Learning Approach Research Articles

Critical thinking disposition and learning approach as predictors of mathematics performance

In the Philippines, improving pre-service math teachers’ critical thinking is receiving increasing attention, emphasizing the importance of tailoring instructional methods to students’ learning approaches for a more equitable environment and enhanced mathematics performance. Thus, this study aimed to determine if the critical thinking disposition subscales (reflective, attentiveness, open-mindedness, organization, perseverance, and intrinsic motivation) and learning approach (deep approach and surface approach) predict the mathematics performance of pre-service math teachers. This study employed a descriptive-correlational research design to randomly selected 125 pre-service math teachers from Central Luzon, Philippines. The survey instruments are administered through the student-educator negotiated CTDs scale, the revised two-factor study process questionnaire, and the 40- item validated test. Using descriptive analysis, findings revealed that preservice mathematics teachers have moderate levels of CTD, most of which use a deep approach and have average mathematics performance. Regression analysis showed that CTD and the deep approach were predictors. Therefore, pre-service mathematics teachers with a higher CTD and a deep approach are likelier to perform better in mathematics. These findings provide valuable insights into enhancing mathematics teacher education.

Improving imbalanced class intrusion detection in IoT with ensemble learning and ADASYN-MLP approach

Improving imbalanced class intrusion detection in IoT with ensemble learning and ADASYN-MLP approach

Optimizing olefin purification: An artificial intelligence-based process-conscious PI controller tuning for double dividing wall column distillation

This study investigates the light olefin separation using dual dividing wall columns (DWCs) and compares various proportional-integral (PI) controller tuning methods. A novel process-conscious reinforcement learning (RL) approach, utilizing Deep Deterministic Policy Gradient (DDPG), is developed by incorporating domain-specific knowledge into the reward function to ensure compliance with critical process variables and product purity. The DDPG-based PI tuning is evaluated against traditional methods such as Aspen’s recommended initial tuning, Ziegler-Nichols (ZN), and Cohen-Coon (CC). The result shows that the DDPG method significantly enhances control stability and accuracy, reducing error by factors of 11.9, 2.3, and 1.6 compared to Aspen, ZN, and CC, respectively. Additionally, DDPG demonstrates superior energy efficiency, consuming 13% less energy than the next best method. It also reduces purification costs by up to 13.5% and CO2 emissions by 20% compared to other methods. This study highlights the potential of integrating advanced RL techniques into industrial process control, delivering substantial improvements in stability, energy efficiency, economic, and environmental performance.

Multilevel hybrid handcrafted feature extraction based depression recognition method using speech

Background and purposeDiagnosis of depression is based on tests performed by psychiatrists and information provided by patients or their relatives. In the field of machine learning (ML), numerous models have been devised to detect depression automatically through the analysis of speech audio signals. While deep learning approaches often achieve superior classification accuracy, they are notably resource-intensive. This research introduces an innovative, multilevel hybrid feature extraction-based classification model, specifically designed for depression detection, which exhibits reduced time complexity. Materials and methodsMODMA dataset consisting of 29 healthy and 23 Major depressive disorder audio signals was used. The constructed model architecture integrates multilevel hybrid feature extraction, iterative feature selection, and classification processes. During the Hybrid Handcrafted Feature (HHF) generation stage, a combination of textural and statistical methods was employed to extract low-level features from speech audio signals. To enhance this process for high-level feature creation, a Multilevel Discrete Wavelet Transform (MDWT) was applied. This technique produced wavelet subbands, which were then input into the hybrid feature extractor, enabling the extraction of both high and low-level features. For the selection of the most pertinent features from these extracted vectors, Iterative Neighborhood Component Analysis (INCA) was utilized. Finally, in the classification phase, a one-dimensional nearest neighbor classifier, augmented with ten-fold cross-validation, was implemented to achieve detailed, results. ResultsThe HHF-based speech audio signal classification model attained excellent performance, with the 94.63 % classification accuracy. ConclusionsThe findings validate the remarkable proficiency of the introduced HHF-based model in depression classification, underscoring its computational efficiency.

Identifying momentary suicidal ideation using machine learning in patients at high-risk for suicide.

