conditional entropy-based assignment of regulators improves the handling of missing or hidden regulators. We show that data simulators such as SynTReN are very well suited for the purpose of developing, testing and improving module network algorithms. We used SynTReN data to develop and test an alternative module network learning strategy, which is incorporated in the software package LeMoNe, and we provide evidence that this alternative strategy has several advantages with respect to existing methods.

Development and validation of a machine learning algorithm and hybrid system to predict the need for life-saving interventions in trauma patients.

PubMed

Liu, Nehemiah T; Holcomb, John B; Wade, Charles E; Batchinsky, Andriy I; Cancio, Leopoldo C; Darrah, Mark I; Salinas, José

2014-02-01

Accurate and effective diagnosis of actual injury severity can be problematic in trauma patients. Inherent physiologic compensatory mechanisms may prevent accurate diagnosis and mask true severity in many circumstances. The objective of this project was the development and validation of a multiparameter machine learning algorithm and system capable of predicting the need for life-saving interventions (LSIs) in trauma patients. Statistics based on means, slopes, and maxima of various vital sign measurements corresponding to 79 trauma patient records generated over 110,000 feature sets, which were used to develop, train, and implement the system. Comparisons among several machine learning models proved that a multilayer perceptron would best implement the algorithm in a hybrid system consisting of a machine learning component and basic detection rules. Additionally, 295,994 feature sets from 82 h of trauma patient data showed that the system can obtain 89.8 % accuracy within 5 min of recorded LSIs. Use of machine learning technologies combined with basic detection rules provides a potential approach for accurately assessing the need for LSIs in trauma patients. The performance of this system demonstrates that machine learning technology can be implemented in a real-time fashion and potentially used in a critical care environment.

Instruments evaluating the quality of the clinical learning environment in nursing education: A systematic review of psychometric properties.

PubMed

Mansutti, Irene; Saiani, Luisa; Grassetti, Luca; Palese, Alvisa

2017-03-01

The clinical learning environment is fundamental to nursing education paths, capable of affecting learning processes and outcomes. Several instruments have been developed in nursing education, aimed at evaluating the quality of the clinical learning environments; however, no systematic review of the psychometric properties and methodological quality of these studies has been performed to date. The aims of the study were: 1) to identify validated instruments evaluating the clinical learning environments in nursing education; 2) to evaluate critically the methodological quality of the psychometric property estimation used; and 3) to compare psychometric properties across the instruments available. A systematic review of the literature (using the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines) and an evaluation of the methodological quality of psychometric properties (using the COnsensus-based Standards for the selection of health Measurement INstruments guidelines). The Medline and CINAHL databases were searched. Eligible studies were those that satisfied the following criteria: a) validation studies of instruments evaluating the quality of clinical learning environments; b) in nursing education; c) published in English or Italian; d) before April 2016. The included studies were evaluated for the methodological quality of the psychometric properties measured and then compared in terms of both the psychometric properties and the methodological quality of the processes used. The search strategy yielded a total of 26 studies and eight clinical learning environment evaluation instruments. A variety of psychometric properties have been estimated for each instrument, with differing qualities in the methodology used. Concept and construct validity were poorly assessed in terms of their significance and rarely judged by the target population (nursing students). Some properties were rarely considered (e.g., reliability, measurement error, criterion validity), whereas others were frequently estimated, but using different coefficients and statistical analyses (e.g., internal consistency, structural validity), thus rendering comparison across instruments difficult. Moreover, the methodological quality adopted in the property assessments was poor or fair in most studies, compromising the goodness of the psychometric values estimated. Clinical learning placements represent the key strategies in educating the future nursing workforce: instruments evaluating the quality of the settings, as well as their capacity to promote significant learning, are strongly recommended. Studies estimating psychometric properties, using an increased quality of research methodologies are needed in order to support nursing educators in the process of clinical placements accreditation and quality improvement. Copyright © 2017 Elsevier Ltd. All rights reserved.

Enhanced Data Representation by Kernel Metric Learning for Dementia Diagnosis

PubMed Central

Cárdenas-Peña, David; Collazos-Huertas, Diego; Castellanos-Dominguez, German

2017-01-01

Alzheimer's disease (AD) is the kind of dementia that affects the most people around the world. Therefore, an early identification supporting effective treatments is required to increase the life quality of a wide number of patients. Recently, computer-aided diagnosis tools for dementia using Magnetic Resonance Imaging scans have been successfully proposed to discriminate between patients with AD, mild cognitive impairment, and healthy controls. Most of the attention has been given to the clinical data, provided by initiatives as the ADNI, supporting reliable researches on intervention, prevention, and treatments of AD. Therefore, there is a need for improving the performance of classification machines. In this paper, we propose a kernel framework for learning metrics that enhances conventional machines and supports the diagnosis of dementia. Our framework aims at building discriminative spaces through the maximization of center kernel alignment function, aiming at improving the discrimination of the three considered neurological classes. The proposed metric learning performance is evaluated on the widely-known ADNI database using three supervised classification machines (k-nn, SVM and NNs) for multi-class and bi-class scenarios from structural MRIs. Specifically, from ADNI collection 286 AD patients, 379 MCI patients and 231 healthy controls are used for development and validation of our proposed metric learning framework. For the experimental validation, we split the data into two subsets: 30% of subjects used like a blindfolded assessment and 70% employed for parameter tuning. Then, in the preprocessing stage, each structural MRI scan a total of 310 morphological measurements are automatically extracted from by FreeSurfer software package and concatenated to build an input feature matrix. Obtained test performance results, show that including a supervised metric learning improves the compared baseline classifiers in both scenarios. In the multi-class scenario, we achieve the best performance (accuracy 60.1%) for pretrained 1-layered NN, and we obtain measures over 90% in the average for HC vs. AD task. From the machine learning point of view, our proposal enhances the classifier performance by building spaces with a better class separability. From the clinical application, our enhancement results in a more balanced performance in each class than the compared approaches from the CADDementia challenge by increasing the sensitivity of pathological groups and the specificity of healthy controls. PMID:28798659

Teachable, high-content analytics for live-cell, phase contrast movies.

PubMed

Alworth, Samuel V; Watanabe, Hirotada; Lee, James S J

2010-09-01

CL-Quant is a new solution platform for broad, high-content, live-cell image analysis. Powered by novel machine learning technologies and teach-by-example interfaces, CL-Quant provides a platform for the rapid development and application of scalable, high-performance, and fully automated analytics for a broad range of live-cell microscopy imaging applications, including label-free phase contrast imaging. The authors used CL-Quant to teach off-the-shelf universal analytics, called standard recipes, for cell proliferation, wound healing, cell counting, and cell motility assays using phase contrast movies collected on the BioStation CT and BioStation IM platforms. Similar to application modules, standard recipes are intended to work robustly across a wide range of imaging conditions without requiring customization by the end user. The authors validated the performance of the standard recipes by comparing their performance with truth created manually, or by custom analytics optimized for each individual movie (and therefore yielding the best possible result for the image), and validated by independent review. The validation data show that the standard recipes' performance is comparable with the validated truth with low variation. The data validate that the CL-Quant standard recipes can provide robust results without customization for live-cell assays in broad cell types and laboratory settings.

[A new low-cost webcam-based laparoscopic training model].

PubMed

Langeron, A; Mercier, G; Lima, S; Chauleur, C; Golfier, F; Seffert, P; Chêne, G

2012-01-01

To validate a new laparoscopy home training model (GYN Trainer®) in order to practise and learn basic laparoscopic surgery. Ten junior surgical residents and six experienced operators were timed and assessed during six laparoscopic exercises performed on the home training model. Acquisition of skill was 35%. All the novices significantly improved performance in surgical skills despite an 8% partial loss of acquisition between two training sessions. Qualitative evaluation of the system was good (3.8/5). This low-cost personal laparoscopic model seems to be a useful tool to assist surgical novices in learning basic laparoscopic skills. Copyright © 2012 Elsevier Masson SAS. All rights reserved.

Active learning increases student performance in science, engineering, and mathematics.

PubMed

Freeman, Scott; Eddy, Sarah L; McDonough, Miles; Smith, Michelle K; Okoroafor, Nnadozie; Jordt, Hannah; Wenderoth, Mary Pat

2014-06-10

To test the hypothesis that lecturing maximizes learning and course performance, we metaanalyzed 225 studies that reported data on examination scores or failure rates when comparing student performance in undergraduate science, technology, engineering, and mathematics (STEM) courses under traditional lecturing versus active learning. The effect sizes indicate that on average, student performance on examinations and concept inventories increased by 0.47 SDs under active learning (n = 158 studies), and that the odds ratio for failing was 1.95 under traditional lecturing (n = 67 studies). These results indicate that average examination scores improved by about 6% in active learning sections, and that students in classes with traditional lecturing were 1.5 times more likely to fail than were students in classes with active learning. Heterogeneity analyses indicated that both results hold across the STEM disciplines, that active learning increases scores on concept inventories more than on course examinations, and that active learning appears effective across all class sizes--although the greatest effects are in small (n ≤ 50) classes. Trim and fill analyses and fail-safe n calculations suggest that the results are not due to publication bias. The results also appear robust to variation in the methodological rigor of the included studies, based on the quality of controls over student quality and instructor identity. This is the largest and most comprehensive metaanalysis of undergraduate STEM education published to date. The results raise questions about the continued use of traditional lecturing as a control in research studies, and support active learning as the preferred, empirically validated teaching practice in regular classrooms.

The moderating role of team resources in translating nursing teams' accountability into learning and performance: a cross-sectional study.

PubMed

Rashkovits, Sarit; Drach-Zahavy, Anat

2017-05-01

The aim of this study was to test the moderated-mediation model suggesting that nursing teams' accountability affects team effectiveness by enhancing team learning when relevant resources are available to the team. Disappointing evidence regarding improvement in nurses' safe and quality care elevate the need in broadening our knowledge regarding the factors that enhance constant learning in nursing teams. Accountability is considered as crucial for team learning and quality of care but empirical findings have shown mixed evidence. A cross-sectional design. Forty-four nursing teams participated in the study. Data were collected in 2013-2014: Head nurses completed validated questionnaires, regarding team resources for learning (time availability, team autonomy and team performance feedback), and nursing teams' effectiveness; and nurses answered questionnaires regarding teams' accountability and learning (answers were aggregated to the team level). The model was tested using a moderated-mediation analysis with resources as moderating variables, and team learning as the mediator in the team accountability-team effectiveness link. The results of a mixed linear regression show that, as expected, nursing teams' accountability was positively linked to nursing teams' learning, when time availability, and team autonomy were high rather than low, and team performance feedback was low rather than high. Nurturing team accountability is not enough for achieving team learning and subsequent team effectiveness. Rather there is a need to provide nursing teams with adequate time, autonomy, and be cautious with performance feedback, as the latter may motivate nurses to repeat routine work strategies rather than explore improved ones. © 2016 John Wiley & Sons Ltd.

Active learning increases student performance in science, engineering, and mathematics

PubMed Central

Freeman, Scott; Eddy, Sarah L.; McDonough, Miles; Smith, Michelle K.; Okoroafor, Nnadozie; Jordt, Hannah; Wenderoth, Mary Pat

2014-01-01

To test the hypothesis that lecturing maximizes learning and course performance, we metaanalyzed 225 studies that reported data on examination scores or failure rates when comparing student performance in undergraduate science, technology, engineering, and mathematics (STEM) courses under traditional lecturing versus active learning. The effect sizes indicate that on average, student performance on examinations and concept inventories increased by 0.47 SDs under active learning (n = 158 studies), and that the odds ratio for failing was 1.95 under traditional lecturing (n = 67 studies). These results indicate that average examination scores improved by about 6% in active learning sections, and that students in classes with traditional lecturing were 1.5 times more likely to fail than were students in classes with active learning. Heterogeneity analyses indicated that both results hold across the STEM disciplines, that active learning increases scores on concept inventories more than on course examinations, and that active learning appears effective across all class sizes—although the greatest effects are in small (n ≤ 50) classes. Trim and fill analyses and fail-safe n calculations suggest that the results are not due to publication bias. The results also appear robust to variation in the methodological rigor of the included studies, based on the quality of controls over student quality and instructor identity. This is the largest and most comprehensive metaanalysis of undergraduate STEM education published to date. The results raise questions about the continued use of traditional lecturing as a control in research studies, and support active learning as the preferred, empirically validated teaching practice in regular classrooms. PMID:24821756

NAEP Validity Studies: Improving the Information Value of Performance Items in Large Scale Assessments. Working Paper No. 2003-08

ERIC Educational Resources Information Center

Pearson, P. David; Garavaglia, Diane R.

2003-01-01

The purpose of this essay is to explore both what is known and what needs to be learned about the information value of performance items "when they are used in large scale assessments." Within the context of the National Assessment of Educational Progress (NAEP), there is substantial motivation for answering these questions. Over the…

Development and validation of a virtual reality simulator: human factors input to interventional radiology training.

PubMed

Johnson, Sheena Joanne; Guediri, Sara M; Kilkenny, Caroline; Clough, Peter J

2011-12-01

This study developed and validated a virtual reality (VR) simulator for use by interventional radiologists. Research in the area of skill acquisition reports practice as essential to become a task expert. Studies on simulation show skills learned in VR can be successfully transferred to a real-world task. Recently, with improvements in technology, VR simulators have been developed to allow complex medical procedures to be practiced without risking the patient. Three studies are reported. In Study I, 35 consultant interventional radiologists took part in a cognitive task analysis to empirically establish the key competencies of the Seldinger procedure. In Study 2, 62 participants performed one simulated procedure, and their performance was compared by expertise. In Study 3, the transferability of simulator training to a real-world procedure was assessed with 14 trainees. Study I produced 23 key competencies that were implemented as performance measures in the simulator. Study 2 showed the simulator had both face and construct validity, although some issues were identified. Study 3 showed the group that had undergone simulator training received significantly higher mean performance ratings on a subsequent patient procedure. The findings of this study support the centrality of validation in the successful design of simulators and show the utility of simulators as a training device. The studies show the key elements of a validation program for a simulator. In addition to task analysis and face and construct validities, the authors highlight the importance of transfer of training in validation studies.

The role of simulation in continuing medical education for acute care physicians: a systematic review.

PubMed

Khanduja, P Kristina; Bould, M Dylan; Naik, Viren N; Hladkowicz, Emily; Boet, Sylvain

2015-01-01

We systematically reviewed the effectiveness of simulation-based education, targeting independently practicing qualified physicians in acute care specialties. We also describe how simulation is used for performance assessment in this population. Data source included: DataMEDLINE, Embase, Cochrane Database of Systematic Reviews, Cochrane CENTRAL Database of Controlled Trials, and National Health Service Economic Evaluation Database. The last date of search was January 31, 2013. All original research describing simulation-based education for independently practicing physicians in anesthesiology, critical care, and emergency medicine was reviewed. Data analysis was performed in duplicate with further review by a third author in cases of disagreement until consensus was reached. Data extraction was focused on effectiveness according to Kirkpatrick's model. For simulation-based performance assessment, tool characteristics and sources of validity evidence were also collated. Of 39 studies identified, 30 studies focused on the effectiveness of simulation-based education and nine studies evaluated the validity of simulation-based assessment. Thirteen studies (30%) targeted the lower levels of Kirkpatrick's hierarchy with reliance on self-reporting. Simulation was unanimously described as a positive learning experience with perceived impact on clinical practice. Of the 17 remaining studies, 10 used a single group or "no intervention comparison group" design. The majority (n = 17; 44%) were able to demonstrate both immediate and sustained improvements in educational outcomes. Nine studies reported the psychometric properties of simulation-based performance assessment as their sole objective. These predominantly recruited independent practitioners as a convenience sample to establish whether the tool could discriminate between experienced and inexperienced operators and concentrated on a single aspect of validity evidence. Simulation is perceived as a positive learning experience with limited evidence to support improved learning. Future research should focus on the optimal modality and frequency of exposure, quality of assessment tools and on the impact of simulation-based education beyond the individuals toward improved patient care.

The Predictive Value of Ultrasound Learning Curves Across Simulated and Clinical Settings.

PubMed

Madsen, Mette E; Nørgaard, Lone N; Tabor, Ann; Konge, Lars; Ringsted, Charlotte; Tolsgaard, Martin G

2017-01-01

The aim of the study was to explore whether learning curves on a virtual-reality (VR) sonographic simulator can be used to predict subsequent learning curves on a physical mannequin and learning curves during clinical training. Twenty midwives completed a simulation-based training program in transvaginal sonography. The training was conducted on a VR simulator as well as on a physical mannequin. A subgroup of 6 participants underwent subsequent clinical training. During each of the 3 steps, the participants' performance was assessed using instruments with established validity evidence, and they advanced to the next level only after attaining predefined levels of performance. The number of repetitions and time needed to achieve predefined performance levels were recorded along with the performance scores in each setting. Finally, the outcomes were correlated across settings. A good correlation was found between time needed to achieve predefined performance levels on the VR simulator and the physical mannequin (Pearson correlation coefficient .78; P < .001). Performance scores on the VR simulator correlated well to the clinical performance scores (Pearson correlation coefficient .81; P = .049). No significant correlations were found between numbers of attempts needed to reach proficiency across the 3 different settings. A post hoc analysis found that the 50% fastest trainees at reaching proficiency during simulation-based training received higher clinical performance scores compared to trainees with scores placing them among the 50% slowest (P = .025). Performances during simulation-based sonography training may predict performance in related tasks and subsequent clinical learning curves. © 2016 by the American Institute of Ultrasound in Medicine.

The effectiveness of physics learning material based on South Kalimantan local wisdom

NASA Astrophysics Data System (ADS)

Hartini, Sri; Misbah, Helda, Dewantara, Dewi

2017-08-01

The local wisdom is essential element incorporated into learning process. However, there are no learning materials in Physics learning process which contain South Kalimantan local wisdom. Therefore, it is necessary to develop a Physics learning material based on South Kalimantan local wisdom. The objective of this research is to produce products in the form of learning material based on South Kalimantan local wisdom that is feasible and effective based on the validity, practicality, effectiveness of learning material and achievement of waja sampai kaputing (wasaka) character. This research is a research and development which refers to the ADDIE model. Data were obtained through the validation sheet of learning material, questionnaire, the test of learning outcomes and the sheet of character assesment. The research results showed that (1) the validity category of the learning material was very valid, (2) the practicality category of the learning material was very practical, (3) the effectiveness category of thelearning material was very effective, and (4) the achivement of wasaka characters was very good. In conclusion, the Physics learning materials based on South Kalimantan local wisdom are feasible and effective to be used in learning activities.

Judgments of learning are significantly higher following feedback on relatively good versus relatively poor trials despite no actual learning differences.

PubMed

Carter, Michael J; Smith, Victoria; Ste-Marie, Diane M

2016-02-01

Studies have consistently shown that prospective metacognitive judgments of learning are often inaccurate because humans mistakenly interpret current performance levels as valid indices of learning. These metacognitive discrepancies are strongly related to conditions of practice. Here, we examined how the type of feedback (after good versus poor trials) received during practice and awareness (aware versus unaware) of this manipulation affected judgments of learning and actual learning. After each six-trial block, participants received feedback on their three best trials or three worst trials and half of the participants were made explicitly aware of the type of feedback they received while the other half were unaware. Judgments of learning were made at the end of each six-trial block and before the 24-h retention test. Results indicated no motor performance differences between groups in practice or retention; however, receiving feedback on relatively good compared to relatively poor trials resulted in significantly higher judgments of learning in practice and retention, irrespective of awareness. These results suggest that KR on relatively good versus relatively poor trials can have dissociable effects on judgments of learning in the absence of actual learning differences, even when participants are made aware of their feedback manipulation. Copyright © 2015 Elsevier B.V. All rights reserved.

Measuring learning potential in people with schizophrenia: A comparison of two tasks.

PubMed

Rempfer, Melisa V; McDowd, Joan M; Brown, Catana E

2017-12-01

Learning potential measures utilize dynamic assessment methods to capture performance changes following training on a cognitive task. Learning potential has been explored in schizophrenia research as a predictor of functional outcome and there have been calls for psychometric development in this area. Because the majority of learning potential studies have utilized the Wisconsin Card Sorting Test (WCST), we extended this work using a novel measure, the Rey Osterrieth Complex Figure Test (ROCFT). This study had the following aims: 1) to examine relationships among different learning potential indices for two dynamic assessment tasks, 2) to examine the association between WCST and ROCFT learning potential measures, and 3) to address concurrent validity with a performance-based measure of functioning (Test of Grocery Shopping Skills; TOGSS). Eighty-one adults with schizophrenia or schizoaffective disorder completed WCST and ROCFT learning measures and the TOGSS. Results indicated the various learning potential computational indices are intercorrelated and, similar to other studies, we found support for regression residuals and post-test scores as optimal indices. Further, we found modest relationships between the two learning potential measures and the TOGSS. These findings suggest learning potential includes both general and task-specific constructs but future research is needed to further explore this question. Copyright © 2017 Elsevier B.V. All rights reserved.

29 CFR Section 1607.16 - Definitions.

Code of Federal Regulations, 2010 CFR

2010-07-01

... action are open to users. T. Skill. A present, observable competence to perform a learned psychomoter act... criterion-related validity studies. These conditions include: (1) An adequate sample of persons available for the study to achieve findings of statistical significance; (2) having or being able to obtain a...

Soft Research on a Hard Subject: Student Evaluations Reconsidered

ERIC Educational Resources Information Center

Soper, John C.

1973-01-01

Methods of evaluation of faculty classroom performance are considered. The author cites research studies which attempt to assess the validity of student evaluations of teachers. Data are presented suggesting that the students' perceptions of their teachers' abilities are not connected with what those students learn. (SM)

Comparison of machine learning and semi-quantification algorithms for (I123)FP-CIT classification: the beginning of the end for semi-quantification?

PubMed

Taylor, Jonathan Christopher; Fenner, John Wesley

2017-11-29

Semi-quantification methods are well established in the clinic for assisted reporting of (I123) Ioflupane images. Arguably, these are limited diagnostic tools. Recent research has demonstrated the potential for improved classification performance offered by machine learning algorithms. A direct comparison between methods is required to establish whether a move towards widespread clinical adoption of machine learning algorithms is justified. This study compared three machine learning algorithms with that of a range of semi-quantification methods, using the Parkinson's Progression Markers Initiative (PPMI) research database and a locally derived clinical database for validation. Machine learning algorithms were based on support vector machine classifiers with three different sets of features: Voxel intensities Principal components of image voxel intensities Striatal binding radios from the putamen and caudate. Semi-quantification methods were based on striatal binding ratios (SBRs) from both putamina, with and without consideration of the caudates. Normal limits for the SBRs were defined through four different methods: Minimum of age-matched controls Mean minus 1/1.5/2 standard deviations from age-matched controls Linear regression of normal patient data against age (minus 1/1.5/2 standard errors) Selection of the optimum operating point on the receiver operator characteristic curve from normal and abnormal training data Each machine learning and semi-quantification technique was evaluated with stratified, nested 10-fold cross-validation, repeated 10 times. The mean accuracy of the semi-quantitative methods for classification of local data into Parkinsonian and non-Parkinsonian groups varied from 0.78 to 0.87, contrasting with 0.89 to 0.95 for classifying PPMI data into healthy controls and Parkinson's disease groups. The machine learning algorithms gave mean accuracies between 0.88 to 0.92 and 0.95 to 0.97 for local and PPMI data respectively. Classification performance was lower for the local database than the research database for both semi-quantitative and machine learning algorithms. However, for both databases, the machine learning methods generated equal or higher mean accuracies (with lower variance) than any of the semi-quantification approaches. The gain in performance from using machine learning algorithms as compared to semi-quantification was relatively small and may be insufficient, when considered in isolation, to offer significant advantages in the clinical context.

Controlled Hydrogen Fleet and Infrastructure Demonstration and Validation Project

DOE Office of Scientific and Technical Information (OSTI.GOV)

Stottler, Gary

General Motors, LLC and energy partner Shell Hydrogen, LLC, deployed a system of hydrogen fuel cell electric vehicles integrated with a hydrogen fueling station infrastructure to operate under real world conditions as part of the U.S. Department of Energy's Controlled Hydrogen Fleet and Infrastructure Validation and Demonstration Project. This technical report documents the performance and describes the learnings from progressive generations of vehicle fuel cell system technology and multiple approaches to hydrogen generation and delivery for vehicle fueling.

Validity evidence for an OSCE to assess competency in systems-based practice and practice-based learning and improvement: a preliminary investigation.

PubMed

Varkey, Prathibha; Natt, Neena; Lesnick, Timothy; Downing, Steven; Yudkowsky, Rachel

2008-08-01

To determine the psychometric properties and validity of an OSCE to assess the competencies of Practice-Based Learning and Improvement (PBLI) and Systems-Based Practice (SBP) in graduate medical education. An eight-station OSCE was piloted at the end of a three-week Quality Improvement elective for nine preventive medicine and endocrinology fellows at Mayo Clinic. The stations assessed performance in quality measurement, root cause analysis, evidence-based medicine, insurance systems, team collaboration, prescription errors, Nolan's model, and negotiation. Fellows' performance in each of the stations was assessed by three faculty experts using checklists and a five-point global competency scale. A modified Angoff procedure was used to set standards. Evidence for the OSCE's validity, feasibility, and acceptability was gathered. Evidence for content and response process validity was judged as excellent by institutional content experts. Interrater reliability of scores ranged from 0.85 to 1 for most stations. Interstation correlation coefficients ranged from -0.62 to 0.99, reflecting case specificity. Implementation cost was approximately $255 per fellow. All faculty members agreed that the OSCE was realistic and capable of providing accurate assessments. The OSCE provides an opportunity to systematically sample the different subdomains of Quality Improvement. Furthermore, the OSCE provides an opportunity for the demonstration of skills rather than the testing of knowledge alone, thus making it a potentially powerful assessment tool for SBP and PBLI. The study OSCE was well suited to assess SBP and PBLI. The evidence gathered through this study lays the foundation for future validation work.

Guiding dental student learning and assessing performance in critical thinking with analysis of emerging strategies.

PubMed

Johnsen, David C; Lipp, Mitchell J; Finkelstein, Michael W; Cunningham-Ford, Marsha A

2012-12-01

Patient-centered care involves an inseparable set of knowledge, abilities, and professional traits on the part of the health care provider. For practical reasons, health professions education is segmented into disciplines or domains like knowledge, technical skills, and critical thinking, and the culture of dental education is weighted toward knowledge and technical skills. Critical thinking, however, has become a growing presence in dental curricula. To guide student learning and assess performance in critical thinking, guidelines have been developed over the past several decades in the educational literature. Prominent among these guidelines are the following: engage the student in multiple situations/exercises reflecting critical thinking; for each exercise, emulate the intended activity for validity; gain agreement of faculty members across disciplines and curriculum years on the learning construct, application, and performance assessment protocol for reliability; and use the same instrument to guide learning and assess performance. The purposes of this article are 1) to offer a set of concepts from the education literature potentially helpful to guide program design or corroborate existing programs in dental education; 2) to offer an implementation model consolidating these concepts as a guide for program design and execution; 3) to cite specific examples of exercises and programs in critical thinking in the dental education literature analyzed against these concepts; and 4) to discuss opportunities and challenges in guiding student learning and assessing performance in critical thinking for dentistry.

The Development of Learning Management System Using Edmodo

NASA Astrophysics Data System (ADS)

Joko; Septia Wulandari, Gayuh

2018-04-01

The development of Learning Management System (LMS) can be used as an online learning media by managing the teacher in delivering the material and giving a task. This study aims to: 1) to know the validity of learning devices using LMS with Edmodo, 2) know the student’s response to LMS implementation using Edmodo, and 3) to know the difference of the learning outcome that is students who learned by using LMS with Edmodo and Direct Learning Model (DLM). This research method is quasi experimental by using control group pretest-posttest design. The population of the study was the student at SMKN 1 Sidoarjo. Research sample X TITL 1 class as control goup, and X TITL 2 class as experimental group. The researcher used scale rating to analyze the data validity and students’ respon, and t-test was used to examine the difference of learning outcomes with significant 0.05. The result of the research shows: 1) the average learning device validity use Edmodo 88.14%, lesson plan validity is 92.45%, pretest-posttest validity is 89.15%, learning material validity is 84.64%, and affective and psychomotor-portfolio observation sheets validity is 86.33 included very good criteria or very suitable to be used for research; 2) the result of students’ response questionnaire after taught by using LMS with Edmodo 86.03% in very good category and students agreed that Edmodo can be used in learning; and 3) the learning outcome of LMS by using Edmodo with DLM are: a) there are significant difference of the student cognitive learning outcome which is taught by using Edmodo with the student who use DLM. The average of student learning outcome that is taught LMS using Edmodo is 81.69 compared to student with DLM outcome 76.39, b) there is difference of affective learning outcome that is taught LMS using Edmodo compared to student using DLM. The average of student learning outcomeof affective that is taught LMS by using Edmodo is 83.50 compared students who use DLM 80.34, and c) there is difference of student psychomotor learning outcome that is taught with LMS using Edmodo compared student who use DLM. The average of student learning outcome that is taught with LMS using Edmodo is 85.60 compared to student who uses DLM 82.31.

Predicting the survival of diabetes using neural network

NASA Astrophysics Data System (ADS)

Mamuda, Mamman; Sathasivam, Saratha

2017-08-01

Data mining techniques at the present time are used in predicting diseases of health care industries. Neural Network is one among the prevailing method in data mining techniques of an intelligent field for predicting diseases in health care industries. This paper presents a study on the prediction of the survival of diabetes diseases using different learning algorithms from the supervised learning algorithms of neural network. Three learning algorithms are considered in this study: (i) The levenberg-marquardt learning algorithm (ii) The Bayesian regulation learning algorithm and (iii) The scaled conjugate gradient learning algorithm. The network is trained using the Pima Indian Diabetes Dataset with the help of MATLAB R2014(a) software. The performance of each algorithm is further discussed through regression analysis. The prediction accuracy of the best algorithm is further computed to validate the accurate prediction

Development of machine learning models for diagnosis of glaucoma.

PubMed

Kim, Seong Jae; Cho, Kyong Jin; Oh, Sejong

2017-01-01

The study aimed to develop machine learning models that have strong prediction power and interpretability for diagnosis of glaucoma based on retinal nerve fiber layer (RNFL) thickness and visual field (VF). We collected various candidate features from the examination of retinal nerve fiber layer (RNFL) thickness and visual field (VF). We also developed synthesized features from original features. We then selected the best features proper for classification (diagnosis) through feature evaluation. We used 100 cases of data as a test dataset and 399 cases of data as a training and validation dataset. To develop the glaucoma prediction model, we considered four machine learning algorithms: C5.0, random forest (RF), support vector machine (SVM), and k-nearest neighbor (KNN). We repeatedly composed a learning model using the training dataset and evaluated it by using the validation dataset. Finally, we got the best learning model that produces the highest validation accuracy. We analyzed quality of the models using several measures. The random forest model shows best performance and C5.0, SVM, and KNN models show similar accuracy. In the random forest model, the classification accuracy is 0.98, sensitivity is 0.983, specificity is 0.975, and AUC is 0.979. The developed prediction models show high accuracy, sensitivity, specificity, and AUC in classifying among glaucoma and healthy eyes. It will be used for predicting glaucoma against unknown examination records. Clinicians may reference the prediction results and be able to make better decisions. We may combine multiple learning models to increase prediction accuracy. The C5.0 model includes decision rules for prediction. It can be used to explain the reasons for specific predictions.

Learning Style Scales: a valid and reliable questionnaire.

PubMed

Abdollahimohammad, Abdolghani; Ja'afar, Rogayah

2014-01-01

Learning-style instruments assist students in developing their own learning strategies and outcomes, in eliminating learning barriers, and in acknowledging peer diversity. Only a few psychometrically validated learning-style instruments are available. This study aimed to develop a valid and reliable learning-style instrument for nursing students. A cross-sectional survey study was conducted in two nursing schools in two countries. A purposive sample of 156 undergraduate nursing students participated in the study. Face and content validity was obtained from an expert panel. The LSS construct was established using principal axis factoring (PAF) with oblimin rotation, a scree plot test, and parallel analysis (PA). The reliability of LSS was tested using Cronbach's α, corrected item-total correlation, and test-retest. Factor analysis revealed five components, confirmed by PA and a relatively clear curve on the scree plot. Component strength and interpretability were also confirmed. The factors were labeled as perceptive, solitary, analytic, competitive, and imaginative learning styles. Cronbach's α was >0.70 for all subscales in both study populations. The corrected item-total correlations were >0.30 for the items in each component. The LSS is a valid and reliable inventory for evaluating learning style preferences in nursing students in various multicultural environments.

Development and Validation of a New Measure of Faculty Assessments of Reformed Teaching and Learning Practices

ERIC Educational Resources Information Center

Ellett, Chad D.; Monsaas, Judy; Martin-Hansen, Lisa; Demir, Abdulkadir

2012-01-01

This study reports on the continued large-sample validation of the Inventory for Teaching and Learning (ITAL), a new teacher perception measure of "reformed (inquiry- and standards-based) and traditional teaching and learning" developed for use in science and mathematics classrooms. The continued validation of the ITAL used large samples…

The Third Round of the Czech Validation of the Motivated Strategies for Learning Questionnaire (MSLQ)

ERIC Educational Resources Information Center

Vaculíková, Jitka

2016-01-01

The authors present findings on the third round of the Czech validation of the Motivated Strategies for learning questionnaire (MSLQ), originally developed by Pintrich et al. (1991). The validation only covered an area designed to access motivation in self-regulated learning. Data was collected from a sample of university students in regular…

[Use of nondeclarative and automatic memory processes in motor learning: how to mitigate the effects of aging].

PubMed

Chauvel, Guillaume; Maquestiaux, François; Didierjean, André; Joubert, Sven; Dieudonné, Bénédicte; Verny, Marc

2011-12-01

Does normal aging inexorably lead to diminished motor learning abilities? This article provides an overview of the literature on the question, with particular emphasis on the functional dissociation between two sets of memory processes: declarative, effortful processes, and non-declarative, automatic processes. There is abundant evidence suggesting that aging does impair learning when past memories of former actions are required (episodic memory) and recollected through controlled processing (working memory). However, other studies have shown that aging does not impair learning when motor actions are performed non verbally and automatically (tapping procedural memory). These findings led us to hypothesize that one can minimize the impact of aging on the ability to learn new motor actions by favouring procedural learning. Recent data validating this hypothesis are presented. Our findings underline the importance of developing new motor learning strategies, which "bypass" declarative, effortful memory processes.

Learning Methodology in the Classroom to Encourage Participation

ERIC Educational Resources Information Center

Luna, Esther; Folgueiras, Pilar

2014-01-01

Service learning is a methodology that promotes the participation of citizens in their community. This article presents a brief conceptualization of citizen participation, characteristics of service learning methodology, and validation of a programme that promotes service-learning projects. This validation highlights the suitability of this…

Robotic action acquisition with cognitive biases in coarse-grained state space.

PubMed

Uragami, Daisuke; Kohno, Yu; Takahashi, Tatsuji

2016-07-01

Some of the authors have previously proposed a cognitively inspired reinforcement learning architecture (LS-Q) that mimics cognitive biases in humans. LS-Q adaptively learns under uniform, coarse-grained state division and performs well without parameter tuning in a giant-swing robot task. However, these results were shown only in simulations. In this study, we test the validity of the LS-Q implemented in a robot in a real environment. In addition, we analyze the learning process to elucidate the mechanism by which the LS-Q adaptively learns under the partially observable environment. We argue that the LS-Q may be a versatile reinforcement learning architecture, which is, despite its simplicity, easily applicable and does not require well-prepared settings. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Relatively effortless listening promotes understanding and recall of medical instructions in older adults

PubMed Central

DiDonato, Roberta M.; Surprenant, Aimée M.

2015-01-01

Communication success under adverse conditions requires efficient and effective recruitment of both bottom-up (sensori-perceptual) and top-down (cognitive-linguistic) resources to decode the intended auditory-verbal message. Employing these limited capacity resources has been shown to vary across the lifespan, with evidence indicating that younger adults out-perform older adults for both comprehension and memory of the message. This study examined how sources of interference arising from the speaker (message spoken with conversational vs. clear speech technique), the listener (hearing-listening and cognitive-linguistic factors), and the environment (in competing speech babble noise vs. quiet) interact and influence learning and memory performance using more ecologically valid methods than has been done previously. The results suggest that when older adults listened to complex medical prescription instructions with “clear speech,” (presented at audible levels through insertion earphones) their learning efficiency, immediate, and delayed memory performance improved relative to their performance when they listened with a normal conversational speech rate (presented at audible levels in sound field). This better learning and memory performance for clear speech listening was maintained even in the presence of speech babble noise. The finding that there was the largest learning-practice effect on 2nd trial performance in the conversational speech when the clear speech listening condition was first is suggestive of greater experience-dependent perceptual learning or adaptation to the speaker's speech and voice pattern in clear speech. This suggests that experience-dependent perceptual learning plays a role in facilitating the language processing and comprehension of a message and subsequent memory encoding. PMID:26106353

Teaching of anatomical sciences: A blended learning approach.

