Search
110 articles for “Public model”
-
ML Model Comparison for Sentiment Analysis Across Diverse Datasets
Abstract: Analyzing sentiment is crucial for understanding public opinion on various issues in marketing, politics, and social sciences. This study compares the performance of seven different machine learning algorithms for sentiment classification, focusing on their effectiveness, accuracy, and complexity. The research is conducted on a pre-processed dataset with balanced text samples, utilizing feature extraction methods such as Term Frequency-Inverse Document Frequency (TF-IDF). The performance assessment criteria consist of accuracy, precision, recall, …
Published in Journal of Operating Systems Development & Trends · Vol. 12, Issue 2, 2025 · pp. 26–33 Read article
-
Cybersecurity of AI and IoT Integrated for Mechanical Industries
Abstract: By facilitating the concept of Industry 4.0, the intersection of artificial intelligence (AI) and the Internet of Things (IoT) has changed the mechanical industries. When combined, these technologies are advancing process optimization, predictive maintenance, real-time condition monitoring, and smarter automation. In order to give proactive system control and intelligent decision-making, AI algorithms mine large datasets generated via IoT devices for relevant patterns. In the meanwhile, IoT guarantees smooth communication between …
Published in Journal of Mechatronics and Automation · Vol. 12, Issue 2, 2025 · pp. 27–33 Read article
-
Neurodevelopmental Effects of Cell Tower Radiation in Children: A Longitudinal Study
Abstract: This study investigates the impact of radiation exposure from cell phone towers on the neurodevelopmental outcomes of children aged 0–5 years. A prospective cohort approach was employed to assess key developmental parameters, including Gross Motor Skills, Fine Motor Skills, and sleep disorders. Given the increasing presence of wireless communication infrastructure, understanding its potential effects on early childhood development is crucial for public health.To analyze the collected data, advanced machine learning …
Published in Research and Reviews : Journal of Computational Biology · Vol. 14, Issue 2, 2025 Read article
-
Unveiling Fairness: A Quest for Ethical Artificial Intelligence and Bias Mitigation
Abstract: Artificial intelligence (AI) systems have become ubiquitous across areas like finance, healthcare, employment, and criminal justice. However, they suffer from issues of unfair bias, lack of transparency, and broad ethical implications impacting vulnerable societal groups disproportionately. This paper reviews key challenges around AI ethics and bias while proposing data-driven guidelines mitigating such algorithmic harms through rigorous statistical testing, predictive modeling ensembles adjusting distortion vectors and AI audits by domain experts …
Published in International Journal of Information Security Engineering · Vol. 1, Issue 2, 2023 · pp. 28–31 Read article
-
Significant Advances in Cloud Computing in Information and Communications Technology
Abstract: The critical advances in information and communications technology (ICT) over the last half-century have led to the increasingly common vision that computing will one day become the 5th utility. This computing utility will provide the essential level of computing service considered basic to meet the everyday needs of the general public. To convey this vision, a number of computing models have been proposed, with the most recent being cloud computing. …
Published in Recent Trends in Parallel Computing · Vol. 11, Issue 3, 2024 · pp. 33–38 Read article
-
Epidemiology and transmission of infectious diseases study using Machine learning
Abstract: Infectious diseases remain a formidable global health challenge, characterized by rapid evolution and complex transmission dynamics that often outpace traditional epidemiological surveillance and response mechanisms. This study investigates the transformative potential of machine learning (ML) methodologies to enhance our understanding and prediction of infectious disease epidemiology and transmission. Leveraging diverse datasets—including clinical records, genomic sequences, environmental factors, social mobility data, and real-time digital footprints—we studies and presented various ML models …
Published in International Journal of Pathogens · Vol. 2, Issue 2, 2025 Read article
-
An Empirical Study of Hyperparameter Impact on Deep Learning Models for Cardamom Leaf Disease Classification
