Entomology: Promoting Creativity in the Science Lab

ERIC Educational Resources Information Center

Akcay, Behiye B.

2013-01-01

A class activity has been designed to help fourth grade students to identify basic insect features as a means of promoting student creativity while making an imaginary insect model. The 5Es (Engage, Explore, Explain, Extend [or Elaborate], and Evaluate) learning cycle teaching model is used. The 5Es approach allows students to work in small…

One night of sleep is insufficient to achieve sleep-to-forget emotional decontextualisation processes.

PubMed

Deliens, Gaétane; Peigneux, Philippe

2014-01-01

Neutral memories unbind from their emotional acquisition context when sleep is allowed the night after learning and testing takes place after two additional nights of sleep. However, mood-dependent memory (MDM) effects are not abolished after a restricted sleep episode mostly featuring non rapid-eye-movement (NREM) or rapid-eye-movement (REM) sleep. Here, we tested whether (1) one night of sleep featuring several NREM-REM sleep cycles is sufficient to suppress MDM effects and (2) a neutral mood is a sufficiently contrasting state to induce MDM effects, i.e. interfere with the recall of information learned in happy or sad states. Results disclosed MDM effects both in the post-learning sleep and wake conditions, with better recall in congruent than incongruent emotional contexts. Our findings suggest that the emotional unbinding needs several consecutive nights of sleep to be complete, and that even subtle mood changes are sufficient to produce MDM effects.

Eliciting design patterns for e-learning systems

NASA Astrophysics Data System (ADS)

Retalis, Symeon; Georgiakakis, Petros; Dimitriadis, Yannis

2006-06-01

Design pattern creation, especially in the e-learning domain, is a highly complex process that has not been sufficiently studied and formalized. In this paper, we propose a systematic pattern development cycle, whose most important aspects focus on reverse engineering of existing systems in order to elicit features that are cross-validated through the use of appropriate, authentic scenarios. However, an iterative pattern process is proposed that takes advantage of multiple data sources, thus emphasizing a holistic view of the teaching learning processes. The proposed schema of pattern mining has been extensively validated for Asynchronous Network Supported Collaborative Learning (ANSCL) systems, as well as for other types of tools in a variety of scenarios, with promising results.

Development of a web-based learning medium on mechanism of labour for nursing students.

PubMed

Gerdprasert, Sailom; Pruksacheva, Tassanee; Panijpan, Bhinyo; Ruenwongsa, Pintip

2010-07-01

This study aimed to develop a web-based learning media on the process and mechanism of labour for the third-year university nursing and midwifery students. This media was developed based on integrating principles of the mechanism of labour with the 5Es inquiry cycle and interactive features of information technology. In this study, the web-based learning unit was used to supplement the conventional lecture as in the traditional teaching. Students' achievements were assessed by using the pre- and post-test on factual knowledge and semi-structured interviews on attitude to the unit. Supplementation with this learning unit made learning significantly more effective than the traditional lecture by itself. The students also showed positive attitude toward the learning unit. Copyright 2009 Elsevier Ltd. All rights reserved.

The Sequence of Learning Cycle Activities in High School Chemistry.

ERIC Educational Resources Information Center

Abraham, Michael R.; Renner, John W.

1986-01-01

Different learning cycle sequences were investigated to determine factors accounting for success of the cycle, compared learning with conventional instruction, and examined relationships between Piaget's theory and learning cycles. Results show that the normal learning cycle sequence is the optimum sequence for achievement of content knowledge in…

Learning to learn physics: The implementation of process-oriented instruction in the first year of higher education

NASA Astrophysics Data System (ADS)

Vertenten, Kristin

2002-01-01

Finding a way to encourage first year students to use deep processing strategies was the aim of this research. The need for an adequate method became clear after using the Inventory of Learning Styles (ILS) of Vermunt: almost half of the first year students turned out to have an undirected or a reproduction-directed learning style. A possible intervention is process-oriented instruction. In this type of instruction learning strategies are taught in coherence with domain specific knowledge. The emphasis is on a gradual transfer from a strongly instruction-guided regulation of the learning process towards a student-regulation. By promoting congruence and constructive frictions between instruction and learning strategies, students are challenged to improve their learning strategies. These general features of process-oriented instruction were refined by Vermunt (1992) in twelve general and specific principles. Literature was studied in which researchers reported about their experiences with interventions aimed at teaching physics knowledge, physics strategies and/or learning and thinking strategies. It became obvious that several successful interventions stressed four principles: (1) the student must experience (constructive) f&barbelow;rictions, including cognitive conflicts; (2) he must be encouraged to ṟeflect on his experiences (thinking about them and analysing them); (3) the instruction must e&barbelow;xplicate and demonstrate the necessary knowledge and strategies; and (4) the student must be given the opportunity to practice (ḏoing) with the learned knowledge and strategies. These four FRED-principles are useful for teaching both general and domain specific knowledge and strategies. They show similarities with the four stages in the learning cycle of Kolb (1984). Moreover, other elements of process-oriented instruction are also depicted by the learning cycle, which, when used in process-oriented instruction, has to start with experiencing (constructive) frictions. The gradual shift of the regulation of the learning process can also be translated to the learning cycle. This can be accomplished by giving a new meaning to the radius of the circle which must represent the growing self-regulation of the learning process. This transforms the learning cycle into a learning spiral. The four FRED-principles were used to develop a learning environment for the first year physics problem-solving classes. After working in this learning environment during the first semester, students began using deep processing strategies in a self-regulated manner. After the second semester the reproduction-directed and undirected learning style were vanished or strongly diminished. These effects were not found in a traditional learning environment. The experimental group also obtained better study results. Working in the developed learning environment did not heighten the study load. (Abstract shortened by UMI.)

Transitions to Chaos in a Seven-Equation Model of the Business Cycle with Income Redistribution and Private Debt

NASA Astrophysics Data System (ADS)

Colacchio, Giorgio

In the present paper, we investigate the chaotic implications of a seven-equation model of the business cycle. The main distinguishing features of the model are related to: (a) the role played by the bargaining power in the process of income redistribution; (b) the consideration of hysteresis effects on workers’ consumption demand; (c) the effect of public expenditure on labor productivity. In addition, the role played by the agents’ memory on the actual dynamics of the economic system, with particular regard to their learning-by-doing process, is particularly emphasized. Under all these assumptions, the system exhibits a rich and complex phenomenology, characterized by a number of transitions to chaos (in particular via sequences of period doubling bifurcations), aperiodic behavior, bistability, tristability, etc. We maintain that our analysis takes us another step forward in the building of a more general model of the business cycle. In particular, the model we propose may be of help in the explanation of some peculiar features of advanced capitalist economies, with particular regard to the role played by the State in the determination of agents’ disposable income, to the debt dynamics of the various macroagents, and to the main dilemmas of economic policy. More in general, the main lesson one learns from our investigation is that “disequilibrium paths”, characterized by “complicated” dynamics which, more often than not, takes the form of aperiodic motion, should be considered as the “normal” state of the system.

The Earth System Course at the University of Oklahoma: Science and Pedagogy Aimed at Pre-service Teachers

NASA Astrophysics Data System (ADS)

Postawko, S.; Soreghan, M.; Marek, E.

2005-12-01

Traditionally, education majors at the University of Oklahoma took either Introduction to Physical Geology or Introduction to Meteorology to fulfill their physical sciences requirement. Science education majors were required to take both courses. These courses are large-enrollment lecture type courses, with required lab sections taught by graduate teaching assistants. Beginning in 1997, faculty from the Colleges of Education and Geosciences at the University of Oklahoma began working together to provide effective earth science education for pre-service teachers. The first step in this collaboration was the development of a new course on The Earth System that focuses on Earth as a whole rather than on the more narrow focus of either the geology or meteorology courses. The new course, which was taught for the first time in the Spring of 2001, covers a number of major themes related to Earth Science, including the Carbon Cycle, Earth Materials, Plate Tectonics, Atmosphere and Oceans. The particular concepts within each theme were chosen based on two criteria: 1) alignment with content advocated by national (NSES) and state (Priority Academic Student Skills-PASS) standards; and 2) they are amenable to a learning cycle pedagogical approach. Besides an interdisciplinary approach to the content, the new course features pedagogical innovations. In lieu of independent laboratory and lecture times, we scheduled two class periods of longer duration, so that active learning, involving hands-on activities and experiments were possible throughout each class period. The activities modeled the learning-cycle approach with an exploration, concept invention, and an expansion phase (Marek and Cavallo, 1997). Therefore, the pre-service teachers experienced the learning cycle in practice prior to learning the theory in their upper division "methods" course. In the first 3 years that the course was taught, students were given surveys early in the semester and at the end of the semester. The surveys aimed to both assess the students' learning and retention (compared to students in the more traditional Introductory Geology course, who were given similar surveys), and solicit the students' opinions of the inquiry-based learning approach compared to more traditional lecture/lab classroom teaching methods.

Use of the 5E learning cycle model combined with problem-based learning for a fundamentals of nursing course.

PubMed

Jun, Won Hee; Lee, Eun Ju; Park, Han Jong; Chang, Ae Kyung; Kim, Mi Ja

2013-12-01

The 5E learning cycle model has shown a positive effect on student learning in science education, particularly in courses with theory and practice components. Combining problem-based learning (PBL) with the 5E learning cycle was suggested as a better option for students' learning of theory and practice. The purpose of this study was to compare the effects of the traditional learning method with the 5E learning cycle model with PBL. The control group (n = 78) was subjected to a learning method that consisted of lecture and practice. The experimental group (n = 83) learned by using the 5E learning cycle model with PBL. The results showed that the experimental group had significantly improved self-efficacy, critical thinking, learning attitude, and learning satisfaction. Such an approach could be used in other countries to enhance students' learning of fundamental nursing. Copyright 2013, SLACK Incorporated.

Combining advanced networked technology and pedagogical methods to improve collaborative distance learning.

PubMed

Staccini, Pascal; Dufour, Jean-Charles; Raps, Hervé; Fieschi, Marius

2005-01-01

Making educational material be available on a network cannot be reduced to merely implementing hypermedia and interactive resources on a server. A pedagogical schema has to be defined to guide students for learning and to provide teachers with guidelines to prepare valuable and upgradeable resources. Components of a learning environment, as well as interactions between students and other roles such as author, tutor and manager, can be deduced from cognitive foundations of learning, such as the constructivist approach. Scripting the way a student will to navigate among information nodes and interact with tools to build his/her own knowledge can be a good way of deducing the features of the graphic interface related to the management of the objects. We defined a typology of pedagogical resources, their data model and their logic of use. We implemented a generic and web-based authoring and publishing platform (called J@LON for Join And Learn On the Net) within an object-oriented and open-source programming environment (called Zope) embedding a content management system (called Plone). Workflow features have been used to mark the progress of students and to trace the life cycle of resources shared by the teaching staff. The platform integrated advanced on line authoring features to create interactive exercises and support live courses diffusion. The platform engine has been generalized to the whole curriculum of medical studies in our faculty; it also supports an international master of risk management in health care and will be extent to all other continuous training diploma.

Integrating Concept Mapping and the Learning Cycle To Teach Diffusion and Osmosis Concepts to High School Biology Students.

ERIC Educational Resources Information Center

Odom, Arthur L.; Kelly, Paul V.

2001-01-01

Explores the effectiveness of concept mapping, the learning cycle, expository instruction, and a combination of concept mapping/learning cycle in promoting conceptual understanding of diffusion and osmosis. Concludes that the concept mapping/learning cycle and concept mapping treatment groups significantly outperformed the expository treatment…

Jet and flash imprint defectivity: assessment and reduction for semiconductor applications

NASA Astrophysics Data System (ADS)

Malloy, Matt; Litt, Lloyd C.; Johnson, Steve; Resnick, Douglas J.; Lovell, David

2011-04-01

Defectivity has been historically identified as a leading technical roadblock to the implementation of nanoimprint lithography for semiconductor high volume manufacturing. The lack of confidence in nanoimprint's ability to meet defect requirements originates in part from the industry's past experiences with 1X lithography and the shortage in end-user generated defect data. SEMATECH has therefore initiated a defect assessment aimed at addressing these concerns. The goal is to determine whether nanoimprint, specifically Jet and Flash Imprint Lithography from Molecular Imprints, is capable of meeting semiconductor industry defect requirements. At this time, several cycles of learning have been completed in SEMATECH's defect assessment, with promising results. J-FIL process random defectivity of < 0.1 def/cm2 has been demonstrated using a 120nm half-pitch template, providing proof of concept that a low defect nanoimprint process is possible. Template defectivity has also improved significantly as shown by a pre-production grade template at 80nm pitch. Cycles of learning continue on feature sizes down to 22nm.

Integrating Research on Misconceptions, Reasoning Patterns and Three Types of Learning Cycles.

ERIC Educational Resources Information Center

Lawson, Anton E.

This paper describes how the learning cycle leads students to become more skilled reasoners. The three phases of the learning cycle are described and examples and goals of each are provided. Information is also offered on the three types of learning cycles: the descriptive; the empirical-inductive; and the hypothetical-deductive. Each is described…

The Learning Cycle: A Reintroduction

NASA Astrophysics Data System (ADS)

Maier, Steven J.; Marek, Edmund A.

2006-02-01

The learning cycle is an inquiry approach to instruction that continues to demonstrate significant effectiveness in the classroom.1-3 Rooted in Piaget's theory of intellectual development, learning cycles provide a structured means for students to construct concepts from direct experiences with science phenomena. Learning cycles have been the subject of numerous articles in science practitioner periodicals as well as the focus of much research in science education journals.4 This paper reintroduces the learning cycle by giving a brief description, followed by an example suitable for a range of physics classrooms.

Using a Learning Cycle to Deepen Chinese Primary Students' Concept Learning of the "Phases of the Moon"

ERIC Educational Resources Information Center

Lin, Jing

2016-01-01

This study focuses on the internal conditions of students' concept learning and builds a learning cycle' based on the "phases of the Moon" (MP) to, deepen students' understanding. The learning cycle of MP developed in this study includes three basic learning links, which are: cognitive conflict, abstraction and generalization, and…

Motor Task Variation Induces Structural Learning

PubMed Central

Braun, Daniel A.; Aertsen, Ad; Wolpert, Daniel M.; Mehring, Carsten

2009-01-01

Summary When we have learned a motor skill, such as cycling or ice-skating, we can rapidly generalize to novel tasks, such as motorcycling or rollerblading [1–8]. Such facilitation of learning could arise through two distinct mechanisms by which the motor system might adjust its control parameters. First, fast learning could simply be a consequence of the proximity of the original and final settings of the control parameters. Second, by structural learning [9–14], the motor system could constrain the parameter adjustments to conform to the control parameters' covariance structure. Thus, facilitation of learning would rely on the novel task parameters' lying on the structure of a lower-dimensional subspace that can be explored more efficiently. To test between these two hypotheses, we exposed subjects to randomly varying visuomotor tasks of fixed structure. Although such randomly varying tasks are thought to prevent learning, we show that when subsequently presented with novel tasks, subjects exhibit three key features of structural learning: facilitated learning of tasks with the same structure, strong reduction in interference normally observed when switching between tasks that require opposite control strategies, and preferential exploration along the learned structure. These results suggest that skill generalization relies on task variation and structural learning. PMID:19217296

Motor task variation induces structural learning.

PubMed

Braun, Daniel A; Aertsen, Ad; Wolpert, Daniel M; Mehring, Carsten

2009-02-24

When we have learned a motor skill, such as cycling or ice-skating, we can rapidly generalize to novel tasks, such as motorcycling or rollerblading [1-8]. Such facilitation of learning could arise through two distinct mechanisms by which the motor system might adjust its control parameters. First, fast learning could simply be a consequence of the proximity of the original and final settings of the control parameters. Second, by structural learning [9-14], the motor system could constrain the parameter adjustments to conform to the control parameters' covariance structure. Thus, facilitation of learning would rely on the novel task parameters' lying on the structure of a lower-dimensional subspace that can be explored more efficiently. To test between these two hypotheses, we exposed subjects to randomly varying visuomotor tasks of fixed structure. Although such randomly varying tasks are thought to prevent learning, we show that when subsequently presented with novel tasks, subjects exhibit three key features of structural learning: facilitated learning of tasks with the same structure, strong reduction in interference normally observed when switching between tasks that require opposite control strategies, and preferential exploration along the learned structure. These results suggest that skill generalization relies on task variation and structural learning.

Using the Learning Cycle To Teach Physical Science: A Hands-on Approach for the Middle Grades.

ERIC Educational Resources Information Center

Beisenherz, Paul; Dantonio, Marylou

The Learning Cycle Strategy enables students themselves to construct discrete science concepts and includes an exploration phase, introduction phase, and application phase. This book focuses on the use of the Learning Cycle to teach physical sciences and is divided into three sections. Section I develops a rationale for the Learning Cycle as an…

Log In to Experiential Learning Theory: Supporting Web-Based Faculty Development

PubMed Central

Brien, Sarah; Parry, Marcus

2017-01-01

Background For an increasingly busy and geographically dispersed faculty, the Faculty of Medicine at the University of Southampton, United Kingdom, developed a range of Web-based faculty development modules, based on Kolb’s experiential learning cycle, to complement the faculty’s face-to-face workshops. Objective The objective of this study was to assess users’ views and perceptions of the effectiveness of Web-based faculty development modules based on Kolb’s experiential learning cycle. We explored (1) users’ satisfaction with the modules, (2) whether Kolb’s design framework supported users’ learning, and (3) whether the design principle impacts their work as educators. Methods We gathered data from users over a 3-year period using evaluation surveys built into each of the seven modules. Quantitative data were analyzed using descriptive statistics, and responses to open-ended questions were analyzed using content analysis. Results Out of the 409 module users, 283 completed the survey (69.1% response rate). Over 80% of the users reported being satisfied or very satisfied with seven individual aspects of the modules. The findings suggest a strong synergy between the design features that users rated most highly and the key stages of Kolb’s learning cycle. The use of simulations and videos to give the users an initial experience as well as the opportunity to “Have a go” and receive feedback in a safe environment were both considered particularly useful. In addition to providing an opportunity for reflection, many participants considered that the modules would enhance their roles as educators through: increasing their knowledge on various education topics and the required standards for medical training, and improving their skills in teaching and assessing students through practice and feedback and ultimately increasing their confidence. Conclusions Kolb’s theory-based design principle used for Web-based faculty development can support faculty to improve their skills and has impact on their role as educators. Grounding Web-based training in learning theory offers an effective and flexible approach for faculty development. PMID:28954718

Feature Reinforcement Learning: Part I. Unstructured MDPs

NASA Astrophysics Data System (ADS)

Hutter, Marcus

2009-12-01

General-purpose, intelligent, learning agents cycle through sequences of observations, actions, and rewards that are complex, uncertain, unknown, and non-Markovian. On the other hand, reinforcement learning is well-developed for small finite state Markov decision processes (MDPs). Up to now, extracting the right state representations out of bare observations, that is, reducing the general agent setup to the MDP framework, is an art that involves significant effort by designers. The primary goal of this work is to automate the reduction process and thereby significantly expand the scope of many existing reinforcement learning algorithms and the agents that employ them. Before we can think of mechanizing this search for suitable MDPs, we need a formal objective criterion. The main contribution of this article is to develop such a criterion. I also integrate the various parts into one learning algorithm. Extensions to more realistic dynamic Bayesian networks are developed in Part II (Hutter, 2009c). The role of POMDPs is also considered there.

Training for Content Teachers of English Language Learners: Using Experiential Learning to Improve Instruction

ERIC Educational Resources Information Center

Bohon, Leslie L.; McKelvey, Susan; Rhodes, Joan A.; Robnolt, Valerie J.

2017-01-01

Experiential learning theory places experience at the center of learning. Kolb's four-stage cycle of experiential learning suggests that effective learners must engage fully in each stage of the cycle--feeling, reflection, thinking, and action. This research assesses the alignment of Kolb's experiential learning cycle with the week-long Summer…

Active-learning strategies in computer-assisted drug discovery.

PubMed

Reker, Daniel; Schneider, Gisbert

2015-04-01

High-throughput compound screening is time and resource consuming, and considerable effort is invested into screening compound libraries, profiling, and selecting the most promising candidates for further testing. Active-learning methods assist the selection process by focusing on areas of chemical space that have the greatest chance of success while considering structural novelty. The core feature of these algorithms is their ability to adapt the structure-activity landscapes through feedback. Instead of full-deck screening, only focused subsets of compounds are tested, and the experimental readout is used to refine molecule selection for subsequent screening cycles. Once implemented, these techniques have the potential to reduce costs and save precious materials. Here, we provide a comprehensive overview of the various computational active-learning approaches and outline their potential for drug discovery. Copyright © 2014 Elsevier Ltd. All rights reserved.

Assessing Understanding of the Learning Cycle: The ULC

NASA Astrophysics Data System (ADS)

Marek, Edmund A.; Maier, Steven J.; McCann, Florence

2008-08-01

An 18-item, multiple choice, 2-tiered instrument designed to measure understanding of the learning cycle (ULC) was developed and field-tested from the learning cycle test (LCT) of Odom and Settlage ( Journal of Science Teacher Education, 7, 123 142, 1996). All question sets of the LCT were modified to some degree and 5 new sets were added, resulting in the ULC. The ULC measures (a) understandings and misunderstandings of the learning cycle, (b) the learning cycle’s association with Piaget’s ( Biology and knowledge theory: An essay on the relations between organic regulations and cognitive processes, 1975) theory of mental functioning, and (c) applications of the learning cycle. The resulting ULC instrument was evaluated for internal consistency with Cronbach’s alpha, yielding a coefficient of .791.

Text feature extraction based on deep learning: a review.

PubMed

Liang, Hong; Sun, Xiao; Sun, Yunlei; Gao, Yuan

2017-01-01

Selection of text feature item is a basic and important matter for text mining and information retrieval. Traditional methods of feature extraction require handcrafted features. To hand-design, an effective feature is a lengthy process, but aiming at new applications, deep learning enables to acquire new effective feature representation from training data. As a new feature extraction method, deep learning has made achievements in text mining. The major difference between deep learning and conventional methods is that deep learning automatically learns features from big data, instead of adopting handcrafted features, which mainly depends on priori knowledge of designers and is highly impossible to take the advantage of big data. Deep learning can automatically learn feature representation from big data, including millions of parameters. This thesis outlines the common methods used in text feature extraction first, and then expands frequently used deep learning methods in text feature extraction and its applications, and forecasts the application of deep learning in feature extraction.

Guided Inquiry Learning With Sea Water Battery Project

NASA Astrophysics Data System (ADS)

Mashudi, A.

2017-02-01

Science learning process is expected to produce valuable product, innovative and real learning environment, and provide memorable learning experience. That orientation can be contained in Inquiry Based Learning. SMP N 4 Juwana is located close to the beach. That’s why, Sea Water Battery Project is very suitable to be applied in learning activity as an effort to fulfill the renewable energy based on local wisdom. This study aims to increase interest, activity and achievement of students. Learning implementation stage, namely : Constructing Sea Water Battery project, observation, group presentations, and feedback. Sea Water Battery is renewable energy battery from materials easily found around the learner. The materials used are copper plate as the anode, zinc plate as the cathode and sea water as the electrolyte. Average score of students Interest on the first cycle 76, while on the second cycle 85. Average score of students Activity on the first cycle 76 and on the second cycle 86. Average score of students achievement on the first cycle 75, while on the second cycle 84. This learning process gave nurturant effect for students to keep innovating and construct engineering technology for the future.

Convection Connections.

ERIC Educational Resources Information Center

Cavallo, Ann M. L.

2001-01-01

Introduces three science activities for elementary and middle school students on the concepts of heat transfer and temperature. Includes two learning cycles. The first learning cycle examines the effects of temperature on air movement, and the second learning cycle investigates heat movement in water. (YDS)

Nucleolar asymmetry and the importance of septin integrity upon cell cycle arrest

PubMed Central

Rai, Urvashi; Najm, Fadi

2017-01-01

Cell cycle arrest can be imposed by inactivating the anaphase promoting complex (APC). In S. cerevisiae this arrest has been reported to stabilize a metaphase-like intermediate in which the nuclear envelope spans the bud neck, while chromatin repeatedly translocates between the mother and bud domains. The present investigation was undertaken to learn how other features of nuclear organization are affected upon depletion of the APC activator, Cdc20. We observe that the spindle pole bodies and the spindle repeatedly translocate across the narrow orifice at the level of the neck. Nevertheless, we find that the nucleolus (organized around rDNA repeats on the long right arm of chromosome XII) remains in the mother domain, marking the polarity of the nucleus. Accordingly, chromosome XII is polarized: TelXIIR remains in the mother domain and its centromere is predominantly located in the bud domain. In order to learn why the nucleolus remains in the mother domain, we studied the impact of inhibiting rRNA synthesis in arrested cells. We observed that this fragments the nucleolus and that these fragments entered the bud domain. Taken together with earlier observations, the restriction of the nucleolus to the mother domain therefore can be attributed to its massive structure. We also observed that inactivation of septins allowed arrested cells to complete the cell cycle, that the alternative APC activator, Cdh1, was required for completion of the cell cycle and that induction of Cdh1 itself caused arrested cells to progress to the end of the cell cycle. PMID:28339487

Quality improvement on chemistry practicum courses through implementation of 5E learning cycle

NASA Astrophysics Data System (ADS)

Merdekawati, Krisna

2017-03-01

Two of bachelor of chemical education's competences are having practical skills and mastering chemistry material. Practicum courses are organized to support the competency achievement. Based on observation and evaluation, many problems were found in the implementation of practicum courses. Preliminary study indicated that 5E Learning Cycle can be used as an alternative solution in order to improve the quality of chemistry practicum course. The 5E Learning Cycle can provide positive influence on the achievement of the competence, laboratory skills, and students' understanding. The aim of the research was to describe the feasibility of implementation of 5E Learning Cycle on chemistry practicum courses. The research was based on phenomenology method in qualitative approach. The participants of the research were 5 person of chemistry laboratory manager (lecturers at chemistry and chemistry education department). They concluded that the 5E Learning Cycle could be implemented to improve the quality of the chemistry practicum courses. Practicum guides and assistant competences were organized to support the implementation of 5E Learning Cycle. It needed training for assistants to understand and implement in the stages of 5E Learning Cycle. Preparation of practical guidelines referred to the stages of 5E Learning Cycle, started with the introduction of contextual and applicable materials, then followed with work procedures that accommodate the stage of engagement, exploration, explanation, extension, and evaluation

Unsupervised feature learning for autonomous rock image classification

NASA Astrophysics Data System (ADS)

Shu, Lei; McIsaac, Kenneth; Osinski, Gordon R.; Francis, Raymond

2017-09-01

Autonomous rock image classification can enhance the capability of robots for geological detection and enlarge the scientific returns, both in investigation on Earth and planetary surface exploration on Mars. Since rock textural images are usually inhomogeneous and manually hand-crafting features is not always reliable, we propose an unsupervised feature learning method to autonomously learn the feature representation for rock images. In our tests, rock image classification using the learned features shows that the learned features can outperform manually selected features. Self-taught learning is also proposed to learn the feature representation from a large database of unlabelled rock images of mixed class. The learned features can then be used repeatedly for classification of any subclass. This takes advantage of the large dataset of unlabelled rock images and learns a general feature representation for many kinds of rocks. We show experimental results supporting the feasibility of self-taught learning on rock images.

The development of learning material using learning cycle 5E model based stem to improve students’ learning outcomes in Thermochemistry

NASA Astrophysics Data System (ADS)

sugiarti, A. C.; suyatno, S.; Sanjaya, I. G. M.

2018-04-01

The objective of this study is describing the feasibility of Learning Cycle 5E STEM (Science, Technology, Engineering, and Mathematics) based learning material which is appropriate to improve students’ learning achievement in Thermochemistry. The study design used 4-D models and one group pretest-posttest design to obtain the information about the improvement of sudents’ learning outcomes. The subject was learning cycle 5E based STEM learning materials which the data were collected from 30 students of Science class at 11th Grade. The techniques used in this study were validation, observation, test, and questionnaire. Some result attain: (1) all the learning materials contents were valid, (2) the practicality and the effectiveness of all the learning materials contents were classified as good. The conclution of this study based on those three condition, the Learnig Cycle 5E based STEM learning materials is appropriate to improve students’ learning outcomes in studying Thermochemistry.

Learning outcomes through the cooperative learning team assisted individualization on research methodology’ course

NASA Astrophysics Data System (ADS)

Pakpahan, N. F. D. B.

2018-01-01

All articles must contain an abstract. The research methodology is a subject in which the materials must be understood by the students who will take the thesis. Implementation of learning should create the conditions for active learning, interactive and effective are called Team Assisted Individualization (TAI) cooperative learning. The purpose of this study: 1) improving student learning outcomes at the course research methodology on TAI cooperative learning. 2) improvement of teaching activities. 3) improvement of learning activities. This study is a classroom action research conducted at the Department of Civil Engineering Universitas Negeri Surabaya. The research subjects were 30 students and lecturer of courses. Student results are complete in the first cycle by 20 students (67%) and did not complete 10 students (33%). In the second cycle students who complete being 26 students (87%) and did not complete 4 students (13%). There is an increase in learning outcomes by 20%. Results of teaching activities in the first cycle obtained the value of 3.15 with the criteria enough well. In the second cycle obtained the value of 4.22 with good criterion. The results of learning activities in the first cycle obtained the value of 3.05 with enough criterion. In the second cycle was obtained 3.95 with good criterion.

The Development of SCORM-Conformant Learning Content Based on the Learning Cycle Using Participatory Design

ERIC Educational Resources Information Center

Su, C. Y.; Chiu, C. H.; Wang, T. I.

2010-01-01

This study incorporates the 5E learning cycle strategy to design and develop Sharable Content Object Reference Model-conformant materials for elementary science education. The 5E learning cycle that supports the constructivist approach has been widely applied in science education. The strategy consists of five phases: engagement, exploration,…

A 5E Learning Cycle Approach-Based, Multimedia-Supplemented Instructional Unit for Structured Query Language

ERIC Educational Resources Information Center

Piyayodilokchai, Hongsiri; Panjaburee, Patcharin; Laosinchai, Parames; Ketpichainarong, Watcharee; Ruenwongsa, Pintip

2013-01-01

With the benefit of multimedia and the learning cycle approach in promoting effective active learning, this paper proposed a learning cycle approach-based, multimedia-supplemented instructional unit for Structured Query Language (SQL) for second-year undergraduate students with the aim of enhancing their basic knowledge of SQL and ability to apply…

A New Learning Model on Physical Education: 5E Learning Cycle

ERIC Educational Resources Information Center

Senturk, Halil Evren; Camliyer, Huseyin

2016-01-01

Many fields of education at the moment, especially in physical and technological educations, use 5E learning cycle. The process is defined as five "E"s. These represent the verbs engage, explore, explain, elaborate and evaluate. The literature has been systematically reviewed and the results show that the 5E learning cycle is an untested…

Lifelong Learning: The Whole DAMN Cycle--A Singapore Perspective.

ERIC Educational Resources Information Center

Pan, Daphne Yuen

The Desire, Ability, Means, and Need (DAMN) Cycle is a useful paradigm for understanding the lifelong learning framework in Singapore. The cycle suggests that, for learning to occur, students must have a desire and an ability to learn, including inquiring minds and higher order process skills; the means must be provided through a well-defined…

Moving and Learning: Expanding Style and Increasing Flexibility

ERIC Educational Resources Information Center

Peterson, Kay; DeCato, Lisa; Kolb, David A.

2015-01-01

This article introduces ways in which movement can enhance one's understanding of how to learn using Experiential Learning Theory (ELT) concepts of the Learning Cycle, Learning Styles, and Learning Flexibility. The theoretical correspondence between the dialectic dimensions of the Learning Cycle and the dimensions of the Laban Movement Analysis…

Teaching Significant Figures Using a Learning Cycle.

ERIC Educational Resources Information Center

Guymon, E. Park; And Others

1986-01-01

Describes an instructional strategy based on the learning cycle for teaching the use of significant figures. Provides explanations of teaching activities for each phase of the learning cycle (exploration, invention, application). Compares this approach to teaching significant figures with the traditional textbook approach. (TW)

A Learning Cycle Approach To Introducing Osmosis.

ERIC Educational Resources Information Center

Lawson, Anton E.

2000-01-01

Presents an inquiry activity with a learning cycle approach to engage students in testing their own hypotheses about how molecules move through cell membranes. Offers student materials and teacher materials, including teaching tips for each phase of the learning cycle. (Contains 11 references.) (ASK)

Removing Preconceptions with a "Learning Cycle."

ERIC Educational Resources Information Center

Gang, Su

1995-01-01

Describes a teaching experiment that uses the Learning Cycle to achieve the reorientation of physics' students conceptual frameworks away from commonsense perspectives toward scientifically rigorous outlooks. Uses Archimedes' principle as the content topic while using the Learning Cycle to remove students' nonscientific preconceptions. (JRH)

Online estimation of lithium-ion battery capacity using sparse Bayesian learning

NASA Astrophysics Data System (ADS)

Hu, Chao; Jain, Gaurav; Schmidt, Craig; Strief, Carrie; Sullivan, Melani

2015-09-01

Lithium-ion (Li-ion) rechargeable batteries are used as one of the major energy storage components for implantable medical devices. Reliability of Li-ion batteries used in these devices has been recognized as of high importance from a broad range of stakeholders, including medical device manufacturers, regulatory agencies, patients and physicians. To ensure a Li-ion battery operates reliably, it is important to develop health monitoring techniques that accurately estimate the capacity of the battery throughout its life-time. This paper presents a sparse Bayesian learning method that utilizes the charge voltage and current measurements to estimate the capacity of a Li-ion battery used in an implantable medical device. Relevance Vector Machine (RVM) is employed as a probabilistic kernel regression method to learn the complex dependency of the battery capacity on the characteristic features that are extracted from the charge voltage and current measurements. Owing to the sparsity property of RVM, the proposed method generates a reduced-scale regression model that consumes only a small fraction of the CPU time required by a full-scale model, which makes online capacity estimation computationally efficient. 10 years' continuous cycling data and post-explant cycling data obtained from Li-ion prismatic cells are used to verify the performance of the proposed method.

An English Vocabulary Learning System Based on Fuzzy Theory and Memory Cycle

NASA Astrophysics Data System (ADS)

Wang, Tzone I.; Chiu, Ti Kai; Huang, Liang Jun; Fu, Ru Xuan; Hsieh, Tung-Cheng

This paper proposes an English Vocabulary Learning System based on the Fuzzy Theory and the Memory Cycle Theory to help a learner to memorize vocabularies easily. By using fuzzy inferences and personal memory cycles, it is possible to find an article that best suits a learner. After reading an article, a quiz is provided for the learner to improve his/her memory of the vocabulary in the article. Early researches use just explicit response (ex. quiz exam) to update memory cycles of newly learned vocabulary; apart from that approach, this paper proposes a methodology that also modify implicitly the memory cycles of learned word. By intensive reading of articles recommended by our approach, a learner learns new words quickly and reviews learned words implicitly as well, and by which the vocabulary ability of the learner improves efficiently.

A Piagetian Learning Cycle for Introductory Chemical Kinetics.

ERIC Educational Resources Information Center

Batt, Russell H.

1980-01-01

Described is a Piagetian learning cycle based on Monte Carlo modeling of several simple reaction mechanisms. Included are descriptions of learning cycle phases (exploration, invention, and discovery) and four BASIC-PLUS computer programs to be used in the explanation of chemical reacting systems. (Author/DS)

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…

Why Do Athletes Drink Sports Drinks? A Learning Cycle to Explore the Concept of Osmosis

ERIC Educational Resources Information Center

Carlsen, Brook; Marek, Edmund A.

2010-01-01

Why does an athlete reach for a sports drink after a tough game or practice? The learning cycle presented in this article helps students answer this question. Learning cycles (Marek 2009) are designed to guide students through direct experiences with a particular concept. In this article, students learn about "osmosis," or the moving of water into…

The Effect of 7E Learning Cycle on Learning in Science Teaching: A Meta-Analysis Study

ERIC Educational Resources Information Center

Balta, Nuri; Sarac, Hakan

2016-01-01

This article reports the results of a meta-analysis of the effectiveness of 7E learning cycle in science teaching. Totally 35 different effect sizes from 24 experimental studies, comprising 2918 students were included in the meta-analysis. The results confirmed that 7E learning cycle have a positive effect on students' achievement. The overall…

Feature Inference Learning and Eyetracking

ERIC Educational Resources Information Center

Rehder, Bob; Colner, Robert M.; Hoffman, Aaron B.

2009-01-01

Besides traditional supervised classification learning, people can learn categories by inferring the missing features of category members. It has been proposed that feature inference learning promotes learning a category's internal structure (e.g., its typical features and interfeature correlations) whereas classification promotes the learning of…

A Classroom Learning Cycle: Using Diagrams to Classify Matter.

ERIC Educational Resources Information Center

James, Helen J.; Nelson, Samuel L.

1981-01-01

A learning cycle involves the active participation of students in exploration, invention, and application phases. Describes one such learning cycle dealing with classification of matter and designed to provide students with an understanding of the terms: atom, molecule, element, compound, solution, and heterogeneous matter. (Author/JN)

Evaluating Online CPD Using Educational Criteria Derived from the Experiential Learning Cycle.

ERIC Educational Resources Information Center

Friedman, Andrew; Watts, David; Croston, Judith; Durkin, Catherine

2002-01-01

Develops a set of educational evaluation criteria for online continuing professional development (CPD) courses using Kolb's experiential learning cycle theory. Evaluates five courses provided by online CPD Web sites, concludes that these online courses neglect parts of the learning cycle, and suggests improvements. (Author/LRW)

The Twin-Cycle Experiential Learning Model: Reconceptualising Kolb's Theory

ERIC Educational Resources Information Center

Bergsteiner, Harald; Avery, Gayle C.

2014-01-01

Experiential learning styles remain popular despite criticisms about their validity, usefulness, fragmentation and poor definitions and categorisation. After examining four prominent models and building on Bergsteiner, Avery, and Neumann's suggestion of a dual cycle, this paper proposes a twin-cycle experiential learning model to overcome…

Heart murmur detection based on wavelet transformation and a synergy between artificial neural network and modified neighbor annealing methods.

PubMed

Eslamizadeh, Gholamhossein; Barati, Ramin

2017-05-01

Early recognition of heart disease plays a vital role in saving lives. Heart murmurs are one of the common heart problems. In this study, Artificial Neural Network (ANN) is trained with Modified Neighbor Annealing (MNA) to classify heart cycles into normal and murmur classes. Heart cycles are separated from heart sounds using wavelet transformer. The network inputs are features extracted from individual heart cycles, and two classification outputs. Classification accuracy of the proposed model is compared with five multilayer perceptron trained with Levenberg-Marquardt, Extreme-learning-machine, back-propagation, simulated-annealing, and neighbor-annealing algorithms. It is also compared with a Self-Organizing Map (SOM) ANN. The proposed model is trained and tested using real heart sounds available in the Pascal database to show the applicability of the proposed scheme. Also, a device to record real heart sounds has been developed and used for comparison purposes too. Based on the results of this study, MNA can be used to produce considerable results as a heart cycle classifier. Copyright © 2017 Elsevier B.V. All rights reserved.

The Effects of Mobile Natural-Science Learning Based on the 5E Learning Cycle: A Case Study

ERIC Educational Resources Information Center

Liu, Tzu-Chien; Peng, Hsinyi; Wu, Wen-Hsuan; Lin, Ming-Sheng

2009-01-01

This study has three major purposes, including designing mobile natural-science learning activities that rest on the 5E Learning Cycle, examining the effects of these learning activities on students' performances of learning aquatic plants, and exploring students' perceptions toward these learning activities. A case-study method is utilized and…

New features and applications of PRESTO, a computer code for the performance of regenerative, superheated steam turbine cycles

NASA Technical Reports Server (NTRS)

Choo, Y. K.; Staiger, P. J.

1982-01-01

The code was designed to analyze performance at valves-wide-open design flow. The code can model conventional steam cycles as well as cycles that include such special features as process steam extraction and induction and feedwater heating by external heat sources. Convenience features and extensions to the special features were incorporated into the PRESTO code. The features are described, and detailed examples illustrating the use of both the original and the special features are given.

Modulations of eye movement patterns by spatial filtering during the learning and testing phases of an old/new face recognition task.

PubMed

Lemieux, Chantal L; Collin, Charles A; Nelson, Elizabeth A

2015-02-01

In two experiments, we examined the effects of varying the spatial frequency (SF) content of face images on eye movements during the learning and testing phases of an old/new recognition task. At both learning and testing, participants were presented with face stimuli band-pass filtered to 11 different SF bands, as well as an unfiltered baseline condition. We found that eye movements varied significantly as a function of SF. Specifically, the frequency of transitions between facial features showed a band-pass pattern, with more transitions for middle-band faces (≈5-20 cycles/face) than for low-band (≈<5 cpf) or high-band (≈>20 cpf) ones. These findings were similar for the learning and testing phases. The distributions of transitions across facial features were similar for the middle-band, high-band, and unfiltered faces, showing a concentration on the eyes and mouth; conversely, low-band faces elicited mostly transitions involving the nose and nasion. The eye movement patterns elicited by low, middle, and high bands are similar to those previous researchers have suggested reflect holistic, configural, and featural processing, respectively. More generally, our results are compatible with the hypotheses that eye movements are functional, and that the visual system makes flexible use of visuospatial information in face processing. Finally, our finding that only middle spatial frequencies yielded the same number and distribution of fixations as unfiltered faces adds more evidence to the idea that these frequencies are especially important for face recognition, and reveals a possible mediator for the superior performance that they elicit.

Log In to Experiential Learning Theory: Supporting Web-Based Faculty Development.

PubMed

Omer, Selma; Choi, Sunhea; Brien, Sarah; Parry, Marcus

2017-09-27

For an increasingly busy and geographically dispersed faculty, the Faculty of Medicine at the University of Southampton, United Kingdom, developed a range of Web-based faculty development modules, based on Kolb's experiential learning cycle, to complement the faculty's face-to-face workshops. The objective of this study was to assess users' views and perceptions of the effectiveness of Web-based faculty development modules based on Kolb's experiential learning cycle. We explored (1) users' satisfaction with the modules, (2) whether Kolb's design framework supported users' learning, and (3) whether the design principle impacts their work as educators. We gathered data from users over a 3-year period using evaluation surveys built into each of the seven modules. Quantitative data were analyzed using descriptive statistics, and responses to open-ended questions were analyzed using content analysis. Out of the 409 module users, 283 completed the survey (69.1% response rate). Over 80% of the users reported being satisfied or very satisfied with seven individual aspects of the modules. The findings suggest a strong synergy between the design features that users rated most highly and the key stages of Kolb's learning cycle. The use of simulations and videos to give the users an initial experience as well as the opportunity to "Have a go" and receive feedback in a safe environment were both considered particularly useful. In addition to providing an opportunity for reflection, many participants considered that the modules would enhance their roles as educators through: increasing their knowledge on various education topics and the required standards for medical training, and improving their skills in teaching and assessing students through practice and feedback and ultimately increasing their confidence. Kolb's theory-based design principle used for Web-based faculty development can support faculty to improve their skills and has impact on their role as educators. Grounding Web-based training in learning theory offers an effective and flexible approach for faculty development. ©Selma Omer, Sunhea Choi, Sarah Brien, Marcus Parry. Originally published in JMIR Medical Education (http://mededu.jmir.org), 27.09.2017.

Transportation life cycle assessment (LCA) synthesis : life cycle assessment learning module series.

DOT National Transportation Integrated Search

2015-03-12

The Life Cycle Assessment Learning Module Series is a set of narrated, self-advancing slideshows on : various topics related to environmental life cycle assessment (LCA). This research project produced the first 27 of such modules, which : are freely...

The Experiential Learning Cycle in Visual Design

ERIC Educational Resources Information Center

Arsoy, Aysu; Özad, Bahire Efe

2004-01-01

Experiential Learning Cycle has been applied to the Layout and Graphics Design in Computer Course provided by the Faculty of Communication and Media Studies to the students studying at the Public Relations and Advertising Department. It is hoped that by applying the Experiential Learning Cycle, the creativity and problem solving strategies of the…

Students' Understanding of Analogy after a Core (Chemical Observations, Representations, Experimentation) Learning Cycle, General Chemistry Experiment

ERIC Educational Resources Information Center

Avargil, Shirly; Bruce, Mitchell R. M.; Amar, Franc¸ois G.; Bruce, Alice E.

2015-01-01

Students' understanding about analogy was investigated after a CORE learning cycle general chemistry experiment. CORE (Chemical Observations, Representations, Experimentation) is a new three-phase learning cycle that involves (phase 1) guiding students through chemical observations while they consider a series of open-ended questions, (phase 2)…

Action research and millennials: Improving pedagogical approaches to encourage critical thinking.

PubMed

Erlam, Gwen; Smythe, Liz; Wright-St Clair, Valerie

2018-02-01

This article examines the effects of intergenerational diversity on pedagogical practice in nursing education. While generational cohorts are not entirely homogenous, certain generational features do emerge. These features may require alternative approaches in educational design in order to maximize learning for millennial students. Action research is employed with undergraduate millennial nursing students (n=161) who are co-researchers in that they are asked for changes in current simulation environments which will improve their learning in the areas of knowledge acquisition, skill development, critical thinking, and communication. These changes are put into place and a re-evaluation of the effectiveness of simulation progresses through three action cycles. Millennials, due to a tendency for risk aversion, may gravitate towards more supportive learning environments which allow for free access to educators. This tendency is mitigated by the educator modeling expected behaviors, followed by student opportunity to repeat the behavior. Millennials tend to prefer to work in teams, see tangible improvement, and employ strategies to improve inter-professional communication. This research highlights the need for nurse educators working in simulation to engage in critical discourse regarding the adequacy and effectiveness of current pedagogy informing simulation design. Pedagogical approaches which maximize repetition, modeling, immersive feedback, and effective communication tend to be favored by millennial students. Copyright © 2017 Elsevier Ltd. All rights reserved.

Multi-feature machine learning model for automatic segmentation of green fractional vegetation cover for high-throughput field phenotyping.

PubMed

Sadeghi-Tehran, Pouria; Virlet, Nicolas; Sabermanesh, Kasra; Hawkesford, Malcolm J

2017-01-01

Accurately segmenting vegetation from the background within digital images is both a fundamental and a challenging task in phenotyping. The performance of traditional methods is satisfactory in homogeneous environments, however, performance decreases when applied to images acquired in dynamic field environments. In this paper, a multi-feature learning method is proposed to quantify vegetation growth in outdoor field conditions. The introduced technique is compared with the state-of the-art and other learning methods on digital images. All methods are compared and evaluated with different environmental conditions and the following criteria: (1) comparison with ground-truth images, (2) variation along a day with changes in ambient illumination, (3) comparison with manual measurements and (4) an estimation of performance along the full life cycle of a wheat canopy. The method described is capable of coping with the environmental challenges faced in field conditions, with high levels of adaptiveness and without the need for adjusting a threshold for each digital image. The proposed method is also an ideal candidate to process a time series of phenotypic information throughout the crop growth acquired in the field. Moreover, the introduced method has an advantage that it is not limited to growth measurements only but can be applied on other applications such as identifying weeds, diseases, stress, etc.

The Organizational Learning Cycle. How We Can Learn Collectively.

ERIC Educational Resources Information Center

Dixon, Nancy

This book, which is designed for individuals interested in changing and developing their organizations, examines the organizational learning cycle and ways of learning collectively. Among the topics discussed in the book's nine chapters are the following: (1) changing nature of work and organizational learning; (2) theoretical framework of…

Effectiveness and Student Perceptions of an Active Learning Activity Using a Headline News Story to Enhance In-Class Learning of Cell Cycle Regulation

ERIC Educational Resources Information Center

Dirks-Naylor, Amie J.

2016-01-01

An active learning activity was used to engage students and enhance in-class learning of cell cycle regulation in a PharmD level integrated biological sciences course. The aim of the present study was to determine the effectiveness and perception of the in-class activity. After completion of a lecture on the topic of cell cycle regulation,…

Varying irrelevant phonetic features hinders learning of the feature being trained.

PubMed

Antoniou, Mark; Wong, Patrick C M

2016-01-01

Learning to distinguish nonnative words that differ in a critical phonetic feature can be difficult. Speech training studies typically employ methods that explicitly direct the learner's attention to the relevant nonnative feature to be learned. However, studies on vision have demonstrated that perceptual learning may occur implicitly, by exposing learners to stimulus features, even if they are irrelevant to the task, and it has recently been suggested that this task-irrelevant perceptual learning framework also applies to speech. In this study, subjects took part in a seven-day training regimen to learn to distinguish one of two nonnative features, namely, voice onset time or lexical tone, using explicit training methods consistent with most speech training studies. Critically, half of the subjects were exposed to stimuli that varied not only in the relevant feature, but in the irrelevant feature as well. The results showed that subjects who were trained with stimuli that varied in the relevant feature and held the irrelevant feature constant achieved the best learning outcomes. Varying both features hindered learning and generalization to new stimuli.

Learning Sparse Feature Representations using Probabilistic Quadtrees and Deep Belief Nets

DTIC Science & Technology

2015-04-24

Feature Representations usingProbabilistic Quadtrees and Deep Belief Nets Learning sparse feature representations is a useful instru- ment for solving an...novel framework for the classifi cation of handwritten digits that learns sparse representations using probabilistic quadtrees and Deep Belief Nets... Learning Sparse Feature Representations usingProbabilistic Quadtrees and Deep Belief Nets Report Title Learning sparse feature representations is a useful

Science Learning Cycle Method to Enhance the Conceptual Understanding and the Learning Independence on Physics Learning

ERIC Educational Resources Information Center

Sulisworo, Dwi; Sutadi, Novitasari

2017-01-01

There have been many studies related to the implementation of cooperative learning. However, there are still many problems in school related to the learning outcomes on science lesson, especially in physics. The aim of this study is to observe the application of science learning cycle (SLC) model on improving scientific literacy for secondary…

The College Science Learning Cycle: An Instructional Model for Reformed Teaching

PubMed Central

Withers, Michelle

2016-01-01

Finding the time for developing or locating new class materials is one of the biggest barriers for instructors reforming their teaching approaches. Even instructors who have taken part in training workshops may feel overwhelmed by the task of transforming passive lecture content to engaging learning activities. Learning cycles have been instrumental in helping K–12 science teachers design effective instruction for decades. This paper introduces the College Science Learning Cycle adapted from the popular Biological Sciences Curriculum Study 5E to help science, technology, engineering, and mathematics faculty develop course materials to support active, student-centered teaching approaches in their classrooms. The learning cycle is embedded in backward design, a learning outcomes–oriented instructional design approach, and is accompanied by resources and examples to help faculty transform their teaching in a time-efficient manner. PMID:27909030

Features: Real-Time Adaptive Feature and Document Learning for Web Search.

ERIC Educational Resources Information Center

Chen, Zhixiang; Meng, Xiannong; Fowler, Richard H.; Zhu, Binhai

2001-01-01

Describes Features, an intelligent Web search engine that is able to perform real-time adaptive feature (i.e., keyword) and document learning. Explains how Features learns from users' document relevance feedback and automatically extracts and suggests indexing keywords relevant to a search query, and learns from users' keyword relevance feedback…

Incorporating Young Adult Literature into the 5E Learning Cycle

ERIC Educational Resources Information Center

Niederberger, Susan

2009-01-01

Since the U.S.S.R. released Sputnik I into space in 1957, American science teachers have been focused on preparing scientifically literate students. New instructional approaches have emerged, with the 5E learning cycle being one of the more popular methods used. The 5E learning cycle gets its name from its five stages: Engage, Explore, Explain,…

Piaget and Organic Chemistry: Teaching Introductory Organic Chemistry through Learning Cycles

NASA Astrophysics Data System (ADS)

Libby, R. Daniel

1995-07-01

This paper describes the first application of the Piaget-based learning cycle technique (Atkin & Karplus, Sci. Teach. 1962, 29, 45-51) to an introductory organic chemistry course. It also presents the step-by-step process used to convert a lecture course into a discussion-based active learning course. The course is taught in a series of learning cycles. A learning cycle is a three phase process that provides opportunities for students to explore new material and work with an instructor to recognize logical patterns in data, and devise and test hypotheses. In this application, the first phase, exploration, involves out-of-class student evaluation of data in attempts to identify significant trends and develop hypotheses that might explain the trends in terms of fundamental scientific principles. In the second phase, concept invention, the students and instructor work together in-class to evaluate student hypotheses and find concepts that work best in explaining the data. The third phase, application, is an out-of-class application of the concept to new situations. The development of learning cycles from lecture notes is presented as an 8 step procedure. The process involves revaluation and restructuring of the course material to maintain a continuity of concept development according to the instructor's logic, dividing topics into individual concepts or techniques, and refocusing the presentation in terms of large numbers of examples that can serve as data for students in their exploration and application activities. A sample learning cycle and suggestions for ways of limited implementation of learning cycles into existing courses are also provided.

Benefits for Voice Learning Caused by Concurrent Faces Develop over Time.

PubMed

Zäske, Romi; Mühl, Constanze; Schweinberger, Stefan R

2015-01-01

Recognition of personally familiar voices benefits from the concurrent presentation of the corresponding speakers' faces. This effect of audiovisual integration is most pronounced for voices combined with dynamic articulating faces. However, it is unclear if learning unfamiliar voices also benefits from audiovisual face-voice integration or, alternatively, is hampered by attentional capture of faces, i.e., "face-overshadowing". In six study-test cycles we compared the recognition of newly-learned voices following unimodal voice learning vs. bimodal face-voice learning with either static (Exp. 1) or dynamic articulating faces (Exp. 2). Voice recognition accuracies significantly increased for bimodal learning across study-test cycles while remaining stable for unimodal learning, as reflected in numerical costs of bimodal relative to unimodal voice learning in the first two study-test cycles and benefits in the last two cycles. This was independent of whether faces were static images (Exp. 1) or dynamic videos (Exp. 2). In both experiments, slower reaction times to voices previously studied with faces compared to voices only may result from visual search for faces during memory retrieval. A general decrease of reaction times across study-test cycles suggests facilitated recognition with more speaker repetitions. Overall, our data suggest two simultaneous and opposing mechanisms during bimodal face-voice learning: while attentional capture of faces may initially impede voice learning, audiovisual integration may facilitate it thereafter.

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.

Developing mathematical practices through reflection cycles

NASA Astrophysics Data System (ADS)

Reinholz, Daniel L.

2016-09-01

This paper focuses on reflection in learning mathematical practices. While there is a long history of research on reflection in mathematics, it has focused primarily on the development of conceptual understanding. Building on notion of learning as participation in social practices, this paper broadens the theory of reflection in mathematics learning. To do so, it introduces the concept of reflection cycles. Each cycle begins with prospective reflection, which guides one's actions during an experience, and ends with retrospective reflection, which consolidates the experience and informs the next reflection cycle. Using reflection cycles as an organizing framework, this paper synthesizes the literature on reflective practices at a variety of levels: (1) metacognition, (2) self-assessment, (3) noticing, and (4) lifelong learning. These practices represent a spectrum of reflection, ranging from the micro level (1) to macro level (4).