PubMed

Khalil, Mohammed K; Abdel Meguid, Eiman M; Elkhider, Ihsan A

2018-04-01

Blended learning is the integration of different learning approaches, new technologies, and activities that combine traditional face-to-face teaching methods with authentic online methodologies. Although advances in educational technology have helped to expand the selection of different pedagogies, the teaching of anatomical sciences has been challenged by implementation difficulties and other limitations. These challenges are reported to include lack of time, costs, and lack of qualified teachers. Easy access to online information and advances in technology make it possible to resolve these limitations by adopting blended learning approaches. Blended learning strategies have been shown to improve students' academic performance, motivation, attitude, and satisfaction, and to provide convenient and flexible learning. Implementation of blended learning strategies has also proved cost effective. This article provides a theoretical foundation for blended learning and proposes a validated framework for the design of blended learning activities in the teaching and learning of anatomical sciences. Clin. Anat. 31:323-329, 2018. © 2018 Wiley Periodicals, Inc. © 2018 Wiley Periodicals, Inc.

Computer Science Concept Inventories: Past and Future

ERIC Educational Resources Information Center

Taylor, C.; Zingaro, D.; Porter, L.; Webb, K. C.; Lee, C. B.; Clancy, M.

2014-01-01

Concept Inventories (CIs) are assessments designed to measure student learning of core concepts. CIs have become well known for their major impact on pedagogical techniques in other sciences, especially physics. Presently, there are no widely used, validated CIs for computer science. However, considerable groundwork has been performed in the form…

Assessing Students' Communication Skills: Validation of a Global Rating

ERIC Educational Resources Information Center

Scheffer, Simone; Muehlinghaus, Isabel; Froehmel, Annette; Ortwein, Heiderose

2008-01-01

Communication skills training is an accepted part of undergraduate medical programs nowadays. In addition to learning experiences its importance should be emphasised by performance-based assessment. As detailed checklists have been shown to be not well suited for the assessment of communication skills for different reasons, this study aimed to…

Cognitive Integrity Predicts Transitive Inference Performance Bias and Success

ERIC Educational Resources Information Center

Moses, Sandra N.; Villate, Christina; Binns, Malcolm A.; Davidson, Patrick S. R.; Ryan, Jennifer D.

2008-01-01

Transitive inference has traditionally been regarded as a relational proposition-based reasoning task, however, recent investigations question the validity of this assumption. Although some results support the use of a relational proposition-based approach, other studies find evidence for the use of associative learning. We examined whether…

Critical-Inquiry-Based-Learning: Model of Learning to Promote Critical Thinking Ability of Pre-service Teachers

NASA Astrophysics Data System (ADS)

Prayogi, S.; Yuanita, L.; Wasis

2018-01-01

This study aimed to develop Critical-Inquiry-Based-Learning (CIBL) learning model to promote critical thinking (CT) ability of preservice teachers. The CIBL learning model was developed by meeting the criteria of validity, practicality, and effectiveness. Validation of the model involves 4 expert validators through the mechanism of the focus group discussion (FGD). CIBL learning model declared valid to promote CT ability, with the validity level (Va) of 4.20 and reliability (r) of 90,1% (very reliable). The practicality of the model was evaluated when it was implemented that involving 17 of preservice teachers. The CIBL learning model had been declared practice, its measuring from learning feasibility (LF) with very good criteria (LF-score = 4.75). The effectiveness of the model was evaluated from the improvement CT ability after the implementation of the model. CT ability were evaluated using the scoring technique adapted from Ennis-Weir Critical Thinking Essay Test. The average score of CT ability on pretest is - 1.53 (uncritical criteria), whereas on posttest is 8.76 (critical criteria), with N-gain score of 0.76 (high criteria). Based on the results of this study, it can be concluded that developed CIBL learning model is feasible to promote CT ability of preservice teachers.

Concurrent Validity Between a Shared Curriculum, the Internal Medicine In-Training Examination, and the American Board of Internal Medicine Certifying Examination

PubMed Central

Sisson, Stephen D.; Bertram, Amanda; Yeh, Hsin-Chieh

2015-01-01

Background A core objective of residency education is to facilitate learning, and programs need more curricula and assessment tools with demonstrated validity evidence. Objective We sought to demonstrate concurrent validity between performance on a widely shared, ambulatory curriculum (the Johns Hopkins Internal Medicine Curriculum), the Internal Medicine In-Training Examination (IM-ITE), and the American Board of Internal Medicine Certifying Examination (ABIM-CE). Methods A cohort study of 443 postgraduate year (PGY)-3 residents at 22 academic and community hospital internal medicine residency programs using the curriculum through the Johns Hopkins Internet Learning Center (ILC). Total and percentile rank scores on ILC didactic modules were compared with total and percentile rank scores on the IM-ITE and total scores on the ABIM-CE. Results The average score on didactic modules was 80.1%; the percentile rank was 53.8. The average IM-ITE score was 64.1% with a percentile rank of 54.8. The average score on the ABIM-CE was 464. Scores on the didactic modules, IM-ITE, and ABIM-CE correlated with each other (P < .05). Residents completing greater numbers of didactic modules, regardless of scores, had higher IM-ITE total and percentile rank scores (P < .05). Resident performance on modules covering back pain, hypertension, preoperative evaluation, and upper respiratory tract infection was associated with IM-ITE percentile rank. Conclusions Performance on a widely shared ambulatory curriculum is associated with performance on the IM-ITE and the ABIM-CE. PMID:26217421

Application of Machine Learning in Postural Control Kinematics for the Diagnosis of Alzheimer's Disease

PubMed Central

Yelshyna, Darya; Bicho, Estela

2016-01-01

The use of wearable devices to study gait and postural control is a growing field on neurodegenerative disorders such as Alzheimer's disease (AD). In this paper, we investigate if machine-learning classifiers offer the discriminative power for the diagnosis of AD based on postural control kinematics. We compared Support Vector Machines (SVMs), Multiple Layer Perceptrons (MLPs), Radial Basis Function Neural Networks (RBNs), and Deep Belief Networks (DBNs) on 72 participants (36 AD patients and 36 healthy subjects) exposed to seven increasingly difficult postural tasks. The decisional space was composed of 18 kinematic variables (adjusted for age, education, height, and weight), with or without neuropsychological evaluation (Montreal cognitive assessment (MoCA) score), top ranked in an error incremental analysis. Classification results were based on threefold cross validation of 50 independent and randomized runs sets: training (50%), test (40%), and validation (10%). Having a decisional space relying solely on postural kinematics, accuracy of AD diagnosis ranged from 71.7 to 86.1%. Adding the MoCA variable, the accuracy ranged between 91 and 96.6%. MLP classifier achieved top performance in both decisional spaces. Having comprehended the interdynamic interaction between postural stability and cognitive performance, our results endorse machine-learning models as a useful tool for computer-aided diagnosis of AD based on postural control kinematics. PMID:28074090

Application of Machine Learning in Postural Control Kinematics for the Diagnosis of Alzheimer's Disease.

PubMed

Costa, Luís; Gago, Miguel F; Yelshyna, Darya; Ferreira, Jaime; David Silva, Hélder; Rocha, Luís; Sousa, Nuno; Bicho, Estela

2016-01-01

The use of wearable devices to study gait and postural control is a growing field on neurodegenerative disorders such as Alzheimer's disease (AD). In this paper, we investigate if machine-learning classifiers offer the discriminative power for the diagnosis of AD based on postural control kinematics. We compared Support Vector Machines (SVMs), Multiple Layer Perceptrons (MLPs), Radial Basis Function Neural Networks (RBNs), and Deep Belief Networks (DBNs) on 72 participants (36 AD patients and 36 healthy subjects) exposed to seven increasingly difficult postural tasks. The decisional space was composed of 18 kinematic variables (adjusted for age, education, height, and weight), with or without neuropsychological evaluation (Montreal cognitive assessment (MoCA) score), top ranked in an error incremental analysis. Classification results were based on threefold cross validation of 50 independent and randomized runs sets: training (50%), test (40%), and validation (10%). Having a decisional space relying solely on postural kinematics, accuracy of AD diagnosis ranged from 71.7 to 86.1%. Adding the MoCA variable, the accuracy ranged between 91 and 96.6%. MLP classifier achieved top performance in both decisional spaces. Having comprehended the interdynamic interaction between postural stability and cognitive performance, our results endorse machine-learning models as a useful tool for computer-aided diagnosis of AD based on postural control kinematics.

Beginning science teachers' performances: Assessment in times of reform

NASA Astrophysics Data System (ADS)

Budzinsky, Fie K.

2000-10-01

The current reform in science education and the research on effective teaching and student learning have reinforced the importance of teacher competency. To better measure performances in the teaching of science, performance assessment has been added to Connecticut's licensure process for beginning science teachers. Teaching portfolios are used to document teaching and learning over time. Portfolios, however, are not without problems. One of the major concerns with the portfolio assessment process is its subjectivity. Assessors may not have opportunities to ask clarifying or follow-up questions to enhance the interpretation of a teacher's performance. In addition, portfolios often contain components based on self-documentation, which are subjective. Furthermore, the use of portfolios raises test equity issues. These concerns present challenges for persons in charge of establishing the validity of a portfolio-based licensure process. In high-stakes decision processes, such as teaching licensure, the validity of the assessment instruments must be studied. The primary purpose of this study was to explore the criterion-related validity of the Connecticut State Department of Education's Beginning Science Teaching Portfolio by comparing the interpretations of performances from science teaching portfolios to those derived from another assessment method, the Expert Science Teaching Educational and Evaluation Model, (ESTEEM). The analysis of correlations between the Beginning Science Teaching Portfolio and ESTEEM instrument scores was the primary method for establishing support for validity. The results indicated moderate correlations between all Beginning Science Teaching Portfolio and ESTEEM category and total variables. Multiple regression was used to examine whether differences existed in beginning science teachers' performances based on gender, poverty group, school level, and science discipline taught. None of these variables significantly contributed to the explanation of variance in the ESTEEM (p > .05), but poverty group and gender were significant predictors of portfolio performances, accounting for 21% of the total variance. Finally, data from interviews, written surveys, and beginning teacher attendance records at state-supported seminars were analyzed qualitatively and quantitatively. This information provided insight about the quality and quantity of support beginning science teachers received in their efforts to document, via the science teaching portfolio, their abilities to implement the Connecticut Professional Science Teaching Standards.

VALUE: Valid Assessment of Learning in Undergraduate Education

ERIC Educational Resources Information Center

Rhodes, Terrel L.

2008-01-01

This chapter discusses the Association of American Colleges and Universities' (AAC&U's) Valid Assessment of Learning in Undergraduate Education (VALUE) project, which aims to demonstrate that faculty across the country share fundamental expectations about student learning on all of the essential learning outcomes deemed critical for student…

Self Directed Learning and Self Management. Symposium.

ERIC Educational Resources Information Center

2002

This document contains three papers from a symposium on self-directed learning and self-management. "Validating a More-Dimensional Conception of Self-Directed Learning" (Gerald A. Straka, Cornelia Schaefer) discusses the development and validation of a conception of self-directed learning as a dynamic interplay between behavior,…

Real-life memory and spatial navigation in patients with focal epilepsy: ecological validity of a virtual reality supermarket task.

PubMed

Grewe, P; Lahr, D; Kohsik, A; Dyck, E; Markowitsch, H J; Bien, C G; Botsch, M; Piefke, M

2014-02-01

Ecological assessment and training of real-life cognitive functions such as visual-spatial abilities in patients with epilepsy remain challenging. Some studies have applied virtual reality (VR) paradigms, but external validity of VR programs has not sufficiently been proven. Patients with focal epilepsy (EG, n=14) accomplished an 8-day program in a VR supermarket, which consisted of learning and buying items on a shopping list. Performance of the EG was compared with that of healthy controls (HCG, n=19). A comprehensive neuropsychological examination was administered. Real-life performance was investigated in a real supermarket. Learning in the VR supermarket was significantly impaired in the EG on different VR measures. Delayed free recall of products did not differ between the EG and the HCG. Virtual reality scores were correlated with neuropsychological measures of visual-spatial cognition, subjective estimates of memory, and performance in the real supermarket. The data indicate that our VR approach allows for the assessment of real-life visual-spatial memory and cognition in patients with focal epilepsy. The multimodal, active, and complex VR paradigm may particularly enhance visual-spatial cognitive resources. Copyright © 2013 Elsevier Inc. All rights reserved.

Learning in a Physics Classroom Community: Physics Learning Identity Construct Development, Measurement and Validation

NASA Astrophysics Data System (ADS)

Li, Sissi L.

At the university level, introductory science courses usually have high student to teacher ratios which increases the challenge to meaningfully connect with students. Various curricula have been developed in physics education to actively engage students in learning through social interactions with peers and instructors in class. This learning environment demands not only conceptual understanding but also learning to be a scientist. However, the success of student learning is typically measured in test performance and course grades while assessment of student development as science learners is largely ignored. This dissertation addresses this issue with the development of an instrument towards a measure of physics learning identity (PLI) which is used to guide and complement case studies through student interviews and in class observations. Using the conceptual framework based on Etienne Wenger's communities of practice (1998), I examine the relationship between science learning and learning identity from a situated perspective in the context of a large enrollment science class as a community of practice. This conceptual framework emphasizes the central role of identity in the practices negotiated in the classroom community and in the way students figure out their trajectory as members. Using this framework, I seek to understand how the changes in student learning identity are supported by active engagement based instruction. In turn, this understanding can better facilitate the building of a productive learning community and provide a measure for achievement of the curricular learning goals in active engagement strategies. Based on the conceptual framework, I developed and validated an instrument for measuring physics learning identity in terms of student learning preferences, self-efficacy for learning physics, and self-image as a physics learner. The instrument was pilot tested with a population of Oregon State University students taking calculus based introductory physics. The responses were analyzed using principal component exploratory factor analysis. The emergent factors were analyzed to create reliable subscales to measure PLI in terms of physics learning self-efficacy and social expectations about learning. Using these subscales, I present a case study of a student who performed well in the course but resisted the identity learning goals of the curriculum. These findings are used to support the factors that emerged from the statistical analysis and suggest a potential model of the relationships between the factors describing science learning and learning identity in large enrollment college science classes. This study offers an instrument with which to measure aspects of physics learning identity and insights on how PLI might develop in a classroom community of practice.

Assessment of two different types of bias affecting the results of outcome-based evaluation in undergraduate medical education.

PubMed

Schiekirka, Sarah; Anders, Sven; Raupach, Tobias

2014-07-21

Estimating learning outcome from comparative student self-ratings is a reliable and valid method to identify specific strengths and shortcomings in undergraduate medical curricula. However, requiring students to complete two evaluation forms (i.e. one before and one after teaching) might adversely affect response rates. Alternatively, students could be asked to rate their initial performance level retrospectively. This approach might threaten the validity of results due to response shift or effort justification bias. Two consecutive cohorts of medical students enrolled in a six-week cardio-respiratory module were enrolled in this study. In both cohorts, performance gain was estimated for 33 specific learning objectives. In the first cohort, outcomes calculated from ratings provided before (pretest) and after (posttest) teaching were compared to outcomes derived from comparative self-ratings collected after teaching only (thentest and posttest). In the second cohort, only thentests and posttests were used to calculate outcomes, but data collection tools differed with regard to item presentation. In one group, thentest and posttest ratings were obtained sequentially on separate forms while in the other, both ratings were obtained simultaneously for each learning objective. Using thentest ratings to calculate performance gain produced slightly higher values than using true pretest ratings. Direct comparison of then- and posttest ratings also yielded slightly higher performance gain than sequential ratings, but this effect was negligibly small. Given the small effect sizes, using thentests appears to be equivalent to using true pretest ratings. Item presentation in the posttest does not significantly impact on results.

Assessment of two different types of bias affecting the results of outcome-based evaluation in undergraduate medical education

PubMed Central

2014-01-01

Background Estimating learning outcome from comparative student self-ratings is a reliable and valid method to identify specific strengths and shortcomings in undergraduate medical curricula. However, requiring students to complete two evaluation forms (i.e. one before and one after teaching) might adversely affect response rates. Alternatively, students could be asked to rate their initial performance level retrospectively. This approach might threaten the validity of results due to response shift or effort justification bias. Methods Two consecutive cohorts of medical students enrolled in a six-week cardio-respiratory module were enrolled in this study. In both cohorts, performance gain was estimated for 33 specific learning objectives. In the first cohort, outcomes calculated from ratings provided before (pretest) and after (posttest) teaching were compared to outcomes derived from comparative self-ratings collected after teaching only (thentest and posttest). In the second cohort, only thentests and posttests were used to calculate outcomes, but data collection tools differed with regard to item presentation. In one group, thentest and posttest ratings were obtained sequentially on separate forms while in the other, both ratings were obtained simultaneously for each learning objective. Results Using thentest ratings to calculate performance gain produced slightly higher values than using true pretest ratings. Direct comparison of then- and posttest ratings also yielded slightly higher performance gain than sequential ratings, but this effect was negligibly small. Conclusions Given the small effect sizes, using thentests appears to be equivalent to using true pretest ratings. Item presentation in the posttest does not significantly impact on results. PMID:25043503

Evaluation of different machine learning models for predicting and mapping the susceptibility of gully erosion

NASA Astrophysics Data System (ADS)

Rahmati, Omid; Tahmasebipour, Nasser; Haghizadeh, Ali; Pourghasemi, Hamid Reza; Feizizadeh, Bakhtiar

2017-12-01

Gully erosion constitutes a serious problem for land degradation in a wide range of environments. The main objective of this research was to compare the performance of seven state-of-the-art machine learning models (SVM with four kernel types, BP-ANN, RF, and BRT) to model the occurrence of gully erosion in the Kashkan-Poldokhtar Watershed, Iran. In the first step, a gully inventory map consisting of 65 gully polygons was prepared through field surveys. Three different sample data sets (S1, S2, and S3), including both positive and negative cells (70% for training and 30% for validation), were randomly prepared to evaluate the robustness of the models. To model the gully erosion susceptibility, 12 geo-environmental factors were selected as predictors. Finally, the goodness-of-fit and prediction skill of the models were evaluated by different criteria, including efficiency percent, kappa coefficient, and the area under the ROC curves (AUC). In terms of accuracy, the RF, RBF-SVM, BRT, and P-SVM models performed excellently both in the degree of fitting and in predictive performance (AUC values well above 0.9), which resulted in accurate predictions. Therefore, these models can be used in other gully erosion studies, as they are capable of rapidly producing accurate and robust gully erosion susceptibility maps (GESMs) for decision-making and soil and water management practices. Furthermore, it was found that performance of RF and RBF-SVM for modelling gully erosion occurrence is quite stable when the learning and validation samples are changed.

Cross Cultural Perspectives of the Learning Organization: Assessing the Validity and Reliability of the DLOQ in Korea

ERIC Educational Resources Information Center

Song, Ji Hoon; Kim, Jin Yong; Chermack, Thomas J.; Yang; Baiyin

2008-01-01

The primary purpose of this research was to adapt the Dimensions of Learning Organization Questionnaire (DLOQ) from Watkins and Marsick (1993, 1996) and examine its validity and reliability in a Korean context. Results indicate that the DLOQ produces valid and reliable scores of learning organization characteristics in a Korean cultural context.…

Virtual reality cataract surgery training: learning curves and concurrent validity.

PubMed

Selvander, Madeleine; Åsman, Peter

2012-08-01

To investigate initial learning curves on a virtual reality (VR) eye surgery simulator and whether achieved skills are transferable between tasks. Thirty-five medical students were randomized to complete ten iterations on either the VR Caspulorhexis module (group A) or the Cataract navigation training module (group B) and then two iterations on the other module. Learning curves were compared between groups. The second Capsulorhexis video was saved and evaluated with the performance rating tool Objective Structured Assessment of Cataract Surgical Skill (OSACSS). The students' stereoacuity was examined. Both groups demonstrated significant improvements in performance over the 10 iterations: group A for all parameters analysed including score (p < 0.0001), time (p < 0.0001) and corneal damage (p = 0.0003), group B for time (p < 0.0001), corneal damage (p < 0.0001) but not for score (p = 0.752). Training on one module did not improve performance on the other. Capsulorhexis score correlated significantly with evaluation of the videos using the OSACSS performance rating tool. For stereoacuity < and ≥120 seconds of arc, sum of both modules' second iteration score was 73.5 and 41.0, respectively (p = 0.062). An initial rapid improvement in performance on a simulator with repeated practice was shown. For capsulorhexis, 10 iterations with only simulator feedback are not enough to reach a plateau for overall score. Skills transfer between modules was not found suggesting benefits from training on both modules. Stereoacuity may be of importance in the recruitment and training of new cataract surgeons. Additional studies are needed to investigate this further. Concurrent validity was found for Capsulorhexis module. © 2010 The Authors. Acta Ophthalmologica © 2010 Acta Ophthalmologica Scandinavica Foundation.

Development and implementation of a virtual reality laparoscopic colorectal training curriculum.

PubMed

Wynn, Greg; Lykoudis, Panagis; Berlingieri, Pasquale

2017-12-12

Contemporary surgical training can be compromised by fewer practical opportunities. Simulation can fill this gap to optimize skills' development and progress monitoring. A structured virtual reality (VR) laparoscopic sigmoid colectomy curriculum is constructed and its validity and outcomes assessed. Parameters and thresholds were defined by analysing the performance of six expert surgeons completing the relevant module on the LAP Mentor simulator. Fourteen surgical trainees followed the curriculum, performance being recorded and analysed. Evidence of validity was assessed. Time to complete procedure, number of movements of right and left instrument, and total path length of right and left instrument movements demonstrated evidence of validity and clear learning curves, with a median of 14 attempts needed to complete the curriculum. A structured curriculum is proposed for training in laparoscopic sigmoid colectomy in a VR environment based on objective metrics in addition to expert consensus. Validity has been demonstrated for some key metrics. Copyright © 2017 Elsevier Inc. All rights reserved.

Validating a Technology Enhanced Student-Centered Learning Model

ERIC Educational Resources Information Center

Kang, Myunghee; Hahn, Jungsun; Chung, Warren

2015-01-01

The Technology Enhanced Student Centered Learning (TESCL) Model in this study presents the core factors that ensure the quality of learning in a technology-supported environment. Although the model was conceptually constructed using a student-centered learning framework and drawing upon previous studies, it should be validated through real-world…

Machine Learning Principles Can Improve Hip Fracture Prediction.

PubMed

Kruse, Christian; Eiken, Pia; Vestergaard, Peter

2017-04-01

Apply machine learning principles to predict hip fractures and estimate predictor importance in Dual-energy X-ray absorptiometry (DXA)-scanned men and women. Dual-energy X-ray absorptiometry data from two Danish regions between 1996 and 2006 were combined with national Danish patient data to comprise 4722 women and 717 men with 5 years of follow-up time (original cohort n = 6606 men and women). Twenty-four statistical models were built on 75% of data points through k-5, 5-repeat cross-validation, and then validated on the remaining 25% of data points to calculate area under the curve (AUC) and calibrate probability estimates. The best models were retrained with restricted predictor subsets to estimate the best subsets. For women, bootstrap aggregated flexible discriminant analysis ("bagFDA") performed best with a test AUC of 0.92 [0.89; 0.94] and well-calibrated probabilities following Naïve Bayes adjustments. A "bagFDA" model limited to 11 predictors (among them bone mineral densities (BMD), biochemical glucose measurements, general practitioner and dentist use) achieved a test AUC of 0.91 [0.88; 0.93]. For men, eXtreme Gradient Boosting ("xgbTree") performed best with a test AUC of 0.89 [0.82; 0.95], but with poor calibration in higher probabilities. A ten predictor subset (BMD, biochemical cholesterol and liver function tests, penicillin use and osteoarthritis diagnoses) achieved a test AUC of 0.86 [0.78; 0.94] using an "xgbTree" model. Machine learning can improve hip fracture prediction beyond logistic regression using ensemble models. Compiling data from international cohorts of longer follow-up and performing similar machine learning procedures has the potential to further improve discrimination and calibration.

Translating Theory Into Practice: Implementing a Program of Assessment.

PubMed

Hauer, Karen E; O'Sullivan, Patricia S; Fitzhenry, Kristen; Boscardin, Christy

2018-03-01

A program of assessment addresses challenges in learner assessment using a centrally planned, coordinated approach that emphasizes assessment for learning. This report describes the steps taken to implement a program of assessment framework within a medical school. A literature review on best practices in assessment highlighted six principles that guided implementation of the program of assessment in 2016-2017: (1) a centrally coordinated plan for assessment aligns with and supports a curricular vision; (2) multiple assessment tools used longitudinally generate multiple data points; (3) learners require ready access to information-rich feedback to promote reflection and informed self-assessment; (4) mentoring is essential to facilitate effective data use for reflection and learning planning; (5) the program of assessment fosters self-regulated learning behaviors; and (6) expert groups make summative decisions about grades and readiness for advancement. Implementation incorporated stakeholder engagement, use of multiple assessment tools, design of a coaching program, and creation of a learner performance dashboard. The assessment team monitors adherence to principles defining the program of assessment and gathers and responds to regular feedback from key stakeholders, including faculty, staff, and students. Next steps include systematically collecting evidence for validity of individual assessments and the program overall. Iterative review of student performance data informs curricular improvements. The program of assessment also highlights technology needs that will be addressed with information technology experts. The outcome ultimately will entail showing evidence of validity that the program produces physicians who engage in lifelong learning and provide high-quality patient care.

Novel word acquisition in aphasia: Facing the word-referent ambiguity of natural language learning contexts.

PubMed

Peñaloza, Claudia; Mirman, Daniel; Tuomiranta, Leena; Benetello, Annalisa; Heikius, Ida-Maria; Järvinen, Sonja; Majos, Maria C; Cardona, Pedro; Juncadella, Montserrat; Laine, Matti; Martin, Nadine; Rodríguez-Fornells, Antoni

2016-06-01

Recent research suggests that some people with aphasia preserve some ability to learn novel words and to retain them in the long-term. However, this novel word learning ability has been studied only in the context of single word-picture pairings. We examined the ability of people with chronic aphasia to learn novel words using a paradigm that presents new word forms together with a limited set of different possible visual referents and requires the identification of the correct word-object associations on the basis of online feedback. We also studied the relationship between word learning ability and aphasia severity, word processing abilities, and verbal short-term memory (STM). We further examined the influence of gross lesion location on new word learning. The word learning task was first validated with a group of forty-five young adults. Fourteen participants with chronic aphasia were administered the task and underwent tests of immediate and long-term recognition memory at 1 week. Their performance was compared to that of a group of fourteen matched controls using growth curve analysis. The learning curve and recognition performance of the aphasia group was significantly below the matched control group, although above-chance recognition performance and case-by-case analyses indicated that some participants with aphasia had learned the correct word-referent mappings. Verbal STM but not word processing abilities predicted word learning ability after controlling for aphasia severity. Importantly, participants with lesions in the left frontal cortex performed significantly worse than participants with lesions that spared the left frontal region both during word learning and on the recognition tests. Our findings indicate that some people with aphasia can preserve the ability to learn a small novel lexicon in an ambiguous word-referent context. This learning and recognition memory ability was associated with verbal STM capacity, aphasia severity and the integrity of the left inferior frontal region. Copyright © 2016 Elsevier Ltd. All rights reserved.

Novel word acquisition in aphasia: Facing the word-referent ambiguity of natural language learning contexts

PubMed Central

Peñaloza, Claudia; Mirman, Daniel; Tuomiranta, Leena; Benetello, Annalisa; Heikius, Ida-Maria; Järvinen, Sonja; Majos, Maria C.; Cardona, Pedro; Juncadella, Montserrat; Laine, Matti; Martin, Nadine; Rodríguez-Fornells, Antoni

2017-01-01

Recent research suggests that some people with aphasia preserve some ability to learn novel words and to retain them in the long-term. However, this novel word learning ability has been studied only in the context of single word-picture pairings. We examined the ability of people with chronic aphasia to learn novel words using a paradigm that presents new word forms together with a limited set of different possible visual referents and requires the identification of the correct word-object associations on the basis of online feedback. We also studied the relationship between word learning ability and aphasia severity, word processing abilities, and verbal short-term memory (STM). We further examined the influence of gross lesion location on new word learning. The word learning task was first validated with a group of forty-five young adults. Fourteen participants with chronic aphasia were administered the task and underwent tests of immediate and long-term recognition memory at 1 week. Their performance was compared to that of a group of fourteen matched controls using growth curve analysis. The learning curve and recognition performance of the aphasia group was significantly below the matched control group, although above-chance recognition performance and case-by-case analyses indicated that some participants with aphasia had learned the correct word-referent mappings. Verbal STM but not word processing abilities predicted word learning ability after controlling for aphasia severity. Importantly, participants with lesions in the left frontal cortex performed significantly worse than participants with lesions that spared the left frontal region both during word learning and on the recognition tests. Our findings indicate that some people with aphasia can preserve the ability to learn a small novel lexicon in an ambiguous word-referent context. This learning and recognition memory ability was associated with verbal STM capacity, aphasia severity and the integrity of the left inferior frontal region. PMID:27085892

Implementing the Science Assessment Standards: Developing and validating a set of laboratory assessment tasks in high school biology

NASA Astrophysics Data System (ADS)

Saha, Gouranga Chandra

Very often a number of factors, especially time, space and money, deter many science educators from using inquiry-based, hands-on, laboratory practical tasks as alternative assessment instruments in science. A shortage of valid inquiry-based laboratory tasks for high school biology has been cited. Driven by this need, this study addressed the following three research questions: (1) How can laboratory-based performance tasks be designed and developed that are doable by students for whom they are designed/written? (2) Do student responses to the laboratory-based performance tasks validly represent at least some of the intended process skills that new biology learning goals want students to acquire? (3) Are the laboratory-based performance tasks psychometrically consistent as individual tasks and as a set? To answer these questions, three tasks were used from the six biology tasks initially designed and developed by an iterative process of trial testing. Analyses of data from 224 students showed that performance-based laboratory tasks that are doable by all students require careful and iterative process of development. Although the students demonstrated more skill in performing than planning and reasoning, their performances at the item level were very poor for some items. Possible reasons for the poor performances have been discussed and suggestions on how to remediate the deficiencies have been made. Empirical evidences for validity and reliability of the instrument have been presented both from the classical and the modern validity criteria point of view. Limitations of the study have been identified. Finally implications of the study and directions for further research have been discussed.

A cross-cultural validation of the Technology-Rich Outcomes-Focused Learning Environment Inventory (TROFLEI) in Turkey and the USA

NASA Astrophysics Data System (ADS)

Welch, Anita G.; Cakir, Mustafa; Peterson, Claudette M.; Ray, Chris M.

2012-04-01

Background . Studies exploring the relationship between students' achievement and the quality of the classroom learning environments have shown that there is a strong relationship between these two concepts. Learning environment instruments are constantly being revised and updated, including for use in different cultures, which requires continued validation efforts. Purpose The purpose of this study was to establish cross-cultural reliability and validity of the Technology-Rich Outcomes-Focused Learning Environment Inventory (TROFLEI) in both Turkey and the USA. Sample Approximately 980 students attending grades 9-12 in Turkey and 130 students attending grades 9-12 in the USA participated in the study. Design and method Scale reliability analyses and confirmatory factor analysis (CFA) were performed separately for Turkish and US participants for both actual and preferred responses to each scale to confirm the structure of the TROFLEI across these two distinct samples. Results Cronbach's alpha reliability coefficients, ranging from α = 0.820 to 0.931 for Turkish participants and from α = 0.778 to 0.939 for US participants, indicated that all scales have satisfactory internal consistency for both samples. Confirmatory factor analyses resulted in evidence of adequate model fit across both samples for both actual and preferred responses, with the root mean square error of approximation ranging from 0.052 to 0.057 and the comparative fit index ranging from 0.920 to 0.982. Conclusions This study provides initial evidence that the TROFLEI is valid for use in both the Turkish and US high-school populations (grades 9-12). However, the psychometric properties should be examined further with different populations, such as middle-school students (grades 6-8).

Nonverbal Cognitive Development in Children With Cochlear Implants: Relationship Between the Mullen Scales of Early Learning and Later Performance on the Leiter International Performance Scales–Revised

PubMed Central

Caudle, Susan E.; Katzenstein, Jennifer M.; Oghalai, John S.; Lin, Jerry; Caudle, Donald D.

2013-01-01

Methodologically, longitudinal assessment of cognitive development in young children has proven difficult because few measures span infancy through school age. This matter is further complicated when the child presents with a sensory deficit such as hearing loss. Few measures are validated in this population, and children who are evaluated for cochlear implantation are often reevaluated annually. The authors sought to evaluate the predictive validity of subscales of the Mullen Scales of Early Learning (MSEL) on Leiter International Performance Scales–Revised (LIPS-R) Full-Scale IQ scores. To further elucidate the relationship of these two measures, comparisons were also made with the Vineland Adaptive Behavior Scale–Second Edition (VABS), which provides a measure of adaptive functioning across the life span. Participants included 35 children (14 female, 21 male) who were evaluated both as part of the precandidacy process for cochlear implantation using the MSEL and VABS and following implantation with the LIPS-R and VABS. Hierarchical linear regression revealed that the MSEL Visual Reception subdomain score significantly predicted 52% of the variance in LIPS-R Full-Scale IQ scores at follow-up, F(1, 34) = 35.80, p < .0001, R2 = .52, β = .72. This result suggests that the Visual Reception subscale offers predictive validity of later LIPS-R Full-Scale IQ scores. The VABS was also significantly correlated with cognitive variables at each time point. PMID:22353228

Nonverbal cognitive development in children with cochlear implants: relationship between the Mullen Scales of Early Learning and later performance on the Leiter International Performance Scales-Revised.

PubMed

Caudle, Susan E; Katzenstein, Jennifer M; Oghalai, John S; Lin, Jerry; Caudle, Donald D

2014-02-01

Methodologically, longitudinal assessment of cognitive development in young children has proven difficult because few measures span infancy through school age. This matter is further complicated when the child presents with a sensory deficit such as hearing loss. Few measures are validated in this population, and children who are evaluated for cochlear implantation are often reevaluated annually. The authors sought to evaluate the predictive validity of subscales of the Mullen Scales of Early Learning (MSEL) on Leiter International Performance Scales-Revised (LIPS-R) Full-Scale IQ scores. To further elucidate the relationship of these two measures, comparisons were also made with the Vineland Adaptive Behavior Scale-Second Edition (VABS), which provides a measure of adaptive functioning across the life span. Participants included 35 children (14 female, 21 male) who were evaluated both as part of the precandidacy process for cochlear implantation using the MSEL and VABS and following implantation with the LIPS-R and VABS. Hierarchical linear regression revealed that the MSEL Visual Reception subdomain score significantly predicted 52% of the variance in LIPS-R Full-Scale IQ scores at follow-up, F(1, 34) = 35.80, p < .0001, R (2) = .52, β = .72. This result suggests that the Visual Reception subscale offers predictive validity of later LIPS-R Full-Scale IQ scores. The VABS was also significantly correlated with cognitive variables at each time point.

Applications of machine learning in cancer prediction and prognosis.

PubMed

Cruz, Joseph A; Wishart, David S

2007-02-11

Machine learning is a branch of artificial intelligence that employs a variety of statistical, probabilistic and optimization techniques that allows computers to "learn" from past examples and to detect hard-to-discern patterns from large, noisy or complex data sets. This capability is particularly well-suited to medical applications, especially those that depend on complex proteomic and genomic measurements. As a result, machine learning is frequently used in cancer diagnosis and detection. More recently machine learning has been applied to cancer prognosis and prediction. This latter approach is particularly interesting as it is part of a growing trend towards personalized, predictive medicine. In assembling this review we conducted a broad survey of the different types of machine learning methods being used, the types of data being integrated and the performance of these methods in cancer prediction and prognosis. A number of trends are noted, including a growing dependence on protein biomarkers and microarray data, a strong bias towards applications in prostate and breast cancer, and a heavy reliance on "older" technologies such artificial neural networks (ANNs) instead of more recently developed or more easily interpretable machine learning methods. A number of published studies also appear to lack an appropriate level of validation or testing. Among the better designed and validated studies it is clear that machine learning methods can be used to substantially (15-25%) improve the accuracy of predicting cancer susceptibility, recurrence and mortality. At a more fundamental level, it is also evident that machine learning is also helping to improve our basic understanding of cancer development and progression.

Interactive learning media based on flash for basic electronic engineering development for SMK Negeri 1 Driyorejo - Gresik

NASA Astrophysics Data System (ADS)

Mandigo Anggana Raras, Gustav

2018-04-01

This research aims to produce a product in the form of flash based interactive learning media on a basic electronic engineering subject that reliable to be used and to know students’ responses about the media. The target of this research is X-TEI 1 class at SMK Negeri 1 Driyorejo – Gresik. The method used in this study is R&D that has been limited into seven stages only (1) potential and problems, (2) data collection, (3) product design, (4) product validation, (5) product revision, (6) field test, and (7) analysis and writing. The obtained result is interactive learning media named MELDASH. Validation process used to produce a valid interactive learning media. The result of media validation state that the interactive learning media has a 90.83% rating. Students’ responses to this interactive learning media is really good with 88.89% rating.

Validity and Reliability Testing of an e-learning Questionnaire for Chemistry Instruction

NASA Astrophysics Data System (ADS)

Guspatni, G.; Kurniawati, Y.

2018-04-01

The aim of this paper is to examine validity and reliability of a questionnaire used to evaluate e-learning implementation in chemistry instruction. 48 questionnaires were filled in by students who had studied chemistry through e-learning system. The questionnaire consisted of 20 indicators evaluating students’ perception on using e-learning. Parametric testing was done as data were assumed to follow normal distribution. Item validity of the questionnaire was examined through item-total correlation using Pearson’s formula while its reliability was assessed with Cronbach’s alpha formula. Moreover, convergent validity was assessed to see whether indicators building a factor had theoretically the same underlying construct. The result of validity testing revealed 19 valid indicators while the result of reliability testing revealed Cronbach’s alpha value of .886. The result of factor analysis showed that questionnaire consisted of five factors, and each of them had indicators building the same construct. This article shows the importance of factor analysis to get a construct valid questionnaire before it is used as research instrument.

