Optimal Learning Research Articles

Physics-guided machine learning enhanced electrostatic actuated method for in-situ measurement of Young’s modulus

Abstract Young's modulus of polysilicon is a vital mechanical parameter highly dependent on sample preparation and growth techniques. In-situ measurement of this property is essential for effective process control monitoring in MEMS fabrication. In this work, an innovative electrostatic actuated method without pull-in instability for in-situ test is proposed. Based on the behavior simulated through finite element analysis, physics-guided neural networks which integrate the advantage of both data science models and physics-guided ones are utilized to extract the Young’s modulus and assess the probability of pull-in instability. Moreover, the performance of structure is evaluated and optimized through Pareto analysis based on genetic algorithm. It is found that the mapping relationship between systematic parameters, excitation, and response of the structure can be modeled by physics-guided neural network accurately, and the optimization of design facilities the convenience of measurement. Moreover, error of this method is within 5% under most circumstances, and the measured Young’s modulus through this method is close to that by nanoindentation test. This work explores potential applications of machine learning in MEMS design, testing, and optimization.

Predicting grip strength-related frailty in middle-aged and older Chinese adults using interpretable machine learning models: a prospective cohort study

IntroductionFrailty is an emerging global health burden, and there is no consensus on the precise prediction of frailty. We aimed to explore the association between grip strength and frailty and interpret the optimal machine learning (ML) model using the SHapley Additive exPlanation (SHAP) to predict the risk of frailty.MethodsData for the study were extracted from the China Health and Retirement Longitudinal Study (CHARLS) database. Socio-demographic, medical history, anthropometric, psychological, and sleep parameters were analyzed in this study. We used the least absolute shrinkage and selection operator (LASSO) regression to filter the model for the best predictor variables and constructed six ML models for predicting frailty. The feature performance of six ML models was compared based on the area under the receiver operating characteristic curve (AUROC) and the light gradient boosting machine (LightGBM) model was selected as the best predictive frailty model. We used SHAP to interpret the LightGBM model and to reveal the decision-making process by which the model predicts frailty.ResultsA total of 10,834 eligible participants were included in the study. Using the lowest quartile of grip strength as a reference, grip strength was negatively associated with the risk of frailty when grip strength was >29.00 kg for males or >19.00 kg for females (p < 0.001). The LightGBM model predicted frailty with optimal performance with an AUROC of 0.768 (95% CI 0.741 ~ 0.795). The SHAP summary plot showed that all features predicted frailty in order of importance, with cognitive function being considered the most important predictive feature. The poorer the cognitive function, nighttime sleep duration, body mass index (BMI), and grip strength, the higher the risk of frailty in middle-aged and older adults. The SHAP individual force plot clearly shows that the LightGBM model predicts frailty in the individual decision-making process.ConclusionThe grip strength-related LightGBM prediction model based on SHAP has high accuracy and robustness in predicting the risk of frailty. Increasing grip strength, cognitive function, nighttime sleep duration, and BMI reduce the risk of frailty and may provide strategies for individualized management of frailty.

How do the current e-learning offers affect the learning behaviour of students? A study of e-learning offers and learning behaviour among students from different universities and colleges in the fields of media management and business administration in Baden-Württemberg

Students today have unlimited access to digital resources, yet this abundance often hinders independent learning, which is crucial for academic success. This study investigates how current e-learning tools influence the learning behaviour of students specializing in media management and business administration across universities in Baden-Württemberg. A qualitative group discussion with eight students aged 20–24, analyzed through Mayring's content analysis, reveals that while e-learning platforms offer flexibility and accessibility, they also present challenges such as distraction and the need for self-discipline. The findings highlight that optimal learning outcomes require structured e-learning strategies tailored to individual needs and emphasize the hybrid model as a promising approach for future education.