More than one kind of inference: re-examining what's learned in feature inference and classification.

PubMed

Sweller, Naomi; Hayes, Brett K

2010-08-01

Three studies examined how task demands that impact on attention to typical or atypical category features shape the category representations formed through classification learning and inference learning. During training categories were learned via exemplar classification or by inferring missing exemplar features. In the latter condition inferences were made about missing typical features alone (typical feature inference) or about both missing typical and atypical features (mixed feature inference). Classification and mixed feature inference led to the incorporation of typical and atypical features into category representations, with both kinds of features influencing inferences about familiar (Experiments 1 and 2) and novel (Experiment 3) test items. Those in the typical inference condition focused primarily on typical features. Together with formal modelling, these results challenge previous accounts that have characterized inference learning as producing a focus on typical category features. The results show that two different kinds of inference learning are possible and that these are subserved by different kinds of category representations.

Predicting Failure Under Laboratory Conditions: Learning the Physics of Slow Frictional Slip and Dynamic Failure

NASA Astrophysics Data System (ADS)

Rouet-Leduc, B.; Hulbert, C.; Riviere, J.; Lubbers, N.; Barros, K.; Marone, C.; Johnson, P. A.

2016-12-01

Forecasting failure is a primary goal in diverse domains that include earthquake physics, materials science, nondestructive evaluation of materials and other engineering applications. Due to the highly complex physics of material failure and limitations on gathering data in the failure nucleation zone, this goal has often appeared out of reach; however, recent advances in instrumentation sensitivity, instrument density and data analysis show promise toward forecasting failure times. Here, we show that we can predict frictional failure times of both slow and fast stick slip failure events in the laboratory. This advance is made possible by applying a machine learning approach known as Random Forests1(RF) to the continuous acoustic emission (AE) time series recorded by detectors located on the fault blocks. The RF is trained using a large number of statistical features derived from the AE time series signal. The model is then applied to data not previously analyzed. Remarkably, we find that the RF method predicts upcoming failure time far in advance of a stick slip event, based only on a short time window of data. Further, the algorithm accurately predicts the time of the beginning and end of the next slip event. The predicted time improves as failure is approached, as other data features add to prediction. Our results show robust predictions of slow and dynamic failure based on acoustic emissions from the fault zone throughout the laboratory seismic cycle. The predictions are based on previously unidentified tremor-like acoustic signals that occur during stress build up and the onset of macroscopic frictional weakening. We suggest that the tremor-like signals carry information about fault zone processes and allow precise predictions of failure at any time in the slow slip or stick slip cycle2. If the laboratory experiments represent Earth frictional conditions, it could well be that signals are being missed that contain highly useful predictive information. 1Breiman, L. Random forests. Machine Learning 45, 5-32 (2001). 2Rouet-Leduc, B. C. Hulbert, N. Lubbers, K. Barros and P. A. Johnson, Learning the physics of failure, in review (2016).

From the field to classrooms: Scientists and educators collaborating to develop K-12 lessons on arctic carbon cycling and climate change that align with Next Generation Science Standards, and informal outreach programs that bring authentic data to informal audiences.

NASA Astrophysics Data System (ADS)

Brinker, R.; Cory, R. M.

2014-12-01

Next Generation Science Standards (NGSS) calls for students across grade levels to understand climate change and its impacts. To achieve this goal, the NSF-sponsored PolarTREC program paired an educator with scientists studying carbon cycling in the Arctic. The data collection and fieldwork performed by the team will form the basis of hands-on science learning in the classroom and will be incorporated into informal outreach sessions in the community. Over a 16-day period, the educator was stationed at Toolik Field Station in the High Arctic. (Toolik is run by the University of Alaska, Fairbanks, Institute of Arctic Biology.) She participated in a project that analyzed the effects of sunlight and microbial content on carbon production in Artic watersheds. Data collected will be used to introduce the following NGSS standards into the middle-school science curriculum: 1) Construct a scientific explanation based on evidence. 2) Develop a model to explain cycling of water. 3) Develop and use a model to describe phenomena. 4) Analyze and interpret data. 5) A change in one system causes and effect in other systems. Lessons can be telescoped to meet the needs of classrooms in higher or lower grades. Through these activities, students will learn strategies to model an aspect of carbon cycling, interpret authentic scientific data collected in the field, and conduct geoscience research on carbon cycling. Community outreach sessions are also an effective method to introduce and discuss the importance of geoscience education. Informal discussions of firsthand experience gained during fieldwork can help communicate to a lay audience the biological, physical, and chemical aspects of the arctic carbon cycle and the impacts of climate change on these features. Outreach methods will also include novel use of online tools to directly connect audiences with scientists in an effective and time-efficient manner.

Associative learning in baboons (Papio papio) and humans (Homo sapiens): species differences in learned attention to visual features.

PubMed

Fagot, J; Kruschke, J K; Dépy, D; Vauclair, J

1998-10-01

We examined attention shifting in baboons and humans during the learning of visual categories. Within a conditional matching-to-sample task, participants of the two species sequentially learned two two-feature categories which shared a common feature. Results showed that humans encoded both features of the initially learned category, but predominantly only the distinctive feature of the subsequently learned category. Although baboons initially encoded both features of the first category, they ultimately retained only the distinctive features of each category. Empirical data from the two species were analyzed with the 1996 ADIT connectionist model of Kruschke. ADIT fits the baboon data when the attentional shift rate is zero, and the human data when the attentional shift rate is not zero. These empirical and modeling results suggest species differences in learned attention to visual features.

European Management Learning: A Cross-Cultural Interpretation of Kolb's Learning Cycle.

ERIC Educational Resources Information Center

Jackson, Terence

1995-01-01

A survey of a French business school with multinational branch campuses received 123 usable responses supporting the proposition that cross-cultural differences exist within each of Kolb's learning cycle stages. National profiles of learning preferences were developed for French, German, Spanish, Anglo-Irish, and Eastern European learners. (SK)

[Stimulation of D1-receptors improves passive avoidance learning of female rats during ovary cycle].

PubMed

Fedotova, Iu O; Sapronov, N S

2012-01-01

The involvement of D1-receptors in learning/memory processes during ovary cycle was assessed in the adult female rats. SKF-38393 (0,1 mg/kg, i.p.), D1-receptor agonist and SCH-23390 (0,1 mg/kg, i.p.), D1-receptor antagonist were injected chronically to adult female rats. Learning of these animals was assessed in different models: passive avoidance performance and Morris water maze. Chronic SKF-3839 administration to females resulted in the appearance of the passive avoidance performance in proestrous and estrous, as distinct from the control animals, but failed to change the dynamics of spatial learning in Morris water maze. Chronic SCH-23390 administration similarly impaired non-spatial and spatial learning in females during all phases of ovary cycle. The results of the study suggest modulating role of D1-receptors in learning/memory processes during ovary cycle in the adult female rats.

VLSI realization of learning vector quantization with hardware/software co-design for different applications

NASA Astrophysics Data System (ADS)

An, Fengwei; Akazawa, Toshinobu; Yamasaki, Shogo; Chen, Lei; Jürgen Mattausch, Hans

2015-04-01

This paper reports a VLSI realization of learning vector quantization (LVQ) with high flexibility for different applications. It is based on a hardware/software (HW/SW) co-design concept for on-chip learning and recognition and designed as a SoC in 180 nm CMOS. The time consuming nearest Euclidean distance search in the LVQ algorithm’s competition layer is efficiently implemented as a pipeline with parallel p-word input. Since neuron number in the competition layer, weight values, input and output number are scalable, the requirements of many different applications can be satisfied without hardware changes. Classification of a d-dimensional input vector is completed in n × \\lceil d/p \\rceil + R clock cycles, where R is the pipeline depth, and n is the number of reference feature vectors (FVs). Adjustment of stored reference FVs during learning is done by the embedded 32-bit RISC CPU, because this operation is not time critical. The high flexibility is verified by the application of human detection with different numbers for the dimensionality of the FVs.

The Effect of Teaching Model ‘Learning Cycles 5E’ toward Students’ Achievement in Learning Mathematic at X Years Class SMA Negeri 1 Banuhampu 2013/2014 Academic Year

NASA Astrophysics Data System (ADS)

Yeni, N.; Suryabayu, E. P.; Handayani, T.

2017-02-01

Based on the survey showed that mathematics teacher still dominated in teaching and learning process. The process of learning is centered on the teacher while the students only work based on instructions provided by the teacher without any creativity and activities that stimulate students to explore their potential. Realized the problem above the writer interested in finding the solution by applying teaching model ‘Learning Cycles 5E’. The purpose of his research is to know whether teaching model ‘Learning Cycles 5E’ is better than conventional teaching in teaching mathematic. The type of the research is quasi experiment by Randomized Control test Group Only Design. The population in this research were all X years class students. The sample is chosen randomly after doing normality, homogeneity test and average level of students’ achievement. As the sample of this research was X.7’s class as experiment class used teaching model learning cycles 5E and X.8’s class as control class used conventional teaching. The result showed us that the students achievement in the class that used teaching model ‘Learning Cycles 5E’ is better than the class which did not use the model.

Collaborative Learning in the Texas Medicaid 1115 Waiver Program.

PubMed

Revere, Lee; Semaan, Adele; Lievsay, Nicole; Hall, Jessica; Wang, Zheng M; Begley, Charles

The Texas Medicaid 1115 Transformation Waiver reforms the state's safety net systems by creating a Delivery System Reform Incentive Payment incentive pool for innovative healthcare delivery. The Waiver supports the design and implementation of transformative projects. As part of the Waiver requirements, regions created Learning Collaboratives to collaborate on project implementation and outcomes. This paper describes the experience of one region in adapting the Institute for Healthcare Improvement Breakthrough Series (IHI BTS) model, as a framework for their Learning Collaborative. Implementation of the Learning Collaborative was systematic, multidimensional, and regularly evaluated. Some features of the IHI model were adapted, specifically longer Plan-Do-Check-Act cycles and the lack of a single clinical focus. This experience demonstrates the ability of a region to improve health from a more diverse perspective than the traditional IHI BTS Collaboratives. Within the region, organizations are connecting, agencies are building continuums of care, and stakeholders are involved in healthcare delivery. The initial stages show a remarkable increase in communication and enhanced relationships between providers. At the end of the 5-year Waiver, evaluation of the impact of the regional and cohort Learning Collaboratives will determine how well the adapted IHI BTS model facilitated improvements in the community's health.

Identification of fuel cycle simulator functionalities for analysis of transition to a new fuel cycle

DOE PAGES

Brown, Nicholas R.; Carlsen, Brett W.; Dixon, Brent W.; ...

2016-06-09

Dynamic fuel cycle simulation tools are intended to model holistic transient nuclear fuel cycle scenarios. As with all simulation tools, fuel cycle simulators require verification through unit tests, benchmark cases, and integral tests. Model validation is a vital aspect as well. Although compara-tive studies have been performed, there is no comprehensive unit test and benchmark library for fuel cycle simulator tools. The objective of this paper is to identify the must test functionalities of a fuel cycle simulator tool within the context of specific problems of interest to the Fuel Cycle Options Campaign within the U.S. Department of Energy smore » Office of Nuclear Energy. The approach in this paper identifies the features needed to cover the range of promising fuel cycle options identified in the DOE-NE Fuel Cycle Evaluation and Screening (E&S) and categorizes these features to facilitate prioritization. Features were categorized as essential functions, integrating features, and exemplary capabilities. One objective of this paper is to propose a library of unit tests applicable to each of the essential functions. Another underlying motivation for this paper is to encourage an international dialog on the functionalities and standard test methods for fuel cycle simulator tools.« less

Learning about the internal structure of categories through classification and feature inference.

PubMed

Jee, Benjamin D; Wiley, Jennifer

2014-01-01

Previous research on category learning has found that classification tasks produce representations that are skewed toward diagnostic feature dimensions, whereas feature inference tasks lead to richer representations of within-category structure. Yet, prior studies often measure category knowledge through tasks that involve identifying only the typical features of a category. This neglects an important aspect of a category's internal structure: how typical and atypical features are distributed within a category. The present experiments tested the hypothesis that inference learning results in richer knowledge of internal category structure than classification learning. We introduced several new measures to probe learners' representations of within-category structure. Experiment 1 found that participants in the inference condition learned and used a wider range of feature dimensions than classification learners. Classification learners, however, were more sensitive to the presence of atypical features within categories. Experiment 2 provided converging evidence that classification learners were more likely to incorporate atypical features into their representations. Inference learners were less likely to encode atypical category features, even in a "partial inference" condition that focused learners' attention on the feature dimensions relevant to classification. Overall, these results are contrary to the hypothesis that inference learning produces superior knowledge of within-category structure. Although inference learning promoted representations that included a broad range of category-typical features, classification learning promoted greater sensitivity to the distribution of typical and atypical features within categories.

Implementation of ICARE learning model using visualization animation on biotechnology course

NASA Astrophysics Data System (ADS)

Hidayat, Habibi

2017-12-01

ICARE is a learning model that directly ensure the students to actively participate in the learning process using animation media visualization. ICARE have five key elements of learning experience from children and adult that is introduction, connection, application, reflection and extension. The use of Icare system to ensure that participants have opportunity to apply what have been they learned. So that, the message delivered by lecture to students can be understood and recorded by students in a long time. Learning model that was deemed capable of improving learning outcomes and interest to learn in following learning process Biotechnology with applying the ICARE learning model using visualization animation. This learning model have been giving motivation to participate in the learning process and learning outcomes obtained becomes more increased than before. From the results of student learning in subjects Biotechnology by applying the ICARE learning model using Visualization Animation can improving study results of student from the average value of middle test amounted to 70.98 with the percentage of 75% increased value of final test to be 71.57 with the percentage of 68.63%. The interest to learn from students more increasing visits of student activities at each cycle, namely the first cycle obtained average value by 33.5 with enough category. The second cycle is obtained an average value of 36.5 to good category and third cycle the average value of 36.5 with a student activity to good category.

Improvement of Learning Process and Learning Outcomes in Physics Learning by Using Collaborative Learning Model of Group Investigation at High School (Grade X, SMAN 14 Jakarta)

ERIC Educational Resources Information Center

Astra, I. Made; Wahyuni, Citra; Nasbey, Hadi

2015-01-01

The aim of this research is to improve the quality of physics learning through application of collaborative learning of group investigation at grade X MIPA 2 SMAN 14 Jakarta. The method used in this research is classroom action research. This research consisted of three cycles was conducted from April to May in 2014. Each cycle consists of…

An implementation of 7E Learning Cycle Model to Improve Student Self-esteem

NASA Astrophysics Data System (ADS)

Firdaus, F.; Priatna, N.; Suhendra, S.

2017-09-01

One of the affective factors that affect student learning outcomes is student self-esteem in mathematics, learning achievement and self-esteem influence each other. The purpose of this research is to know whether self-esteem students who get 7E learning cycle model is better than students who get conventional learning. This research method is a non-control group design. Based on the results obtained that the normal and homogeneous data so that the t test and from the test results showed there are significant differences in self-esteem students learning with 7E learning cycle model compared with students who get conventional learning. The implications of the results of this study are that students should be required to conduct many discussions, presentations and evaluations on classroom activities as these learning stages can improve students’ self-esteem especially pride in the results achieved.

Learning Achievement Improvement Efforts Course Learn and Learning Using the Jigsaw Method and Card Media in STKIP PGRI Ngawi 2014/2015 Academic Year

ERIC Educational Resources Information Center

Haryono

2015-01-01

Subject Teaching and Learning is a basic educational courses that must be taken by all student teachers. Class Action Research aims to improve student achievement Teaching and Learning course by applying Jigsaw and media cards. Research procedures using Classroom Action Research (CAR) with multiple cycles. Each cycle includes four phases:…

Simultaneous Local Binary Feature Learning and Encoding for Homogeneous and Heterogeneous Face Recognition.

PubMed

Lu, Jiwen; Erin Liong, Venice; Zhou, Jie

2017-08-09

In this paper, we propose a simultaneous local binary feature learning and encoding (SLBFLE) approach for both homogeneous and heterogeneous face recognition. Unlike existing hand-crafted face descriptors such as local binary pattern (LBP) and Gabor features which usually require strong prior knowledge, our SLBFLE is an unsupervised feature learning approach which automatically learns face representation from raw pixels. Unlike existing binary face descriptors such as the LBP, discriminant face descriptor (DFD), and compact binary face descriptor (CBFD) which use a two-stage feature extraction procedure, our SLBFLE jointly learns binary codes and the codebook for local face patches so that discriminative information from raw pixels from face images of different identities can be obtained by using a one-stage feature learning and encoding procedure. Moreover, we propose a coupled simultaneous local binary feature learning and encoding (C-SLBFLE) method to make the proposed approach suitable for heterogeneous face matching. Unlike most existing coupled feature learning methods which learn a pair of transformation matrices for each modality, we exploit both the common and specific information from heterogeneous face samples to characterize their underlying correlations. Experimental results on six widely used face datasets are presented to demonstrate the effectiveness of the proposed method.

The surprisingly high human efficiency at learning to recognize faces

PubMed Central

Peterson, Matthew F.; Abbey, Craig K.; Eckstein, Miguel P.

2009-01-01

We investigated the ability of humans to optimize face recognition performance through rapid learning of individual relevant features. We created artificial faces with discriminating visual information heavily concentrated in single features (nose, eyes, chin or mouth). In each of 2500 learning blocks a feature was randomly selected and retained over the course of four trials, during which observers identified randomly sampled, noisy face images. Observers learned the discriminating feature through indirect feedback, leading to large performance gains. Performance was compared to a learning Bayesian ideal observer, resulting in unexpectedly high learning compared to previous studies with simpler stimuli. We explore various explanations and conclude that the higher learning measured with faces cannot be driven by adaptive eye movement strategies but can be mostly accounted for by suboptimalities in human face discrimination when observers are uncertain about the discriminating feature. We show that an initial bias of humans to use specific features to perform the task even though they are informed that each of four features is equally likely to be the discriminatory feature would lead to seemingly supra-optimal learning. We also examine the possibility of inefficient human integration of visual information across the spatially distributed facial features. Together, the results suggest that humans can show large performance improvement effects in discriminating faces as they learn to identify the feature containing the discriminatory information. PMID:19000918

Self-supervised ARTMAP.

PubMed

Amis, Gregory P; Carpenter, Gail A

2010-03-01

Computational models of learning typically train on labeled input patterns (supervised learning), unlabeled input patterns (unsupervised learning), or a combination of the two (semi-supervised learning). In each case input patterns have a fixed number of features throughout training and testing. Human and machine learning contexts present additional opportunities for expanding incomplete knowledge from formal training, via self-directed learning that incorporates features not previously experienced. This article defines a new self-supervised learning paradigm to address these richer learning contexts, introducing a neural network called self-supervised ARTMAP. Self-supervised learning integrates knowledge from a teacher (labeled patterns with some features), knowledge from the environment (unlabeled patterns with more features), and knowledge from internal model activation (self-labeled patterns). Self-supervised ARTMAP learns about novel features from unlabeled patterns without destroying partial knowledge previously acquired from labeled patterns. A category selection function bases system predictions on known features, and distributed network activation scales unlabeled learning to prediction confidence. Slow distributed learning on unlabeled patterns focuses on novel features and confident predictions, defining classification boundaries that were ambiguous in the labeled patterns. Self-supervised ARTMAP improves test accuracy on illustrative low-dimensional problems and on high-dimensional benchmarks. Model code and benchmark data are available from: http://techlab.eu.edu/SSART/. Copyright 2009 Elsevier Ltd. All rights reserved.

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

Brown, Nicholas R.; Carlsen, Brett W.; Dixon, Brent W.

Dynamic fuel cycle simulation tools are intended to model holistic transient nuclear fuel cycle scenarios. As with all simulation tools, fuel cycle simulators require verification through unit tests, benchmark cases, and integral tests. Model validation is a vital aspect as well. Although compara-tive studies have been performed, there is no comprehensive unit test and benchmark library for fuel cycle simulator tools. The objective of this paper is to identify the must test functionalities of a fuel cycle simulator tool within the context of specific problems of interest to the Fuel Cycle Options Campaign within the U.S. Department of Energy smore » Office of Nuclear Energy. The approach in this paper identifies the features needed to cover the range of promising fuel cycle options identified in the DOE-NE Fuel Cycle Evaluation and Screening (E&S) and categorizes these features to facilitate prioritization. Features were categorized as essential functions, integrating features, and exemplary capabilities. One objective of this paper is to propose a library of unit tests applicable to each of the essential functions. Another underlying motivation for this paper is to encourage an international dialog on the functionalities and standard test methods for fuel cycle simulator tools.« less

Joint Feature Selection and Classification for Multilabel Learning.

PubMed

Huang, Jun; Li, Guorong; Huang, Qingming; Wu, Xindong

2018-03-01

Multilabel learning deals with examples having multiple class labels simultaneously. It has been applied to a variety of applications, such as text categorization and image annotation. A large number of algorithms have been proposed for multilabel learning, most of which concentrate on multilabel classification problems and only a few of them are feature selection algorithms. Current multilabel classification models are mainly built on a single data representation composed of all the features which are shared by all the class labels. Since each class label might be decided by some specific features of its own, and the problems of classification and feature selection are often addressed independently, in this paper, we propose a novel method which can perform joint feature selection and classification for multilabel learning, named JFSC. Different from many existing methods, JFSC learns both shared features and label-specific features by considering pairwise label correlations, and builds the multilabel classifier on the learned low-dimensional data representations simultaneously. A comparative study with state-of-the-art approaches manifests a competitive performance of our proposed method both in classification and feature selection for multilabel learning.

An Ontological Representation of Learning Objects and Learning Designs as Codified Knowledge

ERIC Educational Resources Information Center

Sanchez-Alonso, Salvador; Frosch-Wilke, Dirk

2005-01-01

Purpose: The aim of this paper is discussing about the similarities between the life cycle of knowledge management and the processes in which learning objects are created, evaluated and used. Design/methodology/approach: The paper describes LO and learning designs and depicts their integration into the knowledge life cycle (KLC) of the KMCI,…

Deformable MR Prostate Segmentation via Deep Feature Learning and Sparse Patch Matching

PubMed Central

Guo, Yanrong; Gao, Yaozong

2016-01-01

Automatic and reliable segmentation of the prostate is an important but difficult task for various clinical applications such as prostate cancer radiotherapy. The main challenges for accurate MR prostate localization lie in two aspects: (1) inhomogeneous and inconsistent appearance around prostate boundary, and (2) the large shape variation across different patients. To tackle these two problems, we propose a new deformable MR prostate segmentation method by unifying deep feature learning with the sparse patch matching. First, instead of directly using handcrafted features, we propose to learn the latent feature representation from prostate MR images by the stacked sparse auto-encoder (SSAE). Since the deep learning algorithm learns the feature hierarchy from the data, the learned features are often more concise and effective than the handcrafted features in describing the underlying data. To improve the discriminability of learned features, we further refine the feature representation in a supervised fashion. Second, based on the learned features, a sparse patch matching method is proposed to infer a prostate likelihood map by transferring the prostate labels from multiple atlases to the new prostate MR image. Finally, a deformable segmentation is used to integrate a sparse shape model with the prostate likelihood map for achieving the final segmentation. The proposed method has been extensively evaluated on the dataset that contains 66 T2-wighted prostate MR images. Experimental results show that the deep-learned features are more effective than the handcrafted features in guiding MR prostate segmentation. Moreover, our method shows superior performance than other state-of-the-art segmentation methods. PMID:26685226

The effects of traditional learning and a learning cycle inquiry learning strategy on students' science achievement and attitudes toward elementary science

NASA Astrophysics Data System (ADS)

Ebrahim, Ali

The purpose of this study is to examine the impact of two instructional methods on students' academic achievement and attitudes toward elementary science in the State of Kuwait: traditional teaching method and the 4-E learning cycle inquiry teaching method. The subjects were 111 students from four intact 4th grade classes. The experiment group (n = 56) received the learning cycle instruction while the control group (n = 55) received a more traditional approach over a four week period. The same female teacher taught the experimental and control groups for boys and a different female teacher taught experimental and control groups for girls. The dependent variables were measured through the use of: (1) a science achievement test to assess student achievement; and (2) an attitude survey to measure students' attitudes toward science. Quantitative data were collected on students' pre- and post-treatment achievement and attitudes measures. The two way MANOVA reveals that: the 4-E learning cycle instructional method produces significantly greater achievement and attitudes among fourth grade science students than the traditional teaching approach F (2, 93) = 19.765, (P = .000), corresponding to Wilks' Lambda = .702 with an effect size of .298 and a power of 1. In light of these findings, it is therefore suggested that students can achieve greater and have higher science attitudes when the 4-E learning cycle is used. In addition, these findings support the notion that effective instruction in teaching science, such as the 4-E learning cycle instruction, should be proposed and implemented in elementary schools.

Attentional Bias in Human Category Learning: The Case of Deep Learning.

PubMed

Hanson, Catherine; Caglar, Leyla Roskan; Hanson, Stephen José

2018-01-01

Category learning performance is influenced by both the nature of the category's structure and the way category features are processed during learning. Shepard (1964, 1987) showed that stimuli can have structures with features that are statistically uncorrelated (separable) or statistically correlated (integral) within categories. Humans find it much easier to learn categories having separable features, especially when attention to only a subset of relevant features is required, and harder to learn categories having integral features, which require consideration of all of the available features and integration of all the relevant category features satisfying the category rule (Garner, 1974). In contrast to humans, a single hidden layer backpropagation (BP) neural network has been shown to learn both separable and integral categories equally easily, independent of the category rule (Kruschke, 1993). This "failure" to replicate human category performance appeared to be strong evidence that connectionist networks were incapable of modeling human attentional bias. We tested the presumed limitations of attentional bias in networks in two ways: (1) by having networks learn categories with exemplars that have high feature complexity in contrast to the low dimensional stimuli previously used, and (2) by investigating whether a Deep Learning (DL) network, which has demonstrated humanlike performance in many different kinds of tasks (language translation, autonomous driving, etc.), would display human-like attentional bias during category learning. We were able to show a number of interesting results. First, we replicated the failure of BP to differentially process integral and separable category structures when low dimensional stimuli are used (Garner, 1974; Kruschke, 1993). Second, we show that using the same low dimensional stimuli, Deep Learning (DL), unlike BP but similar to humans, learns separable category structures more quickly than integral category structures. Third, we show that even BP can exhibit human like learning differences between integral and separable category structures when high dimensional stimuli (face exemplars) are used. We conclude, after visualizing the hidden unit representations, that DL appears to extend initial learning due to feature development thereby reducing destructive feature competition by incrementally refining feature detectors throughout later layers until a tipping point (in terms of error) is reached resulting in rapid asymptotic learning.

Analysis of critical thinking ability of VII grade students based on the mathematical anxiety level through learning cycle 7E model

NASA Astrophysics Data System (ADS)

Widyaningsih, E.; Waluya, S. B.; Kurniasih, A. W.

2018-03-01

This study aims to know mastery learning of students’ critical thinking ability with learning cycle 7E, determine whether the critical thinking ability of the students with learning cycle 7E is better than students’ critical thinking ability with expository model, and describe the students’ critical thinking phases based on the mathematical anxiety level. The method is mixed method with concurrent embedded. The population is VII grade students of SMP Negeri 3 Kebumen academic year 2016/2017. Subjects are determined by purposive sampling, selected two students from each level of mathematical anxiety. Data collection techniques include test, questionnaire, interview, and documentation. Quantitative data analysis techniques include mean test, proportion test, difference test of two means, difference test of two proportions and for qualitative data used Miles and Huberman model. The results show that: (1) students’ critical thinking ability with learning cycle 7E achieve mastery learning; (2) students’ critical thinking ability with learning cycle 7E is better than students’ critical thinking ability with expository model; (3) description of students’ critical thinking phases based on the mathematical anxiety level that is the lower the mathematical anxiety level, the subjects have been able to fulfil all of the indicators of clarification, assessment, inference, and strategies phases.

Upscaling Ameriflux observations to assess drought impacts on gross primary productivity across the Southwest

NASA Astrophysics Data System (ADS)

Barnes, M.; Moore, D. J.; Scott, R. L.; MacBean, N.; Ponce-Campos, G. E.; Breshears, D. D.

2017-12-01

Both satellite observations and eddy covariance estimates provide crucial information about the Earth's carbon, water and energy cycles. Continuous measurements from flux towers facilitate exploration of the exchange of carbon dioxide, water and energy between the land surface and the atmosphere at fine temporal and spatial scales, while satellite observations can fill in the large spatial gaps of in-situ measurements and provide long-term temporal continuity. The Southwest (Southwest United States and Northwest Mexico) and other semi-arid regions represent a key uncertainty in interannual variability in carbon uptake. Comparisons of existing global upscaled gross primary production (GPP) products with flux tower data at sites across the Southwest show widespread mischaracterization of seasonality in vegetation carbon uptake, resulting in large (up to 200%) errors in annual carbon uptake estimates. Here, remotely sensed and distributed meteorological inputs are used to upscale GPP estimates from 25 Ameriflux towers across the Southwest to the regional scale using a machine learning approach. Our random forest model incorporates two novel features that improve the spatial and temporal variability in GPP. First, we incorporate a multi-scalar drought index at multiple timescales to account for differential seasonality between ecosystem types. Second, our machine learning algorithm was trained on twenty five ecologically diverse sites to optimize both the monthly variability in and the seasonal cycle of GPP. The product and its components will be used to examine drought impacts on terrestrial carbon cycling across the Southwest including the effects of drought seasonality and on carbon uptake. Our spatially and temporally continuous upscaled GPP product drawing from both ground and satellite data over the Southwest region helps us understand linkages between the carbon and water cycles in semi-arid ecosystems and informs predictions of vegetation response to future climate conditions.

[Effect of agonist and antagonist of 5-HT(1A) receptors on learning in female rats during ovarian cycle].

PubMed

Fedotova, Iu O; Ordian, N E

2010-01-01

The involvement of 5-HT(1A) receptors in learning/memory processes during ovary cycle was assessed in the adult female rats. 8-OH-DPAT (0.05 mg/kg, s.c.), 5-HT(1A) receptor agonist and NAN-190 (0.1 mg/kg, i.p.), 5-HT(1A) receptor antagonist were injected chronically to adult female rats. Learning of these animals was assessed in different models: passive avoidance performance and Morris water maze. Chronic NAN-190 administration to females resulted in the appearance of the passive avoidance performance in proestrous and estrous, as distinct from the control animals, but failed to change the dynamics of spatial learning in Morris water maze. Chronic 8-OH-DPAT administration similarly impaired non-spatial and spatial learning in females during all phases of ovary cycle. The results of the study suggest modulating role of 5-HT(1A) receptors in learning/memory processes during ovary cycle in the adult female rats.

Questions, Curiosity and the Inquiry Cycle

ERIC Educational Resources Information Center

Casey, Leo

2014-01-01

This article discusses the conceptual relationship between questions, curiosity and learning as inquiry elaborated in the work of Chip Bruce and others as the Inquiry Cycle. The Inquiry Cycle describes learning in terms of a continuous dynamic of ask, investigate, create, discuss and reflect. Of these elements "ask" has a privileged…

The Learning Cycle and College Science Teaching.

ERIC Educational Resources Information Center

Barman, Charles R.; Allard, David W.

Originally developed in an elementary science program called the Science Curriculum Improvement Study, the learning cycle (LC) teaching approach involves students in an active learning process modeled on four elements of Jean Piaget's theory of cognitive development: physical experience, referring to the biological growth of the central nervous…

The Remedial Effect of a Biological Learning Game.

ERIC Educational Resources Information Center

Blum, Abraham

1979-01-01

Investigates the effectiveness of a structured learning game in overcoming learning difficulties encountered by Israeli students when studying the life cycles of fungi because of lack of structural conceptualization. The Fungi Life Cycle Game (FLCG) was used by undergraduate students enrolled in a phytopathology course. (HM)

Developing PK-12 Preservice Teachers' Skills for Understanding Data-Driven Instruction through Inquiry Learning

ERIC Educational Resources Information Center

Odom, Arthur Louis; Bell, Clare Valerie

2017-01-01

This article offers a description of how empirical experiences through the use of procedural knowledge can serve as the stage for the development of hypothetical concepts using the learning cycle, an inquiry teaching and learning method with a long history in science education. The learning cycle brings a unique epistemology by way of using…

Students' Critical Thinking Skills in Chemistry Learning Using Local Culture-Based 7E Learning Cycle Model

ERIC Educational Resources Information Center

Suardana, I. Nyoman; Redhana, I. Wayan; Sudiatmika, A. A. Istri Agung Rai; Selamat, I. Nyoman

2018-01-01

This research aimed at describing the effectiveness of the local culture-based 7E learning cycle model in improving students' critical thinking skills in chemistry learning. It was an experimental research with post-test only control group design. The population was the eleventh-grade students of senior high schools in Singaraja, Indonesia. The…

The Workplace Learning Cycle: A Problem-Based Curriculum Model for the Preparation of Workplace Learning Professionals

ERIC Educational Resources Information Center

O'Connor, Bridget N.

2004-01-01

Building on the conceptual foundations suggested in the previous two papers in this issue, this article describes the application of a workplace learning cycle theory to the construction of a curriculum for a graduate-level course of study in workplace education. As a way to prepare chief learning officers and heads of corporate universities, the…

[Influence of stimulation and blockade of α4β2 nicotinic acetylcholine receptors on learning of female rats in basic phases of ovary cycle].

PubMed

Fedotova, Iu O

2014-03-01

The present work was devoted to the comparative analysis of α4β2 nicotinic acetylcholine receptors (nAChRs) in learning/memory processes during ovary cycle in the adult female rats. RJR-2403 (1.0 mg/kg, i. p.), α4β2 nAChRs agonist and mecamylamine (1.0 mg/kg, i. p.), α4β2 nAChRs antagonist were injected chronically during 14 days. The processes of learning/memory were assessed in different models of learning: passive avoidance performance and Morris water maze. Chronic RJR-2403 administration to females improved the passive avoidance performance in proestrous and estrous as compared to the control animals. Also, RJR-2403 restored spatial learning of rats during proestrous phases in Morris water maze, and stimulated the dynamics of spatial learning during estrous phases. On the contrary, the chronic mecamylamine administration impaired non-spatial, and especially, spatial learning in females during key phases of ovary cycle. The results of the study suggest positive effect of α4β2 nAChRs stimulation in learning/memory processes during ovary cycle in the adult female rats.

The Relationship Between the Learning Style Perceptual Preferences of Urban Fourth Grade Children and the Acquisition of Selected Physical Science Concepts Through Learning Cycle Instructional Methodology.

NASA Astrophysics Data System (ADS)

Adams, Kenneth Mark

The purpose of this research was to investigate the relationship between the learning style perceptual preferences of fourth grade urban students and the attainment of selected physical science concepts for three simple machines as taught using learning cycle methodology. The sample included all fourth grade children from one urban elementary school (N = 91). The research design followed a quasi-experimental format with a single group, equivalent teacher demonstration and student investigation materials, and identical learning cycle instructional treatment. All subjects completed the Understanding Simple Machines Test (USMT) prior to instructional treatment, and at the conclusion of treatment to measure student concept attainment related to the pendulum, the lever and fulcrum, and the inclined plane. USMT pre and post-test scores, California Achievement Test (CAT-5) percentile scores, and Learning Style Inventory (LSI) standard scores for four perceptual elements for each subject were held in a double blind until completion of the USMT post-test. The hypothesis tested in this study was: Learning style perceptual preferences of fourth grade students as measured by the Dunn, Dunn, and Price Learning Style Inventory (LSI) are significant predictors of success in the acquisition of physical science concepts taught through use of the learning cycle. Analysis of pre and post USMT scores, 18.18 and 30.20 respectively, yielded a significant mean gain of +12.02. A controlled stepwise regression was employed to identify significant predictors of success on the USMT post-test from among USMT pre-test, four CAT-5 percentile scores, and four LSI perceptual standard scores. The CAT -5 Total Math and Total Reading accounted for 64.06% of the variance in the USMT post-test score. The only perceptual element to act as a significant predictor was the Kinesthetic standard score, accounting for 1.72% of the variance. The study revealed that learning cycle instruction does not appear to be sensitive to different perceptual preferences. Students with different preferences for auditory, visual, and tactile modalities, when learning, seem to benefit equally from learning cycle exposure. Increased use of a double blind for future learning styles research was recommended.

An open-source solution for advanced imaging flow cytometry data analysis using machine learning.

PubMed

Hennig, Holger; Rees, Paul; Blasi, Thomas; Kamentsky, Lee; Hung, Jane; Dao, David; Carpenter, Anne E; Filby, Andrew

2017-01-01

Imaging flow cytometry (IFC) enables the high throughput collection of morphological and spatial information from hundreds of thousands of single cells. This high content, information rich image data can in theory resolve important biological differences among complex, often heterogeneous biological samples. However, data analysis is often performed in a highly manual and subjective manner using very limited image analysis techniques in combination with conventional flow cytometry gating strategies. This approach is not scalable to the hundreds of available image-based features per cell and thus makes use of only a fraction of the spatial and morphometric information. As a result, the quality, reproducibility and rigour of results are limited by the skill, experience and ingenuity of the data analyst. Here, we describe a pipeline using open-source software that leverages the rich information in digital imagery using machine learning algorithms. Compensated and corrected raw image files (.rif) data files from an imaging flow cytometer (the proprietary .cif file format) are imported into the open-source software CellProfiler, where an image processing pipeline identifies cells and subcellular compartments allowing hundreds of morphological features to be measured. This high-dimensional data can then be analysed using cutting-edge machine learning and clustering approaches using "user-friendly" platforms such as CellProfiler Analyst. Researchers can train an automated cell classifier to recognize different cell types, cell cycle phases, drug treatment/control conditions, etc., using supervised machine learning. This workflow should enable the scientific community to leverage the full analytical power of IFC-derived data sets. It will help to reveal otherwise unappreciated populations of cells based on features that may be hidden to the human eye that include subtle measured differences in label free detection channels such as bright-field and dark-field imagery. Copyright © 2016 The Authors. Published by Elsevier Inc. All rights reserved.

Accounting for length-bias and selection effects in estimating the distribution of menstrual cycle length

PubMed Central

Lum, Kirsten J.; Sundaram, Rajeshwari; Louis, Thomas A.

2015-01-01

Prospective pregnancy studies are a valuable source of longitudinal data on menstrual cycle length. However, care is needed when making inferences of such renewal processes. For example, accounting for the sampling plan is necessary for unbiased estimation of the menstrual cycle length distribution for the study population. If couples can enroll when they learn of the study as opposed to waiting for the start of a new menstrual cycle, then due to length-bias, the enrollment cycle will be stochastically larger than the general run of cycles, a typical property of prevalent cohort studies. Furthermore, the probability of enrollment can depend on the length of time since a woman’s last menstrual period (a backward recurrence time), resulting in selection effects. We focus on accounting for length-bias and selection effects in the likelihood for enrollment menstrual cycle length, using a recursive two-stage approach wherein we first estimate the probability of enrollment as a function of the backward recurrence time and then use it in a likelihood with sampling weights that account for length-bias and selection effects. To broaden the applicability of our methods, we augment our model to incorporate a couple-specific random effect and time-independent covariate. A simulation study quantifies performance for two scenarios of enrollment probability when proper account is taken of sampling plan features. In addition, we estimate the probability of enrollment and the distribution of menstrual cycle length for the study population of the Longitudinal Investigation of Fertility and the Environment Study. PMID:25027273

A Multiobjective Sparse Feature Learning Model for Deep Neural Networks.

PubMed

Gong, Maoguo; Liu, Jia; Li, Hao; Cai, Qing; Su, Linzhi

2015-12-01

Hierarchical deep neural networks are currently popular learning models for imitating the hierarchical architecture of human brain. Single-layer feature extractors are the bricks to build deep networks. Sparse feature learning models are popular models that can learn useful representations. But most of those models need a user-defined constant to control the sparsity of representations. In this paper, we propose a multiobjective sparse feature learning model based on the autoencoder. The parameters of the model are learnt by optimizing two objectives, reconstruction error and the sparsity of hidden units simultaneously to find a reasonable compromise between them automatically. We design a multiobjective induced learning procedure for this model based on a multiobjective evolutionary algorithm. In the experiments, we demonstrate that the learning procedure is effective, and the proposed multiobjective model can learn useful sparse features.

Latitude Distribution of Sunspots: Analysis Using Sunspot Data and a Dynamo Model

NASA Astrophysics Data System (ADS)

Mandal, Sudip; Karak, Bidya Binay; Banerjee, Dipankar

2017-12-01

In this paper, we explore the evolution of sunspot latitude distribution and explore its relations with the cycle strength. With the progress of the solar cycle, the distributions in two hemispheres from mid-latitudes propagate toward the equator and then (before the usual solar minimum) these two distributions touch each other. By visualizing the evolution of the distributions in two hemispheres, we separate the solar cycles by excluding this hemispheric overlap. From these isolated solar cycles in two hemispheres, we generate latitude distributions for each cycle, starting from cycle 8 to cycle 23. We find that the parameters of these distributions, namely the central latitude (C), width (δ), and height (H), evolve with the cycle number, and they show some hemispheric asymmetries. Although the asymmetries in these parameters persist for a few successive cycles, they get corrected within a few cycles, and the new asymmetries appear again. In agreement with the previous study, we find that distribution parameters are correlated with the strengths of the cycles, although these correlations are significantly different in two hemispheres. The general trend features, i.e., (i) stronger cycles that begin sunspot eruptions at relatively higher latitudes, and (ii) stronger cycles that have wider bands of sunspot emergence latitudes, are confirmed when combining the data from two hemispheres. We explore these features using a flux transport dynamo model with stochastic fluctuations. We find that these features are correctly reproduced in this model. The solar cycle evolution of the distribution center is also in good agreement with observations. Possible explanations of the observed features based on this dynamo model are presented.

Caudate nucleus reactivity predicts perceptual learning rate for visual feature conjunctions.

PubMed

Reavis, Eric A; Frank, Sebastian M; Tse, Peter U

2015-04-15

Useful information in the visual environment is often contained in specific conjunctions of visual features (e.g., color and shape). The ability to quickly and accurately process such conjunctions can be learned. However, the neural mechanisms responsible for such learning remain largely unknown. It has been suggested that some forms of visual learning might involve the dopaminergic neuromodulatory system (Roelfsema et al., 2010; Seitz and Watanabe, 2005), but this hypothesis has not yet been directly tested. Here we test the hypothesis that learning visual feature conjunctions involves the dopaminergic system, using functional neuroimaging, genetic assays, and behavioral testing techniques. We use a correlative approach to evaluate potential associations between individual differences in visual feature conjunction learning rate and individual differences in dopaminergic function as indexed by neuroimaging and genetic markers. We find a significant correlation between activity in the caudate nucleus (a component of the dopaminergic system connected to visual areas of the brain) and visual feature conjunction learning rate. Specifically, individuals who showed a larger difference in activity between positive and negative feedback on an unrelated cognitive task, indicative of a more reactive dopaminergic system, learned visual feature conjunctions more quickly than those who showed a smaller activity difference. This finding supports the hypothesis that the dopaminergic system is involved in visual learning, and suggests that visual feature conjunction learning could be closely related to associative learning. However, no significant, reliable correlations were found between feature conjunction learning and genotype or dopaminergic activity in any other regions of interest. Copyright © 2015 Elsevier Inc. All rights reserved.

Aberrant light directly impairs mood and learning through melanopsin-expressing neurons.

PubMed

LeGates, Tara A; Altimus, Cara M; Wang, Hui; Lee, Hey-Kyoung; Yang, Sunggu; Zhao, Haiqing; Kirkwood, Alfredo; Weber, E Todd; Hattar, Samer

2012-11-22

The daily solar cycle allows organisms to synchronize their circadian rhythms and sleep-wake cycles to the correct temporal niche. Changes in day-length, shift-work, and transmeridian travel lead to mood alterations and cognitive function deficits. Sleep deprivation and circadian disruption underlie mood and cognitive disorders associated with irregular light schedules. Whether irregular light schedules directly affect mood and cognitive functions in the context of normal sleep and circadian rhythms remains unclear. Here we show, using an aberrant light cycle that neither changes the amount and architecture of sleep nor causes changes in the circadian timing system, that light directly regulates mood-related behaviours and cognitive functions in mice. Animals exposed to the aberrant light cycle maintain daily corticosterone rhythms, but the overall levels of corticosterone are increased. Despite normal circadian and sleep structures, these animals show increased depression-like behaviours and impaired hippocampal long-term potentiation and learning. Administration of the antidepressant drugs fluoxetine or desipramine restores learning in mice exposed to the aberrant light cycle, suggesting that the mood deficit precedes the learning impairments. To determine the retinal circuits underlying this impairment of mood and learning, we examined the behavioural consequences of this light cycle in animals that lack intrinsically photosensitive retinal ganglion cells. In these animals, the aberrant light cycle does not impair mood and learning, despite the presence of the conventional retinal ganglion cells and the ability of these animals to detect light for image formation. These findings demonstrate the ability of light to influence cognitive and mood functions directly through intrinsically photosensitive retinal ganglion cells.

Learning, Unlearning and Relearning--Knowledge Life Cycles in Library and Information Science Education

ERIC Educational Resources Information Center

Bedford, Denise A. D.

2015-01-01

The knowledge life cycle is applied to two core capabilities of library and information science (LIS) education--teaching, and research and development. The knowledge claim validation, invalidation and integration steps of the knowledge life cycle are translated to learning, unlearning and relearning processes. Mixed methods are used to determine…

Learning at Every Age? Life Cycle Dynamics of Adult Education in Europe

ERIC Educational Resources Information Center

Beblavy, Miroslav; Thum, Anna-Elisabeth; Potjagailo, Galina

2014-01-01

Adult learning is seen as a key factor for enhancing employment, innovation and growth. The aim of this paper is to understand the points in the life cycle at which adult learning takes place and whether it leads to reaching a medium or high level of educational attainment. We perform a synthetic panel analysis of adult learning for cohorts aged…

Dynamic adaptive learning for decision-making supporting systems

NASA Astrophysics Data System (ADS)

He, Haibo; Cao, Yuan; Chen, Sheng; Desai, Sachi; Hohil, Myron E.

2008-03-01

This paper proposes a novel adaptive learning method for data mining in support of decision-making systems. Due to the inherent characteristics of information ambiguity/uncertainty, high dimensionality and noisy in many homeland security and defense applications, such as surveillances, monitoring, net-centric battlefield, and others, it is critical to develop autonomous learning methods to efficiently learn useful information from raw data to help the decision making process. The proposed method is based on a dynamic learning principle in the feature spaces. Generally speaking, conventional approaches of learning from high dimensional data sets include various feature extraction (principal component analysis, wavelet transform, and others) and feature selection (embedded approach, wrapper approach, filter approach, and others) methods. However, very limited understandings of adaptive learning from different feature spaces have been achieved. We propose an integrative approach that takes advantages of feature selection and hypothesis ensemble techniques to achieve our goal. Based on the training data distributions, a feature score function is used to provide a measurement of the importance of different features for learning purpose. Then multiple hypotheses are iteratively developed in different feature spaces according to their learning capabilities. Unlike the pre-set iteration steps in many of the existing ensemble learning approaches, such as adaptive boosting (AdaBoost) method, the iterative learning process will automatically stop when the intelligent system can not provide a better understanding than a random guess in that particular subset of feature spaces. Finally, a voting algorithm is used to combine all the decisions from different hypotheses to provide the final prediction results. Simulation analyses of the proposed method on classification of different US military aircraft databases show the effectiveness of this method.

77 FR 73557 - Airworthiness Directives; Turbomeca S.A. Turboshaft Engines

Federal Register 2010, 2011, 2012, 2013, 2014

2012-12-11

... turboshaft engines. This proposed AD was prompted by a finding that the engine's tachometer unit cycle... tachometer's unit cycle counting feature. This proposed AD would also require ground-run functional checks... accuracy of the engine's tachometer cycle counting feature. We are proposing this AD to prevent uncontained...

What Do We Learn from Binding Features? Evidence for Multilevel Feature Integration

ERIC Educational Resources Information Center

Colzato, Lorenza S.; Raffone, Antonino; Hommel, Bernhard

2006-01-01

Four experiments were conducted to investigate the relationship between the binding of visual features (as measured by their after-effects on subsequent binding) and the learning of feature-conjunction probabilities. Both binding and learning effects were obtained, but they did not interact. Interestingly, (shape-color) binding effects…

Feature saliency and feedback information interactively impact visual category learning

PubMed Central

Hammer, Rubi; Sloutsky, Vladimir; Grill-Spector, Kalanit

2015-01-01

Visual category learning (VCL) involves detecting which features are most relevant for categorization. VCL relies on attentional learning, which enables effectively redirecting attention to object’s features most relevant for categorization, while ‘filtering out’ irrelevant features. When features relevant for categorization are not salient, VCL relies also on perceptual learning, which enables becoming more sensitive to subtle yet important differences between objects. Little is known about how attentional learning and perceptual learning interact when VCL relies on both processes at the same time. Here we tested this interaction. Participants performed VCL tasks in which they learned to categorize novel stimuli by detecting the feature dimension relevant for categorization. Tasks varied both in feature saliency (low-saliency tasks that required perceptual learning vs. high-saliency tasks), and in feedback information (tasks with mid-information, moderately ambiguous feedback that increased attentional load, vs. tasks with high-information non-ambiguous feedback). We found that mid-information and high-information feedback were similarly effective for VCL in high-saliency tasks. This suggests that an increased attentional load, associated with the processing of moderately ambiguous feedback, has little effect on VCL when features are salient. In low-saliency tasks, VCL relied on slower perceptual learning; but when the feedback was highly informative participants were able to ultimately attain the same performance as during the high-saliency VCL tasks. However, VCL was significantly compromised in the low-saliency mid-information feedback task. We suggest that such low-saliency mid-information learning scenarios are characterized by a ‘cognitive loop paradox’ where two interdependent learning processes have to take place simultaneously. PMID:25745404

Cost-Sensitive Local Binary Feature Learning for Facial Age Estimation.

PubMed

Lu, Jiwen; Liong, Venice Erin; Zhou, Jie

2015-12-01

In this paper, we propose a cost-sensitive local binary feature learning (CS-LBFL) method for facial age estimation. Unlike the conventional facial age estimation methods that employ hand-crafted descriptors or holistically learned descriptors for feature representation, our CS-LBFL method learns discriminative local features directly from raw pixels for face representation. Motivated by the fact that facial age estimation is a cost-sensitive computer vision problem and local binary features are more robust to illumination and expression variations than holistic features, we learn a series of hashing functions to project raw pixel values extracted from face patches into low-dimensional binary codes, where binary codes with similar chronological ages are projected as close as possible, and those with dissimilar chronological ages are projected as far as possible. Then, we pool and encode these local binary codes within each face image as a real-valued histogram feature for face representation. Moreover, we propose a cost-sensitive local binary multi-feature learning method to jointly learn multiple sets of hashing functions using face patches extracted from different scales to exploit complementary information. Our methods achieve competitive performance on four widely used face aging data sets.

Methods and Strategies: What's the Story?

ERIC Educational Resources Information Center

Lipsitz, Kelsey; Cisterna, Dante; Hanuscin, Deborah

2017-01-01

This column provides ideas and techniques to enhance your science teaching. This month's issue discusses using the 5E learning cycle to create coherent storylines. The 5E learning cycle provides an important framework to help teachers organize activities. To realize the full potential of the 5E framework for student learning, lessons must also…

The College Science Learning Cycle: An Instructional Model for Reformed Teaching

ERIC Educational Resources Information Center

Withers, Michelle

2016-01-01

Finding the time for developing or locating new class materials is one of the biggest barriers for instructors reforming their teaching approaches. Even instructors who have taken part in training workshops may feel overwhelmed by the task of transforming passive lecture content to engaging learning activities. Learning cycles have been…

Teaching and Learning International Survey TALIS 2013: Conceptual Framework. Final

ERIC Educational Resources Information Center

Rutkowski, David; Rutkowski, Leslie; Bélanger, Julie; Knoll, Steffen; Weatherby, Kristen; Prusinski, Ellen

2013-01-01

In 2008, the initial cycle of the OECD's Teaching and Learning International Survey (TALIS 2008) established, for the first time, an international, large-scale survey of the teaching workforce, the conditions of teaching, and the learning environments of schools in participating countries. The second cycle of TALIS (TALIS 2013) aims to continue…

e-Learning Application for Machine Maintenance Process using Iterative Method in XYZ Company

NASA Astrophysics Data System (ADS)

Nurunisa, Suaidah; Kurniawati, Amelia; Pramuditya Soesanto, Rayinda; Yunan Kurnia Septo Hediyanto, Umar

2016-02-01

XYZ Company is a company based on manufacturing part for airplane, one of the machine that is categorized as key facility in the company is Millac 5H6P. As a key facility, the machines should be assured to work well and in peak condition, therefore, maintenance process is needed periodically. From the data gathering, it is known that there are lack of competency from the maintenance staff to maintain different type of machine which is not assigned by the supervisor, this indicate that knowledge which possessed by maintenance staff are uneven. The purpose of this research is to create knowledge-based e-learning application as a realization from externalization process in knowledge transfer process to maintain the machine. The application feature are adjusted for maintenance purpose using e-learning framework for maintenance process, the content of the application support multimedia for learning purpose. QFD is used in this research to understand the needs from user. The application is built using moodle with iterative method for software development cycle and UML Diagram. The result from this research is e-learning application as sharing knowledge media for maintenance staff in the company. From the test, it is known that the application make maintenance staff easy to understand the competencies.

Integrated Low-Rank-Based Discriminative Feature Learning for Recognition.

PubMed

Zhou, Pan; Lin, Zhouchen; Zhang, Chao

2016-05-01

Feature learning plays a central role in pattern recognition. In recent years, many representation-based feature learning methods have been proposed and have achieved great success in many applications. However, these methods perform feature learning and subsequent classification in two separate steps, which may not be optimal for recognition tasks. In this paper, we present a supervised low-rank-based approach for learning discriminative features. By integrating latent low-rank representation (LatLRR) with a ridge regression-based classifier, our approach combines feature learning with classification, so that the regulated classification error is minimized. In this way, the extracted features are more discriminative for the recognition tasks. Our approach benefits from a recent discovery on the closed-form solutions to noiseless LatLRR. When there is noise, a robust Principal Component Analysis (PCA)-based denoising step can be added as preprocessing. When the scale of a problem is large, we utilize a fast randomized algorithm to speed up the computation of robust PCA. Extensive experimental results demonstrate the effectiveness and robustness of our method.

3 Steps to Great Coaching: A Simple but Powerful Instructional Coaching Cycle Nets Results

ERIC Educational Resources Information Center

Knight, Jim; Elford, Marti; Hock, Michael; Dunekack, Devona; Bradley, Barbara; Deshler, Donald D.; Knight, David

2015-01-01

In this article the authors describe a three-step instructional coaching cycle that can helps coaches become more effective. The article provides the steps and related components to: (1) Identify; (2) Learn; and (3) Improve. While the instructional coaching cycle is only one effective coaching program, coaches also need professional learning that…

Know your RO from your AE? Learning styles in practice.

