Engineering, General Engineering, Control and Systems Engineering
FUTURE PROJECTS
Primary Prediction of Disease
Applications Invited
5
Scopus Publications
Scopus Publications
Hybrid Genetic Algorithm-Fuzzy Logic Framework for Optimized Seed Quality Assessment and Yield Enhancement S. Eswari, Swati Kedar Nadgaundi, RVS Praveen, Kartik Trakroo, Vandana, Manoj Senthil K Proceedings of 5th International Conference on Ubiquitous Computing and Intelligent Information Systems Icuis 2025, 2025 The evaluation of seed quality is important for agricultural output, yet conventional techniques are still physically demanding, inaccurate, and capable of mistakes. This study presents a Hybrid Genetic Algorithm–Fuzzy Logic framework for optimal seed quality assessment and yield enhancement in order to address these issues. Traditional methods like CNN models, Random Forest, Decision Trees, and Logistic Regression were trained and compared. According to experimental data, the suggested model performed much better than current methods in terms of RMSE, accuracy, precision, and recall. The framework supports sustainable agricultural improvement and global food security by combining machine learning and computational intelligence to create an effective, affordable, and stable method for automated seed quality analysis.
Intelligent Agents System for Vegetable Plant Disease Detection Using MDTW-LSTM Model Abhay Chaturvedi, Swati Kedar Nadgaundi, M. Karthick Raja, Vivek Ravishankar Dubey, Abhinav Singhal, Varuna Gupta 2024 3rd International Conference for Innovation in Technology Inocon 2024, 2024 When it comes to agricultural output, nation, India, ranks first in the world, and agriculture is unparalleled. The need to categorize and trade agricultural goods is paramount. Manual organization, which is tedious and laborious, is not a choice. When agricultural products are graded automatically, a lot of time is saved. The application of image processing techniques facilitates the examination and evaluation of the products. A technique for identifying diseased vegetables is the focus of this effort. Feature extraction, preprocessing, segmentation, and training the model are all heavily dependent on sequence. Among the preprocessing technologies at disposal are image segmentation and filtering. Using Kapur's thresholding based segmentation method, the image's sick areas can be located during the segmentation process. Use k-means clustering for feature extraction to identify vegetable plant diseases. The training of an MDTW-LSTM model relies heavily on feature selection. In terms of performance, the proposed method surpasses two cutting-edge algorithms: LSTM and DTW. The results showed an accuracy of 97.35 percent, indicating a remarkable improvement.
Challenging the Anomaly Detection Paradigm: CNN-CRF Approach P. Kanagaraju, Swati Kedar Nadganndi, Tukaram N. Sawant, Saranya Ekambaram, Palak Keshwani, Yadavalli Suresh Kumar 2nd International Conference on Intelligent Data Communication Technologies and Internet of Things Idciot 2024, 2024 Since intrusion detection has gained so much popularity, scientists continue to dedicate a lot of time and energy to studying it. Even after all these years of research, the intrusion detection community still has problems. Recognizing previously unseen attack patterns is hampered by a high rate of false positives, which is an ongoing pro blem. However, new research has shown that there are exits from this impasse. Intrusion detection relies heavily on the ability to spot anomalies, or unexpected behavior, because they indicate the presence of malicious activity. Data preparation, feature selection, and model training are all parts of the suggested approach. Machine learning algorithms can analyze the data for the development of a predictive model thanks to data preparation methods. For feature selection, the proposed approach relied on principal component analysis and iterative grading. After collecting the features, CNN -CRF is utilized to train the models. The proposed method is superior to the popular algorithms CNN and CRF. There is a 98.63% success rate when using this strategy.
A Deep Learning Framework For Human Disease Prediction Using Microbiome Data Ashwin Gadupudi, Mudarakola Lakshmi Prasad, Swati Kedar Nadgaundi, Pundru Chandra Shaker Reddy, Swati Sharma, Nipun Sharma 2nd International Conference on Integrated Circuits and Communication Systems Icicacs 2024, 2024 More and more research points to the microbiome's potential as a disease predictor, and the human microbiota is already playing an important role in human health. Microbiome data is notoriously high-dimensional (on the order of hundreds of thousands of dimensions), and prediction methods based on machine learning have a tough time with small sample numbers. Because of this disparity, the data is extremely scarce, which hinders the ability to train a more accurate prediction model. Existing approaches sometimes overlook taxonomic connections across microbial species or fail to account for plenty profiles from both known &nknown microbial-organisms, resulting in a substantial loss of knowledge. However, because to its exceptional feature-learning capability, deep learning has demonstrated unparalleled benefits in categorization tasks. On the other hand, it runs into trouble with metagenome-based illness prediction due to the fact that black-box models don't provide biological explanations and high-dimensional, low-sample-size metagenomic datasets might cause overfitting. Our solution to these issues is MetaDR, an all-encompassing framework for disease prediction in humans that makes use of deep learning and a wide range of data sources. The experimental findings show that MetaDR successfully finds the informative features using biological insights, and it achieves competitive prediction performance while reducing running time.
Smart Helmet for Coal Mine Workers Punam J Patil, Manisha Bhole, Dilip N. Pawar, Swati Nadgaundi, Reshma Pawar, Atharva Mhatre 2023 International Conference on Integration of Computational Intelligent System Icicis 2023, 2023 A more conventional version of the smart helmet has been developed to help miners while working in the mining sector. The mining industry frequently has dangerous occurrences, many of which end in fatalities or seriously injured parties. Using different sensors, the smart helmet able to recognize catastrophic situations such as presence of harmful gases like Carbon-Monoxide (CO), Methane (CH <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">4</inf> ), Ammonia (NH3) as well as temperature and humidity within the mine areas. Also the pulse of the coal miner monitored continuously so that it can be detected whether the miner is facing some difficulty or if any accident has occurred in the mine. Helmet wear by miner or not wear, is detected by an infrared sensor, hence negligence of the miner for not wearing the safety helmet can be avoided. Each sensor used has a threshold value that, if that value is exceeded, it causes the buzzer to activate, signaling the miners and supervisors. Wi-Fi and ThingSpeak is used for the remote transmission of information from coal mine to a central location. This technology may improve the safety and scale back accidents within the coal mines.
GRANT DETAILS
Minor Research Grant-Heat Exchanger Control using PLC 2018-19 (co investigator)(25000/- grant sanctioned)
