Meta-cognitive learning algorithm for neuro-fuzzy inference systems

This research work focuses on the development of meta-cognitive sequential learning algorithms in Radial Basis Function (RBF) network classiers, and their application to the early diagnosis of neurodegenerative diseases. The important issues in existing sequential learning algorithms are proper selection of training samples, nding minimal network structure and selection of an appropriate learning strategy. In addition, the random sequence of sample arrival inuences the performance signicantly. It has been reported in human learning that best learning strategies employ meta-cognition (metacognition means cognition about cognition) to address fundamental problems of what-tolearn, when-to-learn and how-to-learn. This thesis develops such meta-cognitive sequential learning algorithms in RBF network for classication problems. We call a RBF network employing meta-cognitive algorithm as `meta-cognitive RBF network' (McRBFN). McRBFN is developed based on Nelson and Narens model of meta-cognition for human learning. Accordingly, McRBFN has two components, namely cognitive and meta-cognitive components. A RBF network with evolving structure is the cognitive component and a self-regulatory learning mechanism is its meta-cognitive component. List of Figures 1.1 Nelson and Narens model of meta-cognition . . . . . . . . . . . . . . . .

A meta-cognitive sequential learning algorithm for neuro-fuzzy inference system

In this paper, we propose a Projection Based Learning (PBL) algorithm for a Meta-Cognitive Neuro-Fuzzy Inference (McFIS) together referred to as PBL-McFIS. McFIS consists of a cognitive component, which is a zero-order Takagi-Sugeno-Kang adaptive neuro-fuzzy inference system, and a meta-cognitive component, which is a self-regulatory learning mechanism for the neuro-fuzzy inference system. The learning in the cognitive component begins with zero rules, and as new samples are presented to the network, the meta-cognitive component monitors the hinge-loss error and spherical potential of the current sample to efficiently decide on what-to-learn, when-to-learn and how-to-learn. In this work we employ PBL-McFIS to solve classification problems and hence the monitory signals employ class-specific self-adaptive thresholds to decide on efficient learning strategies. These thresholds are self-adapted such that the trained network is compact and avoids over-fitting. During addition of new rules or updating of existing rules, the optimal output weights corresponding to the minimum hinge-loss error is computed using PBL algorithm. The learning algorithm considers class-specific as well as class overlap factors during training. The performance of PBL-McFIS is evaluated on a set of benchmark classification problems. The statistical performance analysis with other state-of-the-art neuro-fuzzy inference systems and SVM indicate improved classification ability of the proposed algorithm.

Neuro-fuzzy [Jang,1997][Abraham,2005] are hybrid systems that combine the learning capacity of neural nets [Haykin,1999] with the linguistic interpretation of fuzzy inference systems [Ross,2004]. These systems have been evaluated quite intensively in machine learning tasks. This is mainly due to a number of factors: the applicability of learning algorithms developed for neural nets; the possibility of promoting implicit and explicit knowledge integration; and the possibility of extracting knowledge in the form of fuzzy rules. Most of the well known neuro-fuzzy systems, however, present limitations regarding the number of inputs allowed or the limited (or nonexistent) form to create their own structure and rules [Nauck,1997][Nauck,19 98][Vuorimaa,1994][Zhang,1995]. This paper describes a new class of neuro-fuzzy models, called Hierarchical Neuro-Fuzzy BSP Systems (HNFB). These models employ the BSP partitioning (Binary Space Partitioning) of the input space [Chrysanthou,1996] and have been developed to bypass traditional drawbacks of neuro-fuzzy systems. This paper introduces the HNFB models based on supervised learning algorithm. These models were evaluated in many benchmark applications related to classification and time-series forecasting. A second paper, entitled Hierarchical Neuro-Fuzzy Systems Part II, focuses on hierarchical neuro-fuzzy models based on reinforcement learning algorithms.

