Open Access

ARTICLE

EMA-GhostConv YOLOv8 Based Enhanced Vehicle Detection in Intelligent Transportation Applications

A. S. M. Masudur Rahman¹, Muhammad Zunair Zamir¹, Syed Sajid Ullah^2,*, Salman Khan², Maria Saman¹, Naqash Bahadar¹

Journal on Artificial Intelligence, Vol.8, pp. 119-136, 2026, DOI:10.32604/jai.2026.076274 - 24 February 2026
Abstract Vehicle detection plays a pivotal role in autonomous driving, traffic monitoring, and intelligent surveillance systems. While YOLOv8 offers strong real-time performance, its detection accuracy is often limited by insufficient feature stability and suboptimal multi-scale feature fusion in complex scenes. To address these issues, we propose an enhanced YOLOv8 framework that retains the original backbone and detection head for efficiency while introducing targeted improvements to the neck architecture. Specifically, the model incorporates an Exponential Moving Average (EMA) feature layer to stabilize learning through temporally smoothed feature representations, which reduces noise and enhances generalization, and integrates GhostConv… More >

View

86

Download

30

Open Access

ARTICLE

Fine Tuned QA Models for Java Programming

Jeevan Pralhad Tonde^*, Satish Sankaye

Journal on Artificial Intelligence, Vol.8, pp. 107-118, 2026, DOI:10.32604/jai.2026.075857 - 13 February 2026
（This article belongs to the Special Issue: Advances in Artificial Intelligence for Engineering and Sciences)
Abstract As education continues to evolve alongside artificial intelligence, there is growing interest in how large language models (LLMs) can support more personalized and intelligent learning experiences. This study focuses on building a domain-specific question answering (QA) system tailored to computer science education, with a particular emphasis on Java programming. While transformer-based models such as BERT, RoBERTa, and DistilBERT have demonstrated strong performance on general-purpose datasets like SQuAD, they often struggle with technical educational content where annotated data is scarce. To address this challenge, we developed a custom dataset, JavaFactoidQA, consisting of 1000 fact-based question–answer pairs… More >

View

284

Download

65

Open Access

ARTICLE

A Novel Math-Inspired Metaheuristic Algorithm for Retinal Vessel Segmentation: Quadratic Interpolation Optimization (QIO) Algorithm

Mehmet Bahadır Çetinkaya^1,*, Sevim Adige^2,3

Journal on Artificial Intelligence, Vol.8, pp. 89-106, 2026, DOI:10.32604/jai.2026.074459 - 13 February 2026
Abstract Math-inspired metaheuristic algorithms stand out with their simple algorithm structures and the inclusion of fewer control parameters. In this study, the recently proposed math-inspired Quadratic Interpolation Optimization (QIO) algorithm was improved as a clustering-based algorithm and then applied to retinal vessel segmentation. Afterwards, its performance was compared with the math-inspired Sine Cosine Algorithm (SCA) and Arithmetic Optimization Algorithm (AOA), which have been frequently applied to engineering problems. First, the performance of the QIO algorithm was analyzed in terms of sensitivity (Se), specificity (Sp), accuracy (Acc), and precision (Prec). An average success rate of approximately 70% or higher… More >

View

224

Download

85

Open Access

ARTICLE

Machine Learning Model Development for Classification of Audio Commands

Kaveh Heidary^*

Journal on Artificial Intelligence, Vol.8, pp. 65-87, 2026, DOI:10.32604/jai.2026.072857 - 13 February 2026
Abstract This paper presents a comprehensive investigation into the development and evaluation of Convolutional Neural Network (CNN) models for limited-vocabulary spoken word classification, a fundamental component of many voice-controlled systems. Two distinct CNN architectures are examined: a timeseries 1D CNN that operates directly on the temporal waveform samples of the audio signal, and a 2D CNN that leverages the richer time–frequency representation provided by spectrograms. The study systematically analyzes the influence of key architectural and training parameters, including the number of CNN layers, convolution kernel sizes, and the dimensionality of fully connected layers, on classification accuracy.… More >

