All of the articles in this proceedings volume have been presented at the International Conference on Artificial Intelligence and Secure Data Analytics (ICAISDA-2025) during 29-30, December 2025 in Puducherry, India. These articles have been peer reviewed by the members of the Organising Committee and...

Solid-State Drives (SSDs) have transformed modern data storage through their superior speed, durability, and energy efficiency over traditional hard drives. However, as data-intensive and AI-powered applications proliferate, conventional SSD management techniques face limitations in scalability, adaptability,...

Personalized Learning (PL) has evolved to address the unique needs of individual learners by adapting content delivery based on preferences, prior knowledge and contextual factors. This paper presents a comparative study between two personalized learning models-CEPL (Context Emotion Personalized Learner)...

Fake traffic fine messages are becoming a serious online threat. Cybercriminals send SMS texts pretending to be government authorities, pressuring people to pay fines immediately. These messages often include suspicious links, urgent wording, and fake sender names, making them hard for the average user...

Software development, a multi-phase process composed of requirements, coding, testing, and deployment that can take a lot of time, be error-prone, and consume a lot of resources to do manually. AI-assisted tools that currently exist, such as code suggestion tools, are focused on single tasks and do not...

Chronic disease management requires intelligent, flexible, and proactive clinical tools. This study proposes a physician-focused multi-agent system (MAS) that leverages modular AI-powered agents to streamline patient data extraction, analysis, and decision-making. The system integrates real-time monitoring,...

Modern enterprises face escalating risks of insider threats, data leakage, and document tampering as digital workflows grow increasingly complex. Conventional rule-based security tools fail to detect adaptive, authorized-user attacks that exploit behavioral and semantic anomalies. This study presents...

Bearings are essential components in industrial machinery, facilitating smooth rotational motion, minimizing friction, and supporting substantial mechanical loads. In scraper conveyor systems, these bearings are exposed to extremely harsh environments involving high-impact loads, intense noise interference,...

Autonomous vehicles (AVs) rely on Vehicle-to-Everything (V2X) communication to ensure safe and efficient navigation. However, the increasing sophistication of cyber-physical threats—such as Simple, Bad-Mouth, and Zig-Zag attacks—threatens the reliability and security of these systems. This paper presents...

Software defect prediction (SDP) plays a critical role in ensuring software reliability, yet most existing approaches rely on static machine learning or optimization frameworks that struggle with data imbalance, feature redundancy, and limited adaptability across evolving software systems. To address...

The reliable early diagnosis of Autism Spectrum Disorder (ASD), a complex neurodevelopmental condition, continues to present significant difficulties for healthcare and educational systems. This research performs a methodical review of contemporary machine learning (ML) techniques applied to ASD identification....

Human Activity Recognition aims to automatically identify human actions using video, wearable sensors, or environmental data. It is widely used in hospitals, schools, public areas, malls, and smart environments for safety monitoring, anomaly detection, behavior understanding, and automation. Traditional...

Data centers worldwide use amounts of electricity that contributes to ever-increasing carbon emissions that change by time and across regions. Currently, cloud computation schedulers do not account for the real-time carbon intensity associated with electricity usage. This regional variability leads to...

Phantom inventory is the difference between what a retailer has recorded in their inventory system and the stock that is physically available in the store. This difference leads to loss of sales, customer dissatisfaction and supply chain waste. The proposed approach implements a system based on Federated...

Smartphones are mostly controlled by touch. However, current voice assistants provide limited navigation, especially for complex or changing interfaces. This limitation drives research into multimodal systems that combine speech, vision, and language understanding. Past work in this area falls into three...

Reading acquisition is crucial for academic achievement and social participation, yet approximately 10–12% of children worldwide face difficulties due to dyslexia, a neuro developmental disorder that impairs reading, spelling, and writing despite normal intelligence. Early detection plays a vital role,...

The widespread use of digital medical imaging modalities such as MRI, CT, and X-ray has increased the risk of malicious manipulation through deepfake techniques, including artificial atrophy insertion, pixel modification, and GAN-generated forgeries. Such tampering can mislead clinicians, compromise...