PubMed

Woods, Helen Buckley

2012-06-01

In this article, Kolb's cycle of learning is put forward as a useful theory to consult when planning information literacy or other teaching sessions. The learning cycle is contextualised and Kolb's and other theories are briefly explored. The author then considers how learning style theories can be utilised when planning teaching and learning activities. The use of planning tools is advocated and ideas for sessions are suggested. HS. © 2012 The authors. Health Information and Libraries Journal © 2012 Health Libraries Group.

Enhancing the Pronunciation of English Suprasegmental Features through Reflective Learning Method

ERIC Educational Resources Information Center

Suwartono

2014-01-01

Suprasegmental features are of paramount importance in spoken English. Yet, these pronunciation features are marginalised in EFL/ESL teaching-learning. This article reported a study that was aimed at improving the students' mastery of English suprasegmental features through the use of reflective learning method. The study adopted Kemmis and…

Categorical Structure among Shared Features in Networks of Early-Learned Nouns

ERIC Educational Resources Information Center

Hills, Thomas T.; Maouene, Mounir; Maouene, Josita; Sheya, Adam; Smith, Linda

2009-01-01

The shared features that characterize the noun categories that young children learn first are a formative basis of the human category system. To investigate the potential categorical information contained in the features of early-learned nouns, we examine the graph-theoretic properties of noun-feature networks. The networks are built from the…

Model-Based Learning of Local Image Features for Unsupervised Texture Segmentation

NASA Astrophysics Data System (ADS)

Kiechle, Martin; Storath, Martin; Weinmann, Andreas; Kleinsteuber, Martin

2018-04-01

Features that capture well the textural patterns of a certain class of images are crucial for the performance of texture segmentation methods. The manual selection of features or designing new ones can be a tedious task. Therefore, it is desirable to automatically adapt the features to a certain image or class of images. Typically, this requires a large set of training images with similar textures and ground truth segmentation. In this work, we propose a framework to learn features for texture segmentation when no such training data is available. The cost function for our learning process is constructed to match a commonly used segmentation model, the piecewise constant Mumford-Shah model. This means that the features are learned such that they provide an approximately piecewise constant feature image with a small jump set. Based on this idea, we develop a two-stage algorithm which first learns suitable convolutional features and then performs a segmentation. We note that the features can be learned from a small set of images, from a single image, or even from image patches. The proposed method achieves a competitive rank in the Prague texture segmentation benchmark, and it is effective for segmenting histological images.

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.

Teacher Responses to Learning Cycle Science Lessons for Early Childhood Education

NASA Astrophysics Data System (ADS)

Kraemer, Emily N.

Three learning cycle science lessons were developed for preschoolers in an early childhood children's center in Costa Mesa, California. The lessons were field tested by both novice and experienced teachers with children ranging from three to five years old. Teachers were then interviewed informally to collect feedback on the structure and flow the lessons. The feedback was encouraging remarks towards the use of learning cycle science lessons for early childhood educators. Adjustments were made to the lessons based on teacher feedback. The lessons and their implications for preschool education are discussed.

Expanding the 5E Model.

ERIC Educational Resources Information Center

Eisenkraft, Arthur

2003-01-01

Amends the current 5E learning cycle and instructional model to a 7E model. Changes ensure that instructors do not omit crucial elements for learning from their lessons while under the incorrect assumption that they are meeting the requirements of the learning cycle. The proposed 7E model includes: (1) engage; (2) explore; (3) explain; (4) elicit;…

Methods and Strategies: Literacy in the Learning Cycle

ERIC Educational Resources Information Center

Everett, Susan; Moyer, Richard

2009-01-01

Trade books can be used in all phases of the learning cycle to support effective teaching and learning. Romance and Vitale (1992) found that texts and other nonfiction science books can be effective tools for teaching reading, as the science activities give learners a purpose for their reading. In this article, the authors share ways to…

To Tan or Not to Tan?: Students Learn About Sunscreens through an Inquiry Activity Based on the Learning Cycle

ERIC Educational Resources Information Center

Keen-Rocha, Linda

2005-01-01

Science instructors sometimes avoid inquiry-based activities due to limited classroom time. Inquiry takes time, as students choose problems, design experiments, obtain materials, conduct investigations, gather data, communicate results, and discuss their experiments. While there are no quick solutions to time concerns, the 5E learning cycle seeks…

Relations of Cognitive and Motivational Variables with Students' Human Circulatory System Achievement in Traditional and Learning Cycle Classrooms

ERIC Educational Resources Information Center

Sadi, Özlem; Çakiroglu, Jale

2014-01-01

This study is aimed at investigating the relationships among students' relevant prior knowledge, meaningful learning orientation, reasoning ability, self-efficacy, locus of control, attitudes toward biology and achievement with the human circulatory system (HCS) using the learning cycle (LC) and the traditional classroom setting. The study was…

Comparing American and Chinese Students' Learning Progression on Carbon Cycling in Socio-Ecological Systems

ERIC Educational Resources Information Center

Chen, J.; Anderson, C. W.

2015-01-01

Previous studies identified a learning progression on the concept of carbon cycling that was typically followed by American students when they progress from elementary to high school. This study examines the validity of this previously identified learning progression for a different group of learners--Chinese students. The results indicate that…

Engagement, Exploration, Explanation, Extension, and Evaluation (5E) Learning Cycle and Conceptual Change Text as Learning Tools

ERIC Educational Resources Information Center

Balci, Sibel; Cakiroglu, Jale; Tekkaya, Ceren

2006-01-01

The purpose of this study is to investigate the effects of the Engagement, Exploration, Explanation, Extension, and Evaluation (5E) learning cycle, conceptual change texts, and traditional instructions on 8th grade students' understanding of photosynthesis and respiration in plants. Students' understanding of photosynthesis and respiration in…

Quantitative assessment of cancer cell morphology and motility using telecentric digital holographic microscopy and machine learning.

PubMed

Lam, Van K; Nguyen, Thanh C; Chung, Byung M; Nehmetallah, George; Raub, Christopher B

2018-03-01

The noninvasive, fast acquisition of quantitative phase maps using digital holographic microscopy (DHM) allows tracking of rapid cellular motility on transparent substrates. On two-dimensional surfaces in vitro, MDA-MB-231 cancer cells assume several morphologies related to the mode of migration and substrate stiffness, relevant to mechanisms of cancer invasiveness in vivo. The quantitative phase information from DHM may accurately classify adhesive cancer cell subpopulations with clinical relevance. To test this, cells from the invasive breast cancer MDA-MB-231 cell line were cultured on glass, tissue-culture treated polystyrene, and collagen hydrogels, and imaged with DHM followed by epifluorescence microscopy after staining F-actin and nuclei. Trends in cell phase parameters were tracked on the different substrates, during cell division, and during matrix adhesion, relating them to F-actin features. Support vector machine learning algorithms were trained and tested using parameters from holographic phase reconstructions and cell geometric features from conventional phase images, and used to distinguish between elongated and rounded cell morphologies. DHM was able to distinguish between elongated and rounded morphologies of MDA-MB-231 cells with 94% accuracy, compared to 83% accuracy using cell geometric features from conventional brightfield microscopy. This finding indicates the potential of DHM to detect and monitor cancer cell morphologies relevant to cell cycle phase status, substrate adhesion, and motility. © 2017 International Society for Advancement of Cytometry. © 2017 International Society for Advancement of Cytometry.

Community Resilience Informed by Science and Experience (C-RISE)

NASA Astrophysics Data System (ADS)

Young Morse, R.; Peake, L.; Bowness, G.

2017-12-01

The Gulf of Maine Research Institute is developing an interactive learning experience that engages participants in the interdependence of humans and the environment, the cycles of observation and experiment that advance science knowledge, and the changes we see now and that are predicted for sea level and storm frequency. These scientific concepts and principles will be brought to human scale through the connection to the challenge of city planning in our harbor communities. We are leveraging the ESRI Story Maps platform to build rich visualization-based narratives that feature NOAA maps, data and tools. Our program participants work in teams to navigate the content and participate in facilitated group discussions led by our educators. Based on the adult learning experience and in concert with new content being developed for the LabVenture program around the theme of Climate Change, we will develop a learning experience for 5th and 6th graders.Our goal is to immerse 1000+ adults from target communities in Greater Portland region as well as 8000+ middle school students from throughout the state in the experience.

[Stimulation of D2-receptors improves passive avoidance learning in female rats].

PubMed

Fedotova, Iu O

2012-01-01

The involvement of D2-receptors in learning/memory processes during ovary cycle was assessed in the adult female rats. Quinperole (0,1 mg/kg, i.p.), D2-receptor agonist and sulpiride (10,0 mg/kg, i.p.), D2-receptor antagonist were injected chronically to adult female rats. Learning of these animals was assessed in different models: passive avoidance performance and Morris water maze. Chronic quinperole administration to females resulted in the appearance of the passive avoidance performance in proestrous and estrous, as distinct from the control animals. Also, quinperole improved spatial learning in proestrous and stimulated it in estrous in Morris water maze. Chronic sulpiride administration similarly impaired non-spatial and spatial learning in females during all phases of ovary cycle. The results of the study suggest modulating role of D2-receptors in learning/memory processes during ovary cycle in the adult female rats.

Learning through Feature Prediction: An Initial Investigation into Teaching Categories to Children with Autism through Predicting Missing Features

ERIC Educational Resources Information Center

Sweller, Naomi

2015-01-01

Individuals with autism have difficulty generalising information from one situation to another, a process that requires the learning of categories and concepts. Category information may be learned through: (1) classifying items into categories, or (2) predicting missing features of category items. Predicting missing features has to this point been…

Attentional Selection Can Be Predicted by Reinforcement Learning of Task-relevant Stimulus Features Weighted by Value-independent Stickiness.

PubMed

Balcarras, Matthew; Ardid, Salva; Kaping, Daniel; Everling, Stefan; Womelsdorf, Thilo

2016-02-01

Attention includes processes that evaluate stimuli relevance, select the most relevant stimulus against less relevant stimuli, and bias choice behavior toward the selected information. It is not clear how these processes interact. Here, we captured these processes in a reinforcement learning framework applied to a feature-based attention task that required macaques to learn and update the value of stimulus features while ignoring nonrelevant sensory features, locations, and action plans. We found that value-based reinforcement learning mechanisms could account for feature-based attentional selection and choice behavior but required a value-independent stickiness selection process to explain selection errors while at asymptotic behavior. By comparing different reinforcement learning schemes, we found that trial-by-trial selections were best predicted by a model that only represents expected values for the task-relevant feature dimension, with nonrelevant stimulus features and action plans having only a marginal influence on covert selections. These findings show that attentional control subprocesses can be described by (1) the reinforcement learning of feature values within a restricted feature space that excludes irrelevant feature dimensions, (2) a stochastic selection process on feature-specific value representations, and (3) value-independent stickiness toward previous feature selections akin to perseveration in the motor domain. We speculate that these three mechanisms are implemented by distinct but interacting brain circuits and that the proposed formal account of feature-based stimulus selection will be important to understand how attentional subprocesses are implemented in primate brain networks.

Raphanus sativus, Germination, and Inquiry: A Learning Cycle Approach for Novice Experimenters.

ERIC Educational Resources Information Center

Rillero, Peter

1999-01-01

Describes open-ended experiments with seeds from the common garden radish (Raphanus sativus). The phases of the 5-E learning cycle--Engagement, Exploration, Explanation, Extension, and Evaluation--guide this activity series. (Author/MM)

Implementation of 7e learning cycle model using technology based constructivist teaching (TBCT) approach to improve students' understanding achievment in mechanical wave material

NASA Astrophysics Data System (ADS)

Warliani, Resti; Muslim, Setiawan, Wawan

2017-05-01

This study aims to determine the increase in the understanding achievement in senior high school students through the Learning Cycle 7E with technology based constructivist teaching approach (TBCT). This study uses a pretest-posttest control group design. The participants were 67 high school students of eleventh grade in Garut city with two class in control and experiment class. Experiment class applying the Learning Cycle 7E through TBCT approach and control class applying the 7E Learning Cycle through Constructivist Teaching approach (CT). Data collection tools from mechanical wave concept test with totally 22 questions with reability coefficient was found 0,86. The findings show the increase of the understanding achievement of the experiment class is in the amount of 0.51 was higher than the control class that is in the amount of 0.33.

Impact of feature saliency on visual category learning.

PubMed

Hammer, Rubi

2015-01-01

People have to sort numerous objects into a large number of meaningful categories while operating in varying contexts. This requires identifying the visual features that best predict the 'essence' of objects (e.g., edibility), rather than categorizing objects based on the most salient features in a given context. To gain this capacity, visual category learning (VCL) relies on multiple cognitive processes. These may include unsupervised statistical learning, that requires observing multiple objects for learning the statistics of their features. Other learning processes enable incorporating different sources of supervisory information, alongside the visual features of the categorized objects, from which the categorical relations between few objects can be deduced. These deductions enable inferring that objects from the same category may differ from one another in some high-saliency feature dimensions, whereas lower-saliency feature dimensions can best differentiate objects from distinct categories. Here I illustrate how feature saliency affects VCL, by also discussing kinds of supervisory information enabling reflective categorization. Arguably, principles debated here are often being ignored in categorization studies.

Impact of feature saliency on visual category learning

PubMed Central

Hammer, Rubi

2015-01-01

People have to sort numerous objects into a large number of meaningful categories while operating in varying contexts. This requires identifying the visual features that best predict the ‘essence’ of objects (e.g., edibility), rather than categorizing objects based on the most salient features in a given context. To gain this capacity, visual category learning (VCL) relies on multiple cognitive processes. These may include unsupervised statistical learning, that requires observing multiple objects for learning the statistics of their features. Other learning processes enable incorporating different sources of supervisory information, alongside the visual features of the categorized objects, from which the categorical relations between few objects can be deduced. These deductions enable inferring that objects from the same category may differ from one another in some high-saliency feature dimensions, whereas lower-saliency feature dimensions can best differentiate objects from distinct categories. Here I illustrate how feature saliency affects VCL, by also discussing kinds of supervisory information enabling reflective categorization. Arguably, principles debated here are often being ignored in categorization studies. PMID:25954220

Features Students Really Expect from Learning Analytics

ERIC Educational Resources Information Center

Schumacher, Clara; Ifenthaler, Dirk

2016-01-01

In higher education settings more and more learning is facilitated through online learning environments. To support and understand students' learning processes better, learning analytics offers a promising approach. The purpose of this study was to investigate students' expectations toward features of learning analytics systems. In a first…

Accounting for length-bias and selection effects in estimating the distribution of menstrual cycle length.

PubMed

Lum, Kirsten J; Sundaram, Rajeshwari; Louis, Thomas A

2015-01-01

Prospective pregnancy studies are a valuable source of longitudinal data on menstrual cycle length. However, care is needed when making inferences of such renewal processes. For example, accounting for the sampling plan is necessary for unbiased estimation of the menstrual cycle length distribution for the study population. If couples can enroll when they learn of the study as opposed to waiting for the start of a new menstrual cycle, then due to length-bias, the enrollment cycle will be stochastically larger than the general run of cycles, a typical property of prevalent cohort studies. Furthermore, the probability of enrollment can depend on the length of time since a woman's last menstrual period (a backward recurrence time), resulting in selection effects. We focus on accounting for length-bias and selection effects in the likelihood for enrollment menstrual cycle length, using a recursive two-stage approach wherein we first estimate the probability of enrollment as a function of the backward recurrence time and then use it in a likelihood with sampling weights that account for length-bias and selection effects. To broaden the applicability of our methods, we augment our model to incorporate a couple-specific random effect and time-independent covariate. A simulation study quantifies performance for two scenarios of enrollment probability when proper account is taken of sampling plan features. In addition, we estimate the probability of enrollment and the distribution of menstrual cycle length for the study population of the Longitudinal Investigation of Fertility and the Environment Study. Published by Oxford University Press 2014. This work is written by (a) US Government employee(s) and is in the public domain in the US.

Unsupervised Feature Learning With Winner-Takes-All Based STDP

PubMed Central

Ferré, Paul; Mamalet, Franck; Thorpe, Simon J.

2018-01-01

We present a novel strategy for unsupervised feature learning in image applications inspired by the Spike-Timing-Dependent-Plasticity (STDP) biological learning rule. We show equivalence between rank order coding Leaky-Integrate-and-Fire neurons and ReLU artificial neurons when applied to non-temporal data. We apply this to images using rank-order coding, which allows us to perform a full network simulation with a single feed-forward pass using GPU hardware. Next we introduce a binary STDP learning rule compatible with training on batches of images. Two mechanisms to stabilize the training are also presented : a Winner-Takes-All (WTA) framework which selects the most relevant patches to learn from along the spatial dimensions, and a simple feature-wise normalization as homeostatic process. This learning process allows us to train multi-layer architectures of convolutional sparse features. We apply our method to extract features from the MNIST, ETH80, CIFAR-10, and STL-10 datasets and show that these features are relevant for classification. We finally compare these results with several other state of the art unsupervised learning methods. PMID:29674961

Perceptual learning of basic visual features remains task specific with Training-Plus-Exposure (TPE) training.

PubMed

Cong, Lin-Juan; Wang, Ru-Jie; Yu, Cong; Zhang, Jun-Yun

2016-01-01

Visual perceptual learning is known to be specific to the trained retinal location, feature, and task. However, location and feature specificity can be eliminated by double-training or TPE training protocols, in which observers receive additional exposure to the transfer location or feature dimension via an irrelevant task besides the primary learning task Here we tested whether these new training protocols could even make learning transfer across different tasks involving discrimination of basic visual features (e.g., orientation and contrast). Observers practiced a near-threshold orientation (or contrast) discrimination task. Following a TPE training protocol, they also received exposure to the transfer task via performing suprathreshold contrast (or orientation) discrimination in alternating blocks of trials in the same sessions. The results showed no evidence for significant learning transfer to the untrained near-threshold contrast (or orientation) discrimination task after discounting the pretest effects and the suprathreshold practice effects. These results thus do not support a hypothetical task-independent component in perceptual learning of basic visual features. They also set the boundary of the new training protocols in their capability to enable learning transfer.

Experience in Implementing Resource-Based Learning in Agrarian College of Management and Law Poltava State Agrarian Academy

ERIC Educational Resources Information Center

Kononets, Natalia

2015-01-01

The introduction of resource-based learning disciplines of computer cycles in Agrarian College. The article focused on the issue of implementation of resource-based learning courses in the agricultural cycle computer college. Tested approach to creating elearning resources through free hosting and their further use in the classroom. Noted that the…

The MOOC and Learning Analytics Innovation Cycle (MOLAC): A Reflective Summary of Ongoing Research and Its Challenges

ERIC Educational Resources Information Center

Drachsler, H.; Kalz, M.

2016-01-01

The article deals with the interplay between learning analytics and massive open online courses (MOOCs) and provides a conceptual framework to situate ongoing research in the MOOC and learning analytics innovation cycle (MOLAC framework). The MOLAC framework is organized on three levels: On the micro-level, the data collection and analytics…

The College Science Learning Cycle: An Instructional Model for Reformed Teaching.

PubMed

Withers, Michelle

2016-01-01

Finding the time for developing or locating new class materials is one of the biggest barriers for instructors reforming their teaching approaches. Even instructors who have taken part in training workshops may feel overwhelmed by the task of transforming passive lecture content to engaging learning activities. Learning cycles have been instrumental in helping K-12 science teachers design effective instruction for decades. This paper introduces the College Science Learning Cycle adapted from the popular Biological Sciences Curriculum Study 5E to help science, technology, engineering, and mathematics faculty develop course materials to support active, student-centered teaching approaches in their classrooms. The learning cycle is embedded in backward design, a learning outcomes-oriented instructional design approach, and is accompanied by resources and examples to help faculty transform their teaching in a time-efficient manner. © 2016 M. Withers. CBE—Life Sciences Education © 2016 The American Society for Cell Biology. This article is distributed by The American Society for Cell Biology under license from the author(s). It is available to the public under an Attribution–Noncommercial–Share Alike 3.0 Unported Creative Commons License (http://creativecommons.org/licenses/by-nc-sa/3.0).

node2vec: Scalable Feature Learning for Networks

PubMed Central

Grover, Aditya; Leskovec, Jure

2016-01-01

Prediction tasks over nodes and edges in networks require careful effort in engineering features used by learning algorithms. Recent research in the broader field of representation learning has led to significant progress in automating prediction by learning the features themselves. However, present feature learning approaches are not expressive enough to capture the diversity of connectivity patterns observed in networks. Here we propose node2vec, an algorithmic framework for learning continuous feature representations for nodes in networks. In node2vec, we learn a mapping of nodes to a low-dimensional space of features that maximizes the likelihood of preserving network neighborhoods of nodes. We define a flexible notion of a node’s network neighborhood and design a biased random walk procedure, which efficiently explores diverse neighborhoods. Our algorithm generalizes prior work which is based on rigid notions of network neighborhoods, and we argue that the added flexibility in exploring neighborhoods is the key to learning richer representations. We demonstrate the efficacy of node2vec over existing state-of-the-art techniques on multi-label classification and link prediction in several real-world networks from diverse domains. Taken together, our work represents a new way for efficiently learning state-of-the-art task-independent representations in complex networks. PMID:27853626

Category Representation for Classification and Feature Inference

ERIC Educational Resources Information Center

Johansen, Mark K.; Kruschke, John K.

2005-01-01

This research's purpose was to contrast the representations resulting from learning of the same categories by either classifying instances or inferring instance features. Prior inference learning research, particularly T. Yamauchi and A. B. Markman (1998), has suggested that feature inference learning fosters prototype representation, whereas…

Detecting Parkinsons' symptoms in uncontrolled home environments: a multiple instance learning approach.

PubMed

Das, Samarjit; Amoedo, Breogan; De la Torre, Fernando; Hodgins, Jessica

2012-01-01

In this paper, we propose to use a weakly supervised machine learning framework for automatic detection of Parkinson's Disease motor symptoms in daily living environments. Our primary goal is to develop a monitoring system capable of being used outside of controlled laboratory settings. Such a system would enable us to track medication cycles at home and provide valuable clinical feedback. Most of the relevant prior works involve supervised learning frameworks (e.g., Support Vector Machines). However, in-home monitoring provides only coarse ground truth information about symptom occurrences, making it very hard to adapt and train supervised learning classifiers for symptom detection. We address this challenge by formulating symptom detection under incomplete ground truth information as a multiple instance learning (MIL) problem. MIL is a weakly supervised learning framework that does not require exact instances of symptom occurrences for training; rather, it learns from approximate time intervals within which a symptom might or might not have occurred on a given day. Once trained, the MIL detector was able to spot symptom-prone time windows on other days and approximately localize the symptom instances. We monitored two Parkinson's disease (PD) patients, each for four days with a set of five triaxial accelerometers and utilized a MIL algorithm based on axis parallel rectangle (APR) fitting in the feature space. We were able to detect subject specific symptoms (e.g. dyskinesia) that conformed with a daily log maintained by the patients.

Transcription Factor Binding Profiles Reveal Cyclic Expression of Human Protein-coding Genes and Non-coding RNAs

PubMed Central

Cheng, Chao; Ung, Matthew; Grant, Gavin D.; Whitfield, Michael L.

2013-01-01

Cell cycle is a complex and highly supervised process that must proceed with regulatory precision to achieve successful cellular division. Despite the wide application, microarray time course experiments have several limitations in identifying cell cycle genes. We thus propose a computational model to predict human cell cycle genes based on transcription factor (TF) binding and regulatory motif information in their promoters. We utilize ENCODE ChIP-seq data and motif information as predictors to discriminate cell cycle against non-cell cycle genes. Our results show that both the trans- TF features and the cis- motif features are predictive of cell cycle genes, and a combination of the two types of features can further improve prediction accuracy. We apply our model to a complete list of GENCODE promoters to predict novel cell cycle driving promoters for both protein-coding genes and non-coding RNAs such as lincRNAs. We find that a similar percentage of lincRNAs are cell cycle regulated as protein-coding genes, suggesting the importance of non-coding RNAs in cell cycle division. The model we propose here provides not only a practical tool for identifying novel cell cycle genes with high accuracy, but also new insights on cell cycle regulation by TFs and cis-regulatory elements. PMID:23874175

Neural correlates of context-dependent feature conjunction learning in visual search tasks.

PubMed

Reavis, Eric A; Frank, Sebastian M; Greenlee, Mark W; Tse, Peter U

2016-06-01

Many perceptual learning experiments show that repeated exposure to a basic visual feature such as a specific orientation or spatial frequency can modify perception of that feature, and that those perceptual changes are associated with changes in neural tuning early in visual processing. Such perceptual learning effects thus exert a bottom-up influence on subsequent stimulus processing, independent of task-demands or endogenous influences (e.g., volitional attention). However, it is unclear whether such bottom-up changes in perception can occur as more complex stimuli such as conjunctions of visual features are learned. It is not known whether changes in the efficiency with which people learn to process feature conjunctions in a task (e.g., visual search) reflect true bottom-up perceptual learning versus top-down, task-related learning (e.g., learning better control of endogenous attention). Here we show that feature conjunction learning in visual search leads to bottom-up changes in stimulus processing. First, using fMRI, we demonstrate that conjunction learning in visual search has a distinct neural signature: an increase in target-evoked activity relative to distractor-evoked activity (i.e., a relative increase in target salience). Second, we demonstrate that after learning, this neural signature is still evident even when participants passively view learned stimuli while performing an unrelated, attention-demanding task. This suggests that conjunction learning results in altered bottom-up perceptual processing of the learned conjunction stimuli (i.e., a perceptual change independent of the task). We further show that the acquired change in target-evoked activity is contextually dependent on the presence of distractors, suggesting that search array Gestalts are learned. Hum Brain Mapp 37:2319-2330, 2016. © 2016 Wiley Periodicals, Inc. © 2016 Wiley Periodicals, Inc.

Multi-channel feature dictionaries for RGB-D object recognition

NASA Astrophysics Data System (ADS)

Lan, Xiaodong; Li, Qiming; Chong, Mina; Song, Jian; Li, Jun

2018-04-01

Hierarchical matching pursuit (HMP) is a popular feature learning method for RGB-D object recognition. However, the feature representation with only one dictionary for RGB channels in HMP does not capture sufficient visual information. In this paper, we propose multi-channel feature dictionaries based feature learning method for RGB-D object recognition. The process of feature extraction in the proposed method consists of two layers. The K-SVD algorithm is used to learn dictionaries in sparse coding of these two layers. In the first-layer, we obtain features by performing max pooling on sparse codes of pixels in a cell. And the obtained features of cells in a patch are concatenated to generate patch jointly features. Then, patch jointly features in the first-layer are used to learn the dictionary and sparse codes in the second-layer. Finally, spatial pyramid pooling can be applied to the patch jointly features of any layer to generate the final object features in our method. Experimental results show that our method with first or second-layer features can obtain a comparable or better performance than some published state-of-the-art methods.

Identification of Cell Cycle-Regulated Genes by Convolutional Neural Network.

PubMed

Liu, Chenglin; Cui, Peng; Huang, Tao

2017-01-01

The cell cycle-regulated genes express periodically with the cell cycle stages, and the identification and study of these genes can provide a deep understanding of the cell cycle process. Large false positives and low overlaps are big problems in cell cycle-regulated gene detection. Here, a computational framework called DLGene was proposed for cell cycle-regulated gene detection. It is based on the convolutional neural network, a deep learning algorithm representing raw form of data pattern without assumption of their distribution. First, the expression data was transformed to categorical state data to denote the changing state of gene expression, and four different expression patterns were revealed for the reported cell cycle-regulated genes. Then, DLGene was applied to discriminate the non-cell cycle gene and the four subtypes of cell cycle genes. Its performances were compared with six traditional machine learning methods. At last, the biological functions of representative cell cycle genes for each subtype are analyzed. Our method showed better and more balanced performance of sensitivity and specificity comparing to other machine learning algorithms. The cell cycle genes had very different expression pattern with non-cell cycle genes and among the cell-cycle genes, there were four subtypes. Our method not only detects the cell cycle genes, but also describes its expression pattern, such as when its highest expression level is reached and how it changes with time. For each type, we analyzed the biological functions of the representative genes and such results provided novel insight to the cell cycle mechanisms. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

Representation learning: a unified deep learning framework for automatic prostate MR segmentation.

PubMed

Liao, Shu; Gao, Yaozong; Oto, Aytekin; Shen, Dinggang

2013-01-01

Image representation plays an important role in medical image analysis. The key to the success of different medical image analysis algorithms is heavily dependent on how we represent the input data, namely features used to characterize the input image. In the literature, feature engineering remains as an active research topic, and many novel hand-crafted features are designed such as Haar wavelet, histogram of oriented gradient, and local binary patterns. However, such features are not designed with the guidance of the underlying dataset at hand. To this end, we argue that the most effective features should be designed in a learning based manner, namely representation learning, which can be adapted to different patient datasets at hand. In this paper, we introduce a deep learning framework to achieve this goal. Specifically, a stacked independent subspace analysis (ISA) network is adopted to learn the most effective features in a hierarchical and unsupervised manner. The learnt features are adapted to the dataset at hand and encode high level semantic anatomical information. The proposed method is evaluated on the application of automatic prostate MR segmentation. Experimental results show that significant segmentation accuracy improvement can be achieved by the proposed deep learning method compared to other state-of-the-art segmentation approaches.

The Effect of Learning Cycle Constructivist-Based Approach on Students' Academic Achievement and Attitude towards Chemistry in Secondary Schools in North-Eastern Part of Nigeria

ERIC Educational Resources Information Center

Jack, Gladys Uzezi

2017-01-01

This study investigated the effect of learning cycle constructivist-based approach on secondary schools students' academic achievement and their attitude towards chemistry. The design used was a pre-test, post-test non randomized control group quasi experimental research design. The design consisted of two instructional groups (learning cycle…

The Effect of Learning Cycle Models on Achievement of Students: A Meta-Analysis Study

ERIC Educational Resources Information Center

Sarac, Hakan

2018-01-01

In the study, a meta-analysis was conducted to determine the effect of the use of the learning cycle model on the achievements of the students. Doctorate and master theses, made between 2007 and 2016, were searched using the keywords in Turkish and English. As a result of the screening, a total of 123 dissertations, which used learning cycle…

A Flexible Mechanism of Rule Selection Enables Rapid Feature-Based Reinforcement Learning

PubMed Central

Balcarras, Matthew; Womelsdorf, Thilo

2016-01-01

Learning in a new environment is influenced by prior learning and experience. Correctly applying a rule that maps a context to stimuli, actions, and outcomes enables faster learning and better outcomes compared to relying on strategies for learning that are ignorant of task structure. However, it is often difficult to know when and how to apply learned rules in new contexts. In our study we explored how subjects employ different strategies for learning the relationship between stimulus features and positive outcomes in a probabilistic task context. We test the hypothesis that task naive subjects will show enhanced learning of feature specific reward associations by switching to the use of an abstract rule that associates stimuli by feature type and restricts selections to that dimension. To test this hypothesis we designed a decision making task where subjects receive probabilistic feedback following choices between pairs of stimuli. In the task, trials are grouped in two contexts by blocks, where in one type of block there is no unique relationship between a specific feature dimension (stimulus shape or color) and positive outcomes, and following an un-cued transition, alternating blocks have outcomes that are linked to either stimulus shape or color. Two-thirds of subjects (n = 22/32) exhibited behavior that was best fit by a hierarchical feature-rule model. Supporting the prediction of the model mechanism these subjects showed significantly enhanced performance in feature-reward blocks, and rapidly switched their choice strategy to using abstract feature rules when reward contingencies changed. Choice behavior of other subjects (n = 10/32) was fit by a range of alternative reinforcement learning models representing strategies that do not benefit from applying previously learned rules. In summary, these results show that untrained subjects are capable of flexibly shifting between behavioral rules by leveraging simple model-free reinforcement learning and context-specific selections to drive responses. PMID:27064794

Multi-Source Multi-Target Dictionary Learning for Prediction of Cognitive Decline.

PubMed

Zhang, Jie; Li, Qingyang; Caselli, Richard J; Thompson, Paul M; Ye, Jieping; Wang, Yalin

2017-06-01

Alzheimer's Disease (AD) is the most common type of dementia. Identifying correct biomarkers may determine pre-symptomatic AD subjects and enable early intervention. Recently, Multi-task sparse feature learning has been successfully applied to many computer vision and biomedical informatics researches. It aims to improve the generalization performance by exploiting the shared features among different tasks. However, most of the existing algorithms are formulated as a supervised learning scheme. Its drawback is with either insufficient feature numbers or missing label information. To address these challenges, we formulate an unsupervised framework for multi-task sparse feature learning based on a novel dictionary learning algorithm. To solve the unsupervised learning problem, we propose a two-stage Multi-Source Multi-Target Dictionary Learning (MMDL) algorithm. In stage 1, we propose a multi-source dictionary learning method to utilize the common and individual sparse features in different time slots. In stage 2, supported by a rigorous theoretical analysis, we develop a multi-task learning method to solve the missing label problem. Empirical studies on an N = 3970 longitudinal brain image data set, which involves 2 sources and 5 targets, demonstrate the improved prediction accuracy and speed efficiency of MMDL in comparison with other state-of-the-art algorithms.

An Evaluation of Feature Learning Methods for High Resolution Image Classification

NASA Astrophysics Data System (ADS)

Tokarczyk, P.; Montoya, J.; Schindler, K.

2012-07-01

Automatic image classification is one of the fundamental problems of remote sensing research. The classification problem is even more challenging in high-resolution images of urban areas, where the objects are small and heterogeneous. Two questions arise, namely which features to extract from the raw sensor data to capture the local radiometry and image structure at each pixel or segment, and which classification method to apply to the feature vectors. While classifiers are nowadays well understood, selecting the right features remains a largely empirical process. Here we concentrate on the features. Several methods are evaluated which allow one to learn suitable features from unlabelled image data by analysing the image statistics. In a comparative study, we evaluate unsupervised feature learning with different linear and non-linear learning methods, including principal component analysis (PCA) and deep belief networks (DBN). We also compare these automatically learned features with popular choices of ad-hoc features including raw intensity values, standard combinations like the NDVI, a few PCA channels, and texture filters. The comparison is done in a unified framework using the same images, the target classes, reference data and a Random Forest classifier.

Students' Reflections on the Relationships between Safe Learning Environments, Learning Challenge and Positive Experiences of Learning in a Simulated GP Clinic

ERIC Educational Resources Information Center

Young, J. E.; Williamson, M. I.; Egan, T. G.

2016-01-01

Learning environments are a significant determinant of student behaviour, achievement and satisfaction. In this article we use students' reflective essays to identify key features of the learning environment that contributed to positive and transformative learning experiences. We explore the relationships between these features, the students'…

Investigating Relationships between Features of Learning Designs and Student Learning Outcomes

ERIC Educational Resources Information Center

McNaught, Carmel; Lam, Paul; Cheng, Kin Fai

2012-01-01

This article reports a study of eLearning in 21 courses in Hong Kong universities that had a blended design of face-to-face classes combined with online learning. The main focus of the study was to examine possible relationships between features of online learning designs and student learning outcomes. Data-collection strategies included expert…

Toolkits and Libraries for Deep Learning.

PubMed

Erickson, Bradley J; Korfiatis, Panagiotis; Akkus, Zeynettin; Kline, Timothy; Philbrick, Kenneth

2017-08-01

Deep learning is an important new area of machine learning which encompasses a wide range of neural network architectures designed to complete various tasks. In the medical imaging domain, example tasks include organ segmentation, lesion detection, and tumor classification. The most popular network architecture for deep learning for images is the convolutional neural network (CNN). Whereas traditional machine learning requires determination and calculation of features from which the algorithm learns, deep learning approaches learn the important features as well as the proper weighting of those features to make predictions for new data. In this paper, we will describe some of the libraries and tools that are available to aid in the construction and efficient execution of deep learning as applied to medical images.

Feature highlighting enhances learning of a complex natural-science category.

PubMed

Miyatsu, Toshiya; Gouravajhala, Reshma; Nosofsky, Robert M; McDaniel, Mark A

2018-04-26

Learning naturalistic categories, which tend to have fuzzy boundaries and vary on many dimensions, can often be harder than learning well defined categories. One method for facilitating the category learning of naturalistic stimuli may be to provide explicit feature descriptions that highlight the characteristic features of each category. Although this method is commonly used in textbooks and classrooms, theoretically it remains uncertain whether feature descriptions should advantage learning complex natural-science categories. In three experiments, participants were trained on 12 categories of rocks, either without or with a brief description highlighting key features of each category. After training, they were tested on their ability to categorize both old and new rocks from each of the categories. Providing feature descriptions as a caption under a rock image failed to improve category learning relative to providing only the rock image with its category label (Experiment 1). However, when these same feature descriptions were presented such that they were explicitly linked to the relevant parts of the rock image (feature highlighting), participants showed significantly higher performance on both immediate generalization to new rocks (Experiment 2) and generalization after a 2-day delay (Experiment 3). Theoretical and practical implications are discussed. (PsycINFO Database Record (c) 2018 APA, all rights reserved).

Context-Aware Local Binary Feature Learning for Face Recognition.

PubMed

Duan, Yueqi; Lu, Jiwen; Feng, Jianjiang; Zhou, Jie

2018-05-01

In this paper, we propose a context-aware local binary feature learning (CA-LBFL) method for face recognition. Unlike existing learning-based local face descriptors such as discriminant face descriptor (DFD) and compact binary face descriptor (CBFD) which learn each feature code individually, our CA-LBFL exploits the contextual information of adjacent bits by constraining the number of shifts from different binary bits, so that more robust information can be exploited for face representation. Given a face image, we first extract pixel difference vectors (PDV) in local patches, and learn a discriminative mapping in an unsupervised manner to project each pixel difference vector into a context-aware binary vector. Then, we perform clustering on the learned binary codes to construct a codebook, and extract a histogram feature for each face image with the learned codebook as the final representation. In order to exploit local information from different scales, we propose a context-aware local binary multi-scale feature learning (CA-LBMFL) method to jointly learn multiple projection matrices for face representation. To make the proposed methods applicable for heterogeneous face recognition, we present a coupled CA-LBFL (C-CA-LBFL) method and a coupled CA-LBMFL (C-CA-LBMFL) method to reduce the modality gap of corresponding heterogeneous faces in the feature level, respectively. Extensive experimental results on four widely used face datasets clearly show that our methods outperform most state-of-the-art face descriptors.

Intelligent Fault Diagnosis of Rotary Machinery Based on Unsupervised Multiscale Representation Learning

NASA Astrophysics Data System (ADS)

Jiang, Guo-Qian; Xie, Ping; Wang, Xiao; Chen, Meng; He, Qun

2017-11-01

The performance of traditional vibration based fault diagnosis methods greatly depends on those handcrafted features extracted using signal processing algorithms, which require significant amounts of domain knowledge and human labor, and do not generalize well to new diagnosis domains. Recently, unsupervised representation learning provides an alternative promising solution to feature extraction in traditional fault diagnosis due to its superior learning ability from unlabeled data. Given that vibration signals usually contain multiple temporal structures, this paper proposes a multiscale representation learning (MSRL) framework to learn useful features directly from raw vibration signals, with the aim to capture rich and complementary fault pattern information at different scales. In our proposed approach, a coarse-grained procedure is first employed to obtain multiple scale signals from an original vibration signal. Then, sparse filtering, a newly developed unsupervised learning algorithm, is applied to automatically learn useful features from each scale signal, respectively, and then the learned features at each scale to be concatenated one by one to obtain multiscale representations. Finally, the multiscale representations are fed into a supervised classifier to achieve diagnosis results. Our proposed approach is evaluated using two different case studies: motor bearing and wind turbine gearbox fault diagnosis. Experimental results show that the proposed MSRL approach can take full advantages of the availability of unlabeled data to learn discriminative features and achieved better performance with higher accuracy and stability compared to the traditional approaches.

Perceptual learning of basic visual features remains task specific with Training-Plus-Exposure (TPE) training

PubMed Central

Cong, Lin-Juan; Wang, Ru-Jie; Yu, Cong; Zhang, Jun-Yun

2016-01-01

Visual perceptual learning is known to be specific to the trained retinal location, feature, and task. However, location and feature specificity can be eliminated by double-training or TPE training protocols, in which observers receive additional exposure to the transfer location or feature dimension via an irrelevant task besides the primary learning task Here we tested whether these new training protocols could even make learning transfer across different tasks involving discrimination of basic visual features (e.g., orientation and contrast). Observers practiced a near-threshold orientation (or contrast) discrimination task. Following a TPE training protocol, they also received exposure to the transfer task via performing suprathreshold contrast (or orientation) discrimination in alternating blocks of trials in the same sessions. The results showed no evidence for significant learning transfer to the untrained near-threshold contrast (or orientation) discrimination task after discounting the pretest effects and the suprathreshold practice effects. These results thus do not support a hypothetical task-independent component in perceptual learning of basic visual features. They also set the boundary of the new training protocols in their capability to enable learning transfer. PMID:26873777

Practice of the Education for the Principle of Otto Cycle by the E-Learning CG-Content

NASA Astrophysics Data System (ADS)

Sato, Tomoaki; Nagaoka, Keizo; Oguchi, Kosei

A CG-animation content which supports the learning of the Otto cycle was developed. This content has a piston assembly and the diagrams of PV, VS, TP and TS. The each diagram has a pointer which moves along the line of the graph and they are synchronized with the movement of the piston. The learners can operate this content directly on the e-learning system. While watching the movements of the piston assembly, the learners can confirm the state of the engine about temperature, pressure, volume, and entropy by the synchronized pointer on the diagrams. This content was used for the class of the machining practice exercise. The learning effect of the content was examined by the score of the short test. As the result of this examination, the CG-animation content was effective in the learning of the Otto cycle.

Evolution and regulation of complex life cycles: a brown algal perspective.

PubMed

Cock, J Mark; Godfroy, Olivier; Macaisne, Nicolas; Peters, Akira F; Coelho, Susana M

2014-02-01

The life cycle of an organism is one of its fundamental features, influencing many aspects of its biology. The brown algae exhibit a diverse range of life cycles indicating that transitions between life cycle types may have been key adaptive events in the evolution of this group. Life cycle mutants, identified in the model organism Ectocarpus, are providing information about how life cycle progression is regulated at the molecular level in brown algae. We explore some of the implications of the phenotypes of the life cycle mutants described to date and draw comparisons with recent insights into life cycle regulation in the green lineage. Given the importance of coordinating growth and development with life cycle progression, we suggest that the co-option of ancient life cycle regulators to control key developmental events may be a common feature in diverse groups of multicellular eukaryotes. Copyright © 2013 Elsevier Ltd. All rights reserved.

Building Trust and Shared Knowledge in Communities of E-Learning Practice: Collaborative Leadership in the JISC eLISA and CAMEL Lifelong Learning Projects

ERIC Educational Resources Information Center

Jameson, Jill; Ferrell, Gill; Kelly, Jacquie; Walker, Simon; Ryan, Malcolm

2006-01-01

Trust and collective learning are useful features that are enabled by effective collaborative leadership of e-learning projects across higher and further education (HE/FE) institutions promoting lifelong learning. These features contribute effectively to the development of design for learning in communities of e-learning practice. For this,…

Exploring Growth (and Mitosis) through a Learning Cycle.

ERIC Educational Resources Information Center

Lawson, Anton E.

1991-01-01

Presents a learning cycle lesson plan in which students investigate the question of how cells divide. Students use microscopes to explore actual plant root and stem tissues to generate and test hypotheses to answer the question. Includes teacher material, student material, and teaching tips. (MDH)

Promoting students’ mathematical problem-solving skills through 7e learning cycle and hypnoteaching model

NASA Astrophysics Data System (ADS)

Saleh, H.; Suryadi, D.; Dahlan, J. A.

2018-01-01

The aim of this research was to find out whether 7E learning cycle under hypnoteaching model can enhance students’ mathematical problem-solving skill. This research was quasi-experimental study. The design of this study was pretest-posttest control group design. There were two groups of sample used in the study. The experimental group was given 7E learning cycle under hypnoteaching model, while the control group was given conventional model. The population of this study was the student of mathematics education program at one university in Tangerang. The statistical analysis used to test the hypothesis of this study were t-test and Mann-Whitney U. The result of this study show that: (1) The students’ achievement of mathematical problem solving skill who obtained 7E learning cycle under hypnoteaching model are higher than the students who obtained conventional model; (2) There are differences in the students’ enhancement of mathematical problem-solving skill based on students’ prior mathematical knowledge (PMK) category (high, middle, and low).

Blockade of 5-HT2A/2C-type receptors impairs learning in female rats in the course of estrous cycle.

PubMed

Fedotova, Yu O; Ordyan, N E

2010-12-01

We studied the effects of chronic administration (14 days) of agonist of 5-HT2B/2C serotonin receptors m-CPP (0.5 mg/kg subcutaneously) and agonist of 5-HT2A/2C serotonin receptors ketanserin (0.1 mg/kg intraperitoneally) on conditioned reactions in female rats in different phases of the estrous cycle. Passive avoidance (PA) paradigm and Morris water maze were used as behavioral tests. Chronic administration of m-CPP did not affect PA retrieval during the proestrus and estrus phases, but improved the dynamics of spatial learning in Morris water maze in comparison with control rats. Chronic administration of ketanserin uniformly impaired processes of spatial and nonspatial learning in female rats irrespective to the phase of the estrous cycle. A modulating role of 5-HT2A/2C and 5-HT2B/2C serotonin receptors in process of learning in female rats during the key phases of the estrous cycle was demonstrated.

OLMS: Online Learning Management System for E-Learning

ERIC Educational Resources Information Center

Ippakayala, Vinay Kumar; El-Ocla, Hosam

2017-01-01

In this paper we introduce a learning management system that provides a management system for centralized control of course content. A secure system to record lectures is implemented as a key feature of this application. This feature would be accessed through web camera and mobile recording. These features are mainly designed for e-learning…

Embedded Incremental Feature Selection for Reinforcement Learning

DTIC Science & Technology

2012-05-01

Prior to this work, feature selection for reinforce- ment learning has focused on linear value function ap- proximation ( Kolter and Ng, 2009; Parr et al...InProceed- ings of the the 23rd International Conference on Ma- chine Learning, pages 449–456. Kolter , J. Z. and Ng, A. Y. (2009). Regularization and feature

The US business cycle: power law scaling for interacting units with complex internal structure

NASA Astrophysics Data System (ADS)

Ormerod, Paul

2002-11-01

In the social sciences, there is increasing evidence of the existence of power law distributions. The distribution of recessions in capitalist economies has recently been shown to follow such a distribution. The preferred explanation for this is self-organised criticality. Gene Stanley and colleagues propose an alternative, namely that power law scaling can arise from the interplay between random multiplicative growth and the complex structure of the units composing the system. This paper offers a parsimonious model of the US business cycle based on similar principles. The business cycle, along with long-term growth, is one of the two features which distinguishes capitalism from all previously existing societies. Yet, economics lacks a satisfactory theory of the cycle. The source of cycles is posited in economic theory to be a series of random shocks which are external to the system. In this model, the cycle is an internal feature of the system, arising from the level of industrial concentration of the agents and the interactions between them. The model-in contrast to existing economic theories of the cycle-accounts for the key features of output growth in the US business cycle in the 20th century.

Discriminatively learning for representing local image features with quadruplet model

NASA Astrophysics Data System (ADS)

Zhang, Da-long; Zhao, Lei; Xu, Duan-qing; Lu, Dong-ming

2017-11-01

Traditional hand-crafted features for representing local image patches are evolving into current data-driven and learning-based image feature, but learning a robust and discriminative descriptor which is capable of controlling various patch-level computer vision tasks is still an open problem. In this work, we propose a novel deep convolutional neural network (CNN) to learn local feature descriptors. We utilize the quadruplets with positive and negative training samples, together with a constraint to restrict the intra-class variance, to learn good discriminative CNN representations. Compared with previous works, our model reduces the overlap in feature space between corresponding and non-corresponding patch pairs, and mitigates margin varying problem caused by commonly used triplet loss. We demonstrate that our method achieves better embedding result than some latest works, like PN-Net and TN-TG, on benchmark dataset.

Development of the living thing transportation systems worksheet on learning cycle model to increase student understanding

NASA Astrophysics Data System (ADS)

Rachmawati, E.; Nurohman, S.; Widowati, A.

2018-01-01

This study aims to know: 1) the feasibility LKPD review of aspects of the didactic requirements, construction requirements, technical requirements and compliance with the Learning Cycle. 2) Increase understanding of learners with Learning Model Learning Cycle in SMP N 1 Wates in the form LKPD. 3) The response of learners and educators SMP N 1 Wates to quality LKPD Transportation Systems Beings. This study is an R & D with the 4D model (Define, Design, Develop and Disseminate). Data were analyzed using qualitative analysis and quantitative analysis. Qualitative analysis in the form of advice description and assessment scores from all validates that was converted to a scale of 4. While the analysis of quantitative data by calculating the percentage of materializing learning and achievement using the standard gain an increased understanding and calculation of the KKM completeness evaluation value as an indicator of the achievement of students understanding. the results of this study yield LKPD IPA model learning Cycle theme Transportation Systems Beings obtain 108.5 total scores of a maximum score of 128 including the excellent category (A). LKPD IPA developed able to demonstrate an improved understanding of learners and the response of learners was very good to this quality LKPD IPA.

Analysis of in vivo single cell behavior by high throughput, human-in-the-loop segmentation of three-dimensional images.

PubMed

Chiang, Michael; Hallman, Sam; Cinquin, Amanda; de Mochel, Nabora Reyes; Paz, Adrian; Kawauchi, Shimako; Calof, Anne L; Cho, Ken W; Fowlkes, Charless C; Cinquin, Olivier

2015-11-25

Analysis of single cells in their native environment is a powerful method to address key questions in developmental systems biology. Confocal microscopy imaging of intact tissues, followed by automatic image segmentation, provides a means to conduct cytometric studies while at the same time preserving crucial information about the spatial organization of the tissue and morphological features of the cells. This technique is rapidly evolving but is still not in widespread use among research groups that do not specialize in technique development, perhaps in part for lack of tools that automate repetitive tasks while allowing experts to make the best use of their time in injecting their domain-specific knowledge. Here we focus on a well-established stem cell model system, the C. elegans gonad, as well as on two other model systems widely used to study cell fate specification and morphogenesis: the pre-implantation mouse embryo and the developing mouse olfactory epithelium. We report a pipeline that integrates machine-learning-based cell detection, fast human-in-the-loop curation of these detections, and running of active contours seeded from detections to segment cells. The procedure can be bootstrapped by a small number of manual detections, and outperforms alternative pieces of software we benchmarked on C. elegans gonad datasets. Using cell segmentations to quantify fluorescence contents, we report previously-uncharacterized cell behaviors in the model systems we used. We further show how cell morphological features can be used to identify cell cycle phase; this provides a basis for future tools that will streamline cell cycle experiments by minimizing the need for exogenous cell cycle phase labels. High-throughput 3D segmentation makes it possible to extract rich information from images that are routinely acquired by biologists, and provides insights - in particular with respect to the cell cycle - that would be difficult to derive otherwise.

An Interprofessional Collaborative Practice model for preparation of clinical educators.

PubMed

Scarvell, Jennie M; Stone, Judy

2010-07-01

Work-integrated learning is essential to health professional education, but faces increasing academic and industry resource pressures. The aim of this pilot "Professional Practice Project" was to develop and implement an innovative education intervention for clinical educators across several health disciplines. The project used interprofessional collaboration as its underlying philosophy, and a participatory action research methodology in four cycles: Cycle 1: Formation of an interprofessional project executive and working party from academic staff. Data collection of student insights into work integrated learning. Cycle 2: Formation of an interprofessional reference group to inform curriculum development for a series of clinical education workshops. Cycle 3: Delivery of workshops; 174 clinical educators, supervisors and preceptors attended two workshops: "Introduction to experiential learning" and " utilizing available resources for learning". Cycle 4: Seminar discussion of the Professional Practice Project at a national health-education conference. This pilot project demonstrated the advantages of using collaborative synergies to allow innovation around clinical education, free from the constraints of traditional discipline-specific education models. The planning, delivery and evaluation of clinical education workshops describe the benefits of interprofessional collaboration through enhanced creative thinking, sharing of clinical education models and a broadening of experience for both learners and facilitators.

An ecohydraulic view on stream resilience and ecosystem functioning - what can science teach management?

NASA Astrophysics Data System (ADS)

Battin, Tom J.; Dzubakova, Katharina; Boodoo, Kyle; Ulseth, Amber

2017-04-01

Streams and rivers are increasingly exposed to environmental change across various spatial and temporal scales. Consequently, ecosystem health and integrity are becoming compromised. Most management strategies designed to recover and maintain stream ecosystem health involve engineering measures of geomorphology. The success of such engineering measures relies on a thorough understanding of the underlying physical, chemical and biological process coupling across scales. First, we present results from experimental work unraveling the relevance of streambed heterogeneity for the resilience of phototrophic biofilms. This is critical as phototrophic biofilms are key for nutrient removal and hence for keeping the water clean. These biofilms are also the machinery of primary production and related carbon fluxes in stream ecosystems. Next, we show how climate change may affect primary production, including CO2, in streams and the networks they form. In fact, streams are now recognized as major sources of CO2 to the atmosphere and contributors to the global carbon cycle. Despite this, we do not yet understand how geomorphological features, themselves continuously reworked by hydrology and sedimentary dynamics, affect CO2 fluxes in streams. We show that gravel bars, clearly conspicuous geomorphological features, are hotspots of CO2 fluxes compared to the streamwater itself. This has major implications for carbon cycling and stream ecosystem functioning. Finally, we discuss what stream management could learn from ecohydraulic insights from young scientists doing excellent basic research.

Understanding the Influence of Learners' Forethought on Their Use of Science Study Strategies in Postsecondary Science Learning

NASA Astrophysics Data System (ADS)

Dunn, Karee E.; Lo, Wen-Juo

2015-11-01

Understanding self-regulation in science learning is important for theorists and practitioners alike. However, very little has been done to explore and understand students' self-regulatory processes in postsecondary science courses. In this study, the influence of science efficacy, learning value, and goal orientation on the perceived use of science study strategies was explored using structural equation modeling. In addition, the study served to validate the first two stages of Zimmerman's cyclical model of self-regulation and to address the common methodological weakness in self-regulation research in which data are all collected at one point after the learning cycle is complete. Thus, data were collected across the learning cycle rather than asking students to reflect upon each construct after the learning cycle was complete. The findings supported the hypothesized model in which it was predicted that self-efficacy would significantly and positively influence students' perceived science strategy use, and the influence of students' valuation of science learning on science study strategies would be mediated by their learning goal orientation. The findings of the study are discussed and implications for undergraduate science instructors are proposed.

