Rakesh Kalshetty

@msrit.edu

Assistant Professor at CSE(Artificial Intelligence and Machine Learning), CSE(Cyber Security) and M.Tech., in AI Department
M S Ramaiah Institute of Techonlogy

Rakesh Kalshetty


                                    Download Compact PDF  
https://researchid.co/rakeshsk
Working as Assistant Professor, AWS Educator, BoE, Placement & Social Media Coordinator in Department of CSE(Artificial Intelligence and Machine Learning), CSE(Cyber Security) and M.Tech., in AI at M S Ramaiah Institute of Technology , having 4+ years of Experience as Design Engineer at Shri Siddhi Vinayak Constructions and Builders. I am also a life time Member of IAENG and ISTE. Professional Member of AIER and IEEE. My area of interest are Wireless Sensor Networks, Machine Learning and Internet of Things.

EDUCATION

Ph.D. from Visvesvaraya Technological University in the research area of Wireless Sensor Networks, Machine Learning and Internet of Things. Completed my Bachelor of Engineering and Master of Technology from Poojya Doddappa Appa College of Engineering.

RESEARCH, TEACHING, or OTHER INTERESTS

Artificial Intelligence, Computer Vision and Pattern Recognition, Computer Networks and Communications, Computer Science
4

Scopus Publications

33

Scholar Citations

2

Scholar h-index

1

Scholar i10-index

Scopus Publications

  • A Critical Benchmark of Hybrid Quantum-Classical Graph Neural Networks for Molecular Property Prediction: Revealing Performance Bottlenecks in Current Architectures
    Rakesh Kalshetty, Manish S M, Shashank Kotagi, Vishwas Desai
    2025 9th International Conference on Computational System and Information Technology for Sustainable Solutions Csitss 2025, 2025
    Hybrid quantum-classical neural networks (HQCNNs) represent a promising but largely unproven paradigm for enhancing molecular property prediction in drug discovery. Despite growing interest and optimistic claims in recent literature, rigorous benchmarks comparing these hybrid architectures against strong classical baselines remain scarce. This work implements and systematically evaluates a representative HQCNN architecture against its classical equivalent using standardized molecular datasets (QM9 and ZINC-250K) within a reproducible, multi-seed experimental framework. Contrary to optimistic expectations, our results reveal that the hybrid model consistently underperforms the classical baseline, showing a 49% increase in MAE on QM9 (1.0834 vs 0.7256) and a devastating 107% degradation on ZINC (1.4006 vs 0.6755), with R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> values dropping by over 80% on both datasets. Through detailed analysis, we identify fundamental challenges including information bottlenecks during quantum encoding and difficult optimization landscapes in variational quantum circuits as primary causes of performance degradation. This work provides a crucial, datadriven reality check for the field, demonstrating that current “plug-and-play” quantum layer approaches may be insufficient for practical quantum advantages. All experimental code and data are publicly released to enable community replication and investigation of more sophisticated quantum-native architectures.
  • Polycystic Ovary Syndrome Detection Using Contextual Ensemble Network and ELMAN Neural Network with Green Anaconda Optimization
    Rakesh Kalshetty, N. Vedavathi, M. Narender, C. I. Johnpaul, Tojo Mathew
    Journal of Multiscale Modelling, 2024
    Polycystic Ovary Syndrome (PCOS) is a metabolic reproductive disorder characterized condition by an extended menstrual cycle. There are many methods currently in use, but they all have major limitations. The prediction rate, which takes longer due to factors like heterogeneity is one of the main aspects of PCOS that makes it difficult. Moreover, there was no correlation between the network’s generalization ability assessment and precise predictions. The ELMAN Neural Network has been used to identify PCOS in order to eliminate the aforementioned problems. The ovarian ultrasound image is pre-processed with Fast Local Laplacian Filter (FLLF) and Brightness Preserving Bi-Histogram Equalization. The Contextual Ensemble Network (CENET) is used in the segmentation process and the textural features are extracted using the Projective Integral (PI) and the color features are extracted using the Color Auto Correlogram (CAC). Finally, an Elman Network with a Green Anaconda Optimization (GAO) is employed for classification purposes to diagnose PCOS. According to the results of the experimental research, the proposed ELMAN network has an accuracy of 95%, 93% for precision, 92.5% for recall, 90% for specificity, F1-score is 91%. Thus, the CENET with ELMAN Neural Network for PCOS detection from ultrasound images was considerably simpler and more efficient.
  • Abnormal event detection model using an improved ResNet101 in context aware surveillance system
    Rakesh Kalshetty, Asma Parveen
    Cognitive Computation and Systems, 2023
    Surveillance system plays a significant role for achieving security monitoring in the place of crowd areas. Offline monitoring of these crowd activity is quite challenging because it requires huge number of human resources for attaining efficient tracking. For shortcoming these issue automated and intelligent based system must be developed for efficiently monitor crowd and detect abnormal activity. However the existing methods faces issues like irrelevant features, high cost and process complexity. In this current research context aware surveillance‐system utilising hybrid ResNet101‐ANN is developed for effective abnormal activity detection. For this proposed approach video acquired from surveillance camera is considered as input. Then, acquired video is segmented into multiple frames. After that pre‐processing techniques such as denoising using mean filter, motion deblurring, contrast enhancement using Histogram Equalisation and canny edge detection is applied in this segmented frames. Further, the pre‐processed frame is fetched into hybrid ResNet101‐ANN classifier for abnormal event classification. Here, ResNet101 is used for extracting the features from the frames and Artificial neural network which replaces the fully connected layer of ResNet101 us used to detect the abnormal activity. If once abnormal‐events detected the context aware services generate alert to the user for preventing abnormal‐activities. Accuracy, precision, recall, and error values reached for the proposed‐model on simulation were 0.98, 0.98, 0.98 and 0.017 respectively. Using this proposed model effective crowd monitoring and abnormal activity detection can be achieved.
  • The various surveillance and detection techniques based on wireless sensor networks
    Rakesh Kalshetty, Asma Parveen
    Proceedings of the 2020 International Conference on Smart Innovations in Design Environment Management Planning and Computing Icsidempc 2020, 2020
    In this paper, we describe multiple methods used for surveillance and tracking of abnormalities instead of a commercial image processing system, we build an efficient surveillance system in areas of interest by utilizing internet of things and wireless sensors platform. The kinds of cameras and sensors considered that are to be deployed in the area of interest for monitoring suspicious behavior of intruders and conditions such as temperature, humidity, and fire accidents. Then the sensed data is collected and processed locally then transmitted wirelessly to alert an administrator or caretaker about mishappening in the area of interest.