Diabetic Retinopathy (DR) is a leading cause of preventable blindness, and early diagnosis remains challenging due to subtle lesion patterns and the need for expert-grade annotations. Recent advances in Artificial Intelligence—particularly Convolutional Neural Networks (CNNs) and Vision Transformers...

Wireless IoT devices are all around us in smart homes, hospitals, factories, and fields quietly sensing and sharing data to make life easier and safer. But because they run on tiny batteries, have almost no memory, and talk over open airwaves, they are incredibly easy to attack. Traditional security...

Face recognition has achieved remarkable progress in recent years, yet the task of distinguishing monozygotic twins remains a major challenge due to their highly similar facial structures. Traditional biometric modalities, including 2D facial recognition and DNA-based identification, often fail to provide...

Emotion recognition plays a crucial role in intelligent systems, as emotions influence communication, decision-making, and human–machine interaction. Audio-only methods such as CNN-BiLSTM often perform poorly because emotional expression varies across speech, facial cues, and textual semantics. This...

Traditional web authentication systems face significant challenges from sophisticated spoofing attacks and lack of continuous verification mechanisms. This paper presents a novel CNN-based multimodal biometric framework that integrates face recognition, voice authentication, and liveness detection with...

The exponential growth of Unified Payments Interface (UPI) transactions has raised significant concerns over user authentication security, especially in protecting against shoulder-surfing and fraudulent access. This paper proposes a dual-layer security framework that integrates Covert Attentional Shoulder-Surfing...

With the rapid growth of e-commerce platforms, ensuring secure and trustworthy user interactions has become a major challenge. Anomalies such as fraudulent transactions, fake reviews, and bot-driven activities pose significant threats to platform integrity and customer trust. Traditional anomaly detection...

Students who are visually impaired often encounter serious obstacles during examinations, mainly because most existing platforms do not offer truly accessible and independent exam-taking experiences. Typically, blind students must rely on scribes or assistants who read questions and write answers for...

Autonomous vehicle (AV) navigation is facilitated using LiDAR and imaging sensors for detecting objects and identifying vehicles. In particular, computer vision (CV) and automated processing are required to maximize navigation through image processing. The problem of vehicle detection and classification...

This paper presents a holistic end-to-end framework for sentiment analysis, incorporating sophisticated machine learning methodologies within a scalable web application. The framework ensures that sentiment categorisation is accurate and fast by combining DistilBERT with strong preprocessing and deployment...

One of the most common endocrine syndromes in males, Testosterone Deficiency (TD), is often accompanied by reduced quality of life, infertility, metabolic dysfunctions, and potentially chronic diseases. Traditional methods rely solely on invasive biochemical tests and clinical evaluations and can consume...

Grain quality plays an integral role to agricultural productivity and global food security, influencing market price, customer preference and trade regulation. Rice grains had been traditionally categorized in ‘full’ and ‘broken’ by manual visual inspection which is laborious, time consuming subjective...

Pneumonia is a severe respiratory illness that continues to be a major health challenge worldwide, especially impacting infants and older others individuals, patients with weakened immunity. Timely and precise identification is essential to avoid severe complications, yet current diagnostic practices...

Disaster environments frequently disrupt conventional communication infrastructures, causing mobile networks and internet services to fail when they are most needed. Such breakdowns leave affected citizens unable to transmit distress signals and hinder coordinated emergency response. This survey examines...

Traditional education learning models are facing challenges in learning scenarios in terms of poor scalability for remote users, less motivation for steps to enhance learning, and limited knowledge retention. The existing models and gamification mechanisms, although addressing these challenges, still...

Timely integration of heterogeneous spatiotemporal and spectral information from various satellite observations is crucial to the remote sensing domain for advanced applications such as land cover classification, change detection, and environmental monitoring. As an extension of our previously proposed...