Enhancing Malicious Activity Detection in IoT-Enabled Network and IoMT Systems Through Meta-Heuristic Optimization and Machine Learning

Enhancing Malicious Activity Detection in IoT-Enabled Network and IoMT Systems Through Meta-Heuristic Optimization and Machine Learning

An idiodynamic study on students’ negative emotions in relation to instructor clarity and non-verbal immediacy in a CLIL classroom

ABSTRACT While positive teacher behaviors are recognized as crucial for effective learning, empirical research on their moment-to-moment impact on student emotions, particularly in the context of CLIL classrooms remains limited. This study addresses the gap by employing the idiodynamic method, a novel approach grounded in Dynamic Systems Theory, to provide a nuanced understanding of how individual Chinese university students’ negative academic emotions evolve in response to specific teacher behaviors. Using a mixed-methods design, the study reveals that teacher communication behaviors significantly influence students’ emotional trajectories, highlighting the coexistence and potential benefits of both negative and positive emotions in fostering a healthy language learning environment. While CLIL increases cognitive load and anxiety, effective teacher clarity and nonverbal immediacy strategies can mitigate these effects, fostering engagement and reducing negative emotions. The study challenges the simplistic categorization of emotions as either negative or positive, emphasizing the coexistence of diverse emotions and the potential benefits of negative activating emotions in language learning. It underscores the need for teacher training programs to incorporate not only pedagogical knowledge but also strategies for fostering positive communication and leveraging the dynamic interplay of student emotions for optimal learning outcomes.

Utilization and Challenges of Using ICT at SPM Al-Mashduqiah: Perception of English Teachers

The use of technology in English learning is becoming increasingly crucial to achieve optimal learning outcomes. This study aims to explore teachers' perceptions regarding the use and challenges of using Information and Communication Technology (ICT) in English learning at SPM Al-Mashduqiah. Using a qualitative method with a case study type, this study focuses on the perception of English teachers in the school as the subject of the study. Data were obtained through semi-structured interviews, observations, and documentation, which were then analyzed using a descriptive approach to describe and interpret the teacher's experiences and views in detail. The findings reveal that teachers have been utilizing ICT in various aspects of English learning, including the use of learning apps, interactive videos, and online platforms for assignments and evaluations. However, teachers face several challenges, such as limited facilities, lack of technical training, and resistance to changes from traditional teaching methods. Teachers' perceptions of ICT utilization vary; most view ICT as a tool capable of increasing student engagement and learning effectiveness, while others feel burdened by the need to master new technologies in their use in English learning. The study concludes that although the use of ICT in English learning at SPM Al-Mashduqiah has great potential to improve the quality of education, further efforts are needed to address existing challenges, including increased facility support and ongoing training for teachers. These findings are expected to provide valuable insights for policymakers and education practitioners in designing effective strategies for ICT integration, making an English learning more enjoyable and effective.

Cost-Aware Calibration of Classifiers

Most classification techniques in machine learning are able to produce probability predictions in addition to class predictions. However, these predicted probabilities are often not well calibrated in that they deviate from the actual outcome rates (i.e., the proportion of data instances that actually belong to a certain class). A lack of calibration can jeopardize downstream decision tasks that rely on accurate probability predictions. Although several post hoc calibration methods have been proposed, they generally do not consider the potentially asymmetric costs associated with overprediction versus underprediction. In this research, we formally define the problem of cost-aware calibration and propose a metric to quantify the cost of miscalibration for a given classifier. Next, we propose three approaches to achieve cost-aware calibration, two of which are cost-aware adaptations of existing calibration algorithms; the third one (named MetaCal) is a Bayes optimal learning algorithm inspired by prior work on cost-aware classification. We carry out systematic empirical evaluations on multiple public data sets to demonstrate the effectiveness of the proposed approaches in reducing the cost of miscalibration. Finally, we generalize the definition and metric as well as solution algorithms of cost-aware calibration to account for nonlinear cost structures that may arise in real-world decision tasks. Data Ethics & Reproducibility Note: There are no data ethics considerations. The code capsule is available on Code Ocean at https://doi.org/10.24433/CO.8552538.v1 and in the e-Companion to this article (available at https://doi.org/10.1287/ijds.2024.0038 ).

