Volume-12, Issue-3

Posted on , by Editor IJARIIT

Volume-12, Issue-3

May-June, 2026

Research Paper

1. MARG: Ikigai-Based Career Guidance System

Career selection has become increasingly complex due to evolving industries and diverse opportunities. Many students face difficulty in identifying suitable career paths that align with their abilities and interests. This paper introduces MARG, a career guidance system that utilizes an Ikigai-based approach to evaluate user profiles across multiple dimensions. The system analyzes interests, skills, personality traits, and external factors to generate meaningful career recommendations. It further provides structured guidance through skill development plans and learning resources. The objective is to support informed decision-making while ensuring long-term satisfaction and adaptability. The proposed approach enhances clarity and enables individuals to explore career paths aligned with both personal goals and practical opportunities

Published by: Tanvi Pankaj Samarth, Rohit A. Parsode, Yashika A. Khandale, Rohan R. Landge, Ritish K. Das, Rohit C. Sakharkar, Vaishali Surjuse, Tejaswini MankarResearch Area: Computer Science & Engineering

Organisation: KDK College of Engineering, MaharashtraKeywords: Career Guidance, Artificial Intelligence, Ikigai Framework, Personalized Recommendation System, Career Decision-Making, Student Development, Skill Mapping, Career Planning, Intelligent Systems, Job Market Analysis.

Full Details View PDF Search on Google
Full Details View PDF  Google
Research Paper

2. Nuclear Households, Persistent Values: Urbanisation and Family Change in Contemporary India

This paper examines how urbanisation, economic change, and shifting cultural expectations have reshaped family life in Indian cities across three dimensions: household composition, gender roles, and intergenerational relationships. A structured literature review brings together canonical sociological frameworks, including those of Parsons, Oakley, and Giddens, alongside India-specific scholarship from Uberoi, Gupta, Shah, Desai, Rao, Chakrabarti, Manchanda, and Bhattacharya. Empirical grounding is provided by census data and a 2026 field study of 100 households in Yelahanka, Bangalore. The central finding is that nuclear residential forms have been widely adopted across urban India since 1991, but the obligations and values associated with joint family living have not collapsed alongside them. Women have entered paid employment in considerably larger numbers, yet domestic and caregiving responsibilities have not been redistributed in any proportionate way. Intergenerational financial transfers remain near universal, though physical distance has created measurable social isolation among elderly people in nuclear households. The paper concludes that urban Indian family change is best understood not as modernisation in the Western sociological sense, but as a process of structural adaptation in which residential forms shift while relational premises remain largely intact.

Published by: Abhirath MehtaResearch Area: Sociology

Organisation: Prabhavati Padamashi Soni International Junior College, MaharashtraKeywords: Family Structures, India, Urban.

Full Details View PDF Search on Google
Full Details View PDF  Google
Research Paper

3. Can SaMD Enhance Diagnostic Consistency and Turnaround Time in Resource-Constrained Public Healthcare Settings without Hardware Modification?

Long diagnostic turnaround times (TAT), equipment obsolescence, infrastructural inadequacies, and a lack of personnel are some of the ongoing issues facing resource-constrained healthcare systems. By integrating into current digital workflows, Software as a Medical Device (SaMD), especially AI-enabled systems, provides a scalable solution without necessitating changes to the underlying medical hardware. This study investigates whether SaMD may significantly increase turnaround time and diagnostic decision consistency in resource-constrained public healthcare settings. The results indicate that SaMD can greatly improve workflow efficiency and lower inter-operator variability. However, the main implementation obstacles continue to be algorithmic drift, regulatory fragmentation, cybersecurity concerns, and reimbursement constraints. The study concludes that SaMD is a workable, scalable solution for bolstering diagnostic systems in resource-poor areas when implemented through organised regulatory, financial, and cloud-based approaches.

Published by: Safal MuthaResearch Area: Computer Science

Organisation: VIBGYOR High, MaharashtraKeywords: Software as a Medical Device (SaMD), Artificial Intelligence (AI), Diagnostic Decision Consistency, Digital Health Infrastructure, Public Health Technology Integration.

Full Details View PDF Search on Google
Full Details View PDF  Google
Research Paper

4. AI Voice Agent-Based Virtual Interview Platform

A full-stack AI mock interview platform using Next.js, Tailwind CSS, Vapi for real-time voice interactions, and Firebase for backend services and authentication. The project guides developers through setting up the Vapi dashboard for AI agent creation and integrating Google Gemini for dynamic, tailored interview question generation based on user input role, level, and tech stack. Key features implemented include authenticating users, generating personalized interview scenarios, initiating real-time voice conversations with the AI agent, and saving transcripts. Additionally, the tutorial covers designing a professional UI to display past interviews and generating detailed feedback based on the conversation transcript. By the end of this comprehensive guide, learners will possess the practical skills to deploy a portfolio-worthy application that leverages real-time AI voice technology. This is a practical, project-based approach designed to help developers level up their skills with real-world scenarios.

Published by: Parth Potbhare, Ayush Nikade, Sahil karnahake, Vaibhav Chinchulkar, Shreyash Janglekar, Sandesh jagtap, Abhishek Nachankar, Neha DhuriyaResearch Area: Artificial Intelligence Engineering

Organisation: Karmaveer Dadasaheb Kannamwar Engineering College, MaharashtraKeywords: Natural Language Processing (NLP), Speech Recognition, Google Gemini API, Automated Feedback System, Real-Time Communication, Interview Preparation, Adaptive Question Generation.