The brain–computer interface (BCI) is a branch of Human–Computer Interaction (HCI) enabling the communication between electronic devices like a mobile phone and a computer and the human brain. Emotions have a significant impact on human intelligence, perception, social interaction, and logical decision-making....

Sign language is one of the most important means of communication for people with hearing and speech impairments. In recent years, research on Sign Language Recognition has advanced rapidly, especially for widely studied languages like American Sign Language, Indian Sign Language, and Arabic Sign Language....

The intensive development of drone technology has increased the pressure on the long-term flight time, an essential parameter that determines the effectiveness of actions in different fields of application: surveillance, agricultural activities, logistics, and disaster management. The paper examines...

The Ocean Thermal Energy Conversion (OTEC) system is a sustainable technology that harnesses power and freshwater from seawater by utilizing the temperature gradient between surface seawater and deep seawater, making it suitable for remote islands. However, it is highly influenced by variations in Sea...

Millets, including pearl, finger, foxtail, proso, kodo, and little millet, are small-grained cereals known for their climate resilience. These crops require enhanced digital tools for species and cultivar recognition, disease detection, and origin and quality assessment. ML techniques based on neural...

This paper reviews recent progress in multimodal deepfake detection with an emphasis on multi-scale transformer architectures. It examines the challenges of detecting manipulations across both visual and audio modalities, focusing on cross-modal inconsistencies and synchronization issues. Approaches...

Aerial scene understanding is important for applications involving land use analysis, environmental monitoring and urban planning based on high-resolution drone and satellite imagery. Existing methodologies are limited due to the temporal variation, noise sensitivity, and the limited capability of regional...

Shoe sizing systems vary significantly around the world, with each country using their own system such as US, UK, European, and Japanese. However, these systems developed internationally have largely been developed based on western foot shapes, and are not a good fit for the unique morphological aspect...

Vehicle-to-Everything (V2X) communication represents an essential application of 5G networks, as it enables the transfer of data with low latency and high throughput among vehicles, between vehicles and infrastructure, and across network connectivity. However, dynamic mobility in V2X environments creates...

Long queues at traditional billing counters significantly degrade the customer experience in retail environments and increase operational costs for stores. While existing smart cart solutions offer automated billing through computer vision or RFID, they often lack integrated packing systems and require...

Heart failure alters vocal characteristics due to cardiopulmonary fatigue, leading to measurable acoustic deviations. This study compares a Spiking Neural Network (SNN) and a hybrid SNN–Diffusion model for early heart failure detection from speech recordings. The SNN captures temporal-spike dynamics...

Autonomous navigation in extreme hazardous environments where human access is impossible remains a critical challenge for unmanned aerial vehicles (UAVs). This paper presents a novel Hierarchical Multi-Agent Deep Reinforcement Learning (HMA-DRL) framework for coordinated UAV swarms capable of exploring...

Financial fraud continues to threaten digital banking and online payment systems, particularly through device misuse, IP manipulation, and identity-related inconsistencies. Existing detection methods, including blacklist-based systems, clustering algorithms like DBSCAN, and optimization techniques such...

The rapid expansion of digital payments and cryptocurrencies has created both opportunities and vulnerabilities in the modern financial landscape. A critical concern emerges when funds are swiftly transferred from traditional banking systems to cryptocurrency wallets, often using fraudulent or compromised...

The wide usage of social media has transformed global communication, but also amplified the dissemination of hate speech and misogynistic content that is prone to severe threats to online safety and societal harmony. The usage of code-mixed texts, where users mix English with regional languages, has...

In modern technology, lithium-ion batteries play a key role in powering critical applications from portable electronics and electric vehicles to large-scale renewable energy. To ensure the safety, reliability, and cost-effectiveness of these systems, accurately predicting their Remaining Useful Life...

Fibromyalgia (FM) is a heterogeneous, multi-symptom disorder whose early recognition is hampered by symptom overlap with other conditions and reliance on subjective reports. This paper systematically reviews 25 studies (2015–2025) and proposes an integrated ML framework for early FM risk stratification...

