Denoising Medical Images With Machine & Deep Learning Aneesh Sai Praneeth, Savita Choudary 2025 2nd International Conference on New Frontiers in Communication Automation Management and Security Iccams 2025, 2025 Advancements in medical imaging technologies such as MRI, X-ray, CT and ultrasound have become a vital part of modern medical diagnosis. These images, however, often contain noise due to factors such as sensor imperfections and environmental influences to mention a few. This paper explores the fundamentals of denoising medical images, the role of Machine and Deep Learning models in the denoising phase and the evaluation of the models.
6G Cyber Security Resilience: Trends and Challenges Savita Choudhary, Abin P. John, Mayuk Sequeira, Soumya Bhattacharya, S. Mohammed Sohail Advanced Sciences and Technologies for Security Applications, 2025
Automated Detection of Polycystic Ovary Syndrome Using Convolutional Neural Networks on Ultrasound Images Varshitha D N, Gowrishankar B S, Sailaja Mulakaluri, Chaitra Nayak J, Savita Choudhary, Varshiya T Y, Sanjana B N Salud Ciencia Y Tecnologia, 2025 Polycystic Ovary Syndrome (PCOS) is a prevalent endocrine disorder affecting millions of women worldwide, yet it remains frequently underdiagnosed due to symptom variability and limited diagnostic resources. This paper presents a Convolutional Neural Network (CNN)-based system for automated PCOS detection from ultrasound images. The model leverages deep learning for accurate feature extraction and classification, aiming to support clinicians and improve diagnostic accessibility. Experimental results demonstrate high accuracy, underscoring the potential of AI-driven solutions in advancing women’s healthcare. Beyond accuracy, the system offers scalability, reduced diagnostic time, and potential integration into telemedicine platforms, highlighting its role in bridging healthcare gaps and enabling earlier intervention.
The new machine learning feature selection method used in fertilizer recommendation Varshitha D N, Savita Choudhary Bulletin of Electrical Engineering and Informatics, 2024 Fertilizer recommendation is the crucial factor to be considered in automation of agricultural predictions. Fertilizer fill the necessary portion of any farming region. There are some micronutrients and macro nutrients which need to be given to crops for proper growth. If fertilization is not done to an optimum level, it may badly harm the soil quality and crop health ,so optimum fertilization is important. In this paper we discuss fertilizer and nutrient recommender, where we have used a new feature selection methodology. We have shown the difference between two implementation cases considering presence and absence of feature ranking and selection. Feature ranking and selection has clearly increased the efficiency of the fertilizer nutrient recommender in our work from 85% to 98%. Feature selection raking has been introduced with random forest approach.
Hybrid classification framework for chronic kidney disease prediction model Smitha Patil, Savita Choudhary Imaging Science Journal, 2024 ‘Chronic kidney disease (CKD) – or chronic renal failure (CRF) is a term that encompasses all degrees of decreased kidney function, from damaged–at risk through mild, moderate, and severe chronic kidney failure’. As a risky factor, the disease has steadily turned out to be a major cause of death and morbidity. Accordingly, ultrasound (US) is significant in enhancing the rates of early recognition of CKD. Here, a new CKD detection model is introduced that includes ‘(1) Pre-processing (2) segmentation (3) Feature extraction, and (4) Classification’. Improved Gaussian filtering is used for pre-processing, and watershed-based segmentation is carried out. Additionally, features like the ROI, mean intensity, and the projected Local Vector Pattern (LVP) are retrieved. The ‘Optimized Neural Network (NN) and Long Short-Term Memory (LSTM)’ are then provided the output of the features. Additionally, using Self Updated Cat Swarm Optimization, the weights of NN are adjusted in order to increase the classifier's prediction accuracy (SU-CSO). The categorized output is then calculated by averaging the results from the improved NN and LSTM. Lastly, it is demonstrated that the proposed strategy is superior to other options.
Parametrized Optimization Based on an Investigation of Musical Similarities Using SPARK and Hadoop Savita Chaudhary, V. Karthik, R. Shankar, Ayesha Taranum, E. Naresh SN Computer Science, 2024 The big data processing framework Spark is used to power a parameterizable recommender system that can make recommendations for music based on a user’s individual tastes and take into account a variety of musical tonal qualities. The system as it is presently built is completely scalable, which means that additional songs can be contributed to the data, the cluster size could be increased, and new types of audio information, in addition to more cutting-edge similarity evaluations, may be included. Another issue discussed in this research paper is the parallel collection of required audio characteristics on a computer cluster. Song recommendations for a dataset including more than 114,000 songs may be created on a Spark cluster with 16 nodes in under 12 s by integrating eight distinct audio feature types and similarity assessments. After the features have been retrieved, they are sent to the Spark-based recommender system to be processed. The calculated distance was displayed, examined, and graphically depicted. By computing the distance depending on the melody, rhythmic, and timbral components of the music, the final software controls song suggestion.