Full Details View PDF Search on Google
Full Details View PDF  Google
Research Paper

5. Perceived Parenting Skills Among Parents of Children Undergoing Surgery: A Descriptive Analysis

Abstract: Surgery can be difficult for children and their parents. Effective parenting skills help to reduce the surgery-related discomfort and promote wellness and, consequently, favorable psychosocial surgical experiences for children. Most parents have anxiety before a pediatric surgical procedure. Parental anxiety may impair the parents' ability to cope with new or stressful situations while their children are undergoing surgery. Hence, in this study, the investigator has tried to assess the perceived parenting skills among parents of children undergoing surgery. Methods: This study was conducted using a descriptive correlational design among 100 parents of children undergoing surgery who met the inclusion criteria and were selected using a purposive sampling technique. Tools such as the demographic variable proforma of parents and children, and a rating scale to assess the perceived parenting skills were used. Results: The findings of the study revealed that the mean and standard deviation of the perceived parenting skills (M =32.93 & SD =3.30), indicating that most parents had consistently high levels of parenting skills with minimal variation among them. The association analysis reveals that among all selected background variables, mother’s occupation showed a statistically significant association with perceived parenting skills (χ² = 6.921, p = 0.008). Overall, the study highlights the need for continued support and targeted interventions to further strengthen parenting skills and enhance child outcomes during surgery.

Published by: Joselin Anna Bel P. C, Dr. Nesa Sathya Satchi, Hilda Rose MaryResearch Area: Nursing

Organisation: Apollo College of Nursing, Tamil NaduKeywords: Perceived Parenting Skills, Surgery, Children.

Full Details View PDF Search on Google
Full Details View PDF  Google
Research Paper

6. Social Protection and Economic Marginality: A Study of Domestic Workers in Tamil Nadu

Domestic work represents a significant segment of the informal economy in India, particularly in Tamil Nadu, where women dominate this occupation. Despite their crucial role in sustaining households and supporting the urban and rural economy, domestic workers remain economically marginalized and socially excluded. This study examines the socio-economic conditions, income patterns, and access to social protection among domestic workers in Tamil Nadu, with specific reference to Namakkal District. Using a descriptive research design, primary data were collected from 120 respondents through structured questionnaires and interviews. Secondary data from government reports and scholarly studies were also used. The findings reveal that domestic workers face low wages, irregular employment, lack of legal protection, and limited access to welfare schemes. The study concludes that effective policy intervention, awareness, and inclusion in formal labour frameworks are essential to ensure economic security and social justice.

Published by: Mrs. Sutha. P, Dr. Parvathi. SResearch Area: Economics

Organisation: Kandaswami Kandar's College, Velur, Namakkal, Tamil NaduKeywords: Domestic Workers, Informal Sector, Social Protection, Economic Marginality, Tamil Nadu.

Full Details View PDF Search on Google
Full Details View PDF  Google
Research Paper

7. CentralResume: A Unified Protocol for Structured Resume Management and Interoperable Job Profile Sharing

Creating and maintaining job profiles across multiple recruitment platforms is a redundant process. Users are often required to manually enter the same information repeatedly on those platforms, which makes it difficult to update the information later, increasing the risk of inconsistent data. Additionally, job seekers frequently maintain multiple versions of resumes tailored for different roles or industries, where only a subset of the information differs. Managing these variations manually reduces maintainability and scattered files and information. Moreover, parsing resume PDFs is inherently unreliable due to formatting variations and the lack of a standardized structure. This paper proposes a standardized protocol for maintaining a centralized repository of structured resumes that solves all the mentioned problems. The system allows users to store their professional information in a single authoritative location while enabling multiple variants of resumes tailored to specific roles or contexts using tags with minimal effort. To support interoperability across recruitment platforms and to minimize parsing issues, we introduce a standardized JSON-based schema for representing resume data, along with a sharing protocol powered by OAuth that allows recruiters and job portals to access resume information in a structured way. By eliminating the need for repeated manual data entry and unreliable document parsing, the proposed approach improves data consistency, simplifies resume management, and enables seamless integration between job seekers and recruitment platforms. It saves time by making resume sharing as easy as logging in with Google.

Published by: Anish Araz, Piyush Raj, Niraj Shah Rauniyar, Dr. Gowthul Alam M MResearch Area: Software Protocol

Organisation: Jain University, KarnatakaKeywords: Centralized Resume Management System (CRMS), Structured Resume Data, Resume Standardization, JSON Resume Schema, Resume Interoperability, Applicant Tracking Systems (ATS), Resume Parsing, Dynamic Resume Generation, Persistent Resume Links, Tag-Based Resume Versioning, Resume Sharing Protocol, Professional Profile Management, Recruitment Platforms, Structured Data Exchange, Resume Data Portability.

Full Details View PDF Search on Google
Full Details View PDF  Google
Research Paper

8. Udaan Path – Data visualization and Interest Prediction with AI integration

Traditional student evaluation systems primarily focus on academic performance and often overlook individual interests, co-curricular involvement, and overall development. This paper presents UdaanPath, a Django-based educational data-driven web platform that uses the academic and non-academic performance data of students to make predictive calculations and provide career guidance for them using AI. We aim to give teachers and parents a tool that helps them to determine the best possible insights for a child. We implement the built-in administration panel of Django, which gives a dynamic manager tool to the school admin for administrative processes. We develop features like a personalised student dashboard, an AI-generated study plan for each student, a parent portal and career path suggestions in the project presented in this paper.

Published by: Shreyash Shastrakar, Suvidha Gurnule, Suraj Naranje, Sakshi Bongirwar, Vansh Waghmare, Sushil Borkar, Prathamesh Wankhede, Dr. Ajay Jaiswal, Sachin VermaResearch Area: Data Science

Organisation: KDK College of Engineering, MaharashtraKeywords: Educational Analytics, Interest Prediction, Data Visualization, Django, Personalized Learning, Parent Portal, AI Study Plan Generation, Gemini API.

Full Details View PDF Search on Google
Full Details View PDF  Google
Research Paper

9. Online Banking Services and Customer Retention in India

The rapid advancement of digital technology has transformed the banking sector across the globe. In India, online banking services have become an integral part of financial transactions, enabling customers to access banking facilities conveniently and efficiently. The growth of internet penetration, smartphone usage, and digital payment systems has significantly contributed to the expansion of online banking. This study examines the relationship between online banking services and customer retention in India. It highlights the role of service quality, customer satisfaction, security, trust, and technological innovation in retaining banking customers. The paper also discusses the challenges faced by banks in maintaining customer loyalty in an increasingly competitive digital environment. The study concludes that effective online banking services enhance customer retention by improving convenience, reliability, and overall customer experience.