Gas leakage is the most common aspect to be considered in home appliances, industries, coal mines, transportation, and so on. Identification of this gas leakage at an early stage is most important as intervention by humans is always impossible due to the nature of the gas, which is colourless and odourless,...

Lung and colon cancers are among the leading cancers worldwide and are major contributors to mortality since they are often diagnosed at a late stage. Early and precise histopathological classification is essential for determining appropriate treatment options. In this work, we propose a lightweight...

Today, digital diasporas pave the brightest way for immersive dimensional environments, and the implications have transcended education and botanical domains. With increasing interests in culture and healthcare literacy, Virtual Herbal Gardens emerge as accessible and engaging learning resources. Promising...

In the Software Development Life Cycle (SDLC), software evolution plays a crucial role in maintaining product quality, minimizing risks, and reducing the need for extensive rework. The software industry continuously seeks to enhance the quality and reliability of software products. Recent development...

Traditional credit risk assessment models often underperform when applied to real-world data from medium and micro enterprises (MMEs), primarily due to data imbalance, noisy financial records, and limited historical credit information [7, 12]. In this study, we propose a deep learning–based framework...

Customer churn remains a significant issue across industries such as ecommerce, telecom, and subscription-based services, often leading to substantial revenue loss and reduced customer loyalty. Multiple approaches have been proposed to address churn prediction and pricing strategies. Transformer-based...

Cyberbullying has emerged as one of the biggest challenges of the era, where social media platforms provide anonymity and speed that often fuel harmful interactions. Victims of such behaviour face significant emotional and psychological consequences, including anxiety, depression, and self-harm. Detecting...

The rapid rise in criminal activity has highlighted the necessity of intelligent surveillance systems that can detect threats proactively and monitor in real time. Typical drawbacks of traditional deep learning models for identifying aberrant behavior include low accuracy, high computational expense,...

Event safety has become a growing concern with the surge in large gatherings such as festivals, concerts, political rallies, and urban public events. Existing event safety systems such as CCTV-based monitoring and IoT sensors often face problems including hardware dependence, poor scalability, slow detection...

Depression is one of the most widespread mental wellbeing problems, which, being untreated, may lead to severe social, psychological and actual working issues. The most important aspect of DAC is early diagnosis, through which appropriate medical care, treatment, and planning is achieved. This paper...

Breast cancer remains has the major health concern at global level, ranking as one of the most cancer among women worldwide and is the leading cause of cancer-related deaths. In 2022, it has affected 2.3 million women across the globe and lead to more than 670,000 deaths [1]. Faster Early detection is...

Ectopic pregnancy is a life-threatening condition that requires urgent and accurate diagnosis or management to avoid dire consequences. The success of any predictor or diagnosis model relies on the quality and consistency of input data. This research describes the preprocessing step of a multimodal deep...

Water sources are increasingly threatened by pollution from rapid urbanization, industrial discharge, and agricultural runoff, which introduce harmful contaminants into aquatic ecosystems. Due to their durability, irregular morphology, and possible hazards to the environment and human health, microplastics...

“Communication barriers remain a significant challenge for individuals with hearing impairments, especially in everyday face-to-face situations. To address this issue, GestureTalk has been developed as a dual-mode mobile and web application that enables real-time interpretation between Indian Sign Language...

Osteopenia and osteoporosis are progressive conditions that weaken bones, making them more vulnerable to fractures, especially in older adults. Early detection is vital for preventing serious complications and ensuring prompt medical care. However, traditional diagnostic methods often depend on manual...

One of the leading causes of death is caused by accidents, which frequently lead to delayed emergency services and evidence gathering for investigation. In this proposed paper uses embedded control technologies and the Internet of Things (IOT) in collision detection and drone based evidence capture system...

Vehicle detection in real-time accurately is a vital component in modern Intelligent Transport Systems (ITS) for eliminating urban traffic congestion. While there are many deep learning models often a trade-off between accuracy and inference speed exists. This paper shows a complete high performing baseline...

