Search
41 articles for “SHAP interpretability”
-
Predicting Student Placement Readiness: A Machine Learning Approach Using Coding Activities and Multi-Dimensional Performance Indicators
Abstract: In the modern information-driven academic world, identifying student employability and placement preparedness has predicted. be made a part and parcel of academic planning and career. development. This study provides a machine learning-based. structure to evaluate and forecast student placement pre-paredness by combining various performance aspects-academic achieve- ment, coding activity, aptitude and behavioral engage-ment metrics. Multi-source was gathered and preprocessed in the study. student information, such as student records (CGPA, attendance), …
Published in International Journal of Education Sciences · Vol. 3, Issue 2, 2026 Read article
-
ML-Based Predictive Modeling of Mechanical Properties in 3D-Printed Polymer Composites for IoT Applications
Abstract: This study aims to develop an interpretable and high-accuracy machine learning framework for predicting the mechanical properties of 3D-printed fiber-reinforced polymer composites, with a focus on structure–property correlations relevant to polymer processing and functional performance. Composite specimens based on PLA and ABS matrices were fabricated using FDM with varying weight fractions (5–20 wt%) of carbon and glass fibers. Standardized mechanical testing (ASTM D638, D256, D790) was performed to evaluate tensile …
Published in Journal of Polymer & Composites · Vol. 13, Issue 4, 2025 · pp. 61–78 Read article
-
Early Alzheimer's Disease Detection Using Deep Ensemble Learning and MRI Image Analysis
Abstract: Early detection of Alzheimer's disease (AD) is crucial to slowing cognitive decline and enabling timely clinical interventions. Traditional diagnostic methods, including cognitive tests and single-model classifiers, have limited sensitivity during early stages of the disease. This paper presents a deep ensemble learning approach that integrates multiple convolutional neural networks (CNNs) for accurate Alzheimer's disease detection using structural Magnetic Resonance Imaging (MRI) data. The proposed framework utilizes ResNet50, VGG16, and DenseNet121 …
Published in Research and Reviews : Journal of Computational Biology · Vol. 15, Issue 1, 2026 Read article
-
Ethical and Responsible AI: A Comprehensive Review of Principles, Methods, and Tools
Abstract: Quick development of artificial intelligence (AI) has revolutionized a number of industries, including healthcare, banking, and government, by providing creative answers to challenging issues. However, there are serious ethical issues with growing integration of AI into crucial decision-making processes, including prejudice, a lack of transparency, abuses of data privacy, and accountability gaps. A systematic strategy that incorporates technical solutions, legal frameworks, and ethical standards is needed to address these issues. …
Published in International Journal of Information Security Engineering · Vol. 4, Issue 1, 2026 · pp. 23–34 Read article
-
Early Alzheimer’s Disease Prediction Using Vision Transformers and Attention-Guided MRI Analysis
Abstract: Alzheimer’s Disease (AD) continues to be a major global health concern, with early detection being crucial for effective intervention. While conventional machine learning and convolutional neural network (CNN) approaches have made notable progress in automated AD diagnosis using MRI data, they often struggle with capturing long-range dependencies and maintaining spatial contextual awareness. In this research, we propose a novel framework using Vision Transformers (ViTs) for early Alzheimer’s prediction from 3D …
Published in Research and Reviews: A Journal of Neuroscience · Vol. 16, Issue 1, 2026 · pp. 30–40 Read article
-
Machine Learning Assisted Design and Analysis of Polymer Composite Materials for Sustainable Renewable Energy Systems
Abstract: Accurate prediction and optimization of polymer composite properties is of paramount importance in the design of these lightweight, durable, and sustainable materials within renewable energy technologies. This work will provide a holistic machine learning-assisted framework that unites materials informatics with domain-specific features and state-of-the-art ML methodologies in the prediction of the mechanical properties of polymer composites, such as tensile strength. This includes embedding several ensemble models, including Random Forest and …
Published in Journal of Polymer & Composites · Vol. 14, Issue 3, 2026 · pp. 391–402 Read article
-
AI-Based Early Diagnosis & Prevention of Diabetes
Abstract: The worldwide burden of Diabetes Mellitus, especially Type 2 diabetes (T2D) has escalated to a critical level. Early detection of diabetes is essential to reduce long‑term complications and healthcare costs. This study explores the use of artificial intelligence (AI) techniques to improve the early diagnosis and prevention of diabetes. We developed an AI model using the Random Forest algorithm, the model predicts diabetes risk based on clinical and lifestyle variables …