Published by: Dr. V. VelvizhiResearch Area: Economics

Organisation: Government Arts and Science College, Tamil NaduKeywords: Online Banking, Customer Retention, Digital Banking, Consumer Behaviour, Financial Technology, India, Customer Satisfaction.

Full Details View PDF Search on Google
Full Details View PDF  Google
Review Paper

10. An IoT–AR Framework for Enhancing Interoperability for People with Disabilities

Advanced technologies continue to accelerate, particularly in the fields of the Internet of Things (IoT) and Augmented Reality (AR), which have demonstrated significant potential in assistive technologies. Globally, approximately 15% of the population lives with some form of disability, highlighting the urgent need for intelligent and accessible solutions. In Saudi Arabia, recent statistical reports indicate that 5.9% of Saudi citizens experience at least one mild physical difficulty, while 1.8% of the total population lives with at least one disability, with mobility and visual impairments among the most prevalent categories. To better understand real-world challenges, in 2024, an interview was conducted with a PhD holder with visual impairment, focusing on daily mobility challenges, current assistive technologies, and desired improvements. The findings revealed critical limitations in accuracy, response time, usability, and system integration. This paper analyzes existing AR–IoT assistive solutions and identifies key challenges, particularly latency, accuracy, and interoperability between heterogeneous devices and platforms. Current systems often require multiple software applications and hardware components, increasing complexity and cost. Therefore, this research proposes enhancing interoperability between AR and IoT technologies through a unified compatibility framework aimed at reducing system complexity, improving efficiency, and increasing accessibility for individuals with disabilities.

Published by: Abdulmalek ALdosseryResearch Area: Computer Engineering

Organisation: Qassim University, Saudi ArabiaKeywords: Internet of Things (IoT), Augmented Reality (AR), Assistive Technologies, Interoperability, People with Disabilities, Human–Computer Interaction, Saudi Arabia.

Full Details View PDF Search on Google
Full Details View PDF  Google
Research Paper

11. Digitalization of Payments and GDP- A Global Perspective

This paper focuses on the growing importance of digital payment systems in facilitating the evolution of contemporary economies through increased efficiency and transparency in transactions as well as greater financial inclusiveness. Moreover, the comparison of the adoption and consequences of digital payments in advanced economies and EMDEs is analyzed. The development of technologies such as artificial intelligence and the Internet of Things contributes to increased efficiency, reliability, and safety of payments while posing threats that must be addressed. The paper considers the economic implications of digital payment systems, paying particular attention to their development in EMDEs, where the use of digital payments has been growing rapidly since 2014. In EMDEs, the percentage of adults using digital payments grew dramatically from 2014 to 2021. This paper considers the link between digital payment adoption and economic development by analyzing GDP per capita, total factor productivity, and employment in the informal economy. The paper also considers the role of central banks in fostering digital financial systems by providing efficient payment infrastructure and inclusive monetary policies. Overall, the study investigates whether digital payments have supported financial inclusion, economic modernization, and sustainable economic growth.

Published by: Rishaan LullaResearch Area: Economics And Finance

Organisation: Bombay Scottish School, MaharashtraKeywords: Digital Payments, Cashless Economy, Financial Inclusion, Transaction Efficiency, GDP Growth, GDP Per Capita, UPI, Payment Cards, Internet Banking, Mobile Payments, Economic Development, Digital Infrastructure, Cybersecurity, Fraud Detection, Machine Learning, Artificial Intelligence, Internet of Things, Contactless Payments, Economic Indicators, Digital Adoption, Emerging Economies, Developed Economies, Data Privacy, Payment Systems, QR Code Payments, Real-Time Transactions, Mobile Wallets, Banking Access, Transaction Security, Digital Literacy.

Full Details View PDF Search on Google
Full Details View PDF  Google
Research Paper

12. Online Banking Services and Customer Retention in India

The rapid advancement of digital technology has transformed the banking sector across the globe. In India, online banking services have become an integral part of financial transactions, enabling customers to access banking facilities conveniently and efficiently. The growth of internet penetration, smartphone usage, and digital payment systems has significantly contributed to the expansion of online banking. This study examines the relationship between online banking services and customer retention in India. It highlights the role of service quality, customer satisfaction, security, trust, and technological innovation in retaining banking customers. The paper also discusses the challenges faced by banks in maintaining customer loyalty in an increasingly competitive digital environment. The study concludes that effective online banking services enhance customer retention by improving convenience, reliability, and overall customer experience.

Published by: Dr. V. VelvizhiResearch Area: Economics

Organisation: Government Arts and Science, College, Mettur, Salem, Tamil NaduKeywords: Online Banking, Customer Retention, Digital Banking, Consumer Behaviour, Financial Technology, India, Customer Satisfaction.

Full Details View PDF Search on Google
Full Details View PDF  Google
Research Paper

13. Scalable Quality-Aware Depth Map Generation Using Edge-Conditioned Deep Learning Priors

While monocular depth estimation remains a primary hurdle in computer vision, this research presents a sophisticated hybrid framework designed to extract high-fidelity depth information from static 2D images. The core of this methodology lies in its dual-stream architecture: it synchronizes a global depth hypothesis generated via Deep Learning with a localized, edge-sensitive segmentation strategy. To ensure the system remains versatile across a spectrum of hardware from high-performance servers to resource-constrained mobile devices, this work implements a quality-scalable block partitioning scheme. By discretizing the image into adjustable blocks, the system can dynamically balance computational overhead against spatial precision. This process is deeply informed by the luminance channel's edge probability, which acts as a structural guide to ensure that depth transitions are mathematically anchored to the actual physical boundaries of objects. To bridge the gap between discrete block processing and a continuous, natural depth field, a guided bilateral filter is employed in the final stage. This specific refinement serves two purposes: it effectively dissolves 'staircase' or blocky artifacts resulting from the segmentation, while simultaneously acting as a 'boundary-lock' to preserve the crispness of foreground silhouettes. The resulting depth maps exhibit a granular level of detail, particularly at high-resolution block settings—providing the necessary structural accuracy for seamless 3D conversion, cinematic depth-of-field effects, and high-immersion Augmented Reality (AR) environments. GENERATION USING EDGE-CONDITIONED DEEP LEARNING PRIORS

Published by: Ramola Joy P, Remya Madhavan UResearch Area: Image Processing

Organisation: Marian Engineering College, KeralaKeywords: Monocular Depth Estimation, Deep Learning, Bilateral Filtering, Scalable Systems, Edge Detection.

