Authors - Vanishree Pabalkar, Anuja Bokhare Abstract - Sentiment analysis in multilingual social media data is a challenging and critical task due to the diversity of languages and sentiments expressed by users worldwide. In this study, we focus on conducting sentiment analysis on the Twitter US Airline Sentiment dataset, which includes tweets in English from users expressing their opinions about various US airlines. We address the research gap of multilingual sentiment analysis by leveraging advanced NLP techniques and machine learning algorithms. Count Vectorization and TF-IDF Vectorization is used during the study to extract features after cleaning up the data and processing the text. To categorize tweets as having positive or negative sentiment, we assess the effectiveness of three classifiers: Multinomial Naive Bayes, Bernoulli Naive Bayes, and Logistic Regression. We examine these classifiers' accuracy on a different collection of unlabeled tweets without ratings in more detail. The work provides valuable insights into the opinions posted by individuals on Twitter about US airlines and intends to develop multilingual sentiment analysis, especially for social media data. The findings serve as a basis for creating sentiment analysis algorithms that are more precise and reliable and that can be used to various language groups on social media platforms.
Authors - Tanuja R. Patil, Samiksha Dandgall, Vishwanath P. Baligar Abstract - Early diagnosis of brain diseases is very important and challenging nowadays. Detecting neurological disorders such as brain tumors using magnetic resonance imaging (MRI) has become an important research topic. Recently many machine learning and deep learning models have been proposed to detect and classify the brain abnormalities. Many of these models have high time complexity and still efficient models are required. The proposed model makes use of a Novel and Low Complexity Approach to solve the problem of classification of brain images. This approach is a less complexity deep learning model which uses novel methods for Denoising, Segmentation, Feature extraction and Classification of brain tumors. Here, it makes use of the advantages of bit plane approach and a unique feature extraction method. The proposed model makes use of the data set from Kaggle in which, size of the training data set is 2870 with four classes namely No Tumor, Glioma Tumor, Meningioma Tumor and Pituitary Tumor. The size of the testing data set is 394. A feature vector which matches most with the feature vector of the input image is considered as the class of the input image. The proposed method makes use of advantages of time domain and able to give good results. The overall performance of the proposed algorithm considering both training and testing data set is 97.34%. The proposed idea is comparable with the many existing models and the results are compared with three models CNN, VGG19 and Inception-V3 models and found to be promising.
Authors - Arnav Rahul Jade, Jatin Santosh Jaiswal, Nishad Sachin Kamat, Vedant Mahesh Kandarkar, Amruta Pabarekar Abstract - The Cloud-Based Plant Health Monitoring System is designed to help farmers and agricultural experts precisely identify plant diseases using artificial intelligence and cloud technology. Traditional plant health assessments rely on manual inspection, which can be time-consuming and prone to errors. This project automates the process by allowing users to upload images of plant leaves, analyzed by a machine learning model hosted on a cloud platform. The system identifies whether the plant is healthy or has a disease, providing instant results through a simple mobile or web application. To achieve this, the system uses a Convolutional Neural Network (CNN) trained on a dataset of plant leaf images, covering both healthy and diseased conditions. The application is designed to be user-friendly, allowing even non experts to access plant health information easily. This approach reduces the need for excessive pesticide use, saves time, and supports sustainable farming practices by helping users respond to plant health issues promptly. Keywords-plant health monitoring, artificial intelligence, convolutional neural network (CNN), plant disease detection, cloud computing, mobile application and machine learning.
Tuesday August 25, 2026 12:30pm - 2:30pm IST Virtual Room CGOA, India
Authors - Arunabh Barooah, S. Saranya Rubini Abstract - In the context of the digital music industry, accurate classification of music into genres and the ability to recommend appropriate genres for a user greatly improves usability of various streaming platforms. Several traditional machine learning approaches that rely on metadata face significant limitations, such as inconsistencies in the data, the growing diversity of musical styles, and a lack of focus on the actual musical content of songs. These shortcomings often result in suboptimal performance, particularly in recommendation systems. In response to these issues, this work proposes Deep Tune Network (DTN), a deep learning system for automated genre analysis and discovery of music based on similar acoustic patterns. This system uses Convolutional Neural Networks (CNNs) and Mel-frequency cepstral coefficients (MFCCs) to identify the repetitive patterns inside audio signal needed to classify music into different genre. The model achieves a maximum test accuracy of 93.01%, demonstrating its reliability in real-world applications. Additionally, a cosine similarity-based recommendation system is implemented to suggest acoustically similar songs, bridging accurate genre classification with personalized playlist curation.