Abstract: Recent advancements in deep learning models like convolutional neural networks and self- attention mechanisms have achieved great success in the field of plant disease classification. This study investigates the efficacy of two pre-trained models, ConvNeXT-Tiny and Swin Transformer-Tiny, for leaf disease classification in cardamom using a publicly available dataset constituting three categories of leaves, namely Healthy, Colletotrichum Blight and Phyllosticta Leaf Spot. The effectiveness of the models highly depends on …
Published in Current Trends in Information Technology · Vol. 15, Issue 3, 2025 · pp. 48–60 Read article
-
A Hybrid Mathematical Model for Epidemic Outbreak Forecasting Using Machine Learning and Cloud Computing
Abstract: The increasing frequency of infectious disease outbreaks has emphasized the necessity for intelligent epidemic surveillance systems capable of predicting disease spread at an early stage. Conventional outbreak detection approaches rely heavily on delayed statistical reporting and manual monitoring techniques, resulting in reduced responsiveness during critical periods. This paper presents a mathematical predictive framework for epidemic outbreak detection using machine learning and cloud computing technologies. The proposed framework integrates the Susceptible–Infected–Recovered …
Published in Research & Reviews: Discrete Mathematical Structures · Vol. 13, Issue 2, 2026 · pp. 01–06 Read article
-
Optimizing Sampling Techniques Using Fuzzy Set Theory: A Comprehensive Approach
Abstract: Sampling is a critical process in statistics, used to estimate population parameters without needing to examine the entire population. Traditional sampling methods, such as simple random sampling, stratified sampling, and cluster sampling, face limitations when applied to complex or heterogeneous populations with imprecise boundaries. These methods often fail to accurately represent populations with overlapping characteristics or missing data, resulting in sampling bias and reduced accuracy. To address these challenges, this …
Published in Research & Reviews: Discrete Mathematical Structures · Vol. 12, Issue 1, 2025 · pp. 29–43 Read article
-
AI- based Prediction of Misinformation Virality Before Wide Dissemination using Attention-based Multi-modal
Abstract: Misinformation on social media has emerged as a critical global challenge, impacting public health, democratic institutions, and societal trust. While existing research has largely concentrated on detecting misinformation after it begins circulating, predicting its virality before wide dissemination remains an underexplored area, limited work addresses predicting its virality before wide dissemination. This paper presents a conceptual framework using attention-based multi-modal deep learning models to estimate the virality of misinformation posts …
Published in Journal of Mobile Computing, Communications & Mobile Networks · Vol. 12, Issue 3, 2025 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
-
Robust Classification of Traffic Signs Using Relief Feature Reduction Technique
Abstract: Ensuring driver safety amidst the rapid growth of global population and vehicular density continues to be a paramount challenge for transportation authorities and governments worldwide. With the rise of smart mobility solutions and autonomous driving technologies, the ability to detect, classify, and respond to traffic signs accurately has become critically important, especially under diverse and adverse environmental conditions such as rain, fog, or poor lighting. Reliable traffic sign recognition not …
Published in Journal of Artificial Intelligence Research & Advances · Vol. 12, Issue 3, 2025 · pp. 30–37 Read article
-
LLM Evolution: Secrets and Disadvantages
Abstract: The advancement of large language models (LLMs) has initiated a significant transformation in artificial intelligence, with substantial effects on fields including natural language processing, machine learning, and human-computer interaction. This research examines the diverse improvements in LLMs, emphasizing significant milestones from early models such as GPT-2 to contemporary state-of-the-art designs. The investigation highlights the novel training methodologies, such as unsupervised learning and transfer learning, which have markedly improved the capabilities …
Published in Journal of Web Engineering & Technology · Vol. 12, Issue 1, 2025 · pp. 25–36 Read article
-
Integrating Atmospheric Science: Understanding Greenhouse Gases, Aerosols, and Air Quality Dynamics
Abstract: Atmospheric science investigates the Earth’s atmospheric systems to understand their composition, dynamics, and the implications for climate, weather, and air quality. This review explores five primary areas within the field: atmospheric composition, atmospheric modeling, remote sensing, air pollution, and boundary layer dynamics, highlighting critical challenges and advancements. Rising levels of greenhouse gases (GHGs), including carbon dioxide and methane, continue to drive global warming, while feedback mechanisms—like cloud interactions and surface …