Fragmentation aware heuristic algorithm for routing and wavelength assignment in optical networks Hamsaveni Mogannaiah, Savita Choudhary, Paramesha Kenchappa Indonesian Journal of Electrical Engineering and Computer Science, 2023 Wavelength division multiplexing (WDM) is one of the dominating technologies with high-capacity back bone networks. The cost associated with the high-capacity networks given more importance. The major issue is allocating and managing the available resources. To achieve this most efficient algorithms has to be used. We are considering the routing of lightpath and wavelength assignment problem, called as the routing and wavelength assignment (RWA) problem. The optimization of wavelength fragmentation in the WDM network is very much important in resource utilization. Wavelength fragmentation is one of the most important challenges in the area of the WDM network. Where it leads to some serious issues for the operators, such as the rejection of new requests. We are using integer linear program (ILP), here the problem is based on the node link formation. It is based on the multilayer concept and the original WDM network consists of several layers. We propose an efficient heuristic approach to solve this problem of finding the shortest path and assigning a wavelength without wavelength conversion. The model achieves better performance with fragmentation aware wavelength allocation strategy that minimizes fragmentation.
Prediction of Ultrasound Kidney Imaging Using Convolution Neural Networks Smitha Patil, Savita Choudhary Proceedings 2023 12th IEEE International Conference on Communication Systems and Network Technologies Csnt 2023, 2023 Deep learning is now being used in the medical field to detect ailments such as cancer, diabetes, kidney disease, etc. Kidney disease has become a major public health concern around the globe. If CKD is not diagnosed at an early stage, it can lead to loss of kidney function and which require costly treatments like dialysis and a kidney transplant. Using CNN, an automatic model has been developed to predict chronic renal disease. The major goal of this study is to predict CKD and non-CKD patients. Convolutional neural networks are used to classify chronic renal disease in this proposed system, and the batch prediction method is evaluated for CKD prediction. The precision with which renal disease can be predicted is 95%, and the accuracy for the classification of CKD ultrasound images using CNN is 80%.
Survey on Liver Disease Prediction and Recommendation Alvakonda Krishna Sai, Kuruba Geethika, Chaitanya Krishna Peddi, Haripriya D G, Savitha Choudhary Proceedings 2023 12th IEEE International Conference on Communication Systems and Network Technologies Csnt 2023, 2023 Liver is one among the crucial organs of a human body. If the liver’s normal functioning is compromised it leads to liver disease. The way people live today has completely changed, and many of them consume alcohol, unhealthy foods, energy drinks, self-medication, and other things like environmental pollution. And some of them continue to engage in these activities daily. Human livers will be severely damaged by this, and much suffering will result. Particularly heavy drinking makes many people more susceptible to liver failure and makes living a perilous life for them. The liver is the most important organ in humans, performing a wide range of tasks such as bile generation, bile and bilirubin excretion, protein and carbohydrate metabolism, enzyme activation, glycogen storage, vitamin and mineral absorption, plasma protein synthesis, and the manufacture of clotting factors. As a result, it is increasingly crucial to detect diseases at an early stage, as doing so enables the use of early, low-dose treatments to help prevent disease. However, because the signs of liver illness at the beginning are so minimal, it is too difficult to detect it. Machine learning holds great promise for automated disease diagnosis. The discovery and treatment of illnesses have undergone a complete transformation this is because of machine learning development in medicine. Machine learning model application in healthcare research includes knowledge extraction and decision support.
Comparative Analysis of 5G Security Mechanisms Tanya Sachdeva, Siddhant Kumar, Manoj Diwakar, Prabhishek Singh, Neeraj Kumar Pandey, Savita Choudhary 2023 6th International Conference on Information Systems and Computer Networks Iscon 2023, 2023 As networks continue to expand, they become increasingly heterogeneous, accommodating a diverse range of devices, from sensors and IoT to clients and servers. This ecosystem is highly distributed, with network facilities supporting many broadband devices, as well as device mobility and dynamic variations in networks, which makes them vulnerable to security attacks. In light of this, this paper reviews previous research on securing 5G networks and identifies the most effective methods. By analyzing various approaches, we determine which method is the most appropriate and provides the highest accuracy for securing our 5G networks. This review paper provides a valuable resource for those seeking to optimize the security of their 5G networks in the face of evolving security threats.
