Authors - Prema Sahane, Shreyas Borse, Kartik Narkhede, Manasi Choudhari, Pradnya GaikWad, Ashwini Bhosale, Rutuja Khedkar Abstract - An innovative strategy to address one of the main causes of blindness in diabetic patients is presented in AI-Vision: Forecasting Diabetic Retinopathy for Preventive Care. Through sophisticated predictive modelling, this study uses artificial intelligence (AI) to transform the diagnosis and treatment of diabetic retinopathy (DR). Our approach improves the accuracy of DR diagnosis and makes it easier to identify risk factors that contribute to the progression of the disease by combining cutting-edge Convolutional Neural Networks (CNNs) with extensive medical datasets. Healthcare practitioners may now use individualized preventative tactics based on patient profiles thanks to our cutting-edge model, which uses real-time data analytics to deliver actionable insights. By empowering doctors to intervene promptly, this proactive approach not only seeks to identify DR in its early stages but also lowers the likelihood of serious sequelae .Our research also shows how AI can be used to streamline automated screening processes. AI-Vision hopes to establish a new benchmark in preventative healthcare by bridging the gap between ophthalmology and AI, with the ultimate goal of eradicating avoidable blindness in diabetic populations worldwide.
Authors - Jalindar Gandal, Nilesh Gorade, Kunal Sonawane, Khushal Patil Abstract - Cattle health and productivity are fundamental to the livelihoods of agriculturalists and the overall agricultural economy. Traditional cattle health monitoring methods are often time-consuming and lack the capacity for real-time assessment of cattle health, resulting in reduced milk productivity and economic losses. To address these challenges, we propose the implementation of an Internet of Things (IoT) technology-based, low-cost, real-time cattle health monitoring system. The system comprises wearable sensors for continuous monitoring of vital parameters such as body temperature, heart rate, and activity level. These sensor values are relayed wirelessly to a cloud server, where data is processed and analyzed to identify anomalies indicative of potential health-related problems. This information is presented to the farmer through a user-friendly mobile application, which displays real-time alerts and suggests preventive or remedial actions. The system facilitates early disease detection, leading to improved cattle health, enhanced milk production, and enhanced farm profitability. The system emphasizes cost-effectiveness by utilizing readily available hardware, thereby increasing accessibility for smallholder farmers. The system offers a long-term solution for cattle health management. This paper aims to demonstrate the transformative potential of integrating low-cost IoT technologies with livestock farming to establish precision agriculture and enhance the prosperity of rural farming communities.
Authors - Samadhan Pujari, Hetvi Saroliya, Vedika Gawde, Ekansh Manral, Jalpa Mehta, Deepika Patil, Rashmi Malvankar Abstract - Mortality prediction is crucial for public health, aiding resource allocation, policy-making, and preventive strategies. This study applies ARIMA and SARIMA models to analyze mortality trends in India (1990–2022) using data on infectious diseases such as Malaria, HIV/AIDS, Tuberculosis, as well as non-communicable diseases like Nutritional deficiencies and neonatal disorders. ARIMA [1, 3, 4] captures non-seasonal trends, while SARIMA, incorporating seasonality, proves more accurate. Implemented using Python libraries like pandas, stats models, and scikit-learn, their accuracy is assessed using Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE). Findings indicate that SARIMA outperforms ARIMA, emphasizing the role of seasonality in mortality patterns.[6,7,16] A significant decline in deaths from infectious diseases like Malaria and Measles is observed, attributed to public health initiatives, immunization programs, and improved healthcare facilities while neonatal and non-communicable diseases remain pressing concerns. Accurate data collection is essential for improving predictive modeling, and ARIMA/SARIMA provide critical insights for public health planning. Future research could integrate factors such as climate change, economic conditions, and machine learning techniques to refine forecasting models further. This study reinforces the significance of time series forecasting in public health decision-making and strategic healthcare interventions.
Authors - Vaishali S. Katti, Kailash J. Karande Abstract - This paper reviews significant advancements in sentiment analysis, emphasizing various innovative applications in fields such as poetry analysis, human resources, customer feedback, and mental health monitoring. The study systematically examines methodologies adopted in recent research, elucidating their contributions to the field while presenting diagrams to enhance understanding. This overview not only highlights the evolution of sentiment analysis but also explores its implications across diverse sectors.
Authors - Manjunath Inamati, Goutami Naragund, Chetan Paranatti, Saroja Siddamal Abstract - Electrocardiogram (ECG) signals are vital for diagnosing cardiovascular conditions. However, they are often contaminated by noise, hindering accurate analysis. This paper presents the FPGA implementation of Infinite Impulse Response (IIR) elliptic filters for denoising ECG signals. Elliptic filters were chosen for their sharp roll-off and computational efficiency, while an FPGA platform was utilized for real-time, low-latency processing. The design leveraged MATLAB as the primary tool for filter parameterization and hardware-oriented signal processing due to its comprehensive functionality, ease of use, and seamless integration with HDL Coder for Verilog code generation. Synthesis and hardware deployment were performed using Xilinx Vivado. The system was validated using both synthetic and real ECG signals, demonstrating effective noise suppression while preserving diagnostic features. Results indicate the potential of FPGA-based digital filters, designed with MATLAB, for portable and efficient biomedical applications.