Full Details View PDF Search on Google
Full Details View PDF  Google
Research Paper

14. GovAI – Smart Government Scheme & Exam Finder Using Intelligent Eligibility Filtering

The increasing number of government welfare schemes and competitive examinations in India has made it difficult for citizens to identify opportunities suitable for their eligibility. Most users face challenges due to scattered information sources, a lack of awareness, and complex eligibility conditions. To solve this problem, the proposed project “GovAI – Smart Government Scheme & Exam Finder” provides a web-based recommendation platform that suggests suitable government schemes and competitive examinations based on user details. The system collects information such as age, income, gender, occupation, educational qualification, and state from users. Using eligibility-based filtering logic, the application recommends relevant schemes and examinations along with application links. The system is developed using Python, Flask, HTML, and CSS, and deployed online using GitHub and Render. The proposed platform reduces manual searching effort, improves accessibility, and provides a centralised solution for personalised recommendations. The project also demonstrates the practical use of intelligent filtering systems and modern web technologies in improving public service accessibility.

Published by: Mohammed Zakhwan, Dr. G. Sharmila SujathaResearch Area: Information Technology (Computer Science)

Organisation: Andhra University, Andhra PradeshKeywords: Government Schemes, Recommendation System, Flask, Python, Eligibility Filtering, Web Application, Competitive Examinations, E-Governance, Citizen Support System.

Full Details View PDF Search on Google
Full Details View PDF  Google
Review Paper

15. Review of Heart-Risk Monitoring System

Cardiovascular diseases continue to be among the major causes of death globally, hence making early diagnosis and monitoring crucial to enhance the quality of care. Systems that utilise electrocardiogram (ECG) signals together with artificial intelligence,e such as machine learning, deep learning, and the Internet of Things (IoT), together with wearable health devices, have revolutionised cardiac diagnostics in the contemporary age. In this literature review, there will be an extensive evaluation of new developments in ECG signal processing and arrhythmia detection techniques, wearable ECG monitors, and intelligent health applications. This work assesses different machine learning algorithms that include SVM, CNN, LSTM, MLP and hybrid deep learning algorithms that can be applied to classify ECG signals. Other areas that are covered include remote IoT healthcare systems, cloud computing based on ECG monitoring, explainable artificial intelligence models, FHIR interoperability standards and others. The strengths, limitations, data sets, pre-processing techniques, and results achieved by recent studies are reviewed.

Published by: D R Vishal, Harshith Kumar K M, Jashwanth S R, Bipin Babu R, Harshada J PatilResearch Area: Healthcare

Organisation: Vemana Institute of Technology, KarnatakaKeywords: Heart Risk Monitoring, ECG, SpO₂, AD8232, MAX30102, ESP32, Machine Learning, IoT Healthcare, Cardiovascular Disease Prediction, Real-Time Monitoring.

Full Details View PDF Search on Google
Full Details View PDF  Google
Research Paper

16. IoT-Enabled Smart Parking and Blind Spot Detection

Accelerating urbanisation, combined with a sharp rise in privately owned automobiles, has placed considerable pressure on city infrastructures, particularly with respect to parking management and vehicular safety. Locating an available parking slot consumes significant driver time, indirectly amplifying fuel usage, traffic density, and urban air pollution. Simultaneously, limited driver visibility around a vehicle—especially in blind-spot regions—continues to be a leading contributor to low-speed accidents during parking manoeuvres. This paper offers a thorough review of prevailing technological frameworks, with particular emphasis on deploying ESP32 microcontrollers alongside arrays of heterogeneous sensors to achieve real-time proximity monitoring and obstacle awareness. The study traces the evolution from conventional camera-only solutions toward affordable, omnidirectional IoT architectures designed to strengthen situational awareness comprehensively. Key findings underscore the value of ultrasonic sensing paired with cloud-connected dashboards and smartphone interfaces in building a safer, fully networked vehicular ecosystem.

Published by: Rahul G P, Prithviraj R, KS Maneesh Kumar, Manvith DO, Raghuveer C MResearch Area: IOT And Embedded Domain

Organisation: Vemana Institute of Technology, KarnatakaKeywords: Smart Parking, Internet of Things (IoT), ESP32, Ultrasonic Sensors, Blind Spot Monitoring.

Full Details View PDF Search on Google
Full Details View PDF  Google
Research Paper

17. Comparative Evaluation of Machine Learning Approaches for Physiological Stress Detection Using ECG and EEG Signal Modalities

Stress is a complicated physiological and psychological phenomenon that has a huge impact on the health and performance of people. Conventional methods of measuring stress are dependent upon self-reports, making it difficult to determine if they are truthful and cannot be noted in real-time. In this study, the use of machine learning techniques to identify stress objectively based on physiological signals taken from ECG and EEG was examined. While other studies have only examined one signal type (either ECG or EEG), this study compared the two modalities side-by-side under the same experimental conditions, using equal amounts of data from publicly available datasets. Multiple machine learning models (Logistic Regression, Support Vector Machine, Random Forest, XGBoost, LSTM) were compared and contrasted using available datasets. Physiological signal features (heart rate variability, electrodermal activity) were taken into account and analysed to understand both autonomic and neural activation due to stress. The results demonstrated that the Random Forest model yielded the highest level of performance (F1-score=.86, AUC=.90), indicating that Random Forest is better suited to handling complex physiological signals than any other machine learning model. An analysis of the physiological signals indicated that stress causes a decrease in heart rate variability, an increase in skin conductance, and an increase in cardiovascular activity (during the physical response) due to increased sympathetic nervous system stimulation. In summary, this research points to machine learning-based techniques yielding dependable, non-invasive means for detecting stress. This research indicates that there is an opportunity to use physiologic signal analysis in combination with AI to provide future possibilities for monitoring mental health and wearable technology.