Strategies to detect the presence of suicidal ideation (SI) or characteristics of ideation that indicate marked suicide risk are critically needed to guide interventions and improve care during care transition periods. Some studies indicate that machine learning can be applied to momentary data to improve classification of SI. This study examined whether the classification accuracy of these models varies as a function of type of training data or characteristics of ideation. A total of 257 psychiatric inpatients completed a 3-week battery of ecological momentary assessment and measures of suicide risk factors. The accuracy of machine learning models in classifying the presence, duration, or intensity of ideation was compared across models trained on baseline and/or momentary suicide risk data. Relative feature importance metrics were examined to identify the risk factors that were most important for outcome classification. Models including both baseline and momentary features outperformed models with only one feature type, providing important information in both correctly classifying and differentiating individual characteristics of SI. Models classifying SI presence, duration, and intensity performed similarly. Results of this study may not generalize beyond a high-risk, psychiatric inpatient sample, and additional work is needed to examine temporal ordering of the relationships identified. Our results support using machine learning approaches for accurate identification of SI characteristics and underscore the importance of understanding the factors that differentiate and drive different characteristics of SI. Expansion of this work can support use of these models to guide intervention strategies.

BOATMAP: Bayesian Optimization Active Targeting for Monomorphic Arrhythmia Pace-mapping

Recent advances in machine learning and deep learning have presented new opportunities for learning to localize the origin of ventricular activation from 12-lead electrocardiograms (ECGs), an important step in guiding ablation therapies for ventricular tachycardia. Passively learning from population data is faced with challenges due to significant variations among subjects, and building a patient-specific model raises the open question of where to select pace-mapping data for training. This work introduces BOATMAP, a novel active learning approach designed to provide clinicians with interpretable guidance that progressively assists in locating the origin of ventricular activation from 12-lead ECGs. BOATMAP inverts the input–output relationship in traditional machine learning solutions to this problem and learns the similarity between a target ECG and a paced ECG as a function of the pacing site coordinates. Using Gaussian processes (GP) as a surrogate model, BOATMAP iteratively refines the estimated similarity landscape while providing suggestions to clinicians regarding the next optimal pacing site. Furthermore, it can incorporate constraints to avoid suggesting pacing in non-viable regions such as the core of the myocardial scar. Tested in a realistic simulation environment in various heart geometries and tissue properties, BOATMAP demonstrated the ability to accurately localize the origin of activation, achieving an average localization accuracy of 3.9±3.6mm with only 8.0±4.0 pacing sites. BOATMAP offers real-time interpretable guidance for accurate localization and enhancing clinical decision-making.

A Data and Model-Driven Deep Learning Approach to Robust Downlink Beamforming Optimization

A Data and Model-Driven Deep Learning Approach to Robust Downlink Beamforming Optimization

Enhancing network security using unsupervised learning approach to combat zero-day attack

Enhancing network security using unsupervised learning approach to combat zero-day attack

Enhancing early detection of autistic spectrum disorder in children using machine learning approaches

Diagnosing Autism Spectrum Disorder (ASD) presents a multifaceted challenge, demanding accurate and efficient screening methods. Applying machine learning techniques offers a promising avenue for enhancing diagnostic accuracy and efficiency. This research investigates the efficiency of machine learning in distinguishing individuals with ASD from those without, utilizing a comprehensive dataset comprising screening questions, demographic factors, and ASD related diagnostic classifications. We applied chi-square feature selection technique and also tested Random Forest, Logistic Regression, Gradient Boosting Classifier, and Extra Trees Classifier. Each model showed optimal performance and exhibit high precision, recall, and F1-score for both ASD-positive and ASD-negative instances. Additionally, AUROC curves further validated the models’ exceptional discriminatory abilities, with exceptional results. Our findings highlight the potential of machine learning algorithms for enhancing ASD diagnosis accuracy and efficiency in clinical settings. Further research and validation on larger datasets are required to understand the importance of machine learning methods in ASD diagnosis.

