All of the articles in this proceedings volume have been presented at the International Conference on Innovation and Practices in Artificial Intelligence, ICIPAI-2026 during 15-16 May 2026” in Quantum University, Roorkee. These articles have been peer reviewed by the members of the Program Committee...

Sugarcane has been significant to agricultural economy of the world particularly in India where it has been a cash crop. Although sugarcane is important, the production of this crop is under severe threat due to the occurrence of different leaf diseases that reduce the quality and output of crops. The...

The mango (Mangifera indica) is a key fruit crop which is commonly grown in tropical and subtropical areas. Nevertheless, production of mango is also usually influenced by a number of leaf diseases which are attributed to fungal, bacterial and environmental factors. These illnesses decrease quality of...

Deepfake technology represents a growing threat within digital media, not only because of the risks of misinforming the public but also of privacy violations and security breaches. This research works on the binary classification of facial features to increase deepfake detection. Taking advantage of...

Modern health care systems generate large scale diagnostic data in the form of lab reports, blood test results, and electronic medical records which patients have difficulty in making sense of and which doctors have trouble processing. This issue of translation of medical info sees delay in diagnosis,...

The convergence of digital twins and Industrial 5.0 represents a transformative shift in smart manufacturing, where human-centricity, sustainability, and advanced technologies intersect. This systematic literature review explores the expanding role of digital twins within Industry 5.0, with particular...

This paper presents a hybrid computational framework that integrates classical and quantum optimization techniques to improve the efficiency of Huffman encoding and string-matching algorithms. On the classical side, performance is enhanced through SIMD (Single Instruction, Multiple Data) parallelism,...

Accurate identification of the medicinal plants is of critical importance for the formulation of Ayurvedic medicines. Conventional methods of identification involve a large degree of reliance on experienced botanists and direct experience of the physical characteristics of the plants, such as the shape...

This research investigates the current scenario of mental disorders among aged individuals and proposes a machine learning–based prediction model to identify and classify major geriatric mental health issues. Accuracy metrics, confusion matrices, ROC analysis, and feature importance ranking are used...

Neurocognitive disorders (NCDs) such as Alzheimer’s disease and dementia. These are increasing public health challenges that require timely and correct observation. Our study suggests a novel, multimodal ensemble-based machine learning (ML) framework that divides neurocognitive health into five levels....

In order to ensure the safe and efficient working of electric vehicle motors, it is imperative to ensure the reliable and timely identification of defects. For this purpose, the Internet of Things, Fast Fourier Transform, and Edge Artificial Intelligence have been employed in the defect identification...

This paper presents a novel SQL-based secure processing framework for medical images that combines hybrid encoding with a Learning with Errors (LWE)-inspired encryption scheme. Traditional encryption methods require decryption before any computation, which introduces security risks. The proposed system...

Class imbalance has been a challenging phenomenon for supervised learning, resulting in biased classifiers that are biased towards the majority classes and show poor performance for minority classes. This paper presents a Generative AI-based synthetic data augmentation framework that attempts to alleviate...

The proliferation of digital educational tools has brought about a need for reliable systems for tracking and predicting the academic performance of learners. This paper describes a cloud-based system for analyzing student performance which uses machine learning models with cloud computing to identify...

This paper presents a thorough examination of the encoderdecoder architecture for detection of salient image regions, a key objective in the area of computer vision (CV) where it is necessary to locate and evaluate the primary visible features within an image. Beginning with a description of how design...

Modern-day medical care is performed through EHRs (electronic health records). These systems have caused a major change in the way that physicians keep records. Most of today’s EHRs incorporate centralized systems. The centralized system introduces major security issues, breaches of patient privacy,...

POROUS-SHIELD is an interaction-sensitive multi-layer architecture for real-time intrusion detection in complex enterprise systems, introduced in this paper. The detection in the proposed approach is formulated as a context-sensitive risk inference problem on heterogeneous and time-varying security signals,...

Food waste and food insecurity continue to coexist as critical global challenges, particularly in developing economies such as India, where inefficient distribution systems result in the simultaneous loss of edible food and inadequate access to nutrition. This study proposes an AI-assisted smart food...