Comparing statistical and machine learning classifiers: alternatives for predictive modeling in human factors research.

PubMed

Carnahan, Brian; Meyer, Gérard; Kuntz, Lois-Ann

2003-01-01

Multivariate classification models play an increasingly important role in human factors research. In the past, these models have been based primarily on discriminant analysis and logistic regression. Models developed from machine learning research offer the human factors professional a viable alternative to these traditional statistical classification methods. To illustrate this point, two machine learning approaches--genetic programming and decision tree induction--were used to construct classification models designed to predict whether or not a student truck driver would pass his or her commercial driver license (CDL) examination. The models were developed and validated using the curriculum scores and CDL exam performances of 37 student truck drivers who had completed a 320-hr driver training course. Results indicated that the machine learning classification models were superior to discriminant analysis and logistic regression in terms of predictive accuracy. Actual or potential applications of this research include the creation of models that more accurately predict human performance outcomes.

Impact of statistical learning methods on the predictive power of multivariate normal tissue complication probability models.

PubMed

Xu, Cheng-Jian; van der Schaaf, Arjen; Schilstra, Cornelis; Langendijk, Johannes A; van't Veld, Aart A

2012-03-15

To study the impact of different statistical learning methods on the prediction performance of multivariate normal tissue complication probability (NTCP) models. In this study, three learning methods, stepwise selection, least absolute shrinkage and selection operator (LASSO), and Bayesian model averaging (BMA), were used to build NTCP models of xerostomia following radiotherapy treatment for head and neck cancer. Performance of each learning method was evaluated by a repeated cross-validation scheme in order to obtain a fair comparison among methods. It was found that the LASSO and BMA methods produced models with significantly better predictive power than that of the stepwise selection method. Furthermore, the LASSO method yields an easily interpretable model as the stepwise method does, in contrast to the less intuitive BMA method. The commonly used stepwise selection method, which is simple to execute, may be insufficient for NTCP modeling. The LASSO method is recommended. Copyright © 2012 Elsevier Inc. All rights reserved.

Digital mammographic tumor classification using transfer learning from deep convolutional neural networks.

PubMed

Huynh, Benjamin Q; Li, Hui; Giger, Maryellen L

2016-07-01

Convolutional neural networks (CNNs) show potential for computer-aided diagnosis (CADx) by learning features directly from the image data instead of using analytically extracted features. However, CNNs are difficult to train from scratch for medical images due to small sample sizes and variations in tumor presentations. Instead, transfer learning can be used to extract tumor information from medical images via CNNs originally pretrained for nonmedical tasks, alleviating the need for large datasets. Our database includes 219 breast lesions (607 full-field digital mammographic images). We compared support vector machine classifiers based on the CNN-extracted image features and our prior computer-extracted tumor features in the task of distinguishing between benign and malignant breast lesions. Five-fold cross validation (by lesion) was conducted with the area under the receiver operating characteristic (ROC) curve as the performance metric. Results show that classifiers based on CNN-extracted features (with transfer learning) perform comparably to those using analytically extracted features [area under the ROC curve [Formula: see text

Online Cross-Validation-Based Ensemble Learning

PubMed Central

Benkeser, David; Ju, Cheng; Lendle, Sam; van der Laan, Mark

2017-01-01

Online estimators update a current estimate with a new incoming batch of data without having to revisit past data thereby providing streaming estimates that are scalable to big data. We develop flexible, ensemble-based online estimators of an infinite-dimensional target parameter, such as a regression function, in the setting where data are generated sequentially by a common conditional data distribution given summary measures of the past. This setting encompasses a wide range of time-series models and as special case, models for independent and identically distributed data. Our estimator considers a large library of candidate online estimators and uses online cross-validation to identify the algorithm with the best performance. We show that by basing estimates on the cross-validation-selected algorithm, we are asymptotically guaranteed to perform as well as the true, unknown best-performing algorithm. We provide extensions of this approach including online estimation of the optimal ensemble of candidate online estimators. We illustrate excellent performance of our methods using simulations and a real data example where we make streaming predictions of infectious disease incidence using data from a large database. PMID:28474419

MetaKTSP: a meta-analytic top scoring pair method for robust cross-study validation of omics prediction analysis.

PubMed

Kim, SungHwan; Lin, Chien-Wei; Tseng, George C

2016-07-01

Supervised machine learning is widely applied to transcriptomic data to predict disease diagnosis, prognosis or survival. Robust and interpretable classifiers with high accuracy are usually favored for their clinical and translational potential. The top scoring pair (TSP) algorithm is an example that applies a simple rank-based algorithm to identify rank-altered gene pairs for classifier construction. Although many classification methods perform well in cross-validation of single expression profile, the performance usually greatly reduces in cross-study validation (i.e. the prediction model is established in the training study and applied to an independent test study) for all machine learning methods, including TSP. The failure of cross-study validation has largely diminished the potential translational and clinical values of the models. The purpose of this article is to develop a meta-analytic top scoring pair (MetaKTSP) framework that combines multiple transcriptomic studies and generates a robust prediction model applicable to independent test studies. We proposed two frameworks, by averaging TSP scores or by combining P-values from individual studies, to select the top gene pairs for model construction. We applied the proposed methods in simulated data sets and three large-scale real applications in breast cancer, idiopathic pulmonary fibrosis and pan-cancer methylation. The result showed superior performance of cross-study validation accuracy and biomarker selection for the new meta-analytic framework. In conclusion, combining multiple omics data sets in the public domain increases robustness and accuracy of the classification model that will ultimately improve disease understanding and clinical treatment decisions to benefit patients. An R package MetaKTSP is available online. (http://tsenglab.biostat.pitt.edu/software.htm). ctseng@pitt.edu Supplementary data are available at Bioinformatics online. © The Author 2016. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

Assessment of processing speed in children with mild TBI: a "first look" at the validity of pediatric ImPACT.

PubMed

Newman, Julie B; Reesman, Jennifer H; Vaughan, Christopher G; Gioia, Gerard A

2013-01-01

Deficit in the speed of cognitive processing is a commonly identified neuropsychological change in children recovering from a mild TBI. However, there are few validated child assessment instruments that allow for serial assessment over the course of recovery in this population. Pediatric ImPACT is a novel measure that purports to assess cognitive speed, learning, and efficiency in this population. The current study sought to validate the use of this new measure by comparing it to traditional paper and pencil measures of processing speed. One hundred and sixty-four children (71% male) age 5-12 with mild TBI evaluated in an outpatient concussion clinic were administered Pediatric ImPACT and other neuropsychological test measures as part of a flexible test battery. Performance on the Response Speed Composite of Pediatric ImPACT was more strongly associated with other measures of cognitive processing speed, than with measures of immediate/working memory and learning/memory in this sample of injured children. There is preliminary support for convergent and discriminant validity of Pediatric ImPACT as a measure for use in post-concussion evaluations of processing speed in children.

Development of a novel fingerprint for chemical reactions and its application to large-scale reaction classification and similarity.

PubMed

Schneider, Nadine; Lowe, Daniel M; Sayle, Roger A; Landrum, Gregory A

2015-01-26

Fingerprint methods applied to molecules have proven to be useful for similarity determination and as inputs to machine-learning models. Here, we present the development of a new fingerprint for chemical reactions and validate its usefulness in building machine-learning models and in similarity assessment. Our final fingerprint is constructed as the difference of the atom-pair fingerprints of products and reactants and includes agents via calculated physicochemical properties. We validated the fingerprints on a large data set of reactions text-mined from granted United States patents from the last 40 years that have been classified using a substructure-based expert system. We applied machine learning to build a 50-class predictive model for reaction-type classification that correctly predicts 97% of the reactions in an external test set. Impressive accuracies were also observed when applying the classifier to reactions from an in-house electronic laboratory notebook. The performance of the novel fingerprint for assessing reaction similarity was evaluated by a cluster analysis that recovered 48 out of 50 of the reaction classes with a median F-score of 0.63 for the clusters. The data sets used for training and primary validation as well as all python scripts required to reproduce the analysis are provided in the Supporting Information.

Attention Recognition in EEG-Based Affective Learning Research Using CFS+KNN Algorithm.

PubMed

Hu, Bin; Li, Xiaowei; Sun, Shuting; Ratcliffe, Martyn

2018-01-01

The research detailed in this paper focuses on the processing of Electroencephalography (EEG) data to identify attention during the learning process. The identification of affect using our procedures is integrated into a simulated distance learning system that provides feedback to the user with respect to attention and concentration. The authors propose a classification procedure that combines correlation-based feature selection (CFS) and a k-nearest-neighbor (KNN) data mining algorithm. To evaluate the CFS+KNN algorithm, it was test against CFS+C4.5 algorithm and other classification algorithms. The classification performance was measured 10 times with different 3-fold cross validation data. The data was derived from 10 subjects while they were attempting to learn material in a simulated distance learning environment. A self-assessment model of self-report was used with a single valence to evaluate attention on 3 levels (high, neutral, low). It was found that CFS+KNN had a much better performance, giving the highest correct classification rate (CCR) of % for the valence dimension divided into three classes.

The rat's not for turning: Dissociating the psychological components of cognitive inflexibility☆

PubMed Central

Nilsson, Simon R.O.; Alsiö, Johan; Somerville, Elizabeth M.; Clifton, Peter G.

2015-01-01

Executive function is commonly assessed by assays of cognitive flexibility such as reversal learning and attentional set-shifting. Disrupted performance in these assays, apparent in many neuropsychiatric disorders, is frequently interpreted as inability to overcome prior associations with reward. However, non-rewarded or irrelevant associations may be of considerable importance in both discrimination learning and cognitive flexibility. Non-rewarded associations can have greater influence on choice behaviour than rewarded associations in discrimination learning. Pathology-related deficits in cognitive flexibility can produce selective disruptions to both the processing of irrelevant associations and associations with reward. Genetic and pharmacological animal models demonstrate that modulation of reversal learning may result from alterations in either rewarded or non-rewarded associations. Successful performance in assays of cognitive flexibility can therefore depend on a combination of rewarded, non-rewarded, and irrelevant associations derived from previous learning, accounting for some inconsistencies observed in the literature. Taking this combination into account may increase the validity of animal models and may also reveal pathology-specific differences in problem solving and executive function. PMID:26112128

Reliability and validity of the McDonald Play Inventory.

PubMed

McDonald, Ann E; Vigen, Cheryl

2012-01-01

This study examined the ability of a two-part self-report instrument, the McDonald Play Inventory, to reliably and validly measure the play activities and play styles of 7- to 11-yr-old children and to discriminate between the play of neurotypical children and children with known learning and developmental disabilities. A total of 124 children ages 7-11 recruited from a sample of convenience and a subsample of 17 parents participated in this study. Reliability estimates yielded moderate correlations for internal consistency, total test intercorrelations, and test-retest reliability. Validity estimates were established for content and construct validity. The results suggest that a self-report instrument yields reliable and valid measures of a child's perceived play performance and discriminates between the play of children with and without disabilities. Copyright © 2012 by the American Occupational Therapy Association, Inc.

A Tool for Measuring Active Learning in the Classroom

PubMed Central

Devlin, John W.; Kirwin, Jennifer L.; Qualters, Donna M.

2007-01-01

Objectives To develop a valid and reliable active-learning inventory tool for use in large classrooms and compare faculty perceptions of active-learning using the Active-Learning Inventory Tool. Methods The Active-Learning Inventory Tool was developed using published literature and validated by national experts in educational research. Reliability was established by trained faculty members who used the Active-Learning Inventory Tool to observe 9 pharmacy lectures. Instructors were then interviewed to elicit perceptions regarding active learning and asked to share their perceptions. Results Per lecture, 13 (range: 4-34) episodes of active learning encompassing 3 (range: 2-5) different types of active learning occurred over 2.2 minutes (0.6-16) per episode. Both interobserver (≥87%) and observer-instructor agreement (≥68%) were high for these outcomes. Conclusions The Active-Learning Inventory Tool is a valid and reliable tool to measure active learning in the classroom. Future studies are needed to determine the impact of the Active-Learning Inventory Tool on teaching and its usefulness in other disciplines. PMID:17998982

A machine learning approach to triaging patients with chronic obstructive pulmonary disease

PubMed Central

Qirko, Klajdi; Smith, Ted; Corcoran, Ethan; Wysham, Nicholas G.; Bazaz, Gaurav; Kappel, George; Gerber, Anthony N.

2017-01-01

COPD patients are burdened with a daily risk of acute exacerbation and loss of control, which could be mitigated by effective, on-demand decision support tools. In this study, we present a machine learning-based strategy for early detection of exacerbations and subsequent triage. Our application uses physician opinion in a statistically and clinically comprehensive set of patient cases to train a supervised prediction algorithm. The accuracy of the model is assessed against a panel of physicians each triaging identical cases in a representative patient validation set. Our results show that algorithm accuracy and safety indicators surpass all individual pulmonologists in both identifying exacerbations and predicting the consensus triage in a 101 case validation set. The algorithm is also the top performer in sensitivity, specificity, and ppv when predicting a patient’s need for emergency care. PMID:29166411

Frontostriatal anatomical connections predict age- and difficulty-related differences in reinforcement learning.

PubMed

van de Vijver, Irene; Ridderinkhof, K Richard; Harsay, Helga; Reneman, Liesbeth; Cavanagh, James F; Buitenweg, Jessika I V; Cohen, Michael X

2016-10-01

Reinforcement learning (RL) is supported by a network of striatal and frontal cortical structures that are connected through white-matter fiber bundles. With age, the integrity of these white-matter connections declines. The role of structural frontostriatal connectivity in individual and age-related differences in RL is unclear, although local white-matter density and diffusivity have been linked to individual differences in RL. Here we show that frontostriatal tract counts in young human adults (aged 18-28), as assessed noninvasively with diffusion-weighted magnetic resonance imaging and probabilistic tractography, positively predicted individual differences in RL when learning was difficult (70% valid feedback). In older adults (aged 63-87), in contrast, learning under both easy (90% valid feedback) and difficult conditions was predicted by tract counts in the same frontostriatal network. Furthermore, network-level analyses showed a double dissociation between the task-relevant networks in young and older adults, suggesting that older adults relied on different frontostriatal networks than young adults to obtain the same task performance. These results highlight the importance of successful information integration across striatal and frontal regions during RL, especially with variable outcomes. Copyright © 2016 Elsevier Inc. All rights reserved.

Identifying Active Travel Behaviors in Challenging Environments Using GPS, Accelerometers, and Machine Learning Algorithms.

PubMed

Ellis, Katherine; Godbole, Suneeta; Marshall, Simon; Lanckriet, Gert; Staudenmayer, John; Kerr, Jacqueline

2014-01-01

Active travel is an important area in physical activity research, but objective measurement of active travel is still difficult. Automated methods to measure travel behaviors will improve research in this area. In this paper, we present a supervised machine learning method for transportation mode prediction from global positioning system (GPS) and accelerometer data. We collected a dataset of about 150 h of GPS and accelerometer data from two research assistants following a protocol of prescribed trips consisting of five activities: bicycling, riding in a vehicle, walking, sitting, and standing. We extracted 49 features from 1-min windows of this data. We compared the performance of several machine learning algorithms and chose a random forest algorithm to classify the transportation mode. We used a moving average output filter to smooth the output predictions over time. The random forest algorithm achieved 89.8% cross-validated accuracy on this dataset. Adding the moving average filter to smooth output predictions increased the cross-validated accuracy to 91.9%. Machine learning methods are a viable approach for automating measurement of active travel, particularly for measuring travel activities that traditional accelerometer data processing methods misclassify, such as bicycling and vehicle travel.

Spatial affect learning restricted in major depression relative to anxiety disorders and healthy controls.

PubMed

Gollan, Jackie K; Norris, Catherine J; Hoxha, Denada; Irick, John Stockton; Hawkley, Louise C; Cacioppo, John T

2014-01-01

Detecting and learning the location of unpleasant or pleasant scenarios, or spatial affect learning, is an essential skill that safeguards well-being (Crawford & Cacioppo, 2002). Potentially altered by psychiatric illness, this skill has yet to be measured in adults with and without major depressive disorder (MDD) and anxiety disorders (AD). This study enrolled 199 adults diagnosed with MDD and AD (n=53), MDD (n=47), AD (n=54), and no disorders (n=45). Measures included clinical interviews, self-reports, and a validated spatial affect task using affective pictures (IAPS; Lang, Bradley, & Cuthbert, 2005). Participants with MDD showed impaired spatial affect learning of negative stimuli and irrelevant learning of pleasant pictures compared with non-depressed adults. Adults with MDD may use a "GOOD is UP" heuristic reflected by their impaired learning of the opposite correlation (i.e., "BAD is UP") and performance in the pleasant version of the task.

Validation of a Spanish Version of the Distance Education Learning Environments Survey (DELES) in Spain

ERIC Educational Resources Information Center

Fernández-Pascual, Maria Dolores; Ferrer-Cascales, Rosario; Reig-Ferrer, Abilio; Albaladejo-Blázquez, Natalia; Walker, Scott L.

2015-01-01

The aim of this study was to examine the validity of the Spanish version of the Distance Education Learning Environments Survey (Sp-DELES). This instrument assesses students' perceptions of virtual learning environments using six scales: Instructor Support, Student Interaction and Collaboration, Personal Relevance, Authentic Learning, Active…

Recognition, Accreditation and Validation of Non-Formal and Informal Learning: Prospects for Lifelong Learning in Nepal

ERIC Educational Resources Information Center

Regmi, Kapil Dev

2009-01-01

This study was an exploration on the various issues related to recognition, accreditation and validation of non-formal and informal learning to open up avenues for lifelong learning and continuing education in Nepal. The perceptions, experiences, and opinions of Nepalese Development Activists, Educational Administrators, Policy Actors and…

Motor Learning as Young Gymnast's Talent Indicator.

PubMed

di Cagno, Alessandra; Battaglia, Claudia; Fiorilli, Giovanni; Piazza, Marina; Giombini, Arrigo; Fagnani, Federica; Borrione, Paolo; Calcagno, Giuseppe; Pigozzi, Fabio

2014-12-01

Talent identification plans are designed to select young athletes with the ability to achieve future success in sports. The aim of the study was to verify the predictive value of coordination and precision in skill acquisition during motor learning, as indicators of talent. One hundred gymnasts, both cadets (aged 11.5 ± 0.5 yr.) and juniors (aged 13.3 ± 0.5 years), competing at the national level, were enrolled in the study. The assessment of motor coordination involved three tests of the validated Hirtz's battery (1985), and motor skill learning involved four technical tests, specific of rhythmic gymnastics. All the tests were correlated with ranking and performance scores reached by each gymnast in the 2011, 2012, and 2013 National Championships. Coordination tests were significantly correlated to 2013 Championships scores (p < 0.01) and ranking (p < 0.05) of elite cadet athletes. Precision, in skill acquisition test results, was positively and significantly associated with scores in 2013 (adj. R(2) = 0.26, p < 0.01). Gymnasts with the best results in coordination and motor learning tests went on to achieve better competition results in three- year time. Key pointsIn talent identification and selection procedures it is better to include the evaluation of coordination and motor learning ability.Motor learning assessment concerns performance improvement and the ability to develop it, rather than evaluating the athlete's current performance.In this manner talent identification processes should be focused on the future performance capabilities of athletes.

Motor Learning as Young Gymnast’s Talent Indicator

PubMed Central

di Cagno, Alessandra; Battaglia, Claudia; Fiorilli, Giovanni; Piazza, Marina; Giombini, Arrigo; Fagnani, Federica; Borrione, Paolo; Calcagno, Giuseppe; Pigozzi, Fabio

2014-01-01

Talent identification plans are designed to select young athletes with the ability to achieve future success in sports. The aim of the study was to verify the predictive value of coordination and precision in skill acquisition during motor learning, as indicators of talent. One hundred gymnasts, both cadets (aged 11.5 ± 0.5 yr.) and juniors (aged 13.3 ± 0.5 years), competing at the national level, were enrolled in the study. The assessment of motor coordination involved three tests of the validated Hirtz’s battery (1985), and motor skill learning involved four technical tests, specific of rhythmic gymnastics. All the tests were correlated with ranking and performance scores reached by each gymnast in the 2011, 2012, and 2013 National Championships. Coordination tests were significantly correlated to 2013 Championships scores (p < 0.01) and ranking (p < 0.05) of elite cadet athletes. Precision, in skill acquisition test results, was positively and significantly associated with scores in 2013 (adj. R2 = 0.26, p < 0.01). Gymnasts with the best results in coordination and motor learning tests went on to achieve better competition results in three- year time. Key points In talent identification and selection procedures it is better to include the evaluation of coordination and motor learning ability. Motor learning assessment concerns performance improvement and the ability to develop it, rather than evaluating the athlete’s current performance. In this manner talent identification processes should be focused on the future performance capabilities of athletes. PMID:25435768

Consideration of learning orientations as an application of achievement goals in evaluating life science majors in introductory physics

NASA Astrophysics Data System (ADS)

Mason, Andrew J.; Bertram, Charles A.

2018-06-01

When considering performing an Introductory Physics for Life Sciences course transformation for one's own institution, life science majors' achievement goals are a necessary consideration to ensure the pedagogical transformation will be effective. However, achievement goals are rarely an explicit consideration in physics education research topics such as metacognition. We investigate a sample population of 218 students in a first-semester introductory algebra-based physics course, drawn from 14 laboratory sections within six semesters of course sections, to determine the influence of achievement goals on life science majors' attitudes towards physics. Learning orientations that, respectively, pertain to mastery goals and performance goals, in addition to a learning orientation that does not report a performance goal, were recorded from students in the specific context of learning a problem-solving framework during an in-class exercise. Students' learning orientations, defined within the context of students' self-reported statements in the specific context of a problem-solving-related research-based course implementation, are compared to pre-post results on physics problem-solving items in a well-established attitudinal survey instrument, in order to establish the categories' validity. In addition, mastery-related and performance-related orientations appear to extend to overall pre-post attitudinal shifts, but not to force and motion concepts or to overall course grade, within the scope of an introductory physics course. There also appears to be differentiation regarding overall course performance within health science majors, but not within biology majors, in terms of learning orientations; however, health science majors generally appear to fare less well on all measurements in the study than do biology majors, regardless of learning orientations.

The Development of English and Mathematics Self-Efficacy: A Latent Growth Curve Analysis

ERIC Educational Resources Information Center

Phan, Huy P.

2012-01-01

Empirical research has provided evidence supporting the validation and prediction of 4 major sources of self-efficacy: enactive performance accomplishments, vicarious experiences, verbal persuasion, and emotional states. Other research studies have also attested to the importance and potency of self-efficacy in academic learning and achievement.…

School Asthma Screening and Case Management: Attendance and Learning Outcomes

ERIC Educational Resources Information Center

Moricca, Michelle L.; Grasska, Merry A.; BMarthaler, Marcia; Morphew, Tricia; Weismuller, Penny C.; Galant, Stanley P.

2013-01-01

Asthma is related to school absenteeism and underperformance in elementary students. This pilot study assessed whether school nurse case management (CM) in children identified with asthma impacts academic performance and school absenteeism in one school. A validated questionnaire was used to identify children at risk for asthma and CM was provided…

The Effects of Competition on Achievement Motivation in Chinese Classrooms

ERIC Educational Resources Information Center

Lam, S-f.; Yim, P-s.; Law, J. S. F.; Cheung, R. W. Y.

2004-01-01

Background: Laboratory studies have consistently found that competition induces performance goals and affects learning motivation. However, the ecological validity of these results is yet to be established. There is a need for investigation of whether the results hold in both the classroom context and non-Western culture. Aim: The study…

Fairness and Using Reflective Journals in Assessment

ERIC Educational Resources Information Center

Clarkeburn, Henriikka; Kettula, Kirsi

2012-01-01

This study looks at the fairness of assessing learning journals both as the fairness in creating a valid and robust marking process as well as how different student groups may have unfair disadvantages in performing well in reflective assessment tasks. The fairness of a marking process is discussed through reflecting on the practical process and…

How to Assign Individualized Scores on a Group Project: An Empirical Evaluation

ERIC Educational Resources Information Center

Zhang, Bo; Ohland, Matthew W.

2009-01-01

One major challenge in using group projects to assess student learning is accounting for the differences of contribution among group members so that the mark assigned to each individual actually reflects their performance. This research addresses the validity of grading group projects by evaluating different methods that derive individualized…

Stakes Matter: Student Motivation and the Validity of Student Assessments for Teacher Evaluation

ERIC Educational Resources Information Center

Rutkowski, David; Wild, Justin

2015-01-01

In 2011, Indiana lawmakers established a system to evaluate teachers using existing standardized assessments as an indicator of student learning. In this study we examined one component of Indiana's evaluation system to determine whether student knowledge of the test's consequences is predictive of test performance. Using an experimental design,…

Student Performance in High-Stakes Examinations Based on Content Area in Senior Secondary (VCE) Physical Education

ERIC Educational Resources Information Center

Whittle, Rachael J.; Benson, Amanda C.; Ullah, Shahid; Telford, Amanda

2017-01-01

Background: Senior secondary physical education courses for certification continue to evolve with curricula reform occurring to ensure content is contemporary, student learning outcomes are maximised and assessment practices are valid for determining certification of students. The content of examinable senior secondary physical education courses…

Professional Re-Accreditation: Constructing Educational Policy for Career-Long Teacher Professional Learning

ERIC Educational Resources Information Center

Watson, Cate; Fox, Alison

2015-01-01

Competence as a measure of "fitness to practice" and its evaluation through mechanisms of personal performance review, has led to the introduction of systems in a number of professions which link appraisal to the maintenance of professional registration (variously referred to as re-validation, re-certification, re-accreditation, etc.).…

Development and Validation of a Rubric for Diagnosing Students' Experimental Design Knowledge and Difficulties

ERIC Educational Resources Information Center

Dasgupta, Annwesa P.; Anderson, Trevor R.; Pelaez, Nancy

2014-01-01

It is essential to teach students about experimental design, as this facilitates their deeper understanding of how most biological knowledge was generated and gives them tools to perform their own investigations. Despite the importance of this area, surprisingly little is known about what students actually learn from designing biological…

Mental Health Training

DTIC Science & Technology

2016-01-01

performance. The model integrates the roles of internal (personal) and external ( environmental ) resources specifically for developing , sustaining, and... through these systems. Conclusion Adult education and adult learning is most effective when curriculum is experienced- based and the instructor...synthesis, integration and validation of knowledge derived through the scientific method. In NATO, S&T is addressed using different business models

Rethinking Teachers' Goal Orientations: Conceptual and Methodological Enhancements

ERIC Educational Resources Information Center

Nitsche, Sebastian; Dickhauser, Oliver; Fasching, Michaela S.; Dresel, Markus

2011-01-01

The article provides a theoretical extension of the goal orientation approach for teaching by proposing three different competence facets of learning goals and four types of addressees for performance approach and avoidance goals. On the basis of responses from 495 teacher trainees and 224 in-service teachers, the development and validation of an…

Guided Inquiry Facilitated Blended Learning to Improve Metacognitive and Learning Outcome of High School Students

NASA Astrophysics Data System (ADS)

Suwono, H.; Susanti, S.; Lestari, U.

2017-04-01

The learning activities that involve the students to learn actively is one of the characteristics of a qualified education. The learning strategy that involves students’ active learning is guided inquiry. Learning problems today are growing metacognitive skills and cognitive learning outcomes. It is the research and development of learning module by using 4D models of Thiagarajan. The first phase is Define, which analyses the problems and needs required by the prior preparation of the module. The second phase is Design, which formulates learning design and devices to obtain the initial draft of learning modules. The third stage is Develop, which is developing and writing module, module validation, product testing, revision, and the resulting an end-product results module development. The fourth stage is Disseminate, which is disseminating of the valid products. Modules were validated by education experts, practitioners, subject matter experts, and expert of online media. The results of the validation module indicated that the module was valid and could be used in teaching and learning. In the validation phase of testing methods, we used experiments to know the difference of metacognitive skills and learning outcomes between the control group and experimental group. The experimental design was a one group pretest-posttest design. The results of the data analysis showed that the modules could enhance metacognitive skills and learning outcomes. The advantages of this module is as follows, 1) module is accompanied by a video link on a website that contains practical activities that are appropriate to Curriculum 2013, 2) module is accompanied by a video link on a website that contains about manual laboratory activities that will be used in the classroom face-to-face, so that students are ready when doing laboratory activities, 3) this module can be online through chat to increase students’ understanding. The disadvantages of this module are the material presented in the modules is limited. It is suggested that for the better utilisation of the online activities, students should be present at every meeting of the activities, so as to make all the students participate actively. It is also suggested that school set up facilities to support blended learning.

Feedback Error Learning Controller for Functional Electrical Stimulation Assistance in a Hybrid Robotic System for Reaching Rehabilitation

PubMed Central

Resquín, Francisco; Gonzalez-Vargas, Jose; Ibáñez, Jaime; Brunetti, Fernando; Pons, José Luis

2016-01-01

Hybrid robotic systems represent a novel research field, where functional electrical stimulation (FES) is combined with a robotic device for rehabilitation of motor impairment. Under this approach, the design of robust FES controllers still remains an open challenge. In this work, we aimed at developing a learning FES controller to assist in the performance of reaching movements in a simple hybrid robotic system setting. We implemented a Feedback Error Learning (FEL) control strategy consisting of a feedback PID controller and a feedforward controller based on a neural network. A passive exoskeleton complemented the FES controller by compensating the effects of gravity. We carried out experiments with healthy subjects to validate the performance of the system. Results show that the FEL control strategy is able to adjust the FES intensity to track the desired trajectory accurately without the need of a previous mathematical model. PMID:27990245

Exploring discrepancies between quantitative validation results and the geomorphic plausibility of statistical landslide susceptibility maps

NASA Astrophysics Data System (ADS)

Steger, Stefan; Brenning, Alexander; Bell, Rainer; Petschko, Helene; Glade, Thomas

2016-06-01

Empirical models are frequently applied to produce landslide susceptibility maps for large areas. Subsequent quantitative validation results are routinely used as the primary criteria to infer the validity and applicability of the final maps or to select one of several models. This study hypothesizes that such direct deductions can be misleading. The main objective was to explore discrepancies between the predictive performance of a landslide susceptibility model and the geomorphic plausibility of subsequent landslide susceptibility maps while a particular emphasis was placed on the influence of incomplete landslide inventories on modelling and validation results. The study was conducted within the Flysch Zone of Lower Austria (1,354 km2) which is known to be highly susceptible to landslides of the slide-type movement. Sixteen susceptibility models were generated by applying two statistical classifiers (logistic regression and generalized additive model) and two machine learning techniques (random forest and support vector machine) separately for two landslide inventories of differing completeness and two predictor sets. The results were validated quantitatively by estimating the area under the receiver operating characteristic curve (AUROC) with single holdout and spatial cross-validation technique. The heuristic evaluation of the geomorphic plausibility of the final results was supported by findings of an exploratory data analysis, an estimation of odds ratios and an evaluation of the spatial structure of the final maps. The results showed that maps generated by different inventories, classifiers and predictors appeared differently while holdout validation revealed similar high predictive performances. Spatial cross-validation proved useful to expose spatially varying inconsistencies of the modelling results while additionally providing evidence for slightly overfitted machine learning-based models. However, the highest predictive performances were obtained for maps that explicitly expressed geomorphically implausible relationships indicating that the predictive performance of a model might be misleading in the case a predictor systematically relates to a spatially consistent bias of the inventory. Furthermore, we observed that random forest-based maps displayed spatial artifacts. The most plausible susceptibility map of the study area showed smooth prediction surfaces while the underlying model revealed a high predictive capability and was generated with an accurate landslide inventory and predictors that did not directly describe a bias. However, none of the presented models was found to be completely unbiased. This study showed that high predictive performances cannot be equated with a high plausibility and applicability of subsequent landslide susceptibility maps. We suggest that greater emphasis should be placed on identifying confounding factors and biases in landslide inventories. A joint discussion between modelers and decision makers of the spatial pattern of the final susceptibility maps in the field might increase their acceptance and applicability.

Lessons Learned in Developing and Validating Models of Visual Search and Target Acquisition

DTIC Science & Technology

2000-03-01

n al th at d istin gu ish es th e center t x u e t a s t o h t m g t o c r w t e f c lirregularity. texture transition that might occur with a...shown in Figure 5, and it allows the model to simulate the blue squares, and red squares). Neisser and others have performance of experienced human...Processes that Affect STA features support pop-out. For example, Neisser found that after extensive training, observers can learn to rapidly pick Another

Extreme learning machines: a new approach for modeling dissolved oxygen (DO) concentration with and without water quality variables as predictors.

PubMed

Heddam, Salim; Kisi, Ozgur

2017-07-01

In this paper, several extreme learning machine (ELM) models, including standard extreme learning machine with sigmoid activation function (S-ELM), extreme learning machine with radial basis activation function (R-ELM), online sequential extreme learning machine (OS-ELM), and optimally pruned extreme learning machine (OP-ELM), are newly applied for predicting dissolved oxygen concentration with and without water quality variables as predictors. Firstly, using data from eight United States Geological Survey (USGS) stations located in different rivers basins, USA, the S-ELM, R-ELM, OS-ELM, and OP-ELM were compared against the measured dissolved oxygen (DO) using four water quality variables, water temperature, specific conductance, turbidity, and pH, as predictors. For each station, we used data measured at an hourly time step for a period of 4 years. The dataset was divided into a training set (70%) and a validation set (30%). We selected several combinations of the water quality variables as inputs for each ELM model and six different scenarios were compared. Secondly, an attempt was made to predict DO concentration without water quality variables. To achieve this goal, we used the year numbers, 2008, 2009, etc., month numbers from (1) to (12), day numbers from (1) to (31) and hour numbers from (00:00) to (24:00) as predictors. Thirdly, the best ELM models were trained using validation dataset and tested with the training dataset. The performances of the four ELM models were evaluated using four statistical indices: the coefficient of correlation (R), the Nash-Sutcliffe efficiency (NSE), the root mean squared error (RMSE), and the mean absolute error (MAE). Results obtained from the eight stations indicated that: (i) the best results were obtained by the S-ELM, R-ELM, OS-ELM, and OP-ELM models having four water quality variables as predictors; (ii) out of eight stations, the OP-ELM performed better than the other three ELM models at seven stations while the R-ELM performed the best at one station. The OS-ELM models performed the worst and provided the lowest accuracy; (iii) for predicting DO without water quality variables, the R-ELM performed the best at seven stations followed by the S-ELM in the second place and the OP-ELM performed the worst with low accuracy; (iv) for the final application where training ELM models with validation dataset and testing with training dataset, the OP-ELM provided the best accuracy using water quality variables and the R-ELM performed the best at all eight stations without water quality variables. Fourthly, and finally, we compared the results obtained from different ELM models with those obtained using multiple linear regression (MLR) and multilayer perceptron neural network (MLPNN). Results obtained using MLPNN and MLR models reveal that: (i) using water quality variables as predictors, the MLR performed the worst and provided the lowest accuracy in all stations; (ii) MLPNN was ranked in the second place at two stations, in the third place at four stations, and finally, in the fourth place at two stations, (iii) for predicting DO without water quality variables, MLPNN is ranked in the second place at five stations, and ranked in the third, fourth, and fifth places in the remaining three stations, while MLR was ranked in the last place with very low accuracy at all stations. Overall, the results suggest that the ELM is more effective than the MLPNN and MLR for modelling DO concentration in river ecosystems.

Concrete Condition Assessment Using Impact-Echo Method and Extreme Learning Machines

PubMed Central

Zhang, Jing-Kui; Yan, Weizhong; Cui, De-Mi

2016-01-01

The impact-echo (IE) method is a popular non-destructive testing (NDT) technique widely used for measuring the thickness of plate-like structures and for detecting certain defects inside concrete elements or structures. However, the IE method is not effective for full condition assessment (i.e., defect detection, defect diagnosis, defect sizing and location), because the simple frequency spectrum analysis involved in the existing IE method is not sufficient to capture the IE signal patterns associated with different conditions. In this paper, we attempt to enhance the IE technique and enable it for full condition assessment of concrete elements by introducing advanced machine learning techniques for performing comprehensive analysis and pattern recognition of IE signals. Specifically, we use wavelet decomposition for extracting signatures or features out of the raw IE signals and apply extreme learning machine, one of the recently developed machine learning techniques, as classification models for full condition assessment. To validate the capabilities of the proposed method, we build a number of specimens with various types, sizes, and locations of defects and perform IE testing on these specimens in a lab environment. Based on analysis of the collected IE signals using the proposed machine learning based IE method, we demonstrate that the proposed method is effective in performing full condition assessment of concrete elements or structures. PMID:27023563

Associative learning performance is impaired in zebrafish (Danio rerio) by the NMDA-R antagonist MK-801

PubMed Central

Sison, Margarette; Gerlai, Robert

2011-01-01

The zebrafish is gaining popularity in behavioral neuroscience perhaps because of a promise of efficient large scale mutagenesis and drug screens that could identify a substantial number of yet undiscovered molecular players involved in complex traits. Learning and memory are complex functions of the brain and the analysis of their mechanisms may benefit from such large scale zebrafish screens. One bottleneck in this research is the paucity of appropriate behavioral screening paradigms, which may be due to the relatively uncharacterized nature of the behavior of this species. Here we show that zebrafish exhibit good learning performance in a task adapted from the mammalian literature, a plus maze in which zebrafish are required to associate a neutral visual stimulus with the presence of conspecifics, the rewarding unconditioned stimulus. Furthermore, we show that MK-801, a non-competitive NMDA-R antagonist, impairs memory performance in this maze when administered right after training or just before recall but not when given before training at a dose that does not impair motor function, perception or motivation. These results suggest that the plus maze associative learning paradigm has face and construct validity and that zebrafish may become an appropriate and translationally relevant study species for the analysis of the mechanisms of vertebrate, including mammalian, learning and memory. PMID:21596149

An ecologically valid performance-based social functioning assessment battery for schizophrenia.