Exploring Deep Learning and Transfer Learning for Colonic Polyp Classification

PubMed Central

Uhl, Andreas; Wimmer, Georg; Häfner, Michael

2016-01-01

Recently, Deep Learning, especially through Convolutional Neural Networks (CNNs) has been widely used to enable the extraction of highly representative features. This is done among the network layers by filtering, selecting, and using these features in the last fully connected layers for pattern classification. However, CNN training for automated endoscopic image classification still provides a challenge due to the lack of large and publicly available annotated databases. In this work we explore Deep Learning for the automated classification of colonic polyps using different configurations for training CNNs from scratch (or full training) and distinct architectures of pretrained CNNs tested on 8-HD-endoscopic image databases acquired using different modalities. We compare our results with some commonly used features for colonic polyp classification and the good results suggest that features learned by CNNs trained from scratch and the “off-the-shelf” CNNs features can be highly relevant for automated classification of colonic polyps. Moreover, we also show that the combination of classical features and “off-the-shelf” CNNs features can be a good approach to further improve the results. PMID:27847543

FSMRank: feature selection algorithm for learning to rank.

PubMed

Lai, Han-Jiang; Pan, Yan; Tang, Yong; Yu, Rong

2013-06-01

In recent years, there has been growing interest in learning to rank. The introduction of feature selection into different learning problems has been proven effective. These facts motivate us to investigate the problem of feature selection for learning to rank. We propose a joint convex optimization formulation which minimizes ranking errors while simultaneously conducting feature selection. This optimization formulation provides a flexible framework in which we can easily incorporate various importance measures and similarity measures of the features. To solve this optimization problem, we use the Nesterov's approach to derive an accelerated gradient algorithm with a fast convergence rate O(1/T(2)). We further develop a generalization bound for the proposed optimization problem using the Rademacher complexities. Extensive experimental evaluations are conducted on the public LETOR benchmark datasets. The results demonstrate that the proposed method shows: 1) significant ranking performance gain compared to several feature selection baselines for ranking, and 2) very competitive performance compared to several state-of-the-art learning-to-rank algorithms.

Rapid and long-lasting learning of feature binding

PubMed Central

Yashar, Amit; Carrasco, Marisa

2016-01-01

How are features integrated (bound) into objects and how can this process be facilitated? Here we investigated the role of rapid perceptual learning in feature binding and its long-lasting effects. By isolating the contributions of individual features from their conjunctions between training and test displays, we demonstrate for the first time that training can rapidly and substantially improve feature binding. Observers trained on a conjunction search task consisting of a rapid display with one target-conjunction, then tested with a new target-conjunction. Features were the same between training and test displays. Learning transferred to the new target when its conjunction was presented as a distractor, but not when only its component features were presented in different conjunction distractors during training. Training improvement lasted for up to 16 months, but, in all conditions, it was specific to the trained target. Our findings suggest that with short training observers’ ability to bind two specific features into an object is improved, and that this learning effect can last for over a year. Moreover, our findings show that while the short-term learning effect reflects activation of presented items and their binding, long-term consolidation is task specific. PMID:27289484

Opening the Learning Process: The Potential Role of Feature Film in Teaching Employment Relations

ERIC Educational Resources Information Center

Lafferty, George

2016-01-01

This paper explores the potential of feature film to encourage more inclusive, participatory and open learning in the area of employment relations. Evaluations of student responses in a single postgraduate course over a five-year period revealed how feature film could encourage participatory learning processes in which students reexamined their…

Feature Biases in Early Word Learning: Network Distinctiveness Predicts Age of Acquisition

ERIC Educational Resources Information Center

Engelthaler, Tomas; Hills, Thomas T.

2017-01-01

Do properties of a word's features influence the order of its acquisition in early word learning? Combining the principles of mutual exclusivity and shape bias, the present work takes a network analysis approach to understanding how feature distinctiveness predicts the order of early word learning. Distance networks were built from nouns with edge…

The influence of gender and the estrous cycle on learned helplessness in the rat.

PubMed

Jenkins, J A; Williams, P; Kramer, G L; Davis, L L; Petty, F

2001-11-01

Although the etiology of clinical depression is unknown, women are more likely to suffer from major depressive disorder than men. In addition, in some women, there is a clear association between depression and specific phases of the menstrual cycle. Surprisingly little research has examined gender differences and the influences of the estrous cycle in this and other animal behavioral models of clinical depression. Learned helplessness is a valid animal model of stress-induced behavioral depression in which prior exposure to inescapable stress produces deficits in escape testing. Learned helplessness was studied in rats using an inescapable tail shock stress followed by a shuttle box test to determine escape latencies. Animals with mean escape latencies of >or=20 s after shuttle-box testing are defined as learned helpless. Males and normal cycling female rats in the estrus and diestrus II phases were studied. Female rats in the diestrus II phase had significantly higher escape latencies and exhibited a more helpless behavior than female rats in the estrus phase. Male rat escape latencies were intermediate between the two female phases. These results suggest a role for gonadal hormones in the development of stress-induced behavioral depression or 'learned helplessness.'

Multi-Source Multi-Target Dictionary Learning for Prediction of Cognitive Decline

PubMed Central

Zhang, Jie; Li, Qingyang; Caselli, Richard J.; Thompson, Paul M.; Ye, Jieping; Wang, Yalin

2017-01-01

Alzheimer’s Disease (AD) is the most common type of dementia. Identifying correct biomarkers may determine pre-symptomatic AD subjects and enable early intervention. Recently, Multi-task sparse feature learning has been successfully applied to many computer vision and biomedical informatics researches. It aims to improve the generalization performance by exploiting the shared features among different tasks. However, most of the existing algorithms are formulated as a supervised learning scheme. Its drawback is with either insufficient feature numbers or missing label information. To address these challenges, we formulate an unsupervised framework for multi-task sparse feature learning based on a novel dictionary learning algorithm. To solve the unsupervised learning problem, we propose a two-stage Multi-Source Multi-Target Dictionary Learning (MMDL) algorithm. In stage 1, we propose a multi-source dictionary learning method to utilize the common and individual sparse features in different time slots. In stage 2, supported by a rigorous theoretical analysis, we develop a multi-task learning method to solve the missing label problem. Empirical studies on an N = 3970 longitudinal brain image data set, which involves 2 sources and 5 targets, demonstrate the improved prediction accuracy and speed efficiency of MMDL in comparison with other state-of-the-art algorithms. PMID:28943731

Of Mice, Birds, and Men: The Mouse Ultrasonic Song System Has Some Features Similar to Humans and Song-Learning Birds

PubMed Central

Arriaga, Gustavo; Zhou, Eric P.; Jarvis, Erich D.

2012-01-01

Humans and song-learning birds communicate acoustically using learned vocalizations. The characteristic features of this social communication behavior include vocal control by forebrain motor areas, a direct cortical projection to brainstem vocal motor neurons, and dependence on auditory feedback to develop and maintain learned vocalizations. These features have so far not been found in closely related primate and avian species that do not learn vocalizations. Male mice produce courtship ultrasonic vocalizations with acoustic features similar to songs of song-learning birds. However, it is assumed that mice lack a forebrain system for vocal modification and that their ultrasonic vocalizations are innate. Here we investigated the mouse song system and discovered that it includes a motor cortex region active during singing, that projects directly to brainstem vocal motor neurons and is necessary for keeping song more stereotyped and on pitch. We also discovered that male mice depend on auditory feedback to maintain some ultrasonic song features, and that sub-strains with differences in their songs can match each other's pitch when cross-housed under competitive social conditions. We conclude that male mice have some limited vocal modification abilities with at least some neuroanatomical features thought to be unique to humans and song-learning birds. To explain our findings, we propose a continuum hypothesis of vocal learning. PMID:23071596

Enhancing interpretability of automatically extracted machine learning features: application to a RBM-Random Forest system on brain lesion segmentation.

PubMed

Pereira, Sérgio; Meier, Raphael; McKinley, Richard; Wiest, Roland; Alves, Victor; Silva, Carlos A; Reyes, Mauricio

2018-02-01

Machine learning systems are achieving better performances at the cost of becoming increasingly complex. However, because of that, they become less interpretable, which may cause some distrust by the end-user of the system. This is especially important as these systems are pervasively being introduced to critical domains, such as the medical field. Representation Learning techniques are general methods for automatic feature computation. Nevertheless, these techniques are regarded as uninterpretable "black boxes". In this paper, we propose a methodology to enhance the interpretability of automatically extracted machine learning features. The proposed system is composed of a Restricted Boltzmann Machine for unsupervised feature learning, and a Random Forest classifier, which are combined to jointly consider existing correlations between imaging data, features, and target variables. We define two levels of interpretation: global and local. The former is devoted to understanding if the system learned the relevant relations in the data correctly, while the later is focused on predictions performed on a voxel- and patient-level. In addition, we propose a novel feature importance strategy that considers both imaging data and target variables, and we demonstrate the ability of the approach to leverage the interpretability of the obtained representation for the task at hand. We evaluated the proposed methodology in brain tumor segmentation and penumbra estimation in ischemic stroke lesions. We show the ability of the proposed methodology to unveil information regarding relationships between imaging modalities and extracted features and their usefulness for the task at hand. In both clinical scenarios, we demonstrate that the proposed methodology enhances the interpretability of automatically learned features, highlighting specific learning patterns that resemble how an expert extracts relevant data from medical images. Copyright © 2017 Elsevier B.V. All rights reserved.

Tying It All Together

ERIC Educational Resources Information Center

Hirsh, Stephanie; Crow, Tracy

2017-01-01

The learning team cycle as described in "Becoming a Learning Team: A Guide to a Teacher-Led Cycle of Continuous Improvement" by Stephanie Hirsh and Tracy Crow was created to support teams of teachers working on particular lessons and instructional challenges within classrooms. Even as the day-to-day work of classroom teaching continues,…

Learning in Structured Connectionist Networks

DTIC Science & Technology

1988-04-01

the structure is too rigid and learning too difficult for cognitive modeling. Two algorithms for learning simple, feature-based concept descriptions...and learning too difficult for cognitive model- ing. Two algorithms for learning simple, feature-based concept descriptions were also implemented. The...Term Goals Recent progress in connectionist research has been encouraging; networks have success- fully modeled human performance for various cognitive

The Effectiveness of Using the 7E's Learning Cycle Strategy on the Immediate and Delayed Mathematics Achievement and the Longitudinal Impact of Learning among Preparatory Year Students at King Saud University (KSU)

ERIC Educational Resources Information Center

Khashan, Khaled

2016-01-01

This study aimed to investigate the effectiveness of teaching Mathematics by using 7E's Learning Cycle strategy in immediate and delayed achievement and retention among Preparatory Year students at King Saud University (KSU)--Saudi Arabia, in comparison with the traditional method. The study sample consisted of (73) Preparatory Year students at…

A Deep Learning Approach for Fault Diagnosis of Induction Motors in Manufacturing

NASA Astrophysics Data System (ADS)

Shao, Si-Yu; Sun, Wen-Jun; Yan, Ru-Qiang; Wang, Peng; Gao, Robert X.

2017-11-01

Extracting features from original signals is a key procedure for traditional fault diagnosis of induction motors, as it directly influences the performance of fault recognition. However, high quality features need expert knowledge and human intervention. In this paper, a deep learning approach based on deep belief networks (DBN) is developed to learn features from frequency distribution of vibration signals with the purpose of characterizing working status of induction motors. It combines feature extraction procedure with classification task together to achieve automated and intelligent fault diagnosis. The DBN model is built by stacking multiple-units of restricted Boltzmann machine (RBM), and is trained using layer-by-layer pre-training algorithm. Compared with traditional diagnostic approaches where feature extraction is needed, the presented approach has the ability of learning hierarchical representations, which are suitable for fault classification, directly from frequency distribution of the measurement data. The structure of the DBN model is investigated as the scale and depth of the DBN architecture directly affect its classification performance. Experimental study conducted on a machine fault simulator verifies the effectiveness of the deep learning approach for fault diagnosis of induction motors. This research proposes an intelligent diagnosis method for induction motor which utilizes deep learning model to automatically learn features from sensor data and realize working status recognition.

Supporting new graduate professional development: a clinical learning framework.

PubMed

Fitzgerald, Cate; Moores, Alis; Coleman, Allison; Fleming, Jennifer

2015-02-01

New graduate occupational therapists are required to competently deliver health-care practices within complex care environments. An occupational therapy clinical education programme within a large public sector health service sought to investigate methods to support new graduates in their clinical learning and professional development. Three cycles of an insider action research approach each using the steps of planning, action, critical observation and reflection were undertaken to investigate new graduate learning strategies, develop a learning framework and pilot its utility. Qualitative research methods were used to analyse data gathered during the action research cycles. Action research identified variations in current practices to support new graduate learning and to the development of the Occupational Therapy Clinical Learning Framework (OTCLF). Investigation into the utility of the OTCLF revealed two themes associated with its implementation namely (i) contribution to learning goal development and (ii) compatibility with existing learning supports. The action research cycles aimed to review current practices to support new graduate learning. The learning framework developed encourages reflection to identify learning needs and the review, discussion of, and engagement in, goal setting and learning strategies. Preliminary evidence indicates that the OTCLF has potential as an approach to guide new graduate goal development supported by supervision. Future opportunity to implement a similar learning framework in other allied health professions was identified, enabling a continuation of the cyclical nature of enquiry, integral to this research approach within the workplace. © 2014 Occupational Therapy Australia.

Successful Solutions to SSME/AT Development Turbine Blade Distress

NASA Technical Reports Server (NTRS)

Montgomery, Stuart K.

1999-01-01

As part of the High-Pressure Fuel Turbopump/Alternate Turbopump (HPFTP/AT) turbine blade development program, unique turbine blade design features were implemented to address 2nd stage turbine blade high cycle fatigue distress and improve turbine robustness. Features included the addition of platform featherseal dampers, asymmetric blade tip seal segments, gold plating of the blade attachments, and airfoil tip trailing edge modifications. Development testing shows these features have eliminated turbine blade high cycle fatigue distress and consequently these features are currently planned for incorporation to the flight configuration. Certification testing will begin in 1999. This presentation summarizes these features.

Multi-channel EEG-based sleep stage classification with joint collaborative representation and multiple kernel learning.

PubMed

Shi, Jun; Liu, Xiao; Li, Yan; Zhang, Qi; Li, Yingjie; Ying, Shihui

2015-10-30

Electroencephalography (EEG) based sleep staging is commonly used in clinical routine. Feature extraction and representation plays a crucial role in EEG-based automatic classification of sleep stages. Sparse representation (SR) is a state-of-the-art unsupervised feature learning method suitable for EEG feature representation. Collaborative representation (CR) is an effective data coding method used as a classifier. Here we use CR as a data representation method to learn features from the EEG signal. A joint collaboration model is established to develop a multi-view learning algorithm, and generate joint CR (JCR) codes to fuse and represent multi-channel EEG signals. A two-stage multi-view learning-based sleep staging framework is then constructed, in which JCR and joint sparse representation (JSR) algorithms first fuse and learning the feature representation from multi-channel EEG signals, respectively. Multi-view JCR and JSR features are then integrated and sleep stages recognized by a multiple kernel extreme learning machine (MK-ELM) algorithm with grid search. The proposed two-stage multi-view learning algorithm achieves superior performance for sleep staging. With a K-means clustering based dictionary, the mean classification accuracy, sensitivity and specificity are 81.10 ± 0.15%, 71.42 ± 0.66% and 94.57 ± 0.07%, respectively; while with the dictionary learned using the submodular optimization method, they are 80.29 ± 0.22%, 71.26 ± 0.78% and 94.38 ± 0.10%, respectively. The two-stage multi-view learning based sleep staging framework outperforms all other classification methods compared in this work, while JCR is superior to JSR. The proposed multi-view learning framework has the potential for sleep staging based on multi-channel or multi-modality polysomnography signals. Copyright © 2015 Elsevier B.V. All rights reserved.

A Review of Integrating Mobile Phones for Language Learning

ERIC Educational Resources Information Center

Darmi, Ramiza; Albion, Peter

2014-01-01

Mobile learning (m-learning) is gradually being introduced in language classrooms. All forms of mobile technology represent portability with smarter features. Studies have proven the concomitant role of technology beneficial for language learning. Various features in the technology have been exploited and researched for acquiring and learning…

Prediction of residue-residue contact matrix for protein-protein interaction with Fisher score features and deep learning.

PubMed

Du, Tianchuan; Liao, Li; Wu, Cathy H; Sun, Bilin

2016-11-01

Protein-protein interactions play essential roles in many biological processes. Acquiring knowledge of the residue-residue contact information of two interacting proteins is not only helpful in annotating functions for proteins, but also critical for structure-based drug design. The prediction of the protein residue-residue contact matrix of the interfacial regions is challenging. In this work, we introduced deep learning techniques (specifically, stacked autoencoders) to build deep neural network models to tackled the residue-residue contact prediction problem. In tandem with interaction profile Hidden Markov Models, which was used first to extract Fisher score features from protein sequences, stacked autoencoders were deployed to extract and learn hidden abstract features. The deep learning model showed significant improvement over the traditional machine learning model, Support Vector Machines (SVM), with the overall accuracy increased by 15% from 65.40% to 80.82%. We showed that the stacked autoencoders could extract novel features, which can be utilized by deep neural networks and other classifiers to enhance learning, out of the Fisher score features. It is further shown that deep neural networks have significant advantages over SVM in making use of the newly extracted features. Copyright © 2016. Published by Elsevier Inc.

Internal attention to features in visual short-term memory guides object learning

PubMed Central

Fan, Judith E.; Turk-Browne, Nicholas B.

2013-01-01

Attending to objects in the world affects how we perceive and remember them. What are the consequences of attending to an object in mind? In particular, how does reporting the features of a recently seen object guide visual learning? In three experiments, observers were presented with abstract shapes in a particular color, orientation, and location. After viewing each object, observers were cued to report one feature from visual short-term memory (VSTM). In a subsequent test, observers were cued to report features of the same objects from visual long-term memory (VLTM). We tested whether reporting a feature from VSTM: (1) enhances VLTM for just that feature (practice-benefit hypothesis), (2) enhances VLTM for all features (object-based hypothesis), or (3) simultaneously enhances VLTM for that feature and suppresses VLTM for unreported features (feature-competition hypothesis). The results provided support for the feature-competition hypothesis, whereby the representation of an object in VLTM was biased towards features reported from VSTM and away from unreported features (Experiment 1). This bias could not be explained by the amount of sensory exposure or response learning (Experiment 2) and was amplified by the reporting of multiple features (Experiment 3). Taken together, these results suggest that selective internal attention induces competitive dynamics among features during visual learning, flexibly tuning object representations to align with prior mnemonic goals. PMID:23954925

Internal attention to features in visual short-term memory guides object learning.

PubMed

Fan, Judith E; Turk-Browne, Nicholas B

2013-11-01

Attending to objects in the world affects how we perceive and remember them. What are the consequences of attending to an object in mind? In particular, how does reporting the features of a recently seen object guide visual learning? In three experiments, observers were presented with abstract shapes in a particular color, orientation, and location. After viewing each object, observers were cued to report one feature from visual short-term memory (VSTM). In a subsequent test, observers were cued to report features of the same objects from visual long-term memory (VLTM). We tested whether reporting a feature from VSTM: (1) enhances VLTM for just that feature (practice-benefit hypothesis), (2) enhances VLTM for all features (object-based hypothesis), or (3) simultaneously enhances VLTM for that feature and suppresses VLTM for unreported features (feature-competition hypothesis). The results provided support for the feature-competition hypothesis, whereby the representation of an object in VLTM was biased towards features reported from VSTM and away from unreported features (Experiment 1). This bias could not be explained by the amount of sensory exposure or response learning (Experiment 2) and was amplified by the reporting of multiple features (Experiment 3). Taken together, these results suggest that selective internal attention induces competitive dynamics among features during visual learning, flexibly tuning object representations to align with prior mnemonic goals. Copyright © 2013 Elsevier B.V. All rights reserved.

A SCALE-UP Mock-Up: Comparison of Student Learning Gains in High- and Low-Tech Active-Learning Environments

ERIC Educational Resources Information Center

Soneral, Paula A. G.; Wyse, Sara A.

2017-01-01

Student-centered learning environments with upside-down pedagogies (SCALE-UP) are widely implemented at institutions across the country, and learning gains from these classrooms have been well documented. This study investigates the specific design feature(s) of the SCALE-UP classroom most conducive to teaching and learning. Using pilot survey…

The cost of selective attention in category learning: Developmental differences between adults and infants

PubMed Central

Best, Catherine A.; Yim, Hyungwook; Sloutsky, Vladimir M.

2013-01-01

Selective attention plays an important role in category learning. However, immaturities of top-down attentional control during infancy coupled with successful category learning suggest that early category learning is achieved without attending selectively. Research presented here examines this possibility by focusing on category learning in infants (6–8 months old) and adults. Participants were trained on a novel visual category. Halfway through the experiment, unbeknownst to participants, the to-be-learned category switched to another category, where previously relevant features became irrelevant and previously irrelevant features became relevant. If participants attend selectively to the relevant features of the first category, they should incur a cost of selective attention immediately after the unknown category switch. Results revealed that adults demonstrated a cost, as evidenced by a decrease in accuracy and response time on test trials as well as a decrease in visual attention to newly relevant features. In contrast, infants did not demonstrate a similar cost of selective attention as adults despite evidence of learning both to-be-learned categories. Findings are discussed as supporting multiple systems of category learning and as suggesting that learning mechanisms engaged by adults may be different from those engaged by infants. PMID:23773914

Influence of Perceptual Saliency Hierarchy on Learning of Language Structures: An Artificial Language Learning Experiment

PubMed Central

Gong, Tao; Lam, Yau W.; Shuai, Lan

2016-01-01

Psychological experiments have revealed that in normal visual perception of humans, color cues are more salient than shape cues, which are more salient than textural patterns. We carried out an artificial language learning experiment to study whether such perceptual saliency hierarchy (color > shape > texture) influences the learning of orders regulating adjectives of involved visual features in a manner either congruent (expressing a salient feature in a salient part of the form) or incongruent (expressing a salient feature in a less salient part of the form) with that hierarchy. Results showed that within a few rounds of learning participants could learn the compositional segments encoding the visual features and the order between them, generalize the learned knowledge to unseen instances with the same or different orders, and show learning biases for orders that are congruent with the perceptual saliency hierarchy. Although the learning performances for both the biased and unbiased orders became similar given more learning trials, our study confirms that this type of individual perceptual constraint could contribute to the structural configuration of language, and points out that such constraint, as well as other factors, could collectively affect the structural diversity in languages. PMID:28066281

Influence of Perceptual Saliency Hierarchy on Learning of Language Structures: An Artificial Language Learning Experiment.

PubMed

Gong, Tao; Lam, Yau W; Shuai, Lan

2016-01-01

Psychological experiments have revealed that in normal visual perception of humans, color cues are more salient than shape cues, which are more salient than textural patterns. We carried out an artificial language learning experiment to study whether such perceptual saliency hierarchy (color > shape > texture) influences the learning of orders regulating adjectives of involved visual features in a manner either congruent (expressing a salient feature in a salient part of the form) or incongruent (expressing a salient feature in a less salient part of the form) with that hierarchy. Results showed that within a few rounds of learning participants could learn the compositional segments encoding the visual features and the order between them, generalize the learned knowledge to unseen instances with the same or different orders, and show learning biases for orders that are congruent with the perceptual saliency hierarchy. Although the learning performances for both the biased and unbiased orders became similar given more learning trials, our study confirms that this type of individual perceptual constraint could contribute to the structural configuration of language, and points out that such constraint, as well as other factors, could collectively affect the structural diversity in languages.

Experiential Learning: From Discourse Model to Conversation. Interview with David Kolb.

ERIC Educational Resources Information Center

Hamalainen, Kauko; Siirala, Eeva

1998-01-01

In this interview, Kolb, developer of the experiential learning cycle model, explores learning motivation, aspects of conversation (as experiential learning and as evaluation), and standardization versus diversity in education. (SK)

Effects of Vocal Fold Nodules on Glottal Cycle Measurements Derived from High-Speed Videoendoscopy in Children

PubMed Central

2016-01-01

The goal of this study is to quantify the effects of vocal fold nodules on vibratory motion in children using high-speed videoendoscopy. Differences in vibratory motion were evaluated in 20 children with vocal fold nodules (5–11 years) and 20 age and gender matched typically developing children (5–11 years) during sustained phonation at typical pitch and loudness. Normalized kinematic features of vocal fold displacements from the mid-membranous vocal fold point were extracted from the steady-state high-speed video. A total of 12 kinematic features representing spatial and temporal characteristics of vibratory motion were calculated. Average values and standard deviations (cycle-to-cycle variability) of the following kinematic features were computed: normalized peak displacement, normalized average opening velocity, normalized average closing velocity, normalized peak closing velocity, speed quotient, and open quotient. Group differences between children with and without vocal fold nodules were statistically investigated. While a moderate effect size was observed for the spatial feature of speed quotient, and the temporal feature of normalized average closing velocity in children with nodules compared to vocally normal children, none of the features were statistically significant between the groups after Bonferroni correction. The kinematic analysis of the mid-membranous vocal fold displacement revealed that children with nodules primarily differ from typically developing children in closing phase kinematics of the glottal cycle, whereas the opening phase kinematics are similar. Higher speed quotients and similar opening phase velocities suggest greater relative forces are acting on vocal fold in the closing phase. These findings suggest that future large-scale studies should focus on spatial and temporal features related to the closing phase of the glottal cycle for differentiating the kinematics of children with and without vocal fold nodules. PMID:27124157

Unsupervised Deep Learning Applied to Breast Density Segmentation and Mammographic Risk Scoring.

PubMed

Kallenberg, Michiel; Petersen, Kersten; Nielsen, Mads; Ng, Andrew Y; Pengfei Diao; Igel, Christian; Vachon, Celine M; Holland, Katharina; Winkel, Rikke Rass; Karssemeijer, Nico; Lillholm, Martin

2016-05-01

Mammographic risk scoring has commonly been automated by extracting a set of handcrafted features from mammograms, and relating the responses directly or indirectly to breast cancer risk. We present a method that learns a feature hierarchy from unlabeled data. When the learned features are used as the input to a simple classifier, two different tasks can be addressed: i) breast density segmentation, and ii) scoring of mammographic texture. The proposed model learns features at multiple scales. To control the models capacity a novel sparsity regularizer is introduced that incorporates both lifetime and population sparsity. We evaluated our method on three different clinical datasets. Our state-of-the-art results show that the learned breast density scores have a very strong positive relationship with manual ones, and that the learned texture scores are predictive of breast cancer. The model is easy to apply and generalizes to many other segmentation and scoring problems.

Hybrid image representation learning model with invariant features for basal cell carcinoma detection

NASA Astrophysics Data System (ADS)

Arevalo, John; Cruz-Roa, Angel; González, Fabio A.

2013-11-01

This paper presents a novel method for basal-cell carcinoma detection, which combines state-of-the-art methods for unsupervised feature learning (UFL) and bag of features (BOF) representation. BOF, which is a form of representation learning, has shown a good performance in automatic histopathology image classi cation. In BOF, patches are usually represented using descriptors such as SIFT and DCT. We propose to use UFL to learn the patch representation itself. This is accomplished by applying a topographic UFL method (T-RICA), which automatically learns visual invariance properties of color, scale and rotation from an image collection. These learned features also reveals these visual properties associated to cancerous and healthy tissues and improves carcinoma detection results by 7% with respect to traditional autoencoders, and 6% with respect to standard DCT representations obtaining in average 92% in terms of F-score and 93% of balanced accuracy.

Deep learning of support vector machines with class probability output networks.

PubMed

Kim, Sangwook; Yu, Zhibin; Kil, Rhee Man; Lee, Minho

2015-04-01

Deep learning methods endeavor to learn features automatically at multiple levels and allow systems to learn complex functions mapping from the input space to the output space for the given data. The ability to learn powerful features automatically is increasingly important as the volume of data and range of applications of machine learning methods continues to grow. This paper proposes a new deep architecture that uses support vector machines (SVMs) with class probability output networks (CPONs) to provide better generalization power for pattern classification problems. As a result, deep features are extracted without additional feature engineering steps, using multiple layers of the SVM classifiers with CPONs. The proposed structure closely approaches the ideal Bayes classifier as the number of layers increases. Using a simulation of classification problems, the effectiveness of the proposed method is demonstrated. Copyright © 2014 Elsevier Ltd. All rights reserved.

Crack Damage Detection Method via Multiple Visual Features and Efficient Multi-Task Learning Model.

PubMed

Wang, Baoxian; Zhao, Weigang; Gao, Po; Zhang, Yufeng; Wang, Zhe

2018-06-02

This paper proposes an effective and efficient model for concrete crack detection. The presented work consists of two modules: multi-view image feature extraction and multi-task crack region detection. Specifically, multiple visual features (such as texture, edge, etc.) of image regions are calculated, which can suppress various background noises (such as illumination, pockmark, stripe, blurring, etc.). With the computed multiple visual features, a novel crack region detector is advocated using a multi-task learning framework, which involves restraining the variability for different crack region features and emphasizing the separability between crack region features and complex background ones. Furthermore, the extreme learning machine is utilized to construct this multi-task learning model, thereby leading to high computing efficiency and good generalization. Experimental results of the practical concrete images demonstrate that the developed algorithm can achieve favorable crack detection performance compared with traditional crack detectors.

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.

Deep learning based classification for head and neck cancer detection with hyperspectral imaging in an animal model

NASA Astrophysics Data System (ADS)

Ma, Ling; Lu, Guolan; Wang, Dongsheng; Wang, Xu; Chen, Zhuo Georgia; Muller, Susan; Chen, Amy; Fei, Baowei

2017-03-01

Hyperspectral imaging (HSI) is an emerging imaging modality that can provide a noninvasive tool for cancer detection and image-guided surgery. HSI acquires high-resolution images at hundreds of spectral bands, providing big data to differentiating different types of tissue. We proposed a deep learning based method for the detection of head and neck cancer with hyperspectral images. Since the deep learning algorithm can learn the feature hierarchically, the learned features are more discriminative and concise than the handcrafted features. In this study, we adopt convolutional neural networks (CNN) to learn the deep feature of pixels for classifying each pixel into tumor or normal tissue. We evaluated our proposed classification method on the dataset containing hyperspectral images from 12 tumor-bearing mice. Experimental results show that our method achieved an average accuracy of 91.36%. The preliminary study demonstrated that our deep learning method can be applied to hyperspectral images for detecting head and neck tumors in animal models.

Newton's First Law: A Learning Cycle Approach

ERIC Educational Resources Information Center

McCarthy, Deborah

2005-01-01

To demonstrate how Newton's first law of motion applies to students' everyday lives, the author developed a learning cycle series of activities on inertia. The discrepant event at the heart of these activities is sure to elicit wide-eyed stares and puzzled looks from students, but also promote critical thinking and help bring an abstract concept…

Life-Cycle Analysis and Inquiry-Based Learning in Chemistry Teaching

ERIC Educational Resources Information Center

Juntunen, Marianne; Aksela, Maija

2013-01-01

The purpose of this design research is to improve the quality of environmental literacy and sustainability education in chemistry teaching through combining a socio-scientific issue, life-cycle analysis (LCA), with inquiry-based learning (IBL). This first phase of the cyclic design research involved 20 inservice trained chemistry teachers from…

Sequencing Language and Activities in Teaching High School Chemistry. A Report to the National Science Foundation.

ERIC Educational Resources Information Center

Abraham, Michael R.; Renner, John W.

A learning cycle consists of three phases: exploration; conceptual invention; and expansion of an idea. These phases parallel Piaget's functioning model of assimilation, disequilibrium and accomodation, and organization respectively. The learning cycle perceives students as actors rather than reactors to the environment. Inherent in that…

Developing a Multi-Year Learning Progression for Carbon Cycling in Socio-Ecological Systems

ERIC Educational Resources Information Center

Mohan, Lindsey; Chen, Jing; Anderson, Charles W.

2009-01-01

This study reports on our steps toward achieving a conceptually coherent and empirically validated learning progression for carbon cycling in socio-ecological systems. It describes an iterative process of designing and analyzing assessment and interview data from students in upper elementary through high school. The product of our development…

Teachers Teaching Teachers (T3)[TM]. Volume 4, Number 7

ERIC Educational Resources Information Center

von Frank, Valerie, Ed.

2009-01-01

"Teachers Teaching Teachers" ("T3") focuses on coaches' roles in the professional development of teachers. Each issue also explores the challenges and rewards that teacher leaders encounter. This issue includes: (1) Learning Cycle Spins Individuals into a Team (Valerie von Frank); (2) NSDC Tool: The Professional Teaching and Learning Cycle; (3)…

Using the 5E Learning Cycle Sequence with Carbon Dioxide

ERIC Educational Resources Information Center

Schlenker, Richard M.; Blanke, Regina; Mecca, Peter

2007-01-01

The authors used the 5E learning cycle (engage, explore, explain, extend, and evaluate) and a pulmonary carbon dioxide mystery to introduce eighth grade students to the study of chemistry. The activity engages students in measurement, data collection, data analysis, media and internet research, research design, and report writing as they search…

Lives in Context: Facilitating Online, Cross-Course, Collaborative Service Projects

ERIC Educational Resources Information Center

Elwood, Susan A.

2014-01-01

An inquiry-based, cross-course, collaborative structure is being implemented toward a graduate program's goals of using project-based learning as a consistent, core learning experience in each course cycle. This paper focuses upon the course collaborative structure and the two key forms of assessment used in each collaborative cycle: a progressive…

Two-layer contractive encodings for learning stable nonlinear features.

PubMed

Schulz, Hannes; Cho, Kyunghyun; Raiko, Tapani; Behnke, Sven

2015-04-01

Unsupervised learning of feature hierarchies is often a good strategy to initialize deep architectures for supervised learning. Most existing deep learning methods build these feature hierarchies layer by layer in a greedy fashion using either auto-encoders or restricted Boltzmann machines. Both yield encoders which compute linear projections of input followed by a smooth thresholding function. In this work, we demonstrate that these encoders fail to find stable features when the required computation is in the exclusive-or class. To overcome this limitation, we propose a two-layer encoder which is less restricted in the type of features it can learn. The proposed encoder is regularized by an extension of previous work on contractive regularization. This proposed two-layer contractive encoder potentially poses a more difficult optimization problem, and we further propose to linearly transform hidden neurons of the encoder to make learning easier. We demonstrate the advantages of the two-layer encoders qualitatively on artificially constructed datasets as well as commonly used benchmark datasets. We also conduct experiments on a semi-supervised learning task and show the benefits of the proposed two-layer encoders trained with the linear transformation of perceptrons. Copyright © 2014 Elsevier Ltd. All rights reserved.

Maximum entropy methods for extracting the learned features of deep neural networks.

PubMed

Finnegan, Alex; Song, Jun S

2017-10-01

New architectures of multilayer artificial neural networks and new methods for training them are rapidly revolutionizing the application of machine learning in diverse fields, including business, social science, physical sciences, and biology. Interpreting deep neural networks, however, currently remains elusive, and a critical challenge lies in understanding which meaningful features a network is actually learning. We present a general method for interpreting deep neural networks and extracting network-learned features from input data. We describe our algorithm in the context of biological sequence analysis. Our approach, based on ideas from statistical physics, samples from the maximum entropy distribution over possible sequences, anchored at an input sequence and subject to constraints implied by the empirical function learned by a network. Using our framework, we demonstrate that local transcription factor binding motifs can be identified from a network trained on ChIP-seq data and that nucleosome positioning signals are indeed learned by a network trained on chemical cleavage nucleosome maps. Imposing a further constraint on the maximum entropy distribution also allows us to probe whether a network is learning global sequence features, such as the high GC content in nucleosome-rich regions. This work thus provides valuable mathematical tools for interpreting and extracting learned features from feed-forward neural networks.

The Comparative Effects of Prediction/Discussion-Based Learning Cycle, Conceptual Change Text, and Traditional Instructions on Student Understanding of Genetics

NASA Astrophysics Data System (ADS)

Yilmaz, Diba; Tekkaya, Ceren; Sungur, Semra

2011-03-01

The present study examined the comparative effects of a prediction/discussion-based learning cycle, conceptual change text (CCT), and traditional instructions on students' understanding of genetics concepts. A quasi-experimental research design of the pre-test-post-test non-equivalent control group was adopted. The three intact classes, taught by the same science teacher, were randomly assigned as prediction/discussion-based learning cycle class (N = 30), CCT class (N = 25), and traditional class (N = 26). Participants completed the genetics concept test as pre-test, post-test, and delayed post-test to examine the effects of instructional strategies on their genetics understanding and retention. While the dependent variable of this study was students' understanding of genetics, the independent variables were time (Time 1, Time 2, and Time 3) and mode of instruction. The mixed between-within subjects analysis of variance revealed that students in both prediction/discussion-based learning cycle and CCT groups understood the genetics concepts and retained their knowledge significantly better than students in the traditional instruction group.

Infrared vehicle recognition using unsupervised feature learning based on K-feature

NASA Astrophysics Data System (ADS)

Lin, Jin; Tan, Yihua; Xia, Haijiao; Tian, Jinwen

2018-02-01

Subject to the complex battlefield environment, it is difficult to establish a complete knowledge base in practical application of vehicle recognition algorithms. The infrared vehicle recognition is always difficult and challenging, which plays an important role in remote sensing. In this paper we propose a new unsupervised feature learning method based on K-feature to recognize vehicle in infrared images. First, we use the target detection algorithm which is based on the saliency to detect the initial image. Then, the unsupervised feature learning based on K-feature, which is generated by Kmeans clustering algorithm that extracted features by learning a visual dictionary from a large number of samples without label, is calculated to suppress the false alarm and improve the accuracy. Finally, the vehicle target recognition image is finished by some post-processing. Large numbers of experiments demonstrate that the proposed method has satisfy recognition effectiveness and robustness for vehicle recognition in infrared images under complex backgrounds, and it also improve the reliability of it.

Comparison of Feature Learning Methods for Human Activity Recognition Using Wearable Sensors

PubMed Central

Li, Frédéric; Nisar, Muhammad Adeel; Köping, Lukas; Grzegorzek, Marcin

2018-01-01

Getting a good feature representation of data is paramount for Human Activity Recognition (HAR) using wearable sensors. An increasing number of feature learning approaches—in particular deep-learning based—have been proposed to extract an effective feature representation by analyzing large amounts of data. However, getting an objective interpretation of their performances faces two problems: the lack of a baseline evaluation setup, which makes a strict comparison between them impossible, and the insufficiency of implementation details, which can hinder their use. In this paper, we attempt to address both issues: we firstly propose an evaluation framework allowing a rigorous comparison of features extracted by different methods, and use it to carry out extensive experiments with state-of-the-art feature learning approaches. We then provide all the codes and implementation details to make both the reproduction of the results reported in this paper and the re-use of our framework easier for other researchers. Our studies carried out on the OPPORTUNITY and UniMiB-SHAR datasets highlight the effectiveness of hybrid deep-learning architectures involving convolutional and Long-Short-Term-Memory (LSTM) to obtain features characterising both short- and long-term time dependencies in the data. PMID:29495310

Comparison of Feature Learning Methods for Human Activity Recognition Using Wearable Sensors.

PubMed

Li, Frédéric; Shirahama, Kimiaki; Nisar, Muhammad Adeel; Köping, Lukas; Grzegorzek, Marcin

2018-02-24

Getting a good feature representation of data is paramount for Human Activity Recognition (HAR) using wearable sensors. An increasing number of feature learning approaches-in particular deep-learning based-have been proposed to extract an effective feature representation by analyzing large amounts of data. However, getting an objective interpretation of their performances faces two problems: the lack of a baseline evaluation setup, which makes a strict comparison between them impossible, and the insufficiency of implementation details, which can hinder their use. In this paper, we attempt to address both issues: we firstly propose an evaluation framework allowing a rigorous comparison of features extracted by different methods, and use it to carry out extensive experiments with state-of-the-art feature learning approaches. We then provide all the codes and implementation details to make both the reproduction of the results reported in this paper and the re-use of our framework easier for other researchers. Our studies carried out on the OPPORTUNITY and UniMiB-SHAR datasets highlight the effectiveness of hybrid deep-learning architectures involving convolutional and Long-Short-Term-Memory (LSTM) to obtain features characterising both short- and long-term time dependencies in the data.

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.

Cascaded K-means convolutional feature learner and its application to face recognition

NASA Astrophysics Data System (ADS)

Zhou, Daoxiang; Yang, Dan; Zhang, Xiaohong; Huang, Sheng; Feng, Shu

2017-09-01

Currently, considerable efforts have been devoted to devise image representation. However, handcrafted methods need strong domain knowledge and show low generalization ability, and conventional feature learning methods require enormous training data and rich parameters tuning experience. A lightened feature learner is presented to solve these problems with application to face recognition, which shares similar topology architecture as a convolutional neural network. Our model is divided into three components: cascaded convolution filters bank learning layer, nonlinear processing layer, and feature pooling layer. Specifically, in the filters learning layer, we use K-means to learn convolution filters. Features are extracted via convoluting images with the learned filters. Afterward, in the nonlinear processing layer, hyperbolic tangent is employed to capture the nonlinear feature. In the feature pooling layer, to remove the redundancy information and incorporate the spatial layout, we exploit multilevel spatial pyramid second-order pooling technique to pool the features in subregions and concatenate them together as the final representation. Extensive experiments on four representative datasets demonstrate the effectiveness and robustness of our model to various variations, yielding competitive recognition results on extended Yale B and FERET. In addition, our method achieves the best identification performance on AR and labeled faces in the wild datasets among the comparative methods.

Acquiring concepts and features of novel words by two types of learning: direct mapping and inference.

PubMed

Chen, Shuang; Wang, Lin; Yang, Yufang

2014-04-01

This study examined the semantic representation of novel words learnt in two conditions: directly mapping a novel word to a concept (Direct mapping: DM) and inferring the concept from provided features (Inferred learning: IF). A condition where no definite concept could be inferred (No basic-level meaning: NM) served as a baseline. The semantic representation of the novel word was assessed via a semantic-relatedness judgment task. In this task, the learned novel word served as a prime, while the corresponding concept, an unlearned feature of the concept, and an unrelated word served as targets. ERP responses to the targets, primed by the novel words in the three learning conditions, were compared. For the corresponding concept, smaller N400s were elicited in the DM and IF conditions than in the NM condition, indicating that the concept could be obtained in both learning conditions. However, for the unlearned feature, the targets in the IF condition produced an N400 effect while in the DM condition elicited an LPC effect relative to the NM learning condition. No ERP difference was observed among the three learning conditions for the unrelated words. The results indicate that conditions of learning affect the semantic representation of novel word, and that the unlearned feature was only activated by the novel word in the IF learning condition. Copyright © 2014 Elsevier Ltd. All rights reserved.

Key Features of High-Quality Policies and Guidelines to Support Social and Emotional Learning: Recommendations and Examples for the Collaborating States Initiative (CSI)

ERIC Educational Resources Information Center

Dusenbury, Linda; Yoder, Nick

2017-01-01

The current document serves two purposes. First, it provides an overview of six key features of a high-quality, comprehensive package of policies and guidance to support student social and emotional learning (SEL). These features are based on Collaborative for Academic Social, and Emotional Learning's (CASEL's) review of the research literature on…

Scalable High Performance Image Registration Framework by Unsupervised Deep Feature Representations Learning

PubMed Central

Wu, Guorong; Kim, Minjeong; Wang, Qian; Munsell, Brent C.

2015-01-01

Feature selection is a critical step in deformable image registration. In particular, selecting the most discriminative features that accurately and concisely describe complex morphological patterns in image patches improves correspondence detection, which in turn improves image registration accuracy. Furthermore, since more and more imaging modalities are being invented to better identify morphological changes in medical imaging data,, the development of deformable image registration method that scales well to new image modalities or new image applications with little to no human intervention would have a significant impact on the medical image analysis community. To address these concerns, a learning-based image registration framework is proposed that uses deep learning to discover compact and highly discriminative features upon observed imaging data. Specifically, the proposed feature selection method uses a convolutional stacked auto-encoder to identify intrinsic deep feature representations in image patches. Since deep learning is an unsupervised learning method, no ground truth label knowledge is required. This makes the proposed feature selection method more flexible to new imaging modalities since feature representations can be directly learned from the observed imaging data in a very short amount of time. Using the LONI and ADNI imaging datasets, image registration performance was compared to two existing state-of-the-art deformable image registration methods that use handcrafted features. To demonstrate the scalability of the proposed image registration framework image registration experiments were conducted on 7.0-tesla brain MR images. In all experiments, the results showed the new image registration framework consistently demonstrated more accurate registration results when compared to state-of-the-art. PMID:26552069

Scalable High-Performance Image Registration Framework by Unsupervised Deep Feature Representations Learning.

PubMed

Wu, Guorong; Kim, Minjeong; Wang, Qian; Munsell, Brent C; Shen, Dinggang

2016-07-01

Feature selection is a critical step in deformable image registration. In particular, selecting the most discriminative features that accurately and concisely describe complex morphological patterns in image patches improves correspondence detection, which in turn improves image registration accuracy. Furthermore, since more and more imaging modalities are being invented to better identify morphological changes in medical imaging data, the development of deformable image registration method that scales well to new image modalities or new image applications with little to no human intervention would have a significant impact on the medical image analysis community. To address these concerns, a learning-based image registration framework is proposed that uses deep learning to discover compact and highly discriminative features upon observed imaging data. Specifically, the proposed feature selection method uses a convolutional stacked autoencoder to identify intrinsic deep feature representations in image patches. Since deep learning is an unsupervised learning method, no ground truth label knowledge is required. This makes the proposed feature selection method more flexible to new imaging modalities since feature representations can be directly learned from the observed imaging data in a very short amount of time. Using the LONI and ADNI imaging datasets, image registration performance was compared to two existing state-of-the-art deformable image registration methods that use handcrafted features. To demonstrate the scalability of the proposed image registration framework, image registration experiments were conducted on 7.0-T brain MR images. In all experiments, the results showed that the new image registration framework consistently demonstrated more accurate registration results when compared to state of the art.

The Role of Book Features in Young Children's Transfer of Information from Picture Books to Real-World Contexts

PubMed Central

Strouse, Gabrielle A.; Nyhout, Angela; Ganea, Patricia A.

2018-01-01

Picture books are an important source of new language, concepts, and lessons for young children. A large body of research has documented the nature of parent-child interactions during shared book reading. A new body of research has begun to investigate the features of picture books that support children's learning and transfer of that information to the real world. In this paper, we discuss how children's symbolic development, analogical reasoning, and reasoning about fantasy may constrain their ability to take away content information from picture books. We then review the nascent body of findings that has focused on the impact of picture book features on children's learning and transfer of words and letters, science concepts, problem solutions, and morals from picture books. In each domain of learning we discuss how children's development may interact with book features to impact their learning. We conclude that children's ability to learn and transfer content from picture books can be disrupted by some book features and research should directly examine the interaction between children's developing abilities and book characteristics on children's learning. PMID:29467690

The Role of Book Features in Young Children's Transfer of Information from Picture Books to Real-World Contexts.

PubMed

Strouse, Gabrielle A; Nyhout, Angela; Ganea, Patricia A

2018-01-01

Picture books are an important source of new language, concepts, and lessons for young children. A large body of research has documented the nature of parent-child interactions during shared book reading. A new body of research has begun to investigate the features of picture books that support children's learning and transfer of that information to the real world. In this paper, we discuss how children's symbolic development, analogical reasoning, and reasoning about fantasy may constrain their ability to take away content information from picture books. We then review the nascent body of findings that has focused on the impact of picture book features on children's learning and transfer of words and letters, science concepts, problem solutions, and morals from picture books. In each domain of learning we discuss how children's development may interact with book features to impact their learning. We conclude that children's ability to learn and transfer content from picture books can be disrupted by some book features and research should directly examine the interaction between children's developing abilities and book characteristics on children's learning.

The Costs of Supervised Classification: The Effect of Learning Task on Conceptual Flexibility

ERIC Educational Resources Information Center

Hoffman, Aaron B.; Rehder, Bob

2010-01-01

Research has shown that learning a concept via standard supervised classification leads to a focus on diagnostic features, whereas learning by inferring missing features promotes the acquisition of within-category information. Accordingly, we predicted that classification learning would produce a deficit in people's ability to draw "novel…

Machine learning vortices at the Kosterlitz-Thouless transition

NASA Astrophysics Data System (ADS)

Beach, Matthew J. S.; Golubeva, Anna; Melko, Roger G.

2018-01-01

Efficient and automated classification of phases from minimally processed data is one goal of machine learning in condensed-matter and statistical physics. Supervised algorithms trained on raw samples of microstates can successfully detect conventional phase transitions via learning a bulk feature such as an order parameter. In this paper, we investigate whether neural networks can learn to classify phases based on topological defects. We address this question on the two-dimensional classical XY model which exhibits a Kosterlitz-Thouless transition. We find significant feature engineering of the raw spin states is required to convincingly claim that features of the vortex configurations are responsible for learning the transition temperature. We further show a single-layer network does not correctly classify the phases of the XY model, while a convolutional network easily performs classification by learning the global magnetization. Finally, we design a deep network capable of learning vortices without feature engineering. We demonstrate the detection of vortices does not necessarily result in the best classification accuracy, especially for lattices of less than approximately 1000 spins. For larger systems, it remains a difficult task to learn vortices.

Assessing reliability of fatigue indicator parameters for small crack growth via a probabilistic framework

NASA Astrophysics Data System (ADS)

Rovinelli, Andrea; Guilhem, Yoann; Proudhon, Henry; Lebensohn, Ricardo A.; Ludwig, Wolfgang; Sangid, Michael D.

2017-06-01

Microstructurally small cracks exhibit large variability in their fatigue crack growth rate. It is accepted that the inherent variability in microstructural features is related to the uncertainty in the growth rate. However, due to (i) the lack of cycle-by-cycle experimental data, (ii) the complexity of the short crack growth phenomenon, and (iii) the incomplete physics of constitutive relationships, only empirical damage metrics have been postulated to describe the short crack driving force metric (SCDFM) at the mesoscale level. The identification of the SCDFM of polycrystalline engineering alloys is a critical need, in order to achieve more reliable fatigue life prediction and improve material design. In this work, the first steps in the development of a general probabilistic framework are presented, which uses experimental result as an input, retrieves missing experimental data through crystal plasticity (CP) simulations, and extracts correlations utilizing machine learning and Bayesian networks (BNs). More precisely, experimental results representing cycle-by-cycle data of a short crack growing through a beta-metastable titanium alloy, VST-55531, have been acquired via phase and diffraction contrast tomography. These results serve as an input for FFT-based CP simulations, which provide the micromechanical fields influenced by the presence of the crack, complementing the information available from the experiment. In order to assess the correlation between postulated SCDFM and experimental observations, the data is mined and analyzed utilizing BNs. Results show the ability of the framework to autonomously capture relevant correlations and the equivalence in the prediction capability of different postulated SCDFMs for the high cycle fatigue regime.

Alexnet Feature Extraction and Multi-Kernel Learning for Objectoriented Classification

NASA Astrophysics Data System (ADS)

Ding, L.; Li, H.; Hu, C.; Zhang, W.; Wang, S.

2018-04-01

In view of the fact that the deep convolutional neural network has stronger ability of feature learning and feature expression, an exploratory research is done on feature extraction and classification for high resolution remote sensing images. Taking the Google image with 0.3 meter spatial resolution in Ludian area of Yunnan Province as an example, the image segmentation object was taken as the basic unit, and the pre-trained AlexNet deep convolution neural network model was used for feature extraction. And the spectral features, AlexNet features and GLCM texture features are combined with multi-kernel learning and SVM classifier, finally the classification results were compared and analyzed. The results show that the deep convolution neural network can extract more accurate remote sensing image features, and significantly improve the overall accuracy of classification, and provide a reference value for earthquake disaster investigation and remote sensing disaster evaluation.

Bockron as a Medium of Learning in The Process of Inquiry based Learning to Improve Science Process Skills of Junior High School Students in Growth and Development Concept

NASA Astrophysics Data System (ADS)

Mayasari, D.

2017-02-01

Investigative research on Influence of bockron as a medium of learning in process of inquiry-based learning to the development of science process skills on the concept of growth and development. This research was done in an effort to follow up underdeveloped skills of observing, communicating andconclude on students. This research was conducted using classroom action research (PTK), which consisted of 3 cycles. Cycle 1 students observe differences in growth and development, cycle 2 students measure the growth rate, cycle 3 students observe factors that influence growth and development, In these three cycles is used as a planting medium bocron (bottles and dacron). It involves 8th grade junior high-school students of 14-15 years old as research subjects in six meetings. Indicators of process skill include observation, communication, interpretation and inference. Data is collected through students’ work sheets, written tests and observation. Processing of the data to see N-Gain used Microsoft Excel 2007, and the results showed that an increase in science process skills with a value of medium N-Gain (0,63). Bokron learning medium easily and cheaply obtainable around the students, particularly those in urban areas is quite difficult to get land to be used as aplanting medium. In addition to observation of growth and development, bokron media can also be used to observe the motion in plants. The use bokron as a learning medium can train and develop science process skills, attitude and scientific method also gives students concrete experience of the process of growth and development in plants.

On equivalent parameter learning in simplified feature space based on Bayesian asymptotic analysis.

PubMed

Yamazaki, Keisuke

2012-07-01

Parametric models for sequential data, such as hidden Markov models, stochastic context-free grammars, and linear dynamical systems, are widely used in time-series analysis and structural data analysis. Computation of the likelihood function is one of primary considerations in many learning methods. Iterative calculation of the likelihood such as the model selection is still time-consuming though there are effective algorithms based on dynamic programming. The present paper studies parameter learning in a simplified feature space to reduce the computational cost. Simplifying data is a common technique seen in feature selection and dimension reduction though an oversimplified space causes adverse learning results. Therefore, we mathematically investigate a condition of the feature map to have an asymptotically equivalent convergence point of estimated parameters, referred to as the vicarious map. As a demonstration to find vicarious maps, we consider the feature space, which limits the length of data, and derive a necessary length for parameter learning in hidden Markov models. Copyright © 2012 Elsevier Ltd. All rights reserved.

Experiential Learning Theory as One of the Foundations of Adult Learning Practice Worldwide

ERIC Educational Resources Information Center

Dernova, Maiya

2015-01-01

The paper presents the analysis of existing theory, assumptions, and models of adult experiential learning. The experiential learning is a learning based on a learning cycle guided by the dual dialectics of action-reflection and experience-abstraction. It defines learning as a process of knowledge creation through experience transformation, so…

Convolutional neural network features based change detection in satellite images

NASA Astrophysics Data System (ADS)

Mohammed El Amin, Arabi; Liu, Qingjie; Wang, Yunhong

2016-07-01

With the popular use of high resolution remote sensing (HRRS) satellite images, a huge research efforts have been placed on change detection (CD) problem. An effective feature selection method can significantly boost the final result. While hand-designed features have proven difficulties to design features that effectively capture high and mid-level representations, the recent developments in machine learning (Deep Learning) omit this problem by learning hierarchical representation in an unsupervised manner directly from data without human intervention. In this letter, we propose approaching the change detection problem from a feature learning perspective. A novel deep Convolutional Neural Networks (CNN) features based HR satellite images change detection method is proposed. The main guideline is to produce a change detection map directly from two images using a pretrained CNN. This method can omit the limited performance of hand-crafted features. Firstly, CNN features are extracted through different convolutional layers. Then, a concatenation step is evaluated after an normalization step, resulting in a unique higher dimensional feature map. Finally, a change map was computed using pixel-wise Euclidean distance. Our method has been validated on real bitemporal HRRS satellite images according to qualitative and quantitative analyses. The results obtained confirm the interest of the proposed method.