Published by: Kevin ShahResearch Area: Computer Science

Organisation: St. Gregorios High School, MaharashtraKeywords: Stress Detection, Machine Learning, ECG, EEG, Heart Rate Variability, Physiological Signals.

Full Details View PDF Search on Google
Full Details View PDF  Google
Review Paper

18. A Comparative Review of Deep Learning Methods for Landmine Detection from Vision Transformers to Ground-Penetrating Radar

Landmines present a real problem around the world, causing injuries and a real threat to deminers’ lives. Due to that, the search for safe and efficient demining methods has been a humanitarian priority for a long time. Traditional methods rely on physical probing and manual demining. However, these methods give high false-alarm rates, risks, costs, and are time-consuming. Thus, there is an urgent need to find innovative technologies and study their potential to give 100% efficient solution. This paper provides a comparative review of recent research in landmine detection and classification, focusing on the application of Artificial Intelligence and Deep Learning. We will evaluate the number of recently used deep learning methodologies, datasets and achieved performance results. This will help identify how Artificial Intelligence can succeed in solving the problems of demining operations. In this study, we will analyse the use of different algorithms with the overall goal of specifying the best findings to ensure high territory clearance, as well as specifying the challenges. This review provides important insights into the current state of the field, highlighting solutions that can enhance demining operations and improve detection accuracy.

Published by: Leidi M.Saleh AoutoResearch Area: Artificial Intelligence And Deep Learning For Remote Sensing

Organisation: Qassim University, Saudi ArabiaKeywords: Landmine Detection, Deep Learning, Computer Vision, Ground-Penetrating Radar (GPR), Thermal Imaging, Optical Imaging, Electromagnetic Induction (EMI), YOLO, Vision Transformer (ViT).

Full Details View PDF Search on Google
Full Details View PDF  Google
Review Paper

19. Review of AI-Driven Methods to Enhance Search and Rescue Operations after Earthquakes

The devastating results of seismic events affect many people’s lives every time they occur. The main damage is caused to people being trapped under the rubble for long periods of time because rescue teams lack intelligent and prioritised plans. To address this problem, we will study the utilisation of various artificial intelligence (AI) technologies in accelerating and enhancing the efficiency of human spotting and rescuing processes after earthquakes. These applications include neural networks, AI-controlled robot systems, and multimodal data fusion, where thermal, visual, and acoustic data are integrated to detect survivors under building debris, in addition to other fusion ideas. This review will focus on studies published between 2023 and 2026. One main outcome of this work is the identification of key limitations in current AI solutions, such as real-time processing constraints, the noisy nature of disaster environments, and hardware deployment challenges in active disaster zones. In conclusion, this review aims to serve as a future research direction for optimising AI-driven methods to enhance detection accuracy, accelerate rescue timelines, and improve the overall survival outcomes in seismic emergencies.

Published by: Lin M.Saleh AoutoResearch Area: Artificial Intelligence

Organisation: Qassim University, Saudi ArabiaKeywords: Earthquake Search and Rescue, Deep Learning, Human Detection, Thermal Imaging, Rescue Robotics.

Full Details View PDF Search on Google
Full Details View PDF  Google
Research Paper

20. Do ESG Rating Divergences Predict Stock Underperformance?

While the ESG investing trend has shifted to the forefront, a rather worrying paradox is also becoming ever more evident, that of the dramatically divergent ESG evaluations rendered for the identical companies, consistently and by rating agencies across the industry. This paper investigates whether that difference of opinion, particularly when combined with unambiguous and highly optimistic environmental rhetoric in corporate filings, might be used as a quantifiable indicator of greenwashing, and if companies with that pattern of behaviour tend subsequently to underperform in equity markets. I employ a sample of 135 international firms from the S&P 500 and MSCI world indices, 2015-2023, providing a dataset of 1,080 firm-year observations. I calculated an aggregated ESG divergence index using pairwise disagreements from MSCI, Sustainalytics, and Bloomberg ESG ratings, and combined it with two text-based indicators from annual reports: a FinBERT sustainability sentiment index and a TF-IDF-based ESG keyword intensity measure for inclusion in my analysis. Ordinary Least Squares (OLS) regressions, two-way fixed effects panel models, and Fama-MacBeth cross-section estimation are used to carry out the empirical investigation. I find, throughout all specifications, that ESG rating divergence is negatively and significantly associated with risk-adjusted returns; each unit of added divergence relates to an annual excess return that is approximately 0.39–0.42% lower (p<0.01). Positive sustainability sentiment in disclosures correlates with better performance, whereas high keyword density unaccompanied by external rating agreement points in the opposite direction, consistent with rhetorical inflation rather than genuine ESG progress. A long-short portfolio sorted on divergence quintiles accumulates approximately 8.7 percentage points of excess return over the nine-year window. The results speak directly to the concerns of asset managers, index providers, and regulators engaged in the ongoing effort to bring rigour to sustainable finance.

Published by: Sheena SyedResearch Area: Financial Economics

Organisation: Symbiosis University, IndiaKeywords: ESG Rating Divergence, Greenwashing, NLP, FinBERT, TF-IDF, Panel Regression, Fama MacBeth, Asset Management, Sustainable Finance, Factor Models, Python, Bloomberg ESG Ratings.

