All of the articles in this proceedings volume have been presented at the International Conference on Sustainable Innovation with Artificial Intelligence and Machine Learning 2025(ICSIAIML 2025) during 9th-10th October 2025 in Vishwakarma University, Pune. These articles have been peer reviewed by the...

Footstep energy harvesting obtains energy from walking hu- mans and transforms it into electricity through mechanisms like piezo- electric materials or electromechanical systems. Footstep power genera- tion technology can be applied in high-traffic areas like train stations, airports, and shopping centers...

Tax laws in India are complex for salaried employees and small businesses, frequently altered by disparate information sources, and require familiarity with specialist knowledge areas to understand legal text. In this paper, we suggest an AI-augmented Tax Law Assis- tant with Retrieval-Augmented Generation,...

Efficient ride-demand forecasting has become essential for modern transportation systems that depend on real-time operational intelligence. This research introduces a machine learning–based approach that predicts Uber ride demand using a high-volume dataset managed through MongoDB Atlas. The dataset...

Birth weight is a critical marker of infant health and APGAR score assessment. A low birth weight is critically considered a common trait of increased infant mortality, developmental concerns, and subsequent complications. This analysis investigates the birth weight of a child based on various maternal...

The Smart Dog Health Tracker is a remote monitoring solution that combines IoT hardware with AI to continuously supervise the health status of dogs. This is enabled through an ESP32 microcontroller with biomedical and environmental sensors, measuring SpO₂, temperature, motion, and location. Sensor data...

Quantum computing is a radical new computational paradigm based on the principles of quantum mechanics. Since it can utilize superposition, entanglement, and interference, it is considered as a potential solution to a variety of high-dimensional, computationally intensive problems that still cannot be...

The accurate estimation of biological age from physical activ- ity data has the potential to revolutionize personalized health monitoring and early disease detection. However, existing deep learning models of- ten lack interpretability, limiting their practical application in real-world healthcare settings....

Wildfires cause extensive damage each year in the United States, impacting lives, property, and ecosystems. This paper presents an exploratory visualization and machine learning approach to under- stand and predict wildfire causes using a large-scale dataset of 1.88 mil- lion U.S. wildfire incidents....

Dementia is a progressive neurological condition characterised by the impairment of memory, cognition, and daily functioning, thus posing challenges for both patients and caregivers. This solution proposes a smart; affordable system designed for dementia care. The solution leverages accessible technology...

Classifying Alzheimer’s Disease (AD) using multimodal neuroimaging data like Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) is a significant challenge in medical imaging. The effectiveness of these models relies heavily on the strategy used to combine data from both modalities....

Proper evaluation of river water quality is the key to the sustenance of the eco-system, sustainable use of resources, and the preservation of human health. In the current work, we will present an artificial intelligence-based algorithm that will predict the Water quality index (WQI) of Indian rivers...

Deep reinforcement learning (DRL) is found to be an interesting model to optimize the complex multi-drug treatment regimens especially in the rare and treatment-resistant cancers. These tumors are usually characterized by shortage in standard treatment approaches, high level of patient-patient het-erogeneity,...

In this work, Green Vision picture restoration pipeline proposed which combines final enhancement, adaptive restoration, and deterioration detection into a single modular architecture. The suggested solution maintains scalability through modular architecture while achieving eco-efficient picture restoration...

Brain MRI datasets with detailed annotations are hard to collect, which limits the effectiveness of diagnostic models. Brain tumor images are especially challenging, and available datasets are often small, which restricts training. We test whether synthetic images can expand these datasets in a useful...

A critical component of the retail sector is comparative sales analysis, which offers insightful information about consumer behavior and aids merchants in identifying areas for development and improvement. The purpose of this research paper is to examine the idea of comparative sales analysis and its...

This work proposes a sentiment analysis method for processing and analyzing customer feedback data of an application developed for online classes and video conferencing. We overcome the problem of an unbalanced dataset by using negation generation methods and oversampling to achieve class balance. A...

With more than 80% of life indoors, Indoor Air Quality (IAQ) issues constitute a major health concern. Existing Internet of Things (IoT) and Machine Learning (ML) monitoring frameworks almost exclusively utilize one-stage models that estimate the Air Quality Index (AQI) from raw sensor measurements,...

Parkinson's Disease (PD) requires early, objective diagnosis, often hindered by subjective clinical assessments. This paper presents a novel, non-invasive PD screening system leveraging keystroke dynamics, a behavioral biometric, to quantify subtle motor deficiencies. Statistical features, including...