Spiking neuro-fuzzy clustering system and its memristor crossbar based implementation

Meta-cognitive Neural Network for classification problems in a sequential learning framework

Domain-Specific Context of Studentś Self-Regulated Learning in the Preparation of Helping Professions

Background: Metacognition, defined as "thinking about thinking," represents a fundamental cognitive process governing how individuals monitor and regulate their learning. While extensive research demonstrates positive correlations between metacognitive awareness and academic performance in various educational contexts, limited investigations have examined this relationship within medical education cohorts. This study investigated the correlation between metacognitive awareness and academic performance among first-year medical students in the subject of anatomy. Methods: A quantitative, cross-sectional correlational study was conducted among 138 Phase-1 MBBS students at a medical college in central Andhra. Metacognitive awareness was assessed using the validated Metacognitive Awareness Inventory (MAI-52), comprising Knowledge of Cognition (17 items) and Regulation of Cognition (35 items) domains. Academic performance was measured using internal assessment scores in anatomy. Statistical analyses included descriptive statistics, Pearson and Spearman correlations, multiple linear regression, and one-way ANOVA. Students were stratified into tertile-based groups for comparative analysis. Results: The sample demonstrated mean theory examination scores of 45.92 ± 12.67 and total MAI scores of 37.04 ± 6.06. All correlations between MAI subscales and academic performance were positive and statistically significant. Total MAI score showed the strongest correlation with academic performance (r = 0.408, p < 0.001), followed by Regulation of Cognition (r = 0.378), Conditional Knowledge (r = 0.330), and Knowledge of Cognition (r = 0.323). Multiple regression analysis revealed that approximately 17% of variance in theory marks was explained by metacognitive components, with Regulation of Cognition emerging as the sole significant predictor (β = 0.80, p = 0.005). Cross-tabulation analysis demonstrated that 57.5% of high MAI students were high achievers, while 53.1% of low MAI students were low achievers. Conclusion: This study establishes a significant positive correlation between metacognitive awareness and academic performance in first-year medical students. Regulation of cognition emerged as the strongest predictor of academic success, suggesting that students' ability to monitor and adjust their learning strategies significantly contributes to academic achievement. These findings support the integration of metacognitive skill development into medical education curricula to enhance learning outcomes and foster self-directed learning capabilities essential for lifelong medical practice. KEYWORDS: Metacognition, metacognitive awareness, medical education, academic performance, self-regulated learning, medical students, anatomy education, learning strategies.

It is increasingly clear that machine learning algorithms need to be integrated in an iterative scientific discovery loop, in which data is queried repeatedly by means of inductive queries and where the computer provides guidance to the experiments that are being performed. In this chapter, we summarise several key challenges in achieving this integration of machine learning and data mining algorithms in methods for the discovery of Quantitative Structure Activity Relationships (QSARs). We introduce the concept of a robot scientist, in which all steps of the discovery process are automated; we discuss the representation of molecular data such that knowledge discovery tools can analyse it, and we discuss the adaptation of machine learning and data mining algorithms to guide QSAR experiments.KeywordsInductive Logic ProgrammingData Mining AlgorithmSubgraph IsomorphismOuterplanar GraphGraph MiningThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

This study examines the relationship between self-regulated learning (SRL) strategies and English language mastery among senior high school students. Specifically, it investigates the overall effect of SRL on English achievement and identifies which specific SRL strategies serve as significant predictors of language proficiency. Using an adapted questionnaire from Magno (2010), SRL levels were measured among 400 students from grades XI and XII across Science and Social streams at X Senior High School, with a final sample size of 196 participants. Findings indicate that students demonstrated a high level of self-regulation in their learning, reflected in a mean SRL score of 2.83, and attained strong English achievement outcomes, with a mean score of 84.08. Statistical analysis confirms a significant effect of SRL on English achievement. However, the presence of heteroscedasticity prevented the application of multiple regression analysis, thereby limiting the identification of the strongest SRL predictors of English success. These results underscore the role of self-regulated learning in shaping academic achievement and highlight the need for further research into refining predictive models to better understand the impact of specific SRL strategies on language proficiency. Keywords: self-regulated, learning strategies, English mastery