Smart agriculture demands scalable, privacy-preserving, and explainable intelligence to improve yield and sustainability. In this paper, AgriSensNet, a federated neuro-symbolic edge learning model, is proposed for chilli farm in the Karimnagar district of Telangana, India. The system combines distributed...

Detecting plant diseases quickly is crucial for maintaining good crop yields and sustainable farming. Current approaches often depend on manual inspection or heavy convolutional neural networks that are computationally expensive and too large to run on IoT devices. To address these issues, this proposed...

Sentiment analysis is an automated methodology for identifying opinions or emotions articulated within textual data. With the proliferation of online platforms for sharing dining experiences, restaurant reviews offer valuable insights for both businesses and consumers. This study concentrates on the...

Unimodal biometric systems have low discriminability, spoofing weaknesses, and noise sensitivity. This research proposes a secure, reversible, and comprehensible multimodal biometric verification architecture that integrates facial, fingerprint, and palmprint characteristics in order to address these...

Accurate segmentation of liver and tumor regions in Computed Tomography (CT) scans is crucial for precise diagnosis, treatment planning, and surgical navigation. Manual segmentation is not only time-consuming but also susceptible to inter-observer variability, emphasizing the necessity for robust automated...

In this paper, we present RiceDx-LIME, a deep learning framework for rice leaf disease detection that combines a novel, context-aware LIME-based explainability module (BioLIME) with a hybrid EfficientNet-B4 architecture to improve diagnostic accuracy and model transparency. With an F1-score of 0.91 and...

Multimodal biometric authentication benefits from combining complementary modalities such as face, iris, and fingerprint to increase recognition accuracy and robustness. Prior work introduced a BiLSTM - based feature extraction pipeline with Falcon Optimization Algorithm (FOA) for cryptographic key extraction,...

Design procedures significantly influence a device’s timing performance, logic usage, and system consistency when developing complicated system designs. For programmable logic designs, the quality of results is greatly impacted by the coding styles used in the HDL. Synthesis tools maximize the performance...

In today’s rapidly evolving technological landscape, voice assistants have become an integral part of everyday life. However, child-specific voice assistants with natural and expressive child-like speech remain limited. Existing solutions often fail to achieve the expected level of naturalness, clarity,...

Vehicle detection plays a critical role in traffic monitoring, intelligent transportation systems, smart cities, surveillance, and autonomous vehicles. Traditional approaches, such as camera-based and radar-based systems, often face limitations including poor performance under adverse weather, occlusion,...

Automated classification of defects in wafer maps continues to face challenges. Wafer shapes vary, there is a large class imbalance with “none” defects being the largest class, and lot-level data leakage can lead to inflated performance estimates. To address these challenges, we have developed a robust...

Accurately identifying Parkinson’s disease and distinguishing between its variations remains a significant challenge for traditional machine learning (ML) models due to the limited availability of labelled data, feature redundancy, and poor generalization across complex biomedical patterns. Conventional...

Despite advancements in AI-driven healthcare, traditional medical systems such as Ayurveda remain underutilized in modern diagnostic methodologies. Limited integration between ancient Ayurvedic principles and AI-based personalized healthcare reduces the accessibility and effectiveness of holistic wellness...

Medical emergencies require quick action during the critical “golden hour” to avoid life-threatening consequences. However, traditional healthcare systems often face problems like delayed identification of health issues, a lack of real-time first-aid guidance, and late notifications to hospitals. These...

Indoor navigation is increasingly important for helping people move smoothly through large and complex indoor spaces such as airports, malls, universities, and hospitals. Because GPS signals are weak or unavailable inside buildings, most indoor navigation systems rely on alternative technologies, yet...

Network security threats are evolving rapidly, becoming more complex and harder to detect, which makes it essential for organizations to adopt intrusion detection systems (IDS) that not only provide accurate results but also ensure accountability in safeguarding critical infrastructures. Traditional...

Early and accurate detection of fetal abnormalities is vital for maternal and neonatal health, yet centralized deep learning models face challenges from privacy concerns and data heterogeneity. This study introduces an Intelligent Federated Learning-Enabled Swin Vision Transformer (Fed-SwinViT) model...