The method of micro-motion cycle feature extraction based on confidence coefficient evaluation criteria

NASA Astrophysics Data System (ADS)

Tang, Chuanzi; Ren, Hongmei; Bo, Li; Jing, Huang

2017-11-01

In radar target recognition, the micro motion characteristics of target is one of the characteristics that researchers pay attention to at home and abroad, in which the characteristics of target precession cycle is one of the important characteristics of target movement characteristics. Periodic feature extraction methods have been studied for years, the complex shape of the target and the scattering center stack lead to random fluctuations of the RCS. These random fluctuations also exist certain periodicity, which has a great influence on the target recognition result. In order to solve the problem, this paper proposes a extraction method of micro-motion cycle feature based on confidence coefficient evaluation criteria.

Slow feature analysis: unsupervised learning of invariances.

PubMed

Wiskott, Laurenz; Sejnowski, Terrence J

2002-04-01

Invariant features of temporally varying signals are useful for analysis and classification. Slow feature analysis (SFA) is a new method for learning invariant or slowly varying features from a vectorial input signal. It is based on a nonlinear expansion of the input signal and application of principal component analysis to this expanded signal and its time derivative. It is guaranteed to find the optimal solution within a family of functions directly and can learn to extract a large number of decorrelated features, which are ordered by their degree of invariance. SFA can be applied hierarchically to process high-dimensional input signals and extract complex features. SFA is applied first to complex cell tuning properties based on simple cell output, including disparity and motion. Then more complicated input-output functions are learned by repeated application of SFA. Finally, a hierarchical network of SFA modules is presented as a simple model of the visual system. The same unstructured network can learn translation, size, rotation, contrast, or, to a lesser degree, illumination invariance for one-dimensional objects, depending on only the training stimulus. Surprisingly, only a few training objects suffice to achieve good generalization to new objects. The generated representation is suitable for object recognition. Performance degrades if the network is trained to learn multiple invariances simultaneously.

CircleBoard-Pro: Concrete manipulative-based learning cycle unit for learning geometry

NASA Astrophysics Data System (ADS)

Jamhari, Wongkia, Wararat

2018-01-01

Currently, a manipulative is commonly used in mathematics education as a supported tool for teaching and learning. With engaging natural interaction of a concrete manipulative and advantages of a learning cycle approach, we proposed the concrete manipulative-based learning cycle unit to promote mathematics learning. Our main objectives are to observe possibilities on the use of a concrete manipulative in learning geometry, and to assess students' understanding of a specific topic, angle properties in a circle, of secondary level students. To meet the first objective, the concrete manipulative, called CricleBoard-Pro, was designed. CircleBoard-Pro is built for easy to writing on or deleting from, accurate angle measurement, and flexible movement. Besides, learning activities and worksheets were created for helping students to learn angle properties in a circle. Twenty eighth graders on a lower secondary school in Indonesia were voluntarily involved to learn mathematics using CircleBoard-Pro with the designed learning activities and worksheets. We informally observed students' performance by focusing on criteria of using manipulative tools in learning mathematics while the learning activities were also observed in terms of whether they work and which step of activities need to be improved. The results of this part showed that CircleBoard-Pro complied the criteria of the use of the manipulative in learning mathematics. Nevertheless, parts of learning activities and worksheets need to be improved. Based on the results of the observation, CircleBoard-Pro, learning activities, and worksheets were merged together and became the CircleBoardPro embedded on 5E (Engage - Explore - Explain - Elaborate - Evaluate) learning cycle unit. Then, students understanding were assessed to reach the second objective. Six ninth graders from an Indonesian school in Thailand were recruited to participate in this study. Conceptual tests for both pre-and post-test, and semi-structured interview were used. Students' pre-and post-test answers were analyzed not only by descriptive statistics but also in qualitatively discussion. The dialogues between the interviewer and interviewees were transcribed and analyzed to find in-depth understanding. Finally, we can conclude that the participated students had better comprehension of angle properties in a circle even they could not perform proof by themselves. For further study, we will focus on how we can help students to develop their geometric thinking.

Kinesthetic Life Cycle of Stars

NASA Astrophysics Data System (ADS)

Reinfeld, Erika L.; Hartman, Mark A.

We present a kinesthetic approach to learning about the life cycle of stars. Using a simplified two-layer model for stellar structure, learners recreate kinesthetically the birth, life, and death of low- and high-mass stars. Examples of how this activity has been used in several settings outside school time provide additional resources for extending student learning about this topic.

What Belongs in Your 15-Bean Soup? Using the Learning Cycle to Address Misconceptions about Construction of Taxonomic Keys

ERIC Educational Resources Information Center

Ross, Ann; Vanderspool, Staria

2004-01-01

Students can use seed characteristics to discriminate between the different kinds of legumes using taxonomic classification processes of sorting and ranking, followed by construction of taxonomic keys. The application of the Learning Cycle process to taxonomic principles, hierarchical classification, and construction of keys presents the…

Fostering Third-Grade Students' Use of Scientific Models with the Water Cycle: Elementary Teachers' Conceptions and Practices

ERIC Educational Resources Information Center

Vo, Tina; Forbes, Cory T.; Zangori, Laura; Schwarz, Christina V.

2015-01-01

Elementary teachers play a crucial role in supporting and scaffolding students' model-based reasoning about natural phenomena, particularly complex systems such as the water cycle. However, little research exists to inform efforts in supporting elementary teachers' learning to foster model-centered, science learning environments. To address this…

Clash of the Titans

ERIC Educational Resources Information Center

Subramaniam, Karthigeyan

2010-01-01

WebQuests and the 5E learning cycle are titans of the science classroom. These popular inquiry-based strategies are most often used as separate entities, but the author has discovered that using a combined WebQuest and 5E learning cycle format taps into the inherent power and potential of both strategies. In the lesson, "Clash of the Titans,"…

Synthesizing Huber's Problem Solving and Kolb's Learning Cycle: A Balanced Approach to Technical Problem Solving

ERIC Educational Resources Information Center

Kamis, Arnold; Khan, Beverly K.

2009-01-01

How do we model and improve technical problem solving, such as network subnetting? This paper reports an experimental study that tested several hypotheses derived from Kolb's experiential learning cycle and Huber's problem solving model. As subjects solved a network subnetting problem, they mapped their mental processes according to Huber's…

Cycles for Science: Biology Curriculum Supplement for Grades 9-12. A Steel Cycles Program.

ERIC Educational Resources Information Center

Rogers, Diana; Laymon, Carol

This document contains project-oriented lessons and hands-on activities developed to integrate steel recycling, natural resource conservation, and solid waster management into science learning. It is designed to assist secondary teachers and students (grades 9-12) in meeting state and local goals for learning in biology, chemistry, general science…

Organisational Learning and the Organisational Life Cycle: The Differential Aspects of an Integrated Relationship in SMEs

ERIC Educational Resources Information Center

Tam, Steven; Gray, David E.

2016-01-01

Purpose: The purpose of this study is to relate the practice of organisational learning in small- and medium-sized enterprises (SMEs) to the organisational life cycle (OLC), contextualising the differential aspects of an integrated relationship between them. Design/methodology/approach: It is a mixed-method study with two consecutive phases. In…

Redefining Our Roles as Teachers, Learners, and Leaders through Continuous Cycles of Practitioner Inquiry

ERIC Educational Resources Information Center

MacDonald, Michelina; Weller, Kristin

2017-01-01

Practitioner inquiry is an alternative form of professional learning that can result in significant changes in teacher practice and student learning. We share our evolution as teacher learners within our classrooms and teacher leaders within our school as we progressed through 10 years of continuous cycles of practitioner inquiry. Beginning as…

A Learning Cycle Approach to Dealing with Pseudoscience Beliefs of Prospective Elementary Teachers.

ERIC Educational Resources Information Center

Rosenthal, Dorothy B.

1993-01-01

Describes a lesson on pseudoscience for a teaching methods course that promotes active student participation, is not a laboratory activity, and follows the sequence of the three phases associated with the learning cycle model. Contains a true-false science questionnaire to be administered to students as a bridge to discussion. (PR)

Impact of Contextuality on Mobile Learning Acceptance: An Empirical Study Based on a Language Learning App

ERIC Educational Resources Information Center

Böhm, Stephan; Constantine, Georges Philip

2016-01-01

Purpose: This paper aims to focus on contextualized features for mobile language learning apps. The scope of this paper is to explore students' perceptions of contextualized mobile language learning. Design/Methodology/Approach: An extended Technology Acceptance Model was developed to analyze the effect of contextual app features on students'…

A review on the application of deep learning in system health management

NASA Astrophysics Data System (ADS)

Khan, Samir; Yairi, Takehisa

2018-07-01

Given the advancements in modern technological capabilities, having an integrated health management and diagnostic strategy becomes an important part of a system's operational life-cycle. This is because it can be used to detect anomalies, analyse failures and predict the future state based on up-to-date information. By utilising condition data and on-site feedback, data models can be trained using machine learning and statistical concepts. Once trained, the logic for data processing can be embedded on on-board controllers whilst enabling real-time health assessment and analysis. However, this integration inevitably faces several difficulties and challenges for the community; indicating the need for novel approaches to address this vexing issue. Deep learning has gained increasing attention due to its potential advantages with data classification and feature extraction problems. It is an evolving research area with diverse application domains and hence its use for system health management applications must been researched if it can be used to increase overall system resilience or potential cost benefits for maintenance, repair, and overhaul activities. This article presents a systematic review of artificial intelligence based system health management with an emphasis on recent trends of deep learning within the field. Various architectures and related theories are discussed to clarify its potential. Based on the reviewed work, deep learning demonstrates plausible benefits for fault diagnosis and prognostics. However, there are a number of limitations that hinder its widespread adoption and require further development. Attention is paid to overcoming these challenges, with future opportunities being enumerated.

Changes in Cerebral Hemodynamics during Complex Motor Learning by Character Entry into Touch-Screen Terminals.

PubMed

Sagari, Akira; Iso, Naoki; Moriuchi, Takefumi; Ogahara, Kakuya; Kitajima, Eiji; Tanaka, Koji; Tabira, Takayuki; Higashi, Toshio

2015-01-01

Studies of cerebral hemodynamics during motor learning have mostly focused on neurorehabilitation interventions and their effectiveness. However, only a few imaging studies of motor learning and the underlying complex cognitive processes have been performed. We measured cerebral hemodynamics using near-infrared spectroscopy (NIRS) in relation to acquisition patterns of motor skills in healthy subjects using character entry into a touch-screen terminal. Twenty healthy, right-handed subjects who had no previous experience with character entry using a touch-screen terminal participated in this study. They were asked to enter the characters of a randomly formed Japanese syllabary into the touch-screen terminal. All subjects performed the task with their right thumb for 15 s alternating with 25 s of rest for 30 repetitions. Performance was calculated by subtracting the number of incorrect answers from the number of correct answers, and gains in motor skills were evaluated according to the changes in performance across cycles. Behavioral and oxygenated hemoglobin concentration changes across task cycles were analyzed using Spearman's rank correlations. Performance correlated positively with task cycle, thus confirming motor learning. Hemodynamic activation over the left sensorimotor cortex (SMC) showed a positive correlation with task cycle, whereas activations over the right prefrontal cortex (PFC) and supplementary motor area (SMA) showed negative correlations. We suggest that increases in finger momentum with motor learning are reflected in the activity of the left SMC. We further speculate that the right PFC and SMA were activated during the early phases of motor learning, and that this activity was attenuated with learning progress.

Virtual and physical toys: open-ended features for non-formal learning.

PubMed

Petersson, Eva; Brooks, Anthony

2006-04-01

This paper examines the integrated toy--both physical and virtual--as an essential resource for collaborative learning. This learning incorporates rehabilitation, training, and education. The data derived from two different cases. Pedagogical issues related to non-formal learning and open-ended features of design are discussed. Findings suggest that social, material, and expressive affordances constitute a base for an alterative interface to encourage children's play and learning.

The cost of selective attention in category learning: developmental differences between adults and infants.

PubMed

Best, Catherine A; Yim, Hyungwook; Sloutsky, Vladimir M

2013-10-01

Selective attention plays an important role in category learning. However, immaturities of top-down attentional control during infancy coupled with successful category learning suggest that early category learning is achieved without attending selectively. Research presented here examines this possibility by focusing on category learning in infants (6-8months old) and adults. Participants were trained on a novel visual category. Halfway through the experiment, unbeknownst to participants, the to-be-learned category switched to another category, where previously relevant features became irrelevant and previously irrelevant features became relevant. If participants attend selectively to the relevant features of the first category, they should incur a cost of selective attention immediately after the unknown category switch. Results revealed that adults demonstrated a cost, as evidenced by a decrease in accuracy and response time on test trials as well as a decrease in visual attention to newly relevant features. In contrast, infants did not demonstrate a similar cost of selective attention as adults despite evidence of learning both to-be-learned categories. Findings are discussed as supporting multiple systems of category learning and as suggesting that learning mechanisms engaged by adults may be different from those engaged by infants. Copyright © 2013 Elsevier Inc. All rights reserved.

Machine Learning for Medical Imaging

PubMed Central

Korfiatis, Panagiotis; Akkus, Zeynettin; Kline, Timothy L.

2017-01-01

Machine learning is a technique for recognizing patterns that can be applied to medical images. Although it is a powerful tool that can help in rendering medical diagnoses, it can be misapplied. Machine learning typically begins with the machine learning algorithm system computing the image features that are believed to be of importance in making the prediction or diagnosis of interest. The machine learning algorithm system then identifies the best combination of these image features for classifying the image or computing some metric for the given image region. There are several methods that can be used, each with different strengths and weaknesses. There are open-source versions of most of these machine learning methods that make them easy to try and apply to images. Several metrics for measuring the performance of an algorithm exist; however, one must be aware of the possible associated pitfalls that can result in misleading metrics. More recently, deep learning has started to be used; this method has the benefit that it does not require image feature identification and calculation as a first step; rather, features are identified as part of the learning process. Machine learning has been used in medical imaging and will have a greater influence in the future. Those working in medical imaging must be aware of how machine learning works. ©RSNA, 2017 PMID:28212054

Machine Learning for Medical Imaging.

PubMed

Erickson, Bradley J; Korfiatis, Panagiotis; Akkus, Zeynettin; Kline, Timothy L

2017-01-01

Machine learning is a technique for recognizing patterns that can be applied to medical images. Although it is a powerful tool that can help in rendering medical diagnoses, it can be misapplied. Machine learning typically begins with the machine learning algorithm system computing the image features that are believed to be of importance in making the prediction or diagnosis of interest. The machine learning algorithm system then identifies the best combination of these image features for classifying the image or computing some metric for the given image region. There are several methods that can be used, each with different strengths and weaknesses. There are open-source versions of most of these machine learning methods that make them easy to try and apply to images. Several metrics for measuring the performance of an algorithm exist; however, one must be aware of the possible associated pitfalls that can result in misleading metrics. More recently, deep learning has started to be used; this method has the benefit that it does not require image feature identification and calculation as a first step; rather, features are identified as part of the learning process. Machine learning has been used in medical imaging and will have a greater influence in the future. Those working in medical imaging must be aware of how machine learning works. © RSNA, 2017.

A Rational Model of the Effects of Distributional Information on Feature Learning

ERIC Educational Resources Information Center

Austerweil, Joseph L.; Griffiths, Thomas L.

2011-01-01

Most psychological theories treat the features of objects as being fixed and immediately available to observers. However, novel objects have an infinite array of properties that could potentially be encoded as features, raising the question of how people learn which features to use in representing those objects. We focus on the effects of…

The Hybrid Automobile and the Atkinson Cycle

NASA Astrophysics Data System (ADS)

Feldman, Bernard J.

2008-10-01

The hybrid automobile is a strikingly new automobile technology with a number of new technological features that dramatically improve energy efficiency. This paper will briefly describe how hybrid automobiles work; what are these new technological features; why the Toyota Prius hybrid internal combustion engine operates on the Atkinson cycle instead of the Otto cycle; and what are the advantages and disadvantages of the hybrid automobile. This is a follow-up to my two previous papers on the physics of automobile engines.1,2

The basic features of a closed fuel cycle without fast reactors

NASA Astrophysics Data System (ADS)

Bobrov, E. A.; Alekseev, P. N.; Teplov, P. S.

2017-01-01

In this paper the basic features of a closed fuel cycle with thermal reactors are considered. The three variants of multiple Pu and U recycling in VVER reactors was investigated. The comparison of MOX and REMIX fuel approaches for closed fuel cycle with thermal reactors is presented. All variants make possible to recycle several times the total amount of Pu and U obtained from spent fuel. The reported study was funded by RFBR according to the research project № 16-38-00021

Which Features Make Illustrations in Multimedia Learning Interesting?

ERIC Educational Resources Information Center

Magner, Ulrike Irmgard Elisabeth; Glogger, Inga; Renkl, Alexander

2016-01-01

How can illustrations motivate learners in multimedia learning? Which features make illustrations interesting? Beside the theoretical relevance of addressing these questions, these issues are practically relevant when instructional designers are to decide which features of illustrations can trigger situational interest irrespective of individual…

From Continuous Improvement to Organisational Learning: Developmental Theory.

ERIC Educational Resources Information Center

Murray, Peter; Chapman, Ross

2003-01-01

Explores continuous improvement methods, which underlie total quality management, finding barriers to implementation in practice that are related to a one-dimensional approach. Suggests a multiple, unbounded learning cycle, a holistic approach that includes adaptive learning, learning styles, generative learning, and capability development.…

Deep learning with convolutional neural networks for EEG decoding and visualization

PubMed Central

Springenberg, Jost Tobias; Fiederer, Lukas Dominique Josef; Glasstetter, Martin; Eggensperger, Katharina; Tangermann, Michael; Hutter, Frank; Burgard, Wolfram; Ball, Tonio

2017-01-01

Abstract Deep learning with convolutional neural networks (deep ConvNets) has revolutionized computer vision through end‐to‐end learning, that is, learning from the raw data. There is increasing interest in using deep ConvNets for end‐to‐end EEG analysis, but a better understanding of how to design and train ConvNets for end‐to‐end EEG decoding and how to visualize the informative EEG features the ConvNets learn is still needed. Here, we studied deep ConvNets with a range of different architectures, designed for decoding imagined or executed tasks from raw EEG. Our results show that recent advances from the machine learning field, including batch normalization and exponential linear units, together with a cropped training strategy, boosted the deep ConvNets decoding performance, reaching at least as good performance as the widely used filter bank common spatial patterns (FBCSP) algorithm (mean decoding accuracies 82.1% FBCSP, 84.0% deep ConvNets). While FBCSP is designed to use spectral power modulations, the features used by ConvNets are not fixed a priori. Our novel methods for visualizing the learned features demonstrated that ConvNets indeed learned to use spectral power modulations in the alpha, beta, and high gamma frequencies, and proved useful for spatially mapping the learned features by revealing the topography of the causal contributions of features in different frequency bands to the decoding decision. Our study thus shows how to design and train ConvNets to decode task‐related information from the raw EEG without handcrafted features and highlights the potential of deep ConvNets combined with advanced visualization techniques for EEG‐based brain mapping. Hum Brain Mapp 38:5391–5420, 2017. © 2017 Wiley Periodicals, Inc. PMID:28782865

Deep learning with convolutional neural networks for EEG decoding and visualization.

PubMed

Schirrmeister, Robin Tibor; Springenberg, Jost Tobias; Fiederer, Lukas Dominique Josef; Glasstetter, Martin; Eggensperger, Katharina; Tangermann, Michael; Hutter, Frank; Burgard, Wolfram; Ball, Tonio

2017-11-01

Deep learning with convolutional neural networks (deep ConvNets) has revolutionized computer vision through end-to-end learning, that is, learning from the raw data. There is increasing interest in using deep ConvNets for end-to-end EEG analysis, but a better understanding of how to design and train ConvNets for end-to-end EEG decoding and how to visualize the informative EEG features the ConvNets learn is still needed. Here, we studied deep ConvNets with a range of different architectures, designed for decoding imagined or executed tasks from raw EEG. Our results show that recent advances from the machine learning field, including batch normalization and exponential linear units, together with a cropped training strategy, boosted the deep ConvNets decoding performance, reaching at least as good performance as the widely used filter bank common spatial patterns (FBCSP) algorithm (mean decoding accuracies 82.1% FBCSP, 84.0% deep ConvNets). While FBCSP is designed to use spectral power modulations, the features used by ConvNets are not fixed a priori. Our novel methods for visualizing the learned features demonstrated that ConvNets indeed learned to use spectral power modulations in the alpha, beta, and high gamma frequencies, and proved useful for spatially mapping the learned features by revealing the topography of the causal contributions of features in different frequency bands to the decoding decision. Our study thus shows how to design and train ConvNets to decode task-related information from the raw EEG without handcrafted features and highlights the potential of deep ConvNets combined with advanced visualization techniques for EEG-based brain mapping. Hum Brain Mapp 38:5391-5420, 2017. © 2017 Wiley Periodicals, Inc. © 2017 The Authors Human Brain Mapping Published by Wiley Periodicals, Inc.

The Edinburgh Electronic Veterinary Curriculum: an online program-wide learning and support environment for veterinary education.

PubMed

Ellaway, Rachel; Pettigrew, Graham; Rhind, Susan; Dewhurst, David

2005-01-01

The Edinburgh Electronic Veterinary Curriculum (EEVeC) is a purpose-built virtual learning support environment for the veterinary medicine program at the University of Edinburgh. It is Web based and adapted from a system developed for the human medical curriculum. It is built around a set of databases and learning objects and incorporates features such as course materials, personalized timetables, staff and student contact pages, a notice board, and discussion forums. The EEVeC also contains global or generic resources such as information on quality enhancement and research options. Many of these features contribute to the aim of building a learning community, but a challenge has been to introduce specific features that enhance student learning. One of these is a searchable lecture database in which learning activities such as quizzes and computer-aided learning exercises (CALs) can be embedded to supplement a synopsis of the lecture and address the key needs of integration and reinforcement of learning. Statistics of use indicate extensive student activity during evenings and weekends, with a pattern of increased usage over the years as more features become available and staff and students progressively engage with the system. An essential feature of EEVeC is its flexibility and the way in which it is evolving to meet the changing needs of the teaching program.

Cyclic Game Dynamics Driven by Iterated Reasoning

PubMed Central

Frey, Seth; Goldstone, Robert L.

2013-01-01

Recent theories from complexity science argue that complex dynamics are ubiquitous in social and economic systems. These claims emerge from the analysis of individually simple agents whose collective behavior is surprisingly complicated. However, economists have argued that iterated reasoning–what you think I think you think–will suppress complex dynamics by stabilizing or accelerating convergence to Nash equilibrium. We report stable and efficient periodic behavior in human groups playing the Mod Game, a multi-player game similar to Rock-Paper-Scissors. The game rewards subjects for thinking exactly one step ahead of others in their group. Groups that play this game exhibit cycles that are inconsistent with any fixed-point solution concept. These cycles are driven by a “hopping” behavior that is consistent with other accounts of iterated reasoning: agents are constrained to about two steps of iterated reasoning and learn an additional one-half step with each session. If higher-order reasoning can be complicit in complex emergent dynamics, then cyclic and chaotic patterns may be endogenous features of real-world social and economic systems. PMID:23441191

Sensor-based atomic layer deposition for rapid process learning and enhanced manufacturability

NASA Astrophysics Data System (ADS)

Lei, Wei

In the search for sensor based atomic layer deposition (ALD) process to accelerate process learning and enhance manufacturability, we have explored new reactor designs and applied in-situ process sensing to W and HfO 2 ALD processes. A novel wafer scale ALD reactor, which features fast gas switching, good process sensing compatibility and significant similarity to the real manufacturing environment, is constructed. The reactor has a unique movable reactor cap design that allows two possible operation modes: (1) steady-state flow with alternating gas species; or (2) fill-and-pump-out cycling of each gas, accelerating the pump-out by lifting the cap to employ the large chamber volume as ballast. Downstream quadrupole mass spectrometry (QMS) sampling is applied for in-situ process sensing of tungsten ALD process. The QMS reveals essential surface reaction dynamics through real-time signals associated with byproduct generation as well as precursor introduction and depletion for each ALD half cycle, which are then used for process learning and optimization. More subtle interactions such as imperfect surface saturation and reactant dose interaction are also directly observed by QMS, indicating that ALD process is more complicated than the suggested layer-by-layer growth. By integrating in real-time the byproduct QMS signals over each exposure and plotting it against process cycle number, the deposition kinetics on the wafer is directly measured. For continuous ALD runs, the total integrated byproduct QMS signal in each ALD run is also linear to ALD film thickness, and therefore can be used for ALD film thickness metrology. The in-situ process sensing is also applied to HfO2 ALD process that is carried out in a furnace type ALD reactor. Precursor dose end-point control is applied to precisely control the precursor dose in each half cycle. Multiple process sensors, including quartz crystal microbalance (QCM) and QMS are used to provide real time process information. The sensing results confirm the proposed surface reaction path and once again reveal the complexity of ALD processes. The impact of this work includes: (1) It explores new ALD reactor designs which enable the implementation of in-situ process sensors for rapid process learning and enhanced manufacturability; (2) It demonstrates in the first time that in-situ QMS can reveal detailed process dynamics and film growth kinetics in wafer-scale ALD process, and thus can be used for ALD film thickness metrology. (3) Based on results from two different processes carried out in two different reactors, it is clear that ALD is a more complicated process than normally believed or advertised, but real-time observation of the operational chemistries in ALD by in-situ sensors provides critical insight to the process and the basis for more effective process control for ALD applications.

Using learned under-sampling pattern for increasing speed of cardiac cine MRI based on compressive sensing principles

NASA Astrophysics Data System (ADS)

Zamani, Pooria; Kayvanrad, Mohammad; Soltanian-Zadeh, Hamid

2012-12-01

This article presents a compressive sensing approach for reducing data acquisition time in cardiac cine magnetic resonance imaging (MRI). In cardiac cine MRI, several images are acquired throughout the cardiac cycle, each of which is reconstructed from the raw data acquired in the Fourier transform domain, traditionally called k-space. In the proposed approach, a majority, e.g., 62.5%, of the k-space lines (trajectories) are acquired at the odd time points and a minority, e.g., 37.5%, of the k-space lines are acquired at the even time points of the cardiac cycle. Optimal data acquisition at the even time points is learned from the data acquired at the odd time points. To this end, statistical features of the k-space data at the odd time points are clustered by fuzzy c-means and the results are considered as the states of Markov chains. The resulting data is used to train hidden Markov models and find their transition matrices. Then, the trajectories corresponding to transition matrices far from an identity matrix are selected for data acquisition. At the end, an iterative thresholding algorithm is used to reconstruct the images from the under-sampled k-space datasets. The proposed approaches for selecting the k-space trajectories and reconstructing the images generate more accurate images compared to alternative methods. The proposed under-sampling approach achieves an acceleration factor of 2 for cardiac cine MRI.

The Implementation of Physics Problem Solving Strategy Combined with Concept Map in General Physics Course

NASA Astrophysics Data System (ADS)

Hidayati, H.; Ramli, R.

2018-04-01

This paper aims to provide a description of the implementation of Physic Problem Solving strategy combined with concept maps in General Physics learning at Department of Physics, Universitas Negeri Padang. Action research has been conducted in two cycles where each end of the cycle is reflected and improved for the next cycle. Implementation of Physics Problem Solving strategy combined with concept map can increase student activity in solving general physics problem with an average increase of 15% and can improve student learning outcomes from 42,7 in the cycle I become 62,7 in cycle II in general physics at the Universitas Negeri Padang. In the future, the implementation of Physic Problem Solving strategy combined with concept maps will need to be considered in Physics courses.

Linguistic labels, dynamic visual features, and attention in infant category learning.

PubMed

Deng, Wei Sophia; Sloutsky, Vladimir M

2015-06-01

How do words affect categorization? According to some accounts, even early in development words are category markers and are different from other features. According to other accounts, early in development words are part of the input and are akin to other features. The current study addressed this issue by examining the role of words and dynamic visual features in category learning in 8- to 12-month-old infants. Infants were familiarized with exemplars from one category in a label-defined or motion-defined condition and then tested with prototypes from the studied category and from a novel contrast category. Eye-tracking results indicated that infants exhibited better category learning in the motion-defined condition than in the label-defined condition, and their attention was more distributed among different features when there was a dynamic visual feature compared with the label-defined condition. These results provide little evidence for the idea that linguistic labels are category markers that facilitate category learning. Copyright © 2015 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

Linguistic Labels, Dynamic Visual Features, and Attention in Infant Category Learning

PubMed Central

Deng, Wei (Sophia); Sloutsky, Vladimir M.

2015-01-01

How do words affect categorization? According to some accounts, even early in development, words are category markers and are different from other features. According to other accounts, early in development, words are part of the input and are akin to other features. The current study addressed this issue by examining the role of words and dynamic visual features in category learning in 8- to 12- month infants. Infants were familiarized with exemplars from one category in a label-defined or motion-defined condition and then tested with prototypes from the studied category and from a novel contrast category. Eye tracking results indicated that infants exhibited better category learning in the motion-defined than in the label-defined condition and their attention was more distributed among different features when there was a dynamic visual feature compared to the label-defined condition. These results provide little evidence for the idea that linguistic labels are category markers that facilitate category learning. PMID:25819100

Predictive Modeling of Implantation Outcome in an In Vitro Fertilization Setting: An Application of Machine Learning Methods.

PubMed

Uyar, Asli; Bener, Ayse; Ciray, H Nadir

2015-08-01

Multiple embryo transfers in in vitro fertilization (IVF) treatment increase the number of successful pregnancies while elevating the risk of multiple gestations. IVF-associated multiple pregnancies exhibit significant financial, social, and medical implications. Clinicians need to decide the number of embryos to be transferred considering the tradeoff between successful outcomes and multiple pregnancies. To predict implantation outcome of individual embryos in an IVF cycle with the aim of providing decision support on the number of embryos transferred. Retrospective cohort study. Electronic health records of one of the largest IVF clinics in Turkey. The study data set included 2453 embryos transferred at day 2 or day 3 after intracytoplasmic sperm injection (ICSI). Each embryo was represented with 18 clinical features and a class label, +1 or -1, indicating positive and negative implantation outcomes, respectively. For each classifier tested, a model was developed using two-thirds of the data set, and prediction performance was evaluated on the remaining one-third of the samples using receiver operating characteristic (ROC) analysis. The training-testing procedure was repeated 10 times on randomly split (two-thirds to one-third) data. The relative predictive values of clinical input characteristics were assessed using information gain feature weighting and forward feature selection methods. The naïve Bayes model provided 80.4% accuracy, 63.7% sensitivity, and 17.6% false alarm rate in embryo-based implantation prediction. Multiple embryo implantations were predicted at a 63.8% sensitivity level. Predictions using the proposed model resulted in higher accuracy compared with expert judgment alone (on average, 75.7% and 60.1%, respectively). A machine learning-based decision support system would be useful in improving the success rates of IVF treatment. © The Author(s) 2014.

Machine Learning for Big Data: A Study to Understand Limits at Scale

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

Sukumar, Sreenivas R.; Del-Castillo-Negrete, Carlos Emilio

This report aims to empirically understand the limits of machine learning when applied to Big Data. We observe that recent innovations in being able to collect, access, organize, integrate, and query massive amounts of data from a wide variety of data sources have brought statistical data mining and machine learning under more scrutiny, evaluation and application for gleaning insights from the data than ever before. Much is expected from algorithms without understanding their limitations at scale while dealing with massive datasets. In that context, we pose and address the following questions How does a machine learning algorithm perform on measuresmore » such as accuracy and execution time with increasing sample size and feature dimensionality? Does training with more samples guarantee better accuracy? How many features to compute for a given problem? Do more features guarantee better accuracy? Do efforts to derive and calculate more features and train on larger samples worth the effort? As problems become more complex and traditional binary classification algorithms are replaced with multi-task, multi-class categorization algorithms do parallel learners perform better? What happens to the accuracy of the learning algorithm when trained to categorize multiple classes within the same feature space? Towards finding answers to these questions, we describe the design of an empirical study and present the results. We conclude with the following observations (i) accuracy of the learning algorithm increases with increasing sample size but saturates at a point, beyond which more samples do not contribute to better accuracy/learning, (ii) the richness of the feature space dictates performance - both accuracy and training time, (iii) increased dimensionality often reflected in better performance (higher accuracy in spite of longer training times) but the improvements are not commensurate the efforts for feature computation and training and (iv) accuracy of the learning algorithms drop significantly with multi-class learners training on the same feature matrix and (v) learning algorithms perform well when categories in labeled data are independent (i.e., no relationship or hierarchy exists among categories).« less

A single-layer network unsupervised feature learning method for white matter hyperintensity segmentation

NASA Astrophysics Data System (ADS)

Vijverberg, Koen; Ghafoorian, Mohsen; van Uden, Inge W. M.; de Leeuw, Frank-Erik; Platel, Bram; Heskes, Tom

2016-03-01

Cerebral small vessel disease (SVD) is a disorder frequently found among the old people and is associated with deterioration in cognitive performance, parkinsonism, motor and mood impairments. White matter hyperintensities (WMH) as well as lacunes, microbleeds and subcortical brain atrophy are part of the spectrum of image findings, related to SVD. Accurate segmentation of WMHs is important for prognosis and diagnosis of multiple neurological disorders such as MS and SVD. Almost all of the published (semi-)automated WMH detection models employ multiple complex hand-crafted features, which require in-depth domain knowledge. In this paper we propose to apply a single-layer network unsupervised feature learning (USFL) method to avoid hand-crafted features, but rather to automatically learn a more efficient set of features. Experimental results show that a computer aided detection system with a USFL system outperforms a hand-crafted approach. Moreover, since the two feature sets have complementary properties, a hybrid system that makes use of both hand-crafted and unsupervised learned features, shows a significant performance boost compared to each system separately, getting close to the performance of an independent human expert.

Alzheimer's disease detection via automatic 3D caudate nucleus segmentation using coupled dictionary learning with level set formulation.

PubMed

Al-Shaikhli, Saif Dawood Salman; Yang, Michael Ying; Rosenhahn, Bodo

2016-12-01

This paper presents a novel method for Alzheimer's disease classification via an automatic 3D caudate nucleus segmentation. The proposed method consists of segmentation and classification steps. In the segmentation step, we propose a novel level set cost function. The proposed cost function is constrained by a sparse representation of local image features using a dictionary learning method. We present coupled dictionaries: a feature dictionary of a grayscale brain image and a label dictionary of a caudate nucleus label image. Using online dictionary learning, the coupled dictionaries are learned from the training data. The learned coupled dictionaries are embedded into a level set function. In the classification step, a region-based feature dictionary is built. The region-based feature dictionary is learned from shape features of the caudate nucleus in the training data. The classification is based on the measure of the similarity between the sparse representation of region-based shape features of the segmented caudate in the test image and the region-based feature dictionary. The experimental results demonstrate the superiority of our method over the state-of-the-art methods by achieving a high segmentation (91.5%) and classification (92.5%) accuracy. In this paper, we find that the study of the caudate nucleus atrophy gives an advantage over the study of whole brain structure atrophy to detect Alzheimer's disease. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Machine vision systems using machine learning for industrial product inspection

NASA Astrophysics Data System (ADS)

Lu, Yi; Chen, Tie Q.; Chen, Jie; Zhang, Jian; Tisler, Anthony

2002-02-01

Machine vision inspection requires efficient processing time and accurate results. In this paper, we present a machine vision inspection architecture, SMV (Smart Machine Vision). SMV decomposes a machine vision inspection problem into two stages, Learning Inspection Features (LIF), and On-Line Inspection (OLI). The LIF is designed to learn visual inspection features from design data and/or from inspection products. During the OLI stage, the inspection system uses the knowledge learnt by the LIF component to inspect the visual features of products. In this paper we will present two machine vision inspection systems developed under the SMV architecture for two different types of products, Printed Circuit Board (PCB) and Vacuum Florescent Displaying (VFD) boards. In the VFD board inspection system, the LIF component learns inspection features from a VFD board and its displaying patterns. In the PCB board inspection system, the LIF learns the inspection features from the CAD file of a PCB board. In both systems, the LIF component also incorporates interactive learning to make the inspection system more powerful and efficient. The VFD system has been deployed successfully in three different manufacturing companies and the PCB inspection system is the process of being deployed in a manufacturing plant.

Utilization of Intelligent Software Agent Features for Improving E-Learning Efforts: A Comprehensive Investigation

ERIC Educational Resources Information Center

Farzaneh, Mandana; Vanani, Iman Raeesi; Sohrabi, Babak

2012-01-01

E-learning is one of the most important learning approaches within which intelligent software agents can be efficiently used so as to automate and facilitate the process of learning. The aim of this paper is to illustrate a comprehensive categorization of intelligent software agent features, which is valuable for being deployed in the virtual…

Fault Diagnosis for Rotating Machinery Using Vibration Measurement Deep Statistical Feature Learning.

PubMed

Li, Chuan; Sánchez, René-Vinicio; Zurita, Grover; Cerrada, Mariela; Cabrera, Diego

2016-06-17

Fault diagnosis is important for the maintenance of rotating machinery. The detection of faults and fault patterns is a challenging part of machinery fault diagnosis. To tackle this problem, a model for deep statistical feature learning from vibration measurements of rotating machinery is presented in this paper. Vibration sensor signals collected from rotating mechanical systems are represented in the time, frequency, and time-frequency domains, each of which is then used to produce a statistical feature set. For learning statistical features, real-value Gaussian-Bernoulli restricted Boltzmann machines (GRBMs) are stacked to develop a Gaussian-Bernoulli deep Boltzmann machine (GDBM). The suggested approach is applied as a deep statistical feature learning tool for both gearbox and bearing systems. The fault classification performances in experiments using this approach are 95.17% for the gearbox, and 91.75% for the bearing system. The proposed approach is compared to such standard methods as a support vector machine, GRBM and a combination model. In experiments, the best fault classification rate was detected using the proposed model. The results show that deep learning with statistical feature extraction has an essential improvement potential for diagnosing rotating machinery faults.

Fault Diagnosis for Rotating Machinery Using Vibration Measurement Deep Statistical Feature Learning

PubMed Central

Li, Chuan; Sánchez, René-Vinicio; Zurita, Grover; Cerrada, Mariela; Cabrera, Diego

2016-01-01

Fault diagnosis is important for the maintenance of rotating machinery. The detection of faults and fault patterns is a challenging part of machinery fault diagnosis. To tackle this problem, a model for deep statistical feature learning from vibration measurements of rotating machinery is presented in this paper. Vibration sensor signals collected from rotating mechanical systems are represented in the time, frequency, and time-frequency domains, each of which is then used to produce a statistical feature set. For learning statistical features, real-value Gaussian-Bernoulli restricted Boltzmann machines (GRBMs) are stacked to develop a Gaussian-Bernoulli deep Boltzmann machine (GDBM). The suggested approach is applied as a deep statistical feature learning tool for both gearbox and bearing systems. The fault classification performances in experiments using this approach are 95.17% for the gearbox, and 91.75% for the bearing system. The proposed approach is compared to such standard methods as a support vector machine, GRBM and a combination model. In experiments, the best fault classification rate was detected using the proposed model. The results show that deep learning with statistical feature extraction has an essential improvement potential for diagnosing rotating machinery faults. PMID:27322273

Dynamic updating of hippocampal object representations reflects new conceptual knowledge

PubMed Central

Mack, Michael L.; Love, Bradley C.; Preston, Alison R.

2016-01-01

Concepts organize the relationship among individual stimuli or events by highlighting shared features. Often, new goals require updating conceptual knowledge to reflect relationships based on different goal-relevant features. Here, our aim is to determine how hippocampal (HPC) object representations are organized and updated to reflect changing conceptual knowledge. Participants learned two classification tasks in which successful learning required attention to different stimulus features, thus providing a means to index how representations of individual stimuli are reorganized according to changing task goals. We used a computational learning model to capture how people attended to goal-relevant features and organized object representations based on those features during learning. Using representational similarity analyses of functional magnetic resonance imaging data, we demonstrate that neural representations in left anterior HPC correspond with model predictions of concept organization. Moreover, we show that during early learning, when concept updating is most consequential, HPC is functionally coupled with prefrontal regions. Based on these findings, we propose that when task goals change, object representations in HPC can be organized in new ways, resulting in updated concepts that highlight the features most critical to the new goal. PMID:27803320

Discriminative Dictionary Learning With Two-Level Low Rank and Group Sparse Decomposition for Image Classification.

PubMed

Wen, Zaidao; Hou, Zaidao; Jiao, Licheng

2017-11-01

Discriminative dictionary learning (DDL) framework has been widely used in image classification which aims to learn some class-specific feature vectors as well as a representative dictionary according to a set of labeled training samples. However, interclass similarities and intraclass variances among input samples and learned features will generally weaken the representability of dictionary and the discrimination of feature vectors so as to degrade the classification performance. Therefore, how to explicitly represent them becomes an important issue. In this paper, we present a novel DDL framework with two-level low rank and group sparse decomposition model. In the first level, we learn a class-shared and several class-specific dictionaries, where a low rank and a group sparse regularization are, respectively, imposed on the corresponding feature matrices. In the second level, the class-specific feature matrix will be further decomposed into a low rank and a sparse matrix so that intraclass variances can be separated to concentrate the corresponding feature vectors. Extensive experimental results demonstrate the effectiveness of our model. Compared with the other state-of-the-arts on several popular image databases, our model can achieve a competitive or better performance in terms of the classification accuracy.

Molecular machinery of signal transduction and cell cycle regulation in Plasmodium.

PubMed

Koyama, Fernanda C; Chakrabarti, Debopam; Garcia, Célia R S

2009-05-01

The regulation of the Plasmodium cell cycle is not understood. Although the Plasmodium falciparum genome is completely sequenced, about 60% of the predicted proteins share little or no sequence similarity with other eukaryotes. This feature impairs the identification of important proteins participating in the regulation of the cell cycle. There are several open questions that concern cell cycle progression in malaria parasites, including the mechanism by which multiple nuclear divisions is controlled and how the cell cycle is managed in all phases of their complex life cycle. Cell cycle synchrony of the parasite population within the host, as well as the circadian rhythm of proliferation, are striking features of some Plasmodium species, the molecular basis of which remains to be elucidated. In this review we discuss the role of indole-related molecules as signals that modulate the cell cycle in Plasmodium and other eukaryotes, and we also consider the possible role of kinases in the signal transduction and in the responses it triggers.

Learning Styles: Fashion Fad or Lever for Change? The Application of Learning Style Theory to Inclusive Curriculum Delivery.

ERIC Educational Resources Information Center

Smith, Jan

2002-01-01

Examines how four classifications of learning styles--field dependence/independence, holistic/sequential, styles linked to the experiential learning cycle, and "deep" and "surface" learning--relate to curriculum values. Draws on research at Sheffield Hallam University into the learning styles of General National Vocational…

Learning feature representations with a cost-relevant sparse autoencoder.

PubMed

Längkvist, Martin; Loutfi, Amy

2015-02-01

There is an increasing interest in the machine learning community to automatically learn feature representations directly from the (unlabeled) data instead of using hand-designed features. The autoencoder is one method that can be used for this purpose. However, for data sets with a high degree of noise, a large amount of the representational capacity in the autoencoder is used to minimize the reconstruction error for these noisy inputs. This paper proposes a method that improves the feature learning process by focusing on the task relevant information in the data. This selective attention is achieved by weighting the reconstruction error and reducing the influence of noisy inputs during the learning process. The proposed model is trained on a number of publicly available image data sets and the test error rate is compared to a standard sparse autoencoder and other methods, such as the denoising autoencoder and contractive autoencoder.

Deep Learning for ECG Classification

NASA Astrophysics Data System (ADS)

Pyakillya, B.; Kazachenko, N.; Mikhailovsky, N.

2017-10-01

The importance of ECG classification is very high now due to many current medical applications where this problem can be stated. Currently, there are many machine learning (ML) solutions which can be used for analyzing and classifying ECG data. However, the main disadvantages of these ML results is use of heuristic hand-crafted or engineered features with shallow feature learning architectures. The problem relies in the possibility not to find most appropriate features which will give high classification accuracy in this ECG problem. One of the proposing solution is to use deep learning architectures where first layers of convolutional neurons behave as feature extractors and in the end some fully-connected (FCN) layers are used for making final decision about ECG classes. In this work the deep learning architecture with 1D convolutional layers and FCN layers for ECG classification is presented and some classification results are showed.

Space Object Classification Using Fused Features of Time Series Data

NASA Astrophysics Data System (ADS)

Jia, B.; Pham, K. D.; Blasch, E.; Shen, D.; Wang, Z.; Chen, G.

In this paper, a fused feature vector consisting of raw time series and texture feature information is proposed for space object classification. The time series data includes historical orbit trajectories and asteroid light curves. The texture feature is derived from recurrence plots using Gabor filters for both unsupervised learning and supervised learning algorithms. The simulation results show that the classification algorithms using the fused feature vector achieve better performance than those using raw time series or texture features only.

Comparison of hand-craft feature based SVM and CNN based deep learning framework for automatic polyp classification.

PubMed

Younghak Shin; Balasingham, Ilangko

2017-07-01

Colonoscopy is a standard method for screening polyps by highly trained physicians. Miss-detected polyps in colonoscopy are potential risk factor for colorectal cancer. In this study, we investigate an automatic polyp classification framework. We aim to compare two different approaches named hand-craft feature method and convolutional neural network (CNN) based deep learning method. Combined shape and color features are used for hand craft feature extraction and support vector machine (SVM) method is adopted for classification. For CNN approach, three convolution and pooling based deep learning framework is used for classification purpose. The proposed framework is evaluated using three public polyp databases. From the experimental results, we have shown that the CNN based deep learning framework shows better classification performance than the hand-craft feature based methods. It achieves over 90% of classification accuracy, sensitivity, specificity and precision.

Deep Learning Methods for Underwater Target Feature Extraction and Recognition

PubMed Central

Peng, Yuan; Qiu, Mengran; Shi, Jianfei; Liu, Liangliang

2018-01-01

The classification and recognition technology of underwater acoustic signal were always an important research content in the field of underwater acoustic signal processing. Currently, wavelet transform, Hilbert-Huang transform, and Mel frequency cepstral coefficients are used as a method of underwater acoustic signal feature extraction. In this paper, a method for feature extraction and identification of underwater noise data based on CNN and ELM is proposed. An automatic feature extraction method of underwater acoustic signals is proposed using depth convolution network. An underwater target recognition classifier is based on extreme learning machine. Although convolution neural networks can execute both feature extraction and classification, their function mainly relies on a full connection layer, which is trained by gradient descent-based; the generalization ability is limited and suboptimal, so an extreme learning machine (ELM) was used in classification stage. Firstly, CNN learns deep and robust features, followed by the removing of the fully connected layers. Then ELM fed with the CNN features is used as the classifier to conduct an excellent classification. Experiments on the actual data set of civil ships obtained 93.04% recognition rate; compared to the traditional Mel frequency cepstral coefficients and Hilbert-Huang feature, recognition rate greatly improved. PMID:29780407

Learning to rank using user clicks and visual features for image retrieval.

PubMed

Yu, Jun; Tao, Dacheng; Wang, Meng; Rui, Yong

2015-04-01

The inconsistency between textual features and visual contents can cause poor image search results. To solve this problem, click features, which are more reliable than textual information in justifying the relevance between a query and clicked images, are adopted in image ranking model. However, the existing ranking model cannot integrate visual features, which are efficient in refining the click-based search results. In this paper, we propose a novel ranking model based on the learning to rank framework. Visual features and click features are simultaneously utilized to obtain the ranking model. Specifically, the proposed approach is based on large margin structured output learning and the visual consistency is integrated with the click features through a hypergraph regularizer term. In accordance with the fast alternating linearization method, we design a novel algorithm to optimize the objective function. This algorithm alternately minimizes two different approximations of the original objective function by keeping one function unchanged and linearizing the other. We conduct experiments on a large-scale dataset collected from the Microsoft Bing image search engine, and the results demonstrate that the proposed learning to rank models based on visual features and user clicks outperforms state-of-the-art algorithms.

Prediction of essential proteins based on gene expression programming.

PubMed

Zhong, Jiancheng; Wang, Jianxin; Peng, Wei; Zhang, Zhen; Pan, Yi

2013-01-01

Essential proteins are indispensable for cell survive. Identifying essential proteins is very important for improving our understanding the way of a cell working. There are various types of features related to the essentiality of proteins. Many methods have been proposed to combine some of them to predict essential proteins. However, it is still a big challenge for designing an effective method to predict them by integrating different features, and explaining how these selected features decide the essentiality of protein. Gene expression programming (GEP) is a learning algorithm and what it learns specifically is about relationships between variables in sets of data and then builds models to explain these relationships. In this work, we propose a GEP-based method to predict essential protein by combing some biological features and topological features. We carry out experiments on S. cerevisiae data. The experimental results show that the our method achieves better prediction performance than those methods using individual features. Moreover, our method outperforms some machine learning methods and performs as well as a method which is obtained by combining the outputs of eight machine learning methods. The accuracy of predicting essential proteins can been improved by using GEP method to combine some topological features and biological features.

Learning Deep Representations for Ground to Aerial Geolocalization (Open Access)

DTIC Science & Technology

2015-10-15

proposed approach, Where-CNN, is inspired by deep learning success in face verification and achieves significant improvements over tra- ditional hand...crafted features and existing deep features learned from other large-scale databases. We show the ef- fectiveness of Where-CNN in finding matches

Effect of Learning Cycle Approach-Based Science Teaching on Academic Achievement, Attitude, Motivation and Retention

ERIC Educational Resources Information Center

Uyanik, Gökhan

2016-01-01

The purpose of this study was to examine the effect of learning cycle approach-based teaching on academic achievement, attitude, motivation and retention at primary school 4th grade science lesson. It was conducted pretest-posttest quasi-experimental design in this study. The study was conducted on a total of 65 students studying in two different…

Prediction/Discussion-Based Learning Cycle versus Conceptual Change Text: Comparative Effects on Students' Understanding of Genetics

ERIC Educational Resources Information Center

Al khawaldeh, Salem A.

2013-01-01

Background and Purpose: The purpose of this study was to investigate the comparative effects of a prediction/discussion-based learning cycle (HPD-LC), conceptual change text (CCT) and traditional instruction on 10th grade students' understanding of genetics concepts. Sample: Participants were 112 10th basic grade male students in three classes of…

The Comparative Effects of Prediction/Discussion-Based Learning Cycle, Conceptual Change Text, and Traditional Instructions on Student Understanding of Genetics

ERIC Educational Resources Information Center

Yilmaz, Diba; Tekkaya, Ceren; Sungur, Semra

2011-01-01

The present study examined the comparative effects of a prediction/discussion-based learning cycle, conceptual change text (CCT), and traditional instructions on students' understanding of genetics concepts. A quasi-experimental research design of the pre-test-post-test non-equivalent control group was adopted. The three intact classes, taught by…

Effect of the Four-Step Learning Cycle Model on Students' Understanding of Concepts Related to Simple Harmonic Motion

ERIC Educational Resources Information Center

Madu, B. C.

2012-01-01

The study explored the efficacy of four-step (4-E) learning cycle approach on students understanding of concepts related to Simple Harmonic Motion (SHM). 124 students (63 for experimental group and 61 for control group) participated in the study. The students' views and ideas in simple Harmonic Achievement test were analyzed qualitatively. The…

DETECTING PLANETARY GEOCHEMICAL CYCLES ON EXOPLANETS: ATMOSPHERIC SIGNATURES AND THE CASE OF SO{sub 2}

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

Kaltenegger, L.; Sasselov, D., E-mail: lkaltene@cfa.harvard.ed

2010-01-10

We study the spectrum of a planetary atmosphere to derive detectable features in low resolution of different global geochemical cycles on exoplanets-using the sulfur cycle as our example. We derive low-resolution detectable features for first generation space- and ground-based telescopes as a first step in comparative planetology. We assume that the surfaces and atmospheres of terrestrial exoplanets (Earth-like and super-Earths) will most often be dominated by a specific geochemical cycle. Here we concentrate on the sulfur cycle driven by outgassing of SO{sub 2} and H{sub 2}S followed by their transformation to other sulfur-bearing species, which is clearly distinguishable from themore » carbon cycle, which is driven by outgassing of CO{sub 2}. Due to increased volcanism, the sulfur cycle is potentially the dominant global geochemical cycle on dry super-Earths with active tectonics. We calculate planetary emission, reflection, and transmission spectrum from 0.4 mum to 40 mum with high and low resolution to assess detectable features using current and Archean Earth models with varying SO{sub 2} and H{sub 2}S concentrations to explore reducing and oxidizing habitable environments on rocky planets. We find specific spectral signatures that are observable with low resolution in a planetary atmosphere with high SO{sub 2} and H{sub 2}S concentration. Therefore, first generation space- and ground-based telescopes can test our understanding of geochemical cycles on rocky planets and potentially distinguish planetary environments dominated by the carbon and sulfur cycles.« less

Paper 8775 - Integrating Natural Resources and Ecological Science into the Disaster Risk CYCLE: Lessons Learned and Future Directions

NASA Astrophysics Data System (ADS)

Brosnan, D. M.

2014-12-01

Familiar to disaster risk reduction (DRR) scientists and professionals, the disaster cycle is an adaptive approach that involves planning, response and learning for the next event. It has proven effective in saving lives and helping communities around the world deal with natural and other hazards. But it has rarely been applied to natural resource and ecological science, despite the fact that many communities are dependent on these resources. This presentation will include lessons learned from applying science to tackle ecological consequences in several disasters in the US and globally, including the Colorado Floods, the SE Asia tsunami, the Montserrat volcanic eruption, and US SAFRR tsunami scenario. The presentation discusses the role that science and scientists can play at each phase of the disaster cycle. The consequences of not including disaster cycles in the management of natural systems leaves these resources and the huge investments made to protect highly vulnerable. The presentation discusses how The presentation discusses how science can help government and communities in planning and responding to these events. It concludes with a set of lessons learned and guidlines for moving forward.

The ability to produce media presentation among beauty study program students to prepare competence vocational school teachers

NASA Astrophysics Data System (ADS)

Widowati, Trisnani

2018-03-01

One of the challenges of this 21st century teachers are teachers who are professionals and always use it in creative ways to convey the subject matter, including the creative use of media in learning. Problems that arise are as Vocational School teachers, Beauty Study Program students have not mastered the manufacture of media presentations. Class action research conducted in three phases with the learning cycle include planning actions, implementation measures, observation/evaluation of the action, and reflection, showed an increase in the results of the study are seen from the average value derived from 55.76 on Cycle I became 71.59 on cycle II and 78.33, in cycle 3. The obstacles encountered in the process of learning that is a limited time for any learning, students are not used to plan the creation of media presentations, limitations of materials supporting the creation of student-owned media presentations: images, animations, videos and the custom copy-paste material. The given solution to overcome the barriers that is emphasized again the steps of making a media presentation, the granting of duty as an exercise, and evaluation.

