CBi-BERT: Efficient Skin Disease Image Segmentation Using Patch-Based Deep Feature Mapping and BERT-Based Attention Mechanism

Summi Goindi; Khushal Thakur; Divneet Singh Kapoor

doi:https://doi.org/10.54216/JISIoT.170117

Journal of Cognitive Human-Computer Interaction | 2025

PhyGital Fit: An AI-Driven Virtual Footwear Solution Integrating Generative AI, AR and Foot Morphology Analysis for Personalized Fit

Rapid development has been seen in Artificial Intel license (AI), which has transformed the retail industry, including online shopping. Selecting the right size of shoes that varies with brands and design is one of the biggest challenges in the E-Commerce footwear industry. This research focuses on AI Powered virtual shoe fitting system using Lens Studio Software. In this, customers are able to try shoes virtually through augmented reality and customized 3D foot models. This innovation solves size issues and benefits online footwear retailers, resulting in greater customer satisfaction. The role of Lens Studio software includes the creation of customized shoes, 3D shoes models, lenses, and size accuracy with the foot tracking mechanism.

groups

Abhimanyu Sangale mail -

Nikita Bhawar mail -

Rutuja Gholap mail -

Bhoomi Raut mail -

Kanchan Suryavanshi mail

link https://doi.org/10.54216/JCHCI.090201

Volume & Issue

Vol. Volume 9 / Iss. Issue 2

Details open_in_new

Journal of Cognitive Human-Computer Interaction | 2025

Climate Change and Sustainability: A Review

Climate change, driven by human activities like burning fossil fuels, deforestation, and industrial agriculture, is one of the most urgent global challenges. The rise in greenhouse gases (GHGs), such as carbon dioxide (CO₂), methane (CH₄), and nitrous oxide (N₂O), is contributing to global warming, sea level rise, and extreme weather events, with developing nations being particularly vulnerable. To address this, sustainability has become a key focus, involving the need to meet present demands without compromising the ability of future generations to meet theirs. Mitigation strategies include reducing emissions, transitioning to renewable energy sources like solar, wind, and hydropower, improving energy efficiency, and using reforestation to absorb carbon dioxide. Adaptation efforts, such as drought-resistant crops and resilient infrastructure, help communities cope with the impacts of climate change. The circular economy, which emphasizes resource efficiency, waste reduction, and recycling, further supports environmental sustainability. Governments, corporations, and individuals must also prioritize social justice, ensuring that underserved areas most affected by climate change receive the necessary support. Through collective action, we can work towards a sustainable future for all.

groups

Balaji Vijayan Venkateswarulu mail -

Ankitha K. mail -

Chandana L. mail -

Likitha M. mail

link https://doi.org/10.54216/JCHCI.090202

Volume & Issue

Vol. Volume 9 / Iss. Issue 2

Details open_in_new

Journal of Cognitive Human-Computer Interaction | 2025

Proposed Strategies for Sustainable Agriculture Domain Chatbot with Blockchain Development

The farm sector is challenged by various factors, such as climate volatility, ineffective resource management, and data security. In this paper, a new methodology is proposed where blockchain technology is combined with a chatbot platform to offer farmers real-time, secure, and accurate crop suggestions. Blockchain allows data integrity to be guaranteed, reducing risks from data tampering. The chatbot is an interactive platform, where farmers can enter soil parameters, location, and weather. The system processes these inputs and gives optimal crop recommendations based on past data and predictive analytics. The proposed solution is enhancing sustainable agriculture practices, boosting productivity, and ensuring long-term food security.

groups

S. Rahini Sudha mail -

Uma mageshwari D. mail -

Vaishnavi N. G. mail -

Sumetha S. S. mail -

Subbalakshmi B. V. mail -

Poovizhi A. mail

link https://doi.org/10.54216/JCHCI.090203

Volume & Issue

Vol. Volume 9 / Iss. Issue 2

Details open_in_new

Journal of Cognitive Human-Computer Interaction | 2025

Review of Machine Learning Technique Based Prediction Model for Phishing Websites Detection

Phishing attacks have emerged as a significant cybersecurity challenge, targeting individuals and organizations by tricking users into revealing sensitive information through deceptive websites. Traditional phishing detection methods, such as blacklists and heuristic-based approaches, struggle to keep pace with the rapid evolution of phishing techniques. Machine learning-based predictive models offer a promising solution by analyzing website attributes, URL structures, and behavioral patterns to distinguish between legitimate and phishing websites. This paper provides a comprehensive review of various machine learning techniques, including decision trees, support vector machines (SVM), random forests, deep learning models, and ensemble methods, employed in phishing website detection. It explores feature selection strategies, dataset characteristics, performance evaluation metrics, and real-world implementation challenges. Furthermore, the study discusses recent advancements such as adversarial resilience, natural language processing (NLP) integration, and real-time phishing detection frameworks. The review highlights existing research gaps and future directions to enhance phishing detection accuracy, scalability, and adaptability in evolving cybersecurity landscapes.