This paper presents a new hybrid AI-driven assistive system aimed at benefiting visually impaired people by rendering visual images into good-quality audio descriptions. The system consists of several Op- tical Character Recognition (OCR) engines, AI-driven image description models, and state-of-the-art...

The worldwide construction business is undergoing a transformation due to rising consumer consciousness, sustainable urbanization, and environmental concerns. Sustainable building materials, or “green bricks,” have therefore become essential for lowering environmental impact and raising the profile of...

With this piling up of online retailing, consumers often find it difficult to look over prices across various e-commerce portals. Looking for the best price across multiple websites might be time-consuming and confusing. PriceTrackr is the solution at hand-a live price comparison website meant for the...

The progressive loss of neurons that results in dementia is a trademark of Alzheimer’s disease (AD). AD growth is linked to structural alterations in the brain that can be studied with magnetic resonance imaging (MRI). Deep learning techniques have recently confirmed potential in the prediction of AD...

Multimedia object detection technology has been a major factor in changing the world industries. It has enabled machines to see and understand visual content which in turn has changed application domains like smart surveillance, healthcare, and e-commerce to name a few, very differently. For example,...

The critical need to reduce greenhouse gas emissions, fossil fuel reliance, and promote sustainable mobility is transforming the global transportation industry. Government green subsidies have become important policy tools to spur innovation and speed the adoption of electric vehicles (EVs) and associated...

Question-answering (QA) systems face a difficult trade-off: the speed of inverted indices versus the understanding of neural models. Traditional TF-IDF is fast but brittle when query wording shifts, while BERT offers deep context at a high computational cost. We bridge this divide with a hybrid architecture...

The growing role of artificial intelligence in tourism marketing is transforming core decision-making processes and shifting them toward data-driven business practices. This paper proposes a process-oriented conceptual model linking the pre-adoption, adoption, and post-adoption phases of artificial intelligence...

The issue of fake news becoming major issue in society, specially in multilingual regions of India. This paper represents a novel solution to classify real news and fake news for four Indian languages as Hindi, Gujrati, Marathi, Telugu. With the help of appropriate datasets for these languages we developed...

The paper introduces a novel test prioritization and prevention testing method with the use of synthetic observability data, identified as logs, traces, and metrics. To this end, a PreventativeTestPro GPT and a Custom ChatGPT were used. The proposed method, according to the real-time analysis of the...

Climate change, caused primarily by man-made activities like greenhouse gas emission and deforestation, causes global warming, weather anomalies and rise in ocean levels, threatening the ecosystem and the lives of man critically. To resolve these issues, our project suggests a machine learning approach...

With air pollution reaching dangerous levels globally—especially across South Asia— there’s a growing need for cleaner, more sustainable indoor air solutions. This study presents a new design for a smart air purifier that replaces traditional plastic components with laminated bamboo boards, offering...

Indoor air pollution remains one of the most pressing public health issues of our time, particularly in South Asia where average AQI levels routinely exceed safe limits [1]. Building on our earlier prototype of a bamboo-based, AI-enhanced air purifier [12], this paper proposes the next stage of development:...

Datasets will determine both the performance of models and the reproducibility, fairness and transferability of their results from laboratory to other applications, and are the foundation of machine learning today and the future of machine learning; this paper offers an exhaustive review of over 30 datasets...

We present the concept of an online-twin method of simulation of the gut microbiome to create personalized probiotic-drug interventions. We propose integration of host data, microbiome sequencing, metabolic models and simulations in order to predict individual response to treatment. Studies indicate...

The long-term stability and aesthetic success of dental implants rely heavily on precise evaluation techniques. To address this, need a hybrid expert system is introduced that integrates rule-based clinical knowledge with automated image analysis. It’s aiming to improve diagnostic accuracy and support...

The COVID-19 pandemic highlighted the urgent need for reliable monitoring of proper face mask usage in public spaces. Manual observation is both labor-intensive and error-prone, making automated solutions essential for safeguarding public health. In this work, we propose a deep learning–based system...

This paper presents an enhanced machine learning framework for delivering high-precision, context-aware recommendations and adaptive user modeling. This system brings together different kinds of data sources, such as IoT devices, smart home systems, cell phones, and wearable tech, to get multi-dimensional...