Published in International Journal of Atmosphere · Vol. 1, Issue 1, 2024 · pp. 32–35 Read article
-
Enhancing Glaucoma Diagnosis with Deep Learning: A Study Using ResNet-50 and DenseNet-121
Abstract: Glaucoma is a leading cause of irreversible blindness worldwide, mainly resulting from progressive optic nerve damage, often related to elevated intraocular pressure. Early detection is essential to prevent vision loss, but traditional diagnostic methods rely on specialized equipment and trained professionals, making large-scale screening difficult. This study uses a publicly available fundus imaging dataset to explore the effectiveness of deep learning models for glaucoma detection. These datasets provide medical images, …
Published in International Journal of Brain Sciences · Vol. 2, Issue 2, 2025 · pp. 9–18 Read article
-
Optimizing Urban Mobility with AI-Based Traffic Management
Abstract: Urban mobility is a pressing concern in modern cities, plagued by issues like traffic congestion and pollution. This research involves, "Optimising Urban Mobility with AI-based Traffic Management", delves into the potential of Artificial Intelligence (AI) to revolutionize traffic management. Focusing on AI algorithms, data analytics, and sensor technologies, the research aims to enhance traffic flow, reduce congestion, and improve overall efficiency. Through statistical analysis and simulations, the research evaluates the …
Published in Trends in Transport Engineering and Applications · Vol. 12, Issue 3, 2025 · pp. 34–43 Read article
-
Multimodal Data Fusion with Hybrid Machine Learning for Enhanced Prediction of Li-Ion Battery Remaining Useful Life and State of Charge
Abstract: Lithium-ion battery materials used in modern energy storage systems are required to exhibit high reliability, safety, and long lifecycle performance under varying operational and environmental conditions. Accurate prediction of Remaining Useful Life (RUL) and State of Charge (SoC) is therefore essential for understanding material degradation behavior, improving manufacturing quality, and enabling effective lifecycle management. However, nonlinear electrochemical aging, load variability, and thermal uncertainty significantly complicate accurate estimation of these parameters. …
Published in International Journal of Electro-Mechanics and Material Behaviour · Vol. 4, Issue 1, 2026 · pp. 1–5 Read article
-
Electromagnetic Field Effects on Biological Systems and Safety Evaluation of Microwave Exposure
Abstract: The increasing use of wireless communication systems, radar technologies, and microwave- based devices has raised growing concerns regarding the potential biological effects of electromagnetic fields (EMFs) on living systems. This review paper investigates the interaction between electromagnetic field exposure, particularly in the microwave frequency range, and biological tissues, with a focus on safety implications and risk assessment. Microwave radiation, commonly emitted from mobile phones, Wi-Fi routers, and industrial equipment, can …
Published in Journal of Microwave Engineering and Technologies · Vol. 13, Issue 1, 2026 · pp. 26–33 Read article
-
A study on IoT and AI for Predictive Modeling and Control of Infectious Disease Transmission
Abstract: Background: The global response to novel and recurring infectious diseases is frequently hindered by surveillance systems that are slow, siloed, and reactive. Traditional epidemiology relies on retrospective analysis of clinical reports, often missing the critical early phase of autocatalytic spread. The urgency of modern public health necessitates a shift toward real-time, predictive intelligence. Methods: This study investigates the development and deployment of a synergistic paradigm integrating the Internet of Things …
Published in International Journal of Pathogens · Vol. 2, Issue 2, 2025 Read article
-
Crime Prediction and Criminal Identification System Using Machine Learning
Abstract: Advanced machine learning and data analytics-driven crime prediction and criminal identification systems have become game-changing instruments for contemporary law enforcement. Utilizing past crime statistics, surveillance footage, and additional resources, these systems forecast criminal activity, manage resources efficiently, and improve investigation capacities. With an emphasis on their importance in enhancing public safety and lowering crime rates, this paper presents an overview of criminal identification and prediction systems. Examining the technologies and …
Published in International Journal of Electronics Automation · Vol. 2, Issue 1, 2024 · pp. 28–34 Read article