International Journal of Digital Technologies

Deep Learning Approach for Brain Tumor Segmentation and Detection

Vikas Humbe, Srikant Somanna — Wed, 31 Dec 2025 00:00:00 +0000

Deep Learning has emerged as a prominent area of focus within the field of machine learning, garnering significant attention from researchers in recent years. This powerful machine learning technique has found widespread application in addressing complex problems necessitating high levels of accuracy and sensitivity, particularly within the medical domain. Among various medical conditions, brain tumors represent a common and aggressive form of malignant disease, often associated with a short life expectancy when diagnosed at advanced stages. Accurate grading of brain tumors following detection is crucial for devising effective treatment strategies. This study employs Convolutional Neural Network (CNN), a widely utilized deep learning architecture, to classify a dataset comprising 3064 T1 weighted contrast-enhanced brain MR images into three tumor classes (Glioma, Meningioma, and Pituitary Tumor). The proposed CNN classifier demonstrates robust performance, achieving an accuracy of 97.52% and 97.39% sensitivity for segmented lesion images.

Cardiac Status Prediction using Machine Learning

Wed, 31 Dec 2025 00:00:00 +0000

This work focuses on creating an IoT platform using machine learning to predict cardiac status with a Raspberry Pi. The system uses a DS18B20 sensor for temperature measurements and a MAX30100 sensor for monitoring heart rate and oxygen saturation. It incorporates various user-specific health features such as age, gender, smoking status, cigarettes per day, hypertension prevalence, blood pressure medication usage, diabetes status, BMI, heart rate, and temperature to improve prediction accuracy. The data collected is processed on the Raspberry Pi using a pre-trained machine learning model (Logistic Regression) to predict cardiac health status. A Flask-based web application provides an intuitive user interface, allowing users to input their health data and receive cardiac status predictions. This work aims to offer a low-cost, efficient, and user-friendly tool for early detection and monitoring of cardiac health, with potential benefits in preventive healthcare and personalized medicine

Predictionof Mental HealthUsing Machine Learning

Wed, 31 Dec 2025 00:00:00 +0000

Mental health disorders have emerged as a paramount problem worldwide, affecting millions and presenting substantial hurdles to healthcare systems. In this research, a method for predicting mental health disorders utilizing extensive machine learning (ML) and artificial intelligence (AI) models is proposed. The proposed system integrates a range of sophisticated machine learning algorithms to analyze user inputs and predict potential mental health issues. By selecting the feature importance, we can select the best suitability model for prediction with high accuracy. The algorithms, K-Neighbors Classifier, Decision Tree Classifier, Random Forest, Boosting and Stacking, are used to predict mental health. Among them, Boosting appears to be the best model based on its highest F1 score. The anticipated likelihood condition was evaluated to make an appropriate recommendation. We focus on college students and older adults, specifically adults older than 18 years. This demographic is at higher risk of mental health challenges due to academic and workplace stress, making early intervention crucial.

Implementation of Augmented Reality to Visualize Cell Organelles

Ai Myachha Chawloo; Monita Wahengbam Subhrojit Saikia — Wed, 31 Dec 2025 00:00:00 +0000

Cell biology is a foundational subject in the life sciences, yet traditional education methods often fail to convey the complexity and spatial relationships of cell organelles. This paper addresses this educational challenge by developing an augmented reality (AR) application that provides an immersive, interactive experience for exploring cell organelles. The primary objective of this application is to find an alternative method to enhance learning and engagement through AR technology, offering detailed 3D models that users can manipulate to understand cellular structures and functions better. The project is being developed primarily utilising Blender and Unity Editor for creating 3D models and integrating them into an android application. The application provides a user-friendly approach to interact with the digitally produced 3D models of the various organelles, to study their structures. This project is an attempt to pave the way for future expansions to include additional topics and more advanced interactive features, ultimately providing a novel approach to study cell biology.

Precision Diagnosis: Leveraging KNN for Breast Cancer Detection

Salka Debbarma; Reyad Hossain; Niladri Das — Wed, 31 Dec 2025 00:00:00 +0000

Breast cancer is a class of disease which is the most common type of cancer nowadays in women and this kind of cancer has millions of new diagnoses globally each year. This research study is focused on early diagnosis for raising cure rates and increasing survival rates among patients. This project will discuss the use of various machine learning models to predict breast cancer, which includes Logistic Regression, Naive Bayes, SVM, K-Nearest Neighbour (KNN), Decision Tree, and Random Forest. KNN outperformed other models with an accuracy of 98.54%, precision of 0.98, and an F1-score of 0.98. To translate this model into a real-world web application, a Flask based web interface was developed to be used by health professionals and patients with real-time predictions. Future work will involve optimization of models, refining features, and integrating the medical system to assist clinical decision-making