View

199

Download

60

Open Access

ARTICLE

Optimized Energy Storage Dispatch Strategy Considering Reliability and Economy

Jiale Hu, Fan Chen^*, Yue Yang, Man Wang

Journal on Artificial Intelligence, Vol.8, pp. 51-64, 2026, DOI:10.32604/jai.2026.075257 - 22 January 2026
Abstract To enhance the operational performance of energy storage systems (ESS), this paper proposes an optimal dispatch strategy that jointly considers reliability and economic efficiency. First, we formulate a cost-minimization model that includes ESS dispatch costs, wind and photovoltaic (PV) curtailment costs, and load loss costs, while explicitly enforcing power supply reliability constraints. Next, we develop a comprehensive evaluation indicator system that integrates reliability, economic performance, renewable-energy utilization, and ESS technical indicators, thereby addressing the limitations of single-indicator assessments. Finally, a case study using real data from a region in China shows that the proposed strategy More >

View

191

Download

98

Open Access

ARTICLE

DWaste: Greener AI for Waste Sorting Using Mobile and Edge Devices

Suman Kunwar^*

Journal on Artificial Intelligence, Vol.8, pp. 39-49, 2026, DOI:10.32604/jai.2026.076674 - 22 January 2026
Abstract The rise in convenience packaging has led to generation of enormous waste, making efficient waste sorting crucial for sustainable waste management. To address this, we developed DWaste, a computer vision-powered platform designed for real-time waste sorting on resource-constrained smartphones and edge devices, including offline functionality. We benchmarked various image classification models (EfficientNetV2S/M, ResNet50/101, MobileNet) and object detection (YOLOv8n, YOLOv11n) including our purposed YOLOv8n-CBAM model using our annotated dataset designed for recycling. We found a clear trade-off between accuracy and resource consumption: the best classifier, EfficientNetV2S, achieved high accuracy (≈96%) but suffered from high latency More >

View

427

Download

112

Open Access

ARTICLE

Enhanced COVID-19 and Viral Pneumonia Classification Using Customized EfficientNet-B0: A Comparative Analysis with VGG16 and ResNet50

Williams Kyei^*, Chunyong Yin, Kelvin Amos Nicodemas, Khagendra Darlami

Journal on Artificial Intelligence, Vol.8, pp. 19-38, 2026, DOI:10.32604/jai.2026.074988 - 20 January 2026
Abstract The COVID-19 pandemic has underscored the need for rapid and accurate diagnostic tools to differentiate respiratory infections from normal cases using chest X-rays (CXRs). Manual interpretation of CXRs is time-consuming and prone to errors, particularly in distinguishing COVID-19 from viral pneumonia. This research addresses these challenges by proposing a customized EfficientNet-B0 model for ternary classification (COVID-19, Viral Pneumonia, Normal) on the COVID-19 Radiography Database. Employing transfer learning with architectural modifications, including a tailored classification head and regularization techniques, the model achieves superior performance. Evaluated via accuracy, F1-score (macro-averaged), AUROC (macro-averaged), precision (macro-averaged), recall (macro-averaged), inference… More >

View

260

Download

96

Open Access

ARTICLE

Building Regulatory Confidence with Human-in-the-Loop AI in Paperless GMP Validation

Manaliben Amin^*

Journal on Artificial Intelligence, Vol.8, pp. 1-18, 2026, DOI:10.32604/jai.2026.073895 - 07 January 2026
（This article belongs to the Special Issue: Advances in Artificial Intelligence for Engineering and Sciences)
Abstract Artificial intelligence (AI) is steadily making its way into pharmaceutical validation, where it promises faster documentation, smarter testing strategies, and better handling of deviations. These gains are attractive, but in a regulated environment speed is never enough. Regulators want assurance that every system is reliable, that decisions are explainable, and that human accountability remains central. This paper sets out a Human-in-the-Loop (HITL) AI approach for Computer System Validation (CSV) and Computer Software Assurance (CSA). It relies on explainable AI (XAI) tools but keeps structured human review in place, so automation can be used without creating… More >

View

424

Download

183

Open Access

REVIEW

A Comprehensive Overview and Comparative Analysis on Deep Learning Models

Farhad Mortezapour Shiri^*, Thinagaran Perumal, Norwati Mustapha, Raihani Mohamed

Journal on Artificial Intelligence, Vol.6, pp. 301-360, 2024, DOI:10.32604/jai.2024.054314
Abstract Deep learning (DL) has emerged as a powerful subset of machine learning (ML) and artificial intelligence (AI), outperforming traditional ML methods, especially in handling unstructured and large datasets. Its impact spans across various domains, including speech recognition, healthcare, autonomous vehicles, cybersecurity, predictive analytics, and more. However, the complexity and dynamic nature of real-world problems present challenges in designing effective deep learning models. Consequently, several deep learning models have been developed to address different problems and applications. In this article, we conduct a comprehensive survey of various deep learning models, including Convolutional Neural Network (CNN), Recurrent… More >