Observational learning from a radical-behavioristic viewpoint

PubMed Central

Deguchi, Hikaru

1984-01-01

Bandura (1972, 1977b) has argued that observational learning has some distinctive features that set it apart from the operant paradigm: (1) acquisition simply through observation, (2) delayed performance through cognitive mediation, and (3) vicarious reinforcement. The present paper first redefines those three features at the descriptive level, and then adopts a radical-behavioristic viewpoint to show how those redefined distinctive features can be explained and tested experimentally. Finally, the origin of observational learning is discussed in terms of recent data of neonatal imitation. The present analysis offers a consistent theoretical and practical understanding of observational learning from a radical-behavioristic viewpoint. PMID:22478602

Jet-images — deep learning edition

DOE PAGES

de Oliveira, Luke; Kagan, Michael; Mackey, Lester; ...

2016-07-13

Building on the notion of a particle physics detector as a camera and the collimated streams of high energy particles, or jets, it measures as an image, we investigate the potential of machine learning techniques based on deep learning architectures to identify highly boosted W bosons. Modern deep learning algorithms trained on jet images can out-perform standard physically-motivated feature driven approaches to jet tagging. We develop techniques for visualizing how these features are learned by the network and what additional information is used to improve performance. Finally, this interplay between physically-motivated feature driven tools and supervised learning algorithms is generalmore » and can be used to significantly increase the sensitivity to discover new particles and new forces, and gain a deeper understanding of the physics within jets.« less

Jet-images — deep learning edition

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

de Oliveira, Luke; Kagan, Michael; Mackey, Lester

Building on the notion of a particle physics detector as a camera and the collimated streams of high energy particles, or jets, it measures as an image, we investigate the potential of machine learning techniques based on deep learning architectures to identify highly boosted W bosons. Modern deep learning algorithms trained on jet images can out-perform standard physically-motivated feature driven approaches to jet tagging. We develop techniques for visualizing how these features are learned by the network and what additional information is used to improve performance. Finally, this interplay between physically-motivated feature driven tools and supervised learning algorithms is generalmore » and can be used to significantly increase the sensitivity to discover new particles and new forces, and gain a deeper understanding of the physics within jets.« less

A puzzle used to teach the cardiac cycle.

PubMed

Marcondes, Fernanda K; Moura, Maria J C S; Sanches, Andrea; Costa, Rafaela; de Lima, Patricia Oliveira; Groppo, Francisco Carlos; Amaral, Maria E C; Zeni, Paula; Gaviao, Kelly Cristina; Montrezor, Luís H

2015-03-01

The aim of the present article is to describe a puzzle developed for use in teaching cardiac physiology classes. The puzzle presents figures of phases of the cardiac cycle and a table with five columns: phases of cardiac cycle, atrial state, ventricular state, state of atrioventricular valves, and pulmonary and aortic valves. Chips are provided for use to complete the table. Students are requested to discuss which is the correct sequence of figures indicating the phases of cardiac cycle. Afterward, they should complete the table with the chips. Students of biology, dentistry, medicine, pharmacy, and nursing graduation courses from seven institutions performed the puzzle evaluation. They were invited to indicate whether the puzzle had been useful for learning about the subject by filling one of four alternatives. Of the students, 4.6% answered that it was not necessary but helped them to confirm what they had learned, 64.5% reported that although they had previously understood the cardiac cycle, the puzzle helped them to solve doubts and promoted a better understanding of it, and 30.9% said that they needed the puzzle to understand the cardiac cycle, without differences among courses, institutions, and course semesters. The results of the present study suggest that a simple and inexpensive puzzle may be useful as an active learning methodology applied after the theoretical lecture, as a complementary tool for studying cardiac cycle physiology. Copyright © 2015 The American Physiological Society.

Improving management of student clinical placements: insights from activity theory.

PubMed

O'Keefe, Maree; Wade, Victoria; McAllister, Sue; Stupans, Ieva; Burgess, Teresa

2016-08-24

An approach to improve management of student clinical placements, the Building Teams for Quality Learning project, was trialed in three different health services. In a previous paper the authors explored in some detail the factors associated with considerable success of this approach at one of these services. In this paper, the authors extend this work with further analysis to determine if the more limited outcomes observed with participants at the other two services could be explained by application of activity theory and in particular the expansive learning cycle. Staff at three health services participated in the Building Teams for Quality Learning project: a dental clinic, a community aged care facility and a rural hospital. At each site a team of seven multi-disciplinary staff completed the project over 9 to 12 months (total 21 participants). Evaluation data were collected through interviews, focus groups and direct observation of staff and students. Following initial thematic analysis, further analysis was conducted to compare the processes and outcomes at each participating health service drawing on activity theory and the expansive learning cycle. Fifty-one interview transcripts, 33 h of workplace observation and 31 sets of workshop field notes (from 36 h of workshops) were generated. All participants were individually supportive of, and committed to, high quality student learning experiences. As was observed with staff at the dental clinic, a number of potentially effective strategies were discussed at the aged care facility and the rural hospital workshops. However, participants in these two health services could not develop a successful implementation plan. The expansive learning cycle element of modeling and testing new solutions was not achieved and participants were unable, collectively to reassess and reinterpret the object of their activities. The application of activity theory and the expansive learning cycle assisted a deeper understanding of the differences in outcomes observed across the three groups of participants. This included identifying specific points in the expansive learning cycle at which the three groups diverged. These findings support some practical recommendations for health services that host student clinical placements.

Design Evolution of the Wide Field Infrared Survey Telescope using Astrophysics Focused Telescope Assets (WFIRST-AFTA) and Lessons Learned

NASA Technical Reports Server (NTRS)

Peabody, Hume; Peters, Carlton; Rodriguez, Juan; McDonald, Carson; Content, David A.; Jackson, Cliff

2015-01-01

The design of the Wide Field Infrared Survey Telescope using Astrophysics Focused Telescope Assets (WFIRST-AFTA) continues to evolve as each design cycle is analyzed. In 2012, two Hubble sized (2.4 m diameter) telescopes were donated to NASA from elsewhere in the Federal Government. NASA began investigating potential uses for these telescopes and identified WFIRST as a mission to benefit from these assets. With an updated, deeper, and sharper field of view than previous design iterations with a smaller telescope, the optical designs of the WFIRST instruments were updated and the mechanical and thermal designs evolved around the new optical layout. Beginning with Design Cycle 3, significant analysis efforts yielded a design and model that could be evaluated for Structural-Thermal-Optical-Performance (STOP) purposes for the Wide Field Imager (WFI) and provided the basis for evaluating the high level observatory requirements. Development of the Cycle 3 thermal model provided some valuable analysis lessons learned and established best practices for future design cycles. However, the Cycle 3 design did include some major liens and evolving requirements which were addressed in the Cycle 4 Design. Some of the design changes are driven by requirements changes, while others are optimizations or solutions to liens from previous cycles. Again in Cycle 4, STOP analysis was performed and further insights into the overall design were gained leading to the Cycle 5 design effort currently underway. This paper seeks to capture the thermal design evolution, with focus on major design drivers, key decisions and their rationale, and lessons learned as the design evolved.

Design Evolution of the Wide Field Infrared Survey Telescope Using Astrophysics Focused Telescope Assets (WFIRST-AFTA) and Lessons Learned

NASA Technical Reports Server (NTRS)

Peabody, Hume L.; Peters, Carlton V.; Rodriguez-Ruiz, Juan E.; McDonald, Carson S.; Content, David A.; Jackson, Clifton E.

2015-01-01

The design of the Wide Field Infrared Survey Telescope using Astrophysics Focused Telescope Assets (WFIRST-AFTA) continues to evolve as each design cycle is analyzed. In 2012, two Hubble sized (2.4 m diameter) telescopes were donated to NASA from elsewhere in the Federal Government. NASA began investigating potential uses for these telescopes and identified WFIRST as a mission to benefit from these assets. With an updated, deeper, and sharper field of view than previous design iterations with a smaller telescope, the optical designs of the WFIRST instruments were updated and the mechanical and thermal designs evolved around the new optical layout. Beginning with Design Cycle 3, significant analysis efforts yielded a design and model that could be evaluated for Structural-Thermal-Optical-Performance (STOP) purposes for the Wide Field Imager (WFI) and provided the basis for evaluating the high level observatory requirements. Development of the Cycle 3 thermal model provided some valuable analysis lessons learned and established best practices for future design cycles. However, the Cycle 3 design did include some major liens and evolving requirements which were addressed in the Cycle 4 Design. Some of the design changes are driven by requirements changes, while others are optimizations or solutions to liens from previous cycles. Again in Cycle 4, STOP analysis was performed and further insights into the overall design were gained leading to the Cycle 5 design effort currently underway. This paper seeks to capture the thermal design evolution, with focus on major design drivers, key decisions and their rationale, and lessons learned as the design evolved.

Replicating human expertise of mechanical ventilation waveform analysis in detecting patient-ventilator cycling asynchrony using machine learning.

PubMed

Gholami, Behnood; Phan, Timothy S; Haddad, Wassim M; Cason, Andrew; Mullis, Jerry; Price, Levi; Bailey, James M

2018-06-01

- Acute respiratory failure is one of the most common problems encountered in intensive care units (ICU) and mechanical ventilation is the mainstay of supportive therapy for such patients. A mismatch between ventilator delivery and patient demand is referred to as patient-ventilator asynchrony (PVA). An important hurdle in addressing PVA is the lack of a reliable framework for continuously and automatically monitoring the patient and detecting various types of PVA. - The problem of replicating human expertise of waveform analysis for detecting cycling asynchrony (i.e., delayed termination, premature termination, or none) was investigated in a pilot study involving 11 patients in the ICU under invasive mechanical ventilation. A machine learning framework is used to detect cycling asynchrony based on waveform analysis. - A panel of five experts with experience in PVA evaluated a total of 1377 breath cycles from 11 mechanically ventilated critical care patients. The majority vote was used to label each breath cycle according to cycling asynchrony type. The proposed framework accurately detected the presence or absence of cycling asynchrony with sensitivity (specificity) of 89% (99%), 94% (98%), and 97% (93%) for delayed termination, premature termination, and no cycling asynchrony, respectively. The system showed strong agreement with human experts as reflected by the kappa coefficients of 0.90, 0.91, and 0.90 for delayed termination, premature termination, and no cycling asynchrony, respectively. - The pilot study establishes the feasibility of using a machine learning framework to provide waveform analysis equivalent to an expert human. Copyright © 2018 Elsevier Ltd. All rights reserved.

A study of metaheuristic algorithms for high dimensional feature selection on microarray data

NASA Astrophysics Data System (ADS)

Dankolo, Muhammad Nasiru; Radzi, Nor Haizan Mohamed; Sallehuddin, Roselina; Mustaffa, Noorfa Haszlinna

2017-11-01

Microarray systems enable experts to examine gene profile at molecular level using machine learning algorithms. It increases the potentials of classification and diagnosis of many diseases at gene expression level. Though, numerous difficulties may affect the efficiency of machine learning algorithms which includes vast number of genes features comprised in the original data. Many of these features may be unrelated to the intended analysis. Therefore, feature selection is necessary to be performed in the data pre-processing. Many feature selection algorithms are developed and applied on microarray which including the metaheuristic optimization algorithms. This paper discusses the application of the metaheuristics algorithms for feature selection in microarray dataset. This study reveals that, the algorithms have yield an interesting result with limited resources thereby saving computational expenses of machine learning algorithms.

A comparative study for chest radiograph image retrieval using binary texture and deep learning classification.

PubMed

Anavi, Yaron; Kogan, Ilya; Gelbart, Elad; Geva, Ofer; Greenspan, Hayit

2015-08-01

In this work various approaches are investigated for X-ray image retrieval and specifically chest pathology retrieval. Given a query image taken from a data set of 443 images, the objective is to rank images according to similarity. Different features, including binary features, texture features, and deep learning (CNN) features are examined. In addition, two approaches are investigated for the retrieval task. One approach is based on the distance of image descriptors using the above features (hereon termed the "descriptor"-based approach); the second approach ("classification"-based approach) is based on a probability descriptor, generated by a pair-wise classification of each two classes (pathologies) and their decision values using an SVM classifier. Best results are achieved using deep learning features in a classification scheme.

Experience, Reflect, Critique: The End of the "Learning Cycles" Era

ERIC Educational Resources Information Center

Seaman, Jayson

2008-01-01

According to prevailing models, experiential learning is by definition a stepwise process beginning with direct experience, followed by reflection, followed by learning. It has been argued, however, that stepwise models inadequately explain the holistic learning processes that are central to learning from experience, and that they lack scientific…

Machine learning approach for automated screening of malaria parasite using light microscopic images.

PubMed

Das, Dev Kumar; Ghosh, Madhumala; Pal, Mallika; Maiti, Asok K; Chakraborty, Chandan

2013-02-01

The aim of this paper is to address the development of computer assisted malaria parasite characterization and classification using machine learning approach based on light microscopic images of peripheral blood smears. In doing this, microscopic image acquisition from stained slides, illumination correction and noise reduction, erythrocyte segmentation, feature extraction, feature selection and finally classification of different stages of malaria (Plasmodium vivax and Plasmodium falciparum) have been investigated. The erythrocytes are segmented using marker controlled watershed transformation and subsequently total ninety six features describing shape-size and texture of erythrocytes are extracted in respect to the parasitemia infected versus non-infected cells. Ninety four features are found to be statistically significant in discriminating six classes. Here a feature selection-cum-classification scheme has been devised by combining F-statistic, statistical learning techniques i.e., Bayesian learning and support vector machine (SVM) in order to provide the higher classification accuracy using best set of discriminating features. Results show that Bayesian approach provides the highest accuracy i.e., 84% for malaria classification by selecting 19 most significant features while SVM provides highest accuracy i.e., 83.5% with 9 most significant features. Finally, the performance of these two classifiers under feature selection framework has been compared toward malaria parasite classification. Copyright © 2012 Elsevier Ltd. All rights reserved.

Feature Selection for Speech Emotion Recognition in Spanish and Basque: On the Use of Machine Learning to Improve Human-Computer Interaction

PubMed Central

Arruti, Andoni; Cearreta, Idoia; Álvarez, Aitor; Lazkano, Elena; Sierra, Basilio

2014-01-01

Study of emotions in human–computer interaction is a growing research area. This paper shows an attempt to select the most significant features for emotion recognition in spoken Basque and Spanish Languages using different methods for feature selection. RekEmozio database was used as the experimental data set. Several Machine Learning paradigms were used for the emotion classification task. Experiments were executed in three phases, using different sets of features as classification variables in each phase. Moreover, feature subset selection was applied at each phase in order to seek for the most relevant feature subset. The three phases approach was selected to check the validity of the proposed approach. Achieved results show that an instance-based learning algorithm using feature subset selection techniques based on evolutionary algorithms is the best Machine Learning paradigm in automatic emotion recognition, with all different feature sets, obtaining a mean of 80,05% emotion recognition rate in Basque and a 74,82% in Spanish. In order to check the goodness of the proposed process, a greedy searching approach (FSS-Forward) has been applied and a comparison between them is provided. Based on achieved results, a set of most relevant non-speaker dependent features is proposed for both languages and new perspectives are suggested. PMID:25279686

Feature learning and change feature classification based on deep learning for ternary change detection in SAR images

NASA Astrophysics Data System (ADS)

Gong, Maoguo; Yang, Hailun; Zhang, Puzhao

2017-07-01

Ternary change detection aims to detect changes and group the changes into positive change and negative change. It is of great significance in the joint interpretation of spatial-temporal synthetic aperture radar images. In this study, sparse autoencoder, convolutional neural networks (CNN) and unsupervised clustering are combined to solve ternary change detection problem without any supervison. Firstly, sparse autoencoder is used to transform log-ratio difference image into a suitable feature space for extracting key changes and suppressing outliers and noise. And then the learned features are clustered into three classes, which are taken as the pseudo labels for training a CNN model as change feature classifier. The reliable training samples for CNN are selected from the feature maps learned by sparse autoencoder with certain selection rules. Having training samples and the corresponding pseudo labels, the CNN model can be trained by using back propagation with stochastic gradient descent. During its training procedure, CNN is driven to learn the concept of change, and more powerful model is established to distinguish different types of changes. Unlike the traditional methods, the proposed framework integrates the merits of sparse autoencoder and CNN to learn more robust difference representations and the concept of change for ternary change detection. Experimental results on real datasets validate the effectiveness and superiority of the proposed framework.

The GenTechnique Project: Developing an Open Environment for Learning Molecular Genetics.

ERIC Educational Resources Information Center

Calza, R. E.; Meade, J. T.

1998-01-01

The GenTechnique project at Washington State University uses a networked learning environment for molecular genetics learning. The project is developing courseware featuring animation, hyper-link controls, and interactive self-assessment exercises focusing on fundamental concepts. The first pilot course featured a Web-based module on DNA…

Characterizing Reinforcement Learning Methods through Parameterized Learning Problems

DTIC Science & Technology

2011-06-03

extraneous. The agent could potentially adapt these representational aspects by applying methods from feature selection ( Kolter and Ng, 2009; Petrik et al...611–616. AAAI Press. Kolter , J. Z. and Ng, A. Y. (2009). Regularization and feature selection in least-squares temporal difference learning. In A. P

Robust Learning of High-dimensional Biological Networks with Bayesian Networks

NASA Astrophysics Data System (ADS)

Nägele, Andreas; Dejori, Mathäus; Stetter, Martin

Structure learning of Bayesian networks applied to gene expression data has become a potentially useful method to estimate interactions between genes. However, the NP-hardness of Bayesian network structure learning renders the reconstruction of the full genetic network with thousands of genes unfeasible. Consequently, the maximal network size is usually restricted dramatically to a small set of genes (corresponding with variables in the Bayesian network). Although this feature reduction step makes structure learning computationally tractable, on the downside, the learned structure might be adversely affected due to the introduction of missing genes. Additionally, gene expression data are usually very sparse with respect to the number of samples, i.e., the number of genes is much greater than the number of different observations. Given these problems, learning robust network features from microarray data is a challenging task. This chapter presents several approaches tackling the robustness issue in order to obtain a more reliable estimation of learned network features.

The Pedagogical, Linguistic, and Content Features of Popular English Language Learning Websites in China: A Framework for Analysis and Design

ERIC Educational Resources Information Center

Kettle, Margaret; Yuan, Yifeng; Luke, Allan; Ewing, Robyn; Shen, Huizhong

2012-01-01

As increasing numbers of Chinese language learners choose to learn English online, there is a need to investigate popular websites and their language learning designs. This paper reports on the first stage of a study that analyzed the pedagogical, linguistic, and content features of 25 Chinese English Language Learning (ELL) websites ranked…

A computational psychiatry approach identifies how alpha-2A noradrenergic agonist Guanfacine affects feature-based reinforcement learning in the macaque

PubMed Central

Hassani, S. A.; Oemisch, M.; Balcarras, M.; Westendorff, S.; Ardid, S.; van der Meer, M. A.; Tiesinga, P.; Womelsdorf, T.

2017-01-01

Noradrenaline is believed to support cognitive flexibility through the alpha 2A noradrenergic receptor (a2A-NAR) acting in prefrontal cortex. Enhanced flexibility has been inferred from improved working memory with the a2A-NA agonist Guanfacine. But it has been unclear whether Guanfacine improves specific attention and learning mechanisms beyond working memory, and whether the drug effects can be formalized computationally to allow single subject predictions. We tested and confirmed these suggestions in a case study with a healthy nonhuman primate performing a feature-based reversal learning task evaluating performance using Bayesian and Reinforcement learning models. In an initial dose-testing phase we found a Guanfacine dose that increased performance accuracy, decreased distractibility and improved learning. In a second experimental phase using only that dose we examined the faster feature-based reversal learning with Guanfacine with single-subject computational modeling. Parameter estimation suggested that improved learning is not accounted for by varying a single reinforcement learning mechanism, but by changing the set of parameter values to higher learning rates and stronger suppression of non-chosen over chosen feature information. These findings provide an important starting point for developing nonhuman primate models to discern the synaptic mechanisms of attention and learning functions within the context of a computational neuropsychiatry framework. PMID:28091572

Biologically Inspired Model for Visual Cognition Achieving Unsupervised Episodic and Semantic Feature Learning.

PubMed

Qiao, Hong; Li, Yinlin; Li, Fengfu; Xi, Xuanyang; Wu, Wei

2016-10-01

Recently, many biologically inspired visual computational models have been proposed. The design of these models follows the related biological mechanisms and structures, and these models provide new solutions for visual recognition tasks. In this paper, based on the recent biological evidence, we propose a framework to mimic the active and dynamic learning and recognition process of the primate visual cortex. From principle point of view, the main contributions are that the framework can achieve unsupervised learning of episodic features (including key components and their spatial relations) and semantic features (semantic descriptions of the key components), which support higher level cognition of an object. From performance point of view, the advantages of the framework are as follows: 1) learning episodic features without supervision-for a class of objects without a prior knowledge, the key components, their spatial relations and cover regions can be learned automatically through a deep neural network (DNN); 2) learning semantic features based on episodic features-within the cover regions of the key components, the semantic geometrical values of these components can be computed based on contour detection; 3) forming the general knowledge of a class of objects-the general knowledge of a class of objects can be formed, mainly including the key components, their spatial relations and average semantic values, which is a concise description of the class; and 4) achieving higher level cognition and dynamic updating-for a test image, the model can achieve classification and subclass semantic descriptions. And the test samples with high confidence are selected to dynamically update the whole model. Experiments are conducted on face images, and a good performance is achieved in each layer of the DNN and the semantic description learning process. Furthermore, the model can be generalized to recognition tasks of other objects with learning ability.

Development of a model for whole brain learning of physiology.

PubMed

Eagleton, Saramarie; Muller, Anton

2011-12-01

In this report, a model was developed for whole brain learning based on Curry's onion model. Curry described the effect of personality traits as the inner layer of learning, information-processing styles as the middle layer of learning, and environmental and instructional preferences as the outer layer of learning. The model that was developed elaborates on these layers by relating the personality traits central to learning to the different quadrants of brain preference, as described by Neethling's brain profile, as the inner layer of the onion. This layer is encircled by the learning styles that describe different information-processing preferences for each brain quadrant. For the middle layer, the different stages of Kolb's learning cycle are classified into the four brain quadrants associated with the different brain processing strategies within the information processing circle. Each of the stages of Kolb's learning cycle is also associated with a specific cognitive learning strategy. These two inner circles are enclosed by the circle representing the role of the environment and instruction on learning. It relates environmental factors that affect learning and distinguishes between face-to-face and technology-assisted learning. This model informs on the design of instructional interventions for physiology to encourage whole brain learning.

[The influence of phychological features and learning styles on the academic performance of medical students].

PubMed

Bitran, Marcela; Lafuente, Montserrat; Zúñiga, Denisse; Viviani, Paola; Mena, Beltrán

2004-09-01

The degree of difficulty we experience while learning different concepts and skills depends, among other things, on our psychological features and learning style. This may be particularly true for medical students, whose formation involves the acquisition of multiple cognitive, affective and psychomotor skills. To assess whether the psychological features and learning styles of medical students are associated with their academic performance. The psychological preferences and learning styles of 66 students of the 2001-graduating cohort were determined with the Myers Briggs Type Inventory (MBTI) and the Kolb Learning Style Inventory (LSI), respectively. The academic performance was assessed by the Calificación Médica Nacional (CMN), Chile and by the marks obtained during the Basic (1st to 3rd), Preclinical (4th and 5th) and Clinical (6th and 7th) years of undergraduate training. The psychological features, together with the sex of students were found to be associated with the performance in the Preclinical and Clinical years, and to the CMN. In men, the interest and ability to communicate with people and the concern for harmony, and in women the tendency to function in a systematic and orderly way are the features associated to high academic performance. No associations were found between learning styles and academic performance. The finding that the psychological preferences of medical students are relevent to their academic performance opens a new perspective to analyze the medical education and to design programs aimed at improving learning.

What Is It that Entrepreneurs Learn from Experience?

ERIC Educational Resources Information Center

Martin, Frank; Smith, Ronnie

2010-01-01

The issue of whether or not entrepreneurs really learn from experience has been one of the key themes of entrepreneurship research. If they do learn from experience, what do they learn? The importance of knowledge and learning to the performance of a business has been highlighted by many authors, who emphasize the role of life cycle, learning from…

Personalized Mobile English Vocabulary Learning System Based on Item Response Theory and Learning Memory Cycle

ERIC Educational Resources Information Center

Chen, C. M.; Chung, C. J.

2008-01-01

Since learning English is very popular in non-English speaking countries, developing modern assisted-learning tools that support effective English learning is a critical issue in the English-language education field. Learning English involves memorization and practice of a large number of vocabulary words and numerous grammatical structures.…

Drive Cycle Data | Transportation Secure Data Center | NREL

Science.gov Websites

one file. Download Individual Survey and Study Drive Cycle Data Below you'll find drive cycle data download files for individual surveys and studies. Greater Fairbanks, Alaska, Transportation Survey Drive Cycle Data by Vehicle (24-hour period of operation) Download Learn more about the survey. California

Does It Have a Life Cycle?

ERIC Educational Resources Information Center

Keeley, Page

2010-01-01

If life continues from generation to generation, then all plants and animals must go through a life cycle, even though it may be different from organism to organism. Is this what students have "learned," or do they have their own private conceptions about life cycles? The formative assessment probe "Does It Have a Life Cycle?" reveals some…

Round and Round the Water Cycle

ERIC Educational Resources Information Center

Bradley, Barbara A.

2017-01-01

Children enjoy water play, and kindergarten children can learn about the water cycle. Teachers are already introducing elements of the water cycle when discussing weather and bodies of water. The water cycle also can be a springboard for teaching children about plants and animals and the importance of water for sustaining life and shaping our…

Learning representations for the early detection of sepsis with deep neural networks.

PubMed

Kam, Hye Jin; Kim, Ha Young

2017-10-01

Sepsis is one of the leading causes of death in intensive care unit patients. Early detection of sepsis is vital because mortality increases as the sepsis stage worsens. This study aimed to develop detection models for the early stage of sepsis using deep learning methodologies, and to compare the feasibility and performance of the new deep learning methodology with those of the regression method with conventional temporal feature extraction. Study group selection adhered to the InSight model. The results of the deep learning-based models and the InSight model were compared. With deep feedforward networks, the area under the ROC curve (AUC) of the models were 0.887 and 0.915 for the InSight and the new feature sets, respectively. For the model with the combined feature set, the AUC was the same as that of the basic feature set (0.915). For the long short-term memory model, only the basic feature set was applied and the AUC improved to 0.929 compared with the existing 0.887 of the InSight model. The contributions of this paper can be summarized in three ways: (i) improved performance without feature extraction using domain knowledge, (ii) verification of feature extraction capability of deep neural networks through comparison with reference features, and (iii) improved performance with feedforward neural networks using long short-term memory, a neural network architecture that can learn sequential patterns. Copyright © 2017 Elsevier Ltd. All rights reserved.

Automated Depression Analysis Using Convolutional Neural Networks from Speech.

PubMed

He, Lang; Cao, Cui

2018-05-28

To help clinicians to efficiently diagnose the severity of a person's depression, the affective computing community and the artificial intelligence field have shown a growing interest in designing automated systems. The speech features have useful information for the diagnosis of depression. However, manually designing and domain knowledge are still important for the selection of the feature, which makes the process labor consuming and subjective. In recent years, deep-learned features based on neural networks have shown superior performance to hand-crafted features in various areas. In this paper, to overcome the difficulties mentioned above, we propose a combination of hand-crafted and deep-learned features which can effectively measure the severity of depression from speech. In the proposed method, Deep Convolutional Neural Networks (DCNN) are firstly built to learn deep-learned features from spectrograms and raw speech waveforms. Then we manually extract the state-of-the-art texture descriptors named median robust extended local binary patterns (MRELBP) from spectrograms. To capture the complementary information within the hand-crafted features and deep-learned features, we propose joint fine-tuning layers to combine the raw and spectrogram DCNN to boost the depression recognition performance. Moreover, to address the problems with small samples, a data augmentation method was proposed. Experiments conducted on AVEC2013 and AVEC2014 depression databases show that our approach is robust and effective for the diagnosis of depression when compared to state-of-the-art audio-based methods. Copyright © 2018. Published by Elsevier Inc.

Multi-task feature learning by using trace norm regularization

NASA Astrophysics Data System (ADS)

Jiangmei, Zhang; Binfeng, Yu; Haibo, Ji; Wang, Kunpeng

2017-11-01

Multi-task learning can extract the correlation of multiple related machine learning problems to improve performance. This paper considers applying the multi-task learning method to learn a single task. We propose a new learning approach, which employs the mixture of expert model to divide a learning task into several related sub-tasks, and then uses the trace norm regularization to extract common feature representation of these sub-tasks. A nonlinear extension of this approach by using kernel is also provided. Experiments conducted on both simulated and real data sets demonstrate the advantage of the proposed approach.

Extension of Companion Modeling Using Classification Learning

NASA Astrophysics Data System (ADS)

Torii, Daisuke; Bousquet, François; Ishida, Toru

Companion Modeling is a methodology of refining initial models for understanding reality through a role-playing game (RPG) and a multiagent simulation. In this research, we propose a novel agent model construction methodology in which classification learning is applied to the RPG log data in Companion Modeling. This methodology enables a systematic model construction that handles multi-parameters, independent of the modelers ability. There are three problems in applying classification learning to the RPG log data: 1) It is difficult to gather enough data for the number of features because the cost of gathering data is high. 2) Noise data can affect the learning results because the amount of data may be insufficient. 3) The learning results should be explained as a human decision making model and should be recognized by the expert as being the result that reflects reality. We realized an agent model construction system using the following two approaches: 1) Using a feature selction method, the feature subset that has the best prediction accuracy is identified. In this process, the important features chosen by the expert are always included. 2) The expert eliminates irrelevant features from the learning results after evaluating the learning model through a visualization of the results. Finally, using the RPG log data from the Companion Modeling of agricultural economics in northeastern Thailand, we confirm the capability of this methodology.

A SCALE-UP Mock-Up: Comparison of Student Learning Gains in High- and Low-Tech Active-Learning Environments

PubMed Central

Soneral, Paula A. G.; Wyse, Sara A.

2017-01-01

Student-centered learning environments with upside-down pedagogies (SCALE-UP) are widely implemented at institutions across the country, and learning gains from these classrooms have been well documented. This study investigates the specific design feature(s) of the SCALE-UP classroom most conducive to teaching and learning. Using pilot survey data from instructors and students to prioritize the most salient SCALE-UP classroom features, we created a low-tech “Mock-up” version of this classroom and tested the impact of these features on student learning, attitudes, and satisfaction using a quasi-­experimental setup. The same instructor taught two sections of an introductory biology course in the SCALE-UP and Mock-up rooms. Although students in both sections were equivalent in terms of gender, grade point average, incoming ACT, and drop/fail/withdraw rate, the Mock-up classroom enrolled significantly more freshmen. Controlling for class standing, multiple regression modeling revealed no significant differences in exam, in-class, preclass, and Introduction to Molecular and Cellular Biology Concept Inventory scores between the SCALE-UP and Mock-up classrooms. Thematic analysis of student comments highlighted that collaboration and whiteboards enhanced the learning experience, but technology was not important. Student satisfaction and attitudes were comparable. These results suggest that the benefits of a SCALE-UP experience can be achieved at lower cost without technology features. PMID:28213582

Hierarchical Recurrent Neural Hashing for Image Retrieval With Hierarchical Convolutional Features.

PubMed

Lu, Xiaoqiang; Chen, Yaxiong; Li, Xuelong

Hashing has been an important and effective technology in image retrieval due to its computational efficiency and fast search speed. The traditional hashing methods usually learn hash functions to obtain binary codes by exploiting hand-crafted features, which cannot optimally represent the information of the sample. Recently, deep learning methods can achieve better performance, since deep learning architectures can learn more effective image representation features. However, these methods only use semantic features to generate hash codes by shallow projection but ignore texture details. In this paper, we proposed a novel hashing method, namely hierarchical recurrent neural hashing (HRNH), to exploit hierarchical recurrent neural network to generate effective hash codes. There are three contributions of this paper. First, a deep hashing method is proposed to extensively exploit both spatial details and semantic information, in which, we leverage hierarchical convolutional features to construct image pyramid representation. Second, our proposed deep network can exploit directly convolutional feature maps as input to preserve the spatial structure of convolutional feature maps. Finally, we propose a new loss function that considers the quantization error of binarizing the continuous embeddings into the discrete binary codes, and simultaneously maintains the semantic similarity and balanceable property of hash codes. Experimental results on four widely used data sets demonstrate that the proposed HRNH can achieve superior performance over other state-of-the-art hashing methods.Hashing has been an important and effective technology in image retrieval due to its computational efficiency and fast search speed. The traditional hashing methods usually learn hash functions to obtain binary codes by exploiting hand-crafted features, which cannot optimally represent the information of the sample. Recently, deep learning methods can achieve better performance, since deep learning architectures can learn more effective image representation features. However, these methods only use semantic features to generate hash codes by shallow projection but ignore texture details. In this paper, we proposed a novel hashing method, namely hierarchical recurrent neural hashing (HRNH), to exploit hierarchical recurrent neural network to generate effective hash codes. There are three contributions of this paper. First, a deep hashing method is proposed to extensively exploit both spatial details and semantic information, in which, we leverage hierarchical convolutional features to construct image pyramid representation. Second, our proposed deep network can exploit directly convolutional feature maps as input to preserve the spatial structure of convolutional feature maps. Finally, we propose a new loss function that considers the quantization error of binarizing the continuous embeddings into the discrete binary codes, and simultaneously maintains the semantic similarity and balanceable property of hash codes. Experimental results on four widely used data sets demonstrate that the proposed HRNH can achieve superior performance over other state-of-the-art hashing methods.

The extraction of motion-onset VEP BCI features based on deep learning and compressed sensing.

PubMed

Ma, Teng; Li, Hui; Yang, Hao; Lv, Xulin; Li, Peiyang; Liu, Tiejun; Yao, Dezhong; Xu, Peng

2017-01-01

Motion-onset visual evoked potentials (mVEP) can provide a softer stimulus with reduced fatigue, and it has potential applications for brain computer interface(BCI)systems. However, the mVEP waveform is seriously masked in the strong background EEG activities, and an effective approach is needed to extract the corresponding mVEP features to perform task recognition for BCI control. In the current study, we combine deep learning with compressed sensing to mine discriminative mVEP information to improve the mVEP BCI performance. The deep learning and compressed sensing approach can generate the multi-modality features which can effectively improve the BCI performance with approximately 3.5% accuracy incensement over all 11 subjects and is more effective for those subjects with relatively poor performance when using the conventional features. Compared with the conventional amplitude-based mVEP feature extraction approach, the deep learning and compressed sensing approach has a higher classification accuracy and is more effective for subjects with relatively poor performance. According to the results, the deep learning and compressed sensing approach is more effective for extracting the mVEP feature to construct the corresponding BCI system, and the proposed feature extraction framework is easy to extend to other types of BCIs, such as motor imagery (MI), steady-state visual evoked potential (SSVEP)and P300. Copyright © 2016 Elsevier B.V. All rights reserved.

Super-Resolution Person Re-Identification With Semi-Coupled Low-Rank Discriminant Dictionary Learning.

PubMed

Jing, Xiao-Yuan; Zhu, Xiaoke; Wu, Fei; Hu, Ruimin; You, Xinge; Wang, Yunhong; Feng, Hui; Yang, Jing-Yu

2017-03-01

Person re-identification has been widely studied due to its importance in surveillance and forensics applications. In practice, gallery images are high resolution (HR), while probe images are usually low resolution (LR) in the identification scenarios with large variation of illumination, weather, or quality of cameras. Person re-identification in this kind of scenarios, which we call super-resolution (SR) person re-identification, has not been well studied. In this paper, we propose a semi-coupled low-rank discriminant dictionary learning (SLD 2 L) approach for SR person re-identification task. With the HR and LR dictionary pair and mapping matrices learned from the features of HR and LR training images, SLD 2 L can convert the features of the LR probe images into HR features. To ensure that the converted features have favorable discriminative capability and the learned dictionaries can well characterize intrinsic feature spaces of the HR and LR images, we design a discriminant term and a low-rank regularization term for SLD 2 L. Moreover, considering that low resolution results in different degrees of loss for different types of visual appearance features, we propose a multi-view SLD 2 L (MVSLD 2 L) approach, which can learn the type-specific dictionary pair and mappings for each type of feature. Experimental results on multiple publicly available data sets demonstrate the effectiveness of our proposed approaches for the SR person re-identification task.

Facilitating Conceptual Change in Understanding State of Matter and Solubility Concepts by Using 5E Learning Cycle Model

ERIC Educational Resources Information Center

Ceylan, Eren; Geban, Omer

2009-01-01

The main purpose of the study was to compare the effectiveness of 5E learning cycle model based instruction and traditionally designed chemistry instruction on 10th grade students' understanding of state of matter and solubility concepts. In this study, 119 tenth grade students from chemistry courses instructed by same teacher from an Anatolian…

The Effectiveness of the Learning-Cycle Method on Teaching DC Circuits to Prospective Female and Male Science Teachers

ERIC Educational Resources Information Center

Ates, Salih

2005-01-01

This study was undertaken to explore the effectiveness of the learning-cycle method when teaching direct current (DC) circuits to university students. Four Physics II classes participated in the study, which lasted approximately two and a half weeks in the middle of the spring semester of 2003. Participants were 120 freshmen (55 females and 65…

Applying a machine learning model using a locally preserving projection based feature regeneration algorithm to predict breast cancer risk

NASA Astrophysics Data System (ADS)

Heidari, Morteza; Zargari Khuzani, Abolfazl; Danala, Gopichandh; Mirniaharikandehei, Seyedehnafiseh; Qian, Wei; Zheng, Bin

2018-03-01

Both conventional and deep machine learning has been used to develop decision-support tools applied in medical imaging informatics. In order to take advantages of both conventional and deep learning approach, this study aims to investigate feasibility of applying a locally preserving projection (LPP) based feature regeneration algorithm to build a new machine learning classifier model to predict short-term breast cancer risk. First, a computer-aided image processing scheme was used to segment and quantify breast fibro-glandular tissue volume. Next, initially computed 44 image features related to the bilateral mammographic tissue density asymmetry were extracted. Then, an LLP-based feature combination method was applied to regenerate a new operational feature vector using a maximal variance approach. Last, a k-nearest neighborhood (KNN) algorithm based machine learning classifier using the LPP-generated new feature vectors was developed to predict breast cancer risk. A testing dataset involving negative mammograms acquired from 500 women was used. Among them, 250 were positive and 250 remained negative in the next subsequent mammography screening. Applying to this dataset, LLP-generated feature vector reduced the number of features from 44 to 4. Using a leave-onecase-out validation method, area under ROC curve produced by the KNN classifier significantly increased from 0.62 to 0.68 (p < 0.05) and odds ratio was 4.60 with a 95% confidence interval of [3.16, 6.70]. Study demonstrated that this new LPP-based feature regeneration approach enabled to produce an optimal feature vector and yield improved performance in assisting to predict risk of women having breast cancer detected in the next subsequent mammography screening.

Age-related declines of stability in visual perceptual learning.

PubMed

Chang, Li-Hung; Shibata, Kazuhisa; Andersen, George J; Sasaki, Yuka; Watanabe, Takeo

2014-12-15

One of the biggest questions in learning is how a system can resolve the plasticity and stability dilemma. Specifically, the learning system needs to have not only a high capability of learning new items (plasticity) but also a high stability to retain important items or processing in the system by preventing unimportant or irrelevant information from being learned. This dilemma should hold true for visual perceptual learning (VPL), which is defined as a long-term increase in performance on a visual task as a result of visual experience. Although it is well known that aging influences learning, the effect of aging on the stability and plasticity of the visual system is unclear. To address the question, we asked older and younger adults to perform a task while a task-irrelevant feature was merely exposed. We found that older individuals learned the task-irrelevant features that younger individuals did not learn, both the features that were sufficiently strong for younger individuals to suppress and the features that were too weak for younger individuals to learn. At the same time, there was no plasticity reduction in older individuals within the task tested. These results suggest that the older visual system is less stable to unimportant information than the younger visual system. A learning problem with older individuals may be due to a decrease in stability rather than a decrease in plasticity, at least in VPL. Copyright © 2014 Elsevier Ltd. All rights reserved.

Automatic MeSH term assignment and quality assessment.

PubMed Central

Kim, W.; Aronson, A. R.; Wilbur, W. J.

2001-01-01

For computational purposes documents or other objects are most often represented by a collection of individual attributes that may be strings or numbers. Such attributes are often called features and success in solving a given problem can depend critically on the nature of the features selected to represent documents. Feature selection has received considerable attention in the machine learning literature. In the area of document retrieval we refer to feature selection as indexing. Indexing has not traditionally been evaluated by the same methods used in machine learning feature selection. Here we show how indexing quality may be evaluated in a machine learning setting and apply this methodology to results of the Indexing Initiative at the National Library of Medicine. PMID:11825203

Advanced technology for space shuttle auxiliary propellant valves

NASA Technical Reports Server (NTRS)

Wichmann, H.

1973-01-01

Valves for the gaseous hydrogen/gaseous oxygen shuttle auxiliary propulsion system are required to feature low leakage over a wide temperature range coupled with high cycle life, long term compatibility and minimum maintenance. In addition, those valves used as thruster shutoff valves must feature fast response characteristics to achieve small, repeatable minimum impulse bits. These valve technology problems are solved by developing unique valve components such as sealing closures, guidance devices, and actuation means and by demonstrating two prototype valve concepts. One of the prototype valves is cycled over one million cycles without exceeding a leakage rate of 27 scc's per hour at 450 psia helium inlet pressure throughout the cycling program.

Iterating between lessons on concepts and procedures can improve mathematics knowledge.

PubMed

Rittle-Johnson, Bethany; Koedinger, Kenneth

2009-09-01

Knowledge of concepts and procedures seems to develop in an iterative fashion, with increases in one type of knowledge leading to increases in the other type of knowledge. This suggests that iterating between lessons on concepts and procedures may improve learning. The purpose of the current study was to evaluate the instructional benefits of an iterative lesson sequence compared to a concepts-before-procedures sequence for students learning decimal place-value concepts and arithmetic procedures. In two classroom experiments, sixth-grade students from two schools participated (N=77 and 26). Students completed six decimal lessons on an intelligent-tutoring systems. In the iterative condition, lessons cycled between concept and procedure lessons. In the concepts-first condition, all concept lessons were presented before introducing the procedure lessons. In both experiments, students in the iterative condition gained more knowledge of arithmetic procedures, including ability to transfer the procedures to problems with novel features. Knowledge of concepts was fairly comparable across conditions. Finally, pre-test knowledge of one type predicted gains in knowledge of the other type across experiments. An iterative sequencing of lessons seems to facilitate learning and transfer, particularly of mathematical procedures. The findings support an iterative perspective for the development of knowledge of concepts and procedures.

Soil Moisture Retrieval Using Convolutional Neural Networks: Application to Passive Microwave Remote Sensing

NASA Astrophysics Data System (ADS)

Hu, Z.; Xu, L.; Yu, B.

2018-04-01

A empirical model is established to analyse the daily retrieval of soil moisture from passive microwave remote sensing using convolutional neural networks (CNN). Soil moisture plays an important role in the water cycle. However, with the rapidly increasing of the acquiring technology for remotely sensed data, it's a hard task for remote sensing practitioners to find a fast and convenient model to deal with the massive data. In this paper, the AMSR-E brightness temperatures are used to train CNN for the prediction of the European centre for medium-range weather forecasts (ECMWF) model. Compared with the classical inversion methods, the deep learning-based method is more suitable for global soil moisture retrieval. It is very well supported by graphics processing unit (GPU) acceleration, which can meet the demand of massive data inversion. Once the model trained, a global soil moisture map can be predicted in less than 10 seconds. What's more, the method of soil moisture retrieval based on deep learning can learn the complex texture features from the big remote sensing data. In this experiment, the results demonstrates that the CNN deployed to retrieve global soil moisture can achieve a better performance than the support vector regression (SVR) for soil moisture retrieval.

Identifying Key Features of Student Performance in Educational Video Games and Simulations through Cluster Analysis

ERIC Educational Resources Information Center

Kerr, Deirdre; Chung, Gregory K. W. K.

2012-01-01

The assessment cycle of "evidence-centered design" (ECD) provides a framework for treating an educational video game or simulation as an assessment. One of the main steps in the assessment cycle of ECD is the identification of the key features of student performance. While this process is relatively simple for multiple choice tests, when…

Cross-Domain Semi-Supervised Learning Using Feature Formulation.

PubMed

Xingquan Zhu

2011-12-01

Semi-Supervised Learning (SSL) traditionally makes use of unlabeled samples by including them into the training set through an automated labeling process. Such a primitive Semi-Supervised Learning (pSSL) approach suffers from a number of disadvantages including false labeling and incapable of utilizing out-of-domain samples. In this paper, we propose a formative Semi-Supervised Learning (fSSL) framework which explores hidden features between labeled and unlabeled samples to achieve semi-supervised learning. fSSL regards that both labeled and unlabeled samples are generated from some hidden concepts with labeling information partially observable for some samples. The key of the fSSL is to recover the hidden concepts, and take them as new features to link labeled and unlabeled samples for semi-supervised learning. Because unlabeled samples are only used to generate new features, but not to be explicitly included in the training set like pSSL does, fSSL overcomes the inherent disadvantages of the traditional pSSL methods, especially for samples not within the same domain as the labeled instances. Experimental results and comparisons demonstrate that fSSL significantly outperforms pSSL-based methods for both within-domain and cross-domain semi-supervised learning.

Enculturating Seamless Language Learning through Artifact Creation and Social Interaction Process

ERIC Educational Resources Information Center

Wong, Lung-Hsiang; Chai, Ching Sing; Aw, Guat Poh; King, Ronnel B.

2015-01-01

This paper reports a design-based research (DBR) cycle of MyCLOUD (My Chinese ubiquitOUs learning Days). MyCLOUD is a seamless language learning model that addresses identified limitations of conventional Chinese language teaching, such as the decontextualized and unauthentic learning processes that usually hinder reflection and deep learning.…

Creating an Innovative Learning Organization

ERIC Educational Resources Information Center

Salisbury, Mark

2010-01-01

This article describes how to create an innovative learning (iLearning) organization. It begins by discussing the life cycle of knowledge in an organization, followed by a description of the theoretical foundation for iLearning. Next, the article presents an example of iLearning, followed by a description of the distributed nature of work, the…

The Effect of Teaching with Stories on Associate Degree Nursing Students' Approach to Learning and Reflective Practice

ERIC Educational Resources Information Center

Bradshaw, Vicki

2012-01-01

This action research study is the culmination of several action cycles investigating cognitive information processing and learning strategies based on students approach to learning theory and assessing students' meta-cognitive learning, motivation, and reflective development suggestive of deep learning. The study introduces a reading…

Deep-learning derived features for lung nodule classification with limited datasets

NASA Astrophysics Data System (ADS)

Thammasorn, P.; Wu, W.; Pierce, L. A.; Pipavath, S. N.; Lampe, P. D.; Houghton, A. M.; Haynor, D. R.; Chaovalitwongse, W. A.; Kinahan, P. E.

2018-02-01

Only a few percent of indeterminate nodules found in lung CT images are cancer. However, enabling earlier diagnosis is important to avoid invasive procedures or long-time surveillance to those benign nodules. We are evaluating a classification framework using radiomics features derived with a machine learning approach from a small data set of indeterminate CT lung nodule images. We used a retrospective analysis of 194 cases with pulmonary nodules in the CT images with or without contrast enhancement from lung cancer screening clinics. The nodules were contoured by a radiologist and texture features of the lesion were calculated. In addition, sematic features describing shape were categorized. We also explored a Multiband network, a feature derivation path that uses a modified convolutional neural network (CNN) with a Triplet Network. This was trained to create discriminative feature representations useful for variable-sized nodule classification. The diagnostic accuracy was evaluated for multiple machine learning algorithms using texture, shape, and CNN features. In the CT contrast-enhanced group, the texture or semantic shape features yielded an overall diagnostic accuracy of 80%. Use of a standard deep learning network in the framework for feature derivation yielded features that substantially underperformed compared to texture and/or semantic features. However, the proposed Multiband approach of feature derivation produced results similar in diagnostic accuracy to the texture and semantic features. While the Multiband feature derivation approach did not outperform the texture and/or semantic features, its equivalent performance indicates promise for future improvements to increase diagnostic accuracy. Importantly, the Multiband approach adapts readily to different size lesions without interpolation, and performed well with relatively small amount of training data.

Multi-View Budgeted Learning under Label and Feature Constraints Using Label-Guided Graph-Based Regularization

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

Symons, Christopher T; Arel, Itamar

2011-01-01

Budgeted learning under constraints on both the amount of labeled information and the availability of features at test time pertains to a large number of real world problems. Ideas from multi-view learning, semi-supervised learning, and even active learning have applicability, but a common framework whose assumptions fit these problem spaces is non-trivial to construct. We leverage ideas from these fields based on graph regularizers to construct a robust framework for learning from labeled and unlabeled samples in multiple views that are non-independent and include features that are inaccessible at the time the model would need to be applied. We describemore » examples of applications that fit this scenario, and we provide experimental results to demonstrate the effectiveness of knowledge carryover from training-only views. As learning algorithms are applied to more complex applications, relevant information can be found in a wider variety of forms, and the relationships between these information sources are often quite complex. The assumptions that underlie most learning algorithms do not readily or realistically permit the incorporation of many of the data sources that are available, despite an implicit understanding that useful information exists in these sources. When multiple information sources are available, they are often partially redundant, highly interdependent, and contain noise as well as other information that is irrelevant to the problem under study. In this paper, we are focused on a framework whose assumptions match this reality, as well as the reality that labeled information is usually sparse. Most significantly, we are interested in a framework that can also leverage information in scenarios where many features that would be useful for learning a model are not available when the resulting model will be applied. As with constraints on labels, there are many practical limitations on the acquisition of potentially useful features. A key difference in the case of feature acquisition is that the same constraints often don't pertain to the training samples. This difference provides an opportunity to allow features that are impractical in an applied setting to nevertheless add value during the model-building process. Unfortunately, there are few machine learning frameworks built on assumptions that allow effective utilization of features that are only available at training time. In this paper we formulate a knowledge carryover framework for the budgeted learning scenario with constraints on features and labels. The approach is based on multi-view and semi-supervised learning methods that use graph-encoded regularization. Our main contributions are the following: (1) we propose and provide justification for a methodology for ensuring that changes in the graph regularizer using alternate views are performed in a manner that is target-concept specific, allowing value to be obtained from noisy views; and (2) we demonstrate how this general set-up can be used to effectively improve models by leveraging features unavailable at test time. The rest of the paper is structured as follows. In Section 2, we outline real-world problems to motivate the approach and describe relevant prior work. Section 3 describes the graph construction process and the learning methodologies that are employed. Section 4 provides preliminary discussion regarding theoretical motivation for the method. In Section 5, effectiveness of the approach is demonstrated in a series of experiments employing modified versions of two well-known semi-supervised learning algorithms. Section 6 concludes the paper.« less

Where Do Features Come From?

ERIC Educational Resources Information Center

Hinton, Geoffrey

2014-01-01

It is possible to learn multiple layers of non-linear features by backpropagating error derivatives through a feedforward neural network. This is a very effective learning procedure when there is a huge amount of labeled training data, but for many learning tasks very few labeled examples are available. In an effort to overcome the need for…

Effects of Interactive Vocabulary Instruction on the Vocabulary Learning and Reading Comprehension of Junior-High Learning Disabled Students.

ERIC Educational Resources Information Center

Bos, Candace S.; Anders, Patricia L.

1990-01-01

The study, involving 61 learning-disabled junior high students, compared the short-term and long-term effectiveness of definition instruction with interactive vocabulary strategies (semantic mapping, semantic feature analysis, and semantic/syntactic feature analysis). Students participating in the interactive strategies demonstrated greater…

Improving Measurements of Self-Regulated Learning

ERIC Educational Resources Information Center

Winne, Philip H.

2010-01-01

Articles in this special issue present recent advances in using state-of-the-art software systems that gather data with which to examine and measure features of learning and particularly self-regulated learning (SRL). Despite important advances, there remain challenges. I examine key features of SRL and how they are measured using common tools. I…

Learner Variables Associated with Reading and Learning in a Hypertext Environment.

ERIC Educational Resources Information Center

Niederhauser, Dale S.; Shapiro, Amy

While many elements like character decoding, word recognition, comprehension, and others remain the same as in learning from traditional text, when learning from hypertext, a number of features that are unique to reading hypertext produce added complexity. It is these features that drive research on hypertext in education. There is a greater…

The Effectiveness of Three Serious Games Measuring Generic Learning Features

ERIC Educational Resources Information Center

Bakhuys Roozeboom, Maartje; Visschedijk, Gillian; Oprins, Esther

2017-01-01

Although serious games are more and more used for learning goals, high-quality empirical studies to prove the effectiveness of serious games are relatively scarce. In this paper, three empirical studies are presented that investigate the effectiveness of serious games as opposed to traditional classroom instruction on learning features as well as…

Geographical topic learning for social images with a deep neural network

NASA Astrophysics Data System (ADS)

Feng, Jiangfan; Xu, Xin

2017-03-01

The use of geographical tagging in social-media images is becoming a part of image metadata and a great interest for geographical information science. It is well recognized that geographical topic learning is crucial for geographical annotation. Existing methods usually exploit geographical characteristics using image preprocessing, pixel-based classification, and feature recognition. How to effectively exploit the high-level semantic feature and underlying correlation among different types of contents is a crucial task for geographical topic learning. Deep learning (DL) has recently demonstrated robust capabilities for image tagging and has been introduced into geoscience. It extracts high-level features computed from a whole image component, where the cluttered background may dominate spatial features in the deep representation. Therefore, a method of spatial-attentional DL for geographical topic learning is provided and we can regard it as a special case of DL combined with various deep networks and tuning tricks. Results demonstrated that the method is discriminative for different types of geographical topic learning. In addition, it outperforms other sequential processing models in a tagging task for a geographical image dataset.

Effective collaborative learning in biomedical education using a web-based infrastructure.

PubMed

Wu, Yunfeng; Zheng, Fang; Cai, Suxian; Xiang, Ning; Zhong, Zhangting; He, Jia; Xu, Fang

2012-01-01

This paper presents a feature-rich web-based system used for biomedical education at the undergraduate level. With the powerful groupware features provided by the wiki system, the instructors are able to establish a community-centered mentoring environment that capitalizes on local expertise to create a sense of online collaborative learning among students. The web-based infrastructure can help the instructors effectively organize and coordinate student research projects, and the groupware features may support the interactive activities, such as interpersonal communications and data sharing. The groupware features also provide the web-based system with a wide range of additional ways of organizing collaboratively developed materials, which makes it become an effective tool for online active learning. Students are able to learn the ability to work effectively in teams, with an improvement of project management, design collaboration, and technical writing skills. With the fruitful outcomes in recent years, it is positively thought that the web-based collaborative learning environment can perform an excellent shift away from the conventional instructor-centered teaching to community- centered collaborative learning in the undergraduate education.

Incremental Bayesian Category Learning From Natural Language.