AI-Powered Adolescent Health: Dimensions, Current Trends and Future Prospects

MANDEEP K CHAWLA; RIDHI SHARMA; NAVDEEP KAUR — Wed, 31 Dec 2025 00:00:00 +0000

Adolescence is a critical developmental stage, marked by rapid physical, emotional, and psychological changes, which may give rise to unique health challenges. Artificial intelligence has emerged as a transformative force in addressing these challenges, offering innovative solutions for improving adolescent healthcare. This paper provides significant insights into key dimensions, current trends and future prospects of AI in adolescent health. It explores applications in mental health interventions, remote monitoring, personalized nutrition and fitness, and substance abuse prevention, highlighting the potential for AI-driven systems to enhance healthcare outcomes for adolescents. In particular, AI-powered tools such as machine learning algorithms, predictive analytics and personalized health plans have shown promise in early diagnosis, treatment optimization, and lifestyle management. The paper also addresses significant challenges in the adoption of AI, including ethical concerns, data privacy issues, interoperability and the need for trust and acceptance among adolescents. The review concludes by discussing future directions in fully harnessing AI capabilities to modernize adolescent healthcare.

Evaluating Cybersecurity Risks in Modern Healthcare: Quantitative Assessment of Biomedical Device Compromises and Electronic Health Records Tampering

Kumar Amitabh; Anurag Mathur — Wed, 31 Dec 2025 00:00:00 +0000

The adoption of digital technologies in the health sector has provided better operational effectiveness and care to patients while presenting critical cybersecurity vulnerabilities. The work presented here is the analysis of the cyber risks to the electro-medical devices used in the healthcare sector. An investigation has been done into the occurrences, cost implications, and implications on patient safety due to cyber-attacks on biomedical devices and Electronic Health Records (EHR). The significant data set of industry reports, case studies, and hospital breach records were analyzed and investigated using statistical methods. It provided a data-driven understanding of the relative risks imposed by compromising of biomedical devices and EHR tampering. The financial impact and burden imposed by the cyber-attack and EHR tampering have been elaborated. The findings of the work emphasize the differences and similarities between attack vectors, consequences, and mitigation strategies. It also provides evidence-based recommendations towards fortifying healthcare providers’ cyber security measures.

Traffic Violation Detection

Saurabh Sinha; Nitin Pilkhwal; Rohit Verma; Sunil Kumar; Pawan Kumar Mall — Wed, 31 Dec 2025 00:00:00 +0000

Traffic violations pose significant safety risks and are a growing concern in urban areas. It requires a scalable solution for monitoring and enforcement. There is no alternative for being on the roads but automation may undoubtedly aid the traffic police by reducing the workload associated with booking offenses. Even while this can aid in the recording of violations. The presence of interceptors and police officers on the road tends to serve as a deterrent to traffic violations. This study examines the artificial intelligence role in traffic violation detection. The overall summary of the literature in this field is about classifying different types of detection models over traffic violations and comparative analysis of previous work done in this field.

Explainable AI for Web and Text Mining

Vidya Arnav; LovnishVerma; Anita Budhiraja; Sarwan Singh — Sat, 03 Jan 2026 00:00:00 +0000

This study introduces an Explainable AI (XAI) framework specifically developed for web and text mining applications, addressing the critical challenges of transparency and understandiblity in AI systems. While advanced Artificial Intelligence models, particularly deep learning architectures, excel in predictive capabilities, their "black-box" nature often hinders trust, accountability, and regulatory compliance. The proposed framework bridges this gap by integrating interpretable models with post-hoc clarification methods such as Local Interpretable Modell-agonistic Explanation (LIME) and SHapley Additive exPlanations (SHAP). It also incorporates interactive visualization tools to elucidate outputs like sentiment analysis, topic modeling, and keyword significance, empowering stakeholders to validate and refine AI-driven insights effectively. Through case studies in domains such as healthcare, e-commerce, and legal services, the framework demonstrates its adaptability and practical utility in enhancing user trust and promoting ethical AI practices. Experimental results reveal its ability to balance interpretability with performance, ensuring usability across diverse applications while addressing challenges like scalability and domain-specific explanations. This research advances the field of XAI by providing a structured, transparent, and adaptable solution for web and text mining tasks. Future work will focus on optimizing scalability, tailoring explanations for specific industries, and integrating ethical considerations such as bias mitigation to ensure the responsible deployment of AI systems.