View

11504

Download

2876

Open Access

ARTICLE

Detection of Student Engagement in E-Learning Environments Using EfficientnetV2-L Together with RNN-Based Models

Farhad Mortezapour Shiri^1,*, Ehsan Ahmadi², Mohammadreza Rezaee¹, Thinagaran Perumal¹

Journal on Artificial Intelligence, Vol.6, pp. 85-103, 2024, DOI:10.32604/jai.2024.048911
Abstract Automatic detection of student engagement levels from videos, which is a spatio-temporal classification problem is crucial for enhancing the quality of online education. This paper addresses this challenge by proposing four novel hybrid end-to-end deep learning models designed for the automatic detection of student engagement levels in e-learning videos. The evaluation of these models utilizes the DAiSEE dataset, a public repository capturing student affective states in e-learning scenarios. The initial model integrates EfficientNetV2-L with Gated Recurrent Unit (GRU) and attains an accuracy of 61.45%. Subsequently, the second model combines EfficientNetV2-L with bidirectional GRU (Bi-GRU), yielding More >

View

8728

Download

1723

Open Access

ARTICLE

Hybrid Task Scheduling Algorithm for Makespan Optimisation in Cloud Computing: A Performance Evaluation

Abdulrahman M. Abdulghani^*

Journal on Artificial Intelligence, Vol.6, pp. 241-259, 2024, DOI:10.32604/jai.2024.056259
Abstract Cloud computing has rapidly evolved into a critical technology, seamlessly integrating into various aspects of daily life. As user demand for cloud services continues to surge, the need for efficient virtualization and resource management becomes paramount. At the core of this efficiency lies task scheduling, a complex process that determines how tasks are allocated and executed across cloud resources. While extensive research has been conducted in the area of task scheduling, optimizing multiple objectives simultaneously remains a significant challenge due to the NP (Non-deterministic Polynomial) Complete nature of the problem. This study aims to address… More >

View

8637

Download

1179

Open Access

ARTICLE

A Unified U-Net-Vision Mamba Model with Hierarchical Bottleneck Attention for Detection of Tomato Leaf Diseases

Geoffry Mutiso^*, John Ndia

Journal on Artificial Intelligence, Vol.7, pp. 275-288, 2025, DOI:10.32604/jai.2025.069768
（This article belongs to the Special Issue: Advances in Artificial Intelligence for Engineering and Sciences)
Abstract Tomato leaf diseases significantly reduce crop yield; therefore, early and accurate disease detection is required. Traditional detection methods are laborious and error-prone, particularly in large-scale farms, whereas existing hybrid deep learning models often face computational inefficiencies and poor generalization over diverse environmental and disease conditions. This study presents a unified U-Net-Vision Mamba Model with Hierarchical Bottleneck Attention Mechanism (U-net-Vim-HBAM), which integrates U-Net’s high-resolution segmentation, Vision Mamba’s efficient contextual processing, and a Hierarchical Bottleneck Attention Mechanism to address the challenges of disease detection accuracy, computational complexity, and efficiency in existing models. The model was trained on More >

View

7950

Download

7263

Open Access

ARTICLE

Innovative Concrete Cube Failure Mode Detection Using Image Processing and Machine Learning for Sustainable Construction Practices

Meenakshi S. Patil^1,*, Rajesh B. Ghongade², Hemant B. Dhonde³

Journal on Artificial Intelligence, Vol.7, pp. 289-300, 2025, DOI:10.32604/jai.2025.069500
Abstract This study seeks to establish a novel, semi-automatic system that utilizes Industry 4.0 principles to effectively determine both acceptable and rejectable concrete cubes with regard to their failure modes, significantly contributing to the dependability of concrete quality evaluations. The study utilizes image processing and machine learning (ML) methods, namely object detection models such as YOLOv8 and Convolutional Neural Networks (CNNs), to evaluate images of concrete cubes. These models are trained and validated on an extensive database of annotated images from real-world and laboratory conditions. Preliminary results indicate a good performance in the classification of concrete More >

View

5528

Download

2744

Open Access

REVIEW

Life Cycle-Based Sustainability Assessment and Circularity Mapping for Packaging Materials: Integrating Artificial Intelligence