PubMed

Shi, Chuan; He, Yi; Cheung, Eric F C; Yu, Xin; Chan, Raymond C K

2013-12-30

Psychiatrists pay more attention to the social functioning outcome of schizophrenia nowadays. How to evaluate the real world function among schizophrenia is a challenging task due to culture difference, there is no such kind of instrument in terms of the Chinese setting. This study aimed to report the validation of an ecologically valid performance-based everyday functioning assessment for schizophrenia, namely the Beijing Performance-based Functional Ecological Test (BJ-PERFECT). Fifty community-dwelling adults with schizophrenia and 37 healthy controls were recruited. Fifteen of the healthy controls were re-tested one week later. All participants were administered the University of California, San Diego, Performance-based Skill Assessment-Brief version (UPSA-B) and the MATRICS Consensus Cognitive Battery (MCCB). The finalized assessment included three subdomains: transportation, financial management and work ability. The test-retest and inter-rater reliabilities were good. The total score significantly correlated with the UPSA-B. The performance of individuals with schizophrenia was significantly more impaired than healthy controls, especially in the domain of work ability. Among individuals with schizophrenia, functional outcome was influenced by premorbid functioning, negative symptoms and neurocognition such as processing speed, visual learning and attention/vigilance. © 2013 Elsevier Ireland Ltd. All rights reserved.

Applications of Machine Learning in Cancer Prediction and Prognosis

PubMed Central

Cruz, Joseph A.; Wishart, David S.

2006-01-01

Machine learning is a branch of artificial intelligence that employs a variety of statistical, probabilistic and optimization techniques that allows computers to “learn” from past examples and to detect hard-to-discern patterns from large, noisy or complex data sets. This capability is particularly well-suited to medical applications, especially those that depend on complex proteomic and genomic measurements. As a result, machine learning is frequently used in cancer diagnosis and detection. More recently machine learning has been applied to cancer prognosis and prediction. This latter approach is particularly interesting as it is part of a growing trend towards personalized, predictive medicine. In assembling this review we conducted a broad survey of the different types of machine learning methods being used, the types of data being integrated and the performance of these methods in cancer prediction and prognosis. A number of trends are noted, including a growing dependence on protein biomarkers and microarray data, a strong bias towards applications in prostate and breast cancer, and a heavy reliance on “older” technologies such artificial neural networks (ANNs) instead of more recently developed or more easily interpretable machine learning methods. A number of published studies also appear to lack an appropriate level of validation or testing. Among the better designed and validated studies it is clear that machine learning methods can be used to substantially (15–25%) improve the accuracy of predicting cancer susceptibility, recurrence and mortality. At a more fundamental level, it is also evident that machine learning is also helping to improve our basic understanding of cancer development and progression. PMID:19458758

Assessing College-Level Learning Difficulties and "At Riskness" for Learning Disabilities and ADHD: Development and Validation of the Learning Difficulties Assessment

ERIC Educational Resources Information Center

Kane, Steven T.; Walker, John H.; Schmidt, George R.

2011-01-01

This article describes the development and validation of the "Learning Difficulties Assessment" (LDA), a normed and web-based survey that assesses perceived difficulties with reading, writing, spelling, mathematics, listening, concentration, memory, organizational skills, sense of control, and anxiety in college students. The LDA is designed to…

The Adaptation and Validation of the CEQ and the R-SPQ-2F to the Japanese Tertiary Environment

ERIC Educational Resources Information Center

Fryer, Luke K.; Ginns, Paul; Walker, Richard A.; Nakao, Kaori

2012-01-01

Background: Student learning theory (SLT) has established associations between students' approaches to learning and their perceptions of the learning environment. SLT may provide a useful framework for researching student learning within the Japanese tertiary sector. Aims: The study aims to explore and validate the Course Experience Questionnaire…

Measuring Perceptions of the Learning Environment and Approaches to Learning: Validation of the Learn Questionnaire

ERIC Educational Resources Information Center

Herrmann, Kim Jesper; Bager-Elsborg, Anna; Parpala, Anna

2017-01-01

While focus on quality in Danish higher education has been growing in recent years, limited attention has been devoted to developing and thoroughly validating instruments that allow collecting data about university students' perceptions of the teaching-learning environment. Based on data from a large sample of Danish university students, a Danish…

Measuring comparative hospital performance.

PubMed

Griffith, John R; Alexander, Jeffrey A; Jelinek, Richard C

2002-01-01

Leading healthcare provider organizations now use a "balanced scorecard" of performance measures, expanding information reviewed at the governance level to include financial, customer, and internal performance information, as well as providing an opportunity to learn and grow to provide better strategic guidance. The approach, successfully used by other industries, uses competitor data and benchmarks to identify opportunities for improved mission achievement. This article evaluates one set of nine multidimensional hospital performance measures derived from Medicare reports (cash flow, asset turnover, mortality, complications, length of inpatient stay, cost per case, occupancy, change in occupancy, and percent of revenue from outpatient care). The study examines the content validity, reliability and sensitivity, validity of comparison, and independence and concludes that seven of the nine measures (all but the two occupancy measures) represent a potentially useful set for evaluating most U.S. hospitals. This set reflects correctable differences in performance between hospitals serving similar populations, that is, the measures reflect relative performance and identify opportunities to make the organization more successful.

The development of a virtual reality training curriculum for colonoscopy.

PubMed

Sugden, Colin; Aggarwal, Rajesh; Banerjee, Amrita; Haycock, Adam; Thomas-Gibson, Siwan; Williams, Christopher B; Darzi, Ara

2012-07-01

The development of a structured virtual reality (VR) training curriculum for colonoscopy using high-fidelity simulation. Colonoscopy requires detailed knowledge and technical skill. Changes to working practices in recent times have reduced the availability of traditional training opportunities. Much might, therefore, be achieved by applying novel technologies such as VR simulation to colonoscopy. Scientifically developed device-specific curricula aim to maximize the yield of laboratory-based training by focusing on validated modules and linking progression to the attainment of benchmarked proficiency criteria. Fifty participants comprised of 30 novices (<10 colonoscopies), 10 intermediates (100 to 500 colonoscopies), and 10 experienced (>500 colonoscopies) colonoscopists were recruited to participate. Surrogates of proficiency, such as number of procedures undertaken, determined prospective allocation to 1 of 3 groups (novice, intermediate, and experienced). Construct validity and learning value (comparison between groups and within groups respectively) for each task and metric on the chosen simulator model determined suitability for inclusion in the curriculum. Eight tasks in possession of construct validity and significant learning curves were included in the curriculum: 3 abstract tasks, 4 part-procedural tasks, and 1 procedural task. The whole-procedure task was valid for 11 metrics including the following: "time taken to complete the task" (1238, 343, and 293 s; P < 0.001) and "insertion length with embedded tip" (23.8, 3.6, and 4.9 cm; P = 0.005). Learning curves consistently plateaued at or beyond the ninth attempt. Valid metrics were used to define benchmarks, derived from the performance of the experienced cohort, for each included task. A comprehensive, stratified, benchmarked, whole-procedure curriculum has been developed for a modern high-fidelity VR colonoscopy simulator.

Spiral and Project-Based Learning with Peer Assessment in a Computer Science Project Management Course

NASA Astrophysics Data System (ADS)

Jaime, Arturo; Blanco, José Miguel; Domínguez, César; Sánchez, Ana; Heras, Jónathan; Usandizaga, Imanol

2016-06-01

Different learning methods such as project-based learning, spiral learning and peer assessment have been implemented in science disciplines with different outcomes. This paper presents a proposal for a project management course in the context of a computer science degree. Our proposal combines three well-known methods: project-based learning, spiral learning and peer assessment. Namely, the course is articulated during a semester through the structured (progressive and incremental) development of a sequence of four projects, whose duration, scope and difficulty of management increase as the student gains theoretical and instrumental knowledge related to planning, monitoring and controlling projects. Moreover, the proposal is complemented using peer assessment. The proposal has already been implemented and validated for the last 3 years in two different universities. In the first year, project-based learning and spiral learning methods were combined. Such a combination was also employed in the other 2 years; but additionally, students had the opportunity to assess projects developed by university partners and by students of the other university. A total of 154 students have participated in the study. We obtain a gain in the quality of the subsequently projects derived from the spiral project-based learning. Moreover, this gain is significantly bigger when peer assessment is introduced. In addition, high-performance students take advantage of peer assessment from the first moment, whereas the improvement in poor-performance students is delayed.

Development of probabilistic thinking-oriented learning tools for probability materials at junior high school students

NASA Astrophysics Data System (ADS)

Sari, Dwi Ivayana; Hermanto, Didik

2017-08-01

This research is a developmental research of probabilistic thinking-oriented learning tools for probability materials at ninth grade students. This study is aimed to produce a good probabilistic thinking-oriented learning tools. The subjects were IX-A students of MTs Model Bangkalan. The stages of this development research used 4-D development model which has been modified into define, design and develop. Teaching learning tools consist of lesson plan, students' worksheet, learning teaching media and students' achievement test. The research instrument used was a sheet of learning tools validation, a sheet of teachers' activities, a sheet of students' activities, students' response questionnaire and students' achievement test. The result of those instruments were analyzed descriptively to answer research objectives. The result was teaching learning tools in which oriented to probabilistic thinking of probability at ninth grade students which has been valid. Since teaching and learning tools have been revised based on validation, and after experiment in class produced that teachers' ability in managing class was effective, students' activities were good, students' responses to the learning tools were positive and the validity, sensitivity and reliability category toward achievement test. In summary, this teaching learning tools can be used by teacher to teach probability for develop students' probabilistic thinking.

An Integrated Framework for Human-Robot Collaborative Manipulation.

PubMed

Sheng, Weihua; Thobbi, Anand; Gu, Ye

2015-10-01

This paper presents an integrated learning framework that enables humanoid robots to perform human-robot collaborative manipulation tasks. Specifically, a table-lifting task performed jointly by a human and a humanoid robot is chosen for validation purpose. The proposed framework is split into two phases: 1) phase I-learning to grasp the table and 2) phase II-learning to perform the manipulation task. An imitation learning approach is proposed for phase I. In phase II, the behavior of the robot is controlled by a combination of two types of controllers: 1) reactive and 2) proactive. The reactive controller lets the robot take a reactive control action to make the table horizontal. The proactive controller lets the robot take proactive actions based on human motion prediction. A measure of confidence of the prediction is also generated by the motion predictor. This confidence measure determines the leader/follower behavior of the robot. Hence, the robot can autonomously switch between the behaviors during the task. Finally, the performance of the human-robot team carrying out the collaborative manipulation task is experimentally evaluated on a platform consisting of a Nao humanoid robot and a Vicon motion capture system. Results show that the proposed framework can enable the robot to carry out the collaborative manipulation task successfully.

A statistical learning framework for groundwater nitrate models of the Central Valley, California, USA

USGS Publications Warehouse

Nolan, Bernard T.; Fienen, Michael N.; Lorenz, David L.

2015-01-01

We used a statistical learning framework to evaluate the ability of three machine-learning methods to predict nitrate concentration in shallow groundwater of the Central Valley, California: boosted regression trees (BRT), artificial neural networks (ANN), and Bayesian networks (BN). Machine learning methods can learn complex patterns in the data but because of overfitting may not generalize well to new data. The statistical learning framework involves cross-validation (CV) training and testing data and a separate hold-out data set for model evaluation, with the goal of optimizing predictive performance by controlling for model overfit. The order of prediction performance according to both CV testing R2 and that for the hold-out data set was BRT > BN > ANN. For each method we identified two models based on CV testing results: that with maximum testing R2 and a version with R2 within one standard error of the maximum (the 1SE model). The former yielded CV training R2 values of 0.94–1.0. Cross-validation testing R2 values indicate predictive performance, and these were 0.22–0.39 for the maximum R2 models and 0.19–0.36 for the 1SE models. Evaluation with hold-out data suggested that the 1SE BRT and ANN models predicted better for an independent data set compared with the maximum R2 versions, which is relevant to extrapolation by mapping. Scatterplots of predicted vs. observed hold-out data obtained for final models helped identify prediction bias, which was fairly pronounced for ANN and BN. Lastly, the models were compared with multiple linear regression (MLR) and a previous random forest regression (RFR) model. Whereas BRT results were comparable to RFR, MLR had low hold-out R2 (0.07) and explained less than half the variation in the training data. Spatial patterns of predictions by the final, 1SE BRT model agreed reasonably well with previously observed patterns of nitrate occurrence in groundwater of the Central Valley.

New Dental Accreditation Standard on Critical Thinking: A Call for Learning Models, Outcomes, Assessments.

PubMed

Johnsen, David C; Williams, John N; Baughman, Pauletta Gay; Roesch, Darren M; Feldman, Cecile A

2015-10-01

This opinion article applauds the recent introduction of a new dental accreditation standard addressing critical thinking and problem-solving, but expresses a need for additional means for dental schools to demonstrate they are meeting the new standard because articulated outcomes, learning models, and assessments of competence are still being developed. Validated, research-based learning models are needed to define reference points against which schools can design and assess the education they provide to their students. This article presents one possible learning model for this purpose and calls for national experts from within and outside dental education to develop models that will help schools define outcomes and assess performance in educating their students to become practitioners who are effective critical thinkers and problem-solvers.

Interactive learning in 2×2 normal form games by neural network agents

NASA Astrophysics Data System (ADS)

Spiliopoulos, Leonidas

2012-11-01

This paper models the learning process of populations of randomly rematched tabula rasa neural network (NN) agents playing randomly generated 2×2 normal form games of all strategic classes. This approach has greater external validity than the existing models in the literature, each of which is usually applicable to narrow subsets of classes of games (often a single game) and/or to fixed matching protocols. The learning prowess of NNs with hidden layers was impressive as they learned to play unique pure strategy equilibria with near certainty, adhered to principles of dominance and iterated dominance, and exhibited a preference for risk-dominant equilibria. In contrast, perceptron NNs were found to perform significantly worse than hidden layer NN agents and human subjects in experimental studies.

External validation of ADO, DOSE, COTE and CODEX at predicting death in primary care patients with COPD using standard and machine learning approaches.

PubMed

Morales, Daniel R; Flynn, Rob; Zhang, Jianguo; Trucco, Emmanuel; Quint, Jennifer K; Zutis, Kris

2018-05-01

Several models for predicting the risk of death in people with chronic obstructive pulmonary disease (COPD) exist but have not undergone large scale validation in primary care. The objective of this study was to externally validate these models using statistical and machine learning approaches. We used a primary care COPD cohort identified using data from the UK Clinical Practice Research Datalink. Age-standardised mortality rates were calculated for the population by gender and discrimination of ADO (age, dyspnoea, airflow obstruction), COTE (COPD-specific comorbidity test), DOSE (dyspnoea, airflow obstruction, smoking, exacerbations) and CODEX (comorbidity, dyspnoea, airflow obstruction, exacerbations) at predicting death over 1-3 years measured using logistic regression and a support vector machine learning (SVM) method of analysis. The age-standardised mortality rate was 32.8 (95%CI 32.5-33.1) and 25.2 (95%CI 25.4-25.7) per 1000 person years for men and women respectively. Complete data were available for 54879 patients to predict 1-year mortality. ADO performed the best (c-statistic of 0.730) compared with DOSE (c-statistic 0.645), COTE (c-statistic 0.655) and CODEX (c-statistic 0.649) at predicting 1-year mortality. Discrimination of ADO and DOSE improved at predicting 1-year mortality when combined with COTE comorbidities (c-statistic 0.780 ADO + COTE; c-statistic 0.727 DOSE + COTE). Discrimination did not change significantly over 1-3 years. Comparable results were observed using SVM. In primary care, ADO appears superior at predicting death in COPD. Performance of ADO and DOSE improved when combined with COTE comorbidities suggesting better models may be generated with additional data facilitated using novel approaches. Copyright © 2018. Published by Elsevier Ltd.

Developing a dengue forecast model using machine learning: A case study in China.

PubMed

Guo, Pi; Liu, Tao; Zhang, Qin; Wang, Li; Xiao, Jianpeng; Zhang, Qingying; Luo, Ganfeng; Li, Zhihao; He, Jianfeng; Zhang, Yonghui; Ma, Wenjun

2017-10-01

In China, dengue remains an important public health issue with expanded areas and increased incidence recently. Accurate and timely forecasts of dengue incidence in China are still lacking. We aimed to use the state-of-the-art machine learning algorithms to develop an accurate predictive model of dengue. Weekly dengue cases, Baidu search queries and climate factors (mean temperature, relative humidity and rainfall) during 2011-2014 in Guangdong were gathered. A dengue search index was constructed for developing the predictive models in combination with climate factors. The observed year and week were also included in the models to control for the long-term trend and seasonality. Several machine learning algorithms, including the support vector regression (SVR) algorithm, step-down linear regression model, gradient boosted regression tree algorithm (GBM), negative binomial regression model (NBM), least absolute shrinkage and selection operator (LASSO) linear regression model and generalized additive model (GAM), were used as candidate models to predict dengue incidence. Performance and goodness of fit of the models were assessed using the root-mean-square error (RMSE) and R-squared measures. The residuals of the models were examined using the autocorrelation and partial autocorrelation function analyses to check the validity of the models. The models were further validated using dengue surveillance data from five other provinces. The epidemics during the last 12 weeks and the peak of the 2014 large outbreak were accurately forecasted by the SVR model selected by a cross-validation technique. Moreover, the SVR model had the consistently smallest prediction error rates for tracking the dynamics of dengue and forecasting the outbreaks in other areas in China. The proposed SVR model achieved a superior performance in comparison with other forecasting techniques assessed in this study. The findings can help the government and community respond early to dengue epidemics.

A mobile, high-throughput semi-automated system for testing cognition in large non-primate animal models of Huntington disease.

PubMed

McBride, Sebastian D; Perentos, Nicholas; Morton, A Jennifer

2016-05-30

For reasons of cost and ethical concerns, models of neurodegenerative disorders such as Huntington disease (HD) are currently being developed in farm animals, as an alternative to non-human primates. Developing reliable methods of testing cognitive function is essential to determining the usefulness of such models. Nevertheless, cognitive testing of farm animal species presents a unique set of challenges. The primary aims of this study were to develop and validate a mobile operant system suitable for high throughput cognitive testing of sheep. We designed a semi-automated testing system with the capability of presenting stimuli (visual, auditory) and reward at six spatial locations. Fourteen normal sheep were used to validate the system using a two-choice visual discrimination task. Four stages of training devised to acclimatise animals to the system are also presented. All sheep progressed rapidly through the training stages, over eight sessions. All sheep learned the 2CVDT and performed at least one reversal stage. The mean number of trials the sheep took to reach criterion in the first acquisition learning was 13.9±1.5 and for the reversal learning was 19.1±1.8. This is the first mobile semi-automated operant system developed for testing cognitive function in sheep. We have designed and validated an automated operant behavioural testing system suitable for high throughput cognitive testing in sheep and other medium-sized quadrupeds, such as pigs and dogs. Sheep performance in the two-choice visual discrimination task was very similar to that reported for non-human primates and strongly supports the use of farm animals as pre-clinical models for the study of neurodegenerative diseases. Copyright © 2015 Elsevier B.V. All rights reserved.

Online Radiology Reporting with Peer Review as a Learning and Feedback Tool in Radiology; Implementation, Validity, and Student Impressions.

PubMed

McEvoy, Fintan J; Shen, Nicholas W; Nielsen, Dorte H; Buelund, Lene E; Holm, Peter

2017-02-01

Communicating radiological reports to peers has pedagogical value. Students may be uneasy with the process due to a lack of communication and peer review skills or to their failure to see value in the process. We describe a communication exercise with peer review in an undergraduate veterinary radiology course. The computer code used to manage the course and deliver images online is reported, and we provide links to the executable files. We tested to see if undergraduate peer review of radiological reports has validity and describe student impressions of the learning process. Peer review scores for student-generated radiological reports were compared to scores obtained in the summative multiple choice (MCQ) examination for the course. Student satisfaction was measured using a bespoke questionnaire. There was a weak positive correlation (Pearson correlation coefficient = 0.32, p < 0.01) between peer review scores students received and the student scores obtained in the MCQ examination. The difference in peer review scores received by students grouped according to their level of course performance (high vs. low) was statistically significant (p < 0.05). No correlation was found between peer review scores awarded by the students and the scores they obtained in the MCQ examination (Pearson correlation coefficient = 0.17, p = 0.14). In conclusion, we have created a realistic radiology imaging exercise with readily available software. The peer review scores are valid in that to a limited degree they reflect student future performance in an examination. Students valued the process of learning to communicate radiological findings but do not fully appreciated the value of peer review.

Validity of Students Worksheet Based Problem-Based Learning for 9th Grade Junior High School in living organism Inheritance and Food Biotechnology.

NASA Astrophysics Data System (ADS)

Jefriadi, J.; Ahda, Y.; Sumarmin, R.

2018-04-01

Based on preliminary research of students worksheet used by teachers has several disadvantages such as students worksheet arranged directly drove learners conduct an investigation without preceded by directing learners to a problem or provide stimulation, student's worksheet not provide a concrete imageand presentation activities on the students worksheet not refer to any one learning models curicullum recommended. To address problems Reviews these students then developed a worksheet based on problem-based learning. This is a research development that using Ploom models. The phases are preliminary research, development and assessment. The instruments used in data collection that includes pieces of observation/interviews, instrument self-evaluation, instruments validity. The results of the validation expert on student worksheets get a valid result the average value 80,1%. Validity of students worksheet based problem-based learning for 9th grade junior high school in living organism inheritance and food biotechnology get valid category.

Machine Learning Techniques for Prediction of Early Childhood Obesity.

PubMed

Dugan, T M; Mukhopadhyay, S; Carroll, A; Downs, S

2015-01-01

This paper aims to predict childhood obesity after age two, using only data collected prior to the second birthday by a clinical decision support system called CHICA. Analyses of six different machine learning methods: RandomTree, RandomForest, J48, ID3, Naïve Bayes, and Bayes trained on CHICA data show that an accurate, sensitive model can be created. Of the methods analyzed, the ID3 model trained on the CHICA dataset proved the best overall performance with accuracy of 85% and sensitivity of 89%. Additionally, the ID3 model had a positive predictive value of 84% and a negative predictive value of 88%. The structure of the tree also gives insight into the strongest predictors of future obesity in children. Many of the strongest predictors seen in the ID3 modeling of the CHICA dataset have been independently validated in the literature as correlated with obesity, thereby supporting the validity of the model. This study demonstrated that data from a production clinical decision support system can be used to build an accurate machine learning model to predict obesity in children after age two.

In-lab versus at-home activity recognition in ambulatory subjects with incomplete spinal cord injury.

PubMed

Albert, Mark V; Azeze, Yohannes; Courtois, Michael; Jayaraman, Arun

2017-02-06

Although commercially available activity trackers can aid in tracking therapy and recovery of patients, most devices perform poorly for patients with irregular movement patterns. Standard machine learning techniques can be applied on recorded accelerometer signals in order to classify the activities of ambulatory subjects with incomplete spinal cord injury in a way that is specific to this population and the location of the recording-at home or in the clinic. Subjects were instructed to perform a standardized set of movements while wearing a waist-worn accelerometer in the clinic and at-home. Activities included lying, sitting, standing, walking, wheeling, and stair climbing. Multiple classifiers and validation methods were used to quantify the ability of the machine learning techniques to distinguish the activities recorded in-lab or at-home. In the lab, classifiers trained and tested using within-subject cross-validation provided an accuracy of 91.6%. When the classifier was trained on data collected in the lab but tested on at home data, the accuracy fell to 54.6% indicating distinct movement patterns between locations. However, the accuracy of the at-home classifications, when training the classifier with at-home data, improved to 85.9%. Individuals with unique movement patterns can benefit from using tailored activity recognition algorithms easily implemented using modern machine learning methods on collected movement data.

Enhancing students' learning in problem based learning: validation of a self-assessment scale for active learning and critical thinking.

PubMed

Khoiriyah, Umatul; Roberts, Chris; Jorm, Christine; Van der Vleuten, C P M

2015-08-26

Problem based learning (PBL) is a powerful learning activity but fidelity to intended models may slip and student engagement wane, negatively impacting learning processes, and outcomes. One potential solution to solve this degradation is by encouraging self-assessment in the PBL tutorial. Self-assessment is a central component of the self-regulation of student learning behaviours. There are few measures to investigate self-assessment relevant to PBL processes. We developed a Self-assessment Scale on Active Learning and Critical Thinking (SSACT) to address this gap. We wished to demonstrated evidence of its validity in the context of PBL by exploring its internal structure. We used a mixed methods approach to scale development. We developed scale items from a qualitative investigation, literature review, and consideration of previous existing tools used for study of the PBL process. Expert review panels evaluated its content; a process of validation subsequently reduced the pool of items. We used structural equation modelling to undertake a confirmatory factor analysis (CFA) of the SSACT and coefficient alpha. The 14 item SSACT consisted of two domains "active learning" and "critical thinking." The factorial validity of SSACT was evidenced by all items loading significantly on their expected factors, a good model fit for the data, and good stability across two independent samples. Each subscale had good internal reliability (>0.8) and strongly correlated with each other. The SSACT has sufficient evidence of its validity to support its use in the PBL process to encourage students to self-assess. The implementation of the SSACT may assist students to improve the quality of their learning in achieving PBL goals such as critical thinking and self-directed learning.

Teaching and assessing procedural skills using simulation: metrics and methodology.

PubMed

Lammers, Richard L; Davenport, Moira; Korley, Frederick; Griswold-Theodorson, Sharon; Fitch, Michael T; Narang, Aneesh T; Evans, Leigh V; Gross, Amy; Rodriguez, Elliot; Dodge, Kelly L; Hamann, Cara J; Robey, Walter C

2008-11-01

Simulation allows educators to develop learner-focused training and outcomes-based assessments. However, the effectiveness and validity of simulation-based training in emergency medicine (EM) requires further investigation. Teaching and testing technical skills require methods and assessment instruments that are somewhat different than those used for cognitive or team skills. Drawing from work published by other medical disciplines as well as educational, behavioral, and human factors research, the authors developed six research themes: measurement of procedural skills; development of performance standards; assessment and validation of training methods, simulator models, and assessment tools; optimization of training methods; transfer of skills learned on simulator models to patients; and prevention of skill decay over time. The article reviews relevant and established educational research methodologies and identifies gaps in our knowledge of how physicians learn procedures. The authors present questions requiring further research that, once answered, will advance understanding of simulation-based procedural training and assessment in EM.

Evaluation of a webquest on the theme "management of material resources in nursing" by undergraduate students.

PubMed

Pereira, Marta Cristiane Alves; Melo, Márcia Regina Antonietto da Costa; Silva, Adriana Serafim Bispo E; Evora, Yolanda Dora Martinez

2010-01-01

The learning process mediated by information and communication technology has considerable importance in the current context. This study describes the evaluation of a WebQuest on the theme "Management of Material Resources in Nursing". It was developed in three stages: Stage 1 consisted of its pedagogical aspect, that is, elaboration and definition of content; Stage 2 involved the organization of content, inclusion of images and completion; Stage 3 corresponded to its availability to students. Results confirm the importance of information technology and information as instruments for a mediating teaching practice in the integration between valid knowledge and the complex and dynamic reality of health services. As a result of the students' favorable evaluation of the approximation with the reality of nursing work and satisfaction for performing the activity successfully, the WebQuest method was considered valid and innovating for the teaching-learning process.

Measuring Knowledge Integration Learning of Energy Topics: A two-year longitudinal study

NASA Astrophysics Data System (ADS)

Liu, Ou Lydia; Ryoo, Kihyun; Linn, Marcia C.; Sato, Elissa; Svihla, Vanessa

2015-05-01

Although researchers call for inquiry learning in science, science assessments rarely capture the impact of inquiry instruction. This paper reports on the development and validation of assessments designed to measure middle-school students' progress in gaining integrated understanding of energy while studying an inquiry-oriented curriculum. The assessment development was guided by the knowledge integration framework. Over 2 years of implementation, more than 4,000 students from 4 schools participated in the study, including a cross-sectional and a longitudinal cohort. Results from item response modeling analyses revealed that: (a) the assessments demonstrated satisfactory psychometric properties in terms of reliability and validity; (b) both the cross-sectional and longitudinal cohorts made progress on integrating their understanding energy concepts; and (c) among many factors (e.g. gender, grade, school, and home language) associated with students' science performance, unit implementation was the strongest predictor.

Deep learning for medical image segmentation - using the IBM TrueNorth neurosynaptic system

NASA Astrophysics Data System (ADS)

Moran, Steven; Gaonkar, Bilwaj; Whitehead, William; Wolk, Aidan; Macyszyn, Luke; Iyer, Subramanian S.

2018-03-01

Deep convolutional neural networks have found success in semantic image segmentation tasks in computer vision and medical imaging. These algorithms are executed on conventional von Neumann processor architectures or GPUs. This is suboptimal. Neuromorphic processors that replicate the structure of the brain are better-suited to train and execute deep learning models for image segmentation by relying on massively-parallel processing. However, given that they closely emulate the human brain, on-chip hardware and digital memory limitations also constrain them. Adapting deep learning models to execute image segmentation tasks on such chips, requires specialized training and validation. In this work, we demonstrate for the first-time, spinal image segmentation performed using a deep learning network implemented on neuromorphic hardware of the IBM TrueNorth Neurosynaptic System and validate the performance of our network by comparing it to human-generated segmentations of spinal vertebrae and disks. To achieve this on neuromorphic hardware, the training model constrains the coefficients of individual neurons to {-1,0,1} using the Energy Efficient Deep Neuromorphic (EEDN)1 networks training algorithm. Given the 1 million neurons and 256 million synapses, the scale and size of the neural network implemented by the IBM TrueNorth allows us to execute the requisite mapping between segmented images and non-uniform intensity MR images >20 times faster than on a GPU-accelerated network and using <0.1 W. This speed and efficiency implies that a trained neuromorphic chip can be deployed in intra-operative environments where real-time medical image segmentation is necessary.

Empirical Validation of Integrated Learning Performances for Hydrologic Phenomena: 3rd-Grade Students' Model-Driven Explanation-Construction

ERIC Educational Resources Information Center

Forbes, Cory T.; Zangori, Laura; Schwarz, Christina V.

2015-01-01

Water is a crucial topic that spans the K-12 science curriculum, including the elementary grades. Students should engage in the articulation, negotiation, and revision of model-based explanations about hydrologic phenomena. However, past research has shown that students, particularly early learners, often struggle to understand hydrologic…

Training in the Adolescent Brain: An FMRI Training Study on Divergent Thinking

ERIC Educational Resources Information Center

Kleibeuker, Sietske W.; Stevenson, Claire E.; van der Aar, Laura; Overgaauw, Sandy; van Duijvenvoorde, Anna C.; Crone, Eveline A.

2017-01-01

Prior research suggests that adolescence is a time of enhanced sensitivity for practice and learning. In this study we tested the neural correlates of divergent thinking training in 15- to 16-year-old adolescents relative to an age-matched active control group. All participants performed an alternative uses task, a valid measure to test divergent…

The Influence of Transfer System Factors and Training Elapsed Time on Transfer in a Healthcare Organization

ERIC Educational Resources Information Center

Mihalko, Beverly J.

2010-01-01

Organizations and other sponsors of training face increasing pressure to demonstrate the value or impact of their training programs on individual and organizational performance. A critical element in the validation of training effectiveness is the permanent transfer of learned knowledge, skills, and behaviors to the workplace. The generalization…

Online Proctored versus Unproctored Low-Stakes Internet Test Administration: Is There Differential Test-Taking Behavior and Performance?

ERIC Educational Resources Information Center

Rios, Joseph A.; Liu, Ou Lydia

2017-01-01

Online higher education institutions are presented with the concern of how to obtain valid results when administering student learning outcomes (SLO) assessments remotely. Traditionally, there has been a great reliance on unproctored Internet test administration (UIT) due to increased flexibility and reduced costs; however, a number of validity…

Systems Concepts and Computer-Managed Instruction: An Implementation and Validation Study.

ERIC Educational Resources Information Center

Dick, Walter; Gallagher, Paul

The Florida State model of computer-managed instruction (CMI) differs from other such models in that it assumes a student will achieve his maximum performance level by interacting directly with the computer in order to evaluate his learning experience. In this system the computer plays the role of real-time diagnostician and prescriber for the…

A Two Factor Model of Performance Approach Goals in Student Motivation for Starting Medical School

ERIC Educational Resources Information Center

Wilson, Jacqueline I.

2009-01-01

This study explores what motivates a student to enter medical school by first measuring students' strength of motivation and then by looking for relationships between motivation and career-related values and approaches to learning. Validated and reliable questionnaires were used to obtain data. This study found no differences in strength of…

Development of the Computerized Model of Performance-Based Measurement System to Measure Nurses' Clinical Competence.

PubMed

Liou, Shwu-Ru; Liu, Hsiu-Chen; Tsai, Shu-Ling; Cheng, Ching-Yu; Yu, Wei-Chieh; Chu, Tsui-Ping

2016-04-01

Critical thinking skills and clinical competence are for providing quality patient care. The purpose of this study is to develop the Computerized Model of Performance-Based Measurement system based on the Clinical Reasoning Model. The system can evaluate and identify learning needs for clinical competency and be used as a learning tool to increase clinical competency by using computers. The system includes 10 high-risk, high-volume clinical case scenarios coupled with questions testing clinical reasoning, interpersonal, and technical skills. Questions were sequenced to reflect patients' changing condition and arranged by following the process of collecting and managing information, diagnosing and differentiating urgency of problems, and solving problems. The content validity and known-groups validity was established. The Kuder-Richardson Formula 20 was 0.90 and test-retest reliability was supported (r = 0.78). Nursing educators can use the system to understand students' needs for achieving clinical competence, and therefore, educational plans can be made to better prepare students and facilitate their smooth transition to a future clinical environment. Clinical nurses can use the system to evaluate their performance-based abilities and weakness in clinical reasoning. Appropriate training programs can be designed and implemented to practically promote nurses' clinical competence and quality of patient care.

Application of adaptive boosting to EP-derived multilayer feed-forward neural networks (MLFN) to improve benign/malignant breast cancer classification

NASA Astrophysics Data System (ADS)

Land, Walker H., Jr.; Masters, Timothy D.; Lo, Joseph Y.; McKee, Dan

2001-07-01

A new neural network technology was developed for improving the benign/malignant diagnosis of breast cancer using mammogram findings. A new paradigm, Adaptive Boosting (AB), uses a markedly different theory in solutioning Computational Intelligence (CI) problems. AB, a new machine learning paradigm, focuses on finding weak learning algorithm(s) that initially need to provide slightly better than random performance (i.e., approximately 55%) when processing a mammogram training set. Then, by successive development of additional architectures (using the mammogram training set), the adaptive boosting process improves the performance of the basic Evolutionary Programming derived neural network architectures. The results of these several EP-derived hybrid architectures are then intelligently combined and tested using a similar validation mammogram data set. Optimization focused on improving specificity and positive predictive value at very high sensitivities, where an analysis of the performance of the hybrid would be most meaningful. Using the DUKE mammogram database of 500 biopsy proven samples, on average this hybrid was able to achieve (under statistical 5-fold cross-validation) a specificity of 48.3% and a positive predictive value (PPV) of 51.8% while maintaining 100% sensitivity. At 97% sensitivity, a specificity of 56.6% and a PPV of 55.8% were obtained.

Validity of "Hi_Science" as instructional media based-android refer to experiential learning model

NASA Astrophysics Data System (ADS)

Qamariah, Jumadi, Senam, Wilujeng, Insih

2017-08-01

Hi_Science is instructional media based-android in learning science on material environmental pollution and global warming. This study is aimed: (a) to show the display of Hi_Science that will be applied in Junior High School, and (b) to describe the validity of Hi_Science. Hi_Science as instructional media created with colaboration of innovative learning model and development of technology at the current time. Learning media selected is based-android and collaborated with experiential learning model as an innovative learning model. Hi_Science had adapted student worksheet by Taufiq (2015). Student worksheet had very good category by two expert lecturers and two science teachers (Taufik, 2015). This student worksheet is refined and redeveloped in android as an instructional media which can be used by students for learning science not only in the classroom, but also at home. Therefore, student worksheet which has become instructional media based-android must be validated again. Hi_Science has been validated by two experts. The validation is based on assessment of meterials aspects and media aspects. The data collection was done by media assessment instrument. The result showed the assessment of material aspects has obtained the average value 4,72 with percentage of agreement 96,47%, that means Hi_Science on the material aspects is in excellent category or very valid category. The assessment of media aspects has obtained the average value 4,53 with percentage of agreement 98,70%, that means Hi_Science on the media aspects is in excellent category or very valid category. It was concluded that Hi_Science as instructional media can be applied in the junior high school.

Assessing college-level learning difficulties and "at riskness" for learning disabilities and ADHD: development and validation of the learning difficulties assessment.