Foreword ( Wilbert J. McKeachie). 1. Introduction: Self-Regulation of Learning in Postsecondary Education (Hefer Bembenutty) The chapter introduces this volume on self-regulation of learning and highlights the current trends on self-regulation presented by each of the authors. 2. Purpose of Engagement in Academic Self-Regulation (Einat Lichtinger, Avi Kaplan) This chapter argues that self-regulated learning is not a unitary construct, with students different purposes of engagement in the task meaningfully distinguishing between different types of self-regulation. 3. Self-Regulation and Achievement Goals in the College Classroom (Akane Zusho, Kelcey Edwards) This chapter links self-regulation of learning with achievement goal theory and offers practical tips to educators who struggle with disinterested learners. 4. Understanding and Facilitating Self-Regulated Help Seeking (Stuart A. Karabenick, Myron H. Dembo) The authors describe interventions to develop the competencies and resources that facilitate student help seeking as an effective selfregulated learning strategy. 5. Self-Regulation and Learning Strategies (Claire Ellen Weinstein, Taylor W. Acee, JaeHak Jung) This chapter reviews research on learning strategies, describes a model of strategic and self-regulated learning, and reports on instructional methods, interventions, and assessments that instructors can use to help students develop lifelong learning strategies they need to succeed in college. 6. Academic Delay of Gratifi cation and Academic Achievement (Hefer Bembenutty) This chapter provides a review of research on delay of gratifi cation and suggests ways in which educators can instill in students to delay gratifi cation. 7. Resistance and Disidentifi cation in Refl ective Practice with Preservice Teaching Interns (Michael Middleton, Eleanor Abrams, Jayson Seaman) This chapter examines case studies to identify contextual factors in teacher education programs that promote or inhibit teaching interns' self-refl ective practices. 8. Professional Development Needs and Practices Among Educators and School Psychologists (Timothy J. Cleary) This chapter summarizes research illustrating the importance and need for motivation and self-regulation professional development training for teachers and school psychologists across assessment, intervention, and instructional activities. 9. Transitioning from College Classroom to Teaching Career: Self-Regulation in Prospective Teachers (Judi Randi, Lyn Corno, Elisabeth Johnson) This chapter explores how preservice teachers prepare for the transition from college classroom to career through assignments and features of the learning environment designed to approximate the demands of work settings and job-related tasks. 10. The Role of Web 2.0 Technologies in Self-Regulated Learning (Anastasia Kitsantas, Nada Dabbagh) This chapter demonstrates how Web 2.0 technologies can be used to facilitate self-regulated learning in postsecondary education. The authors show how instructors can integrate social software into course design to promote students self-regulation of learning. 11. Self-Regulation of Learning with Computer-Based Learning Environments (Jeffrey A. Greene, Daniel C. Moos, Roger Azevedo) This chapter outlines how self-regulated learning skills can facilitate learning with computer-based learning environments and how educators can diagnose and build on students' self-regulated learning ability. 12. New Directions for Self-Regulation of Learning in Postsecondary Education (Hefer Bembenutty) This chapter puts into context the major contributions of this volume on self-regulation of learning and provides new directions for its promotion in postsecondary education. INDEX.

Many students rarely use self-regulated learning (SRL) strategies, and little is known about what drives this variation. This study investigates which facets of SRL competence predict students' reported strategy use and performance, and whether these facets can be enhanced through video-based modeling. Based on conceptual change theory, we hypothesize that learners' initial SRL competence influences their ability to acquire SRL strategies. A total of 157 university students participated in a quasi-experimental lab study using a pre-, post-, and follow-up design. Participants watched one of three SRL modeling videos (mastery, coping, control) and completed questionnaires and reflection tasks assessing SRL beliefs, knowledge, and strategy use. Inconsistent beliefs and the interaction between self-efficacy and utility beliefs negatively predicted reported SRL use, while performance was positively associated with SRL knowledge, self-efficacy, and reported strategy use. Participants in the intervention condition showed significantly greater increases in SRL knowledge and reduced inconsistent beliefs. Most notably, learners with an initially low to average SRL strategy use showed the largest improvements following the intervention. These findings underscore the potential importance of addressing both cognitive and belief-related components of SRL. The findings suggest that modeling videos may support conceptual change and the development of SRL competence, particularly among less experienced learners.