AI-Driven Surveillance Drones: An Overview of Capabilities and Applications

Sat, 03 Jan 2026 00:00:00 +0000

Unmanned Aerial Vehicles (UAVs), commonly known as drones, are being used commonly as their applications continue to expand across various fields. The introduction of Artificial Intelligence (AI) has evolved these drones into powerful surveillance tools. Central to their effectiveness is using sensors like advanced CMOS (Complementary Metal-Oxide-Semiconductor) sensors, which provide high-resolution imaging, low power consumption, and adaptability in various lighting conditions, other sensors like thermal sensors. This paper explores innovative approaches to the development and deployment of AI-powered drone systems for surveillance. By reviewing the latest advancements and future trends, this paper aims to showcase the immense potential highlighting key areas and challenges.

Advancing Healthcare Security through Blockchain-Driven Smart Contracts

Swati Gupta; Dinesh Chandra Misra — Sat, 03 Jan 2026 00:00:00 +0000

The increasing digitalization of healthcare systems makes ensuring the integrity of healthcare transactions and protecting of private patient data more challenging. Block-chain technology combined with smart contracts offers a hopeful solution to address these problems by giving a decentralized, open, and tamper-resistant framework. This paper explores the design of a block-chain-powered smart contract security architecture specifically for healthcare. The suggested design is superior to earlier solutions in important aspects such as operational economy, scalability, and data breach security. These areas include better dependability metrics for contract execution, data consistency, and transaction integrity. The suggested blockchain-based architecture is more effective at finding and fixing security flaws than existing techniques. As a consequence, the execution time is shortened and the fault tolerance is improved. The proposed architecture is robust, according to evidence from tests and case studies. This implies that it has the potential to completely transform the way healthcare data is managed and secured. This technology makes it possible for digital healthcare operations to be safe, effective, and scalable by solving major flaws with current systems.

IoT-Driven Innovations in Railways

Ritika Sharma, Gourab Das; Smriti Rekha Dutta — Sat, 03 Jan 2026 00:00:00 +0000

The integration of Internet of Things (IoT) in the railway industry has revolutionized the way railways operate, manage assets, and ensure passenger safety and comfort. This paper presents a comprehensive survey of existing trends and technologies in railways, employing IoT. Various applications of IoT in railways were reviewed, including predictive maintenance, real-time monitoring, safety enhancements, and passenger experience improvements. In this paper discussion about diverse scenarios in the rail industry is carried out and comparative differences among the various IoT technologies introduced in other papers are identified. Additionally,this paper presents a proposed system that consists of an Aadhar based Ticket reservation and Biometrics based ticket verification system, along with biometrics-based casualty and corpse identification system. This system will enhance the ticket reservation & verification system making it more robust. Furthermore, the applications of IoT in the railway sector are discussed

Predictive Maintenance in WSN based on Machine Learning

Shweta Sharma Shailja Agnihotri — Sat, 03 Jan 2026 00:00:00 +0000

Predictive maintenance is one of the key concerns in the field of wireless sensor networks. The purpose of predictive maintenance is to reduce unplanned energy consumption, to increase lifetime of the network and to reduce costs and delays. Predictive maintenance system is a new concept that aids the system to monitor and evaluate the status of those systems for which they are being developed. They also assist in maintaining the actions of these systems by predicting the future quality. With applications in industrial monitoring, smart cities and environmental sensing, the integration of AI and predictive maintenance in WSNs presents a promising path towards intelligent, economical, and scalable network management. In order to tackle the issues of sensor failures, network instability and system deterioration, this paper investigates the predictive maintenance in WSNs and along with the predictive maintenance and machine learning concepts

Optimization of VM migration and Energy Consumption using Adaptative Particle Swarm Optimization Algorithm

Harmeet kaur; Shubham Gargrish — Sat, 03 Jan 2026 00:00:00 +0000

The high energy consumption of cloud computing systems affects both cloud providers and users. Virtualization is needed to save energy. VM consolidation efficiently manages cloud resources for users and cloud providers. It also improves server efficiency and reduces data centers energy use. However, needless VM consolidation efforts lead to poor VM selection and assignment, lowering performance, QoS, and SLAs. Data centers need energy-saving solutions without impacting other metrics. This paper introduces a adaptive Particle Swarm Optimization methodology for energy-efficient Virtual Machine (VM) migration within cloud environments. The technique optimizes energy usage and ensures SLA compliance by optimizing VM-to-Physical Machine (PM) allocations. The evaluation of the proposed method has been done considering the metrics like energy consumption, SLA and resource usage. The results highlight that after incorporating the optimization an enhancement has been observed for all the metrics for the effective VM management.