Analisis Kebutuhan Sarana dan Prasarana untuk Mendukung Proses Pembelajaran di SMK Negeri 1 Surabaya

Vocational education, secondary school facilities and infrastructure play animportant role in the learning process. Management of facilities and infrastructure needs to be done well to achieve success and support the teaching and learning process in vocational schools. To achieve success, the learning process must be supported by the availability of adequate facilities and infrastructure as well as optimal managemet by referring to the management of facilities and infrastructure. This research aims to analyze the need for facilities and infrastructure to supportan optimal learning process at SMK Negeri 1 Surabaya. This article was written using qualitative approach. Through data collection through interviews, documentation, and supported by direct observation at SMK Negeri 1 Surabaya with an approach to he students. It can be concluded that the results of this research show that the dominant facilities and infrastructure at SMK Negeri 1 Surabaya have been utilized optimally. Things to support practice in vocational schools, such as computer labs, as well as studios and other equipment that supports the learning process, are said to be very adequate. Maintenance of facilities and infrastructure has also been carried out periodically. The available facilities and infrastructure greatly increase student enthusiasm for learning and achievement.onclusions.

Implementasi Kurikulum Merdeka dalam Mengatasi Krisis Belajar

<p><em>This study aims to determine the implementation of the Merdeka Curriculum in overcoming the learning crisis at SD BPPI Cokroaminoto Pare. The method used is a qualitative method obtained from direct interviews to find out the planning and implementation of the Merdeka Curriculum carried out by teachers in overcoming the learning crisis at SD BPPI Cokroaminoto Kota Pare. In addition, observations and documentation were used regarding the implementation of the Merdeka Curriculum as part of understanding the basis of IKM. Based on the results of the interviews conducted, the Merdeka Curriculum has been implemented in addressing the learning crisis, but there is still a need for training, webinars, and peer sharing to better understand the Merdeka Curriculum. This is necessary for teachers to be able to understand in depth regarding the implementation of the Merdeka Curriculum. Teachers can provide interesting learning experiences for students so that the learning crisis can be resolved well and produce optimal learning.</em></p>

Accelerating virtual patient generation with a Bayesian optimization and machine learning surrogate model.

The pharmaceutical industry has increasingly adopted model-informed drug discovery and development (MID3) to enhance productivity in drug discovery and development. Quantitative systems pharmacology (QSP), which integrates drug action mechanisms and disease complexities to predict clinical endpoints and biomarkers is central to MID3. QSP modeling has proven successful in metabolic and cardiovascular diseases and has expanded into oncology, immunotherapy, and infectious diseases. Despite its benefits, QSP model validation through clinical trial simulations using virtual patients (VPs) is challenging because of parameter variability and high computational costs. To address these challenges, this study proposes a hybrid method that combines Bayesian optimization with machine learning for efficient parameter screening. Our approach achieved an acceptance rate of 27.5% in QSP simulations, which is in sharp contrast with the 2.5% rate of conventional random search methods, indicating more than 10-fold improvement in efficiency. By facilitating faster and more diverse VPs generation, this method promises to advance clinical trial simulations and accelerate drug development in pharmaceutical research.

Harnessing quantum power: Revolutionizing materials design through advanced quantum computation

AbstractThe design of advanced materials for applications in areas of photovoltaics, energy storage, and structural engineering has made significant strides. However, the rapid proliferation of candidate materials—characterized by structural complexity that complicates the relationships between features—presents substantial challenges in manufacturing, fabrication, and characterization. This review introduces a comprehensive methodology for materials design using cutting‐edge quantum computing, with a particular focus on quadratic unconstrained binary optimization (QUBO) and quantum machine learning (QML). We introduce the loop framework for QUBO‐empowered materials design, including constructing high‐quality datasets that capture critical material properties, employing tailored computational methods for precise material modeling, developing advanced figures of merit to evaluate performance metrics, and utilizing quantum optimization algorithms to discover optimal materials. In addition, we delve into the core principles of QML and illustrate its transformative potential in accelerating material discovery through a range of quantum simulations and innovative adaptations. The review also highlights advanced active learning strategies that integrate quantum artificial intelligence, offering a more efficient pathway to explore the vast, complex material design space. Finally, we discuss the key challenges and future opportunities for QML in material design, emphasizing their potential to revolutionize the field and facilitate groundbreaking innovations.