PubMed

Frermann, Lea; Lapata, Mirella

2016-08-01

Models of category learning have been extensively studied in cognitive science and primarily tested on perceptual abstractions or artificial stimuli. In this paper, we focus on categories acquired from natural language stimuli, that is, words (e.g., chair is a member of the furniture category). We present a Bayesian model that, unlike previous work, learns both categories and their features in a single process. We model category induction as two interrelated subproblems: (a) the acquisition of features that discriminate among categories, and (b) the grouping of concepts into categories based on those features. Our model learns categories incrementally using particle filters, a sequential Monte Carlo method commonly used for approximate probabilistic inference that sequentially integrates newly observed data and can be viewed as a plausible mechanism for human learning. Experimental results show that our incremental learner obtains meaningful categories which yield a closer fit to behavioral data compared to related models while at the same time acquiring features which characterize the learned categories. (An earlier version of this work was published in Frermann and Lapata .). Copyright © 2015 Cognitive Science Society, Inc.

Making YOHKOH SXT Images Available to the Public: The YOHKOH Public Outreach Project

NASA Astrophysics Data System (ADS)

Larson, M. B.; McKenzie, D.; Slater, T.; Acton, L.; Alexander, D.; Freeland, S.; Lemen, J.; Metcalf, T.

1999-05-01

The NASA funded Yohkoh Public Outreach Project (YPOP) provides public access to high quality Yohkoh SXT data via the World Wide Web. The products of this effort are available to the scientific research community, K-12 schools, and informal education centers including planetaria, museums, and libraries. The project utilizes the intrinsic excitement of the SXT data, and in particular the SXT movies, to develop science learning tools and classroom activities. The WWW site at URL: http://solar.physics.montana.edu/YPOP/ uses a movie theater theme to highlight available Yohkoh movies in a format that is entertaining and inviting to non-scientists. The site features informational tours of the Sun as a star, the solar magnetic field, the internal structure and the Sun's general features. The on-line Solar Classroom has proven very popular, showcasing hand-on activities about image filtering, the solar cycle, satellite orbits, image processing, construction of a model Yohkoh satellite, solar rotation, measuring sunspots and building a portable sundial. The YPOP Guestbook has been helpful in evaluating the usefulness of the site with over 300 detailed comments to date.

Effectiveness and student perceptions of an active learning activity using a headline news story to enhance in-class learning of cell cycle regulation.

PubMed

Dirks-Naylor, Amie J

2016-06-01

An active learning activity was used to engage students and enhance in-class learning of cell cycle regulation in a PharmD level integrated biological sciences course. The aim of the present study was to determine the effectiveness and perception of the in-class activity. After completion of a lecture on the topic of cell cycle regulation, students completed a 10-question multiple-choice quiz before and after engaging in the activity. The activity involved reading of a headline news article published by ScienceDaily.com entitled "One Gene Lost Equals One limb Regained." The name of the gene was deleted from the article and, thus, the end goal of the activity was to determine the gene of interest by the description in the story. The activity included compiling a list of all potential gene candidates before sufficient information was given to identify the gene of interest (p21). A survey was completed to determine student perceptions of the activity. Quiz scores improved by an average of 20% after the activity (40.1 ± 1.95 vs. 59.9 ± 2.14,P< 0.0001,n= 96). Students enjoyed the activity, found the news article interesting, and believed that the activity improved their understanding of cell cycle regulation. The majority of students agreed that the in-class activity piqued their interest for learning the subject matter and also agreed that if they understand a concept during class, they are more likely to want to study that concept outside of class. In conclusion, the activity improved in-class understanding and enhanced interest in cell cycle regulation. Copyright © 2016 The American Physiological Society.

The Affective Core of Emotion: Linking Pleasure, Subjective Well-Being, and Optimal Metastability in the Brain

PubMed Central

Kringelbach, Morten L.; Berridge, Kent C.

2017-01-01

Arguably, emotion is always valenced—either pleasant or unpleasant—and dependent on the pleasure system. This system serves adaptive evolutionary functions; relying on separable wanting, liking, and learning neural mechanisms mediated by mesocorticolimbic networks driving pleasure cycles with appetitive, consummatory, and satiation phases. Liking is generated in a small set of discrete hedonic hotspots and coldspots, while wanting is linked to dopamine and to larger distributed brain networks. Breakdown of the pleasure system can lead to anhedonia and other features of affective disorders. Eudaimonia and well-being are difficult to study empirically, yet whole-brain computational models could offer novel insights (e.g., routes to eudaimonia such as caregiving of infants or music) potentially linking eudaimonia to optimal metastability in the pleasure system. PMID:28943891

Characterizing Exoplanet Atmospheres with the James Webb Space Telescope

NASA Technical Reports Server (NTRS)

Greene, Tom

2017-01-01

The James Webb Space Telescope (JWST) will have numerous modes for acquiring photometry and spectra of stars, planets, galaxies, and other astronomical objects over wavelengths of 0.6 - 28 microns. Several of these modes are well-suited for observing atomic and molecular features in the atmospheres of transiting or spatially resolved exoplanets. I will present basic information on JWST capabilities, highlight modes that are well-suited for observing exoplanets, and give examples of what may be learned from JWST observations. This will include simulated spectra and expected retrieved chemical abundance, composition, equilibrium, and thermal information and uncertainties. JWST Cycle 1 general observer proposals are expected to be due in March 2018 with launch in October 2018, and the greater scientific community is encouraged to propose investigations to study exoplanet atmospheres and other topics.

Spoken language identification based on the enhanced self-adjusting extreme learning machine approach.

PubMed

Albadr, Musatafa Abbas Abbood; Tiun, Sabrina; Al-Dhief, Fahad Taha; Sammour, Mahmoud A M

2018-01-01

Spoken Language Identification (LID) is the process of determining and classifying natural language from a given content and dataset. Typically, data must be processed to extract useful features to perform LID. The extracting features for LID, based on literature, is a mature process where the standard features for LID have already been developed using Mel-Frequency Cepstral Coefficients (MFCC), Shifted Delta Cepstral (SDC), the Gaussian Mixture Model (GMM) and ending with the i-vector based framework. However, the process of learning based on extract features remains to be improved (i.e. optimised) to capture all embedded knowledge on the extracted features. The Extreme Learning Machine (ELM) is an effective learning model used to perform classification and regression analysis and is extremely useful to train a single hidden layer neural network. Nevertheless, the learning process of this model is not entirely effective (i.e. optimised) due to the random selection of weights within the input hidden layer. In this study, the ELM is selected as a learning model for LID based on standard feature extraction. One of the optimisation approaches of ELM, the Self-Adjusting Extreme Learning Machine (SA-ELM) is selected as the benchmark and improved by altering the selection phase of the optimisation process. The selection process is performed incorporating both the Split-Ratio and K-Tournament methods, the improved SA-ELM is named Enhanced Self-Adjusting Extreme Learning Machine (ESA-ELM). The results are generated based on LID with the datasets created from eight different languages. The results of the study showed excellent superiority relating to the performance of the Enhanced Self-Adjusting Extreme Learning Machine LID (ESA-ELM LID) compared with the SA-ELM LID, with ESA-ELM LID achieving an accuracy of 96.25%, as compared to the accuracy of SA-ELM LID of only 95.00%.

Spoken language identification based on the enhanced self-adjusting extreme learning machine approach

PubMed Central

Tiun, Sabrina; AL-Dhief, Fahad Taha; Sammour, Mahmoud A. M.

2018-01-01

Spoken Language Identification (LID) is the process of determining and classifying natural language from a given content and dataset. Typically, data must be processed to extract useful features to perform LID. The extracting features for LID, based on literature, is a mature process where the standard features for LID have already been developed using Mel-Frequency Cepstral Coefficients (MFCC), Shifted Delta Cepstral (SDC), the Gaussian Mixture Model (GMM) and ending with the i-vector based framework. However, the process of learning based on extract features remains to be improved (i.e. optimised) to capture all embedded knowledge on the extracted features. The Extreme Learning Machine (ELM) is an effective learning model used to perform classification and regression analysis and is extremely useful to train a single hidden layer neural network. Nevertheless, the learning process of this model is not entirely effective (i.e. optimised) due to the random selection of weights within the input hidden layer. In this study, the ELM is selected as a learning model for LID based on standard feature extraction. One of the optimisation approaches of ELM, the Self-Adjusting Extreme Learning Machine (SA-ELM) is selected as the benchmark and improved by altering the selection phase of the optimisation process. The selection process is performed incorporating both the Split-Ratio and K-Tournament methods, the improved SA-ELM is named Enhanced Self-Adjusting Extreme Learning Machine (ESA-ELM). The results are generated based on LID with the datasets created from eight different languages. The results of the study showed excellent superiority relating to the performance of the Enhanced Self-Adjusting Extreme Learning Machine LID (ESA-ELM LID) compared with the SA-ELM LID, with ESA-ELM LID achieving an accuracy of 96.25%, as compared to the accuracy of SA-ELM LID of only 95.00%. PMID:29672546

Agile Learning: Sprinting through the Semester

ERIC Educational Resources Information Center

Lang, Guido

2017-01-01

This paper introduces agile learning, a novel pedagogical approach that applies the processes and principles of agile software development to the context of learning. Agile learning is characterized by short project cycles, called sprints, in which a usable deliverable is fully planned, designed, built, tested, reviewed, and launched. An…

The GLOBE Carbon Cycle Project: Using a systems approach to understand carbon and the Earth's climate system

NASA Astrophysics Data System (ADS)

Silverberg, S. K.; Ollinger, S. V.; Martin, M. E.; Gengarelly, L. M.; Schloss, A. L.; Bourgeault, J. L.; Randolph, G.; Albrechtova, J.

2009-12-01

National Science Content Standards identify systems as an important unifying concept across the K-12 curriculum. While this standard exists, there is a recognized gap in the ability of students to use a systems thinking approach in their learning. In a similar vein, both popular media as well as some educational curricula move quickly through climate topics to carbon footprint analyses without ever addressing the nature of carbon or the carbon cycle. If students do not gain a concrete understanding of carbon’s role in climate and energy they will not be able to successfully tackle global problems and develop innovative solutions. By participating in the GLOBE Carbon Cycle project, students learn to use a systems thinking approach, while at the same time, gaining a foundation in the carbon cycle and it's relation to climate and energy. Here we present the GLOBE Carbon Cycle project and materials, which incorporate a diverse set of activities geared toward upper middle and high school students with a variety of learning styles. A global carbon cycle adventure story and game let students see the carbon cycle as a complete system, while introducing them to systems thinking concepts including reservoirs, fluxes and equilibrium. Classroom photosynthesis experiments and field measurements of schoolyard vegetation brings the global view to the local level. And the use of computer models at varying levels of complexity (effects on photosynthesis, biomass and carbon storage in global biomes, global carbon cycle) not only reinforces systems concepts and carbon content, but also introduces students to an important scientific tool necessary for understanding climate change.

Developing a Mobile Learning Management System for Outdoors Nature Science Activities Based on 5E Learning Cycle

ERIC Educational Resources Information Center

Lai, Ah-Fur; Lai, Horng-Yih; Chuang, Wei-Hsiang; Wu, Zih-Heng

2015-01-01

Traditional outdoor learning activities such as inquiry-based learning in nature science encounter many dilemmas. Due to prompt development of mobile computing and widespread of mobile devices, mobile learning becomes a big trend on education. The main purpose of this study is to develop a mobile-learning management system for overcoming the…

Technique Feature Analysis or Involvement Load Hypothesis: Estimating Their Predictive Power in Vocabulary Learning.

PubMed

Gohar, Manoochehr Jafari; Rahmanian, Mahboubeh; Soleimani, Hassan

2018-02-05

Vocabulary learning has always been a great concern and has attracted the attention of many researchers. Among the vocabulary learning hypotheses, involvement load hypothesis and technique feature analysis have been proposed which attempt to bring some concepts like noticing, motivation, and generation into focus. In the current study, 90 high proficiency EFL students were assigned into three vocabulary tasks of sentence making, composition, and reading comprehension in order to examine the power of involvement load hypothesis and technique feature analysis frameworks in predicting vocabulary learning. It was unraveled that involvement load hypothesis cannot be a good predictor, and technique feature analysis was a good predictor in pretest to posttest score change and not in during-task activity. The implications of the results will be discussed in the light of preparing vocabulary tasks.

Feature and Region Selection for Visual Learning.

PubMed

Zhao, Ji; Wang, Liantao; Cabral, Ricardo; De la Torre, Fernando

2016-03-01

Visual learning problems, such as object classification and action recognition, are typically approached using extensions of the popular bag-of-words (BoWs) model. Despite its great success, it is unclear what visual features the BoW model is learning. Which regions in the image or video are used to discriminate among classes? Which are the most discriminative visual words? Answering these questions is fundamental for understanding existing BoW models and inspiring better models for visual recognition. To answer these questions, this paper presents a method for feature selection and region selection in the visual BoW model. This allows for an intermediate visualization of the features and regions that are important for visual learning. The main idea is to assign latent weights to the features or regions, and jointly optimize these latent variables with the parameters of a classifier (e.g., support vector machine). There are four main benefits of our approach: 1) our approach accommodates non-linear additive kernels, such as the popular χ(2) and intersection kernel; 2) our approach is able to handle both regions in images and spatio-temporal regions in videos in a unified way; 3) the feature selection problem is convex, and both problems can be solved using a scalable reduced gradient method; and 4) we point out strong connections with multiple kernel learning and multiple instance learning approaches. Experimental results in the PASCAL VOC 2007, MSR Action Dataset II and YouTube illustrate the benefits of our approach.

Classifying Acute Ischemic Stroke Onset Time using Deep Imaging Features

PubMed Central

Ho, King Chung; Speier, William; El-Saden, Suzie; Arnold, Corey W.

2017-01-01

Models have been developed to predict stroke outcomes (e.g., mortality) in attempt to provide better guidance for stroke treatment. However, there is little work in developing classification models for the problem of unknown time-since-stroke (TSS), which determines a patient’s treatment eligibility based on a clinical defined cutoff time point (i.e., <4.5hrs). In this paper, we construct and compare machine learning methods to classify TSS<4.5hrs using magnetic resonance (MR) imaging features. We also propose a deep learning model to extract hidden representations from the MR perfusion-weighted images and demonstrate classification improvement by incorporating these additional imaging features. Finally, we discuss a strategy to visualize the learned features from the proposed deep learning model. The cross-validation results show that our best classifier achieved an area under the curve of 0.68, which improves significantly over current clinical methods (0.58), demonstrating the potential benefit of using advanced machine learning methods in TSS classification. PMID:29854156

An adaptive deep Q-learning strategy for handwritten digit recognition.

PubMed

Qiao, Junfei; Wang, Gongming; Li, Wenjing; Chen, Min

2018-02-22

Handwritten digits recognition is a challenging problem in recent years. Although many deep learning-based classification algorithms are studied for handwritten digits recognition, the recognition accuracy and running time still need to be further improved. In this paper, an adaptive deep Q-learning strategy is proposed to improve accuracy and shorten running time for handwritten digit recognition. The adaptive deep Q-learning strategy combines the feature-extracting capability of deep learning and the decision-making of reinforcement learning to form an adaptive Q-learning deep belief network (Q-ADBN). First, Q-ADBN extracts the features of original images using an adaptive deep auto-encoder (ADAE), and the extracted features are considered as the current states of Q-learning algorithm. Second, Q-ADBN receives Q-function (reward signal) during recognition of the current states, and the final handwritten digits recognition is implemented by maximizing the Q-function using Q-learning algorithm. Finally, experimental results from the well-known MNIST dataset show that the proposed Q-ADBN has a superiority to other similar methods in terms of accuracy and running time. Copyright © 2018 Elsevier Ltd. All rights reserved.

Implicit Learning of Recursive Context-Free Grammars

PubMed Central

Rohrmeier, Martin; Fu, Qiufang; Dienes, Zoltan

2012-01-01

Context-free grammars are fundamental for the description of linguistic syntax. However, most artificial grammar learning experiments have explored learning of simpler finite-state grammars, while studies exploring context-free grammars have not assessed awareness and implicitness. This paper explores the implicit learning of context-free grammars employing features of hierarchical organization, recursive embedding and long-distance dependencies. The grammars also featured the distinction between left- and right-branching structures, as well as between centre- and tail-embedding, both distinctions found in natural languages. People acquired unconscious knowledge of relations between grammatical classes even for dependencies over long distances, in ways that went beyond learning simpler relations (e.g. n-grams) between individual words. The structural distinctions drawn from linguistics also proved important as performance was greater for tail-embedding than centre-embedding structures. The results suggest the plausibility of implicit learning of complex context-free structures, which model some features of natural languages. They support the relevance of artificial grammar learning for probing mechanisms of language learning and challenge existing theories and computational models of implicit learning. PMID:23094021

Deep feature learning for knee cartilage segmentation using a triplanar convolutional neural network.

PubMed

Prasoon, Adhish; Petersen, Kersten; Igel, Christian; Lauze, François; Dam, Erik; Nielsen, Mads

2013-01-01

Segmentation of anatomical structures in medical images is often based on a voxel/pixel classification approach. Deep learning systems, such as convolutional neural networks (CNNs), can infer a hierarchical representation of images that fosters categorization. We propose a novel system for voxel classification integrating three 2D CNNs, which have a one-to-one association with the xy, yz and zx planes of 3D image, respectively. We applied our method to the segmentation of tibial cartilage in low field knee MRI scans and tested it on 114 unseen scans. Although our method uses only 2D features at a single scale, it performs better than a state-of-the-art method using 3D multi-scale features. In the latter approach, the features and the classifier have been carefully adapted to the problem at hand. That we were able to get better results by a deep learning architecture that autonomously learns the features from the images is the main insight of this study.

Less is More: How manipulative features affect children’s learning from picture books

PubMed Central

Tare, Medha; Chiong, Cynthia; Ganea, Patricia; DeLoache, Judy

2010-01-01

Picture books are ubiquitous in young children’s lives and are assumed to support children’s acquisition of information about the world. Given their importance, relatively little research has directly examined children’s learning from picture books. We report two studies examining children’s acquisition of labels and facts from picture books that vary on two dimensions: iconicity of the pictures and presence of manipulative features (or “pop-ups”). In Study 1, 20-month-old children generalized novel labels less well when taught from a book with manipulative features than from standard picture books without such elements. In Study 2, 30- and 36-month-old children learned fewer facts when taught from a manipulative picture book with drawings than from a standard picture book with realistic images and no manipulative features. The results of the two studies indicate that children’s learning from picture books is facilitated by realistic illustrations, but impeded by manipulative features. PMID:20948970

Discriminative Nonlinear Analysis Operator Learning: When Cosparse Model Meets Image Classification.

PubMed

Wen, Zaidao; Hou, Biao; Jiao, Licheng

2017-05-03

Linear synthesis model based dictionary learning framework has achieved remarkable performances in image classification in the last decade. Behaved as a generative feature model, it however suffers from some intrinsic deficiencies. In this paper, we propose a novel parametric nonlinear analysis cosparse model (NACM) with which a unique feature vector will be much more efficiently extracted. Additionally, we derive a deep insight to demonstrate that NACM is capable of simultaneously learning the task adapted feature transformation and regularization to encode our preferences, domain prior knowledge and task oriented supervised information into the features. The proposed NACM is devoted to the classification task as a discriminative feature model and yield a novel discriminative nonlinear analysis operator learning framework (DNAOL). The theoretical analysis and experimental performances clearly demonstrate that DNAOL will not only achieve the better or at least competitive classification accuracies than the state-of-the-art algorithms but it can also dramatically reduce the time complexities in both training and testing phases.

Deep Learning to Predict Falls in Older Adults Based on Daily-Life Trunk Accelerometry.

PubMed

Nait Aicha, Ahmed; Englebienne, Gwenn; van Schooten, Kimberley S; Pijnappels, Mirjam; Kröse, Ben

2018-05-22

Early detection of high fall risk is an essential component of fall prevention in older adults. Wearable sensors can provide valuable insight into daily-life activities; biomechanical features extracted from such inertial data have been shown to be of added value for the assessment of fall risk. Body-worn sensors such as accelerometers can provide valuable insight into fall risk. Currently, biomechanical features derived from accelerometer data are used for the assessment of fall risk. Here, we studied whether deep learning methods from machine learning are suited to automatically derive features from raw accelerometer data that assess fall risk. We used an existing dataset of 296 older adults. We compared the performance of three deep learning model architectures (convolutional neural network (CNN), long short-term memory (LSTM) and a combination of these two (ConvLSTM)) to each other and to a baseline model with biomechanical features on the same dataset. The results show that the deep learning models in a single-task learning mode are strong in recognition of identity of the subject, but that these models only slightly outperform the baseline method on fall risk assessment. When using multi-task learning, with gender and age as auxiliary tasks, deep learning models perform better. We also found that preprocessing of the data resulted in the best performance (AUC = 0.75). We conclude that deep learning models, and in particular multi-task learning, effectively assess fall risk on the basis of wearable sensor data.

Deep Learning to Predict Falls in Older Adults Based on Daily-Life Trunk Accelerometry

PubMed Central

Englebienne, Gwenn; Pijnappels, Mirjam

2018-01-01

Early detection of high fall risk is an essential component of fall prevention in older adults. Wearable sensors can provide valuable insight into daily-life activities; biomechanical features extracted from such inertial data have been shown to be of added value for the assessment of fall risk. Body-worn sensors such as accelerometers can provide valuable insight into fall risk. Currently, biomechanical features derived from accelerometer data are used for the assessment of fall risk. Here, we studied whether deep learning methods from machine learning are suited to automatically derive features from raw accelerometer data that assess fall risk. We used an existing dataset of 296 older adults. We compared the performance of three deep learning model architectures (convolutional neural network (CNN), long short-term memory (LSTM) and a combination of these two (ConvLSTM)) to each other and to a baseline model with biomechanical features on the same dataset. The results show that the deep learning models in a single-task learning mode are strong in recognition of identity of the subject, but that these models only slightly outperform the baseline method on fall risk assessment. When using multi-task learning, with gender and age as auxiliary tasks, deep learning models perform better. We also found that preprocessing of the data resulted in the best performance (AUC = 0.75). We conclude that deep learning models, and in particular multi-task learning, effectively assess fall risk on the basis of wearable sensor data. PMID:29786659

Constrained dictionary learning and probabilistic hypergraph ranking for person re-identification

NASA Astrophysics Data System (ADS)

He, You; Wu, Song; Pu, Nan; Qian, Li; Xiao, Guoqiang

2018-04-01

Person re-identification is a fundamental and inevitable task in public security. In this paper, we propose a novel framework to improve the performance of this task. First, two different types of descriptors are extracted to represent a pedestrian: (1) appearance-based superpixel features, which are constituted mainly by conventional color features and extracted from the supepixel rather than a whole picture and (2) due to the limitation of discrimination of appearance features, the deep features extracted by feature fusion Network are also used. Second, a view invariant subspace is learned by dictionary learning constrained by the minimum negative sample (termed as DL-cMN) to reduce the noise in appearance-based superpixel feature domain. Then, we use deep features and sparse codes transformed by appearancebased features to establish the hyperedges respectively by k-nearest neighbor, rather than jointing different features simply. Finally, a final ranking is performed by probabilistic hypergraph ranking algorithm. Extensive experiments on three challenging datasets (VIPeR, PRID450S and CUHK01) demonstrate the advantages and effectiveness of our proposed algorithm.

Conceptual development and retention within the learning cycle

NASA Astrophysics Data System (ADS)

McWhirter, Lisa Jo

1998-12-01

This research was designed to achieve two goals: (1) examine concept development and retention within the learning cycle and (2) examine how students' concept development is mediated by classroom discussions and the students' small cooperative learning group. Forty-eight sixth-grade students and one teacher at an urban middle school participated in the study. The research utilized both quantitative and qualitative analyses. Quantitative assessments included a concept mapping technique as well as teacher generated multiple choice tests. Preliminary quantitative analysis found that students' reading levels had an effect on students' pretest scores in both the concept mapping and the multiple-choice assessment. Therefore, a covariant design was implemented for the quantitative analyses. Quantitative analysis techniques were used to examine concept development and retention, it was discovered that the students' concept knowledge increased significantly from the time of the conclusion of the term introduction phase to the conclusion of the expansion phase. These findings would indicate that all three phases of the learning cycle are necessary for conceptual development. However, quantitative analyses of concept maps indicated that this is not true for all students. Individual students showed evidence of concept development and integration at each phase. Therefore, concept development is individualized and all phases of the learning cycle are not necessary for all students. As a result, individual's assimilation, disequilibration, accommodation and organization may not correlate with the phases of the learning cycle. Quantitative analysis also indicated a significant decrease in the retention of concepts over time. Qualitative analyses were used to examine how students' concept development is mediated by classroom discussions and the students' small cooperative learning group. It was discovered that there was a correlation between teacher-student interaction and small-group interaction and concept mediation. Therefore, students who had a high level of teacher-student dialogue which utilized teacher led discussions with integrated scaffolding techniques where the same students who mediated the ideas within the small group discussions. Those students whose teacher-student interactions consisted of dialogue with little positive teacher feedback made no contributions within the small group regardless of their level of concept development.

On Social e-Learning

NASA Astrophysics Data System (ADS)

Kim, Won; Jeong, Ok-Ran

Social Web sites include social networking sites and social media sites. They make it possible for people to share user-created contents online and to interact and stay connected with their online people networks. The social features of social Web sites, appropriately adapted, can help turn e-learning into social e-learning and make e-learning significantly more effective. In this paper, we develop requirements for social e-learning systems. They include incorporating the many of the social features of social Web sites, accounting for all key stakeholders and learning subjects, and curbing various types of misuses by people. We also examine the capabilities of representative social e-learning Web sites that are available today.

Daily and Developmental Modulation of “Premotor” Activity in the Birdsong System

PubMed Central

Day, Nancy F.; Kinnischtzke, Amanda K.; Adam, Murtaza; Nick, Teresa A.

2009-01-01

Human speech and birdsong are shaped during a sensorimotor sensitive period in which auditory feedback guides vocal learning. To study brain activity as song learning occurred, we recorded longitudinally from developing zebra finches during the sensorimotor phase. Learned sequences of vocalizations (motifs) were examined along with contemporaneous neural population activity in the song nucleus HVC, which is necessary for the production of learned song (Nottebohm et al. [1976]: J Comp Neurol 165:457–486; Simpson and Vicario [1990]: J Neurosci 10:1541–1556). During singing, HVC activity levels increased as the day progressed and decreased after a night of sleep in juveniles and adults. In contrast, the pattern of HVC activity changed on a daily basis only in juveniles: activity bursts became more pronounced during the day. The HVC of adults was significantly burstier than that of juveniles. HVC bursting was relevant to song behavior because the degree of burstiness inversely correlated with the variance of song features in juveniles. The song of juveniles degrades overnight (Deregnaucourt et al. [2005]: Nature 433:710–716). Consistent with a relationship between HVC activity and song plasticity (Day et al. [2008]: J Neurophys 100:2956–2965), HVC burstiness degraded overnight in young juveniles and the amount of overnight degradation declined with developmental song learning. Nocturnal changes in HVC activity strongly and inversely correlated with the next day's change, suggesting that sleep-dependent degradation of HVC activity may facilitate or enable subsequent diurnal changes. Collectively, these data show that HVC activity levels exhibit daily cycles in adults and juveniles, whereas HVC burstiness and song stereotypy change daily in juveniles only. In addition, the data indicate that HVC burstiness increases with development and inversely correlates with song variability, which is necessary for trial and error vocal learning. PMID:19650042

Computational modeling of spiking neural network with learning rules from STDP and intrinsic plasticity

NASA Astrophysics Data System (ADS)

Li, Xiumin; Wang, Wei; Xue, Fangzheng; Song, Yongduan

2018-02-01

Recently there has been continuously increasing interest in building up computational models of spiking neural networks (SNN), such as the Liquid State Machine (LSM). The biologically inspired self-organized neural networks with neural plasticity can enhance the capability of computational performance, with the characteristic features of dynamical memory and recurrent connection cycles which distinguish them from the more widely used feedforward neural networks. Despite a variety of computational models for brain-like learning and information processing have been proposed, the modeling of self-organized neural networks with multi-neural plasticity is still an important open challenge. The main difficulties lie in the interplay among different forms of neural plasticity rules and understanding how structures and dynamics of neural networks shape the computational performance. In this paper, we propose a novel approach to develop the models of LSM with a biologically inspired self-organizing network based on two neural plasticity learning rules. The connectivity among excitatory neurons is adapted by spike-timing-dependent plasticity (STDP) learning; meanwhile, the degrees of neuronal excitability are regulated to maintain a moderate average activity level by another learning rule: intrinsic plasticity (IP). Our study shows that LSM with STDP+IP performs better than LSM with a random SNN or SNN obtained by STDP alone. The noticeable improvement with the proposed method is due to the better reflected competition among different neurons in the developed SNN model, as well as the more effectively encoded and processed relevant dynamic information with its learning and self-organizing mechanism. This result gives insights to the optimization of computational models of spiking neural networks with neural plasticity.

Problem Finding in Professional Learning Communities: A Learning Study Approach

ERIC Educational Resources Information Center

Tan, Yuen Sze Michelle; Caleon, Imelda Santos

2016-01-01

This study marries collaborative problem solving and learning study in understanding the onset of a cycle of teacher professional development process within school-based professional learning communities (PLCs). It aimed to explore how a PLC carried out collaborative problem finding--a key process involved in collaborative problem solving--that…

Teachers' Use of Experiential Learning Stages in Agricultural Laboratories

ERIC Educational Resources Information Center

Shoulders, Catherine W.; Myers, Brian E.

2013-01-01

Experiential learning in agricultural laboratories has been a foundational component of secondary agricultural education. While inclusion of the four stages of the experiential learning cycle can enhance student learning in laboratory settings to help students reach various goals related to scientific literacy and higher-level thinking,…

Learner-Focused Evaluation Cycles: Facilitating Learning Using Feedforward, Concurrent and Feedback Evaluation

ERIC Educational Resources Information Center

Cathcart, Abby; Greer, Dominique; Neale, Larry

2014-01-01

There is a growing trend to offer students learning opportunities that are flexible, innovative and engaging. As educators embrace student-centred agile teaching and learning methodologies, which require continuous reflection and adaptation, the need to evaluate students' learning in a timely manner has become more pressing. Conventional…

Learning Families: Intergenerational Approach to Literacy Teaching and Learning

ERIC Educational Resources Information Center

Hanemann, Ulrike, Ed.

2015-01-01

Within a learning family, every member is a lifelong learner. A family literacy and learning approach is more likely to break the intergenerational cycle of low education and inadequate literacy skills, particularly among disadvantaged families and communities. The selection of case studies presented in this compilation show that for an…

Learning better deep features for the prediction of occult invasive disease in ductal carcinoma in situ through transfer learning

NASA Astrophysics Data System (ADS)

Shi, Bibo; Hou, Rui; Mazurowski, Maciej A.; Grimm, Lars J.; Ren, Yinhao; Marks, Jeffrey R.; King, Lorraine M.; Maley, Carlo C.; Hwang, E. Shelley; Lo, Joseph Y.

2018-02-01

Purpose: To determine whether domain transfer learning can improve the performance of deep features extracted from digital mammograms using a pre-trained deep convolutional neural network (CNN) in the prediction of occult invasive disease for patients with ductal carcinoma in situ (DCIS) on core needle biopsy. Method: In this study, we collected digital mammography magnification views for 140 patients with DCIS at biopsy, 35 of which were subsequently upstaged to invasive cancer. We utilized a deep CNN model that was pre-trained on two natural image data sets (ImageNet and DTD) and one mammographic data set (INbreast) as the feature extractor, hypothesizing that these data sets are increasingly more similar to our target task and will lead to better representations of deep features to describe DCIS lesions. Through a statistical pooling strategy, three sets of deep features were extracted using the CNNs at different levels of convolutional layers from the lesion areas. A logistic regression classifier was then trained to predict which tumors contain occult invasive disease. The generalization performance was assessed and compared using repeated random sub-sampling validation and receiver operating characteristic (ROC) curve analysis. Result: The best performance of deep features was from CNN model pre-trained on INbreast, and the proposed classifier using this set of deep features was able to achieve a median classification performance of ROC-AUC equal to 0.75, which is significantly better (p<=0.05) than the performance of deep features extracted using ImageNet data set (ROCAUC = 0.68). Conclusion: Transfer learning is helpful for learning a better representation of deep features, and improves the prediction of occult invasive disease in DCIS.

Shallow Strategy Development in a Teachable Agent Environment Designed to Support Self-Regulated Learning

ERIC Educational Resources Information Center

Roscoe, Rod D.; Segedy, James R.; Sulcer, Brian; Jeong, Hogyeong; Biswas, Gautam

2013-01-01

To support self-regulated learning (SRL), computer-based learning environments (CBLEs) are often designed to be open-ended and multidimensional. These systems incorporate diverse features that allow students to enact and reveal their SRL strategies via the choices they make. However, research shows that students' use of such features is limited;…

The Impact of Game-Like Features on Learning from an Intelligent Tutoring System

ERIC Educational Resources Information Center

Millis, Keith; Forsyth, Carol; Wallace, Patricia; Graesser, Arthur C.; Timmins, Gary

2017-01-01

Prior research has shown that students learn from Intelligent Tutoring Systems (ITS). However, students' attention may drift or become disengaged with the task over extended amounts of instruction. To remedy this problem, researchers have examined the impact of game-like features (e.g., a narrative) in digital learning environments on motivation…

Assessing the Utilization Level of E-Learning Resources among ODL Based Pre-Service Teacher Trainees

ERIC Educational Resources Information Center

Olaniran, Sunday O.; Duma, M. A. N.; Nzima, D. R.

2017-01-01

Electronic resources have become a dominant feature of higher education, both traditional and distance learning based. Unlike in the past when universities relied majorly on the physical library and hard copy of books, e-books accessible through e-libraries are the dominant features of this century's institutions of higher learning. This study…

A stable biologically motivated learning mechanism for visual feature extraction to handle facial categorization.

PubMed

Rajaei, Karim; Khaligh-Razavi, Seyed-Mahdi; Ghodrati, Masoud; Ebrahimpour, Reza; Shiri Ahmad Abadi, Mohammad Ebrahim

2012-01-01

The brain mechanism of extracting visual features for recognizing various objects has consistently been a controversial issue in computational models of object recognition. To extract visual features, we introduce a new, biologically motivated model for facial categorization, which is an extension of the Hubel and Wiesel simple-to-complex cell hierarchy. To address the synaptic stability versus plasticity dilemma, we apply the Adaptive Resonance Theory (ART) for extracting informative intermediate level visual features during the learning process, which also makes this model stable against the destruction of previously learned information while learning new information. Such a mechanism has been suggested to be embedded within known laminar microcircuits of the cerebral cortex. To reveal the strength of the proposed visual feature learning mechanism, we show that when we use this mechanism in the training process of a well-known biologically motivated object recognition model (the HMAX model), it performs better than the HMAX model in face/non-face classification tasks. Furthermore, we demonstrate that our proposed mechanism is capable of following similar trends in performance as humans in a psychophysical experiment using a face versus non-face rapid categorization task.

Atoms of recognition in human and computer vision.

PubMed

Ullman, Shimon; Assif, Liav; Fetaya, Ethan; Harari, Daniel

2016-03-08

Discovering the visual features and representations used by the brain to recognize objects is a central problem in the study of vision. Recently, neural network models of visual object recognition, including biological and deep network models, have shown remarkable progress and have begun to rival human performance in some challenging tasks. These models are trained on image examples and learn to extract features and representations and to use them for categorization. It remains unclear, however, whether the representations and learning processes discovered by current models are similar to those used by the human visual system. Here we show, by introducing and using minimal recognizable images, that the human visual system uses features and processes that are not used by current models and that are critical for recognition. We found by psychophysical studies that at the level of minimal recognizable images a minute change in the image can have a drastic effect on recognition, thus identifying features that are critical for the task. Simulations then showed that current models cannot explain this sensitivity to precise feature configurations and, more generally, do not learn to recognize minimal images at a human level. The role of the features shown here is revealed uniquely at the minimal level, where the contribution of each feature is essential. A full understanding of the learning and use of such features will extend our understanding of visual recognition and its cortical mechanisms and will enhance the capacity of computational models to learn from visual experience and to deal with recognition and detailed image interpretation.

Improving Mathematics Achievement of Indonesian 5th Grade Students through Guided Discovery Learning

ERIC Educational Resources Information Center

Yurniwati; Hanum, Latipa

2017-01-01

This research aims to find information about the improvement of mathematics achievement of grade five student through guided discovery learning. This research method is classroom action research using Kemmis and Taggart model consists of three cycles. Data used in this study is learning process and learning results. Learning process data is…

Mobile Learning vs. Traditional Classroom Lessons: A Comparative Study

ERIC Educational Resources Information Center

Furió, D.; Juan, M.-C.; Seguí, I.; Vivó, R.

2015-01-01

Different methods can be used for learning, and they can be compared in several aspects, especially those related to learning outcomes. In this paper, we present a study in order to compare the learning effectiveness and satisfaction of children using an iPhone game for learning the water cycle vs. the traditional classroom lesson. The iPhone game…

The Substance Beneath the Labels of Experiential Learning: The Importance of John Dewey for Outdoor Educators

ERIC Educational Resources Information Center

Ord, Jon; Leather, Mark

2011-01-01

This paper recommends a reconceptualisation of "experience learning". It is premised on a belief that the simplistic learning cycle is problematic and moreover is an oversimplified interpretation of Kolb's original model of experiential learning. We argue that to understand experiential learning fully a return to the original theoretical…

Identifying Students' Difficulties When Learning Technical Skills via a Wireless Sensor Network

ERIC Educational Resources Information Center

Wang, Jingying; Wen, Ming-Lee; Jou, Min

2016-01-01

Practical training and actual application of acquired knowledge and techniques are crucial for the learning of technical skills. We established a wireless sensor network system (WSNS) based on the 5E learning cycle in a practical learning environment to improve students' reflective abilities and to reduce difficulties for the learning of technical…

Perceptual learning: toward a comprehensive theory.

PubMed

Watanabe, Takeo; Sasaki, Yuka

2015-01-03

Visual perceptual learning (VPL) is long-term performance increase resulting from visual perceptual experience. Task-relevant VPL of a feature results from training of a task on the feature relevant to the task. Task-irrelevant VPL arises as a result of exposure to the feature irrelevant to the trained task. At least two serious problems exist. First, there is the controversy over which stage of information processing is changed in association with task-relevant VPL. Second, no model has ever explained both task-relevant and task-irrelevant VPL. Here we propose a dual plasticity model in which feature-based plasticity is a change in a representation of the learned feature, and task-based plasticity is a change in processing of the trained task. Although the two types of plasticity underlie task-relevant VPL, only feature-based plasticity underlies task-irrelevant VPL. This model provides a new comprehensive framework in which apparently contradictory results could be explained.

Accelerating Biomedical Signal Processing Using GPU: A Case Study of Snore Sound Feature Extraction.

PubMed

Guo, Jian; Qian, Kun; Zhang, Gongxuan; Xu, Huijie; Schuller, Björn

2017-12-01

The advent of 'Big Data' and 'Deep Learning' offers both, a great challenge and a huge opportunity for personalised health-care. In machine learning-based biomedical data analysis, feature extraction is a key step for 'feeding' the subsequent classifiers. With increasing numbers of biomedical data, extracting features from these 'big' data is an intensive and time-consuming task. In this case study, we employ a Graphics Processing Unit (GPU) via Python to extract features from a large corpus of snore sound data. Those features can subsequently be imported into many well-known deep learning training frameworks without any format processing. The snore sound data were collected from several hospitals (20 subjects, with 770-990 MB per subject - in total 17.20 GB). Experimental results show that our GPU-based processing significantly speeds up the feature extraction phase, by up to seven times, as compared to the previous CPU system.

Impact of Online Instructional Game Features on College Students' Perceived Motivational Support and Cognitive Investment: A Structural Equation Modeling Study

ERIC Educational Resources Information Center

Huang, Wenhao David; Johnson, Tristan E.; Han, Seung-Hyun Caleb

2013-01-01

Colleges and universities have begun to understand the instructional potential of digital game-based learning (DGBL) due to digital games' immersive features. These features, however, might overload learners as excessive motivational and cognitive stimuli thus impeding intended learning. Current research, however, lacks empirical evidences to…

Comparing Curriculum Types: 'Powerful Knowledge' and '21st Century Learning'

ERIC Educational Resources Information Center

McPhail, Graham; Rata, Elizabeth

2016-01-01

This paper theorises a curriculum model containing four features. We use these features as criteria to analyse and evaluate two distinctive curriculum design types: '21st Century Learning' and 'Powerful Knowledge'. The four features are: (i) the underpinning theory of knowledge in each curriculum design type; (ii) the knowledge structures used to…

The Identification, Implementation, and Evaluation of Critical User Interface Design Features of Computer-Assisted Instruction Programs in Mathematics for Students with Learning Disabilities

ERIC Educational Resources Information Center

Seo, You-Jin; Woo, Honguk

2010-01-01

Critical user interface design features of computer-assisted instruction programs in mathematics for students with learning disabilities and corresponding implementation guidelines were identified in this study. Based on the identified features and guidelines, a multimedia computer-assisted instruction program, "Math Explorer", which delivers…

GalaxyGAN: Generative Adversarial Networks for recovery of galaxy features

NASA Astrophysics Data System (ADS)

Schawinski, Kevin; Zhang, Ce; Zhang, Hantian; Fowler, Lucas; Krishnan Santhanam, Gokula

2017-02-01

GalaxyGAN uses Generative Adversarial Networks to reliably recover features in images of galaxies. The package uses machine learning to train on higher quality data and learns to recover detailed features such as galaxy morphology by effectively building priors. This method opens up the possibility of recovering more information from existing and future imaging data.

Can theories of animal discrimination explain perceptual learning in humans?

PubMed

Mitchell, Chris; Hall, Geoffrey

2014-01-01

We present a review of recent studies of perceptual learning conducted with nonhuman animals. The focus of this research has been to elucidate the mechanisms by which mere exposure to a pair of similar stimuli can increase the ease with which those stimuli are discriminated. These studies establish an important role for 2 mechanisms, one involving inhibitory associations between the unique features of the stimuli, the other involving a long-term habituation process that enhances the relative salience of these features. We then examine recent work investigating equivalent perceptual learning procedures with human participants. Our aim is to determine the extent to which the phenomena exhibited by people are susceptible to explanation in terms of the mechanisms revealed by the animal studies. Although we find no evidence that associative inhibition contributes to the perceptual learning effect in humans, initial detection of unique features (those that allow discrimination between 2 similar stimuli) appears to depend on an habituation process. Once the unique features have been detected, a tendency to attend to those features and to learn about their properties enhances subsequent discrimination. We conclude that the effects obtained with humans engage mechanisms additional to those seen in animals but argue that, for the most part, these have their basis in learning processes that are common to animals and people. In a final section, we discuss some implications of this analysis of perceptual learning for other aspects of experimental psychology and consider some potential applications. (PsycINFO Database Record (c) 2013 APA, all rights reserved).

Sparsity-aware tight frame learning with adaptive subspace recognition for multiple fault diagnosis

NASA Astrophysics Data System (ADS)

Zhang, Han; Chen, Xuefeng; Du, Zhaohui; Yang, Boyuan

2017-09-01

It is a challenging problem to design excellent dictionaries to sparsely represent diverse fault information and simultaneously discriminate different fault sources. Therefore, this paper describes and analyzes a novel multiple feature recognition framework which incorporates the tight frame learning technique with an adaptive subspace recognition strategy. The proposed framework consists of four stages. Firstly, by introducing the tight frame constraint into the popular dictionary learning model, the proposed tight frame learning model could be formulated as a nonconvex optimization problem which can be solved by alternatively implementing hard thresholding operation and singular value decomposition. Secondly, the noises are effectively eliminated through transform sparse coding techniques. Thirdly, the denoised signal is decoupled into discriminative feature subspaces by each tight frame filter. Finally, in guidance of elaborately designed fault related sensitive indexes, latent fault feature subspaces can be adaptively recognized and multiple faults are diagnosed simultaneously. Extensive numerical experiments are sequently implemented to investigate the sparsifying capability of the learned tight frame as well as its comprehensive denoising performance. Most importantly, the feasibility and superiority of the proposed framework is verified through performing multiple fault diagnosis of motor bearings. Compared with the state-of-the-art fault detection techniques, some important advantages have been observed: firstly, the proposed framework incorporates the physical prior with the data-driven strategy and naturally multiple fault feature with similar oscillation morphology can be adaptively decoupled. Secondly, the tight frame dictionary directly learned from the noisy observation can significantly promote the sparsity of fault features compared to analytical tight frames. Thirdly, a satisfactory complete signal space description property is guaranteed and thus weak feature leakage problem is avoided compared to typical learning methods.

Robust sensorimotor representation to physical interaction changes in humanoid motion learning.

PubMed

Shimizu, Toshihiko; Saegusa, Ryo; Ikemoto, Shuhei; Ishiguro, Hiroshi; Metta, Giorgio

2015-05-01

This paper proposes a learning from demonstration system based on a motion feature, called phase transfer sequence. The system aims to synthesize the knowledge on humanoid whole body motions learned during teacher-supported interactions, and apply this knowledge during different physical interactions between a robot and its surroundings. The phase transfer sequence represents the temporal order of the changing points in multiple time sequences. It encodes the dynamical aspects of the sequences so as to absorb the gaps in timing and amplitude derived from interaction changes. The phase transfer sequence was evaluated in reinforcement learning of sitting-up and walking motions conducted by a real humanoid robot and compatible simulator. In both tasks, the robotic motions were less dependent on physical interactions when learned by the proposed feature than by conventional similarity measurements. Phase transfer sequence also enhanced the convergence speed of motion learning. Our proposed feature is original primarily because it absorbs the gaps caused by changes of the originally acquired physical interactions, thereby enhancing the learning speed in subsequent interactions.

Epidermis area detection for immunofluorescence microscopy

NASA Astrophysics Data System (ADS)

Dovganich, Andrey; Krylov, Andrey; Nasonov, Andrey; Makhneva, Natalia

2018-04-01

We propose a novel image segmentation method for immunofluorescence microscopy images of skin tissue for the diagnosis of various skin diseases. The segmentation is based on machine learning algorithms. The feature vector is filled by three groups of features: statistical features, Laws' texture energy measures and local binary patterns. The images are preprocessed for better learning. Different machine learning algorithms have been used and the best results have been obtained with random forest algorithm. We use the proposed method to detect the epidermis region as a part of pemphigus diagnosis system.

Learning diagnostic models using speech and language measures.

PubMed

Peintner, Bart; Jarrold, William; Vergyriy, Dimitra; Richey, Colleen; Tempini, Maria Luisa Gorno; Ogar, Jennifer

2008-01-01

We describe results that show the effectiveness of machine learning in the automatic diagnosis of certain neurodegenerative diseases, several of which alter speech and language production. We analyzed audio from 9 control subjects and 30 patients diagnosed with one of three subtypes of Frontotemporal Lobar Degeneration. From this data, we extracted features of the audio signal and the words the patient used, which were obtained using our automated transcription technologies. We then automatically learned models that predict the diagnosis of the patient using these features. Our results show that learned models over these features predict diagnosis with accuracy significantly better than random. Future studies using higher quality recordings will likely improve these results.

Learning to segment mouse embryo cells

NASA Astrophysics Data System (ADS)

León, Juan; Pardo, Alejandro; Arbeláez, Pablo

2017-11-01

Recent advances in microscopy enable the capture of temporal sequences during cell development stages. However, the study of such sequences is a complex task and time consuming task. In this paper we propose an automatic strategy to adders the problem of semantic and instance segmentation of mouse embryos using NYU's Mouse Embryo Tracking Database. We obtain our instance proposals as refined predictions from the generalized hough transform, using prior knowledge of the embryo's locations and their current cell stage. We use two main approaches to learn the priors: Hand crafted features and automatic learned features. Our strategy increases the baseline jaccard index from 0.12 up to 0.24 using hand crafted features and 0.28 by using automatic learned ones.

Classifying EEG for Brain-Computer Interface: Learning Optimal Filters for Dynamical System Features

PubMed Central

Song, Le; Epps, Julien

2007-01-01

Classification of multichannel EEG recordings during motor imagination has been exploited successfully for brain-computer interfaces (BCI). In this paper, we consider EEG signals as the outputs of a networked dynamical system (the cortex), and exploit synchronization features from the dynamical system for classification. Herein, we also propose a new framework for learning optimal filters automatically from the data, by employing a Fisher ratio criterion. Experimental evaluations comparing the proposed dynamical system features with the CSP and the AR features reveal their competitive performance during classification. Results also show the benefits of employing the spatial and the temporal filters optimized using the proposed learning approach. PMID:18364986

Deep Learning Based Binaural Speech Separation in Reverberant Environments.

PubMed

Zhang, Xueliang; Wang, DeLiang

2017-05-01

Speech signal is usually degraded by room reverberation and additive noises in real environments. This paper focuses on separating target speech signal in reverberant conditions from binaural inputs. Binaural separation is formulated as a supervised learning problem, and we employ deep learning to map from both spatial and spectral features to a training target. With binaural inputs, we first apply a fixed beamformer and then extract several spectral features. A new spatial feature is proposed and extracted to complement the spectral features. The training target is the recently suggested ideal ratio mask. Systematic evaluations and comparisons show that the proposed system achieves very good separation performance and substantially outperforms related algorithms under challenging multi-source and reverberant environments.

Applying data mining techniques for increasing implantation rate by selecting best sperms for intra-cytoplasmic sperm injection treatment.

PubMed

Mirroshandel, Seyed Abolghasem; Ghasemian, Fatemeh; Monji-Azad, Sara

2016-12-01

Aspiration of a good-quality sperm during intracytoplasmic sperm injection (ICSI) is one of the main concerns. Understanding the influence of individual sperm morphology on fertilization, embryo quality, and pregnancy probability is one of the most important subjects in male factor infertility. Embryologists need to decide the best sperm for injection in real time during ICSI cycle. Our objective is to predict the quality of zygote, embryo, and implantation outcome before injection of each sperm in an ICSI cycle for male factor infertility with the aim of providing a decision support system on the sperm selection. The information was collected from 219 patients with male factor infertility at the infertility therapy center of Alzahra hospital in Rasht from 2012 through 2014. The prepared dataset included the quality of zygote, embryo, and implantation outcome of 1544 injected sperms into the related oocytes. In our study, embryo transfer was performed at day 3. Each sperm was represented with thirteen clinical features. Data preprocessing was the first step in the proposed data mining algorithm. After applying more than 30 classifiers, 9 successful classifiers were selected and evaluated by 10-fold cross validation technique using precision, recall, F1, and AUC measures. Another important experiment was measuring the effect of each feature in prediction process. In zygote and embryo quality prediction, IBK and RandomCommittee models provided 79.2% and 83.8% F1, respectively. In implantation outcome prediction, KStar model achieved 95.9% F1, which is even better than prediction of human experts. All these predictions can be done in real time. A machine learning-based decision support system would be helpful in sperm selection phase of ICSI cycle to improve the success rate of ICSI treatment. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

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.

Learning to Teach Elementary Science Through Iterative Cycles of Enactment in Culturally and Linguistically Diverse Contexts

NASA Astrophysics Data System (ADS)

Bottoms, SueAnn I.; Ciechanowski, Kathryn M.; Hartman, Brian

2015-12-01

Iterative cycles of enactment embedded in culturally and linguistically diverse contexts provide rich opportunities for preservice teachers (PSTs) to enact core practices of science. This study is situated in the larger Families Involved in Sociocultural Teaching and Science, Technology, Engineering and Mathematics (FIESTAS) project, which weaves together cycles of enactment, core practices in science education and culturally relevant pedagogies. The theoretical foundation draws upon situated learning theory and communities of practice. Using video analysis by PSTs and course artifacts, the authors studied how the iterative process of these cycles guided PSTs development as teachers of elementary science. Findings demonstrate how PSTs were drawing on resources to inform practice, purposefully noticing their practice, renegotiating their roles in teaching, and reconsidering "professional blindness" through cultural practice.

Effect of Distinctive Feature Training on Paired-Associate Learning

ERIC Educational Resources Information Center

Samuels, S. Jay

1973-01-01

Purpose of this study was to test the hypothesis that training the student to note the distinctive features of a stimulus during perceptual learning facilities the hook-up phase in a paired-associate task. (Author)

Decomposition and extraction: a new framework for visual classification.

PubMed

Fang, Yuqiang; Chen, Qiang; Sun, Lin; Dai, Bin; Yan, Shuicheng

2014-08-01

In this paper, we present a novel framework for visual classification based on hierarchical image decomposition and hybrid midlevel feature extraction. Unlike most midlevel feature learning methods, which focus on the process of coding or pooling, we emphasize that the mechanism of image composition also strongly influences the feature extraction. To effectively explore the image content for the feature extraction, we model a multiplicity feature representation mechanism through meaningful hierarchical image decomposition followed by a fusion step. In particularly, we first propose a new hierarchical image decomposition approach in which each image is decomposed into a series of hierarchical semantical components, i.e, the structure and texture images. Then, different feature extraction schemes can be adopted to match the decomposed structure and texture processes in a dissociative manner. Here, two schemes are explored to produce property related feature representations. One is based on a single-stage network over hand-crafted features and the other is based on a multistage network, which can learn features from raw pixels automatically. Finally, those multiple midlevel features are incorporated by solving a multiple kernel learning task. Extensive experiments are conducted on several challenging data sets for visual classification, and experimental results demonstrate the effectiveness of the proposed method.

Rolling bearing fault feature learning using improved convolutional deep belief network with compressed sensing

NASA Astrophysics Data System (ADS)

Shao, Haidong; Jiang, Hongkai; Zhang, Haizhou; Duan, Wenjing; Liang, Tianchen; Wu, Shuaipeng

2018-02-01

The vibration signals collected from rolling bearing are usually complex and non-stationary with heavy background noise. Therefore, it is a great challenge to efficiently learn the representative fault features of the collected vibration signals. In this paper, a novel method called improved convolutional deep belief network (CDBN) with compressed sensing (CS) is developed for feature learning and fault diagnosis of rolling bearing. Firstly, CS is adopted for reducing the vibration data amount to improve analysis efficiency. Secondly, a new CDBN model is constructed with Gaussian visible units to enhance the feature learning ability for the compressed data. Finally, exponential moving average (EMA) technique is employed to improve the generalization performance of the constructed deep model. The developed method is applied to analyze the experimental rolling bearing vibration signals. The results confirm that the developed method is more effective than the traditional methods.

Machine learning spatial geometry from entanglement features

NASA Astrophysics Data System (ADS)

You, Yi-Zhuang; Yang, Zhao; Qi, Xiao-Liang

2018-02-01

Motivated by the close relations of the renormalization group with both the holography duality and the deep learning, we propose that the holographic geometry can emerge from deep learning the entanglement feature of a quantum many-body state. We develop a concrete algorithm, call the entanglement feature learning (EFL), based on the random tensor network (RTN) model for the tensor network holography. We show that each RTN can be mapped to a Boltzmann machine, trained by the entanglement entropies over all subregions of a given quantum many-body state. The goal is to construct the optimal RTN that best reproduce the entanglement feature. The RTN geometry can then be interpreted as the emergent holographic geometry. We demonstrate the EFL algorithm on a 1D free fermion system and observe the emergence of the hyperbolic geometry (AdS3 spatial geometry) as we tune the fermion system towards the gapless critical point (CFT2 point).