Influences on functional outcome and subjective recovery in individuals with and without First Episode Psychosis: A metacognitive model

This paper proposes a novel approach for achieving sustainable energy systems in unexpected sports event management by integrating machine learning and optimization algorithms. Specifically, we used reinforcement learning for peak load forecasting and bat evolutionary algorithm for optimization, since the energy management problem in sports events is typically non-linear. Machine learning algorithms, specifically reinforcement learning, are used to analyze historical data and provide accurate peak load forecasts. This information can then be used to optimize energy consumption during the event through the use of algorithms such as the bat evolutionary algorithm, which can effectively solve non-linear optimization problems. The integration of these algorithms in unexpected sports event management can lead to significant improvements in sustainability and cost-effectiveness. This paper presents a case study of the implementation of reinforcement learning and bat evolutionary algorithms in an unexpected sports event management scenario, demonstrating the effectiveness of the proposed approach in achieving sustainable energy systems and reducing overall energy consumption. Overall, this paper provides a roadmap for integrating machine learning and optimization algorithms, such as reinforcement learning and bat evolutionary algorithm, in unexpected sports event management to achieve sustainable energy systems, promoting a more sustainable future for the sports event industry and the planet as a whole.

The aging and multimorbid population and health personnel shortages pose a substantial burden on primary health care. While predictive machine learning (ML) algorithms have the potential to address these challenges, concerns include transparency and insufficient reporting of model validation and effectiveness of the implementation in the clinical workflow. To systematically identify predictive ML algorithms implemented in primary care from peer-reviewed literature and US Food and Drug Administration (FDA) and Conformité Européene (CE) registration databases and to ascertain the public availability of evidence, including peer-reviewed literature, gray literature, and technical reports across the artificial intelligence (AI) life cycle. PubMed, Embase, Web of Science, Cochrane Library, Emcare, Academic Search Premier, IEEE Xplore, ACM Digital Library, MathSciNet, AAAI.org (Association for the Advancement of Artificial Intelligence), arXiv, Epistemonikos, PsycINFO, and Google Scholar were searched for studies published between January 2000 and July 2023, with search terms that were related to AI, primary care, and implementation. The search extended to CE-marked or FDA-approved predictive ML algorithms obtained from relevant registration databases. Three reviewers gathered subsequent evidence involving strategies such as product searches, exploration of references, manufacturer website visits, and direct inquiries to authors and product owners. The extent to which the evidence for each predictive ML algorithm aligned with the Dutch AI predictive algorithm (AIPA) guideline requirements was assessed per AI life cycle phase, producing evidence availability scores. The systematic search identified 43 predictive ML algorithms, of which 25 were commercially available and CE-marked or FDA-approved. The predictive ML algorithms spanned multiple clinical domains, but most (27 [63%]) focused on cardiovascular diseases and diabetes. Most (35 [81%]) were published within the past 5 years. The availability of evidence varied across different phases of the predictive ML algorithm life cycle, with evidence being reported the least for phase 1 (preparation) and phase 5 (impact assessment) (19% and 30%, respectively). Twelve (28%) predictive ML algorithms achieved approximately half of their maximum individual evidence availability score. Overall, predictive ML algorithms from peer-reviewed literature showed higher evidence availability compared with those from FDA-approved or CE-marked databases (45% vs 29%). The findings indicate an urgent need to improve the availability of evidence regarding the predictive ML algorithms' quality criteria. Adopting the Dutch AIPA guideline could facilitate transparent and consistent reporting of the quality criteria that could foster trust among end users and facilitating large-scale implementation.