Eeg based smart emotion recognition using meta heuristic optimization and hybrid deep learning techniques

In the domain of passive brain-computer interface applications, the identification of emotions is both essential and formidable. Significant research has recently been undertaken on emotion identification with electroencephalogram (EEG) data. The aim of this project is to develop a system that can analyse an individual’s EEG and differentiate among positive, neutral, and negative emotional states. The suggested methodology use Independent Component Analysis (ICA) to remove artefacts from Electromyogram (EMG) and Electrooculogram (EOG) in EEG channel recordings. Filtering techniques are employed to improve the quality of EEG data by segmenting it into alpha, beta, gamma, and theta frequency bands. Feature extraction is performed with a hybrid meta-heuristic optimisation technique, such as ABC-GWO. The Hybrid Artificial Bee Colony and Grey Wolf Optimiser are employed to extract optimised features from the selected dataset. Finally, comprehensive evaluations are conducted utilising DEAP and SEED, two publically accessible datasets. The CNN model attains an accuracy of approximately 97% on the SEED dataset and 98% on the DEAP dataset. The hybrid CNN-ABC-GWO model achieves an accuracy of approximately 99% on both datasets, with ABC-GWO employed for hyperparameter tuning and classification. The proposed model demonstrates an accuracy of around 99% on the SEED dataset and 100% on the DEAP dataset. The experimental findings are contrasted utilising a singular technique, a widely employed hybrid learning method, or the cutting-edge method; the proposed method enhances recognition performance.

THE RELATIONSHIP BETWEEN INTRINSIC LEARNING MOTIVATION AND STUDENTS LEARNING ACHIEVEMENTS IN NURSING ASSISTANT DEPARTMENT AT VOCATIONAL HIGH SCHOOL 8 BATAM

Intrinsic learning motivation is a strong drive or desire that comes from within a person to achieve optimal learning achievement from within themselves. Students will be more enthusiastic and responsible for the learning activities they participate in, which can be beneficial for their needs in achieving satisfactory learning achievement. This study aims to determine the relationship between intrinsic learning motivation and learning achievement in students majoring in Nursing Assistant at SMK Negeri 8 Batam. This study uses a cross-sectional method. The number of samples in this study was 91 students majoring in Nursing Assistant with a technique of total sampling. The research results showed that univariate analysis of the frequency of high intrinsic learning motivation was obtained by 40 students (43.9%), results of the frequency of student achievement increasing were obtained by 52 students (57.1%), and students who have high intrinsic learning motivation with increasing learning achievement are 31 students (34.1%). Meanwhile, bivariate analysis use Chi Square shows a p-value of 0.007 < 0.05, meaning that there is a significant relationship between positive intrinsic learning motivation and student achievement in the Nursing Assistant Department of SMK Negeri 8 Batam. Students are advised to be more active in asking questions during the teaching and learning process and to independently repeat the lessons they have learned to prepare for the exam.

Effect of teachers' teaching strategies on students' learning engagement: moderated mediation model.