Authors - Aswin Sreerag, Meenakshy P, Akhil A, Anargha Ranjit, Anoop S. Babu Abstract - The field of text-to-video generation is going through a transformation, by the advancements in Artificial Intelligence (AI) and deep learning. AI-powered video generation models helps us in the conversion of textual descriptions into visual content, unlocking new possibilities in the fields of education, entertainment, and multimedia content creation. But the existing systems face challenges such as maintaining temporal coherence, such as ensuring smooth transitions, and correctly aligning video sequences with advanced textual inputs. This research combines Large Language Models (LLMs) and Generative Adversarial Networks (GANs) to develop a high-quality, temporally consistent text-to-video generation framework. The system uses the Gemini model to change textual prompts into detailed and structured descriptions. These descriptions are initially given to the Stable Diffusion model to get the corresponding text-image before being input into a fine-tuned MoCoGAN model for video synthesis. The VATEX dataset, which has extensive video and text pairs, is the primary training resource, this ensures meaningful alignment between textual descriptions and generated visuals. Apart from that, the research also explores the DAMO ViLab which is a diffusion model, that operates without additional training, so that it provides a comparative analysis of different generative approaches. The results shows enhanced video smoothness, improved scene consistency, and stronger semantic alignment with the textual prompts. This work advances text-to-video generation by addressing key limitations, using AI driven storytelling and visualization applications.
Tuesday August 25, 2026 3:30pm - 5:30pm IST Virtual Room CGOA, India
Authors - Jyoti Patil Devaji, P. C. Nissimagoudar, Prerana Savant, V.S.Nandana, Vaishnavi Harlapur, Vidhi Agarwal Abstract - The project aims to focus on improving object detection and safety measures for autonomous vehicles by combining LiDAR and camera data. The main goal is to increase object detection accuracy and resilience by combining LiDAR data with the advanced object detection model YOLOv5. The system detects objects, recognizes and tracks cars, and uses a simple depth estimation technique based on bounding box width to determine how far away vehicles stand. To provide more accurate object localization in 3D space, bounding boxes are constructed around identified objects, and the related depth information is computed using the LiDAR data. A safety function that improves the situational awareness of the autonomous vehicle by generating an audio alert when a vehicle is spotted too close is also included in the system.
Authors - Vismay Tank, Khush Sanghavi, Vyom Gandhi, Pramila Shinde, Jalpa Mehta, Vaishali Korade Abstract - Everyone in the current world hopes that his/her personal information won’t be revealed in any way. Security insurance is essential for protecting personal information from prying eyes. The information may be extensive, and it is important to minimize risk and ensure sensitive information is protected. This analysis addresses the drawbacks of previous customized security and other anonymization techniques by implementing a progressive modified protection saving technique. The core of the suggested technique is composed of two main components. Two additional states that are used in the report table but are hidden in the primary segment are sensitive data and fragile weight. The Fragile Data (DI) of the record holder determines whether the mystery should be retained or, conversely, whether it should be disclosed. Sensitive weight (DW) illustrates how brittle a characteristic's value is in comparison to the others. The following section discusses the Recurrence Circulation Block (FDB) and Semi Identifier Dispersion Block (QIDB), two other portrayals used for anonymization. Exploratory findings show that the suggested framework performs faster and loses less information than existing approaches.
Authors - Manas Tiwari, Rohit Sharma, Nyasa Singh, Sandhya Avasthi Abstract - Although packaged foods are generally considered safe and hygienic, many consumers are unaware of the additives they contain, which can pose serious health risks. This lack of awareness has contributed to a rise in health issues such as allergies, asthma, diabetes, and other chronic illnesses. To address this problem, a mobile application is proposed that helps users make healthier food choices by analyzing packaged food ingredients. The application enables users to scan or upload images of ingredient labels, utilizing image preprocessing techniques (grayscale conversion, Gaussian blur) and Optical Character Recognition (OCR) to extract the ingredients. Users can also input personal health conditions like diabetes, asthma, or allergies, allowing the system to tailor its analysis. By referencing a comprehensive database such as OpenFoodFacts, the application provides immediate health-related insights on the detected ingredients. For ease of understanding, ingredients are classified using a color-coded system: red for highly harmful substances, orange for moderately harmful ones to be consumed in moderation, and green for safe ingredients. This approach empowers consumers to make informed, health-conscious decisions regarding packaged food consumption.
Authors - Nivedya Krishnan M T, Mariya P Jose, Amrita V S Abstract - The Financial Independence, Retire Early (FIRE) movement is primarily focused on giving people financial security through saving and investing in such a way that they become less dependent on regular jobs. This empowers them to stop working earlier than regular retirement ages. The study explored major motivations for adopting FIRE through work-life attitudes, desire for freedom, financial well-being, frugality and minimalism, social influence, and spousal/family support. A survey was administered to collect primary data from students and professionals from rural, urban, and semi-urban areas in India, to reach a sample size of 400 respondents. The structured questionnaire includes a 5-point Likert scale, binary, and frequency-based questions. Data were coded and analyzed using SPSS, with regression analysis employed to test the impact of independent variables on motivation to FIRE. Regression results showed that by far the best predictors of motivation for FIRE were frugality and minimalism, desire for freedom, and spousal support. The model was statistically very highly significant (p