In the automobile manufacturing sector in Pune, India, this study aimed to assess the awareness, adoption & effectiveness of Human Resource Accounting (HRA) practices. Using a mixed-method approach, data from 217 professionals in 14 Original Equipment Manufacturers (OEMs) were retrieved from a mix...

Objective The goal of this study is to develop and verify an AI-based predictive analytics system for hospital waste management in response to the challenges of conventional biomedical waste management practices, which are reactive and inefficient in dealing with waste spikes [11]. Novelty:...

With wider use of computer-based examinations, ensuring academic honesty has been a significant challenge. The traditional methods of manual supervision are limited. They are inconsistent and prone to human error. We developed an automated system to detect cheating. The computer vision and machine learning-based...

YakshaVarnika is a system that combines cultural tradition and modern technology by recognizing characters from Yakshagana performances using images. Our method uses customized Convolutional Neural Networks (CNNs) to uniquely identify characters by analyzing their distinct crown patterns, costume elements,...

This work proposed a novel Convolutional Neural Network (CNN) that can classify fruits and predict when they will be ripe is presented with higher accuracy. The architecture consists of task-specific nodes for classification and regression and a centralized node for shared feature extraction. Preprocessing...

The combination of nanotechnology with eco-friendly drug design has led to innovative cancer treatment therapies. Water-less granules encapsulated in situ self-assembling nanoparticles (ISSANPs) offer a sustainable method of administering chemotherapeutics that are poorly soluble in water, improving...

The rapid advancement of artificial intelligence and synthetic media generation has amplified the threat of deepfakes, raising serious concerns about online authenticity and public trust. Deepfakes, often created using GANs and autoencoders, produce highly realistic images and videos that are increasingly...

Fruit diseases are becoming a bigger threat to farming in tropical areas. These diseases often go undetected until they have done a lot of damage. Traditional methods of finding diseases are slow, manual, and not very scalable. Most AI-based models only look at fruit images and don't take into account...

An examination of the connection between CRM and brand development is the overarching goal of this study. The goal is to identify developments, gaps, and contributions in this field by reviewing the literature from 2001 to 2023. This research makes use of bibliometric methods by reviewing 274 papers...

The main challenge in music listening remains “what to play next?”, despite the plethora of libraries that are available, modern platforms do not take into account real-time preferences, and do so inadvertently by overlooking user mood. To solve this, we created a prototype web app that integrated facial...

Onion is a common and widely grown crop and has its own significance. But it is highly vulnerable to many leaf diseases such as purple blotch, downy mildew, and several other disease. Routine field survey is still the most common way to detect these problems, but it is subjective, slow and is not suitable...

The voices synthesized by AI, as well as deepfake audio applications, are a significant threat to identification software and the credibility of an individual, allowing fraud, deception, and fake news. This is getting more difficult to detect fake voices as synthetic speech gets more realistic.The proposed...

To justify the need for summarizing and extracting information efficiently in right ways, this paper highlights the growing challenge posed by the increasing number of PDF files. Reading lengthy documents is a tedious and time consuming task in many sectors. To save time and quickly comprehend the key...

English language learners face difficulties in pronunciation, grammar, vocabulary, and fluency. Existing digital tools offer general assistance but fail to adapt to individual learner needs. To address this gap, we propose an AI-powered adaptive learning coach that integrates automatic speech recognition,...

Diabetic Retinopathy (DR) is a significant cause of impaired vision on a global scale and primarily characterized by the presence of lesions like microaneurysms and exudates in retinal images. It is imperative to detect such abnormalities when they are at a tender age before they develop serious complications....

Liver cancer ranks among the most fatal tumors globally, necessitating precise and prompt detection systems. . Federated learning (FL) provides an effective approach by facilitating collaborative model training among decentralized institutions while preserving sensitive patient data confidentiality....

Weed infestation remains one of the most persistent challenges in modern agriculture, as weeds compete with crops for nutrients, water, and sunlight, ultimately reducing yield and profitability. Conventional management practices rely heavily on chemical herbicides, which not only increase production...

The increasing need of sustainability has transformed existing innovation paradigms from supply-driven technology advancements to demand-driven changes influenced by consumer/customer’s behavior. This research paper examines the consumer-innovation nexus as a pivotal factor in the shift towards sustainable...

This study presents a practical implementation of the Artificial Intelligence of Things (AIoT) for Koi feeding using low-cost IoT machines powered by Raspberry Pi. To optimize feeding, deep learning is applied in alignment with the widely used five-minute feeding method. YOLOv9-s is employed for shaded...