Full Details View PDF Search on Google
Full Details View PDF  Google
Review Paper

21. Transformer-Based Object Detection Architectures for Autonomous Driving Perception: A Comprehensive Review

Autonomous vehicle perception is one of the most important components in intelligent transportation systems, and the reliable trade-off between high fidelity of detection precision and computational efficiency in real time remains an open problem. Deep learning has proven to be very accurate in controlled settings, but bringing CNN-based solutions to deployment with high latency and substantial memory overhead is often a challenge to the end-to-end deployed Transformer solution. This thorough review provides a systematic analysis of recent developments in transformer-based detection architectures, consolidating 2024–2026 transformer- and CNN-based architectures for detection. It is a thorough review that systematically analyzes recent transformer-based detection architectures, summarizing the current transformer- and CNN-based detection architectures from 2024 to 2026. From our analysis, we can see that there is a clear lack of theoretical sophistication and the real-life edge-deployability of the hardware. In addition, there is a clear disconnection between the 2D camera-based detection approach and the 3D multimodal fusion approach in the literature. The critical research dimensions that are not well met by the current state-of-the-art are identified in this review, including small object detection in dense urban environments and robust inference under challenging weather conditions. This review provides a structured path forward by mapping these interrelated gaps and paving the way for the creation of lightweight, accurate and robust transformer detectors that can be deployed on their own in the field.

Published by: Muhammad HamzaResearch Area: Artificial Intelligence

Organisation: Qassim University, Saudi ArabiaKeywords: Autonomous Driving, Object Detection, Detection Transformers (DETR), Vision Transformers (ViT), Real-Time Perception, Edge AI, Multimodal Fusion.

Full Details View PDF Search on Google
Full Details View PDF  Google
Research Paper

22. Robust Deep Residual Networks with Pixel-Level Pre-Processing for Decentralized Traffic Sign Recognition

While traffic sign recognition systems play a vital role in road safety and autonomous driving, traditional architectures often suffer severe accuracy degradation under adverse environmental conditions such as low light, fog, and heavy shadows. Although federated deep learning and convolutional neural networks (CNNs) have successfully advanced decentralized edge intelligence, standard RGB image processing remains a critical bottleneck for vehicles encountering environmental noise. To address this, we propose a lightweight, decentralized ResNet-34 architecture designed for embedded applications, enhanced by a robust multi-space pixel-level pre-processing pipeline. By incorporating localized edge contrast enhancement and chromatic variance stabilization (utilizing HSV and Ohta spaces), the proposed system isolates critical luminance and structural features prior to decentralized feature extraction. The framework was trained and evaluated on the German Traffic Sign Recognition Benchmark (GTSRB) and the Belgian Traffic Sign Data Set (BTSD). The results demonstrate that coupling dynamic image pre-processing with federated residual learning yields a highly efficient, accurate, and environmentally resilient system suitable for real-time edge deployment.

Published by: Yenugurosireddygari Hemalatha, Sudhakar BathalaResearch Area: Deep Learning

Organisation: Kandula Lakshumma Memorial College of Engineering for Women, Andhra PradeshKeywords: Convolution Neural Network (CNN), Federated Deep Learning, German Traffic Sign Recognition Benchmark (GTSRB), Belgian Traffic Sign Data Set (BTSD).

Full Details View PDF Search on Google
Full Details View PDF  Google
Review Paper

23. Edge-Optimized Pre-Trained Deep Learning Models for Real-Time Detection of Red Palm Weevil and Date Palm Diseases: A Review

Date palm (Phoenix dactylifera L.) constitutes one of the most economically and culturally significant crops across arid and semi-arid regions, yet its productivity faces existential threats from the Red Palm Weevil (Rhynchophorus ferrugineus, RPW) and a spectrum of fungal and bacterial diseases. While deep learning has demonstrated remarkable classification accuracies exceeding 97% in controlled laboratory environments, the transition from academic prototypes to deployable, real-time agricultural solutions remains critically underdeveloped. This comprehensive review systematically examines recent studies, synthesizing the current landscape of deep learning applications for RPW detection and date palm disease classification. Our analysis reveals a persistent disconnect between architectural sophistication and practical deployability. Furthermore, the literature exhibits a pronounced fragmentation between pest detection and disease classification, with few studies addressing the integrated palm health ecosystem. This review identifies critical research dimensions where the current state-of-the-art falls short. By mapping these interconnected gaps across the evaluated literature, this review establishes a structured roadmap for developing lightweight, accurate, and interpretable AI systems that bridge the gap between theoretical accuracy and operational feasibility in precision agriculture.

Published by: Umar Faruk IbrahimResearch Area: Machine Learning

Organisation: Qassim University, Saudi ArabiaKeywords: Red Palm Weevil, Date Palm Disease, Edge Computing, Deep Learning, Transfer Learning, Model Compression, Explainable AI, Precision Agriculture, Real-Time Detection.

Full Details View PDF Search on Google
Full Details View PDF  Google
Review Paper

24. A Review of Explainable Federated Learning Frameworks for Chest X-ray Diagnosis under Heterogeneous Hospital Data

The application of deep learning in chest X-ray diagnosis has demonstrated promising results in detecting multiple thoracic diseases. However, traditional centralized approaches face significant challenges, including limited generalization across hospitals with heterogeneous patient populations and imaging protocols, compounded by strict privacy regulations such as the Health Insurance Portability and Accountability Act (HIPAA) and the General Data Protection Regulation (GDPR) that prevent data sharing between institutions. Although centralized deep learning approaches perform well and achieve high local accuracy on their predictions, they are often “black boxes,” which limits clinical trust and interpretability. This review examines existing explainable federated learning frameworks for chest X-ray diagnosis under heterogeneous data conditions. Current approaches enable decentralized training across non-independent and identically distributed (non-IID) hospital environments, utilizing robust aggregation strategies such as Federated Averaging (FedAvg) and Federated Proximal (FedProx) to address label, quantity, and feature skew. To establish clinical trust, explainable Artificial Intelligence (XAI) techniques, such as Gradient weighted Class Activation Mapping (Grad CAM) and SHapley Additive exPlanations (SHAP), have been incorporated to generate interpretable visual explanations. The reviewed frameworks are evaluated on classification performance, robustness under heterogeneity, and stability of generated explanations. However, this review reveals significant gaps: the types of heterogeneity are addressed in isolation, XAI evaluation remains largely qualitative, and explanation stability under non-IID conditions lacks rigorous validation. These findings collectively highlight the need for federated frameworks that unify heterogeneity handling across all its forms simultaneously rather than addressing each in isolation, quantitative XAI assessment, and validation of explanation consistency across diverse hospital environments to enable trustworthy and interpretable clinical deployment.