Published in Research & Reviews: A Journal of Bioinformatics · Vol. 13, Issue 2, 2026 Read article
-
Structure–Property Modeling of Cement-Based Multi-Component Composites Using Ensemble Machine Learning and Explainable Feature Attribution
Abstract: Accurate prediction of compressive strength is central to structure–property optimization, quality control, and sustainability-driven design in cement-based composite materials. Cementitious systems represent heterogeneous multi-phase composites composed of reactive binder matrices and dispersed aggregate phases, whose macroscopic mechanical performance emerges from complex nonlinear interactions among constituents and curing-dependent microstructural evolution. This study develops a data-driven structure–property modeling framework to quantify the nonlinear dependence of compressive strength on multi-component composite composition and …
Published in Journal of Polymer & Composites · Vol. 14, Issue 3, 2026 · pp. 112–131 Read article
-
A Lightweight Cost-Sensitive Explainable Ensemble Framework for Early Heart Disease Risk Prediction
Abstract: Cardiovascular disease is still one of the leading causes of death, and hence, the early prediction of risk is a very important task in preventive medicine. Although recent studies have shown encouraging results in the application of machine learning algorithms to the prediction of heart disease, it has been noticed that most of the algorithms are more concerned with accuracy-driven optimization than the concerns of safety and false negatives. In …
Published in International Journal of Bioinformatics and Computational Biology · Vol. 4, Issue 2, 2026 Read article
-
Predicting Dielectric Constants of Polymers Using Molecular Structural Descriptors and Explainable Machine Learning: A Data-Driven Approach
Abstract: Accurate prediction of dielectric constants in polymeric materials is fundamental to the rational design of advanced electronic components, energy storage capacitors, flexible substrates, and high-frequency communication circuits. Conventional approaches to identifying suitable polymer dielectrics rely on extensive experimental synthesis and characterisation, which are both time-consuming and resource-intensive. In this work, an explainable machine learning framework is developed to predict the dielectric constant of polymers directly from molecular structural descriptors derived …
Published in Journal of Polymer & Composites · Vol. 14, Issue 3, 2026 · pp. 297–304 Read article
-
Real-Time Deepfake Detection in Video Conferencing Systems
Abstract: Deepfake technology presents non-exemplary threats to video conferencing platforms, enabling advanced fraud, impression and misinformation campaigns worth billions annually. Current detection methods either exhibit latencies exceeding 100ms or rely on server-side cloud processing, raising privacy concerns. This paper presents DeepConfGuard, a lightweight hybrid architecture combining MobileNetV2 for spatial feature extraction, a bidirectional LSTM with attention for temporal modelling, and EfficientNetV2 for refinement. It reaches 94.8% accuracy with 85 ms end‑to‑end …
Published in International Journal of Electronics Automation · Vol. 4, Issue 2, 2026 Read article
-
Passive Digital Phenotyping for Longitudinal Burnout and Occupational Mental Health Surveillance: A Transformer-Based Explainable Deep Learning Approach Using Smartphone Behavioral Streams
Abstract: Occupational burnout constitutes a pervasive yet chronically under-surveilled public health threat, its insidious temporal evolution rendering episodic self-report instruments structurally inadequate for early detection. This paper introduces BurnoutSense, a passive digital phenotyping framework that continuously harvests eight heterogeneous smartphone behavioral data streams encompassing application usage ecology, communication metadata, geospatial mobility, screen interaction dynamics, inferred sleep rhythmicity, keystroke kinematics, ambient noise exposure, and battery/charging cadence to construct individualized multivariate behavioral signatures …
Published in International Journal of Behavioral Sciences · Vol. 3, Issue 2, 2026 · pp. 44–53 Read article
-
Neuro-Symbolic Agentic AI for Autonomous Scientific Discovery: Integrating Deep Reinforcement Learning, Quantum Simulation, and XAI-Audited LLM Hypothesis Generation in Drug Target Identification
Abstract: The exponential growth of multi-omics data and the increasing complexity of disease-associated protein interactomes have rendered conventional drug target identification pipelines computationally and epistemologically inadequate. This paper presents the Neuro-Symbolic Agentic AI for Scientific Discovery (NS-AASD) framework, a unified architecture that cohesively integrates deep reinforcement learning (DRL) exploration strategies, variational quantum simulation (VQS) of protein conformational dynamics, and XAI-audited large language model (LLM) hypothesis generation within an autonomous scientific discovery …
Published in Research and Reviews : Journal of Computational Biology · Vol. 15, Issue 2, 2026 Read article