Ragava Raja R^1,2,*, Girish Khanna R³

Journal on Artificial Intelligence, Vol.7, pp. 301-327, 2025, DOI:10.32604/jai.2025.069693
Abstract Packaging materials are indispensable in modern industries but also significantly contribute to environmental degradation, resource consumption, and waste generation. This systematic review critically assesses the integration of artificial intelligence (AI), life cycle sustainability assessment (LCSA) following ISO 14040 standards, and circularity mapping to overcome sustainability barriers in packaging. The study identifies environmental, economic, and social hotspots across the life cycle stages of packaging materials by examining real-world case studies such as Coca-Cola’s adoption of recycled PET bottles and Unilever’s commitment to 100% recyclable plastic. AI technologies highlight transformative tools for optimising resource allocation, enhancing waste… More >

View

3523

Download

2339

Open Access

REVIEW

Natural Language Processing with Transformer-Based Models: A Meta-Analysis

Charles Munyao^*, John Ndia

Journal on Artificial Intelligence, Vol.7, pp. 329-346, 2025, DOI:10.32604/jai.2025.069226
Abstract The natural language processing (NLP) domain has witnessed significant advancements with the emergence of transformer-based models, which have reshaped the text understanding and generation landscape. While their capabilities are well recognized, there remains a limited systematic synthesis of how these models perform across tasks, scale efficiently, adapt to domains, and address ethical challenges. Therefore, the aim of this paper was to analyze the performance of transformer-based models across various NLP tasks, their scalability, domain adaptation, and the ethical implications of such models. This meta-analysis paper synthesizes findings from 25 peer-reviewed studies on NLP transformer-based models,… More >

View

3462

Download

2190

Open Access

ARTICLE

A Deep Learning Model for Insurance Claims Predictions

Umar Isa Abdulkadir^*, Anil Fernando^*

Journal on Artificial Intelligence, Vol.6, pp. 71-83, 2024, DOI:10.32604/jai.2024.045332
Abstract One of the significant issues the insurance industry faces is its ability to predict future claims related to individual policyholders. As risk varies from one policyholder to another, the industry has faced the challenge of using various risk factors to accurately predict the likelihood of claims by policyholders using historical data. Traditional machine-learning models that use neural networks are recognized as exceptional algorithms with predictive capabilities. This study aims to develop a deep learning model using sequential deep regression techniques for insurance claim prediction using historical data obtained from Kaggle with 1339 cases and eight… More >

View

3370

Download

2787

Open Access

ARTICLE

A Performance Analysis of Machine Learning Techniques for Credit Card Fraud Detection

Ayesha Aslam¹, Adil Hussain^2,*

Journal on Artificial Intelligence, Vol.6, pp. 1-21, 2024, DOI:10.32604/jai.2024.047226
Abstract With the increased accessibility of global trade information, transaction fraud has become a major worry in global banking and commerce security. The incidence and magnitude of transaction fraud are increasing daily, resulting in significant financial losses for both customers and financial professionals. With improvements in data mining and machine learning in computer science, the capacity to detect transaction fraud is becoming increasingly attainable. The primary goal of this research is to undertake a comparative examination of cutting-edge machine-learning algorithms developed to detect credit card fraud. The research looks at the efficacy of these machine learning… More >

View

3323

Download

2033

Like

1

Open Access

REVIEW

Enhancing Security in Large Language Models: A Comprehensive Review of Prompt Injection Attacks and Defenses

Eleena Sarah Mathew^*

Journal on Artificial Intelligence, Vol.7, pp. 347-363, 2025, DOI:10.32604/jai.2025.069841
Abstract This review paper explores advanced methods to prompt Large Language Models (LLMs) into generating objectionable or unintended behaviors through adversarial prompt injection attacks. We examine a series of novel projects like HOUYI, Robustly Aligned LLM (RA-LLM), StruQ, and Virtual Prompt Injection that compel LLMs to produce affirmative responses to harmful queries. Several new benchmarks, such as PromptBench, AdvBench, AttackEval, INJECAGENT, and RobustnessSuite, have been created to evaluate the performance and resilience of LLMs against these adversarial attacks. Results show significant success rates in misleading models like Vicuna-7B, LLaMA-2-7B-Chat, GPT-3.5, and GPT-4. The review highlights limitations… More >

View

3057

Download

897