RECENT SCHOLAR PUBLICATIONS

  • Polycystic Ovary Syndrome Detection Using Contextual Ensemble Network and ELMAN Neural Network with Green Anaconda Optimization
    R Kalshetty, N Vedavathi, M Narender, CI Johnpaul, T Mathew
    Journal of Multiscale Modelling 15 (04), 2450007 , 2024
    2024
    Citations: 4
  • Abnormal event detection model using an improved ResNet101 in context aware surveillance system
    R Kalshetty, A Parveen
    Cognitive Computation and Systems 5 (2), 153-167 , 2023
    2023
    Citations: 27
  • Survey on Encoding Binary Data within a Digital Image Using Deep Steganography and Multilayered Neural Network
    A Singh, A Kumar, D Raj, S Jha, R Kalshetty
    Int J Res Appl Sci Eng Technol 11 (3), 1515-1519 , 2023
    2023
    Citations: 1
  • The various surveillance and detection techniques based on wireless sensor networks
    R Kalshetty, A Parveen
    2020 International Conference on Smart Innovations in Design, Environment … , 2020
    2020
    Citations: 1

MOST CITED SCHOLAR PUBLICATIONS

  • Abnormal event detection model using an improved ResNet101 in context aware surveillance system
    R Kalshetty, A Parveen
    Cognitive Computation and Systems 5 (2), 153-167 , 2023
    2023
    Citations: 27
  • Polycystic Ovary Syndrome Detection Using Contextual Ensemble Network and ELMAN Neural Network with Green Anaconda Optimization
    R Kalshetty, N Vedavathi, M Narender, CI Johnpaul, T Mathew
    Journal of Multiscale Modelling 15 (04), 2450007 , 2024
    2024
    Citations: 4
  • Survey on Encoding Binary Data within a Digital Image Using Deep Steganography and Multilayered Neural Network
    A Singh, A Kumar, D Raj, S Jha, R Kalshetty
    Int J Res Appl Sci Eng Technol 11 (3), 1515-1519 , 2023
    2023
    Citations: 1
  • The various surveillance and detection techniques based on wireless sensor networks
    R Kalshetty, A Parveen
    2020 International Conference on Smart Innovations in Design, Environment … , 2020
    2020
    Citations: 1