Tuesday August 25, 2026 12:30pm - 2:30pm IST Virtual Room CGOA, India
Authors - Om Gadhvi, Srushti Pawar, Shravan Gadhvi, Mansi Jadhav, Manya Gidwani Abstract - Farmers in Maharashtra, India face substantial costs and low utilization rates on equipment, leading to significant financial strain. We suggest implementing an AI-powered Dynamic Machine Price Prediction Model that we can use for a digital platform that enables renting out equipment. This model uses Linear Regression, Random Forest, and Gradient Boosting to output what prices equipment should sell for, given the age, how often farmers use it, when they use it, and market demand. Gradient Boosting turned out to be the most accurate model in our exams, giving us a 94% R² score so that our model predictions are trustworthy. The website is built using the MERN stack, and it employs secure transactions through PayPal and a feature that enables farmers to search for equipment based on their location. By adjusting equipment prices on the go, we provide insights to farmers into how much they should charge for renting out their equipment in all conditions The proposed system enhances resource utilization, sustainability, and economic resilience in the agricultural sector.
Authors - Elakkiya R, Sagunthala G, Tanisha Sinha, Gugapriya G Abstract - This project presents an IoT-based predictive maintenance system based on machine learning algorithms—Random Forest, Logistic Regression, SVM, and LSTM—to identify motor faults precisely. Realtime data such as sound, vibration, and RPM are recorded through hardware prototyping, while Simulink simulates speed and torque. Data is transmitted to Firebase for real-time monitoring, prompting automated fault notifications. This system improves industrial efficiency by minimizing sudden failures, reducing maintenance expenses, and increasing machinery lifespan through prompt, data-driven interventions.
Authors - Atharva. Makode, Yash. Kasar, Yatish. Gharat, Yuvraj. Gage, Mandar Ganjapurkar, Kiran Deshpande Abstract - This paper proposes MediLink, a blockchain-based platform to store, share, and manage secure medical records. Patients and care providers in healthcare systems today typically face problems of data privacy compromises, system-to-system noninteroperability, and bureaucratic administration. These present risks to compromised patient care as well as expose data security gaps. MediLink addresses these challenges head-on by developing a decentralized, transparent system that places patients in control, with full control over their medical information while ensuring the integrity and confidentiality of the same. The platform employs smart contracts to carry out important functions such as processing insurance claims, handling patient consent, and keeping track of audit trails. Not only does this reduce human errors between humans but also saves administrative burdens and costs as well. Utilizing the strength of blockchain technology, MediLink not only secures data—yet also streamlines the easy exchange of patient records between healthcare providers. The end result? Seamless care coordination, enhanced patient outcomes, and a smoother experience for all
Authors - D.V.N. Bharathi, K.P.K. Lalitha Vitala, K. Bala Sindhuri, Sai Nikilesh Kudapa, M.L. Hiranya, Lingam Swamy Surendra, Manoj Kumar Juttuka, Kishore Varma Manthena Abstract - This paper explores the design and efficiency of optimized Wallace multipliers integrated with approximate adders to enhance energy efficiency, reduce delay, and minimize hardware complexity in the first address. Five distinct departments are introduced: architectures (AA1–AA5), each offering unique trade-offs regarding power consumption, processing speed, and circuit area. These adders are incorporated into Wallace multipliers, which improve computational speed while lowering energy requirements and design complexity. The proposed designs are evaluated using 90 nm technology to determine their applicability in resource-constrained and error-tolerant domains, such as image processing, machine learning, and IoT applications. The findings demonstrate a versatile balance between accuracy and resource efficiency, making these designs well-suited for real-time systems with different performance demands.
Authors - Deepa Unni, Murale Venugopalan, Sanju Kaladharan Abstract - Community Health Workers (CHWs) does an important role in delivering health to the public. CHW programmes often fail due to the impracticable expectations, lack of proper planning and also the efforts required to implement these activities are often underestimated. Prior to the COVID-19 pandemic, many of the developing countries used digital health technologies to address a range of health issues. Limited research has been held so far to discover the role of e-governance in addressing sustainable community health workforce. This paper bridges this gap by proposing an E-Governance Enabled Sustainability Model for CHWs.
Authors - Aparna Joshi, Moreshwar A. Mahale Abstract - Crop disease diagnosis forms one of the most significant facets of precision farming, which owes a great boost to the power of machine learning. This work presents a new method through which the use of the Tomato Leaf Disease Dataset to classify the tomato leaf's disease is achieved. The database contains 1609 images for ten disease classes: Bacterial Spot, Early Blight, Late Blight, Leaf Mold, Septoria Leaf Spot, Spider Mites, Target Spot, Tomato Yellow Leaf Curl Virus, Tomato Mosaic Virus, and Healthy Leaves. The features are extracted through the combination of Thepade's Sorted Block Truncation Coding (TSBTC) and Haralick Moments (GLCM) to improve texture and intensity description. Extracted features are categorized into multi-level classification (2-ary, 3-ary, 4-ary, 5-ary). The results achieved are stored in an Excel file and re-run using the support of Weka tool where classifiers like Naïve Bayes, Logistic Regression, Sequential Minimal Optimization (SMO), J48, Random Forest, and Random Tree. are employed. The study identifies the optimal model so that accurate and automated diagnosis of crop disease can be performed.