Published by: Muhammad Auwal YusufResearch Area: Artificial Intelligence

Organisation: Qassim University, Saudi ArabiaKeywords: Federated Learning, Explainable AI, Chest X-Ray, Data Heterogeneity, Medical Imaging, Grad-CAM, SHAP, Non-IID, XAI.

Full Details View PDF Search on Google
Full Details View PDF  Google
Review Paper

25. Hybrid Machine Learning and Deep Learning Approaches for Network Traffic Anomaly Detection: A Literature Review

Network traffic produces large volumes of data every second, and traditional security tools often struggle to detect new or unknown attacks hidden within this traffic. Anomaly-based intrusion detection systems address this problem by learning normal network behavior and identifying suspicious deviations. This literature review examines recent studies that use machine learning, deep learning, and hybrid machine learning-deep learning approaches for network traffic anomaly detection. The review focuses on feature selection, model complexity, dataset use, evaluation metrics, and the practical challenges that still limit real-world deployment. The reviewed studies show that traditional machine learning models can remain efficient when supported by careful feature selection, while deep learning models are useful for learning more complex spatial and temporal traffic patterns. Hybrid approaches often report stronger performance because they combine the speed and simplicity of machine learning with the representational power of deep learning. However, the literature also shows continuing weaknesses, including reliance on static benchmark datasets, class imbalance, computational cost, limited explainability, and uncertainty about performance in live networks. The review concludes that hybrid approaches are promising, but their future value depends on making them lighter, more explainable, and more reliable outside controlled experimental settings.

Published by: Abdulhaq NabizoiResearch Area: Anomaly Detection

Organisation: Qassim University, Saudi ArabiaKeywords: Intrusion Detection System, Network Traffic, Anomaly Detection, Machine Learning, Deep Learning, Hybrid Models, Feature Selection.

Full Details View PDF Search on Google
Full Details View PDF  Google
Research Paper

26. Security Challenges in Cross-Chain Asset Transfer Systems

The rapid growth of blockchain technologies and decentralized finance has significantly increased the demand for secure interoperability solutions between independent blockchain networks. Cross-chain asset transfer systems, commonly known as blockchain bridges, enable the movement of digital assets and data across multiple blockchain ecosystems, improving scalability, liquidity distribution, and usability of decentralized applications. However, the increasing adoption of cross-chain infrastructures has also introduced substantial security risks. In recent years, bridge-related exploits have resulted in financial losses exceeding billions of US dollars, making interoperability systems one of the most vulnerable components of decentralized ecosystems. This paper analyzes the primary security challenges associated with cross-chain asset transfer systems and examines the architectural characteristics of modern blockchain bridge solutions. The study reviews major bridge architectures, including lock-and-mint bridges, burn-and-release bridges, liquidity pool bridges, validator-based bridges, and light-client bridges. In addition, the paper investigates common attack vectors such as smart contract vulnerabilities, replay attacks, validator compromise, oracle manipulation, multisignature weaknesses, consensus desynchronization, and liquidity draining attacks. The research further evaluates several major bridge exploits, including the Ronin Bridge, Wormhole, and Nomad incidents, in order to identify recurring security weaknesses and operational failures. The paper also discusses mitigation strategies such as decentralized validation mechanisms, threshold signature schemes, formal verification, anomaly detection systems, transaction monitoring, and rate-limiting approaches. Finally, the study explores future research directions related to zero-knowledge interoperability systems, AI-based fraud detection, trust-minimized bridge architectures, and quantum-resistant cryptographic mechanisms. The findings demonstrate that achieving secure and scalable interoperability remains one of the central challenges in modern blockchain infrastructure development.

Published by: Kyrylo SotnykovResearch Area: Blockchain Security And Interoperability

Organisation: Independent Researcher, USAKeywords: Blockchain Interoperability, Cross-Chain Bridges, Decentralized Finance, Smart Contract Security, Blockchain Security, Validator Compromise, Cross-Chain Attacks, Interoperability Protocols, Decentralized Systems, Zero-Knowledge Bridges.

Full Details View PDF Search on Google
Full Details View PDF  Google
Research Paper

27. Cyber Security Challenges and Protection Strategies in the Modern Digital Era

The rapid expansion of digital technologies across the globe has made cybersecurity an essential component of modern society. As individuals, organizations, and governments increasingly rely on digital platforms, the frequency and complexity of cyber attacks have grown significantly. Threats such as ransomware, phishing schemes, zero-day vulnerabilities, and artificial intelligence–driven attacks continue to challenge existing security frameworks. This review paper examines the major cybersecurity challenges faced in the contemporary digital environment and evaluates current protection mechanisms, including artificial intelligence–based threat detection, encryption techniques, zero-trust security models, and blockchain-oriented solutions. The study adopts a comprehensive research approach that integrates technical analysis, threat modeling, real-world case studies, and human-factor considerations. The paper further highlights existing limitations in current security practices and identifies future research directions required to build secure and resilient digital ecosystems.