PubMed

Kane, Steven T; Walker, John H; Schmidt, George R

2011-01-01

This article describes the development and validation of the Learning Difficulties Assessment (LDA), a normed and web-based survey that assesses perceived difficulties with reading, writing, spelling, mathematics, listening, concentration, memory, organizational skills, sense of control, and anxiety in college students. The LDA is designed to (a) map individual learning strengths and weaknesses, (b) provide users with a comparative sense of their academic skills, (c) integrate research in user-interface design to assist those with reading and learning challenges, and (d) identify individuals who may be at risk for learning disabilities and attention-deficit/hyperactivity disorder (ADHD) and who should thus be further assessed. Data from a large-scale 5-year study describing the instrument's validity as a screening tool for learning disabilities and ADHD are presented. This article also describes unique characteristics of the LDA including its user-interface design, normative characteristics, and use as a no-cost screening tool for identifying college students at risk for learning disorders and ADHD.

Development and testing of the CALDs and CLES+T scales for international nursing students' clinical learning environments.

PubMed

Mikkonen, Kristina; Elo, Satu; Miettunen, Jouko; Saarikoski, Mikko; Kääriäinen, Maria

2017-08-01

The purpose of this study was to develop and test the psychometric properties of the new Cultural and Linguistic Diversity scale, which is designed to be used with the newly validated Clinical Learning Environment, Supervision and Nurse Teacher scale for assessing international nursing students' clinical learning environments. In various developed countries, clinical placements are known to present challenges in the professional development of international nursing students. A cross-sectional survey. Data were collected from eight Finnish universities of applied sciences offering nursing degree courses taught in English during 2015-2016. All the relevant students (N = 664) were invited and 50% chose to participate. Of the total data submitted by the participants, 28% were used for scale validation. The construct validity of the two scales was tested by exploratory factor analysis, while their validity with respect to convergence and discriminability was assessed using Spearman's correlation. Construct validation of the Clinical Learning Environment, Supervision and Nurse Teacher scale yielded an eight-factor model with 34 items, while validation of the Cultural and Linguistic Diversity scale yielded a five-factor model with 21 items. A new scale was developed to improve evidence-based mentorship of international nursing students in clinical learning environments. The instrument will be useful to educators seeking to identify factors that affect the learning of international students. © 2017 John Wiley & Sons Ltd.

Accuracy assessment of high resolution satellite imagery orientation by leave-one-out method

NASA Astrophysics Data System (ADS)

Brovelli, Maria Antonia; Crespi, Mattia; Fratarcangeli, Francesca; Giannone, Francesca; Realini, Eugenio

Interest in high-resolution satellite imagery (HRSI) is spreading in several application fields, at both scientific and commercial levels. Fundamental and critical goals for the geometric use of this kind of imagery are their orientation and orthorectification, processes able to georeference the imagery and correct the geometric deformations they undergo during acquisition. In order to exploit the actual potentialities of orthorectified imagery in Geomatics applications, the definition of a methodology to assess the spatial accuracy achievable from oriented imagery is a crucial topic. In this paper we want to propose a new method for accuracy assessment based on the Leave-One-Out Cross-Validation (LOOCV), a model validation method already applied in different fields such as machine learning, bioinformatics and generally in any other field requiring an evaluation of the performance of a learning algorithm (e.g. in geostatistics), but never applied to HRSI orientation accuracy assessment. The proposed method exhibits interesting features which are able to overcome the most remarkable drawbacks involved by the commonly used method (Hold-Out Validation — HOV), based on the partitioning of the known ground points in two sets: the first is used in the orientation-orthorectification model (GCPs — Ground Control Points) and the second is used to validate the model itself (CPs — Check Points). In fact the HOV is generally not reliable and it is not applicable when a low number of ground points is available. To test the proposed method we implemented a new routine that performs the LOOCV in the software SISAR, developed by the Geodesy and Geomatics Team at the Sapienza University of Rome to perform the rigorous orientation of HRSI; this routine was tested on some EROS-A and QuickBird images. Moreover, these images were also oriented using the world recognized commercial software OrthoEngine v. 10 (included in the Geomatica suite by PCI), manually performing the LOOCV since only the HOV is implemented. The software comparison guaranteed about the overall correctness and good performances of the SISAR model, whereas the results showed the good features of the LOOCV method.

Future goal setting, task motivation and learning of minority and non-minority students in Dutch schools.

PubMed

Andriessen, Iris; Phalet, Karen; Lens, Willy

2006-12-01

Cross-cultural research on minority school achievement yields mixed findings on the motivational impact of future goal setting for students from disadvantaged minority groups. Relevant and recent motivational research, integrating Future Time Perspective Theory with Self-Determination Theory, has not yet been validated among minority students. To replicate across cultures the known motivational benefits of perceived instrumentality and internal regulation by distant future goals; to clarify when and how the future motivates minority students' educational performance. Participants in this study were 279 minority students (100 of Turkish and 179 of Moroccan origin) and 229 native Dutch students in Dutch secondary schools. Participants rated the importance of future goals, their perceptions of instrumentality, their task motivation and learning strategies. Dependent measures and their functional relations with future goal setting were simultaneously validated across minority and non-minority students, using structural equation modelling in multiple groups. As expected, Positive Perceived Instrumentality for the future increases task motivation and (indirectly) adaptive learning of both minority and non-minority students. But especially internally regulating future goals are strongly related to more task motivation and indirectly to more adaptive learning strategies. Our findings throw new light on the role of future goal setting in minority school careers: distant future goals enhance minority and non-minority students' motivation and learning, if students perceive positive instrumentality and if their schoolwork is internally regulated by future goals.

Detection of Pathological Voice Using Cepstrum Vectors: A Deep Learning Approach.

PubMed

Fang, Shih-Hau; Tsao, Yu; Hsiao, Min-Jing; Chen, Ji-Ying; Lai, Ying-Hui; Lin, Feng-Chuan; Wang, Chi-Te

2018-03-19

Computerized detection of voice disorders has attracted considerable academic and clinical interest in the hope of providing an effective screening method for voice diseases before endoscopic confirmation. This study proposes a deep-learning-based approach to detect pathological voice and examines its performance and utility compared with other automatic classification algorithms. This study retrospectively collected 60 normal voice samples and 402 pathological voice samples of 8 common clinical voice disorders in a voice clinic of a tertiary teaching hospital. We extracted Mel frequency cepstral coefficients from 3-second samples of a sustained vowel. The performances of three machine learning algorithms, namely, deep neural network (DNN), support vector machine, and Gaussian mixture model, were evaluated based on a fivefold cross-validation. Collective cases from the voice disorder database of MEEI (Massachusetts Eye and Ear Infirmary) were used to verify the performance of the classification mechanisms. The experimental results demonstrated that DNN outperforms Gaussian mixture model and support vector machine. Its accuracy in detecting voice pathologies reached 94.26% and 90.52% in male and female subjects, based on three representative Mel frequency cepstral coefficient features. When applied to the MEEI database for validation, the DNN also achieved a higher accuracy (99.32%) than the other two classification algorithms. By stacking several layers of neurons with optimized weights, the proposed DNN algorithm can fully utilize the acoustic features and efficiently differentiate between normal and pathological voice samples. Based on this pilot study, future research may proceed to explore more application of DNN from laboratory and clinical perspectives. Copyright © 2018 The Voice Foundation. Published by Elsevier Inc. All rights reserved.

Assessment in the context of licensure and certification.

PubMed

Norcini, John J; Lipner, Rebecca S; Grosso, Louis J

2013-01-01

Over the past 25 years, three major forces have had a significant influence on licensure and certification: the shift in focus from educational process to educational outcomes, the increasing recognition of the need for learning and assessment throughout a physician's career, and the changes in technology and psychometrics that have opened new vistas for assessment. These forces have led to significant changes in assessment for licensure and certification. To respond to these forces, licensure and certification programs have improved the ways in which their examinations are constructed, scored, and delivered. In particular, we note the introduction of adaptive testing; automated item creation, scoring, and test assembly; assessment engineering; and data forensics. Licensure and certification programs have also expanded their repertoire of assessments with the rapid development and adoption of simulation and workplace-based assessment. Finally, they have invested in research intended to validate their programs in four ways: (a) the acceptability of the program to stakeholders, (b) the extent to which stakeholders are encouraged to learn and improve, (c) the extent to which there is a relationship between performance in the programs and external measures, and (d) the extent to which there is a relationship between performance as measured by the assessment and performance in practice. Over the past 25 years, changes in licensure and certification have been driven by the educational outcomes movement, the need for lifelong learning, and advances in technology and psychometrics. Over the next 25 years, we expect these forces to continue to exert pressure for change which will lead to additional improvement and expansion in examination processes, methods of assessment, and validation research.

Seeking Empirical Validity in an Assurance of Learning System

ERIC Educational Resources Information Center

Avery, Sherry L.; McWhorter, Rochell R.; Lirely, Roger; Doty, H. Harold

2014-01-01

Business schools have established measurement tools to support their assurance of learning (AoL) systems and to assess student achievement of learning objectives. However, business schools have not required their tools to be empirically validated, thus ensuring that they measure what they are intended to measure. The authors propose confirmatory…

Psychometric Validation of the "Motivated Strategies for Learning Questionnaire" with Mexican University Students

ERIC Educational Resources Information Center

Ramirez-Dorantes, Maria del Carmen; Canto y Rodriguez, Jose Enrique; Bueno-Alvarez, Jose Antonio; Echazarreta-Moreno, Alejandro

2013-01-01

Introduction: The "Motivated Strategies for Learning Questionnaire" (MSLQ) is a self-report instrument designed to assess students' motivation and learning strategies (cognitive, meta-cognitive, and resource management). In the present study, we focused on translate, adapt and validate the MSLQ to Mexican educational context. Method: The…

Empirical Refinements of a Molecular Genetics Learning Progression: The Molecular Constructs

ERIC Educational Resources Information Center

Todd, Amber; Kenyon, Lisa

2016-01-01

This article describes revisions to four of the eight constructs of the Duncan molecular genetics learning progression [Duncan, Rogat, & Yarden, (2009)]. As learning progressions remain hypothetical models until validated by multiple rounds of empirical studies, these revisions are an important step toward validating the progression. Our…

Design, Development, and Validation of Learning Objects

ERIC Educational Resources Information Center

Nugent, Gwen; Soh, Leen-Kiat; Samal, Ashok

2006-01-01

A learning object is a small, stand-alone, mediated content resource that can be reused in multiple instructional contexts. In this article, we describe our approach to design, develop, and validate Shareable Content Object Reference Model (SCORM) compliant learning objects for undergraduate computer science education. We discuss the advantages of…

Convergent and Divergent Validity of the Learning Transfer System Inventory

ERIC Educational Resources Information Center

Holton, Elwood F., III; Bates, Reid A.; Bookter, Annette I.; Yamkovenko, V. Bogdan

2007-01-01

The Learning Transfer System Inventory (LTSI) was developed to identify a select set of factors with the potential to substantially enhance or inhibit transfer of learning to the work environment. It has undergone a variety of validation studies, including construct, criterion, and crosscultural studies. However, the convergent and divergent…

Principals' Learning Mechanisms: Exploring an Emerging Construct

ERIC Educational Resources Information Center

Schechter, Chen; Qadach, Mowafaq

2016-01-01

This exploration of principal learning mechanisms (PLM) to support a learning-centered school aimed to develop, field-test, and validate a PLM-measuring instrument. Following exploratory and confirmatory factor analyses of items to examine factorial validity, the developed scale was correlated with other work-related established constructs (e.g.,…

SU-D-204-06: Integration of Machine Learning and Bioinformatics Methods to Analyze Genome-Wide Association Study Data for Rectal Bleeding and Erectile Dysfunction Following Radiotherapy in Prostate Cancer

DOE Office of Scientific and Technical Information (OSTI.GOV)

Oh, J; Deasy, J; Kerns, S

Purpose: We investigated whether integration of machine learning and bioinformatics techniques on genome-wide association study (GWAS) data can improve the performance of predictive models in predicting the risk of developing radiation-induced late rectal bleeding and erectile dysfunction in prostate cancer patients. Methods: We analyzed a GWAS dataset generated from 385 prostate cancer patients treated with radiotherapy. Using genotype information from these patients, we designed a machine learning-based predictive model of late radiation-induced toxicities: rectal bleeding and erectile dysfunction. The model building process was performed using 2/3 of samples (training) and the predictive model was tested with 1/3 of samples (validation).more » To identify important single nucleotide polymorphisms (SNPs), we computed the SNP importance score, resulting from our random forest regression model. We performed gene ontology (GO) enrichment analysis for nearby genes of the important SNPs. Results: After univariate analysis on the training dataset, we filtered out many SNPs with p>0.001, resulting in 749 and 367 SNPs that were used in the model building process for rectal bleeding and erectile dysfunction, respectively. On the validation dataset, our random forest regression model achieved the area under the curve (AUC)=0.70 and 0.62 for rectal bleeding and erectile dysfunction, respectively. We performed GO enrichment analysis for the top 25%, 50%, 75%, and 100% SNPs out of the select SNPs in the univariate analysis. When we used the top 50% SNPs, more plausible biological processes were obtained for both toxicities. An additional test with the top 50% SNPs improved predictive power with AUC=0.71 and 0.65 for rectal bleeding and erectile dysfunction. A better performance was achieved with AUC=0.67 when age and androgen deprivation therapy were added to the model for erectile dysfunction. Conclusion: Our approach that combines machine learning and bioinformatics techniques enabled designing better models and identifying more plausible biological processes associated with the outcomes.« less

Improving resident well-being and clinical learning environment through academic initiatives.

PubMed

Lee, Nathaniel; Appelbaum, Nital; Amendola, Michael; Dodson, Kelley; Kaplan, Brian

2017-07-01

Organizational effects on job satisfaction, burnout, work-life balance, and perceived support have not been studied in the context of the clinical learning environment. We evaluated the relationship between academic resources and resident well-being, the clinical learning environment, and in-service examination performance of surgical residents. Residents of general surgery and surgical specialty programs were recruited from March 2016 through June 2016 across the Southeast, Mid-Atlantic, and Northeast regions. Program directors were asked to allow distribution of a paper survey or to forward an electronic survey link onto residents. Five dichotomous questions were asked regarding access to academic resources. Validated measures were obtained assessing resident well-being and perceived clinical learning environment. Data were analyzed through t-tests and chi-squared test of independence. We received 276 respondents across 50 programs. Residents perceiving adequate support to succeed had less burnout (P = 0.008), better resilience (P = 0.009), better job satisfaction (P < 0.001), less work/life strain (P = 0.001), better workplace climate (P < 0.001), better organizational support (P < 0.001), and were more likely to have high performance on the in-service examination (P = 0.001). Specific resources including educational stipends, review questions, in-service board prep, and support for poor performers correlated with improved well-being and perceived clinical learning environment. Provision of academic resources has implications beyond in-service examination performance, correlating with improved resident well-being and perceptions of the clinical learning environment. Copyright © 2017 Elsevier Inc. All rights reserved.

Validation of an e-Learning 3.0 Critical Success Factors Framework: A Qualitative Research

ERIC Educational Resources Information Center

Miranda, Paula; Isaias, Pedro; Costa, Carlos J.; Pifano, Sara

2017-01-01

Aim/Purpose: As e-Learning 3.0 evolves from a theoretical construct into an actual solution for online learning, it becomes crucial to accompany this progress by scrutinising the elements that are at the origin of its success. Background: This paper outlines a framework of e-Learning 3.0's critical success factors and its empirical validation.…

Towards a full integration of optimization and validation phases: An analytical-quality-by-design approach.

PubMed

Hubert, C; Houari, S; Rozet, E; Lebrun, P; Hubert, Ph

2015-05-22

When using an analytical method, defining an analytical target profile (ATP) focused on quantitative performance represents a key input, and this will drive the method development process. In this context, two case studies were selected in order to demonstrate the potential of a quality-by-design (QbD) strategy when applied to two specific phases of the method lifecycle: the pre-validation study and the validation step. The first case study focused on the improvement of a liquid chromatography (LC) coupled to mass spectrometry (MS) stability-indicating method by the means of the QbD concept. The design of experiments (DoE) conducted during the optimization step (i.e. determination of the qualitative design space (DS)) was performed a posteriori. Additional experiments were performed in order to simultaneously conduct the pre-validation study to assist in defining the DoE to be conducted during the formal validation step. This predicted protocol was compared to the one used during the formal validation. A second case study based on the LC/MS-MS determination of glucosamine and galactosamine in human plasma was considered in order to illustrate an innovative strategy allowing the QbD methodology to be incorporated during the validation phase. An operational space, defined by the qualitative DS, was considered during the validation process rather than a specific set of working conditions as conventionally performed. Results of all the validation parameters conventionally studied were compared to those obtained with this innovative approach for glucosamine and galactosamine. Using this strategy, qualitative and quantitative information were obtained. Consequently, an analyst using this approach would be able to select with great confidence several working conditions within the operational space rather than a given condition for the routine use of the method. This innovative strategy combines both a learning process and a thorough assessment of the risk involved. Copyright © 2015 Elsevier B.V. All rights reserved.

Learning by Demonstration for Motion Planning of Upper-Limb Exoskeletons

PubMed Central

Lauretti, Clemente; Cordella, Francesca; Ciancio, Anna Lisa; Trigili, Emilio; Catalan, Jose Maria; Badesa, Francisco Javier; Crea, Simona; Pagliara, Silvio Marcello; Sterzi, Silvia; Vitiello, Nicola; Garcia Aracil, Nicolas; Zollo, Loredana

2018-01-01

The reference joint position of upper-limb exoskeletons is typically obtained by means of Cartesian motion planners and inverse kinematics algorithms with the inverse Jacobian; this approach allows exploiting the available Degrees of Freedom (i.e. DoFs) of the robot kinematic chain to achieve the desired end-effector pose; however, if used to operate non-redundant exoskeletons, it does not ensure that anthropomorphic criteria are satisfied in the whole human-robot workspace. This paper proposes a motion planning system, based on Learning by Demonstration, for upper-limb exoskeletons that allow successfully assisting patients during Activities of Daily Living (ADLs) in unstructured environment, while ensuring that anthropomorphic criteria are satisfied in the whole human-robot workspace. The motion planning system combines Learning by Demonstration with the computation of Dynamic Motion Primitives and machine learning techniques to construct task- and patient-specific joint trajectories based on the learnt trajectories. System validation was carried out in simulation and in a real setting with a 4-DoF upper-limb exoskeleton, a 5-DoF wrist-hand exoskeleton and four patients with Limb Girdle Muscular Dystrophy. Validation was addressed to (i) compare the performance of the proposed motion planning with traditional methods; (ii) assess the generalization capabilities of the proposed method with respect to the environment variability. Three ADLs were chosen to validate the system: drinking, pouring and lifting a light sphere. The achieved results showed a 100% success rate in the task fulfillment, with a high level of generalization with respect to the environment variability. Moreover, an anthropomorphic configuration of the exoskeleton is always ensured. PMID:29527161

Learning by Demonstration for Motion Planning of Upper-Limb Exoskeletons.

PubMed

Lauretti, Clemente; Cordella, Francesca; Ciancio, Anna Lisa; Trigili, Emilio; Catalan, Jose Maria; Badesa, Francisco Javier; Crea, Simona; Pagliara, Silvio Marcello; Sterzi, Silvia; Vitiello, Nicola; Garcia Aracil, Nicolas; Zollo, Loredana

2018-01-01

The reference joint position of upper-limb exoskeletons is typically obtained by means of Cartesian motion planners and inverse kinematics algorithms with the inverse Jacobian; this approach allows exploiting the available Degrees of Freedom (i.e. DoFs) of the robot kinematic chain to achieve the desired end-effector pose; however, if used to operate non-redundant exoskeletons, it does not ensure that anthropomorphic criteria are satisfied in the whole human-robot workspace. This paper proposes a motion planning system, based on Learning by Demonstration, for upper-limb exoskeletons that allow successfully assisting patients during Activities of Daily Living (ADLs) in unstructured environment, while ensuring that anthropomorphic criteria are satisfied in the whole human-robot workspace. The motion planning system combines Learning by Demonstration with the computation of Dynamic Motion Primitives and machine learning techniques to construct task- and patient-specific joint trajectories based on the learnt trajectories. System validation was carried out in simulation and in a real setting with a 4-DoF upper-limb exoskeleton, a 5-DoF wrist-hand exoskeleton and four patients with Limb Girdle Muscular Dystrophy. Validation was addressed to (i) compare the performance of the proposed motion planning with traditional methods; (ii) assess the generalization capabilities of the proposed method with respect to the environment variability. Three ADLs were chosen to validate the system: drinking, pouring and lifting a light sphere. The achieved results showed a 100% success rate in the task fulfillment, with a high level of generalization with respect to the environment variability. Moreover, an anthropomorphic configuration of the exoskeleton is always ensured.

Assessing the quality of activities in a smart environment.

PubMed

Cook, Diane J; Schmitter-Edgecombe, M

2009-01-01

Pervasive computing technology can provide valuable health monitoring and assistance technology to help individuals live independent lives in their own homes. As a critical part of this technology, our objective is to design software algorithms that recognize and assess the consistency of activities of daily living that individuals perform in their own homes. We have designed algorithms that automatically learn Markov models for each class of activity. These models are used to recognize activities that are performed in a smart home and to identify errors and inconsistencies in the performed activity. We validate our approach using data collected from 60 volunteers who performed a series of activities in our smart apartment testbed. The results indicate that the algorithms correctly label the activities and successfully assess the completeness and consistency of the performed task. Our results indicate that activity recognition and assessment can be automated using machine learning algorithms and smart home technology. These algorithms will be useful for automating remote health monitoring and interventions.

Development and content validity of the CENA Program for Educational Training on the Neuropsychology of Learning, with an emphasis on executive functions and attention.

PubMed

Pureza, Janice R; Fonseca, Rochele P

2017-01-01

The importance of executive functions (EF) in childhood development, and their role as indicators of health, well-being, professional and academic success have been demonstrated by several studies in the literature. FE are cognitive processes that aim to control and manage behavior to achieve specific goal and included skills planning, inhibition, cognitive flexibility, (executive) attention and the central executive component of working memory (WM). In the context of education, the EF are crucial for continued learning and efficient academic performance due to their involvement in several components of the educational process. The aim of this article was to describe the development and content validity of the CENA Program for Educational Training on the Neuropsychology of Learning, with an emphasis on executive functions and attention. The study involved seven specialists (four responsible for evaluating the program, and three involved in brainstorming), and was carried out in three stages:Background research: neuropsychology and education;Program development - author brainstorming andEvaluation by expert judges The goals, language and methods. CENA Program were considered adequate, attesting to its content validity as a school-based neuropsychological intervention. Teacher training in school neuropsychology may be an important area for future investment and contribute to academic achievement and student development in the Brazilian education system.

Development and content validity of the CENA Program for Educational Training on the Neuropsychology of Learning, with an emphasis on executive functions and attention

PubMed Central

Pureza, Janice R.; Fonseca, Rochele P.

2017-01-01

Introduction The importance of executive functions (EF) in childhood development, and their role as indicators of health, well-being, professional and academic success have been demonstrated by several studies in the literature. FE are cognitive processes that aim to control and manage behavior to achieve specific goal and included skills planning, inhibition, cognitive flexibility, (executive) attention and the central executive component of working memory (WM). In the context of education, the EF are crucial for continued learning and efficient academic performance due to their involvement in several components of the educational process. Objective The aim of this article was to describe the development and content validity of the CENA Program for Educational Training on the Neuropsychology of Learning, with an emphasis on executive functions and attention. Methods The study involved seven specialists (four responsible for evaluating the program, and three involved in brainstorming), and was carried out in three stages: Background research: neuropsychology and education; Program development - author brainstorming and Evaluation by expert judges The goals, language and methods. Results CENA Program were considered adequate, attesting to its content validity as a school-based neuropsychological intervention. Conclusion Teacher training in school neuropsychology may be an important area for future investment and contribute to academic achievement and student development in the Brazilian education system. PMID:29213497

Interactive design for self-study and developing students’ critical thinking skills in electromagnetic radiation topic

NASA Astrophysics Data System (ADS)

Ambarwati, D.; Suyatna, A.

2018-01-01

The purpose of this research are to create interactive electronic school books (ESB) for electromagnetic radiation topic that can be used for self-study and increasing students’ critical thinking skills. The research method was based on the design of research and development (R&D) model of ADDIE. The research procedure is used limited the design of the product has been validated. Data source at interactive requirement analysis phase of ESB is student and high school teacher of class XII in Lampung province. The validation of interactive ESB designs is performed by experts in science education. The data of ESB interactive needs were collected using questionnaires and analyzed using quantitative descriptive. The results of the questionnaire obtained by 97% of books that are often used in the form of printed books from schools have not been interactive and foster critical thinking of students, and 55% of students stating physics books are used not meet expectations. Expectations of students in physics learning, teachers must use interactive electronic books. The results of the validation experts pointed out, the design of ESB produced is interactive, can be used for self-study, and increasing students’ critical thinking skills, which contains instruction manuals, learning objectives, learning materials, sample questions and discussion, video illustrations, animations, summaries, as well as interactive quizzes incorporating feedback exam practice and preparation for college entrance.

MO-G-BRE-09: Validating FMEA Against Incident Learning Data: A Study in Stereotactic Body Radiation Therapy

DOE Office of Scientific and Technical Information (OSTI.GOV)

Yang, F; Cao, N; Young, L

2014-06-15

Purpose: Though FMEA (Failure Mode and Effects Analysis) is becoming more widely adopted for risk assessment in radiation therapy, to our knowledge it has never been validated against actual incident learning data. The objective of this study was to perform an FMEA analysis of an SBRT (Stereotactic Body Radiation Therapy) treatment planning process and validate this against data recorded within an incident learning system. Methods: FMEA on the SBRT treatment planning process was carried out by a multidisciplinary group including radiation oncologists, medical physicists, and dosimetrists. Potential failure modes were identified through a systematic review of the workflow process. Failuremore » modes were rated for severity, occurrence, and detectability on a scale of 1 to 10 and RPN (Risk Priority Number) was computed. Failure modes were then compared with historical reports identified as relevant to SBRT planning within a departmental incident learning system that had been active for two years. Differences were identified. Results: FMEA identified 63 failure modes. RPN values for the top 25% of failure modes ranged from 60 to 336. Analysis of the incident learning database identified 33 reported near-miss events related to SBRT planning. FMEA failed to anticipate 13 of these events, among which 3 were registered with severity ratings of severe or critical in the incident learning system. Combining both methods yielded a total of 76 failure modes, and when scored for RPN the 13 events missed by FMEA ranked within the middle half of all failure modes. Conclusion: FMEA, though valuable, is subject to certain limitations, among them the limited ability to anticipate all potential errors for a given process. This FMEA exercise failed to identify a significant number of possible errors (17%). Integration of FMEA with retrospective incident data may be able to render an improved overview of risks within a process.« less

Validating FMEA output against incident learning data: A study in stereotactic body radiation therapy.

PubMed

Yang, F; Cao, N; Young, L; Howard, J; Logan, W; Arbuckle, T; Sponseller, P; Korssjoen, T; Meyer, J; Ford, E

2015-06-01

Though failure mode and effects analysis (FMEA) is becoming more widely adopted for risk assessment in radiation therapy, to our knowledge, its output has never been validated against data on errors that actually occur. The objective of this study was to perform FMEA of a stereotactic body radiation therapy (SBRT) treatment planning process and validate the results against data recorded within an incident learning system. FMEA on the SBRT treatment planning process was carried out by a multidisciplinary group including radiation oncologists, medical physicists, dosimetrists, and IT technologists. Potential failure modes were identified through a systematic review of the process map. Failure modes were rated for severity, occurrence, and detectability on a scale of one to ten and risk priority number (RPN) was computed. Failure modes were then compared with historical reports identified as relevant to SBRT planning within a departmental incident learning system that has been active for two and a half years. Differences between FMEA anticipated failure modes and existing incidents were identified. FMEA identified 63 failure modes. RPN values for the top 25% of failure modes ranged from 60 to 336. Analysis of the incident learning database identified 33 reported near-miss events related to SBRT planning. Combining both methods yielded a total of 76 possible process failures, of which 13 (17%) were missed by FMEA while 43 (57%) identified by FMEA only. When scored for RPN, the 13 events missed by FMEA ranked within the lower half of all failure modes and exhibited significantly lower severity relative to those identified by FMEA (p = 0.02). FMEA, though valuable, is subject to certain limitations. In this study, FMEA failed to identify 17% of actual failure modes, though these were of lower risk. Similarly, an incident learning system alone fails to identify a large number of potentially high-severity process errors. Using FMEA in combination with incident learning may render an improved overview of risks within a process.

The mediating effect of self-reflection and learning effectiveness on clinical nursing performance in nursing students: A follow-up study.

PubMed

Pai, Hsiang-Chu; Ko, Hui-Ling; Eng, Cheng-Joo; Yen, Wen-Jiuan

The effectiveness of simulation learning and the effects of anxiety in the simulated situation have been understudied. In addition, research on the association between learning effectiveness and students' clinical care performance in the hospital setting is very limited in Taiwan. The aim of this study is to examine the mediating effect of self-reflection and simulation learning effectiveness on the clinical nursing performance of nursing students. A Prospective, longitudinal, and correlational design was used. The study was conducted from December 2014 to July 2015. Participants were 293 nursing students in southern Taiwan. A structural model was specified and tested using partial least squares structural equation modeling to examine the relationships between the variables. The results revealed that the model was robust in terms of its measurement quality (reliability, validity, and goodness of fit), with the data's explaining 38.3% of variance in nursing competence. As self-reflection and learning effectiveness were added into the structural model, the effect of anxiety on nursing competence was still significant, but the regression coefficient (β) estimate of -0.41 (p<0.05) changed to β=-0.15 (p<0.050),indicating that self-reflection and learning effectiveness mediated the relationship between anxiety and nursing competence. Nursing competence was negatively affected by anxiety and positively affected by self-reflection (β=0.49, p<0.05) and simulation learning effectiveness (β=0.10, p<0.05). The teacher's encouraging learning can have a positive influence on students' self-reflection and learning effectiveness, which then decreases the effect of anxiety on nursing competence and further promotes students' clinical care ability. Copyright © 2017 Elsevier Inc. All rights reserved.

Emotional textile image classification based on cross-domain convolutional sparse autoencoders with feature selection

NASA Astrophysics Data System (ADS)

Li, Zuhe; Fan, Yangyu; Liu, Weihua; Yu, Zeqi; Wang, Fengqin

2017-01-01

We aim to apply sparse autoencoder-based unsupervised feature learning to emotional semantic analysis for textile images. To tackle the problem of limited training data, we present a cross-domain feature learning scheme for emotional textile image classification using convolutional autoencoders. We further propose a correlation-analysis-based feature selection method for the weights learned by sparse autoencoders to reduce the number of features extracted from large size images. First, we randomly collect image patches on an unlabeled image dataset in the source domain and learn local features with a sparse autoencoder. We then conduct feature selection according to the correlation between different weight vectors corresponding to the autoencoder's hidden units. We finally adopt a convolutional neural network including a pooling layer to obtain global feature activations of textile images in the target domain and send these global feature vectors into logistic regression models for emotional image classification. The cross-domain unsupervised feature learning method achieves 65% to 78% average accuracy in the cross-validation experiments corresponding to eight emotional categories and performs better than conventional methods. Feature selection can reduce the computational cost of global feature extraction by about 50% while improving classification performance.

Deep learning based classification of breast tumors with shear-wave elastography.

PubMed

Zhang, Qi; Xiao, Yang; Dai, Wei; Suo, Jingfeng; Wang, Congzhi; Shi, Jun; Zheng, Hairong

2016-12-01

This study aims to build a deep learning (DL) architecture for automated extraction of learned-from-data image features from the shear-wave elastography (SWE), and to evaluate the DL architecture in differentiation between benign and malignant breast tumors. We construct a two-layer DL architecture for SWE feature extraction, comprised of the point-wise gated Boltzmann machine (PGBM) and the restricted Boltzmann machine (RBM). The PGBM contains task-relevant and task-irrelevant hidden units, and the task-relevant units are connected to the RBM. Experimental evaluation was performed with five-fold cross validation on a set of 227 SWE images, 135 of benign tumors and 92 of malignant tumors, from 121 patients. The features learned with our DL architecture were compared with the statistical features quantifying image intensity and texture. Results showed that the DL features achieved better classification performance with an accuracy of 93.4%, a sensitivity of 88.6%, a specificity of 97.1%, and an area under the receiver operating characteristic curve of 0.947. The DL-based method integrates feature learning with feature selection on SWE. It may be potentially used in clinical computer-aided diagnosis of breast cancer. Copyright © 2016 Elsevier B.V. All rights reserved.

Soil-pipe interaction modeling for pipe behavior prediction with super learning based methods

NASA Astrophysics Data System (ADS)

Shi, Fang; Peng, Xiang; Liu, Huan; Hu, Yafei; Liu, Zheng; Li, Eric

2018-03-01

Underground pipelines are subject to severe distress from the surrounding expansive soil. To investigate the structural response of water mains to varying soil movements, field data, including pipe wall strains in situ soil water content, soil pressure and temperature, was collected. The research on monitoring data analysis has been reported, but the relationship between soil properties and pipe deformation has not been well-interpreted. To characterize the relationship between soil property and pipe deformation, this paper presents a super learning based approach combining feature selection algorithms to predict the water mains structural behavior in different soil environments. Furthermore, automatic variable selection method, e.i. recursive feature elimination algorithm, were used to identify the critical predictors contributing to the pipe deformations. To investigate the adaptability of super learning to different predictive models, this research employed super learning based methods to three different datasets. The predictive performance was evaluated by R-squared, root-mean-square error and mean absolute error. Based on the prediction performance evaluation, the superiority of super learning was validated and demonstrated by predicting three types of pipe deformations accurately. In addition, a comprehensive understand of the water mains working environments becomes possible.

Mental Health Risk Adjustment with Clinical Categories and Machine Learning.

PubMed

Shrestha, Akritee; Bergquist, Savannah; Montz, Ellen; Rose, Sherri

2017-12-15

To propose nonparametric ensemble machine learning for mental health and substance use disorders (MHSUD) spending risk adjustment formulas, including considering Clinical Classification Software (CCS) categories as diagnostic covariates over the commonly used Hierarchical Condition Category (HCC) system. 2012-2013 Truven MarketScan database. We implement 21 algorithms to predict MHSUD spending, as well as a weighted combination of these algorithms called super learning. The algorithm collection included seven unique algorithms that were supplied with three differing sets of MHSUD-related predictors alongside demographic covariates: HCC, CCS, and HCC + CCS diagnostic variables. Performance was evaluated based on cross-validated R 2 and predictive ratios. Results show that super learning had the best performance based on both metrics. The top single algorithm was random forests, which improved on ordinary least squares regression by 10 percent with respect to relative efficiency. CCS categories-based formulas were generally more predictive of MHSUD spending compared to HCC-based formulas. Literature supports the potential benefit of implementing a separate MHSUD spending risk adjustment formula. Our results suggest there is an incentive to explore machine learning for MHSUD-specific risk adjustment, as well as considering CCS categories over HCCs. © Health Research and Educational Trust.

Online cross-validation-based ensemble learning.

PubMed

Benkeser, David; Ju, Cheng; Lendle, Sam; van der Laan, Mark

2018-01-30

Online estimators update a current estimate with a new incoming batch of data without having to revisit past data thereby providing streaming estimates that are scalable to big data. We develop flexible, ensemble-based online estimators of an infinite-dimensional target parameter, such as a regression function, in the setting where data are generated sequentially by a common conditional data distribution given summary measures of the past. This setting encompasses a wide range of time-series models and, as special case, models for independent and identically distributed data. Our estimator considers a large library of candidate online estimators and uses online cross-validation to identify the algorithm with the best performance. We show that by basing estimates on the cross-validation-selected algorithm, we are asymptotically guaranteed to perform as well as the true, unknown best-performing algorithm. We provide extensions of this approach including online estimation of the optimal ensemble of candidate online estimators. We illustrate excellent performance of our methods using simulations and a real data example where we make streaming predictions of infectious disease incidence using data from a large database. Copyright © 2017 John Wiley & Sons, Ltd. Copyright © 2017 John Wiley & Sons, Ltd.

Design and Development Computer-Based E-Learning Teaching Material for Improving Mathematical Understanding Ability and Spatial Sense of Junior High School Students

NASA Astrophysics Data System (ADS)

Nurjanah; Dahlan, J. A.; Wibisono, Y.

2017-02-01

This paper aims to make a design and development computer-based e-learning teaching material for improving mathematical understanding ability and spatial sense of junior high school students. Furthermore, the particular aims are (1) getting teaching material design, evaluation model, and intrument to measure mathematical understanding ability and spatial sense of junior high school students; (2) conducting trials computer-based e-learning teaching material model, asessment, and instrument to develop mathematical understanding ability and spatial sense of junior high school students; (3) completing teaching material models of computer-based e-learning, assessment, and develop mathematical understanding ability and spatial sense of junior high school students; (4) resulting research product is teaching materials of computer-based e-learning. Furthermore, the product is an interactive learning disc. The research method is used of this study is developmental research which is conducted by thought experiment and instruction experiment. The result showed that teaching materials could be used very well. This is based on the validation of computer-based e-learning teaching materials, which is validated by 5 multimedia experts. The judgement result of face and content validity of 5 validator shows that the same judgement result to the face and content validity of each item test of mathematical understanding ability and spatial sense. The reliability test of mathematical understanding ability and spatial sense are 0,929 and 0,939. This reliability test is very high. While the validity of both tests have a high and very high criteria.

A cross-level investigation of informal field-based learning and performance improvements.