This study explores the nuanced relationship between teachers' teaching strategies and students' learning engagement within online environments, considering the mediation by students' perceptions of teachers' emotional engagement and the moderation by teachers' expectations. Employing a stratified sampling technique, data were collected from 1,200 Chinese primary and secondary students through the "Survey on Online Learning Engagement." Structural equation modeling was applied to analyze the relationships among teaching strategies, emotional engagement, teachers' expectations, and learning engagement. The study found that teachers' teaching strategies not only directly affect students' learning engagement (r = 0.377***, p < 0.001), but also indirectly affect students' learning engagement through students' perception of teachers' emotional engagement. It showed a significant mediating effect (indirect effect = 0.231***, p < 0.001). Additionally, teachers' expectations exhibit a notable moderating effect on the relationship between perceived emotional engagement and learning engagement (β = 0.073***, p < 0.001). In other words, in addition to teachers' teaching strategies, teachers' emotional involvement and students' perception of teachers' emotional involvement are important factors affecting students' learning involvement. This means that in online classroom teaching, the emotional transmission and experience between teachers and students play a role in the connection. The study highlights the critical role of emotional connection in educational strategies, suggesting that teachers should focus on fostering emotional engagement alongside academic content. Balanced teacher expectations are recommended to facilitate a supportive learning environment that encourages higher levels of student engagement. Educators are advised to integrate emotional warmth and responsiveness into their teaching methods and to maintain realistic expectations to promote optimal learning outcomes.

Research on supercritical CO2-based filled type U-pipe solar evacuated tubular collector: A thermodynamically parametric optimization and implementation machine learning modeling

Using supercritical CO2 as a working fluid in a heat and power system operating on solar energy is an advantageous approach that achieves higher efficiency, carbon capture, and emissions reduction. Therefore, the present work focused on researching the effectiveness of developing a supercritical CO2-based U-pipe solar evacuated tubular collector (ETC) by a filled layer that includes contributions to thermodynamic parametric optimization and machine learning modeling to forecast the outlet temperature intelligently. Results indicated that the filled type increase the outlet temperature by 24.29 % compared with the conventional type. The evaluation of the optimization research findings shows that an optimal mass flow rate of 8.0 kg/hr achieves a maximum exergy efficiency of 13.70 % to 14.51 %. Furthermore, the results recommended that arranging 13 tubes with a length of 1800 mm is optimal for exergy efficiency within a mass flow rate range of 6.0–12.0 kg/hr. Based on machine learning implementations, Gradient Boosting, Support Vector Machine, and Multi-Layer Perceptron neural networks can intelligently predict with R2|Tout = 1.000, 0.997, and 0.995, respectively. A polynomial-based GMDH/ML with R2|Tout = 0.986 was presented to intelligently forecast the outlet temperature using five input (Tamb,ṁ,ηopt,Ltube,It) parameters.

Combining machine learning and computational fluid dynamics for solar panel tilt angle optimization in extreme winds

Although a key driver for green energy development, solar photovoltaic power plants face the major risk of severe wind damages, as there is currently no best practice on how to best stow the panels under strong wind conditions. In this research, an out-of-the-box numerical framework is introduced to inform the discussion around panel design and recommended stow positions, one that leverages the increasing use of solar tracker actuators, that allows panels to set an optimal angle relative to the sun to maximize power output, and incidentally offer a great potential for optimal safeguarding through individual panel piloting. The task of concurrently optimizing multiple panel tilts in a turbulent atmospheric boundary layer wind flow is modeled as a Markov decision process and solved with a single-step deep reinforcement learning algorithm, intended for situations where the optimal policy to be learnt by a neural network does not depend on state. The numerical reward fed to the neural network is computed from high-fidelity numerical simulations combining variational multiscale modeling of the Navier–Stokes equations and anisotropic boundary layer mesh adaptation, to accurately represent critical flow features at affordable computational costs, regardless of the panel tilts chosen by the learning agent. A range of experiments is performed across various learning objectives accounting for different possible causes of breakage (such as tear, vibrations, and fatigue), for which the proposed approach successfully minimizes the aerodynamic efforts on two-dimensional and three-dimensional arrangements of six ground-mounted panels under an incident wind speed of 50 km/h, while outperforming baseline safeguarding practices considered in the literature by several dozen per cent. This gives hope that, by interacting with its computational fluid dynamics environment in a trial-and-error manner, a deep reinforcement learning agent can learn unexpected solutions to this complex decision-making problem and come up with innovative, feasible solutions capable of managing utility-scale solar assets during high-wind events while efficiently complementing engineering intuition and practical experience.