Skin diseases are a problem for millions of people all around the world. It is really important to find out what is wrong with someone’s skin away so they can get the help they need. Usually doctors who are experts in skin problems are the ones who can tell what is wrong. Sometimes these doctors are...

Edge detection is a fundamental task in digital image processing, enabling the identification of object boundaries and structural features required for higher-level vision applications. Classical edge detection techniques, including Sobel, Canny, and Laplacian-based methods, remain widely adopted due...

Hardware malware poses a significant threat to modern computing systems, exploiting vulnerabilities in hardware components such as microprocessors, firmware, and integrated circuits. Unlike traditional software-based threats, hardware malware operates at a lower level, making it highly stealthy, persistent,...

NLP has been one of the best frameworks used in text era especially in today’s world of social media and influence. Sentiment analysis though old is still one of the most used tools; however, with increase of sarcasm in social media, traditional systems are failing to accurately understand and interpret....

The worldwide network perimeter is now a pathwork of exploitable gaps due to billions of unprotected IoT devices. Current intrusion detection systems are confronted with a recurring also breaches the privacy regulations that contemporary deployments are required by law. This study presents B-PriM, a...

The proliferation of constrained Internet of Things (IoT) devices has dramatically increased the use of Wireless Sensor Networks (WSNs), which are at times problematic to design due to limited energy resources and their non- deterministic nature. In this article, we present a new Eco-IoT, an end-to-end...

Phishing attacks are a major issue in cybersecurity, and modern detection systems have a weakness of disjointed feature integration, which restricts their ability to handle advanced multi-vector campaigns. The current paper introduces a novel Adaptive Multi-Mode Phishing Detection (AMPD) system that...

The evolution of cyber threats like zero-day attacks and polymorphic malware has made it increasingly challenging for traditional intrusion detection systems, which depend on static signatures and supervised learning methods, to keep pace. These traditional systems are limited in their adaptability,...

Mango leaf diseases have a significant effect on crop yield and quality, and it presents a significant challenge to sustainable agriculture. These diseases need to be detected early and accurately to reduce the losses and aid in the proper management of the disease. This paper presents a new Agentic...

The growth of online platforms has opened new opportunities to support mental health, yet many existing automated tools still fall short because they rely on only one type of input. Systems that focus solely on text or facial cues often misinterpret emotions—particularly when people mask what they truly...

The proposed Smart Autonomous System for Adaptive Student Profiling delivers a fully implemented and experimentally validated framework for dynamic personalization in learning environments. The system integrates multi-source educational data, including academic, behavioral, cognitive, contextual, social,...

The speedy growth of the Internet of Things (IoT) in the industrial settings has spawned accumulating amounts of multi-modal, heterogeneous, time-series sensor data, which has led to a real chance of shifting away reactive maintenance practices including data-driven predictive maintenance (PdM). The...

Indian Knowledge Systems (IKS) represent a vast, multidisciplinary body of knowledge developed over centuries in domains such as medicine, language, mathematics, stars, farming, and philosophy, will always be valuable to the world. With today’s technological transformation through ‘artificial intelligence’...

The main staple meal is rice (Oryza sativa L.) of over 3.5 billion individuals worldwide, Asia contributing about 90 percent of the output. The impact of rice diseases on losses of annual crop is between 10 and 37 per cent, that posed threat to food security in developing countries. This paper has two...

To effectively classify the sugarcane varieties using the images of the leaves, this paper proposes a new deep learning architecture, DeepVarCaneNet. The conventional approaches of sugarcane variety identification are very dependent on manual examination of morphological characteristics, which are time...

Traditional Nadi Tantra is a pulse diagnosis technique rooted in Ayurveda. It provides a non-invasive way to assess a person’s health by feeling three specific points on the radial artery: Vata, Pitta, and Kapha. Even though this is a comprehensive system, it often struggles in modern clinical settings...

Wrong-way driving represents one of the most vital traffic offenses that considerably increase the frequency of severe accidents and road fatalities. Thus, efficient real-time object detection techniques should be implemented within intelligent traffic environments to detect any cases of wrong-way driving....

Cloud computing has already emerged as a fundamental component of the world-wide digital economy, and it has the elastic, multi-tenant, API-driven structure that keeps on increasing the attack space on both sides of the fence. Rule- and signature-based defences, which are made to work on fixed perimeters,...

