Papers by Keyword: Adaptive Learning

Abstract: It is possible to address learning challenges in a way that is unique to the needs and preferences of students through adaptive learning environments. Using these platforms, learning content can be personalized to reflect a user's interest, past knowledge, present abilities, and strengths and limitations. Conversely, the efficiency of adaptive learning systems depends on the techniques adopted to classify and present the content according to students’ needs and preferences. Artificial Intelligence (AI) techniques have recently been applied in personalized adaptive education systems to address content delivery-related learning challenges. However, not much is known about content adaptation based on bioinspired optimization algorithms. This study offers a comprehensive evaluation of the literature on personalized adaptive learning Management systems based on bioinspired optimization algorithms. The study examined conference proceedings and journal papers published in Scopus, Web of Science, and IEEE databases between 2013 and 2023. Nevertheless, Web of Science yielded no papers that were connected to this investigation. Web of Science was thus left out of the research. 5442 were screened in total, 303 were evaluated, and 6 were deemed eligible for the systematic review. Our findings suggest that there have been a limited number of research or personalized adaptive learning systems based on bioinspired algorithms.

Abstract: Epilepsy is type of neurological disorder characterized by recurrent seizures that may cause injury to self and others. The ability to predict seizure before its occurrence, so that counter measures are considered, would improve the quality of life of epileptic patients. This research work proposes an adaptive seizure prediction approach based on electroencephalography (EEG) signals analysis. We use cross-correlation to estimate synchronization between EEG channels. Abnormal synchronization between brain regions may reveal brain condition and functionality. Two EEG synchronization baselines, normal and pre-seizure, are used to continuously monitor sliding windows of EEG recording to predict the upcoming seizure. The two baselines are continuously updated using distance-based method based on the most recent prediction outcome. Up to 570 hours continuous EEG recording taken from CHB-MIT dataset is used for validating the proposed method. An overall of 84% sensitivity (46 out of 55 seizures are correctly predicted) and 63% specificity are achieved with one hour prediction horizon. The proposed method is suitable to be implemented in mobile or embedded device which has limited processing resources due to its simplicity.

Abstract: This paper studies adaptive learning for diagnostic image recognition and expounds that adaptive resonance theory is utilized to achieve ART artificial neural network of self-stability and self-makeup for recognition, which meets the requirement of learning and adaption. In terms of the principle, an algorithm of self-stability and classifier learning is also provided.

Abstract: With consideration of the impact on adaptive teaching strategy of constructivist learning theory, we put forward essential elements of the smart learning system to achieve individualized teaching. Adaptive learning is coined as a learning method through existing knowledge and experience of learners and interacting with the adaptive learning system to obtain knowledge and gain the ability. An adaptive learning framework is presented by employing fuzzy method and rule reference model. By employing Cognitive Knowledge and Self-feedback, the proposed approach improves the efficiency of learning.

Abstract: In this paper, adaptive learning method of bending force presetting model in a six-high cold rolling mill is introduced. Adaptive learning coefficient of bending force presetting model is calculated by contrast between measured and model calculated actual bending force, then exponential method is used to modify the adaptive learning coefficient to improve the precision of the bending force presetting model. While calculating model calculated actual bending force, Legendre polynomials are used to convert measured flatness data to quadratic and quartic flatness coefficient, then regulating quantity on the quadratic flatness coefficient of intermediate roll bending force and work roll bending force is determined based on their regulate capability. Practical application shows that precision of the bending force presetting model has improved significantly by adaptive learning.

Abstract: Training a SVM corresponds to solving a linearly constrained quadratic problem (QP) in a number of variables equal to the number of data points, this optimization problem becoming challenging when the number of data points exceeds few thousands. Because the computational complexity of the existing algorithms is extremely large in case of few thousands support vectors and therefore the SVM QP-problem becomes intractable, several decomposition algorithms that do not make assumptions on the expected number of support vectors have been proposed instead. In this paper we propose a heuristic learning algorithm of gradient type for learning a SVM using linear separable data, and analyze its performance in terms of accuracy and efficiency. In order to evaluate the efficiency of our learning method, several tests were performed against the Platt’s SMO method, and the conclusions are formulated in the final section of the paper.