Phishing is one of the most common cyber-attacks used to steal sensitive information by deceiving users through fake websites, emails, images, and voice-based communication. Traditional phishing detection systems mainly rely on single-mode analysis, such as URL or email checking, which makes them ineffective...

In modern complex business milieu, managing various aspects of the supply chain has become increasingly challenging. It is vital to improve viability, sales, and customer satisfaction by predicting key relational factors. However, traditional forecasting methods often yield inaccurate results and are...

The incorporation of Artificial Intelligence (AI) in education has progressed swiftly, offering substantial prospects to improve career-personal life balance for women educators; however, its effects on this demographic remain largely unexamined. This research investigates the potential of AI to assist...

Deepfake technology has advanced rapidly, leveraging deep learning to manipulate image, audio, and video content with increasing realism. These developments pose significant threats to digital security, privacy, and trust. Traditional detection methods, which typically focus on unimodal analysis (analysing...

Illegal, Unreported and Unregulated (IUU) fishing continues to harm marine ecosystems and affect global food stability. Vessels involved in such activities often hide their real movement by turning off, altering or spoofing their Automatic Identification System (AIS) signals. Detecting this type of behaviour...

Weld quality inspection is vital for ensuring industrial safety and manufacturing reliability, but traditional manual inspection methods are limited by subjectivity, time, and cost. To address these limitations, this paper proposes an automated, real-time solution for weld defect detection and classification...

The Air Quality Index (AQI) and Particulate Matter (PM) are prominent measures of urban air pollution worldwide, which affect the climate and pose public health risks. This paper aims to conduct an extensive Spatiotemporal Analysis of comprehensive air quality from 2020 to 2024 across 147 countries....

People with dyslexia struggle to understand and use written language because of a neurological impairment. Dyslexic children and their families endure stigma and discrimination when the disorder goes untreated. Children may face significant performance differences without intervention by the time they...

The rapid growth of IoT in precision management, particularly in agriculture and environmental monitoring, demands secure, efficient data processing at the fog layer. Ensuring confidentiality, integrity, and authenticity in resource-limited environments is challenging. This work proposes a lightweight,...

The rapid expansion of Internet of Things (IoT) applications in healthcare, smart homes, and industrial systems demands cryptographic solutions that are both secure and energy-efficient. Conventional algorithms such as RSA and AES provide strong security but introduce significant computational and power...

Lung Cancer is the deadliest of all diseases worldwide. That’s mostly because it’s often diagnosed too late to be treated. Early diagnosis can be life-saving, but images on CT scans are very difficult to read and conventional methods of diagnosing generally fail. In this work, we develop a novel approach...

Cloud forensics requires strong cryptographic assurance and scalable processing to handle large volumes of evidence within limited timeframes. This paper presents an Enhanced Cloud-Native Digital Forensic Framework that integrates XChaCha20-Poly1305 streaming authenticated encryption, BLAKE3 tree-based...

IoT networks face increasing risks from zero-day attacks, scalability issues, and limited resources. These challenges reduce the effectiveness of traditional intrusion detection systems. Predictive modeling has come forward as a promising approach to address these problems. Sixteen recent studies published...

The growing dependency on digital communication and the rapid expansion of image sharing over public networks have made secure image transmission a critical necessity. Chaos theory, characterized by sensitivity to initial conditions, pseudo-random behavior, and non-periodicity, offers unique advantages...

Crowdfunding has emerged as a vital instrument in modern finance, enabling startups, individuals, and nonprofits to raise funds for emergencies, projects, and causes, but existing centralized platforms such as GoFundMe, Kickstarter, and Indiegogo suffer from drawbacks including high transaction fees,...

Searchable Encryption (SE) has become an important tool for secure data outsourcing. It allows keyword search operations on encrypted cloud data without exposing sensitive information. As Cloud Computing, Big Data, and the Internet of Things (IoT) grow, traditional encryption methods are less effective....