PubMed

Wolfson, Mikhail A; Tannenbaum, Scott I; Mathieu, John E; Maynard, M Travis

2018-01-01

Organizations often operate in complex and dynamic environments which place a premium on employees' ongoing learning and acquisition of new competencies. Additionally, the majority of learning in organizations does not take place in formal training settings, but we know relatively little about how informal field-based learning (IFBL) behaviors relate to changes in job performance. In this study, we first clarified the construct of IFBL as a subset of informal learning. Second, on the basis of this clarified construct definition, we developed a measure of IFBL behaviors and demonstrated its psychometric properties using (a) a sample of subject matter experts who made item content validity judgments and (b) both an Amazon Mechanical Turk sample (N = 400) and a sample of 1,707 healthcare employees. Third, we advanced a grounded theory of IFBL in healthcare, and related it to individuals' regulatory foci and contextual moderators of IFBL behaviors-job performance relationships using a cross-level design and lagged nonmethod bound measures. Specifically, using a sample of 407 healthcare workers from 49 hospital units, our results suggested that promotion-focused individuals, especially in well-staffed units, readily engage in IFBL behaviors. Additionally, we found that the IFBL-changes in job performance relationship was strengthened to the extent that individuals worked in units with relatively nonpunitive climates. Interestingly, staffing levels had a weakening moderating effect on the positive IFBL-performance improvements relationship. Detailed follow-up analyses revealed that the peculiar effect was attributable to differential relationships from IFBL subdimensions. Implications for future theory building, research, and practice are discussed. (PsycINFO Database Record (c) 2018 APA, all rights reserved).

A multicenter prospective cohort study on camera navigation training for key user groups in minimally invasive surgery.

PubMed

Graafland, Maurits; Bok, Kiki; Schreuder, Henk W R; Schijven, Marlies P

2014-06-01

Untrained laparoscopic camera assistants in minimally invasive surgery (MIS) may cause suboptimal view of the operating field, thereby increasing risk for errors. Camera navigation is often performed by the least experienced member of the operating team, such as inexperienced surgical residents, operating room nurses, and medical students. The operating room nurses and medical students are currently not included as key user groups in structured laparoscopic training programs. A new virtual reality laparoscopic camera navigation (LCN) module was specifically developed for these key user groups. This multicenter prospective cohort study assesses face validity and construct validity of the LCN module on the Simendo virtual reality simulator. Face validity was assessed through a questionnaire on resemblance to reality and perceived usability of the instrument among experts and trainees. Construct validity was assessed by comparing scores of groups with different levels of experience on outcome parameters of speed and movement proficiency. The results obtained show uniform and positive evaluation of the LCN module among expert users and trainees, signifying face validity. Experts and intermediate experience groups performed significantly better in task time and camera stability during three repetitions, compared to the less experienced user groups (P < .007). Comparison of learning curves showed significant improvement of proficiency in time and camera stability for all groups during three repetitions (P < .007). The results of this study show face validity and construct validity of the LCN module. The module is suitable for use in training curricula for operating room nurses and novice surgical trainees, aimed at improving team performance in minimally invasive surgery. © The Author(s) 2013.

Identifying Active Travel Behaviors in Challenging Environments Using GPS, Accelerometers, and Machine Learning Algorithms

PubMed Central

Ellis, Katherine; Godbole, Suneeta; Marshall, Simon; Lanckriet, Gert; Staudenmayer, John; Kerr, Jacqueline

2014-01-01

Background: Active travel is an important area in physical activity research, but objective measurement of active travel is still difficult. Automated methods to measure travel behaviors will improve research in this area. In this paper, we present a supervised machine learning method for transportation mode prediction from global positioning system (GPS) and accelerometer data. Methods: We collected a dataset of about 150 h of GPS and accelerometer data from two research assistants following a protocol of prescribed trips consisting of five activities: bicycling, riding in a vehicle, walking, sitting, and standing. We extracted 49 features from 1-min windows of this data. We compared the performance of several machine learning algorithms and chose a random forest algorithm to classify the transportation mode. We used a moving average output filter to smooth the output predictions over time. Results: The random forest algorithm achieved 89.8% cross-validated accuracy on this dataset. Adding the moving average filter to smooth output predictions increased the cross-validated accuracy to 91.9%. Conclusion: Machine learning methods are a viable approach for automating measurement of active travel, particularly for measuring travel activities that traditional accelerometer data processing methods misclassify, such as bicycling and vehicle travel. PMID:24795875

Beyond static assessment of children's receptive vocabulary: the dynamic assessment of word learning (DAWL).

PubMed

Camilleri, Bernard; Botting, Nicola

2013-01-01

Children's low scores on vocabulary tests are often erroneously interpreted as reflecting poor cognitive and/or language skills. It may be necessary to incorporate the measurement of word-learning ability in estimating children's lexical abilities. To explore the reliability and validity of the Dynamic Assessment of Word Learning (DAWL), a new dynamic assessment of receptive vocabulary. A dynamic assessment (DA) of word learning ability was developed and adopted within a nursery school setting with 15 children aged between 3;07 and 4;03, ten of whom had been referred to speech and language therapy. A number of quantitative measures were derived from the DA procedure, including measures of children's ability to identify the targeted items and to generalize to a second exemplar, as well as measures of children's ability to retain the targeted items. Internal, inter-rater and test-retest reliability of the DAWL was established as well as correlational measures of concurrent and predictive validity. The DAWL was found to provide both quantitative and qualitative information which could be used to improve the accuracy of differential diagnosis and the understanding of processes underlying the child's performance. The latter can be used for the purpose of designing more individualized interventions. © 2013 Royal College of Speech and Language Therapists.

Ecologically relevant episodic memory assessment indicates an attenuated age-related memory loss - A virtual reality study.

PubMed

Pflueger, Marlon O; Stieglitz, Rolf-Dieter; Lemoine, Patrick; Leyhe, Thomas

2018-06-07

Since the advent of imaging techniques, the role of the neuropsychological assessment has changed. Questions concerning everyday functionality became primarily important and, thus, ecologically valid neuropsychological assessments are mandatory. Virtual reality (VR) environments might provide a way of implementing immersive cognitive assessments with a higher degree of everyday-life-related cognitive demands. We report on a VR-based episodic memory examination in N = 30 young and N = 18 healthy older adults (HOA) using a kitchen scene. The test procedure was designed to be structurally comparable to clinically used California Verbal Learning Test (CVLT) in terms of repeated learning trials as well as short and long delayed recall measures. The results showed that age-related learning and performance decrements were mainly evident in the CVLT but not in the VR-memory examination. The ecologically valid VR-memory examination might provide a more accurate "age-fair" estimation of everyday-life-related memory demands in HOA than the frequently and clinically used CVLT. We concluded this from our finding of context-related automatic and effortless activations of deeply experience based encoding and retrieval strategies with regard to everyday-life-related objects in the HOA, which might not be paralleled by learning arbitrary word associations. (PsycINFO Database Record (c) 2018 APA, all rights reserved).

Development and validation of the Simulation Learning Effectiveness Scale for nursing students.

PubMed

Pai, Hsiang-Chu

2016-11-01

To develop and validate the Simulation Learning Effectiveness Scale, which is based on Bandura's social cognitive theory. A simulation programme is a significant teaching strategy for nursing students. Nevertheless, there are few evidence-based instruments that validate the effectiveness of simulation learning in Taiwan. This is a quantitative descriptive design. In Study 1, a nonprobability convenience sample of 151 student nurses completed the Simulation Learning Effectiveness Scale. Exploratory factor analysis was used to examine the factor structure of the instrument. In Study 2, which involved 365 student nurses, confirmatory factor analysis and structural equation modelling were used to analyse the construct validity of the Simulation Learning Effectiveness Scale. In Study 1, exploratory factor analysis yielded three components: self-regulation, self-efficacy and self-motivation. The three factors explained 29·09, 27·74 and 19·32% of the variance, respectively. The final 12-item instrument with the three factors explained 76·15% of variance. Cronbach's alpha was 0·94. In Study 2, confirmatory factor analysis identified a second-order factor termed Simulation Learning Effectiveness Scale. Goodness-of-fit indices showed an acceptable fit overall with the full model (χ 2 /df (51) = 3·54, comparative fit index = 0·96, Tucker-Lewis index = 0·95 and standardised root-mean-square residual = 0·035). In addition, teacher's competence was found to encourage learning, and self-reflection and insight were significantly and positively associated with Simulation Learning Effectiveness Scale. Teacher's competence in encouraging learning also was significantly and positively associated with self-reflection and insight. Overall, theses variable explained 21·9% of the variance in the student's learning effectiveness. The Simulation Learning Effectiveness Scale is a reliable and valid means to assess simulation learning effectiveness for nursing students. The Simulation Learning Effectiveness Scale can be used to examine nursing students' learning effectiveness and serve as a basis to improve student's learning efficiency through simulation programmes. Future implementation research that focuses on the relationship between learning effectiveness and nursing competence in nursing students is recommended. © 2016 John Wiley & Sons Ltd.

Deep learning and texture-based semantic label fusion for brain tumor segmentation

NASA Astrophysics Data System (ADS)

Vidyaratne, L.; Alam, M.; Shboul, Z.; Iftekharuddin, K. M.

2018-02-01

Brain tumor segmentation is a fundamental step in surgical treatment and therapy. Many hand-crafted and learning based methods have been proposed for automatic brain tumor segmentation from MRI. Studies have shown that these approaches have their inherent advantages and limitations. This work proposes a semantic label fusion algorithm by combining two representative state-of-the-art segmentation algorithms: texture based hand-crafted, and deep learning based methods to obtain robust tumor segmentation. We evaluate the proposed method using publicly available BRATS 2017 brain tumor segmentation challenge dataset. The results show that the proposed method offers improved segmentation by alleviating inherent weaknesses: extensive false positives in texture based method, and the false tumor tissue classification problem in deep learning method, respectively. Furthermore, we investigate the effect of patient's gender on the segmentation performance using a subset of validation dataset. Note the substantial improvement in brain tumor segmentation performance proposed in this work has recently enabled us to secure the first place by our group in overall patient survival prediction task at the BRATS 2017 challenge.

Deep Learning and Texture-Based Semantic Label Fusion for Brain Tumor Segmentation.

PubMed

Vidyaratne, L; Alam, M; Shboul, Z; Iftekharuddin, K M

2018-01-01

Brain tumor segmentation is a fundamental step in surgical treatment and therapy. Many hand-crafted and learning based methods have been proposed for automatic brain tumor segmentation from MRI. Studies have shown that these approaches have their inherent advantages and limitations. This work proposes a semantic label fusion algorithm by combining two representative state-of-the-art segmentation algorithms: texture based hand-crafted, and deep learning based methods to obtain robust tumor segmentation. We evaluate the proposed method using publicly available BRATS 2017 brain tumor segmentation challenge dataset. The results show that the proposed method offers improved segmentation by alleviating inherent weaknesses: extensive false positives in texture based method, and the false tumor tissue classification problem in deep learning method, respectively. Furthermore, we investigate the effect of patient's gender on the segmentation performance using a subset of validation dataset. Note the substantial improvement in brain tumor segmentation performance proposed in this work has recently enabled us to secure the first place by our group in overall patient survival prediction task at the BRATS 2017 challenge.

Progress in computational toxicology.

PubMed

Ekins, Sean

2014-01-01

Computational methods have been widely applied to toxicology across pharmaceutical, consumer product and environmental fields over the past decade. Progress in computational toxicology is now reviewed. A literature review was performed on computational models for hepatotoxicity (e.g. for drug-induced liver injury (DILI)), cardiotoxicity, renal toxicity and genotoxicity. In addition various publications have been highlighted that use machine learning methods. Several computational toxicology model datasets from past publications were used to compare Bayesian and Support Vector Machine (SVM) learning methods. The increasing amounts of data for defined toxicology endpoints have enabled machine learning models that have been increasingly used for predictions. It is shown that across many different models Bayesian and SVM perform similarly based on cross validation data. Considerable progress has been made in computational toxicology in a decade in both model development and availability of larger scale or 'big data' models. The future efforts in toxicology data generation will likely provide us with hundreds of thousands of compounds that are readily accessible for machine learning models. These models will cover relevant chemistry space for pharmaceutical, consumer product and environmental applications. Copyright © 2013 Elsevier Inc. All rights reserved.

Evaluation of an instructional model to teach clinically relevant medicinal chemistry in a campus and a distance pathway.

PubMed

Alsharif, Naser Z; Galt, Kimberly A

2008-04-15

To evaluate an instructional model for teaching clinically relevant medicinal chemistry. An instructional model that uses Bloom's cognitive and Krathwohl's affective taxonomy, published and tested concepts in teaching medicinal chemistry, and active learning strategies, was introduced in the medicinal chemistry courses for second-professional year (P2) doctor of pharmacy (PharmD) students (campus and distance) in the 2005-2006 academic year. Student learning and the overall effectiveness of the instructional model were assessed. Student performance after introducing the instructional model was compared to that in prior years. Student performance on course examinations improved compared to previous years. Students expressed overall enthusiasm about the course and better understood the value of medicinal chemistry to clinical practice. The explicit integration of the cognitive and affective learning objectives improved student performance, student ability to apply medicinal chemistry to clinical practice, and student attitude towards the discipline. Testing this instructional model provided validation to this theoretical framework. The model is effective for both our campus and distance-students. This instructional model may also have broad-based applications to other science courses.

Validity of the Learning Portfolio: Analysis of a Portfolio Proposal for the University

ERIC Educational Resources Information Center

Gregori-Giralt, Eva; Menéndez-Varela, José Luis

2015-01-01

Validity is a central issue in portfolio-based assessment. This empirical study used a quantitative approach to analyse the validity of the inferences drawn from a disciplinary course work portfolio assessment comprising profession-specific and learning competencies. The study also examined the problems involved in the development of the…

The Construct of the Learning Organization: Dimensions, Measurement, and Validation

ERIC Educational Resources Information Center

Yang, Baiyin; Watkins, Karen E.; Marsick, Victoria J.

2004-01-01

This research describes efforts to develop and validate a multidimensional measure of the learning organization. An instrument was developed based on a critical review of both the conceptualization and practice of this construct. Supporting validity evidence for the instrument was obtained from several sources, including best model-data fit among…

Electronic Module Design with Scientifically Character-Charged Approach on Kinematics Material Learning to Improve Holistic Competence of High School Students in 10th Grade

NASA Astrophysics Data System (ADS)

Anggraini, R.; Darvina, Y.; Amir, H.; Murtiani, M.; Yulkifli, Y.

2018-04-01

The availability of modules in schools is currently lacking. Learners have not used the module as a source in the learning process. In accordance with the demands of the 2013 curriculum, that learning should be conducted using a scientific approach and loaded with character values as well as learning using interactive learning resources. The solution of this problem is to create an interactive module with a scientifically charged character approach. This interactive module can be used by learners outside the classroom or in the classroom. This interactive module contains straight motion material, parabolic motion and circular motion of high school physics class X semester 1. The purpose of this research is to produce an interactive module with a scientific approach charged with character and determine the validity and practicality. The research is Research and Development. This study was conducted only until the validity test and practice test. The validity test was conducted by three lecturers of Physics of FMIPA UNP as experts. The instruments used in this research are validation sheet and worksheet sheet. Data analysis technique used is product validity analysis. The object of this research is electronic module, while the subject of this research is three validator.

UK health-care professionals' experience of on-line learning techniques: a systematic review of qualitative data.

PubMed

Carroll, Christopher; Booth, Andrew; Papaioannou, Diana; Sutton, Anthea; Wong, Ruth

2009-01-01

Continuing professional development and education is vital to the provision of better health services and outcomes. The aim of this study is to contribute to the evidence base by performing a systematic review of qualitative data from studies reporting health professionals' experience of e-learning. No such previous review has been published. A systematic review of qualitative data reporting UK health professionals' experiences of the ways in which on-line learning is delivered by higher education and other relevant institutions. Evidence synthesis was performed with the use of thematic analysis grounded in the data. Literature searches identified 19 relevant studies. The subjects of the studies were nurses, midwives, and allied professions (8 studies), general practitioners and hospital doctors (6 studies), and a range of different health practitioners (5 studies). The majority of courses were stand-alone continuing professional development modules. Five key themes emerged from the data: peer communication, flexibility, support, knowledge validation, and course presentation and design. The effectiveness of on-line learning is mediated by the learning experience. If they are to enhance health professionals' experience of e-learning, courses need to address presentation and course design; they must be flexible, offer mechanisms for both support and rapid assessment, and develop effective and efficient means of communication, especially among the students themselves.

Creating a balanced scorecard for a hospital system.

PubMed

Pink, G H; McKillop, I; Schraa, E G; Preyra, C; Montgomery, C; Baker, G R

2001-01-01

In 1999, hospitals in Ontario, Canada, collaborated with a university-based research team to develop a report on the relative performance of individual hospitals in Canada's most populated province. The researchers used the balanced-scorecard framework advocated by Kaplan and Norton. Indicators of performance were developed in four areas: clinical utilization and outcomes, patient satisfaction, system integration and change, and financial performance and condition. The process of selecting, calculating, and validating meaningful indicators of financial performance and condition is outlined. Lessons learned along the way are provided. These lessons may prove valuable to other finance researchers and practitioners who are engaged in performance measurement endeavors.

Nonlinear Semi-Supervised Metric Learning Via Multiple Kernels and Local Topology.

PubMed

Li, Xin; Bai, Yanqin; Peng, Yaxin; Du, Shaoyi; Ying, Shihui

2018-03-01

Changing the metric on the data may change the data distribution, hence a good distance metric can promote the performance of learning algorithm. In this paper, we address the semi-supervised distance metric learning (ML) problem to obtain the best nonlinear metric for the data. First, we describe the nonlinear metric by the multiple kernel representation. By this approach, we project the data into a high dimensional space, where the data can be well represented by linear ML. Then, we reformulate the linear ML by a minimization problem on the positive definite matrix group. Finally, we develop a two-step algorithm for solving this model and design an intrinsic steepest descent algorithm to learn the positive definite metric matrix. Experimental results validate that our proposed method is effective and outperforms several state-of-the-art ML methods.

Learning Transfer--Validation of the Learning Transfer System Inventory in Portugal

ERIC Educational Resources Information Center

Velada, Raquel; Caetano, Antonio; Bates, Reid; Holton, Ed

2009-01-01

Purpose: The purpose of this paper is to analyze the construct validity of learning transfer system inventory (LTSI) for use in Portugal. Furthermore, it also aims to analyze whether LTSI dimensions differ across individual variables such as gender, age, educational level and job tenure. Design/methodology/approach: After a rigorous translation…

Development and Validation of a Scale Measuring Approaches to Work-Related Informal Learning

ERIC Educational Resources Information Center

Froehlich, Dominik E.; Beausaert, Simon; Segers, Mien

2017-01-01

Social approaches to work-related informal learning, such as proactive feedback-seeking, help-seeking and information-seeking, are important determinants of development in the workplace. Unfortunately, previous research has failed to clearly conceptualize these forms of learning and does not provide a validated and generally applicable measurement…

The Development and Validation of a Learning Progression for Argumentation in Science

ERIC Educational Resources Information Center

Osborne, Jonathan F.; Henderson, J. Bryan; MacPherson, Anna; Szu, Evan; Wild, Andrew; Yao, Shi-Ying

2016-01-01

Given the centrality of argumentation in the Next Generation Science Standards, there is an urgent need for an empirically validated learning progression of this core practice and the development of high-quality assessment items. Here, we introduce a hypothesized three-tiered learning progression for scientific argumentation. The learning…

Recognising and Validating Outcomes of Non-Accredited Learning: A Practical Approach.

ERIC Educational Resources Information Center

Greenwood, Maggie, Ed.; Hayes, Amanda, Ed.; Turner, Cheryl, Ed.; Vorhaus, John, Ed.

A group of adult educators in England conducted seven case studies to identify strategies for recognizing adult students' learning progress in nonaccredited programs. The case studies identified the following elements of good practice in the process of recording and validating achievement: (1) initial identification of learning objectives; (2)…

Identifying Wrist Fracture Patients with High Accuracy by Automatic Categorization of X-ray Reports

PubMed Central

de Bruijn, Berry; Cranney, Ann; O’Donnell, Siobhan; Martin, Joel D.; Forster, Alan J.

2006-01-01

The authors performed this study to determine the accuracy of several text classification methods to categorize wrist x-ray reports. We randomly sampled 751 textual wrist x-ray reports. Two expert reviewers rated the presence (n = 301) or absence (n = 450) of an acute fracture of wrist. We developed two information retrieval (IR) text classification methods and a machine learning method using a support vector machine (TC-1). In cross-validation on the derivation set (n = 493), TC-1 outperformed the two IR based methods and six benchmark classifiers, including Naive Bayes and a Neural Network. In the validation set (n = 258), TC-1 demonstrated consistent performance with 93.8% accuracy; 95.5% sensitivity; 92.9% specificity; and 87.5% positive predictive value. TC-1 was easy to implement and superior in performance to the other classification methods. PMID:16929046

Validation and learning in the Procedicus KSA virtual reality surgical simulator.

PubMed

Ström, P; Kjellin, A; Hedman, L; Johnson, E; Wredmark, T; Felländer-Tsai, L

2003-02-01

Advanced simulator training within medicine is a rapidly growing field. Virtual reality simulators are being introduced as cost-saving educational tools, which also lead to increased patient safety. Fifteen medical students were included in the study. For 10 medical students performance was monitored, before and after 1 h of training, in two endoscopic simulators (the Procedicus KSA with haptic feedback and anatomical graphics and the established MIST simulator without this haptic feedback and graphics). Five medical students performed 50 tests in the Procedicus KSA in order to analyze learning curves. One of these five medical students performed multiple training sessions during 2 weeks and performed more than 300 tests. There was a significant improvement after 1 h of training regarding time, movement economy, and total score. The results in the two simulators were highly correlated. Our results show that the use of surgical simulators as a pedagogical tool in medical student training is encouraging. It shows rapid learning curves and our suggestion is to introduce endoscopic simulator training in undergraduate medical education during the course in surgery when motivation is high and before the development of "negative stereotypes" and incorrect practices.

A Cross-Cultural Validity of the E-Learning Acceptance Measure (ElAM) in Lebanon and England: A Confirmatory Factor Analysis

ERIC Educational Resources Information Center

Tarhini, Ali; Teo, Timothy; Tarhini, Takwa

2016-01-01

Despite the prevalence and significance of e-learning in education, there is a dearth of published instruments for educational researchers and practitioners that measure users' acceptance of e-learning. To meet this need, Teo (2010) developed the E-learning Acceptance Measure (ElAM). The main objective of this paper is to validate the ElAM (Teo,…

Hardware-Efficient On-line Learning through Pipelined Truncated-Error Backpropagation in Binary-State Networks

PubMed Central

Mostafa, Hesham; Pedroni, Bruno; Sheik, Sadique; Cauwenberghs, Gert

2017-01-01

Artificial neural networks (ANNs) trained using backpropagation are powerful learning architectures that have achieved state-of-the-art performance in various benchmarks. Significant effort has been devoted to developing custom silicon devices to accelerate inference in ANNs. Accelerating the training phase, however, has attracted relatively little attention. In this paper, we describe a hardware-efficient on-line learning technique for feedforward multi-layer ANNs that is based on pipelined backpropagation. Learning is performed in parallel with inference in the forward pass, removing the need for an explicit backward pass and requiring no extra weight lookup. By using binary state variables in the feedforward network and ternary errors in truncated-error backpropagation, the need for any multiplications in the forward and backward passes is removed, and memory requirements for the pipelining are drastically reduced. Further reduction in addition operations owing to the sparsity in the forward neural and backpropagating error signal paths contributes to highly efficient hardware implementation. For proof-of-concept validation, we demonstrate on-line learning of MNIST handwritten digit classification on a Spartan 6 FPGA interfacing with an external 1Gb DDR2 DRAM, that shows small degradation in test error performance compared to an equivalently sized binary ANN trained off-line using standard back-propagation and exact errors. Our results highlight an attractive synergy between pipelined backpropagation and binary-state networks in substantially reducing computation and memory requirements, making pipelined on-line learning practical in deep networks. PMID:28932180

Hardware-Efficient On-line Learning through Pipelined Truncated-Error Backpropagation in Binary-State Networks.

PubMed

Mostafa, Hesham; Pedroni, Bruno; Sheik, Sadique; Cauwenberghs, Gert

2017-01-01

Artificial neural networks (ANNs) trained using backpropagation are powerful learning architectures that have achieved state-of-the-art performance in various benchmarks. Significant effort has been devoted to developing custom silicon devices to accelerate inference in ANNs. Accelerating the training phase, however, has attracted relatively little attention. In this paper, we describe a hardware-efficient on-line learning technique for feedforward multi-layer ANNs that is based on pipelined backpropagation. Learning is performed in parallel with inference in the forward pass, removing the need for an explicit backward pass and requiring no extra weight lookup. By using binary state variables in the feedforward network and ternary errors in truncated-error backpropagation, the need for any multiplications in the forward and backward passes is removed, and memory requirements for the pipelining are drastically reduced. Further reduction in addition operations owing to the sparsity in the forward neural and backpropagating error signal paths contributes to highly efficient hardware implementation. For proof-of-concept validation, we demonstrate on-line learning of MNIST handwritten digit classification on a Spartan 6 FPGA interfacing with an external 1Gb DDR2 DRAM, that shows small degradation in test error performance compared to an equivalently sized binary ANN trained off-line using standard back-propagation and exact errors. Our results highlight an attractive synergy between pipelined backpropagation and binary-state networks in substantially reducing computation and memory requirements, making pipelined on-line learning practical in deep networks.

Machine learning to predict the occurrence of bisphosphonate-related osteonecrosis of the jaw associated with dental extraction: A preliminary report.

PubMed

Kim, Dong Wook; Kim, Hwiyoung; Nam, Woong; Kim, Hyung Jun; Cha, In-Ho

2018-04-23

The aim of this study was to build and validate five types of machine learning models that can predict the occurrence of BRONJ associated with dental extraction in patients taking bisphosphonates for the management of osteoporosis. A retrospective review of the medical records was conducted to obtain cases and controls for the study. Total 125 patients consisting of 41 cases and 84 controls were selected for the study. Five machine learning prediction algorithms including multivariable logistic regression model, decision tree, support vector machine, artificial neural network, and random forest were implemented. The outputs of these models were compared with each other and also with conventional methods, such as serum CTX level. Area under the receiver operating characteristic (ROC) curve (AUC) was used to compare the results. The performance of machine learning models was significantly superior to conventional statistical methods and single predictors. The random forest model yielded the best performance (AUC = 0.973), followed by artificial neural network (AUC = 0.915), support vector machine (AUC = 0.882), logistic regression (AUC = 0.844), decision tree (AUC = 0.821), drug holiday alone (AUC = 0.810), and CTX level alone (AUC = 0.630). Machine learning methods showed superior performance in predicting BRONJ associated with dental extraction compared to conventional statistical methods using drug holiday and serum CTX level. Machine learning can thus be applied in a wide range of clinical studies. Copyright © 2017. Published by Elsevier Inc.

Detrended fluctuation analysis for major depressive disorder.

PubMed

Mumtaz, Wajid; Malik, Aamir Saeed; Ali, Syed Saad Azhar; Yasin, Mohd Azhar Mohd; Amin, Hafeezullah

2015-01-01

Clinical utility of Electroencephalography (EEG) based diagnostic studies is less clear for major depressive disorder (MDD). In this paper, a novel machine learning (ML) scheme was presented to discriminate the MDD patients and healthy controls. The proposed method inherently involved feature extraction, selection, classification and validation. The EEG data acquisition involved eyes closed (EC) and eyes open (EO) conditions. At feature extraction stage, the de-trended fluctuation analysis (DFA) was performed, based on the EEG data, to achieve scaling exponents. The DFA was performed to analyzes the presence or absence of long-range temporal correlations (LRTC) in the recorded EEG data. The scaling exponents were used as input features to our proposed system. At feature selection stage, 3 different techniques were used for comparison purposes. Logistic regression (LR) classifier was employed. The method was validated by a 10-fold cross-validation. As results, we have observed that the effect of 3 different reference montages on the computed features. The proposed method employed 3 different types of feature selection techniques for comparison purposes as well. The results show that the DFA analysis performed better in LE data compared with the IR and AR data. In addition, during Wilcoxon ranking, the AR performed better than LE and IR. Based on the results, it was concluded that the DFA provided useful information to discriminate the MDD patients and with further validation can be employed in clinics for diagnosis of MDD.

Validity and Normative Data for the Biber Figure Learning Test: A Visual Supraspan Memory Measure.

PubMed

Gifford, Katherine A; Liu, Dandan; Neal, Jacquelyn E; Acosta, Lealani Mae Y; Bell, Susan P; Wiggins, Margaret E; Wisniewski, Kristi M; Godfrey, Mary; Logan, Laura A; Hohman, Timothy J; Pechman, Kimberly R; Libon, David J; Blennow, Kaj; Zetterberg, Henrik; Jefferson, Angela L

2018-05-01

The Biber Figure Learning Test (BFLT), a visuospatial serial figure learning test, was evaluated for biological correlates and psychometric properties, and normative data were generated. Nondemented individuals ( n = 332, 73 ± 7, 41% female) from the Vanderbilt Memory & Aging Project completed a comprehensive neuropsychological protocol. Adjusted regression models related BFLT indices to structural brain magnetic resonance imaging and cerebrospinal fluid (CSF) markers of brain health. Regression-based normative data were generated. Lower BFLT performances (Total Learning, Delayed Recall, Recognition) related to smaller medial temporal lobe volumes and higher CSF tau concentrations but not CSF amyloid. BFLT indices were most strongly correlated with other measures of verbal and nonverbal memory and visuospatial skills. The BFLT provides a comprehensive assessment of all aspects of visuospatial learning and memory and is sensitive to biomarkers of unhealthy brain aging. Enhanced normative data enriches the clinical utility of this visual serial figure learning test for use with older adults.

Deep learning of unsteady laminar flow over a cylinder

NASA Astrophysics Data System (ADS)

Lee, Sangseung; You, Donghyun

2017-11-01

Unsteady flow over a circular cylinder is reconstructed using deep learning with a particular emphasis on elucidating the potential of learning the solution of the Navier-Stokes equations. A deep neural network (DNN) is employed for deep learning, while numerical simulations are conducted to produce training database. Instantaneous and mean flow fields which are reconstructed by deep learning are compared with the simulation results. Fourier transform of flow variables has been conducted to validate the ability of DNN to capture both amplitudes and frequencies of flow motions. Basis decomposition of learned flow is performed to understand the underlying mechanisms of learning flow through DNN. The present study suggests that a deep learning technique can be utilized for reconstruction and, potentially, for prediction of fluid flow instead of solving the Navier-Stokes equations. This work was supported by the National Research Foundation of Korea(NRF) Grant funded by the Korea government(Ministry of Science, ICT and Future Planning) (No. 2014R1A2A1A11049599, No. 2015R1A2A1A15056086, No. 2016R1E1A2A01939553).

Expected energy-based restricted Boltzmann machine for classification.

PubMed

Elfwing, S; Uchibe, E; Doya, K

2015-04-01

In classification tasks, restricted Boltzmann machines (RBMs) have predominantly been used in the first stage, either as feature extractors or to provide initialization of neural networks. In this study, we propose a discriminative learning approach to provide a self-contained RBM method for classification, inspired by free-energy based function approximation (FE-RBM), originally proposed for reinforcement learning. For classification, the FE-RBM method computes the output for an input vector and a class vector by the negative free energy of an RBM. Learning is achieved by stochastic gradient-descent using a mean-squared error training objective. In an earlier study, we demonstrated that the performance and the robustness of FE-RBM function approximation can be improved by scaling the free energy by a constant that is related to the size of network. In this study, we propose that the learning performance of RBM function approximation can be further improved by computing the output by the negative expected energy (EE-RBM), instead of the negative free energy. To create a deep learning architecture, we stack several RBMs on top of each other. We also connect the class nodes to all hidden layers to try to improve the performance even further. We validate the classification performance of EE-RBM using the MNIST data set and the NORB data set, achieving competitive performance compared with other classifiers such as standard neural networks, deep belief networks, classification RBMs, and support vector machines. The purpose of using the NORB data set is to demonstrate that EE-RBM with binary input nodes can achieve high performance in the continuous input domain. Copyright © 2014 The Authors. Published by Elsevier Ltd.. All rights reserved.

Supervised Learning for Detection of Duplicates in Genomic Sequence Databases.

PubMed

Chen, Qingyu; Zobel, Justin; Zhang, Xiuzhen; Verspoor, Karin

2016-01-01

First identified as an issue in 1996, duplication in biological databases introduces redundancy and even leads to inconsistency when contradictory information appears. The amount of data makes purely manual de-duplication impractical, and existing automatic systems cannot detect duplicates as precisely as can experts. Supervised learning has the potential to address such problems by building automatic systems that learn from expert curation to detect duplicates precisely and efficiently. While machine learning is a mature approach in other duplicate detection contexts, it has seen only preliminary application in genomic sequence databases. We developed and evaluated a supervised duplicate detection method based on an expert curated dataset of duplicates, containing over one million pairs across five organisms derived from genomic sequence databases. We selected 22 features to represent distinct attributes of the database records, and developed a binary model and a multi-class model. Both models achieve promising performance; under cross-validation, the binary model had over 90% accuracy in each of the five organisms, while the multi-class model maintains high accuracy and is more robust in generalisation. We performed an ablation study to quantify the impact of different sequence record features, finding that features derived from meta-data, sequence identity, and alignment quality impact performance most strongly. The study demonstrates machine learning can be an effective additional tool for de-duplication of genomic sequence databases. All Data are available as described in the supplementary material.

Active learning in the space engineering education at Technical University of Madrid

NASA Astrophysics Data System (ADS)

Rodríguez, Jacobo; Laverón-Simavilla, Ana; Lapuerta, Victoria; Ezquerro Navarro, Jose Miguel; Cordero-Gracia, Marta

This work describes the innovative activities performed in the field of space education at the Technical University of Madrid (UPM), in collaboration with the center engaged by the European Space Agency (ESA) in Spain to support the operations for scientific experiments on board the International Space Station (E-USOC). These activities have been integrated along the last academic year of the Aerospatiale Engineering degree. A laboratory has been created, where the students have to validate and integrate the subsystems of a microsatellite by using demonstrator satellites. With the acquired skills, the students participate in a training process centered on Project Based Learning, where the students work in groups to perform the conceptual design of a space mission, being each student responsible for the design of a subsystem of the satellite and another one responsible of the mission design. In parallel, the students perform a training using a ground station, installed at the E-USOC building, which allow them to learn how to communicate with satellites, how to download telemetry and how to process the data. This also allows students to learn how the E-USOC works. Two surveys have been conducted to evaluate the impact of these techniques in the student engineering skills and to know the degree of satisfaction of students with respect to the use of these learning methodologies.

Boosting instance prototypes to detect local dermoscopic features.

PubMed

Situ, Ning; Yuan, Xiaojing; Zouridakis, George

2010-01-01

Local dermoscopic features are useful in many dermoscopic criteria for skin cancer detection. We address the problem of detecting local dermoscopic features from epiluminescence (ELM) microscopy skin lesion images. We formulate the recognition of local dermoscopic features as a multi-instance learning (MIL) problem. We employ the method of diverse density (DD) and evidence confidence (EC) function to convert MIL to a single-instance learning (SIL) problem. We apply Adaboost to improve the classification performance with support vector machines (SVMs) as the base classifier. We also propose to boost the selection of instance prototypes through changing the data weights in the DD function. We validate the methods on detecting ten local dermoscopic features from a dataset with 360 images. We compare the performance of the MIL approach, its boosting version, and a baseline method without using MIL. Our results show that boosting can provide performance improvement compared to the other two methods.

Developing Guided Inquiry-Based Student Lab Worksheet for Laboratory Knowledge Course

NASA Astrophysics Data System (ADS)

Rahmi, Y. L.; Novriyanti, E.; Ardi, A.; Rifandi, R.

2018-04-01

The course of laboratory knowledge is an introductory course for biology students to follow various lectures practicing in the biology laboratory. Learning activities of laboratory knowledge course at this time in the Biology Department, Universitas Negeri Padang has not been completed by supporting learning media such as student lab worksheet. Guided inquiry learning model is one of the learning models that can be integrated into laboratory activity. The study aimed to produce student lab worksheet based on guided inquiry for laboratory knowledge course and to determine the validity of lab worksheet. The research was conducted using research and developmet (R&D) model. The instruments used in data collection in this research were questionnaire for student needed analysis and questionnaire to measure the student lab worksheet validity. The data obtained was quantitative from several validators. The validators consist of three lecturers. The percentage of a student lab worksheet validity was 94.18 which can be categorized was very good.

Using Android-Based Educational Game for Learning Colloid Material

NASA Astrophysics Data System (ADS)

Sari, S.; Anjani, R.; Farida, I.; Ramdhani, M. A.

2017-09-01

This research is based on the importance of the development of student’s chemical literacy on Colloid material using Android-based educational game media. Educational game products are developed through research and development design. In the analysis phase, material analysis is performed to generate concept maps, determine chemical literacy indicators, game strategies and set game paths. In the design phase, product packaging is carried out, then validation and feasibility test are performed. Research produces educational game based on Android that has the characteristics that is: Colloid material presented in 12 levels of game in the form of questions and challenges, presents visualization of discourse, images and animation contextually to develop the process of thinking and attitude. Based on the analysis of validation and trial results, the product is considered feasible to use.

Performance of experienced dentists in Switzerland after an e-learning program on ICDAS occlusal caries detection.

