All of the articles in this proceedings volume have been presented at the International Conference on Recent Advances in Intelligent and Sustainable Technologies (RAIST 2026) during 23-25 February, 2026 in Surat, India. These articles have been peer reviewed by the members of the Technical Program Committee...

This paper investigates a secure hybrid radio-frequency/free-space-optical (RF/FSO) communication architecture for smart grid and electric vehicle (EV) infrastructure operating under composite fading channels. An AI-driven controller based on Q-learning dynamically adapts link selection and channel parameters...

This paper presents a novel, AI-driven cross-domain optimization framework designed to synergistically enhance Quality of Service (QoS) in 6G Cognitive Radio (CR) networks and energy efficiency in hybrid AC/DC microgrids. By leveraging a unified ensemble machine learning model—incorporating federated...

Cyber-physical systems (CPS) are critical components in industrial control, automation, and real-time decision, making, where they must frequently rely on cooperative relaying to be able to communicate reliably and with low latency. Nevertheless, advancements in quantum computing capabilities pose a...

The most popular means of travelling around the world is air travel. Nevertheless, there is still a significant issue with baggage mishandling. Manual handling systems and barcode systems are limited by their software. They often do not inform the passengers but RFID-based solutions which automate tracking,...

Sarcasm detection in product reviews requires balancing domain-specific symbolic pattern recognition with deep semantic understanding. Symbolic representations capture explicit linguistic phenomena that are often decisive for sarcasm detection. Existing work either favors interpretable symbolic representation...

Agricultural practice is the main business action of the preference of people. Crop production is a significant factor in agricultural practices, just as soil structure determines the suitability of crops. A major share of India’s GDP (Gross Domestic Product), directly or indirectly, comes from agricultural...

For deaf and hard-of-hearing people, communication barriers remain a major obstacle, particularly in assistive and emergency communication situations. The majority of methods have mainly concentrated on gesture recognition and do not adequately address robustness under real-world variations like motion...

Students often struggle to prioritize concepts during exam preparation due to the lack of structured insights from Previous Years’ Question Papers (PYQs), which remain one of the most valuable yet underutilized academic resources. We have proposed Machine Learning (ML)- powered smart PYQ analyser system...

Deep learning has achieved high accuracy in plant disease classification under fully supervised settings; however, real-world agricultural applications are constrained by limited data and class imbalance. To address these challenges, this work proposes an enhanced ambiguityaware semi-supervised learning...

The design of CMOS based analog circuits has become progressively more challenging as device scaling advances. The transistor sizing strongly influences the performance metrics such as power dissipation, silicon area, unity gain bandwidth, slew rate, and open loop gain. This makes an analog circuit design...

In an evolving supply chain management landscape, accurate demand forecasting and inventory management are critical for cost reduction and meeting customer demands. This paper proposes a machine learning model to forecast food demand and manage inventory using real-world data such as fulfilment centre...

Machine Learning (ML) has revolutionized the banking sector by enabling precise customer segmentation, marketing, and fraud analysis. This study entails predicting customer churn from a credit card customer dataset, which is demographic, transactional, and account-based. Supervised Machine Learning algorithms...

Multi-traffic scene perception is critical for the safe routing and tracking of autonomous vehicles in complex urban environments. This paper proposes an enhanced YOLOv8-based vehicle detection framework for top-view traffic scenes by integrating Channel Attention Modules (CAM) and Multi-Scale Feature...

Currently, the world is going through an AI and ML revolution, and we have seen tremendous growth in the implementation of AI in various sectors over the last decade. Conventional AI-based systems were implemented in a cloud-centric environment, using servers with high processing power, ample storage,...

The proliferation of space debris in Earth’s orbit poses an escalating challenge to satellite operations, space missions, and the longterm sustainability of orbital environments. Traditional debris monitoring systems, which predominantly utilize ground-based radar and optical telescopes, encounter limitations...

The Tor network is one of the most widely used systems for enabling anonymous communication on the Internet. Despite its importance, its anonymity guarantees have been repeatedly challenged by a wide range of deanonymization attacks. This paper presents a comprehensive review of deanonymization attacks...

Speech emotion classification (SEC) is the automatic identification process of the emotional states that are inherent parts of any utterance with the help of computer programming with high potential applications in the domain of medicine, security, surveillance, digital marketing, E-learning, internet...

Human–Swarm Interaction (HSI) supports straightforward control of groups of robots, but many current systems depend on costly sensing equipment like motion capture rigs, depth cameras, or wearable devices, which limits their use in educational and resource constrained environments. In this work, we propose...

Blind spot-related accidents remain a significant safety risk, particularly with cost-sensitive Advanced Driver Assistance Systems (ADAS), where expensive sensing solutions may not always be practical. In this research paper, a real-time vision-based system is constructed using Raspberry Pi platform...

Deepfake detectors trained on a single dataset often fail under unseen manipulations because they rely on dataset-specific artifacts rather than facial characteristics. We propose a physics-informed deepfake detector that grounds decision-making in anatomical invariants of real faces, such as bilateral...

Shape-driven is a key factor that affects nanostructure materials and its response to magnetic fields and its energy loss. This makes it a useful design parameter for biomedical and nano-actuation applications. In this study, we present the methodical synthesis and thorough examination of shape-engineered...

Discourse coherence prediction, essential for automated essay scoring, dialogue systems, and multi-document summarization, is hindered by the inability of existing Graph Neural Network (GNN)-based Natural Language Processing (NLP) models to capture dynamic, multi-granular contextual dependencies. We...

Human fall detection is an important area of concern in the context of healthcare monitoring systems and is a significant issue. Automatic fall detection systems help in the prevention of fatal injuries and rapid medical care for senior citizens living alone, children left alone, as well as in various...

Driver drowsiness is a critical and persistent concern on modern roadways, and most of the accidents due to drowsiness can be avoided by detecting them in time. Previous works mostly rely on either a single-parameter cue, like thresholds on blink frequency or eye aspect ratio, or head-pose deviations....

This paper introduces a consolidated, edge-native architecture engineered to evaluate four distinct medical imaging modalities—retinal fundus photographs, dermatoscopic lesions, thoracic X-rays, and cranial MRI—directly on consumer-grade mobile hardware. Rather than relying on cloud connectivity, we...

This paper presents BookMitra, an intelligent library management system integrated with a hybrid book recommendation framework designed for academic environments. The system combines contentbased filtering using Term Frequency–Inverse Document Frequency (TF–IDF) and cosine similarity with collaborative...

Because of their better electrostatic control and lower short-channel effects, NW-FETs have become attractive options for low-power and high-performance nanoelectronic devices. The drain current and transconductance properties of nanowire FETs are fully investigated in this work, with a focus on low-power...

Predicting molecular toxicity and verifying drug identity in real-world scenarios is a fundamental challenge in ensuring pharmaceutical safety. This paper presents a combined framework addressing both issues through a two-stage pipeline process. First, we validate a reverse transfer learning module,...