Detecting diabetic retinopathy using deep learning Yashal Shakti Kanungo, Bhargav Srinivasan, Savita Choudhary Rteict 2017 2nd IEEE International Conference on Recent Trends in Electronics Information and Communication Technology Proceedings, 2017
Digital technologies for achieving SDG 11 targets: A holistic systems-level perspective D Hariyani, P Hariyani, S Choudhary, S Mishra Sustainable Cities and Society: Advances, 100064 , 2026 2026 Citations: 2
6G Cyber Security Resilience: Trends and Challenges S Choudhary, AP John, M Sequeira, S Bhattacharya, ... 6G Cyber Security Resilience: Trends and Challenges, 47-75 , 2025 2025
Hybrid classification framework for chronic kidney disease prediction model S Patil, S Choudhary The Imaging Science Journal 72 (3), 367-381 , 2024 2024 Citations: 14
The new machine learning feature selection method used in fertilizer recommendation DN Varshitha Bulletin of Electrical Engineering and Informatics , 2024 2024 Citations: 3
Fragmentation aware heuristic algorithm for routing and wavelength assignment in optical networks H Mogannaiah, S Choudhary, P Kenchappa Indonesian Journal of Electrical Engineering and Computer Science 31 (1 … , 2023 2023
Examining the Algorithms used for Routing and Assigning Wavelength in WDM Networks M Hamsaveni, S Choudhary Research Highlights in Mathematics and Computer Science Vol. 8 8, 153-164 , 2023 2023
Prediction of ultrasound kidney imaging using convolution neural networks S Patil, S Choudhary 2023 IEEE 12th International Conference on Communication Systems and Network … , 2023 2023 Citations: 9
A bootstrap aggregation approach for adequate crop fertilizer and nutrition recommendation DN Varshitha, S Choudhary Indones. J. Electr. Eng. Comput. Sci 26, 1773-1780 , 2022 2022 Citations: 3
An artificial intelligence solution for crop recommendation DN Varshitha, S Choudhary Indonesian Journal of Electrical Engineering and Computer Science 25 (3 … , 2022 2022 Citations: 29
Digital Enterprise Software Productivity Metrics and Enhancing Their Business Impacts Using Machine Learning V Gaurav, S Choudhary Enterprise Digital Transformation, 413-430 , 2022 2022
Soil fertility and yield prediction of coffee plantation using machine learning technique DN Varshitha, S Choudhary Res J Agric Sci 13, 514-518 , 2022 2022 Citations: 10
Deep convolutional neural network for chronic kidney disease prediction using ultrasound imaging S Patil, S Choudhary Bio-Algorithms and Med-Systems 17 (2), 137-163 , 2021 2021 Citations: 11
Multilingual medical question answering and information retrieval for rural health intelligence access V Vinod, S Agrawal, V Gaurav, S Choudhary arXiv preprint arXiv:2106.01251 , 2021 2021 Citations: 5
Mining intelligent patterns using svac for precision agriculture and optimizing irrigation (student abstract) V Vinod, V Gaurav, T Sharma, S Choudhary Proceedings of the AAAI Conference on Artificial Intelligence 35 (18), 15909 … , 2021 2021 Citations: 2
RainRoof: automated shared rainwater harvesting prediction V Gaurav, V Vinod, SK Singh, T Sharma, KR Pradyumna, S Choudhary Sustainable Communication Networks and Application: Proceedings of ICSCN … , 2021 2021 Citations: 8
A multi-objective optimization algorithm for routing path selection and wavelength allocation for dynamic WDM network using MO-HLO M Hamsaveni, S Choudhary International Journal of Engineering and Advanced Technology (IJEAT) 10 (5 … , 2021 2021 Citations: 6
Towards Practical and Efficient Computer Vision Models for Extreme-Weather Scenarios in Urban Mobility V Vinod, S Choudhary 2021
An AI solution for soil fertility and crop friendliness detection and monitoring DN Varshitha, S Choudhary International Journal of Engineering and Advanced Technology 10 (3), 172-175 , 2021 2021 Citations: 20
Forecasting dengue and studying its plausible pandemy using machine learning S Choudhary, V Gaurav, T Sharma, P KR Proceedings of the Second International Conference on Emerging Trends in … , 2019 2019 Citations: 1
Autonomous crop irrigation system using artificial intelligence S Choudhary, V Gaurav, A Singh, S Agarwal Int. J. Eng. Adv. Technol 8 (5), 46-51 , 2019 2019 Citations: 84