Implementation of Blended Learning Approach for Tertiary Level Training on Vehicle Electrification

Implementation of Blended Learning Approach for Tertiary Level Training on Vehicle Electrification

Acoustic fingerprints in nature: A self-supervised learning approach for ecosystem activity monitoring

According to the World Health Organization, healthy communities rely on well-functioning ecosystems. Clean air, fresh water, and nutritious food are inextricably linked to ecosystem health. Changes in biological activity convey important information about ecosystem dynamics, and understanding such changes is crucial for the survival of our species. Scientific edge cyberinfrastructures collect distributed data and process it in situ, often using machine learning algorithms. Most current machine learning algorithms deployed on edge cyberinfrastructures, however, are trained on data that does not accurately represent the real stream of data collected at the edge. In this work we explore the applicability of two new self-supervised learning algorithms for characterizing an insufficiently curated, imbalanced, and unlabeled dataset collected by using a set of nine microphones at different locations at the Morton Arboretum, an internationally recognized tree-focused botanical garden and research center in Lisle, IL. Our implementations showed completely autonomous characterization capabilities, such as the separation of spectrograms by recording location, month, week, and hour of the day. The models also showed the ability to discriminate spectrograms by biological and atmospheric activity, including rain, insects, and bird activity, in a completely unsupervised fashion. We validated our findings using a supervised deep learning approach and with a dataset labeled by experts, confirming competitive performance in several features. Toward explainability of our self-supervised learning approach, we used acoustic indices and false color spectrograms, showing that the topology and orientation of the clouds of points in the output space over a 24-h period are strongly linked to the unfolding of biological activity. Our findings show that self-supervised learning has the potential to learn from and process data collected at the edge, characterizing it with minimal human intervention. We believe that further research is crucial to extending this approach for complete autonomous characterization of raw data collected on distributed sensors at the edge.

GWO-ANFIS-RD3PG: A reinforcement learning approach with dynamic adjustment and dual replay mechanism for building energy forecasting

Reliable prediction of building energy consumption is essential for effective and sustainable energy management. Traditional forecasting methods, however, face challenges when dealing with sudden changes in energy consumption. To address the above-mentioned issue, we introduce the GWO-ANFIS-RD3PG prediction model in this paper. This model aims to ensure global forecasting accuracy while minimizing prediction errors at sudden change points. A Grey Wolf Optimization (GWO) algorithm with the Adaptive Neuro-Fuzzy Inference System (ANFIS) is proposed to predict the energy consumption type and its fluctuation magnitude for the next time step. Within the Recurrent Dual Experience Replay Buffer DDPG (RD3PG) prediction module, we employ Long Short-Term Memory (LSTM), as the actor network in the Deep Deterministic Policy Gradient (DDPG), to account for long-term dependencies in time series data. Notably, we introduce an adaptive action modification mechanism that allows the agent to optimize actions based on the output of the aforementioned ANFIS, enabling real-time adjustments during sudden change. To further enhance the model’s performance, we adopt a dual experience replay mechanism to store data samples from sudden change points, capturing insight information during these anomalies. Experimental results on two real-world datasets demonstrate that this method reduces MAE by 5.81% and 13.47%, and RMSE by 5.69% and 15.21% compared to the state-of-art models, showing the significance of the proposed method for energy efficiency improvement in real-world building operations.

Novel sulfide-driven denitrification methane oxidation (SDMO) system based on SBR-MBfR and EGSB-MBfR

Traditional denitrification process consumes external organic carbon leading to an increase in treatment costs and carbon emission. A novel sulfide-driven denitrification methane oxidation (SDMO) system, which could simultaneously utilize CH4 and H2S in biogas as electron donors for denitrification to reduce the cost and carbon emission, has been successfully operated in two kinds of reactors SBR-MBfR and EGSB-MBfR for ∼ 200 days in this study. The performance and microbial community were explored meanwhile machine learning approach have been used for predicting the complex effects on SDMO’s denitrification efficiency. Result shows SBR-MBfR’s superior performance with the maximum nitrate removal efficiency > 90 % while the denitrification rates and biological activity were also better than EGSB-MBfR. The autotrophic denitrification (Auto-D) contributed 5 % much more for nitrate removal in SBR-MBfR than EGSB-MBfR while denitrification anaerobic methane oxidation (DAMO) was more prominent in EGSB-MBfR. Nineteen machine learning models were used for operation data training and random forest regressor was demonstrated to be the optimal model for predicting nitrate removal efficiency in SDMO. According to random forest regressor’s analysis, HRT presented the highest importance in affecting SDMO nitrate removal efficiency. After the introduction of biogas for domestication, Auto-D bacteria Thiobacillus was the dominant bacteria in both systems occupying > 20 % and the abundance would increase gradually from ∼ 20 % to ∼ 60 % as H2S content rising. A hidden positive correlation between DAMO bacteria Candidatus Methylomirabilis and Thiobacillus was uncovered by mantel test analysis here, implying the integrating of Auto-D and DAMO process for nitrate removal. This study not only provides insights into the novel SDMO technology but also offers a potential advancement in simultaneously low-carbon wastewater treatment and biogas utilization.