groups

RishiKesh Dube mail -

Twinkle Sharma mail -

Damodar Tiwari mail -

Kailash Patidar mail

link https://doi.org/10.54216/JCHCI.090204

Volume & Issue

Vol. Volume 9 / Iss. Issue 2

Details open_in_new

Journal of Cognitive Human-Computer Interaction | 2025

Injury Prediction and Prevention for Cricket Players Using AI

Cricket is a physically demanding sport that exposes players to various acute and chronic injuries. Preventing these injuries is crucial for maintaining peak performance and prolonging careers. This project leverages artificial intelligence (AI) and machine learning (ML) to analyze key player data, including biomechanics, workload, fatigue, and mental stress, to assess and mitigate injury risks. Wearable sensors and tracking systems continuously monitor player movements, workload, and physiological parameters, providing real-time insights into their physical condition. By detecting patterns that indicate potential injury risks, the AI model enables early intervention through personalized training modifications and recovery programs. This proactive approach minimizes injuries, optimizes player fitness, and enhances performance. Ultimately, integrating AI-driven injury prevention strategies in cricket ensures better player management, increased longevity, and improved overall team efficiency.

groups

A. V. Adlin Grace mail -

Sanjay Kumar S. mail -

Rajesh S. mail -

Ragul Doss R. mail

link https://doi.org/10.54216/JCHCI.090205

Volume & Issue

Vol. Volume 9 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2025

Hybrid Deep Learning Models for Finger Vein Biometric Authentication with Experimental Insights and Robust Performance Evaluation

The proposed method creates an advanced Deep Residual Convolutional Neural Network (DR-CNN) for finger vein pattern recognition to enhance both accuracy and computational efficiency of the system. The framework implements DR-CNN to handle the reduction of dimensions together with feature extraction while resolving traditional CNN models' overfitting issues. This research utilizes 6,000 images from the VERA and PLUSVein FV3 and MMCBNU_6000 and UTFV databases which form 80% training data and 20% testing data. The ImageNet training includes 4 pooling layers while also using 4 fully connected layers as well as 13 convolutional layers. The DR-CNN classifier achieves optimal authentication-performance through its implementation of Gray Level Co-occurrence Matrices (GLCM) and Scale-Invariant Feature Transform (SIFT) for extracting features. A performance assessment based on accuracy, sensitivity, specificity, F1-score, false acceptance rate (FAR) and false rejection rate (FRR) proves that DR-CNN surpasses traditional techniques. With its implementation of 5,000 images the proposed model demonstrates better accuracy (94.39%) than CNN (92.45%), RNN (88.99%) and DNN (85.91%). Tests show that the system processes 25,000 images within 2.43 milliseconds establishing fast computation speeds. DR-CNN achieves robustness through minimum mean absolute error values of 19.34. The proposed DR-CNN model delivers a 97.8% recognition rate together with a 0.83% error rate which proves its effectiveness for biometric security applications.

groups

Hashem Alyami mail

link https://doi.org/10.54216/FPA.200108

Volume & Issue

Vol. Volume 20 / Iss. Issue 1

Details open_in_new

Journal of Cognitive Human-Computer Interaction | 2025

Detecting Cyberbullying and Hate Speech in Regional Languages Using Hybrid Deep Learning and NLP Models

The rise of social media platforms has led to an increase in cyberbullying and hate speech, which can have severe consequences on individuals and communities. The detection of harmful content, especially in regional languages, remains a significant challenge due to the linguistic diversity, informal expressions, and limited datasets available for training machine learning models. This paper proposes a hybrid deep learning and natural language processing (NLP) model for the detection of cyberbullying and hate speech in regional languages. The model combines convolutional neural networks (CNNs) and recurrent neural networks (RNNs) with advanced NLP techniques such as sentiment analysis and context-aware feature extraction. Preliminary experiments show that the proposed model achieves an accuracy of 86.7% for hate speech detection and 82.3% for cyberbullying detection in regional language datasets. Furthermore, the hybrid model outperforms traditional machine learning techniques by 15% in terms of precision and recall. This approach demonstrates the potential of combining deep learning and NLP to address the challenges of detecting harmful content in diverse linguistic environments.

groups

Ganesh C. mail -

Kumarganesh S. mail -

Elayaraja P. mail -

Thiyaneswaran B. mail

link https://doi.org/10.54216/JCHCI.090206

Volume & Issue

Vol. Volume 9 / Iss. Issue 2

Details open_in_new

Journal of Artificial Intelligence and Metaheuristics | 2025

Nature-Inspired Metaheuristic Optimization for Network Design and Communication Systems: Trends, Applications, and Future Directions