MOST CITED SCHOLAR PUBLICATIONS
Autonomous crop irrigation system using artificial intelligence S Choudhary, V Gaurav, A Singh, S Agarwal Int. J. Eng. Adv. Technol 8 (5), 46-51 , 2019 2019 Citations: 84
Detecting diabetic retinopathy using deep learning YS Kanungo, B Srinivasan, S Choudhary 2017 2nd IEEE International Conference on Recent Trends in Electronics … , 2017 2017 Citations: 84
An artificial intelligence solution for crop recommendation DN Varshitha, S Choudhary Indonesian Journal of Electrical Engineering and Computer Science 25 (3 … , 2022 2022 Citations: 29
An AI solution for soil fertility and crop friendliness detection and monitoring DN Varshitha, S Choudhary International Journal of Engineering and Advanced Technology 10 (3), 172-175 , 2021 2021 Citations: 20
Collaborative job prediction based on Naïve Bayes Classifier using python platform S Choudhary, S Koul, S Mishra, A Thakur, R Jain 2016 international conference on computation system and information … , 2016 2016 Citations: 20
Comparative study and implementation of supervised and unsupervised models for recognizing handwritten Kannada characters S Sen, SV Prabhu, S Jerold, JS Pradeep, S Choudhary 2018 3rd IEEE International Conference on Recent Trends in Electronics … , 2018 2018 Citations: 16
Hybrid classification framework for chronic kidney disease prediction model S Patil, S Choudhary The Imaging Science Journal 72 (3), 367-381 , 2024 2024 Citations: 14
Text detection and recognition from scene images using mser and cnn S Choudhary, NK Singh, S Chichadwani 2018 Second International Conference on Advances in Electronics, Computers … , 2018 2018 Citations: 13
Deep convolutional neural network for chronic kidney disease prediction using ultrasound imaging S Patil, S Choudhary Bio-Algorithms and Med-Systems 17 (2), 137-163 , 2021 2021 Citations: 11
Soil fertility and yield prediction of coffee plantation using machine learning technique DN Varshitha, S Choudhary Res J Agric Sci 13, 514-518 , 2022 2022 Citations: 10
Prediction of ultrasound kidney imaging using convolution neural networks S Patil, S Choudhary 2023 IEEE 12th International Conference on Communication Systems and Network … , 2023 2023 Citations: 9
RainRoof: automated shared rainwater harvesting prediction V Gaurav, V Vinod, SK Singh, T Sharma, KR Pradyumna, S Choudhary Sustainable Communication Networks and Application: Proceedings of ICSCN … , 2021 2021 Citations: 8
A multi-objective optimization algorithm for routing path selection and wavelength allocation for dynamic WDM network using MO-HLO M Hamsaveni, S Choudhary International Journal of Engineering and Advanced Technology (IJEAT) 10 (5 … , 2021 2021 Citations: 6
Multilingual medical question answering and information retrieval for rural health intelligence access V Vinod, S Agrawal, V Gaurav, S Choudhary arXiv preprint arXiv:2106.01251 , 2021 2021 Citations: 5
The new machine learning feature selection method used in fertilizer recommendation DN Varshitha Bulletin of Electrical Engineering and Informatics , 2024 2024 Citations: 3
A bootstrap aggregation approach for adequate crop fertilizer and nutrition recommendation DN Varshitha, S Choudhary Indones. J. Electr. Eng. Comput. Sci 26, 1773-1780 , 2022 2022 Citations: 3
Digital technologies for achieving SDG 11 targets: A holistic systems-level perspective D Hariyani, P Hariyani, S Choudhary, S Mishra Sustainable Cities and Society: Advances, 100064 , 2026 2026 Citations: 2
Mining intelligent patterns using svac for precision agriculture and optimizing irrigation (student abstract) V Vinod, V Gaurav, T Sharma, S Choudhary Proceedings of the AAAI Conference on Artificial Intelligence 35 (18), 15909 … , 2021 2021 Citations: 2
Forecasting dengue and studying its plausible pandemy using machine learning S Choudhary, V Gaurav, T Sharma, P KR Proceedings of the Second International Conference on Emerging Trends in … , 2019 2019 Citations: 1
Design of handwritten signature verification using java–python platform S Choudhary, S Mishra, S Kaul, JB Arun Emerging Research in Computing, Information, Communication and Applications … , 2016 2016 Citations: 1