A systematic review of deep learning-based denoising for low-dose computed tomography from a perceptual quality perspective.

Low-dose computed tomography (LDCT) scans are essential in reducing radiation exposure but often suffer from significant image noise that can impair diagnostic accuracy. While deep learning approaches have enhanced LDCT denoising capabilities, the predominant reliance on objective metrics like PSNR and SSIM has resulted in over-smoothed images that lack critical detail. This paper explores advanced deep learning methods tailored specifically to improve perceptual quality in LDCT images, focusing on generating diagnostic-quality images preferred in clinical practice. We review and compare current methodologies, including perceptual loss functions and generative adversarial networks, addressing the significant limitations of current benchmarks and the subjective nature of perceptual quality evaluation. Through a systematic analysis, this study underscores the urgent need for developing methods that balance both perceptual and diagnostic quality, proposing new directions for future research in the field.

Physics-informed ensemble learning with residual modeling for enhanced building energy prediction

Accurate modeling of building energy use is important to support a diverse spectrum of its downstream applications, such as building energy efficiency assessment, resilience analysis, smart control, etc. As mainstream approaches of building energy modeling, physics-based modeling builds on different fidelities of physics rules yet are usually compromised in modeling accuracy due to insufficiency of physics rules to capture real-world dynamics and incomplete input information. Data-driven approaches are computationally efficient, but black box (uninterpretable) in nature. For improved modeling of building energy use, this work proposes a physics-informed ensemble learning approach in building energy prediction through residual modeling. Specifically, we first analyze the components of building energy use data. Evidence suggests that the building energy use data can be decomposed into the physics-driven part, occupant-driven part, and white noise. Second, high-fidelity physics-based building models (EnergyPlus) and low-fidelity ones (RC models) are developed to capture the physics-driven part while time series methods are explored as the residual modeling approach to capture the occupant-driven discrepancies between physics-based simulation and measured building energy use (i.e., residuals). Finally, the physics-informed ensemble learning is proposed to integrate physics-based and data-driven models for enhanced accuracy of building energy modeling. Results demonstrate 40–90% decrease of discrepancies between modeling and field observations compared to traditional physics-based modeling methods. Moreover, when the training dataset size is small, the proposed ensemble model overperforms the pure data-driven models, demonstrating its higher robustness in extrapolation scenarios. This work makes fundamental contributions to the development of convergent modeling approaches in the building modeling field.

PreAlgPro: Prediction of allergenic proteins with pre-trained protein language model and efficient neutral network

Allergy is a prevalent phenomenon, involving allergens such as nuts and milk. Avoiding exposure to allergens is the most effective preventive measure against allergic reactions. However, current homology-based methods for identifying allergenic proteins encounter challenges when dealing with non-homologous data. Traditional machine learning approaches rely on manually extracted features, which lack important protein functional characteristics, including evolutionary information. Consequently, there is still considerable room for improvement in existing methods. In this study, we present PreAlgPro, a method for identifying allergenic proteins based on pre-trained protein language models and deep learning techniques. Specifically, we employed the ProtT5 model to extract protein embedding features, replacing the manual feature extraction step. Furthermore, we devised an Attention-CNN neural network architecture to identify potential features that contribute to the classification of allergenic proteins. The performance of our model was evaluated on four independent test sets, and the experimental results demonstrate that PreAlgPro surpasses existing state-of-the-art methods. Additionally, we collected allergenic protein samples to validate the robustness of the model and conducted an analysis of model interpretability.