PubMed

Rodrigues, Jonas Almeida; de Oliveira, Renata Schlesner; Hug, Isabel; Neuhaus, Klaus; Lussi, Adrian

2013-08-01

This study aimed to evaluate the effect of an e-learning program on the validity and reproducibility of the International Caries Detection and Assessment System (ICDAS) in detecting occlusal caries. For the study, 170 permanent molars were selected. Four dentists in Switzerland who had no previous contact with ICDAS examined the teeth before and after the e-learning program and scored the sites according to ICDAS. Teeth were histologically prepared and assessed for caries extension. The significance level was set at 0.05. Sensitivity before and after the e-learning program was 0.80 and 0.77 (D1), 0.72 and 0.63 (D2), and 0.74 and 0.67 (D3,4), respectively. Specificity was 0.64 and 0.69 (D1), 0.70 and 0.81 (D2), and 0.81 and 0.87 (D3,4). A McNemar test did not show any difference between the values of sensitivity, specificity, accuracy, and area under the ROC curve (AUC) before and after the e-learning program. The averages of wK values for interexaminer reproducibility were 0.61 (before) and 0.66 (after). Correlation with histology presented wK values of 0.62 (before) and 0.63 (after). A Wilcoxon test showed a statistically significant difference between before and after the e-learning program. In conclusion, even though ICDAS performed well in detecting occlusal caries, the e-learning program did not have any statistically significant effect on its performance by these experienced dentists.

Modeling semantic aspects for cross-media image indexing.

PubMed

Monay, Florent; Gatica-Perez, Daniel

2007-10-01

To go beyond the query-by-example paradigm in image retrieval, there is a need for semantic indexing of large image collections for intuitive text-based image search. Different models have been proposed to learn the dependencies between the visual content of an image set and the associated text captions, then allowing for the automatic creation of semantic indices for unannotated images. The task, however, remains unsolved. In this paper, we present three alternatives to learn a Probabilistic Latent Semantic Analysis model (PLSA) for annotated images, and evaluate their respective performance for automatic image indexing. Under the PLSA assumptions, an image is modeled as a mixture of latent aspects that generates both image features and text captions, and we investigate three ways to learn the mixture of aspects. We also propose a more discriminative image representation than the traditional Blob histogram, concatenating quantized local color information and quantized local texture descriptors. The first learning procedure of a PLSA model for annotated images is a standard EM algorithm, which implicitly assumes that the visual and the textual modalities can be treated equivalently. The other two models are based on an asymmetric PLSA learning, allowing to constrain the definition of the latent space on the visual or on the textual modality. We demonstrate that the textual modality is more appropriate to learn a semantically meaningful latent space, which translates into improved annotation performance. A comparison of our learning algorithms with respect to recent methods on a standard dataset is presented, and a detailed evaluation of the performance shows the validity of our framework.

Validating Machine Learning Algorithms for Twitter Data Against Established Measures of Suicidality.

PubMed

Braithwaite, Scott R; Giraud-Carrier, Christophe; West, Josh; Barnes, Michael D; Hanson, Carl Lee

2016-05-16

One of the leading causes of death in the United States (US) is suicide and new methods of assessment are needed to track its risk in real time. Our objective is to validate the use of machine learning algorithms for Twitter data against empirically validated measures of suicidality in the US population. Using a machine learning algorithm, the Twitter feeds of 135 Mechanical Turk (MTurk) participants were compared with validated, self-report measures of suicide risk. Our findings show that people who are at high suicidal risk can be easily differentiated from those who are not by machine learning algorithms, which accurately identify the clinically significant suicidal rate in 92% of cases (sensitivity: 53%, specificity: 97%, positive predictive value: 75%, negative predictive value: 93%). Machine learning algorithms are efficient in differentiating people who are at a suicidal risk from those who are not. Evidence for suicidality can be measured in nonclinical populations using social media data.

Validating Machine Learning Algorithms for Twitter Data Against Established Measures of Suicidality

PubMed Central

2016-01-01

Background One of the leading causes of death in the United States (US) is suicide and new methods of assessment are needed to track its risk in real time. Objective Our objective is to validate the use of machine learning algorithms for Twitter data against empirically validated measures of suicidality in the US population. Methods Using a machine learning algorithm, the Twitter feeds of 135 Mechanical Turk (MTurk) participants were compared with validated, self-report measures of suicide risk. Results Our findings show that people who are at high suicidal risk can be easily differentiated from those who are not by machine learning algorithms, which accurately identify the clinically significant suicidal rate in 92% of cases (sensitivity: 53%, specificity: 97%, positive predictive value: 75%, negative predictive value: 93%). Conclusions Machine learning algorithms are efficient in differentiating people who are at a suicidal risk from those who are not. Evidence for suicidality can be measured in nonclinical populations using social media data. PMID:27185366

New Tools for Learning: A Case of Organizational Problem Analysis Derived from Debriefing Records in a Medical Center

ERIC Educational Resources Information Center

Holzmann, Vered; Mischari, Shoshana; Goldberg, Shoshana; Ziv, Amitai

2012-01-01

Purpose: This article aims to present a unique systematic and validated method for creating a linkage between past experiences and management of future occurrences in an organization. Design/methodology/approach: The study is based on actual data accumulated in a series of projects performed in a major medical center. Qualitative and quantitative…

Development of Nonword and Irregular Word Lists for Australian Grade 3 Students Using Rasch Analysis

ERIC Educational Resources Information Center

Callinan, Sarah; Cunningham, Everarda; Theiler, Stephen

2014-01-01

Many tests used in educational settings to identify learning difficulties endeavour to pick up only the lowest performers. Yet these tests are generally developed within a Classical Test Theory (CTT) paradigm that assumes that data do not have significant skew. Rasch analysis is more tolerant of skew and was used to validate two newly developed…

Determinants of Success on the ETS Business Major Field Exam for Students in an Undergraduate Multisite Regional University Business Program

ERIC Educational Resources Information Center

Bagamery, Bruce D.; Lasik, John J.; Nixon, Don R.

2005-01-01

Extending previous studies, the authors examined a larger set of variables to identify predictors of student performance on the Educational Testing Service Major Field Exam in Business, which has been shown to be an externally valid measure of student learning outcomes. Significant predictors include gender, whether students took the SAT, and…

Crowdsourced validation of a machine-learning classification system for autism and ADHD.

PubMed

Duda, M; Haber, N; Daniels, J; Wall, D P

2017-05-16

Autism spectrum disorder (ASD) and attention deficit hyperactivity disorder (ADHD) together affect >10% of the children in the United States, but considerable behavioral overlaps between the two disorders can often complicate differential diagnosis. Currently, there is no screening test designed to differentiate between the two disorders, and with waiting times from initial suspicion to diagnosis upwards of a year, methods to quickly and accurately assess risk for these and other developmental disorders are desperately needed. In a previous study, we found that four machine-learning algorithms were able to accurately (area under the curve (AUC)>0.96) distinguish ASD from ADHD using only a small subset of items from the Social Responsiveness Scale (SRS). Here, we expand upon our prior work by including a novel crowdsourced data set of responses to our predefined top 15 SRS-derived questions from parents of children with ASD (n=248) or ADHD (n=174) to improve our model's capability to generalize to new, 'real-world' data. By mixing these novel survey data with our initial archival sample (n=3417) and performing repeated cross-validation with subsampling, we created a classification algorithm that performs with AUC=0.89±0.01 using only 15 questions.

Effects of age on a real-world What-Where-When memory task

PubMed Central

Mazurek, Adèle; Bhoopathy, Raja Meenakshi; Read, Jenny C. A.; Gallagher, Peter; Smulders, Tom V.

2015-01-01

Many cognitive abilities decline with aging, making it difficult to detect pathological changes against a background of natural changes in cognition. Most of the tests to assess cognitive decline are artificial tasks that have little resemblance to the problems faced by people in everyday life. This means both that people may have little practice doing such tasks (potentially contributing to the decline in performance) and that the tasks may not be good predictors of real-world cognitive problems. In this study, we test the performance of young people (18–25 years) and older people (60+-year-olds) on a novel, more ecologically valid test of episodic memory: the real-world What-Where-When (WWW) memory test. We also compare them on a battery of other cognitive tests, including working memory, psychomotor speed, executive function, and episodic memory. Older people show the expected age-related declines on the test battery. In the WWW memory task, older people were more likely to fail to remember any WWW combination than younger people were, although they did not significantly differ in their overall WWW score due to some older people performing as well as or better than most younger people. WWW memory performance was significantly predicted by other measures of episodic memory, such as the single-trial learning and long-term retention in the Rey Auditory Verbal Learning task and Combined Object Location Memory in the Object Relocation task. Self-reported memory complaints also predicted performance on the WWW task. These findings confirm that our real-world WWW memory task is a valid measure of episodic memory, with high ecological validity, which may be useful as a predictor of everyday memory abilities. The task will require a bit more development to improve its sensitivity to cognitive declines in aging and to potentially distinguish between mentally healthy older adults and those with early signs of cognitive pathologies. PMID:26042030

Primary Sclerosing Cholangitis Risk Estimate Tool (PREsTo) Predicts Outcomes in PSC: A Derivation & Validation Study Using Machine Learning.

PubMed

Eaton, John E; Vesterhus, Mette; McCauley, Bryan M; Atkinson, Elizabeth J; Schlicht, Erik M; Juran, Brian D; Gossard, Andrea A; LaRusso, Nicholas F; Gores, Gregory J; Karlsen, Tom H; Lazaridis, Konstantinos N

2018-05-09

Improved methods are needed to risk stratify and predict outcomes in patients with primary sclerosing cholangitis (PSC). Therefore, we sought to derive and validate a new prediction model and compare its performance to existing surrogate markers. The model was derived using 509 subjects from a multicenter North American cohort and validated in an international multicenter cohort (n=278). Gradient boosting, a machine based learning technique, was used to create the model. The endpoint was hepatic decompensation (ascites, variceal hemorrhage or encephalopathy). Subjects with advanced PSC or cholangiocarcinoma at baseline were excluded. The PSC risk estimate tool (PREsTo) consists of 9 variables: bilirubin, albumin, serum alkaline phosphatase (SAP) times the upper limit of normal (ULN), platelets, AST, hemoglobin, sodium, patient age and the number of years since PSC was diagnosed. Validation in an independent cohort confirms PREsTo accurately predicts decompensation (C statistic 0.90, 95% confidence interval (CI) 0.84-0.95) and performed well compared to MELD score (C statistic 0.72, 95% CI 0.57-0.84), Mayo PSC risk score (C statistic 0.85, 95% CI 0.77-0.92) and SAP < 1.5x ULN (C statistic 0.65, 95% CI 0.55-0.73). PREsTo continued to be accurate among individuals with a bilirubin < 2.0 mg/dL (C statistic 0.90, 95% CI 0.82-0.96) and when the score was re-applied at a later course in the disease (C statistic 0.82, 95% CI 0.64-0.95). PREsTo accurately predicts hepatic decompensation in PSC and exceeds the performance among other widely available, noninvasive prognostic scoring systems. This article is protected by copyright. All rights reserved. © 2018 by the American Association for the Study of Liver Diseases.

The Development of Inquiry Learning Materials to Complete Content Life System Organization in Junior High School Students

NASA Astrophysics Data System (ADS)

Mayasari, F.; Raharjo; Supardi, Z. A. I.

2018-01-01

This research aims to develop the material eligibility to complete the inquiry learning of student in the material organization system of junior high school students. Learning materials developed include syllabi, lesson plans, students’ textbook, worksheets, and learning achievement test. This research is the developmental research which employ Dick and Carey model to develop learning material. The experiment was done in Junior High School 4 Lamongan regency using One Group Pretest-Posttest Design. The data collection used validation, observation, achievement test, questionnaire administration, and documentation. Data analysis techniques used quantitative and qualitative descriptive.The results showed that the developed learning material was valid and can be used. Learning activity accomplished with good category, where student activities were observed. The aspects of attitudes were observed during the learning process are honest, responsible, and confident. Student learning achievement gained an average of 81, 85 in complete category, with N-Gain 0, 75 for a high category. The activities and student response to learning was very well categorized. Based on the results, this researcher concluded that the device classified as feasible of inquiry-based learning (valid, practical, and effective) system used on the material organization of junior high school students.

Construction and validation of a distance learning module on premedication antisepsis for nursing professionals.

PubMed

Pereira, Barbara Juliana da Costa; Mendes, Isabel Amélia Costa; Beatriz Maria, Jorge; Mazzo, Alessandra

2013-11-01

The aim of this descriptive study, carried out at a public university, was to design, develop, and validate a distance learning module on intramuscular premedication antisepsis. The content was introduced in the Modular Object-Oriented Dynamic Learning Environment, based on the Systematic Model for Web-Based Training projects. Ten nurses and information technologists at work consented to participate, in compliance with ethical guidelines, and answered a questionnaire to validate the Virtual Learning Environment. The educational aspects of the environment interface were mostly evaluated as "excellent," whereas the assessment of didactic resources indicated interactivity difficulties. It is concluded that distance learning is an important tool for the teaching of premedication antisepsis. To ensure its effectiveness, appropriate methods and interactive devices must be used.

Validation of Skills, Knowledge and Experience in Lifelong Learning in Europe

ERIC Educational Resources Information Center

Ogunleye, James

2012-01-01

The paper examines systems of validation of skills and experience as well as the main methods/tools currently used for validating skills and knowledge in lifelong learning. The paper uses mixed methods--a case study research and content analysis of European Union policy documents and frameworks--as a basis for this research. The selection of the…

Quality Rating and Improvement System (QRIS) Validation Study Designs. CEELO FastFacts

ERIC Educational Resources Information Center

Schilder, D.

2013-01-01

In this "Fast Facts," a state has received Race to the Top Early Learning Challenge funds and is seeking information to inform the design of the Quality Rating and Improvement System (QRIS) validation study. The Center on Enhancing Early Learning Outcomes (CEELO) responds that according to Resnick (2012), validation of a QRIS is an…

"Who's Giving Us the Answers?" Interpreters and the Validation of Prior Foreign Learning

ERIC Educational Resources Information Center

Diedrich, Andreas

2013-01-01

This paper critically discusses the role of the interpreter in the validation of the prior learning of recent immigrants arriving in Sweden by drawing on a perspective from the sociology of translation. The recent immigrants' difficulties with speaking the local language is usually described as the main problem when it comes to validating their…

Box- or Virtual-Reality Trainer: Which Tool Results in Better Transfer of Laparoscopic Basic Skills?-A Prospective Randomized Trial.

PubMed

Brinkmann, Christian; Fritz, Mathias; Pankratius, Ulrich; Bahde, Ralf; Neumann, Philipp; Schlueter, Steffen; Senninger, Norbert; Rijcken, Emile

Simulation training improves laparoscopic performance. Laparoscopic basic skills can be learned in simulators as box- or virtual-reality (VR) trainers. However, there is no clear recommendation for either box or VR trainers as the most appropriate tool for the transfer of acquired laparoscopic basic skills into a surgical procedure. Both training tools were compared, using validated and well-established curricula in the acquirement of basic skills, in a prospective randomized trial in a 5-day structured laparoscopic training course. Participants completed either a box- or VR-trainer curriculum and then applied the learned skills performing an ex situ laparoscopic cholecystectomy on a pig liver. The performance was recorded on video and evaluated offline by 4 blinded observers using the Global Operative Assessment of Laparoscopic Skills (GOALS) score. Learning curves of the various exercises included in the training course were compared and the improvement in each exercise was analyzed. Surgical Skills Lab of the Department of General and Visceral Surgery, University Hospital Muenster. Surgical novices without prior surgical experience (medical students, n = 36). Posttraining evaluation showed significant improvement compared with baseline in both groups, indicating acquisition of laparoscopic basic skills. Learning curves showed almost the same progression with no significant differences. In simulated laparoscopic cholecystectomy, total GOALS score was significantly higher for the box-trained group than the VR-trained group (box: 15.31 ± 3.61 vs. VR: 12.92 ± 3.06; p = 0.039; Hedge׳s g* = 0.699), indicating higher technical skill levels. Despite both systems having advantages and disadvantages, they can both be used for simulation training for laparoscopic skills. In the setting with 2 structured, validated and almost identical curricula, the box-trained group appears to be superior in the better transfer of basic skills into an experimental but structured surgical procedure. Copyright © 2017 Association of Program Directors in Surgery. Published by Elsevier Inc. All rights reserved.

Integration of classroom science performance assessment tasks by participants of the Wisconsin Performance Assessment Development Project (WPADP)

NASA Astrophysics Data System (ADS)

Tonnis, Dorothy Ann

The goals of this interpretive study were to examine selected Wisconsin science teachers' perceptions of teaching and learning science, to describe the scope of classroom performance assessment practices, and to gain an understanding of teachers' personal and professional experiences that influenced their belief systems of teaching, learning and assessment. The study was designed to answer the research questions: (1) How does the integration of performance assessment relate to the teachers' views of teaching and learning? (2) How are the selected teachers integrating performance assessment in their teaching? (3) What past personal and professional experiences have influenced teachers' attitudes and beliefs related to their classroom performance assessment practices? Purposeful sampling was used to select seven Wisconsin elementary, middle and high school science teachers who participated in the WPADP initiative from 1993-1995. Data collection methods included a Teaching Practices Inventory (TPI), semi-structured interviews, teacher developed portfolios, portfolio conferences, and classroom observations. Four themes and multiple categories emerged through data analysis to answer the research questions and to describe the results. Several conclusions were drawn from this research. First, science teachers who appeared to effectively integrate performance assessment, demonstrated transformational thinking in their attitudes and beliefs about teaching and learning science. In addition, these teachers viewed assessment and instructional practices as interdependent. Third, transformational teachers generally used well defined criteria to judge student work and made it public to the students. Transformational teachers provided students with real-world performance assessment tasks that were also learning events. Furthermore, student task responses informed the transformational teachers about effectiveness of instruction, students' complex thinking skills, quality of assessment instruments, students' creativity, and students' self-assessment skills. Finally, transformational teachers maintained integration of performance assessment practices through sustaining teacher support networks, engaging in professional development programs, and reflecting upon past personal and professional experiences related to teaching, learning and assessment. Salient conflicts overcome or minimized by transformational teachers include the conflict between assessment scoring and grading issues, validity and reliability concerns about the performance assessment tasks used, and the difficulty for teachers to consistently provide public criteria to students before task administration.

Elaboration Preferences and Differences in Learning Proficiency.

ERIC Educational Resources Information Center

Rohwer, William D., Jr.; Levin, Joel R.

The major emphasis of this study is on the comparative validities of paired-associate learning tests and IQ tests in predicting reading achievement. The study engages in a brief review of earlier research in order to examine the validity of two assumptions--that the construction and/or the use of a tactic that simplifies a learning task is one of…

Teachers' Cloud-Based Learning Designs: The Development of a Guiding Rubric Using the TPACK Framework

ERIC Educational Resources Information Center

Al-Harthi, Aisha Salim Ali; Campbell, Chris; Karimi, Arafeh

2018-01-01

This study aimed to develop, validate, and trial a rubric for evaluating the cloud-based learning designs (CBLD) that were developed by teachers using virtual learning environments. The rubric was developed using the technological pedagogical content knowledge (TPACK) framework, with rubric development including content and expert validation of…

Developing Instruments Concerning Scientific Epistemic Beliefs and Goal Orientations in Learning Science: A Validation Study

ERIC Educational Resources Information Center

Lin, Tzung-Jin; Tsai, Chin-Chung

2017-01-01

The purpose of this study was to develop and validate two survey instruments to evaluate high school students' scientific epistemic beliefs and goal orientations in learning science. The initial relationships between the sampled students' scientific epistemic beliefs and goal orientations in learning science were also investigated. A final valid…

Validity of Assessment and Recognition of Non-Formal and Informal Learning Achievements in Higher Education

ERIC Educational Resources Information Center

Kaminskiene, Lina; Stasiunaitiene, Egle

2013-01-01

The article identifies the validity of assessment of non-formal and informal learning achievements (NILA) as one of the key factors for encouraging further development of the process of assessing and recognising non-formal and informal learning achievements in higher education. The authors analyse why the recognition of non-formal and informal…

Measuring Social Relations in New Classroom Spaces: Development and Validation of the Social Context and Learning Environments (SCALE) Survey

ERIC Educational Resources Information Center

Walker, J. D.; Baepler, Paul

2017-01-01

This study addresses the need for reliable and valid information concerning how innovative classrooms on college and university campuses affect teaching and learning. The Social Context and Learning Environments (SCALE) survey was developed though a three-stage process involving approximately 1300 college students. Exploratory and confirmatory…

A Study of Developing an Attitude Scale towards Authentic Learning Environments and Evaluation

ERIC Educational Resources Information Center

Çetinkaya, Murat

2018-01-01

The aim of the research is to improve a valid and reliable attributing scale which identifies authentic learning environments and evaluation attributes of the science teacher candidates. The study has been designed on the base of validity and reliability of the scale developed to evaluate the authentic learning environments. The research group is…

Development and Validation of the Learning Progression-Based Assessment of Modern Genetics in a High School Context

ERIC Educational Resources Information Center

Todd, Amber; Romine, William L.; Cook Whitt, Katahdin

2017-01-01

We describe the development, validation, and use of the "Learning Progression-Based Assessment of Modern Genetics" (LPA-MG) in a high school biology context. Items were constructed based on a current learning progression framework for genetics (Shea & Duncan, 2013; Todd & Kenyon, 2015). The 34-item instrument, which was tied to…

Development and Validation of a New Measure of Teacher Perceptions of Science and Mathematics Learning Environments

ERIC Educational Resources Information Center

Ellett, Chad D.; Monsaas, Judy

2011-01-01

This article describes the development and validation of the Inventory of Teaching and Learning (ITAL) as a new measure of teacher perceptions of science and mathematics learning environments. The ITAL was initially developed and administered in 2004 and has subsequently been revised annually. The ITAL is administered using a confidential…

The effects of competition on achievement motivation in Chinese classrooms.

PubMed

Lam, Shui-fong; Yim, Pui-shan; Law, Josephine S F; Cheung, Rebecca W Y

2004-06-01

Laboratory studies have consistently found that competition induces performance goals and affects learning motivation. However, the ecological validity of these results is yet to be established. There is a need for investigation of whether the results hold in both the classroom context and non-Western culture. The study investigated the effects of competition on learning motivation among Chinese students in an authentic classroom setting. The participants were 52 students of grade 7 from two Hong Kong secondary schools. They were randomly assigned to either competitive or non-competitive conditions in a 2-hour Chinese typewriting course. Students in the competitive condition performed better in easy tasks than their counterparts in the non-competitive condition. However, they were more performance-oriented and more likely to sacrifice learning opportunities for better performance. They were also prone to have worse self-evaluation after failure. Although there were no statistically significant differences between the two conditions in task enjoyment and achievement attribution, the direction of the differences was consistently unfavourable to students in the competitive condition. The findings were consistent with the predictions of goal theory. Competitiveness induces performance goals and worse self-evaluation after failure among Chinese students in a classroom setting, as was found with Western students in a laboratory setting.

Machine Learning methods for Quantitative Radiomic Biomarkers.

PubMed

Parmar, Chintan; Grossmann, Patrick; Bussink, Johan; Lambin, Philippe; Aerts, Hugo J W L

2015-08-17

Radiomics extracts and mines large number of medical imaging features quantifying tumor phenotypic characteristics. Highly accurate and reliable machine-learning approaches can drive the success of radiomic applications in clinical care. In this radiomic study, fourteen feature selection methods and twelve classification methods were examined in terms of their performance and stability for predicting overall survival. A total of 440 radiomic features were extracted from pre-treatment computed tomography (CT) images of 464 lung cancer patients. To ensure the unbiased evaluation of different machine-learning methods, publicly available implementations along with reported parameter configurations were used. Furthermore, we used two independent radiomic cohorts for training (n = 310 patients) and validation (n = 154 patients). We identified that Wilcoxon test based feature selection method WLCX (stability = 0.84 ± 0.05, AUC = 0.65 ± 0.02) and a classification method random forest RF (RSD = 3.52%, AUC = 0.66 ± 0.03) had highest prognostic performance with high stability against data perturbation. Our variability analysis indicated that the choice of classification method is the most dominant source of performance variation (34.21% of total variance). Identification of optimal machine-learning methods for radiomic applications is a crucial step towards stable and clinically relevant radiomic biomarkers, providing a non-invasive way of quantifying and monitoring tumor-phenotypic characteristics in clinical practice.

Integrated feature extraction and selection for neuroimage classification

NASA Astrophysics Data System (ADS)

Fan, Yong; Shen, Dinggang

2009-02-01

Feature extraction and selection are of great importance in neuroimage classification for identifying informative features and reducing feature dimensionality, which are generally implemented as two separate steps. This paper presents an integrated feature extraction and selection algorithm with two iterative steps: constrained subspace learning based feature extraction and support vector machine (SVM) based feature selection. The subspace learning based feature extraction focuses on the brain regions with higher possibility of being affected by the disease under study, while the possibility of brain regions being affected by disease is estimated by the SVM based feature selection, in conjunction with SVM classification. This algorithm can not only take into account the inter-correlation among different brain regions, but also overcome the limitation of traditional subspace learning based feature extraction methods. To achieve robust performance and optimal selection of parameters involved in feature extraction, selection, and classification, a bootstrapping strategy is used to generate multiple versions of training and testing sets for parameter optimization, according to the classification performance measured by the area under the ROC (receiver operating characteristic) curve. The integrated feature extraction and selection method is applied to a structural MR image based Alzheimer's disease (AD) study with 98 non-demented and 100 demented subjects. Cross-validation results indicate that the proposed algorithm can improve performance of the traditional subspace learning based classification.

Automatic Estimation of Volumetric Breast Density Using Artificial Neural Network-Based Calibration of Full-Field Digital Mammography: Feasibility on Japanese Women With and Without Breast Cancer.

PubMed

Wang, Jeff; Kato, Fumi; Yamashita, Hiroko; Baba, Motoi; Cui, Yi; Li, Ruijiang; Oyama-Manabe, Noriko; Shirato, Hiroki

2017-04-01

Breast cancer is the most common invasive cancer among women and its incidence is increasing. Risk assessment is valuable and recent methods are incorporating novel biomarkers such as mammographic density. Artificial neural networks (ANN) are adaptive algorithms capable of performing pattern-to-pattern learning and are well suited for medical applications. They are potentially useful for calibrating full-field digital mammography (FFDM) for quantitative analysis. This study uses ANN modeling to estimate volumetric breast density (VBD) from FFDM on Japanese women with and without breast cancer. ANN calibration of VBD was performed using phantom data for one FFDM system. Mammograms of 46 Japanese women diagnosed with invasive carcinoma and 53 with negative findings were analyzed using ANN models learned. ANN-estimated VBD was validated against phantom data, compared intra-patient, with qualitative composition scoring, with MRI VBD, and inter-patient with classical risk factors of breast cancer as well as cancer status. Phantom validations reached an R 2 of 0.993. Intra-patient validations ranged from R 2 of 0.789 with VBD to 0.908 with breast volume. ANN VBD agreed well with BI-RADS scoring and MRI VBD with R 2 ranging from 0.665 with VBD to 0.852 with breast volume. VBD was significantly higher in women with cancer. Associations with age, BMI, menopause, and cancer status previously reported were also confirmed. ANN modeling appears to produce reasonable measures of mammographic density validated with phantoms, with existing measures of breast density, and with classical biomarkers of breast cancer. FFDM VBD is significantly higher in Japanese women with cancer.

Development and validation of the Simulation Learning Effectiveness Inventory.

PubMed

Chen, Shiah-Lian; Huang, Tsai-Wei; Liao, I-Chen; Liu, Chienchi

2015-10-01

To develop and psychometrically test the Simulation Learning Effectiveness Inventory. High-fidelity simulation helps students develop clinical skills and competencies. Yet, reliable instruments measuring learning outcomes are scant. A descriptive cross-sectional survey was used to validate psychometric properties of the instrument measuring students' perception of stimulation learning effectiveness. A purposive sample of 505 nursing students who had taken simulation courses was recruited from a department of nursing of a university in central Taiwan from January 2010-June 2010. The study was conducted in two phases. In Phase I, question items were developed based on the literature review and the preliminary psychometric properties of the inventory were evaluated using exploratory factor analysis. Phase II was conducted to evaluate the reliability and validity of the finalized inventory using confirmatory factor analysis. The results of exploratory and confirmatory factor analyses revealed the instrument was composed of seven factors, named course arrangement, equipment resource, debriefing, clinical ability, problem-solving, confidence and collaboration. A further second-order analysis showed comparable fits between a three second-order factor (preparation, process and outcome) and the seven first-order factor models. Internal consistency was supported by adequate Cronbach's alphas and composite reliability. Convergent and discriminant validities were also supported by confirmatory factor analysis. The study provides evidence that the Simulation Learning Effectiveness Inventory is reliable and valid for measuring student perception of learning effectiveness. The instrument is helpful in building the evidence-based knowledge of the effect of simulation teaching on students' learning outcomes. © 2015 John Wiley & Sons Ltd.

FMRQ-A Multiagent Reinforcement Learning Algorithm for Fully Cooperative Tasks.

PubMed

Zhang, Zhen; Zhao, Dongbin; Gao, Junwei; Wang, Dongqing; Dai, Yujie

2017-06-01

In this paper, we propose a multiagent reinforcement learning algorithm dealing with fully cooperative tasks. The algorithm is called frequency of the maximum reward Q-learning (FMRQ). FMRQ aims to achieve one of the optimal Nash equilibria so as to optimize the performance index in multiagent systems. The frequency of obtaining the highest global immediate reward instead of immediate reward is used as the reinforcement signal. With FMRQ each agent does not need the observation of the other agents' actions and only shares its state and reward at each step. We validate FMRQ through case studies of repeated games: four cases of two-player two-action and one case of three-player two-action. It is demonstrated that FMRQ can converge to one of the optimal Nash equilibria in these cases. Moreover, comparison experiments on tasks with multiple states and finite steps are conducted. One is box-pushing and the other one is distributed sensor network problem. Experimental results show that the proposed algorithm outperforms others with higher performance.

Information based universal feature extraction

NASA Astrophysics Data System (ADS)

Amiri, Mohammad; Brause, Rüdiger

2015-02-01

In many real world image based pattern recognition tasks, the extraction and usage of task-relevant features are the most crucial part of the diagnosis. In the standard approach, they mostly remain task-specific, although humans who perform such a task always use the same image features, trained in early childhood. It seems that universal feature sets exist, but they are not yet systematically found. In our contribution, we tried to find those universal image feature sets that are valuable for most image related tasks. In our approach, we trained a neural network by natural and non-natural images of objects and background, using a Shannon information-based algorithm and learning constraints. The goal was to extract those features that give the most valuable information for classification of visual objects hand-written digits. This will give a good start and performance increase for all other image learning tasks, implementing a transfer learning approach. As result, in our case we found that we could indeed extract features which are valid in all three kinds of tasks.

Using Student-Produced Video to Validate Head-to-Toe Assessment Performance.

PubMed

Purpora, Christina; Prion, Susan

2018-03-01

This study explored third-semester baccalaureate nursing students' perceptions of the value of using student-produced video as an approach for learning head-to-toe assessment, an essential clinical nursing skill taught in the classroom. A cognitive apprenticeship model guided the study. The researchers developed a 34-item survey. A convenience sample of 72 students enrolled in an applied assessment and nursing fundamentals course at a university in the western United States provided the data. Most students reported a videotaping process that worked, supportive faculty, valuable faculty review of their work, confidence, a sense of performance independence, the ability to identify normal assessment findings, and few barriers to learning. The results suggested that a student-produced video approach to learning head-to-toe assessment was effective. Further, the study demonstrated how to leverage available instructional technology to provide meaningful, personalized instruction and feedback to students about an essential nursing skill. [J Nurs Educ. 2018;57(3):154-158.]. Copyright 2018, SLACK Incorporated.

The use of control groups in artificial grammar learning.

PubMed

Reber, Rolf; Perruchet, Pierre

2003-01-01

Experimenters assume that participants of an experimental group have learned an artificial grammar if they classify test items with significantly higher accuracy than does a control group without training. The validity of such a comparison, however, depends on an additivity assumption: Learning is superimposed on the action of non-specific variables-for example, repetitions of letters, which modulate the performance of the experimental group and the control group to the same extent. In two experiments we were able to show that this additivity assumption does not hold. Grammaticality classifications in control groups without training (Experiments 1 and 2) depended on non-specific features. There were no such biases in the experimental groups. Control groups with training on randomized strings (Experiment 2) showed fewer biases than did control groups without training. Furthermore, we reanalysed published research and demonstrated that earlier experiments using control groups without training had produced similar biases in control group performances, bolstering the finding that using control groups without training is methodologically unsound.

Null tDCS Effects in a Sustained Attention Task: The Modulating Role of Learning

PubMed Central

Jacoby, Noa; Lavidor, Michal

2018-01-01

The purpose of this study was to investigate sustained attention through modulation of the fronto-cerebral network with transcranial direct current stimulation (tDCS) in adults with attention-deficit/hyperactivity disorder (ADHD) and control participants. Thirty-seven participants (21 with ADHD) underwent three separate sessions (baseline, active tDCS, and sham) and performed the MOXO Continuous Performance Test (CPT). We applied double anodal stimulation of 1.8 mA tDCS for 20 min over the left and right dorsolateral prefrontal cortex (DLPFC), with the cathode over the cerebellum. Baseline session revealed significant differences between ADHD and control participants in the MOXO-CPT attention and hyperactivity scores, validating the MOXO as a diagnostic tool. However, there were no tDCS effects in most MOXO-CPT measures, except hyperactivity, due to a significant learning effect. We conclude that learning and repetition effects in cognitive tasks need to be considered when designing within-subjects tDCS experiments, as there are natural improvements between sessions that conceal potential stimulation effects. PMID:29681876

Null tDCS Effects in a Sustained Attention Task: The Modulating Role of Learning.

PubMed

Jacoby, Noa; Lavidor, Michal

2018-01-01

The purpose of this study was to investigate sustained attention through modulation of the fronto-cerebral network with transcranial direct current stimulation (tDCS) in adults with attention-deficit/hyperactivity disorder (ADHD) and control participants. Thirty-seven participants (21 with ADHD) underwent three separate sessions (baseline, active tDCS, and sham) and performed the MOXO Continuous Performance Test (CPT). We applied double anodal stimulation of 1.8 mA tDCS for 20 min over the left and right dorsolateral prefrontal cortex (DLPFC), with the cathode over the cerebellum. Baseline session revealed significant differences between ADHD and control participants in the MOXO-CPT attention and hyperactivity scores, validating the MOXO as a diagnostic tool. However, there were no tDCS effects in most MOXO-CPT measures, except hyperactivity, due to a significant learning effect. We conclude that learning and repetition effects in cognitive tasks need to be considered when designing within-subjects tDCS experiments, as there are natural improvements between sessions that conceal potential stimulation effects.

Confused or not Confused?: Disentangling Brain Activity from EEG Data Using Bidirectional LSTM Recurrent Neural Networks.

PubMed

Ni, Zhaoheng; Yuksel, Ahmet Cem; Ni, Xiuyan; Mandel, Michael I; Xie, Lei

2017-08-01

Brain fog, also known as confusion, is one of the main reasons for low performance in the learning process or any kind of daily task that involves and requires thinking. Detecting confusion in a human's mind in real time is a challenging and important task that can be applied to online education, driver fatigue detection and so on. In this paper, we apply Bidirectional LSTM Recurrent Neural Networks to classify students' confusion in watching online course videos from EEG data. The results show that Bidirectional LSTM model achieves the state-of-the-art performance compared with other machine learning approaches, and shows strong robustness as evaluated by cross-validation. We can predict whether or not a student is confused in the accuracy of 73.3%. Furthermore, we find the most important feature to detecting the brain confusion is the gamma 1 wave of EEG signal. Our results suggest that machine learning is a potentially powerful tool to model and understand brain activity.

Low-Quality Structural and Interaction Data Improves Binding Affinity Prediction via Random Forest.

PubMed

Li, Hongjian; Leung, Kwong-Sak; Wong, Man-Hon; Ballester, Pedro J

2015-06-12

Docking scoring functions can be used to predict the strength of protein-ligand binding. It is widely believed that training a scoring function with low-quality data is detrimental for its predictive performance. Nevertheless, there is a surprising lack of systematic validation experiments in support of this hypothesis. In this study, we investigated to which extent training a scoring function with data containing low-quality structural and binding data is detrimental for predictive performance. We actually found that low-quality data is not only non-detrimental, but beneficial for the predictive performance of machine-learning scoring functions, though the improvement is less important than that coming from high-quality data. Furthermore, we observed that classical scoring functions are not able to effectively exploit data beyond an early threshold, regardless of its quality. This demonstrates that exploiting a larger data volume is more important for the performance of machine-learning scoring functions than restricting to a smaller set of higher data quality.

Validation of MODIS Aerosol Observations Over the Netherlands With GLOBE Student Observations: Lessons Learned

NASA Astrophysics Data System (ADS)

de Vroom, J.; Boersma, K. F.