Communication network design (CND) and wireless sensor networks (WSNs) present significant challenges, particularly in optimizing network reliability, energy efficiency, and cost-effectiveness. This literature review discusses the use of metaheuristic algorithms to solve these NP-hard problems and provide accurate results for network reliability, resource-management assignment, and energy utilization in data transmission networks. Recent advancements in hybrid metaheuristic approaches, such as combining Genetic Algorithms with Branch and Bound (GA–BB) or Particle Swarm Optimization with Simulated Annealing (PSO–SA), demonstrate their effectiveness in optimizing network performance in emerging domains such as vehicular ad-hoc networks (VANETs) and Internet of Things (IoT)-enabled WSNs. The review also discusses applications to issues such as cluster-head selection in WSNs, routing protocols in dynamic networks, and supply-chain network design. These developments are essential in evolving technologies such as 6G networks and the Internet of Everything (IoE), where complex systems demand innovative optimization strategies. By highlighting these concerns, this review calls for increased use of metaheuristic techniques to further the application of future networks in smart cities, healthcare, and secure network architectures.

groups

Hussein Ibrahim Hussein mail -

Lateef Abd Zaid Qudr mail -

Weal Hasan Ali Almohammed mail

link https://doi.org/10.54216/JAIM.090107

Volume & Issue

Vol. Volume 9 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2025

Neutrosophic Statistical Analysis on Healthcare Data for Oral Cancer Detection

Oral cancer is presently a growing health concern at the global level, with intense incidences of lifestyle factors. The increasing mortality rates of the diseased shall be controlled with effective early detection mechanisms. However, the traditional statistical approaches in practice fail to deliver in making a precise diagnosis of this cancer due to the intricate and interdependent prevalence of symptoms. This research work provides a solution approach using the potency of neutrosophic statistics in developing neutrosophic-integrated models of random forests and decision trees. Neutrosophic representation of data considering the indeterminacy, values of truth, and falsity facilitates healthcare experts in handling the conflicting patient data. The proposed random forest decision model with neutrosophic logic identifies the significant features, and the neutrosophic decision tree classifier predicts the stages of cancer. The findings are compared with conventional modelling of random forest and decision trees, and it demonstrates the efficiency and precision of neutrosophic statistical analysis in predicting oral cancer. This proposed neutrosophic decision framework will assist and support the medical practitioners and research experts in gaining more insights and deeper comprehension of the cancer progression and suggesting suitable treatment plans to minimize the morbidity rate.

groups

Sakshi Taaresh Khanna mail -

Sunil Kumar Khatri mail -

Neeraj Kumar Sharma mail

link https://doi.org/10.54216/IJNS.260323

Volume & Issue

Vol. Volume 26 / Iss. Issue 3

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2025

CBi-BERT: Efficient Skin Disease Image Segmentation Using Patch-Based Deep Feature Mapping and BERT-Based Attention Mechanism

Skin image segmentation serves as a vital undertaking in medical image analysis, specifically in dermatology, since it enables the detection of skin diseases and the assessment of effectiveness of treatments. Segmenting skin lesions from photographs is a crucial step in working towards this patchive. Nevertheless, the work of segmenting skin lesions is difficult due to the existence of both artificial and natural deviations, inherent characteristics like the shape of the lesion), and deviations in the circumstances during which the images are obtained. In recent years, researchers have been investigating the feasibility of utilizing deep-learning models for skin lesion segmentation. Deep learning methodologies have exhibited encouraging outcomes in various image segmentation initiatives, thereby preventing the possibility of automating and enhancing the precision of skin segmentation. This paper introduces a new hybrid method, named the CBi-BERT framework, aimed to improve the results and architectures of medical image segmentation or patch detection tasks. This architecture employs Convolutional Neural Networks (CNNs) for feature extraction as well Bidirectional LSTM-based encoders to process sequence information and BERT based attention collection across the strongest features. Image normalization, resizing and data augmentation techniques are applied in the proposed method to deal with major challenges faced during medical imaging such as rate of image quality differentiation from noise or bias between benign vs. malign features. We evaluate the performance of CBi-BERT to those benchmark datasets and state-of-the-art models, showing that CBi-BERT outperforms them in all relevant metrics such as Intersection over Union (IoU), recall, mean average precision (bin-MAP) DICE coefficient. Specifically, for images sized 256x256 the model achieved IoU =0.9, recall=0.92, mAP=0.89 and Dice coefficient: =0.91 thereby outperforming some advanced state-of-the-art models as ResNet50, VGG16, UNet, EfficientNet-B-01 Our results show that the framework is able to detect and segment important structures in medical images with high precision which makes it a compelling tool for AI based Healthcare solutions.

groups

Summi Goindi mail -

Khushal Thakur mail -

Divneet Singh Kapoor mail

link https://doi.org/10.54216/JISIoT.170117

Volume & Issue

Vol. Volume 17 / Iss. Issue 1

Details open_in_new