A Deep Learning Approach based on Two-channel 3DCNN Networks to Predict the Risk of Femoral Fracture using CT Images

A Deep Learning Approach based on Two-channel 3DCNN Networks to Predict the Risk of Femoral Fracture using CT Images

Gender-specific factors of suicidal ideation among high school students in Yunnan province, China: A machine learning approach.

Suicidal ideation (SI) assumes a pivotal role in predicting suicidal behaviors. The incidence of SI among high (junior and senior) school students is significantly higher than that of other age groups. The aim of this study is to explore the gender differences in SI among high school students in Yunnan Province. A total of 6180 students in grades 7-12 in Yunnan province, China from May 2021 to May 2022 participated in this survey. Univariate analysis was employed to describe the influencing factors of male and female students' SI. Subsequently, data were stratified by gender. Adopting machine learning technique, including Least Absolute Shrinkage and Selection Operator (Lasso) and Boruta algorithm, and logistic regression model to estimate the direction and effect magnitude of the influencing factors. The prevalence of SI was significantly higher for females (31.34%) than males (16.73%). The logistic regression model was established using the variables screened by Boruta algorithm, indicated that anxiety, depression, suffering emotion abuse or emotion neglect in childhood, non-suicidal self-injury, evening chronotype are common risk factors for SI in male and female students. Notably, female students who exhibited aggressive behavior, have experienced bullying, and were in the junior high school learning stage were more likely to report SI than their male counterparts. Females showed more vulnerability to SI than males especially among females in junior high school, reporting aggressive behavior and bullying experiences. Tailored prevention strategies, informed by these gender-related distinctions, should be developed and implemented.

Adversarial attacks in signature verification: a deep learning approach

Handwritten signature recognition in forensic science is crucial for identity and document authentication. While serving as a legal representation of a person’s agreement or consent to the contents of a document, handwritten signatures de termine the authenticity of a document, identify forgeries, pinpoint the suspects and support other pieces of evidence like ink or document analysis. This work focuses on developing and evaluating a handwritten signature verification sys tem using a convolutional neural network (CNN) and emphasising the model’s efficacy using hand-crafted adversarial attacks. Initially, handwritten signatures have been collected from sixteen volunteers, each contributing ten samples, fol lowed by image normalization and augmentation to boost synthetic data samples and overcome the data scarcity. The proposed model achieved a testing accu racy of 91.35% using an 80:20 train-test split. Additionally, using the five-fold cross-validation, the model achieved a robust validation accuracy of nearly 98%. Finally, the introduction of manually constructed adversarial assaults on the sig nature images undermines the model’s accuracy, bringing the accuracy down to nearly 80%. This highlights the need to consider adversarial resilience while designing deep learning models for classification tasks. Exposing the model to real look-alike fake samples is critical while testing its robustness and refining the model using trial and error methods.

A machine learning approach to map the potential agroecological complexity in an indigenous community of Colombia

Agroecological systems are potential solutions to the environmental challenges of intensive agriculture. Indigenous communities, such as the Kamëntšá Biyá and Kamëntšá Inga from the Sibundoy Valley (SV) in Colombia, have their own ancient agroecological systems called chagras. However, they are threatened by population growth and expansion of intensive agriculture. Establishing new chagras or enhancing existing ones faces impediments such as the necessity for continuous monitoring and mapping of agroecological potential. However, this method is often costly and time consuming. To address this limitation, we created a digital map of the Biodiversity Management Coefficient (BMC) (as a proxy of agroecological potential) using Machine Learning. We utilized 15 environmental predictors and in-situ BMC data from 800 chagras to train an XGBoost model capable of predicting a multiclass BMC structure with 70% accuracy. This model was deployed across the study area to map the extent and spatial distribution of BMC classes, providing detailed information on potential areas for new agroecological chagras as well as areas unsuitable for this purpose. This map captured footprints of past and present disturbance events in the SV, revealing its usefulness for agroecological planning. We highlight the most significant predictors and their optimal values that trigger higher BMC status.