2006-12-01

We have established a network of secondary schools in the Netherlands (www.knmi.nl/globe) with students routinely measuring aerosol optical thickness (AOT) at two wavelengths with hand-held Sun photometers. Students have performed more than 400 measurements between January 2002 and October 2005 over more than 12 locations within the Netherlands as a contribution to Global Learning and Observations to Benefit the Environment (GLOBE). Results from a theoretical error analysis indicate that GLOBE measurements achieve a precision better than 0.02 AOT for both channels. Comparisons with professional instruments generally give high correlations and low scatter and bias. From these tests, we conclude that student data is scientifically valid and may be used to validate MODIS AOT retrievals over the Netherlands. A manuscript on this study has been accepted by AGU's Journal of Geophysical Research. In this presentation, we will address the pro's and con's of setting up a student-based network. Issues such as effective training, the importance of regular school visits, and the need for an intermediate partner will be discussed. As stated in the outlook of our manuscript: routine has it that involved parties are often short of time, and that incidental school visits are not only hard to organize, but also often abandoned. This is regretful, as some schools, after a promising start, fail to continue their measurement record. In summary, school visits are essential to maintaining and prospering a project as described in this study, and should be performed as often as possible.

Predicting radiotherapy outcomes using statistical learning techniques

NASA Astrophysics Data System (ADS)

El Naqa, Issam; Bradley, Jeffrey D.; Lindsay, Patricia E.; Hope, Andrew J.; Deasy, Joseph O.

2009-09-01

Radiotherapy outcomes are determined by complex interactions between treatment, anatomical and patient-related variables. A common obstacle to building maximally predictive outcome models for clinical practice is the failure to capture potential complexity of heterogeneous variable interactions and applicability beyond institutional data. We describe a statistical learning methodology that can automatically screen for nonlinear relations among prognostic variables and generalize to unseen data before. In this work, several types of linear and nonlinear kernels to generate interaction terms and approximate the treatment-response function are evaluated. Examples of institutional datasets of esophagitis, pneumonitis and xerostomia endpoints were used. Furthermore, an independent RTOG dataset was used for 'generalizabilty' validation. We formulated the discrimination between risk groups as a supervised learning problem. The distribution of patient groups was initially analyzed using principle components analysis (PCA) to uncover potential nonlinear behavior. The performance of the different methods was evaluated using bivariate correlations and actuarial analysis. Over-fitting was controlled via cross-validation resampling. Our results suggest that a modified support vector machine (SVM) kernel method provided superior performance on leave-one-out testing compared to logistic regression and neural networks in cases where the data exhibited nonlinear behavior on PCA. For instance, in prediction of esophagitis and pneumonitis endpoints, which exhibited nonlinear behavior on PCA, the method provided 21% and 60% improvements, respectively. Furthermore, evaluation on the independent pneumonitis RTOG dataset demonstrated good generalizabilty beyond institutional data in contrast with other models. This indicates that the prediction of treatment response can be improved by utilizing nonlinear kernel methods for discovering important nonlinear interactions among model variables. These models have the capacity to predict on unseen data. Part of this work was first presented at the Seventh International Conference on Machine Learning and Applications, San Diego, CA, USA, 11-13 December 2008.

[An instrument in Spanish to evaluate the performance of clinical teachers by students].

PubMed

Bitran, Marcela; Mena, Beltrán; Riquelme, Arnoldo; Padilla, Oslando; Sánchez, Ignacio; Moreno, Rodrigo

2010-06-01

The modernization of clinical teaching has called for the creation of faculty development programs, and the design of suitable instruments to evaluate clinical teachers' performance. To report the development and validation of an instrument in Spanish designed to measure the students' perceptions of their clinical teachers' performance and to provide them with feedback to improve their teaching practices. In a process that included the active participation of authorities, professors in charge of courses and internships, clinical teachers, students and medical education experts, we developed a 30-item questionnaire called MEDUC30 to evaluate the performance of clinical teachers by their students. The internal validity was assessed by factor analysis of 5214 evaluations of 265 teachers, gathered from 2004 to 2007. The reliability was measured with the Cronbach's alpha coefficient and the generalizability coefficient (g). MEDUC30 had good content and construct validity. Its internal structure was compatible with four factors: patient-centered teaching, teaching skills, assessment skills and learning climate, and it proved to be consistent with the structure anticipated by the theory. The scores were highly reliable (Cronbach's alpha: 0.97); five evaluations per teacher were sufficient to reach a reliability coefficient (g) of 0.8. MEDUC30 is a valid, reliable and useful instrument to evaluate the performance of clinical teachers. To our knowledge, this is the first instrument in Spanish for which solid validity and reliability evidences have been reported. We hope that MEDUC30 will be used to improve medical education in Spanish-speaking medical schools, providing teachers a specific feedback upon which to improve their pedagogical practice, and authorities with valuable information for the assessment of their faculty.

Job Resources, Physician Work Engagement, and Patient Care Experience in an Academic Medical Setting.

PubMed

Scheepers, Renée A; Lases, Lenny S S; Arah, Onyebuchi A; Heineman, Maas Jan; Lombarts, Kiki M J M H

2017-10-01

Physician work engagement is associated with better work performance and fewer medical errors; however, whether work-engaged physicians perform better from the patient perspective is unknown. Although availability of job resources (autonomy, colleague support, participation in decision making, opportunities for learning) bolster work engagement, this relationship is understudied among physicians. This study investigated associations of physician work engagement with patient care experience and job resources in an academic setting. The authors collected patient care experience evaluations, using nine validated items from the Dutch Consumer Quality index in two academic hospitals (April 2014 to April 2015). Physicians reported job resources and work engagement using, respectively, the validated Questionnaire on Experience and Evaluation of Work and the Utrecht Work Engagement Scale. The authors conducted multivariate adjusted mixed linear model and linear regression analyses. Of the 9,802 eligible patients and 238 eligible physicians, respectively, 4,573 (47%) and 185 (78%) participated. Physician work engagement was not associated with patient care experience (B = 0.01; 95% confidence interval [CI] = -0.02 to 0.03; P = .669). However, learning opportunities (B = 0.28; 95% CI = 0.05 to 0.52; P = .019) and autonomy (B = 0.31; 95% CI = 0.10 to 0.51; P = .004) were positively associated with work engagement. Higher physician work engagement did not translate into better patient care experience. Patient experience may benefit from physicians who deliver stable quality under varying levels of work engagement. From the physicians' perspective, autonomy and learning opportunities could safeguard their work engagement.

Unique and shared validity of the "Wechsler logical memory test", the "California verbal learning test", and the "verbal learning and memory test" in patients with epilepsy.

PubMed

Helmstaedter, Christoph; Wietzke, Jennifer; Lutz, Martin T

2009-12-01

This study was set-up to evaluate the construct validity of three verbal memory tests in epilepsy patients. Sixty-one consecutively evaluated patients with temporal lobe epilepsy (TLE) or extra-temporal epilepsy (E-TLE) underwent testing with the verbal learning and memory test (VLMT, the German equivalent of the Rey auditory verbal learning test, RAVLT); the California verbal learning test (CVLT); the logical memory and digit span subtests of the Wechsler memory scale, revised (WMS-R); and testing of intelligence, attention, speech and executive functions. Factor analysis of the memory tests resulted in test-specific rather than test over-spanning factors. Parameters of the CVLT and WMS-R, and to a much lesser degree of the VLMT, were highly correlated with attention, language function and vocabulary. Delayed recall measures of logical memory and the VLMT differentiated TLE from E-TLE. Learning and memory scores off all three tests differentiated mesial temporal sclerosis from other pathologies. A lateralization of the epilepsy was possible only for a subsample of 15 patients with mesial TLE. Although the three tests provide overlapping indicators for a temporal lobe epilepsy or a mesial pathology, they can hardly be taken in exchange. The tests have different demands on semantic processing and memory organization, and they appear differentially sensitive to performance in non-memory domains. The tests capability to lateralize appears to be poor. The findings encourage the further discussion of the dependency of memory outcomes on test selection.

Unaltered radial maze performance and brain acetylcholine of the endothelial nitric oxide synthase knockout mouse.

PubMed

Dere, E; Frisch, C; De Souza Silva, M A; Gödecke, A; Schrader, J; Huston, J P

2001-01-01

Proceeding from previous findings of a beneficial effect of endothelial nitric oxide synthase (eNOS) gene inactivation on negatively reinforced water maze performance, we asked whether this improvement in place learning capacities also holds for a positively reinforced radial maze task. Unlike its beneficial effects on the water maze task, eNOS gene inactivation did not facilitate radial maze performance. The acquisition performance over the days of place learning did not differ between eNOS knockout (eNOS-/-) and wild-type mice (eNOS+/+). eNOS-/- mice displayed a slight and eNOS+/+ mice a more severe working memory deficit in the place learning version of the radial maze compared to the genetic background C57BL/6 strain. Possible differential effects of eNOS inactivation, related to differences in reinforcement contingencies between the Morris water maze and radial maze tasks, behavioral strategy requirements, or to different emotional and physiological concomitants inherent in the two tasks are discussed. These task-unique characteristics might be differentially affected by the reported anxiogenic and hypertensional effects of eNOS gene inactivation. Post-mortem determination of acetylcholine concentrations in diverse brain structures revealed that acetylcholine and choline contents were not different between eNOS-/- and eNOS+/+ mice, but were increased in eNOS+/+ mice compared to C57BL/6 mice in the frontal cortex. Our findings demonstrate that phenotyping of learning and memory capacities should not rely on one learning task only, but should include tasks employing both negative and positive reinforcement contingencies in order to allow valid statements regarding differences in learning capacities between rodent strains.

Development and evaluation of a simulation-based continuing medical education course: beyond lectures and credit hours.

PubMed

Pugh, Carla M; Arafat, Fahd O; Kwan, Calvin; Cohen, Elaine R; Kurashima, Yo; Vassiliou, Melina C; Fried, Gerald M

2015-10-01

The aim of our study was to modify our previously developed laparoscopic ventral hernia (LVH) simulator to increase difficulty and then reassess validity and feasibility for using the simulator in a newly developed simulation-based continuing medical education course. Participants (N = 30) were practicing surgeons who signed up for a hands-on postgraduate laparoscopic hernia course. An LVH simulator, with prior validity evidence, was modified for the course to increase difficulty. Participants completed 1 of the 3 variations in hernia anatomy: incarcerated omentum, incarcerated bowel, and diffuse adhesions. During the procedure, course faculty and peer observers rated surgeon performance using Global Operative Assessment of Laparoscopic Skills-Incisional Hernia and Global Operative Assessment of Laparoscopic Skills rating scales with prior validity evidence. Rating scale reliability was reassessed for internal consistency. Peer and faculty raters' scores were compared. In addition, quality and completeness of the hernia repairs were rated. Internal consistency on the general skills performance (peer α = .96, faculty α = .94) and procedure-specific performance (peer α = .91, faculty α = .88) scores were high. Peers were more lenient than faculty raters on all LVH items in both the procedure-specific skills and general skills ratings. Overall, participants scored poorly on the quality and completeness of their hernia repairs (mean = 3.90/16, standard deviation = 2.72), suggesting a mismatch between course attendees and hernia difficulty and identifying a learning need. Simulation-based continuing medical education courses provide hands-on experiences that can positively affect clinical practice. Although our data appear to show a significant mismatch between clinical skill and simulator difficulty, these findings also underscore significant learning needs in the surgical community. Copyright © 2015 Elsevier Inc. All rights reserved.

A Virtual Reality Training Curriculum for Laparoscopic Colorectal Surgery.

PubMed

Beyer-Berjot, Laura; Berdah, Stéphane; Hashimoto, Daniel A; Darzi, Ara; Aggarwal, Rajesh

Training within a competency-based curriculum (CBC) outside the operating room enhances performance during real basic surgical procedures. This study aimed to design and validate a virtual reality CBC for an advanced laparoscopic procedure: sigmoid colectomy. This was a multicenter randomized study. Novice (surgeons who had performed <5 laparoscopic colorectal resections as primary operator), intermediate (between 10 and 20), and experienced surgeons (>50) were enrolled. Validity evidence for the metrics given by the virtual reality simulator, the LAP Mentor, was based on the second attempt of each task in between groups. The tasks assessed were 3 modules of a laparoscopic sigmoid colectomy (medial dissection [MD], lateral dissection [LD], and anastomosis) and a full procedure (FP). Novice surgeons were randomized to 1 of 2 groups to perform 8 further attempts of all 3 modules or FP, for learning curve analysis. Two academic tertiary care centers-division of surgery of St. Mary's campus, Imperial College Healthcare NHS Trust, London and Nord Hospital, Assistance Publique-Hôpitaux de Marseille, Aix-Marseille Université, Marseille, were involved. Novice surgeons were residents in digestive surgery at St. Mary's and Nord Hospitals. Intermediate and experienced surgeons were board-certified academic surgeons. A total of 20 novice surgeons, 7 intermediate surgeons, and 6 experienced surgeons were enrolled. Evidence for validity based on experience was identified in MD, LD, and FP for time (p = 0.005, p = 0.003, and p = 0.001, respectively), number of movements (p = 0.013, p = 0.005, and p = 0.001, respectively), and path length (p = 0.03, p = 0.017, and p = 0.001, respectively), and only for time (p = 0.03) and path length (p = 0.013) in the anastomosis module. Novice surgeons' performance significantly improved through repetition for time, movements, and path length in MD, LD, and FP. Experienced surgeons' benchmark criteria were defined for all construct metrics showing validity evidence. A CBC in laparoscopic colorectal surgery has been designed. Such training may reduce the learning curve during real colorectal resections in the operating room. Copyright © 2016 Association of Program Directors in Surgery. Published by Elsevier Inc. All rights reserved.

Development of an evidence-based training program for laparoscopic hysterectomy on a virtual reality simulator.

PubMed

Crochet, Patrice; Aggarwal, Rajesh; Knight, Sophie; Berdah, Stéphane; Boubli, Léon; Agostini, Aubert

2017-06-01

Substantial evidence in the scientific literature supports the use of simulation for surgical education. However, curricula lack for complex laparoscopic procedures in gynecology. The objective was to evaluate the validity of a program that reproduces key specific components of a laparoscopic hysterectomy (LH) procedure until colpotomy on a virtual reality (VR) simulator and to develop an evidence-based and stepwise training curriculum. This prospective cohort study was conducted in a Marseille teaching hospital. Forty participants were enrolled and were divided into experienced (senior surgeons who had performed more than 100 LH; n = 8), intermediate (surgical trainees who had performed 2-10 LH; n = 8) and inexperienced (n = 24) groups. Baselines were assessed on a validated basic task. Participants were tested for the LH procedure on a high-fidelity VR simulator. Validity evidence was proposed as the ability to differentiate between the three levels of experience. Inexperienced subjects performed ten repetitions for learning curve analysis. Proficiency measures were based on experienced surgeons' performances. Outcome measures were simulator-derived metrics and Objective Structured Assessment of Technical Skills (OSATS) scores. Quantitative analysis found significant inter-group differences between experienced intermediate and inexperienced groups for time (1369, 2385 and 3370 s; p < 0.001), number of movements (2033, 3195 and 4056; p = 0.001), path length (3390, 4526 and 5749 cm; p = 0.002), idle time (357, 654 and 747 s; p = 0.001), respect for tissue (24, 40 and 84; p = 0.01) and number of bladder injuries (0.13, 0 and 4.27; p < 0.001). Learning curves plateaued at the 2nd to 6th repetition. Further qualitative analysis found significant inter-group OSATS score differences at first repetition (22, 15 and 8, respectively; p < 0.001) and second repetition (25.5, 19.5 and 14; p < 0.001). The VR program for LH accrued validity evidence and allowed the development of a training curriculum using a structured scientific methodology.

Using statistical text classification to identify health information technology incidents

PubMed Central

Chai, Kevin E K; Anthony, Stephen; Coiera, Enrico; Magrabi, Farah

2013-01-01

Objective To examine the feasibility of using statistical text classification to automatically identify health information technology (HIT) incidents in the USA Food and Drug Administration (FDA) Manufacturer and User Facility Device Experience (MAUDE) database. Design We used a subset of 570 272 incidents including 1534 HIT incidents reported to MAUDE between 1 January 2008 and 1 July 2010. Text classifiers using regularized logistic regression were evaluated with both ‘balanced’ (50% HIT) and ‘stratified’ (0.297% HIT) datasets for training, validation, and testing. Dataset preparation, feature extraction, feature selection, cross-validation, classification, performance evaluation, and error analysis were performed iteratively to further improve the classifiers. Feature-selection techniques such as removing short words and stop words, stemming, lemmatization, and principal component analysis were examined. Measurements κ statistic, F1 score, precision and recall. Results Classification performance was similar on both the stratified (0.954 F1 score) and balanced (0.995 F1 score) datasets. Stemming was the most effective technique, reducing the feature set size to 79% while maintaining comparable performance. Training with balanced datasets improved recall (0.989) but reduced precision (0.165). Conclusions Statistical text classification appears to be a feasible method for identifying HIT reports within large databases of incidents. Automated identification should enable more HIT problems to be detected, analyzed, and addressed in a timely manner. Semi-supervised learning may be necessary when applying machine learning to big data analysis of patient safety incidents and requires further investigation. PMID:23666777

Correlation of HIV protease structure with Indinavir resistance: a data mining and neural networks approach

NASA Astrophysics Data System (ADS)

Draghici, Sorin; Cumberland, Lonnie T., Jr.; Kovari, Ladislau C.

2000-04-01

This paper presents some results of data mining HIV genotypic and structural data. Our aim is to try to relate structural features of HIV enzymes essential to its reproductive abilities to the drug resistance phenomenon. This paper concentrates on the HIV protease enzyme and Indinavir which is one of the FDA approved protease inhibitors. Our starting point was the current list of HIV mutations related to drug resistance. We used the fact that some molecular structures determined through high resolution X-ray crystallography were available for the protease-Indinavir complex. Starting with these structures and the known mutations, we modelled the mutant proteases and studied the pattern of atomic contacts between the protease and the drug. After suitable pre- processing, these patterns have been used as the input of our data mining process. We have used both supervised and unsupervised learning techniques with the aim of understanding the relationship between structural features at a molecular level and resistance to Indinavir. The supervised learning was aimed at predicting IC90 values for arbitrary mutants. The SOFM was aimed at identifying those structural features that are important for drug resistance and discovering a classifier based on such features. We have used validation and cross validation to test the generalization abilities of the learning paradigm we have designed. The straightforward supervised learning was able to learn very successfully but validation results are less than satisfactory. This is due to the insufficient number of patterns in the training set which in turn is due to the scarcity of the available data. The data mining using SOFM was very successful. We have managed to distinguish between resistant and non-resistant mutants using structural features. We have been able to divide all reported HIV mutants into several categories based on their 3- dimensional molecular structures and the pattern of contacts between the mutant protease and Indinavir. Our classifier shows reasonably good prediction performance being able to predict the drug resistance of previously unseen mutants with an accuracy of between 60% and 70%. We believe that this performance can be greatly improved once more data becomes available. The results presented here support the hypothesis that structural features of the molecular structure can be used in antiviral drug treatment selection and drug design.

In silico prediction of Tetrahymena pyriformis toxicity for diverse industrial chemicals with substructure pattern recognition and machine learning methods.

PubMed

Cheng, Feixiong; Shen, Jie; Yu, Yue; Li, Weihua; Liu, Guixia; Lee, Philip W; Tang, Yun

2011-03-01

There is an increasing need for the rapid safety assessment of chemicals by both industries and regulatory agencies throughout the world. In silico techniques are practical alternatives in the environmental hazard assessment. It is especially true to address the persistence, bioaccumulative and toxicity potentials of organic chemicals. Tetrahymena pyriformis toxicity is often used as a toxic endpoint. In this study, 1571 diverse unique chemicals were collected from the literature and composed of the largest diverse data set for T. pyriformis toxicity. Classification predictive models of T. pyriformis toxicity were developed by substructure pattern recognition and different machine learning methods, including support vector machine (SVM), C4.5 decision tree, k-nearest neighbors and random forest. The results of a 5-fold cross-validation showed that the SVM method performed better than other algorithms. The overall predictive accuracies of the SVM classification model with radial basis functions kernel was 92.2% for the 5-fold cross-validation and 92.6% for the external validation set, respectively. Furthermore, several representative substructure patterns for characterizing T. pyriformis toxicity were also identified via the information gain analysis methods. Copyright © 2010 Elsevier Ltd. All rights reserved.

A land use regression model for ambient ultrafine particles in Montreal, Canada: A comparison of linear regression and a machine learning approach.

PubMed

Weichenthal, Scott; Ryswyk, Keith Van; Goldstein, Alon; Bagg, Scott; Shekkarizfard, Maryam; Hatzopoulou, Marianne

2016-04-01

Existing evidence suggests that ambient ultrafine particles (UFPs) (<0.1µm) may contribute to acute cardiorespiratory morbidity. However, few studies have examined the long-term health effects of these pollutants owing in part to a need for exposure surfaces that can be applied in large population-based studies. To address this need, we developed a land use regression model for UFPs in Montreal, Canada using mobile monitoring data collected from 414 road segments during the summer and winter months between 2011 and 2012. Two different approaches were examined for model development including standard multivariable linear regression and a machine learning approach (kernel-based regularized least squares (KRLS)) that learns the functional form of covariate impacts on ambient UFP concentrations from the data. The final models included parameters for population density, ambient temperature and wind speed, land use parameters (park space and open space), length of local roads and rail, and estimated annual average NOx emissions from traffic. The final multivariable linear regression model explained 62% of the spatial variation in ambient UFP concentrations whereas the KRLS model explained 79% of the variance. The KRLS model performed slightly better than the linear regression model when evaluated using an external dataset (R(2)=0.58 vs. 0.55) or a cross-validation procedure (R(2)=0.67 vs. 0.60). In general, our findings suggest that the KRLS approach may offer modest improvements in predictive performance compared to standard multivariable linear regression models used to estimate spatial variations in ambient UFPs. However, differences in predictive performance were not statistically significant when evaluated using the cross-validation procedure. Crown Copyright © 2015. Published by Elsevier Inc. All rights reserved.

Design and validation of a computer-aided learning program to enhance students' ability to recognize lameness in the horse.

PubMed

Barstow, Amy; Pfau, Thilo; Bolt, David M; Smith, Roger K; Weller, Renate

2014-01-01

The ability to recognize lameness in the horse is an important skill for veterinary graduates; however, opportunities to develop this skill at the undergraduate level are limited. Computer-aided learning programs (CALs) have been successful in supplementing practical skills teaching. The aim of this study was to design and validate a CAL for the teaching of equine lameness recognition (CAL1). A control CAL was designed to simulate learning by experience (CAL2). Student volunteers were randomly assigned to either CAL and tested to establish their current ability to recognize lameness. Retesting occurred both immediately following exposure and 1 week later. At each test point, the number of correct responses for forelimb and hind limb cases was determined. Student confidence was assessed before and after CAL exposure, with previous opportunities to recognize lameness taken into account. Immediately following exposure, the number of correct responses was significantly higher for CAL1 than for CAL2, both overall and for forelimb cases but not for hind limb cases. After 1 week, the CAL1 group performed significantly better overall compared to the CAL2 group, with no significant difference between forelimb and hind limb cases. Student confidence and ability to recognize lameness were significantly improved following exposure to CAL1. When considered as one category, students in years 4 and 5 performed significantly better than year 3 students. Gender did not significantly affect performance. CAL1 could be used to supplement current lameness recognition opportunities. CAL1 is, however, limited in its ability to improve lameness recognition, especially in relation to hind limb lameness where it was unable to attain a significant difference from CAL2.

Age and education adjusted normative data and discriminative validity for Rey's Auditory Verbal Learning Test in the elderly Greek population.

PubMed

Messinis, Lambros; Nasios, Grigorios; Mougias, Antonios; Politis, Antonis; Zampakis, Petros; Tsiamaki, Eirini; Malefaki, Sonia; Gourzis, Phillipos; Papathanasopoulos, Panagiotis

2016-01-01

Rey's Auditory Verbal Learning Test (RAVLT) is a widely used neuropsychological test to assess episodic memory. In the present study we sought to establish normative and discriminative validity data for the RAVLT in the elderly population using previously adapted learning lists for the Greek adult population. We administered the test to 258 cognitively healthy elderly participants, aged 60-89 years, and two patient groups (192 with amnestic mild cognitive impairment, aMCI, and 65 with Alzheimer's disease, AD). From the statistical analyses, we found that age and education contributed significantly to most trials of the RAVLT, whereas the influence of gender was not significant. Younger elderly participants with higher education outperformed the older elderly with lower education levels. Moreover, both clinical groups performed significantly worse on most RAVLT trials and composite measures than matched cognitively healthy controls. Furthermore, the AD group performed more poorly than the aMCI group on most RAVLT variables. Receiver operating characteristic (ROC) analysis was used to examine the utility of the RAVLT trials to discriminate cognitively healthy controls from aMCI and AD patients. Area under the curve (AUC), an index of effect size, showed that most of the RAVLT measures (individual and composite) included in this study adequately differentiated between the performance of healthy elders and aMCI/AD patients. We also provide cutoff scores in discriminating cognitively healthy controls from aMCI and AD patients, based on the sensitivity and specificity of the prescribed scores. Moreover, we present age- and education-specific normative data for individual and composite scores for the Greek adapted RAVLT in elderly subjects aged between 60 and 89 years for use in clinical and research settings.

Using machine learning to produce near surface soil moisture estimates from deeper in situ records at U.S. Climate Reference Network (USCRN) locations: Analysis and applications to AMSR-E satellite validation

NASA Astrophysics Data System (ADS)

Coopersmith, Evan J.; Cosh, Michael H.; Bell, Jesse E.; Boyles, Ryan

2016-12-01

Surface soil moisture is a critical parameter for understanding the energy flux at the land atmosphere boundary. Weather modeling, climate prediction, and remote sensing validation are some of the applications for surface soil moisture information. The most common in situ measurement for these purposes are sensors that are installed at depths of approximately 5 cm. There are however, sensor technologies and network designs that do not provide an estimate at this depth. If soil moisture estimates at deeper depths could be extrapolated to the near surface, in situ networks providing estimates at other depths would see their values enhanced. Soil moisture sensors from the U.S. Climate Reference Network (USCRN) were used to generate models of 5 cm soil moisture, with 10 cm soil moisture measurements and antecedent precipitation as inputs, via machine learning techniques. Validation was conducted with the available, in situ, 5 cm resources. It was shown that a 5 cm estimate, which was extrapolated from a 10 cm sensor and antecedent local precipitation, produced a root-mean-squared-error (RMSE) of 0.0215 m3/m3. Next, these machine-learning-generated 5 cm estimates were also compared to AMSR-E estimates at these locations. These results were then compared with the performance of the actual in situ readings against the AMSR-E data. The machine learning estimates at 5 cm produced an RMSE of approximately 0.03 m3/m3 when an optimized gain and offset were applied. This is necessary considering the performance of AMSR-E in locations characterized by high vegetation water contents, which are present across North Carolina. Lastly, the application of this extrapolation technique is applied to the ECONet in North Carolina, which provides a 10 cm depth measurement as its shallowest soil moisture estimate. A raw RMSE of 0.028 m3/m3 was achieved, and with a linear gain and offset applied at each ECONet site, an RMSE of 0.013 m3/m3 was possible.

Validating the Use of Deep Learning Neural Networks for Correction of Large Hydrometric Datasets

NASA Astrophysics Data System (ADS)

Frazier, N.; Ogden, F. L.; Regina, J. A.; Cheng, Y.

2017-12-01

Collection and validation of Earth systems data can be time consuming and labor intensive. In particular, high resolution hydrometric data, including rainfall and streamflow measurements, are difficult to obtain due to a multitude of complicating factors. Measurement equipment is subject to clogs, environmental disturbances, and sensor drift. Manual intervention is typically required to identify, correct, and validate these data. Weirs can become clogged and the pressure transducer may float or drift over time. We typically employ a graphical tool called Time Series Editor to manually remove clogs and sensor drift from the data. However, this process is highly subjective and requires hydrological expertise. Two different people may produce two different data sets. To use this data for scientific discovery and model validation, a more consistent method is needed to processes this field data. Deep learning neural networks have proved to be excellent mechanisms for recognizing patterns in data. We explore the use of Recurrent Neural Networks (RNN) to capture the patterns in the data over time using various gating mechanisms (LSTM and GRU), network architectures, and hyper-parameters to build an automated data correction model. We also explore the required amount of manually corrected training data required to train the network for reasonable accuracy. The benefits of this approach are that the time to process a data set is significantly reduced, and the results are 100% reproducible after training is complete. Additionally, we train the RNN and calibrate a physically-based hydrological model against the same portion of data. Both the RNN and the model are applied to the remaining data using a split-sample methodology. Performance of the machine learning is evaluated for plausibility by comparing with the output of the hydrological model, and this analysis identifies potential periods where additional investigation is warranted.

Sampling algorithms for validation of supervised learning models for Ising-like systems

NASA Astrophysics Data System (ADS)

Portman, Nataliya; Tamblyn, Isaac

2017-12-01

In this paper, we build and explore supervised learning models of ferromagnetic system behavior, using Monte-Carlo sampling of the spin configuration space generated by the 2D Ising model. Given the enormous size of the space of all possible Ising model realizations, the question arises as to how to choose a reasonable number of samples that will form physically meaningful and non-intersecting training and testing datasets. Here, we propose a sampling technique called ;ID-MH; that uses the Metropolis-Hastings algorithm creating Markov process across energy levels within the predefined configuration subspace. We show that application of this method retains phase transitions in both training and testing datasets and serves the purpose of validation of a machine learning algorithm. For larger lattice dimensions, ID-MH is not feasible as it requires knowledge of the complete configuration space. As such, we develop a new ;block-ID; sampling strategy: it decomposes the given structure into square blocks with lattice dimension N ≤ 5 and uses ID-MH sampling of candidate blocks. Further comparison of the performance of commonly used machine learning methods such as random forests, decision trees, k nearest neighbors and artificial neural networks shows that the PCA-based Decision Tree regressor is the most accurate predictor of magnetizations of the Ising model. For energies, however, the accuracy of prediction is not satisfactory, highlighting the need to consider more algorithmically complex methods (e.g., deep learning).

Predicting ground contact events for a continuum of gait types: An application of targeted machine learning using principal component analysis.

PubMed

Osis, Sean T; Hettinga, Blayne A; Ferber, Reed

2016-05-01

An ongoing challenge in the application of gait analysis to clinical settings is the standardized detection of temporal events, with unobtrusive and cost-effective equipment, for a wide range of gait types. The purpose of the current study was to investigate a targeted machine learning approach for the prediction of timing for foot strike (or initial contact) and toe-off, using only kinematics for walking, forefoot running, and heel-toe running. Data were categorized by gait type and split into a training set (∼30%) and a validation set (∼70%). A principal component analysis was performed, and separate linear models were trained and validated for foot strike and toe-off, using ground reaction force data as a gold-standard for event timing. Results indicate the model predicted both foot strike and toe-off timing to within 20ms of the gold-standard for more than 95% of cases in walking and running gaits. The machine learning approach continues to provide robust timing predictions for clinical use, and may offer a flexible methodology to handle new events and gait types. Copyright © 2016 Elsevier B.V. All rights reserved.

Unraveling cognitive traits using the Morris water maze unbiased strategy classification (MUST-C) algorithm.

PubMed

Illouz, Tomer; Madar, Ravit; Louzon, Yoram; Griffioen, Kathleen J; Okun, Eitan

2016-02-01

The assessment of spatial cognitive learning in rodents is a central approach in neuroscience, as it enables one to assess and quantify the effects of treatments and genetic manipulations from a broad perspective. Although the Morris water maze (MWM) is a well-validated paradigm for testing spatial learning abilities, manual categorization of performance in the MWM into behavioral strategies is subject to individual interpretation, and thus to biases. Here we offer a support vector machine (SVM) - based, automated, MWM unbiased strategy classification (MUST-C) algorithm, as well as a cognitive score scale. This model was examined and validated by analyzing data obtained from five MWM experiments with changing platform sizes, revealing a limitation in the spatial capacity of the hippocampus. We have further employed this algorithm to extract novel mechanistic insights on the impact of members of the Toll-like receptor pathway on cognitive spatial learning and memory. The MUST-C algorithm can greatly benefit MWM users as it provides a standardized method of strategy classification as well as a cognitive scoring scale, which cannot be derived from typical analysis of MWM data. Copyright © 2015 The Authors. Published by Elsevier Inc. All rights reserved.

The Development, Validation and Use of the Rural and Remote Teaching, Working, Living and Learning Environment Survey (RRTWLLES)

ERIC Educational Resources Information Center

Dorman, Jeffrey; Kennedy, Joy; Young, Janelle

2015-01-01

Research in rural and remote schools and communities of Queensland resulted in the development and validation of the Rural and Remote Teaching, Working, Living and Learning Environment Survey (RRTWLLES). Samples of 252 teachers and 191 community members were used to validate the structure of this questionnaire. It was developed within the standard…

Why Lessons Learned from the Past Require Haertel's Expanded Scope for Test Validation

ERIC Educational Resources Information Center

Shepard, Lorrie A.

2013-01-01

In his article, Haertel (this issue) asks a fundamental question about how use of a test is expected to cause improvements in the educational system and in learning. He also considers how test validity should be investigated and argues for a more expansive view of validity that does not stop with scoring or generalization (the more technical and…

Lifelong Learning Competence Scale (LLLCS): The Study of Validity and Reliability

ERIC Educational Resources Information Center

Uzunboylu, Huseyin; Hursen, Cigdem

2011-01-01

In this research our aim is to develop a scale for lifelong learning competences and investigate the validity and the reliability of the structure of the scale. The participants of this research are 300 secondary school teachers who are randomly selected. The findings on the scale's validity of the structure are computed by the method of factor…

Immediate effects of Alpha/theta and Sensory-Motor Rhythm feedback on music performance.

PubMed

Gruzelier, J H; Hirst, L; Holmes, P; Leach, J

2014-07-01

This is one of a series of investigations comparing two EEG-neurofeedback protocols - Alpha/theta (A/T) and Sensory-Motor Rhythm (SMR) - for performance enhancement in the Arts, here with the focus on music. The original report (Egner and Gruzelier, 2003) established a beneficial outcome for elite conservatoire musicians following A/T training in two investigations. Subsequently this A/T advantage was replicated for both advanced instrumental and novice singing abilities, including improvisation, while SMR training benefited novice performance only (Gruzelier, Holmes et al., 2014). Here we report a replication of the latter study in university instrumentalists who as before were novice singers with one design change - post-training performances were conducted within the tenth final session instead of on a subsequent occasion. As before expert judges rated the domains of Creativity/Musicality, Communication/Presentation and Technique. The proximity to training of the music performances within the last session likely compromised gains from A/T learning, but perhaps reinforced the impact of SMR training efficacy. In support of validation there was evidence of strong within- and across-session A/T learning and positive linear trends for across-session SMR/theta and SMR/beta-2 ratio learning. In support of mediation learning correlated with music performance. The A/T outcome was markedly discrepant from previous studies and should dispel any impression that the hypnogogic state itself is transferred to the performance context. The effects of SMR ratio training are consistent with an impact on lower-order abilities required in novice performance such as sustained attention and memory, and benefiting all three domains of music assessment. Copyright © 2014 Elsevier B.V. All rights reserved.

Machine Learning Interface for Medical Image Analysis.

PubMed

Zhang, Yi C; Kagen, Alexander C

2017-10-01

TensorFlow is a second-generation open-source machine learning software library with a built-in framework for implementing neural networks in wide variety of perceptual tasks. Although TensorFlow usage is well established with computer vision datasets, the TensorFlow interface with DICOM formats for medical imaging remains to be established. Our goal is to extend the TensorFlow API to accept raw DICOM images as input; 1513 DaTscan DICOM images were obtained from the Parkinson's Progression Markers Initiative (PPMI) database. DICOM pixel intensities were extracted and shaped into tensors, or n-dimensional arrays, to populate the training, validation, and test input datasets for machine learning. A simple neural network was constructed in TensorFlow to classify images into normal or Parkinson's disease groups. Training was executed over 1000 iterations for each cross-validation set. The gradient descent optimization and Adagrad optimization algorithms were used to minimize cross-entropy between the predicted and ground-truth labels. Cross-validation was performed ten times to produce a mean accuracy of 0.938 ± 0.047 (95 % CI 0.908-0.967). The mean sensitivity was 0.974 ± 0.043 (95 % CI 0.947-1.00) and mean specificity was 0.822 ± 0.207 (95 % CI 0.694-0.950). We extended the TensorFlow API to enable DICOM compatibility in the context of DaTscan image analysis. We implemented a neural network classifier that produces diagnostic accuracies on par with excellent results from previous machine learning models. These results indicate the potential role of TensorFlow as a useful adjunct diagnostic tool in the clinical setting.

Validation of the Learning Progression-based Assessment of Modern Genetics in a college context

NASA Astrophysics Data System (ADS)

Todd, Amber; Romine, William L.

2016-07-01

Building upon a methodologically diverse research foundation, we adapted and validated the Learning Progression-based Assessment of Modern Genetics (LPA-MG) for college students' knowledge of the domain. Toward collecting valid learning progression-based measures in a college majors context, we redeveloped and content validated a majority of a previous version of the LPA-MG which was developed for high school students. Using a Rasch model calibrated on 316 students from 2 sections of majors introductory biology, we demonstrate the validity of this version and describe how college students' ideas of modern genetics are likely to change as the students progress from low to high understanding. We then utilize these findings to build theory around the connections college students at different levels of understanding make within and across the many ideas within the domain.

The Predictive Validity of the Assessment of Basic Learning Abilities versus Parents' Predictions with Children with Autism

ERIC Educational Resources Information Center

Murphy, Colleen; Martin, Garry L.; Yu, C. T.

2014-01-01

The Assessment of Basic Learning Abilities (ABLA) is an empirically validated clinical tool for assessing the learning ability of persons with intellectual disabilities and children with autism. An ABLA tester uses standardized prompting and reinforcement procedures to attempt to teach, individually, each of six tasks, called levels, to a testee,…