-
Explainable Machine Learning Integrated with Polymer-Based Diagnostic Technologies for Liver Health Classification
Abstract: Early and reliable assessment of liver health is essential for timely treatment, yet most machine-learning approaches face limitations such as class imbalance and low clinical interpretability. This study proposes a polymer-integrated, explainable machine-learning framework that combines SMOTE-based data balancing, Logistic Regression, and XAI techniques (SHAP and LIME) for transparent liver-health classification. In addition to ML modelling, the study emphasizes the emerging role of polymer-based biosensors, microfluidic polymer chips, polymer nanomaterials, …
Published in Journal of Polymer & Composites · Vol. 14, Issue 3, 2026 · pp. 631–643 Read article
-
A Study on Recent Trends in Chemical Sensors for Detecting Toxic Materials
Abstract: Poisonous materials, such as mutagenic, carcinogenic, and poisonous compounds, are widely produced as a result of industrial development. Such materials continue to be hazardous to human health despite stringent management and control procedures. As a result, practical chemical sensors—such as optical, electrochemical, nanomaterial-based, and biological system-based sensors—are needed for the monitoring of dangerous chemicals. For the detection of harmful compounds, numerous new and existing chemical sensors are being created, along …
Published in Journal of Modern Chemistry & Chemical Technology · Vol. 16, Issue 3, 2025 · pp. 26–35 Read article
-
A SHAP - Enhanced Voice-Based Conversational Agent for Agriculture Using BERT
Abstract: The integration of advanced artificial intelligence technologies into modern agriculture has become increasingly important for narrowing the persistent knowledge gap faced by farmers, especially in regions with limited access to expert advisory services. While state-of-the-art language models such as BERT (Bidirectional Encoder Representations from Transformers) demonstrate exceptional performance in understanding and generating natural language, their opaque “black-box” nature often limits user confidence, trust, and widespread adoption. Farmers may hesitate to …
Published in Journal of Computer Technology & Applications · Vol. 17, Issue 1, 2026 Read article
-
Topology and Geometry in Data Science: Persistent Homology and Beyond
Abstract: In recent years, the interplay between topology, geometry, and data science has gained substantial momentum, offering powerful frameworks to analyze and interpret complex datasets. Traditional statistical and machine learning methods often rely on linear or metric- based assumptions, which may fail to capture the intrinsic structure of high-dimensional or nonlinear data. In contrast, topological and geometric methods provide shape-oriented, scale- invariant tools that focus on the continuity, connectivity, and global …
Published in Recent Trends in Mathematics · Vol. 1, Issue 2, 2024 · pp. 21–27 Read article
-
Sanskruti AI : Rediscovering Indian Culture Using Artificial Intelligence
Abstract: Away from old ways, many young people in India now find customs hard to reach, losing touch with sacred texts, local traditions, and deeper beliefs. Into this space steps Sanskruti AI - an intelligent tool using sound, text, and vision to bring culture closer, tailored to how today & users think and feel. Instead of flat translations, it unpacks verses from Sanskrit with layers: word-for-word sense, background context, inner meaning. …
Published in OmniScience: A Multi-disciplinary Journal · Vol. 16, Issue 2, 2026 Read article
-
Explainable GeoAI-Based Multi-Temporal Remote Sensing Framework for Early Detection of Climate-Induced Land Cover Transformation
Abstract: Climate change has emerged as one of the primary drivers of rapid land cover transformation, affecting ecosystems, agricultural productivity, biodiversity, and regional sustainability. Traditional remote sensing approaches often face challenges in detecting subtle and early-stage land cover changes due to limitations in temporal analysis and model interpretability. This study proposes an Explainable GeoAI-based multi-temporal remote sensing framework for the early detection of climate-induced land cover transformation using multi-source satellite imagery …
Published in International Journal of Satellite Remote Sensing · Vol. 4, Issue 2, 2026 Read article
-
The Role of Optimization and Probability in Shaping Artificial Intelligence
Abstract: This study discusses the basic roles of optimization algorithms and the theory of probability in the process of evolution and development of Artificial intelligence (AI). First, we introduce the role played by the next generation of leading-edge optimization algorithms developed since gradient descent to evolutionary strategies with respect to the learning of high-level AI models and how to enable them to learn to effectively explore high-dimensional parameter spaces. At the …
Published in Journal of Computer Technology & Applications · Vol. 16, Issue 2, 2025 · pp. 123–128 Read article