Crowd disasters in large public gatherings pose a major challenge to public safety, particularly in dense and dynamically changing environments where manual surveillance becomes inefficient, error-prone, and difficult to scale. Computer vision has emerged as a promising tool for automated crowd understanding,...

Increased proliferation of Internet of Things (IoT) devices and the emergence of distributed edge-to-cloud systems have exposed the critical weaknesses of conventional centralized Intrusion Detection Systems (IDSs), which are ill-adapted to the dynamic, heterogeneous, and privacy-sensitive needs of modern...

Among the pre-analytical errors that compromise arterial blood gas (ABG) testing, air bubble contamination stands out for its frequency and its ability to produce systematic, clinically dangerous distortions. Atmospheric air entering a collection syringe raises PO₂, suppresses PCO₂, and shifts pH toward...

The Internet of Vehicles (IoV) enables continuous data exchange between vehicles, roadside units, and remote servers to support safety-critical applications. Because these communications occur over open wireless channels, they are inherently exposed to security threats such as replay attacks, impersonation,...

AI has brought about enormous changes in the decision-making process at the workplace since it allows data-driven insights and predictive analytics. Nevertheless, typical AI systems do not have emotional intelligence (EQ), which restricts their efficacy in multi-faceted human-centered situations. This...

Proposed study represents the blockchain framework using Ethereum tool for pharmaceutical supply chain. Proposed blockchain based pharmaceutical supply chain can trace the drug batches from different stakeholders which makes data more immutable, secure as well as data is decentralized. In the proposed...

PrivGuard is an intelligent cybersecurity platform that is capable of identifying threats and is constantly on-the-fly to respond and upgrade itself. It consists of four main parts: a Red Team which is a creation of realistic attacks, a Blue Team monitoring and defending the systems from activity, an...

In recent times, depression has become a growing global health concern. However, its early detection through non-invasive methods, such as speech/voice analysis, has achieved widespread popularity. This work represents an adaptive machine learning model for voice-based depression detection. We have compared...

The exponential development in social media platforms has altered the way people voice their opinion, feelings, and political positions, with the resulting enormous amount of user-generated data that can be used for data-driven decision-making. Sentiment analysis — one of the important techniques used...

Healthcare chatbot using natural language processing for health monitoring and early diagnosis-piloting. Digital medicine is rapidly developing, which has increased the demand for smart systems that provide timely medical assistance and continuous health monitoring. A possible solution is a Natural Language...

What shapes an interview isn’t just the question bur the way each moment unfolds. With a mock interview system, a job seeker gets to experience a realistic environment where they can practice and enhance their interviewing abilities. Traditional mock interviews are usually conducted by human interviewer...

The exponential growth of online platforms, has accelerated the dissemination of both authentic and misleading information. Researchers adopt the machine learning (ML) and deep learning (DL) based approaches for fake news detection in the recent years, in which the performance of DL models has been found...

Chest X-ray images are usually interpreted by expert radiologists for the diagnosis of pneumonia, which is a time-consuming and subjective process. We propose a light-weight and computationally efficient convolutional neural network (CNN) for automated pneumonia detection to deal with these challenges....

Accurate and automated detection of cardiac arrhythmias Using electrocardiogram (ECG) data is a significant research challenge. Cardiac arrhythmias have been a major cause of cardiovascular mortality. The work proposes a unique end-to-end deep learning (DL) system for automated arrhythmia classification...

Red rot, rust, leaf scald and yellow leaf syndrome are the four major foliar diseases of sugarcane (Saccharum Officinarum), which is a major cash crop in a critical situation throughout the world. Most of the conventional detection methods rely on visual inspection by agronomists, which is labour-intensive...

Background: As search engine architectures transition from heuristic keyword-matching to AI-driven semantic interpretation, small-scale enterprises in high-competition niches face increasing barriers to visibility. Modern search agents, utilizing Deep Learning models such as BERT and Vision AI, now prioritize...

This research investigates an intelligent and integrated traffic monitoring framework which is designed to incorporate conventional surveillance systems. The proposed system considers advanced computer vision and artificial intelligence techniques to perform real-time vehicle, tracking, and analysis...