Published by: Rutuja Kamble, Swapnil Jagtap, Manisha Gadekar, Dr. Vilas WaniResearch Area: Cyber Security

Organisation: Annasaheb Magar Mahavidyalaya, MaharashtraKeywords: Cyber Security, Digital Systems, Cyber Attacks, Zero Trust Security, Artificial Intelligence, Encryption Techniques, Cyber Defense Mechanisms, Information Security.

Full Details View PDF Search on Google
Full Details View PDF  Google
Research Paper

28. Association of Hypertension and Diabetes Mellitus with Reperfusion Timelines in STEMI Patients Undergoing Primary PCI at a Tertiary Care Cardiac Centre in Jodhpur, Rajasthan: A Prospective Observational Study

Background ST-Elevation Myocardial Infarction (STEMI) remains one of the leading causes of cardiovascular morbidity and mortality worldwide. Timely diagnosis and early reperfusion therapy are the cornerstones of management and significantly influence clinical outcomes. Evaluation of demographic characteristics, cardiovascular risk factors, and reperfusion timelines is essential for improving quality indicators in acute cardiac care. Aim: To evaluate the demographic profile, cardiovascular risk factors, STEMI patterns, culprit vessel distribution, and reperfusion timelines among STEMI patients presenting to a tertiary care cardiac centre. Materials and Methods This prospective observational study was conducted at Trinay Hospital, Jodhpur, Rajasthan. A total of 60 consecutive patients diagnosed with STEMI and undergoing primary percutaneous coronary intervention (PCI) were included. Data regarding demographic profile, cardiovascular risk factors, STEMI type, culprit vessel, door-to-ECG time, door-to-balloon time, and total ischemic time were collected using a structured STEMI data collection tool. Statistical analysis was performed using descriptive statistics. Statistical Data Analysis: Chi-Square Analysis of Hypertension and Diabetes Mellitus Correlation. A chi-square test was performed to determine the association between hypertension and diabetes mellitus among STEMI patients. Table 1: Correlation Between Hypertension and Diabetes Mellitus Variable Diabetes Present Diabetes Absent Total Hypertension Present 28 11 39 Hypertension Absent 9 12 21 Total 37 23 60 Statistical Findings • Chi-square (χ²) value = 5.84 • Degrees of freedom = 1 • p-value = 0.015 Interpretation A statistically significant association was observed between hypertension and diabetes mellitus among STEMI patients (p < 0.05). Patients with hypertension were more likely to have coexisting diabetes mellitus. Graphical Analysis Histogram Analysis of Reperfusion Timelines The histogram demonstrated that total ischemic time remained substantially higher than door-to-ECG and door-to-balloon times. Although in-hospital management timelines were within acceptable international standards, delayed patient presentation contributed significantly to prolonged ischemic duration. Comparative Demographic Analysis Gender-wise Comparison Variable Male Female Mean Door-to-Balloon Time 79.4 minutes 84. Interpretation of Comparative Analysis Patients with diabetes mellitus and hypertension demonstrated relatively prolonged ischemic times and delayed reperfusion compared to patients without these risk factors. Female patients also showed slightly prolonged treatment timelines compared to male patients. Results: The mean age of patients was 56.7 ± 8.7 years. Male patients constituted 68.3% of the study population. Hypertension was present in 65%, diabetes mellitus in 61.7%, smoking history in 53.3%, alcohol consumption in 46.7%, and prior coronary artery disease in 25% of patients. Inferior wall STEMI was the most common presentation (45%), followed by anterior wall STEMI (36.7%). The right coronary artery and left anterior descending artery were equally involved as culprit vessels (43.3% each). Mean door-to-ECG time was 12.48 minutes, while mean door-to-balloon time was 81.18 minutes. Mean total ischemic time was 282.6 minutes. Conclusion: STEMI predominantly affected middle-aged male patients with multiple cardiovascular risk factors. Early reperfusion metrics observed in the present study were within acceptable international standards for primary PCI centres. Continuous monitoring of STEMI timelines and quality indicators can further improve patient outcomes.

Published by: Dr. Dhruva SharmaResearch Area: Medical

Organisation: Trinay Hospital, RajasthanKeywords: STEMI, Primary PCI, Door-to-Balloon Time, Reperfusion Therapy, Acute Myocardial Infarction, Cardiology.

Full Details View PDF Search on Google
Full Details View PDF  Google
Research Paper

29. AI-Driven Breath Analysis for Early Lung Cancer Detection Using Optimized Ensemble Learning of VOC Biomarkers

Lung cancer is one of the most prevalent and deadly diseases worldwide, primarily due to late-stage diagnosis and the limitations of conventional detection methods. Early and accurate identification is crucial for improving patient survival rates. This study proposes a novel, non-invasive approach for lung cancer prediction using AI-enhanced breath analysis based on volatile organic compound (VOC) biomarkers. The proposed system utilizes sensor-based breath data to capture VOC patterns associated with lung cancer. Advanced Preprocessing and feature selection techniques are applied to identify the most relevant biomarkers, reducing data complexity and improving model efficiency. An ensemble machine learning framework, combining multiple classifiers such as Random Forest, Support Vector Machine, and Gradient Boosting, is employed to enhance prediction accuracy and robustness. Experimental evaluation demonstrates that the proposed model achieves high accuracy, precision, and recall, outperforming individual classifiers. The system also shows strong potential for real-time implementation due to its computational efficiency. This approach offers a cost-effective, portable, and non-invasive alternative to traditional diagnostic techniques. Overall, the integration of VOC biomarker analysis with feature-selected ensemble learning provides a promising solution for early lung cancer detection, paving the way for improved screening methods and better clinical outcomes.

Published by: Syed Naseemtaj, Syed Nafeesa ThehseenResearch Area: Artificial Intelligence / Machine Learning

Organisation: Kandula Lakshumma Memorial College of Engineering for Women, Andhra PradeshKeywords: Lung Cancer Detection, Breath Analysis, Volatile Organic Compounds (VOCS), Artificial Intelligence, Machine Learning, Ensemble Learning, Feature Selection.

Full Details View PDF Search on Google
Full Details View PDF  Google