Clinical trial tests drug for tumors associated with Krebs-cycle dysfunction | Center for Cancer Research

Cancer.gov

The Krebs cycle is part of the complex process where cells turn food into energy. One of the elements of the Krebs cycle is succinate dehydrogenase (SDH). Loss of SDH activity in cells has been linked to tumor formation. This new trial is studying guadecitabine for tumors associated with Krebs cycle dysfunction. Learn more...

Fast mapping semantic features: performance of adults with normal language, history of disorders of spoken and written language, and attention deficit hyperactivity disorder on a word-learning task.

PubMed

Alt, Mary; Gutmann, Michelle L

2009-01-01

This study was designed to test the word learning abilities of adults with typical language abilities, those with a history of disorders of spoken or written language (hDSWL), and hDSWL plus attention deficit hyperactivity disorder (+ADHD). Sixty-eight adults were required to associate a novel object with a novel label, and then recognize semantic features of the object and phonological features of the label. Participants were tested for overt ability (accuracy) and covert processing (reaction time). The +ADHD group was less accurate at mapping semantic features and slower to respond to lexical labels than both other groups. Different factors correlated with word learning performance for each group. Adults with language and attention deficits are more impaired at word learning than adults with language deficits only. Despite behavioral profiles like typical peers, adults with hDSWL may use different processing strategies than their peers. Readers will be able to: (1) recognize the influence of a dual disability (hDSWL and ADHD) on word learning outcomes; (2) identify factors that may contribute to word learning in adults in terms of (a) the nature of the words to be learned and (b) the language processing of the learner.

Comparison expert and novice scan behavior for using e-learning

NASA Astrophysics Data System (ADS)

Novita Sari, Felisia; Insap Santosa, Paulus; Wibirama, Sunu

2017-06-01

E-Learning is an important media that an educational institution must have. Successful information design for e-learning depends on its user's characteristics. This study explores differences between novice and expert users' eye movement data. This differences between expert and novice users were compared and identified based on gaze features. Each participant must do three main tasks of e-learning. This paper gives the result that there are differences between gaze features of experts and novices.

Unbiased feature selection in learning random forests for high-dimensional data.

PubMed

Nguyen, Thanh-Tung; Huang, Joshua Zhexue; Nguyen, Thuy Thi

2015-01-01

Random forests (RFs) have been widely used as a powerful classification method. However, with the randomization in both bagging samples and feature selection, the trees in the forest tend to select uninformative features for node splitting. This makes RFs have poor accuracy when working with high-dimensional data. Besides that, RFs have bias in the feature selection process where multivalued features are favored. Aiming at debiasing feature selection in RFs, we propose a new RF algorithm, called xRF, to select good features in learning RFs for high-dimensional data. We first remove the uninformative features using p-value assessment, and the subset of unbiased features is then selected based on some statistical measures. This feature subset is then partitioned into two subsets. A feature weighting sampling technique is used to sample features from these two subsets for building trees. This approach enables one to generate more accurate trees, while allowing one to reduce dimensionality and the amount of data needed for learning RFs. An extensive set of experiments has been conducted on 47 high-dimensional real-world datasets including image datasets. The experimental results have shown that RFs with the proposed approach outperformed the existing random forests in increasing the accuracy and the AUC measures.

Low-Rank Discriminant Embedding for Multiview Learning.

PubMed

Li, Jingjing; Wu, Yue; Zhao, Jidong; Lu, Ke

2017-11-01

This paper focuses on the specific problem of multiview learning where samples have the same feature set but different probability distributions, e.g., different viewpoints or different modalities. Since samples lying in different distributions cannot be compared directly, this paper aims to learn a latent subspace shared by multiple views assuming that the input views are generated from this latent subspace. Previous approaches usually learn the common subspace by either maximizing the empirical likelihood, or preserving the geometric structure. However, considering the complementarity between the two objectives, this paper proposes a novel approach, named low-rank discriminant embedding (LRDE), for multiview learning by taking full advantage of both sides. By further considering the duality between data points and features of multiview scene, i.e., data points can be grouped based on their distribution on features, while features can be grouped based on their distribution on the data points, LRDE not only deploys low-rank constraints on both sample level and feature level to dig out the shared factors across different views, but also preserves geometric information in both the ambient sample space and the embedding feature space by designing a novel graph structure under the framework of graph embedding. Finally, LRDE jointly optimizes low-rank representation and graph embedding in a unified framework. Comprehensive experiments in both multiview manner and pairwise manner demonstrate that LRDE performs much better than previous approaches proposed in recent literatures.

Multi-level gene/MiRNA feature selection using deep belief nets and active learning.

PubMed

Ibrahim, Rania; Yousri, Noha A; Ismail, Mohamed A; El-Makky, Nagwa M

2014-01-01

Selecting the most discriminative genes/miRNAs has been raised as an important task in bioinformatics to enhance disease classifiers and to mitigate the dimensionality curse problem. Original feature selection methods choose genes/miRNAs based on their individual features regardless of how they perform together. Considering group features instead of individual ones provides a better view for selecting the most informative genes/miRNAs. Recently, deep learning has proven its ability in representing the data in multiple levels of abstraction, allowing for better discrimination between different classes. However, the idea of using deep learning for feature selection is not widely used in the bioinformatics field yet. In this paper, a novel multi-level feature selection approach named MLFS is proposed for selecting genes/miRNAs based on expression profiles. The approach is based on both deep and active learning. Moreover, an extension to use the technique for miRNAs is presented by considering the biological relation between miRNAs and genes. Experimental results show that the approach was able to outperform classical feature selection methods in hepatocellular carcinoma (HCC) by 9%, lung cancer by 6% and breast cancer by around 10% in F1-measure. Results also show the enhancement in F1-measure of our approach over recently related work in [1] and [2].

Salient object detection based on multi-scale contrast.

PubMed

Wang, Hai; Dai, Lei; Cai, Yingfeng; Sun, Xiaoqiang; Chen, Long

2018-05-01

Due to the development of deep learning networks, a salient object detection based on deep learning networks, which are used to extract the features, has made a great breakthrough compared to the traditional methods. At present, the salient object detection mainly relies on very deep convolutional network, which is used to extract the features. In deep learning networks, an dramatic increase of network depth may cause more training errors instead. In this paper, we use the residual network to increase network depth and to mitigate the errors caused by depth increase simultaneously. Inspired by image simplification, we use color and texture features to obtain simplified image with multiple scales by means of region assimilation on the basis of super-pixels in order to reduce the complexity of images and to improve the accuracy of salient target detection. We refine the feature on pixel level by the multi-scale feature correction method to avoid the feature error when the image is simplified at the above-mentioned region level. The final full connection layer not only integrates features of multi-scale and multi-level but also works as classifier of salient targets. The experimental results show that proposed model achieves better results than other salient object detection models based on original deep learning networks. Copyright © 2018 Elsevier Ltd. All rights reserved.

Using input feature information to improve ultraviolet retrieval in neural networks

NASA Astrophysics Data System (ADS)

Sun, Zhibin; Chang, Ni-Bin; Gao, Wei; Chen, Maosi; Zempila, Melina

2017-09-01

In neural networks, the training/predicting accuracy and algorithm efficiency can be improved significantly via accurate input feature extraction. In this study, some spatial features of several important factors in retrieving surface ultraviolet (UV) are extracted. An extreme learning machine (ELM) is used to retrieve the surface UV of 2014 in the continental United States, using the extracted features. The results conclude that more input weights can improve the learning capacities of neural networks.

Quantum-enhanced feature selection with forward selection and backward elimination

NASA Astrophysics Data System (ADS)

He, Zhimin; Li, Lvzhou; Huang, Zhiming; Situ, Haozhen

2018-07-01

Feature selection is a well-known preprocessing technique in machine learning, which can remove irrelevant features to improve the generalization capability of a classifier and reduce training and inference time. However, feature selection is time-consuming, particularly for the applications those have thousands of features, such as image retrieval, text mining and microarray data analysis. It is crucial to accelerate the feature selection process. We propose a quantum version of wrapper-based feature selection, which converts a classical feature selection to its quantum counterpart. It is valuable for machine learning on quantum computer. In this paper, we focus on two popular kinds of feature selection methods, i.e., wrapper-based forward selection and backward elimination. The proposed feature selection algorithm can quadratically accelerate the classical one.

Deep Multimodal Distance Metric Learning Using Click Constraints for Image Ranking.

PubMed

Yu, Jun; Yang, Xiaokang; Gao, Fei; Tao, Dacheng

2017-12-01

How do we retrieve images accurately? Also, how do we rank a group of images precisely and efficiently for specific queries? These problems are critical for researchers and engineers to generate a novel image searching engine. First, it is important to obtain an appropriate description that effectively represent the images. In this paper, multimodal features are considered for describing images. The images unique properties are reflected by visual features, which are correlated to each other. However, semantic gaps always exist between images visual features and semantics. Therefore, we utilize click feature to reduce the semantic gap. The second key issue is learning an appropriate distance metric to combine these multimodal features. This paper develops a novel deep multimodal distance metric learning (Deep-MDML) method. A structured ranking model is adopted to utilize both visual and click features in distance metric learning (DML). Specifically, images and their related ranking results are first collected to form the training set. Multimodal features, including click and visual features, are collected with these images. Next, a group of autoencoders is applied to obtain initially a distance metric in different visual spaces, and an MDML method is used to assign optimal weights for different modalities. Next, we conduct alternating optimization to train the ranking model, which is used for the ranking of new queries with click features. Compared with existing image ranking methods, the proposed method adopts a new ranking model to use multimodal features, including click features and visual features in DML. We operated experiments to analyze the proposed Deep-MDML in two benchmark data sets, and the results validate the effects of the method.

Introducing and Evaluating the Behavior of Non-Verbal Features in the Virtual Learning

ERIC Educational Resources Information Center

Dharmawansa, Asanka D.; Fukumura, Yoshimi; Marasinghe, Ashu; Madhuwanthi, R. A. M.

2015-01-01

The objective of this research is to introduce the behavior of non-verbal features of e-Learners in the virtual learning environment to establish a fair representation of the real user by an avatar who represents the e-Learner in the virtual environment and to distinguish the deportment of the non-verbal features during the virtual learning…

MRM-Lasso: A Sparse Multiview Feature Selection Method via Low-Rank Analysis.

PubMed

Yang, Wanqi; Gao, Yang; Shi, Yinghuan; Cao, Longbing

2015-11-01

Learning about multiview data involves many applications, such as video understanding, image classification, and social media. However, when the data dimension increases dramatically, it is important but very challenging to remove redundant features in multiview feature selection. In this paper, we propose a novel feature selection algorithm, multiview rank minimization-based Lasso (MRM-Lasso), which jointly utilizes Lasso for sparse feature selection and rank minimization for learning relevant patterns across views. Instead of simply integrating multiple Lasso from view level, we focus on the performance of sample-level (sample significance) and introduce pattern-specific weights into MRM-Lasso. The weights are utilized to measure the contribution of each sample to the labels in the current view. In addition, the latent correlation across different views is successfully captured by learning a low-rank matrix consisting of pattern-specific weights. The alternating direction method of multipliers is applied to optimize the proposed MRM-Lasso. Experiments on four real-life data sets show that features selected by MRM-Lasso have better multiview classification performance than the baselines. Moreover, pattern-specific weights are demonstrated to be significant for learning about multiview data, compared with view-specific weights.

Recurrent neural networks with specialized word embeddings for health-domain named-entity recognition.

PubMed

Jauregi Unanue, Iñigo; Zare Borzeshi, Ehsan; Piccardi, Massimo

2017-12-01

Previous state-of-the-art systems on Drug Name Recognition (DNR) and Clinical Concept Extraction (CCE) have focused on a combination of text "feature engineering" and conventional machine learning algorithms such as conditional random fields and support vector machines. However, developing good features is inherently heavily time-consuming. Conversely, more modern machine learning approaches such as recurrent neural networks (RNNs) have proved capable of automatically learning effective features from either random assignments or automated word "embeddings". (i) To create a highly accurate DNR and CCE system that avoids conventional, time-consuming feature engineering. (ii) To create richer, more specialized word embeddings by using health domain datasets such as MIMIC-III. (iii) To evaluate our systems over three contemporary datasets. Two deep learning methods, namely the Bidirectional LSTM and the Bidirectional LSTM-CRF, are evaluated. A CRF model is set as the baseline to compare the deep learning systems to a traditional machine learning approach. The same features are used for all the models. We have obtained the best results with the Bidirectional LSTM-CRF model, which has outperformed all previously proposed systems. The specialized embeddings have helped to cover unusual words in DrugBank and MedLine, but not in the i2b2/VA dataset. We present a state-of-the-art system for DNR and CCE. Automated word embeddings has allowed us to avoid costly feature engineering and achieve higher accuracy. Nevertheless, the embeddings need to be retrained over datasets that are adequate for the domain, in order to adequately cover the domain-specific vocabulary. Copyright © 2017 Elsevier Inc. All rights reserved.

Getting to the Root of the Problem in Experiential Learning: Using Problem Solving and Collective Reflection to Improve Learning Outcomes

ERIC Educational Resources Information Center

Miller, Richard J.; Maellaro, Rosemary

2016-01-01

Experiential learning alone does not guarantee that students will accurately conceptualize content, or meet course outcomes in subsequent active experimentation stages. In an effort to more effectively meet learning objectives, the experiential learning cycle was modified with a unique combination of the 5 Whys root cause problem-solving tool and…

Professional Development across the Teaching Career: Teachers' Uptake of Formal and Informal Learning Opportunities

ERIC Educational Resources Information Center

Richter, Dirk; Kunter, Mareike; Klusmann, Uta; Ludtke, Oliver; Baumert, Jurgen

2011-01-01

This study examined teachers' uptake of formal and informal learning opportunities across the career cycle. Analyses were based on data from 1939 German secondary teachers in 198 schools. Results showed that formal learning opportunities (in-service training) were used most frequently by mid-career teachers, whereas informal learning opportunities…

Process-Oriented Guided Inquiry Learning: POGIL and the POGIL Project

ERIC Educational Resources Information Center

Moog, Richard S.; Creegan, Frank J.; Hanson, David M.; Spencer, James N.; Straumanis, Andrei R.

2006-01-01

Recent research indicates that students learn best when they are actively engaged and they construct their own understanding. Process-Oriented Guided Inquiry Learning (POGIL) is a student-centered instructional philosophy based on these concepts in which students work in teams on specially prepared activities that follow a learning cycle paradigm.…

Kinesiology and Learning: Implications for Turkish School Curriculum

ERIC Educational Resources Information Center

Ozar, Mirac

2013-01-01

Learning is a complex phenomenon and multi-faceted in nature. There are a number of parameters which influence learning cycle and the process in general. Physical exercise is thought to be one of the variants that affect the learning phenomenon. Accumulated scientific evidence can be found in the literature showing high correlations between…

Implementation of Process Oriented Guided Inquiry Learning (POGIL) in Engineering

ERIC Educational Resources Information Center

Douglas, Elliot P.; Chiu, Chu-Chuan

2013-01-01

This paper describes implementation and testing of an active learning, team-based pedagogical approach to instruction in engineering. This pedagogy has been termed Process Oriented Guided Inquiry Learning (POGIL), and is based upon the learning cycle model. Rather than sitting in traditional lectures, students work in teams to complete worksheets…

Collaborative Learning: Group Interaction in an Intelligent Mobile-Assisted Multiple Language Learning System

ERIC Educational Resources Information Center

Troussas, Christos; Virvou, Maria; Alepis, Efthimios

2014-01-01

This paper proposes a student-oriented approach tailored to effective collaboration between students using mobile phones for language learning within the life cycle of an intelligent tutoring system. For this reason, in this research, a prototype mobile application has been developed for multiple language learning that incorporates intelligence in…

Professional Learning Drives Common Core and Educator Evaluation, Knowledge Brief

ERIC Educational Resources Information Center

Killion, Joellen; Hirsh, Stephanie

2014-01-01

The ultimate key to successful integration and implementation of college- and career-ready standards and educator evaluation systems is the quality of the professional learning that educators engage in every day. Effective professional learning at the school level occurs among a team of teachers learning in a cycle of continuous improvement.…

Expansive Learning in a Library: Actions, Cycles and Deviations from Instructional Intentions

ERIC Educational Resources Information Center

Engestrom, Yrjo; Rantavuori, Juhana; Kerosuo, Hannele

2013-01-01

The theory of expansive learning has been applied in a large number of studies on workplace learning and organizational change. However, detailed comprehensive analyses of entire developmental interventions based on the theory of expansive learning do not exist. Such a study is needed to examine the empirical usability and methodological rigor…

Nimble Navigation: A Constant Cycle Assessment Keeps Learning on Course

ERIC Educational Resources Information Center

James, Wendy; Johanson, Terry

2016-01-01

Just like in a classroom, a professional learning facilitator needs to base planning and instruction on assessment. Adult learners need the learning experience to be as focused as possible on their questions and their teaching circumstances. Whether the professional learning is a half-day session or extends over multiple school years, leaders can…

Deep greedy learning under thermal variability in full diurnal cycles

NASA Astrophysics Data System (ADS)

Rauss, Patrick; Rosario, Dalton

2017-08-01

We study the generalization and scalability behavior of a deep belief network (DBN) applied to a challenging long-wave infrared hyperspectral dataset, consisting of radiance from several manmade and natural materials within a fixed site located 500 m from an observation tower. The collections cover multiple full diurnal cycles and include different atmospheric conditions. Using complementary priors, a DBN uses a greedy algorithm that can learn deep, directed belief networks one layer at a time and has two layers form to provide undirected associative memory. The greedy algorithm initializes a slower learning procedure, which fine-tunes the weights, using a contrastive version of the wake-sleep algorithm. After fine-tuning, a network with three hidden layers forms a very good generative model of the joint distribution of spectral data and their labels, despite significant data variability between and within classes due to environmental and temperature variation occurring within and between full diurnal cycles. We argue, however, that more questions than answers are raised regarding the generalization capacity of these deep nets through experiments aimed at investigating their training and augmented learning behavior.

Robust Radar Emitter Recognition Based on the Three-Dimensional Distribution Feature and Transfer Learning

PubMed Central

Yang, Zhutian; Qiu, Wei; Sun, Hongjian; Nallanathan, Arumugam

2016-01-01

Due to the increasing complexity of electromagnetic signals, there exists a significant challenge for radar emitter signal recognition. To address this challenge, multi-component radar emitter recognition under a complicated noise environment is studied in this paper. A novel radar emitter recognition approach based on the three-dimensional distribution feature and transfer learning is proposed. The cubic feature for the time-frequency-energy distribution is proposed to describe the intra-pulse modulation information of radar emitters. Furthermore, the feature is reconstructed by using transfer learning in order to obtain the robust feature against signal noise rate (SNR) variation. Last, but not the least, the relevance vector machine is used to classify radar emitter signals. Simulations demonstrate that the approach proposed in this paper has better performances in accuracy and robustness than existing approaches. PMID:26927111

Robust Radar Emitter Recognition Based on the Three-Dimensional Distribution Feature and Transfer Learning.

PubMed

Yang, Zhutian; Qiu, Wei; Sun, Hongjian; Nallanathan, Arumugam

2016-02-25

Due to the increasing complexity of electromagnetic signals, there exists a significant challenge for radar emitter signal recognition. To address this challenge, multi-component radar emitter recognition under a complicated noise environment is studied in this paper. A novel radar emitter recognition approach based on the three-dimensional distribution feature and transfer learning is proposed. The cubic feature for the time-frequency-energy distribution is proposed to describe the intra-pulse modulation information of radar emitters. Furthermore, the feature is reconstructed by using transfer learning in order to obtain the robust feature against signal noise rate (SNR) variation. Last, but not the least, the relevance vector machine is used to classify radar emitter signals. Simulations demonstrate that the approach proposed in this paper has better performances in accuracy and robustness than existing approaches.

The effects of aging on the interaction between reinforcement learning and attention.

PubMed

Radulescu, Angela; Daniel, Reka; Niv, Yael

2016-11-01

Reinforcement learning (RL) in complex environments relies on selective attention to uncover those aspects of the environment that are most predictive of reward. Whereas previous work has focused on age-related changes in RL, it is not known whether older adults learn differently from younger adults when selective attention is required. In 2 experiments, we examined how aging affects the interaction between RL and selective attention. Younger and older adults performed a learning task in which only 1 stimulus dimension was relevant to predicting reward, and within it, 1 "target" feature was the most rewarding. Participants had to discover this target feature through trial and error. In Experiment 1, stimuli varied on 1 or 3 dimensions and participants received hints that revealed the target feature, the relevant dimension, or gave no information. Group-related differences in accuracy and RTs differed systematically as a function of the number of dimensions and the type of hint available. In Experiment 2 we used trial-by-trial computational modeling of the learning process to test for age-related differences in learning strategies. Behavior of both young and older adults was explained well by a reinforcement-learning model that uses selective attention to constrain learning. However, the model suggested that older adults restricted their learning to fewer features, employing more focused attention than younger adults. Furthermore, this difference in strategy predicted age-related deficits in accuracy. We discuss these results suggesting that a narrower filter of attention may reflect an adaptation to the reduced capabilities of the reinforcement learning system. (PsycINFO Database Record (c) 2016 APA, all rights reserved).

Understanding Digital Learning and Its Variable Effects

NASA Astrophysics Data System (ADS)

Means, B.

2016-12-01

An increasing proportion of undergraduate courses use an online or blended learning format. This trend signals major changes in the kind of instruction students receive in their STEM courses, yet evidence about the effectiveness of these new approaches is sparse. Existing syntheses and meta-analyses summarize outcomes from experimental or quasi-experimental studies of online and blended courses and document how few studies incorporate proper controls for differences in student characteristics, instructor behaviors, and other course conditions. The evidence that is available suggests that on average blended courses are equal to or better than traditional face-to-face courses and that online courses are equivalent in terms of learning outcomes. But these averages conceal a tremendous underlying variability. Results vary markedly from course to course, even when the same technology is used in both. Some research suggests that online instruction puts lower-achieving students at a disadvantage. It is clear that introducing digital learning per se is no guarantee that student engagement and learning will be enhanced. Getting more consistently positive impacts out of learning technologies is going to require systematic characterization of the features of learning technologies and associated instructional practices as well as attention to context and student characteristics. This presentation will present a framework for characterizing essential features of digital learning resources, implementation practices, and conditions. It will also summarize the research evidence with respect to the learning impacts of specific technology features including spaced practice, immediate feedback, mastery learning based pacing, visualizations and simulations, gaming features, prompts for explanations and reflection, and tools for online collaboration.

Self-directed questions to improve students' ability in solving chemical problems

NASA Astrophysics Data System (ADS)

Sanjaya, Rahmat Eko; Muna, Khairiatul; Suharto, Bambang; Syahmani

2017-12-01

Students' ability in solving chemical problems is seen from their ability to solve chemicals' non-routine problems. It is due to learning faced directly on non-routine problems will generate a meaningful learning for students. Observations in Banjarmasin Public High School 1 (SMA Negeri 1 Banjarmasin) showed that students did not give the expected results when they were given the non-routine problems. Learning activities by emphasizing problem solving was implemented based on the existence of knowledge about cognition and regulation of cognition. Both of these elements are components of metacognition. The self-directed question is a strategy that involves metacognition in solving chemical problems. This research was carried out using classroom action research design in two cycles. Each cycle consists of four stages: planning, action, observation and reflection. The subjects were 34 students of grade XI-4 at majoring science (IPA) of SMA Negeri 1 Banjarmasin. The data were collected using tests of the students' ability in problem solving and non-tests instrument to know the process of implementation of the actions. Data were analyzed with descriptivequantitativeand qualitative analysis. The ability of students in solving chemical problems has increased from an average of 37.96 in cycle I became 61.83 in cycle II. Students' ability to solve chemical problems is viewed based on their ability to answer self-directed questions. Students' ability in comprehension questions increased from 73.04 in the cycle I became 96.32 in cycle II. Connection and strategic questions increased from 54.17 and 16.50 on cycle I became 63.73 and 55.23 on cycle II respectively. In cycle I, reflection questions were 26.96 and elevated into 36.27 in cycle II. The self-directed questions have the ability to help students to solve chemical problems through metacognition questions. Those questions guide students to find solutions in solving chemical problems.

Simulating Thermal Cycling and Isothermal Deformation Response of Polycrystalline NiTi

NASA Technical Reports Server (NTRS)

Manchiraju, Sivom; Gaydosh, Darrell J.; Noebe, Ronald D.; Anderson, Peter M.

2011-01-01

A microstructure-based FEM model that couples crystal plasticity, crystallographic descriptions of the B2-B19' martensitic phase transformation, and anisotropic elasticity is used to simulate thermal cycling and isothermal deformation in polycrystalline NiTi (49.9at% Ni). The model inputs include anisotropic elastic properties, polycrystalline texture, DSC data, and a subset of isothermal deformation and load-biased thermal cycling data. A key experimental trend is captured.namely, the transformation strain during thermal cycling is predicted to reach a peak with increasing bias stress, due to the onset of plasticity at larger bias stress. Plasticity induces internal stress that affects both thermal cycling and isothermal deformation responses. Affected thermal cycling features include hysteretic width, two-way shape memory effect, and evolution of texture with increasing bias stress. Affected isothermal deformation features include increased hardening during loading and retained martensite after unloading. These trends are not captured by microstructural models that lack plasticity, nor are they all captured in a robust manner by phenomenological approaches. Despite this advance in microstructural modeling, quantitative differences exist, such as underprediction of open loop strain during thermal cycling.

Dark-field microscopic image stitching method for surface defects evaluation of large fine optics.

PubMed

Liu, Dong; Wang, Shitong; Cao, Pin; Li, Lu; Cheng, Zhongtao; Gao, Xin; Yang, Yongying

2013-03-11

One of the challenges in surface defects evaluation of large fine optics is to detect defects of microns on surfaces of tens or hundreds of millimeters. Sub-aperture scanning and stitching is considered to be a practical and efficient method. But since there are usually few defects on the large aperture fine optics, resulting in no defects or only one run-through line feature in many sub-aperture images, traditional stitching methods encounter with mismatch problem. In this paper, a feature-based multi-cycle image stitching algorithm is proposed to solve the problem. The overlapping areas of sub-apertures are categorized based on the features they contain. Different types of overlapping areas are then stitched in different cycles with different methods. The stitching trace is changed to follow the one that determined by the features. The whole stitching procedure is a region-growing like process. Sub-aperture blocks grow bigger after each cycle and finally the full aperture image is obtained. Comparison experiment shows that the proposed method is very suitable to stitch sub-apertures that very few feature information exists in the overlapping areas and can stitch the dark-field microscopic sub-aperture images very well.

Spatial features of synaptic adaptation affecting learning performance.

PubMed

Berger, Damian L; de Arcangelis, Lucilla; Herrmann, Hans J

2017-09-08

Recent studies have proposed that the diffusion of messenger molecules, such as monoamines, can mediate the plastic adaptation of synapses in supervised learning of neural networks. Based on these findings we developed a model for neural learning, where the signal for plastic adaptation is assumed to propagate through the extracellular space. We investigate the conditions allowing learning of Boolean rules in a neural network. Even fully excitatory networks show very good learning performances. Moreover, the investigation of the plastic adaptation features optimizing the performance suggests that learning is very sensitive to the extent of the plastic adaptation and the spatial range of synaptic connections.

Generalized query-based active learning to identify differentially methylated regions in DNA.

PubMed

Haque, Md Muksitul; Holder, Lawrence B; Skinner, Michael K; Cook, Diane J

2013-01-01

Active learning is a supervised learning technique that reduces the number of examples required for building a successful classifier, because it can choose the data it learns from. This technique holds promise for many biological domains in which classified examples are expensive and time-consuming to obtain. Most traditional active learning methods ask very specific queries to the Oracle (e.g., a human expert) to label an unlabeled example. The example may consist of numerous features, many of which are irrelevant. Removing such features will create a shorter query with only relevant features, and it will be easier for the Oracle to answer. We propose a generalized query-based active learning (GQAL) approach that constructs generalized queries based on multiple instances. By constructing appropriately generalized queries, we can achieve higher accuracy compared to traditional active learning methods. We apply our active learning method to find differentially DNA methylated regions (DMRs). DMRs are DNA locations in the genome that are known to be involved in tissue differentiation, epigenetic regulation, and disease. We also apply our method on 13 other data sets and show that our method is better than another popular active learning technique.

Use of Machine Learning Classifiers and Sensor Data to Detect Neurological Deficit in Stroke Patients.

PubMed

Park, Eunjeong; Chang, Hyuk-Jae; Nam, Hyo Suk

2017-04-18

The pronator drift test (PDT), a neurological examination, is widely used in clinics to measure motor weakness of stroke patients. The aim of this study was to develop a PDT tool with machine learning classifiers to detect stroke symptoms based on quantification of proximal arm weakness using inertial sensors and signal processing. We extracted features of drift and pronation from accelerometer signals of wearable devices on the inner wrists of 16 stroke patients and 10 healthy controls. Signal processing and feature selection approach were applied to discriminate PDT features used to classify stroke patients. A series of machine learning techniques, namely support vector machine (SVM), radial basis function network (RBFN), and random forest (RF), were implemented to discriminate stroke patients from controls with leave-one-out cross-validation. Signal processing by the PDT tool extracted a total of 12 PDT features from sensors. Feature selection abstracted the major attributes from the 12 PDT features to elucidate the dominant characteristics of proximal weakness of stroke patients using machine learning classification. Our proposed PDT classifiers had an area under the receiver operating characteristic curve (AUC) of .806 (SVM), .769 (RBFN), and .900 (RF) without feature selection, and feature selection improves the AUCs to .913 (SVM), .956 (RBFN), and .975 (RF), representing an average performance enhancement of 15.3%. Sensors and machine learning methods can reliably detect stroke signs and quantify proximal arm weakness. Our proposed solution will facilitate pervasive monitoring of stroke patients. ©Eunjeong Park, Hyuk-Jae Chang, Hyo Suk Nam. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 18.04.2017.

Machine learning-based quantitative texture analysis of CT images of small renal masses: Differentiation of angiomyolipoma without visible fat from renal cell carcinoma.

PubMed

Feng, Zhichao; Rong, Pengfei; Cao, Peng; Zhou, Qingyu; Zhu, Wenwei; Yan, Zhimin; Liu, Qianyun; Wang, Wei

2018-04-01

To evaluate the diagnostic performance of machine-learning based quantitative texture analysis of CT images to differentiate small (≤ 4 cm) angiomyolipoma without visible fat (AMLwvf) from renal cell carcinoma (RCC). This single-institutional retrospective study included 58 patients with pathologically proven small renal mass (17 in AMLwvf and 41 in RCC groups). Texture features were extracted from the largest possible tumorous regions of interest (ROIs) by manual segmentation in preoperative three-phase CT images. Interobserver reliability and the Mann-Whitney U test were applied to select features preliminarily. Then support vector machine with recursive feature elimination (SVM-RFE) and synthetic minority oversampling technique (SMOTE) were adopted to establish discriminative classifiers, and the performance of classifiers was assessed. Of the 42 extracted features, 16 candidate features showed significant intergroup differences (P < 0.05) and had good interobserver agreement. An optimal feature subset including 11 features was further selected by the SVM-RFE method. The SVM-RFE+SMOTE classifier achieved the best performance in discriminating between small AMLwvf and RCC, with the highest accuracy, sensitivity, specificity and AUC of 93.9 %, 87.8 %, 100 % and 0.955, respectively. Machine learning analysis of CT texture features can facilitate the accurate differentiation of small AMLwvf from RCC. • Although conventional CT is useful for diagnosis of SRMs, it has limitations. • Machine-learning based CT texture analysis facilitate differentiation of small AMLwvf from RCC. • The highest accuracy of SVM-RFE+SMOTE classifier reached 93.9 %. • Texture analysis combined with machine-learning methods might spare unnecessary surgery for AMLwvf.

Hyper-homeostatic learning of anticipatory hunger in rats.

PubMed

Jarvandi, Soghra; Booth, David A; Thibault, Louise

2007-11-23

Anticipatory hunger is a learnt increase in intake of food having a flavour or texture that predicts a long fast. This learning was studied in rats trained on a single food or a choice between protein-rich and carbohydrate-rich foods, presented for 1.5 h after 3 h without maintenance food at the start of the dark phase. Eight training cycles provided a pseudo-random sequence of 3 h and 10 h post-prandial fasts with a day on maintenance food between each training fast. The measure of anticipatory hunger is the difference over one 4-day cycle between the intake of test food having an odour predictive of the longer fast (TL) and intake of food with an odour cuing to the shorter fast (TS). Previous experiments showed that conditioning of preference for the odour before the shorter fast competes with learning to avoid hunger during the longer fast (anticipatory hunger), generating a cubic or quartic contrast. TL minus TS showed a strong cubic trend over 8 training cycles with both single and choice meals. There was a switch from preference for the short-fast odour at cycle 2 (TL-TS=-0.86 g) to a peak of anticipatory hunger at cycle 6 (TL-TS=1.57 g). We conclude that anticipatory hunger is learnt when a choice is given between protein-rich and carbohydrate-rich foods as well as on a single food. In addition, since anticipatory hunger extinguishes itself, such learning improves on negative-feedback homeostasis with a feed-forward "hyper-homeostatic" mechanism.

Person Authentication Using Learned Parameters of Lifting Wavelet Filters

NASA Astrophysics Data System (ADS)

Niijima, Koichi

2006-10-01

This paper proposes a method for identifying persons by the use of the lifting wavelet parameters learned by kurtosis-minimization. Our learning method uses desirable properties of kurtosis and wavelet coefficients of a facial image. Exploiting these properties, the lifting parameters are trained so as to minimize the kurtosis of lifting wavelet coefficients computed for the facial image. Since this minimization problem is an ill-posed problem, it is solved by the aid of Tikhonov's regularization method. Our learning algorithm is applied to each of the faces to be identified to generate its feature vector whose components consist of the learned parameters. The constructed feature vectors are memorized together with the corresponding faces in a feature vectors database. Person authentication is performed by comparing the feature vector of a query face with those stored in the database. In numerical experiments, the lifting parameters are trained for each of the neutral faces of 132 persons (74 males and 58 females) in the AR face database. Person authentication is executed by using the smile and anger faces of the same persons in the database.

PBL, Hands-On/ Digital resources in Geology, (Teaching/ Learning)

NASA Astrophysics Data System (ADS)

Soares, Rosa; Santos, Cátia; Carvalho, Sara

2015-04-01

The present study reports the elaboration, application and evaluation of a problem-based learning (PBL) program that aims to evaluate the effectiveness in students learning the Rock Cycle theme. Prior research on both PBL and Rock Cycle was conducted within the context of science education so as to elaborate and construct the intervention program. Findings from these studies indicated both the PBL methodology and Rock Cycle as helpful for teachers and students. PBL methodology has been adopted in this study since it is logically incorporated in a constructivism philosophy application and it was expected that this approach would assist students towards achieving a specific set of competencies. PBL is a student-centered method based on the principle of using problems as the starting point for the acquisition of new knowledge. Problems are based on complex real-world situations. All information needed to solve the problem is initially not given. Students will identify, find, and use appropriate resources to complete the exercise. They work permanently in small groups, developing self-directed activities and increasing participation in discussions. Teacher based guidance allows students to be fully engaged in knowledge building. That way, the learning process is active, integrated, cumulative, and connected. Theme "Rock Cycle" was introduced using a problematic situation, which outlined the geological processes highlighted in "Foz do Douro" the next coastline of the school where the study was developed. The questions proposed by the students were solved, using strategies that involved the use of hands-on activities and virtual labs in Geology. The systematization of the selected theme was performed in a field excursion, implemented according to the organizational model of Nir Orion, to The "Foz do Douro" metamorphic complex. In the evaluation of the learning process, data were obtained on students' development of knowledge and competencies through the application of several instruments such as small questionnaires (Hot Potatoes), Gowin V, scientific report, a grid to evaluate group work and a grid to evaluate the development of competencies. This study intended to evaluate the success of a PBL intervention program when trying to improve students' outcomes. The positive impact obtained allowed us to advance some conclusions and instructional implications regarding teaching Rock Cycle through PBL and different digital and hands-on resources, obtained, especially in the students' questionnaires and Gowin V, allowed us to verify that students did learn about Rock Cycle and developed collaborative work skills.

CYCLING OF DISSOLVED ELEMENTAL MERCURY IN ARCTIC ALASKAN LAKES. (R829796)

EPA Science Inventory

Aqueous production and water-air exchange of elemental mercury (Hg⁰) are important features of the environmental cycling of Hg. We investigated Hg⁰ cycling in ten Arctic Alaskan lakes that spanned a wide range in physicochemical characteristics. Dissolved...

Accurate Identification of Cancerlectins through Hybrid Machine Learning Technology.

PubMed

Zhang, Jieru; Ju, Ying; Lu, Huijuan; Xuan, Ping; Zou, Quan

2016-01-01

Cancerlectins are cancer-related proteins that function as lectins. They have been identified through computational identification techniques, but these techniques have sometimes failed to identify proteins because of sequence diversity among the cancerlectins. Advanced machine learning identification methods, such as support vector machine and basic sequence features (n-gram), have also been used to identify cancerlectins. In this study, various protein fingerprint features and advanced classifiers, including ensemble learning techniques, were utilized to identify this group of proteins. We improved the prediction accuracy of the original feature extraction methods and classification algorithms by more than 10% on average. Our work provides a basis for the computational identification of cancerlectins and reveals the power of hybrid machine learning techniques in computational proteomics.

Why Barack Obama is black: a cognitive account of hypodescent.

PubMed

Halberstadt, Jamin; Sherman, Steven J; Sherman, Jeffrey W

2011-01-01

We propose that hypodescent-the assignment of mixed-race individuals to a minority group-is an emergent feature of basic cognitive processes of learning and categorization. According to attention theory, minority groups are learned by attending to the features that distinguish them from previously learned majority groups. Selective attention creates a strong association between minority groups and their distinctive features, producing a tendency to see individuals who possess a mixture of majority- and minority-group traits as minority-group members. Two experiments on face categorization, using both naturally occurring and manipulated minority groups, support this view, suggesting that hypodescent need not be the product of racist or political motivations, but can be sufficiently explained by an individual's learning history.

Theta Coordinated Error-Driven Learning in the Hippocampus

PubMed Central

Ketz, Nicholas; Morkonda, Srinimisha G.; O'Reilly, Randall C.

2013-01-01

The learning mechanism in the hippocampus has almost universally been assumed to be Hebbian in nature, where individual neurons in an engram join together with synaptic weight increases to support facilitated recall of memories later. However, it is also widely known that Hebbian learning mechanisms impose significant capacity constraints, and are generally less computationally powerful than learning mechanisms that take advantage of error signals. We show that the differential phase relationships of hippocampal subfields within the overall theta rhythm enable a powerful form of error-driven learning, which results in significantly greater capacity, as shown in computer simulations. In one phase of the theta cycle, the bidirectional connectivity between CA1 and entorhinal cortex can be trained in an error-driven fashion to learn to effectively encode the cortical inputs in a compact and sparse form over CA1. In a subsequent portion of the theta cycle, the system attempts to recall an existing memory, via the pathway from entorhinal cortex to CA3 and CA1. Finally the full theta cycle completes when a strong target encoding representation of the current input is imposed onto the CA1 via direct projections from entorhinal cortex. The difference between this target encoding and the attempted recall of the same representation on CA1 constitutes an error signal that can drive the learning of CA3 to CA1 synapses. This CA3 to CA1 pathway is critical for enabling full reinstatement of recalled hippocampal memories out in cortex. Taken together, these new learning dynamics enable a much more robust, high-capacity model of hippocampal learning than was available previously under the classical Hebbian model. PMID:23762019

Decoding Dyslexia, a Common Learning Disability | NIH MedlinePlus the Magazine

MedlinePlus

... JavaScript on. Feature: Dyslexia Decoding Dyslexia, a Common Learning Disability Past Issues / Winter 2016 Table of Contents What Are Learning Disabilities? Learning disabilities affect how someone learns to read, ...

Discrimination of artificial categories structured by family resemblances: a comparative study in people (Homo sapiens) and pigeons (Columba livia).

PubMed

Makino, Hiroshi; Jitsumori, Masako

2007-02-01

Adult humans (Homo sapiens) and pigeons (Columba livia) were trained to discriminate artificial categories that the authors created by mimicking 2 properties of natural categories. One was a family resemblance relationship: The highly variable exemplars, including those that did not have features in common, were structured by a similarity network with the features correlating to one another in each category. The other was a polymorphous rule: No single feature was essential for distinguishing the categories, and all the features overlapped between the categories. Pigeons learned the categories with ease and then showed a prototype effect in accord with the degrees of family resemblance for novel stimuli. Some evidence was also observed for interactive effects of learning of individual exemplars and feature frequencies. Humans had difficulty in learning the categories. The participants who learned the categories generally responded to novel stimuli in an all-or-none fashion on the basis of their acquired classification decision rules. The processes that underlie the classification performances of the 2 species are discussed.

Sparse feature learning for instrument identification: Effects of sampling and pooling methods.

PubMed

Han, Yoonchang; Lee, Subin; Nam, Juhan; Lee, Kyogu

2016-05-01

Feature learning for music applications has recently received considerable attention from many researchers. This paper reports on the sparse feature learning algorithm for musical instrument identification, and in particular, focuses on the effects of the frame sampling techniques for dictionary learning and the pooling methods for feature aggregation. To this end, two frame sampling techniques are examined that are fixed and proportional random sampling. Furthermore, the effect of using onset frame was analyzed for both of proposed sampling methods. Regarding summarization of the feature activation, a standard deviation pooling method is used and compared with the commonly used max- and average-pooling techniques. Using more than 47 000 recordings of 24 instruments from various performers, playing styles, and dynamics, a number of tuning parameters are experimented including the analysis frame size, the dictionary size, and the type of frequency scaling as well as the different sampling and pooling methods. The results show that the combination of proportional sampling and standard deviation pooling achieve the best overall performance of 95.62% while the optimal parameter set varies among the instrument classes.

On the Design of an Efficient Cardiac Health Monitoring System Through Combined Analysis of ECG and SCG Signals.

PubMed

Sahoo, Prasan Kumar; Thakkar, Hiren Kumar; Lin, Wen-Yen; Chang, Po-Cheng; Lee, Ming-Yih

2018-01-28

Cardiovascular disease (CVD) is a major public concern and socioeconomic problem across the globe. The popular high-end cardiac health monitoring systems such as magnetic resonance imaging (MRI), computerized tomography scan (CT scan), and echocardiography (Echo) are highly expensive and do not support long-term continuous monitoring of patients without disrupting their activities of daily living (ADL). In this paper, the continuous and non-invasive cardiac health monitoring using unobtrusive sensors is explored aiming to provide a feasible and low-cost alternative to foresee possible cardiac anomalies in an early stage. It is learned that cardiac health monitoring based on sole usage of electrocardiogram (ECG) signals may not provide powerful insights as ECG provides shallow information on various cardiac activities in the form of electrical impulses only. Hence, a novel low-cost, non-invasive seismocardiogram (SCG) signal along with ECG signals are jointly investigated for the robust cardiac health monitoring. For this purpose, the in-laboratory data collection model is designed for simultaneous acquisition of ECG and SCG signals followed by mechanisms for the automatic delineation of relevant feature points in acquired ECG and SCG signals. In addition, separate feature points based novel approach is adopted to distinguish between normal and abnormal morphology in each ECG and SCG cardiac cycle. Finally, a combined analysis of ECG and SCG is carried out by designing a Naïve Bayes conditional probability model. Experiments on Institutional Review Board (IRB) approved licensed ECG/SCG signals acquired from real subjects containing 12,000 cardiac cycles show that the proposed feature point delineation mechanisms and abnormal morphology detection methods consistently perform well and give promising results. In addition, experimental results show that the combined analysis of ECG and SCG signals provide more reliable cardiac health monitoring compared to the standalone use of ECG and SCG.

On the Design of an Efficient Cardiac Health Monitoring System Through Combined Analysis of ECG and SCG Signals

PubMed Central

Lin, Wen-Yen; Chang, Po-Cheng

2018-01-01

Cardiovascular disease (CVD) is a major public concern and socioeconomic problem across the globe. The popular high-end cardiac health monitoring systems such as magnetic resonance imaging (MRI), computerized tomography scan (CT scan), and echocardiography (Echo) are highly expensive and do not support long-term continuous monitoring of patients without disrupting their activities of daily living (ADL). In this paper, the continuous and non-invasive cardiac health monitoring using unobtrusive sensors is explored aiming to provide a feasible and low-cost alternative to foresee possible cardiac anomalies in an early stage. It is learned that cardiac health monitoring based on sole usage of electrocardiogram (ECG) signals may not provide powerful insights as ECG provides shallow information on various cardiac activities in the form of electrical impulses only. Hence, a novel low-cost, non-invasive seismocardiogram (SCG) signal along with ECG signals are jointly investigated for the robust cardiac health monitoring. For this purpose, the in-laboratory data collection model is designed for simultaneous acquisition of ECG and SCG signals followed by mechanisms for the automatic delineation of relevant feature points in acquired ECG and SCG signals. In addition, separate feature points based novel approach is adopted to distinguish between normal and abnormal morphology in each ECG and SCG cardiac cycle. Finally, a combined analysis of ECG and SCG is carried out by designing a Naïve Bayes conditional probability model. Experiments on Institutional Review Board (IRB) approved licensed ECG/SCG signals acquired from real subjects containing 12,000 cardiac cycles show that the proposed feature point delineation mechanisms and abnormal morphology detection methods consistently perform well and give promising results. In addition, experimental results show that the combined analysis of ECG and SCG signals provide more reliable cardiac health monitoring compared to the standalone use of ECG and SCG. PMID:29382098

Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from 18F-FDG PET/CT images.

PubMed

Wang, Hongkai; Zhou, Zongwei; Li, Yingci; Chen, Zhonghua; Lu, Peiou; Wang, Wenzhi; Liu, Wanyu; Yu, Lijuan

2017-12-01

This study aimed to compare one state-of-the-art deep learning method and four classical machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer (NSCLC) from 18 F-FDG PET/CT images. Another objective was to compare the discriminative power of the recently popular PET/CT texture features with the widely used diagnostic features such as tumor size, CT value, SUV, image contrast, and intensity standard deviation. The four classical machine learning methods included random forests, support vector machines, adaptive boosting, and artificial neural network. The deep learning method was the convolutional neural networks (CNN). The five methods were evaluated using 1397 lymph nodes collected from PET/CT images of 168 patients, with corresponding pathology analysis results as gold standard. The comparison was conducted using 10 times 10-fold cross-validation based on the criterion of sensitivity, specificity, accuracy (ACC), and area under the ROC curve (AUC). For each classical method, different input features were compared to select the optimal feature set. Based on the optimal feature set, the classical methods were compared with CNN, as well as with human doctors from our institute. For the classical methods, the diagnostic features resulted in 81~85% ACC and 0.87~0.92 AUC, which were significantly higher than the results of texture features. CNN's sensitivity, specificity, ACC, and AUC were 84, 88, 86, and 0.91, respectively. There was no significant difference between the results of CNN and the best classical method. The sensitivity, specificity, and ACC of human doctors were 73, 90, and 82, respectively. All the five machine learning methods had higher sensitivities but lower specificities than human doctors. The present study shows that the performance of CNN is not significantly different from the best classical methods and human doctors for classifying mediastinal lymph node metastasis of NSCLC from PET/CT images. Because CNN does not need tumor segmentation or feature calculation, it is more convenient and more objective than the classical methods. However, CNN does not make use of the import diagnostic features, which have been proved more discriminative than the texture features for classifying small-sized lymph nodes. Therefore, incorporating the diagnostic features into CNN is a promising direction for future research.

Perceptual learning in visual search: fast, enduring, but non-specific.

PubMed

Sireteanu, R; Rettenbach, R

1995-07-01

Visual search has been suggested as a tool for isolating visual primitives. Elementary "features" were proposed to involve parallel search, while serial search is necessary for items without a "feature" status, or, in some cases, for conjunctions of "features". In this study, we investigated the role of practice in visual search tasks. We found that, under some circumstances, initially serial tasks can become parallel after a few hundred trials. Learning in visual search is far less specific than learning of visual discriminations and hyperacuity, suggesting that it takes place at another level in the central visual pathway, involving different neural circuits.

Learning Efficient Spatial-Temporal Gait Features with Deep Learning for Human Identification.

PubMed

Liu, Wu; Zhang, Cheng; Ma, Huadong; Li, Shuangqun

2018-02-06

The integration of the latest breakthroughs in bioinformatics technology from one side and artificial intelligence from another side, enables remarkable advances in the fields of intelligent security guard computational biology, healthcare, and so on. Among them, biometrics based automatic human identification is one of the most fundamental and significant research topic. Human gait, which is a biometric features with the unique capability, has gained significant attentions as the remarkable characteristics of remote accessed, robust and security in the biometrics based human identification. However, the existed methods cannot well handle the indistinctive inter-class differences and large intra-class variations of human gait in real-world situation. In this paper, we have developed an efficient spatial-temporal gait features with deep learning for human identification. First of all, we proposed a gait energy image (GEI) based Siamese neural network to automatically extract robust and discriminative spatial gait features for human identification. Furthermore, we exploit the deep 3-dimensional convolutional networks to learn the human gait convolutional 3D (C3D) as the temporal gait features. Finally, the GEI and C3D gait features are embedded into the null space by the Null Foley-Sammon Transform (NFST). In the new space, the spatial-temporal features are sufficiently combined with distance metric learning to drive the similarity metric to be small for pairs of gait from the same person, and large for pairs from different persons. Consequently, the experiments on the world's largest gait database show our framework impressively outperforms state-of-the-art methods.

Protein contact prediction by integrating deep multiple sequence alignments, coevolution and machine learning.

PubMed

Adhikari, Badri; Hou, Jie; Cheng, Jianlin

2018-03-01

In this study, we report the evaluation of the residue-residue contacts predicted by our three different methods in the CASP12 experiment, focusing on studying the impact of multiple sequence alignment, residue coevolution, and machine learning on contact prediction. The first method (MULTICOM-NOVEL) uses only traditional features (sequence profile, secondary structure, and solvent accessibility) with deep learning to predict contacts and serves as a baseline. The second method (MULTICOM-CONSTRUCT) uses our new alignment algorithm to generate deep multiple sequence alignment to derive coevolution-based features, which are integrated by a neural network method to predict contacts. The third method (MULTICOM-CLUSTER) is a consensus combination of the predictions of the first two methods. We evaluated our methods on 94 CASP12 domains. On a subset of 38 free-modeling domains, our methods achieved an average precision of up to 41.7% for top L/5 long-range contact predictions. The comparison of the three methods shows that the quality and effective depth of multiple sequence alignments, coevolution-based features, and machine learning integration of coevolution-based features and traditional features drive the quality of predicted protein contacts. On the full CASP12 dataset, the coevolution-based features alone can improve the average precision from 28.4% to 41.6%, and the machine learning integration of all the features further raises the precision to 56.3%, when top L/5 predicted long-range contacts are evaluated. And the correlation between the precision of contact prediction and the logarithm of the number of effective sequences in alignments is 0.66. © 2017 Wiley Periodicals, Inc.

Learning Computational Models of Video Memorability from fMRI Brain Imaging.

PubMed

Han, Junwei; Chen, Changyuan; Shao, Ling; Hu, Xintao; Han, Jungong; Liu, Tianming

2015-08-01

Generally, various visual media are unequally memorable by the human brain. This paper looks into a new direction of modeling the memorability of video clips and automatically predicting how memorable they are by learning from brain functional magnetic resonance imaging (fMRI). We propose a novel computational framework by integrating the power of low-level audiovisual features and brain activity decoding via fMRI. Initially, a user study experiment is performed to create a ground truth database for measuring video memorability and a set of effective low-level audiovisual features is examined in this database. Then, human subjects' brain fMRI data are obtained when they are watching the video clips. The fMRI-derived features that convey the brain activity of memorizing videos are extracted using a universal brain reference system. Finally, due to the fact that fMRI scanning is expensive and time-consuming, a computational model is learned on our benchmark dataset with the objective of maximizing the correlation between the low-level audiovisual features and the fMRI-derived features using joint subspace learning. The learned model can then automatically predict the memorability of videos without fMRI scans. Evaluations on publically available image and video databases demonstrate the effectiveness of the proposed framework.

Comparison of machine learned approaches for thyroid nodule characterization from shear wave elastography images

NASA Astrophysics Data System (ADS)

Pereira, Carina; Dighe, Manjiri; Alessio, Adam M.

2018-02-01

Various Computer Aided Diagnosis (CAD) systems have been developed that characterize thyroid nodules using the features extracted from the B-mode ultrasound images and Shear Wave Elastography images (SWE). These features, however, are not perfect predictors of malignancy. In other domains, deep learning techniques such as Convolutional Neural Networks (CNNs) have outperformed conventional feature extraction based machine learning approaches. In general, fully trained CNNs require substantial volumes of data, motivating several efforts to use transfer learning with pre-trained CNNs. In this context, we sought to compare the performance of conventional feature extraction, fully trained CNNs, and transfer learning based, pre-trained CNNs for the detection of thyroid malignancy from ultrasound images. We compared these approaches applied to a data set of 964 B-mode and SWE images from 165 patients. The data were divided into 80% training/validation and 20% testing data. The highest accuracies achieved on the testing data for the conventional feature extraction, fully trained CNN, and pre-trained CNN were 0.80, 0.75, and 0.83 respectively. In this application, classification using a pre-trained network yielded the best performance, potentially due to the relatively limited sample size and sub-optimal architecture for the fully trained CNN.

Histopathological Image Classification using Discriminative Feature-oriented Dictionary Learning

PubMed Central

Vu, Tiep Huu; Mousavi, Hojjat Seyed; Monga, Vishal; Rao, Ganesh; Rao, UK Arvind

2016-01-01

In histopathological image analysis, feature extraction for classification is a challenging task due to the diversity of histology features suitable for each problem as well as presence of rich geometrical structures. In this paper, we propose an automatic feature discovery framework via learning class-specific dictionaries and present a low-complexity method for classification and disease grading in histopathology. Essentially, our Discriminative Feature-oriented Dictionary Learning (DFDL) method learns class-specific dictionaries such that under a sparsity constraint, the learned dictionaries allow representing a new image sample parsimoniously via the dictionary corresponding to the class identity of the sample. At the same time, the dictionary is designed to be poorly capable of representing samples from other classes. Experiments on three challenging real-world image databases: 1) histopathological images of intraductal breast lesions, 2) mammalian kidney, lung and spleen images provided by the Animal Diagnostics Lab (ADL) at Pennsylvania State University, and 3) brain tumor images from The Cancer Genome Atlas (TCGA) database, reveal the merits of our proposal over state-of-the-art alternatives. Moreover, we demonstrate that DFDL exhibits a more graceful decay in classification accuracy against the number of training images which is highly desirable in practice where generous training is often not available. PMID:26513781