The transition to electric mobility necessitates a holistic understanding of the complex interplay between EV performance, economic viability, and environmental impact, which remains inadequately addressed in a unified framework. This study employs a multi-method analytical approach—integrating machine...

This study develops a unified machine learning framework to analyze the primary drivers of global CO2 emissions and provide targeted policy guidance for 195 countries. We integrate a comprehensive suite of socioeconomic and environmental data from 1900 to 2023, employing a Random Forest model that achieves...

The pandemic of COVID-19 fast-tracked online learning, with the challenge of maintaining student engagement in the process. This paper introduces a multimodal AI architecture that integrates visual, audio, and behavioral data with lightweight deep learning models for real-time energy-efficient student...

Preventable blindness is often caused by retinal diseases such as Diabetic Retinopathy (DR), Glaucoma, Cataract, and Age-related Macular Degeneration (AMD). Early and accurate diagnosis is essential, but conventional screening uses significant resources, takes time, and depends on qualified ophthalmologists...

Driving presents distinct cognitive challenges for neurodivergent individuals, including those with attention deficit hyperactivity disorder (ADHD), autism spectrum disorder (ASD) and related conditions. These challenges such as inattention, impulsivity, executive dysfunction, and sensory overload can...

The wide spread of misinformation on the web can present a danger to the credibility and quality of online discussion. The proposed work introduces an AI platform that offers real-time fact-checking in debates by using CRAG. The system uses cutting-edge natural language processing and corrective retrieval-augmented...

The proliferation of generative artificial intelligence (AI) presents a foundational challenge to copyright law, disrupting traditional legal doctrines centered on human creators. This paper addresses the jurisprudential problem of AI authorship by first examining established legal philosophies, primarily...

This study explores how green logistics is changing to make supply chains stronger by enhancing technology, improving financial outcomes, and supporting environmental responsibility. In essence, green logistics focuses on reducing the harmful environmental impact of activities like transportation, storage,...

Riding without helmets, triple riding, and speeding, the three biggest road traffic violations, contribute to accidents, loss of life, and congestion (traffic jams) in cities. Facility based monitoring by traffic authorities is traditional, costly in human resource monitoring, and inefficient. To resolve...

The frequency with which disasters of both natural and human-made causes are increasing implies the need of intelligent, versatile, and resilient response systems. The conventional centralized disaster management systems are not very scalable and are slow, and also, highly vulnerable to infrastructure...

The incorporation of the Artificial Intelligence (AI) in education has turned Learning Management Systems (LMS) into the tools of delivering and assessing the content into the tools that focus on helping teachers to develop and building stronger teacher-student relationships. The given paper examines...

The incorporation of the Internet of Things (IoT) into the industry 4.0 is now one of the most important change agents in the manufacturing and logistic sectors. The newest research marks the presence of IoT as a trigger of automation, digital connectivity, and real-time decision-making and shows substantial...

The Smart farming uses AI, IoT, and blockchain to improve productivity, resource efficiency, and sustainability. IoT enables real-time monitoring and automated decisions, while AI helps predict crop health and optimize farming practices. Block-chain ensures secure and transparent data sharing in supply...

This study investigates how Artificial Intelligence (AI) supports the integration of green technologies to advance the circular economy (CE), with a focus on Oman’s sustainable development initiatives under Vision 2040. A systematic literature review (SLR) covering 312 peer-reviewed studies (2018–2023)...

The rapid spread of the application of renewable energy has created an acute need to create intelligent systems that will be able to optimize energy distribution, storage and use in real time. Traditional energy manage-ment systems tend to be inflexible, lack predictive capability and do not possess...

In recent years, face recognition has been a prominent research topic with various real time applications in several areas such as biometric authentication, surveillance systems, autonomous vehicles, smartphone cameras, etc. Face recognition is a method for identifying faces with any position or orientation...

The swift development of machine learning (ML) and deep learning (DL) methods has played an important role in changing the practice of agriculture especially in the context of early detection and identification of crop diseases. Timely and correct diagnosis of diseases is essential in the minimization...

The role of agriculture in global food security remains significant, but crop diseases continue to pose major challenges to yield and quality. Early approaches based on manual inspection are slow, costly, and impractical at scale. With the rise of artificial intelligence and image processing, automated...

Blockchain technology has a high potential to change the dynamic of academic credentials management as the security, transparency, and efficiency concerns that have plagued it are resolved. The traditional systems of providing and validating records are highly prone to fraud, administrative taxation...