A recommendation model for optimizing transfer learning hyper-parameter settings in building heat load prediction with limited data samples

The transfer learning method has gained increasing attention in the domain of building load prediction, particularly in scenarios with limited data samples. Its core principle involves leveraging knowledge obtained from abundant data in source buildings to aid the learning process of models for the target buildings. Existing research has predominantly concentrated on optimizing the selection of source building data to improve transfer learning effectiveness, while the optimization of transfer learning hyper-parameter settings is often neglected. This study proposes a recommendation model tailored for transfer learning hyper-parameter settings in the context of small sample prediction for building heat loads. The objective is to automatically suggest suitable transfer learning hyper-parameter combination based on the specific features of the building heat load data samples. In this study, 200 real building profiles were utilized to generate the input–output dataset required for the recommendation model. By employing data mining techniques such as clustering and classification, the correlation between the features of source building data and the most effective transfer learning hyper-parameter combination is investigated. The developed recommendation model for optimal transfer learning hyper-parameter settings achieves a classification accuracy of 90.5%，and the performance evaluation was conducted using an additional dataset of 30 source buildings. The results show that by employing this recommendation model, the prediction error of the target buildings can be reduced by 0.12% to 6.64% compared to the conventional method of empirically determining transfer learning hyper-parameter settings.

Real-time decision support model for logistics of emergency patient transfers from hospitals via an integrated optimisation and machine learning approach

Real-time decision support model for logistics of emergency patient transfers from hospitals via an integrated optimisation and machine learning approach

Seeking optimal and explainable deep learning models for inertial-based posture recognition

Deep Learning (DL) models, widely used in several domains, are often applied for posture recognition. This work researches five DL architectures for posture recognition: Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Transformer, hybrid CNN-LSTM, and hybrid CNN-Transformer. Agriculture and construction working postures were addressed as use cases, by acquiring an inertial dataset during the simulation of their typical tasks in circuits. Since model performance greatly depends on the choice of the hyperparameters, a grid search was conducted to find the optimal hyperparameters. An extensive analysis of the hyperparameter combinations’ effects is presented, identifying some general tendencies. Moreover, to unveil the black-box DL models, we applied the Gradient-weighted Class Activation Mapping (Grad-CAM) explainability method on CNN’s outputs to better understand the model’s decision-making, in terms of the most important sensors and time steps for each window output. Innovative hybrid architectures combining CNN and LSTM or Transformer encoder were implemented, by using the convolution feature maps as LSTM’s or Transformer’s inputs and fusing both subnetworks’ outputs with weights learned during the training. All architectures successfully recognized the eight posture classes, with the best model of each architecture exceeding 91.5% F1-score in the test. A top F1-score of 94.33%, with an inference time of just 0.29 ms (in a regular laptop), was achieved by a hybrid CNN-Transformer.

Fast generation of entanglement between coupled spins using optimization and deep learning methods

Coupled spins form composite quantum systems which play an important role in many quantum technology applications, with an essential task often being the efficient generation of entanglement between two constituent qubits. The simplest such system is a pair of spins-1/2 coupled with Ising interaction, and in previous works various quantum control methods such as adiabatic processes, shortcuts to adiabaticity and optimal control have been employed to quickly generate there one of the maximally entangled Bell states. In this study, we use machine learning and optimization methods to produce maximally entangled states in minimum time, with the Rabi frequency and the detuning used as bounded control functions. We do not target a specific maximally entangled state, like the preceding studies, but rather find the controls which maximize the concurrence, leading thus automatically the system to the closest such state in shorter time. By increasing the bounds of the control functions we observe that the corresponding optimally selected maximally entangled state also changes and the necessary time to reach it is reduced. The present work demonstrates also that machine learning and optimization offer efficient and flexible techniques for the fast generation of entanglement in coupled spin systems, and we plan to extent it to systems involving more spins, for example spin chains.