Prakash Tunga P

@rnsit.ac.in

Associate Professor, Department of Electronics and Communication Engineering
RNS Institute of Technology

Prakash Tunga P


                           Download Compact PDF  
https://researchid.co/prakash_tunga

RESEARCH, TEACHING, or OTHER INTERESTS

Electrical and Electronic Engineering, Artificial Intelligence
6

Scopus Publications

44

Scholar Citations

3

Scholar h-index

2

Scholar i10-index

Scopus Publications

  • Physical Design Implementation to Enhance Performance of Ultra-Deep Sub-micron (UDSM) Hard Macro-based Design
    Prasad Shenoy, N. Shylashree, Nandini K. S., Prakash Tunga P.
    Wseas Transactions on Electronics, 2024
    Lower technology nodes or Ultra Deep Sub-micron (UDSM) used in today’s System on-chip (SoC) yield high performance and are faster when compared to the Deep Sub-micron (DSM) technology nodes. The challenges faced by a designer have increased multi-fold in SoC design with the technology node evolution. The designs that are trending these days are Hard Macro (HM) based designs. The entire block is divided in the sub- HMs or hierarchical blocks. The sub-HM layout shapes are decided during the partitioning of the top-level block. Each of the hierarchical blocks is implemented separately and the sub-HMs are integrated at the top level to reduce the huge run-time and to reduce the burden of improving the PPA. The processes involved in Physical Design (PD) are interlinked and the effect of the previous process can be seen in the subsequent stages. CTS is implemented using Flexible-H-tree (FHT) with Multiple tap point structure. Experimental results on an industrial design having more than a million instances show that the implementation of the proposed clock tree structure comprising of FHT with Multitap point CTS (DB2), in the design, shows huge improvement in terms of timing and clock metrics when compared to the conventional CTS (DB1). A reduction of 40.47% and 63.9% is seen in terms of hold WNS and hold TNS respectively from DB1 to DB2. The NFE is reduced by 27.33% from DB1 to DB2. DB2 has a clock latency of 1.073 ns which is 27% lesser than that of DB1. Global Skew is reduced by 15.48% and local skew by 20%. Innovus tool is used for the implementation of the design.
  • RAKSHAK - An Energy Efficient Intelligent Helmet
    Aditya Venkata Sheshu, Prakash Tunga P, Sumukha M, Vineeth Kumar Kori
    2022 IEEE Pune Section International Conference Punecon 2022, 2022
    Wearable technology is gaining popularity, being employed in a variety of applications, and wearable safety devices have found high demand in the market as of late. This project work relates to an important area of application for wearable devices, which is road safety. The roads of developing and under-developed countries tend to be largely unsafe and vulnerable to accidents especially for two wheeler users. Apart from the riders own safety, the chaotic environment in roads and highways in such countries also poses safety concerns for the public which is often overlooked. Another key issue with the use of wearable devices is minimizing electronic waste. As environmental issues are a growing concern, it is crucial to use energy efficient methods wherever possible in developing technology. Our proposed device RAKSHAK (meaning ‘protector’ in Hindi) is a secure riding helmet that strives to strike an immaculate balance between incorporating several novel and thoughtful intelligent features involving Machine Learning and the Internet of Things for safety and convenience, as well as taking an environment friendly approach to consumer electronics by using a renewable energy source.
  • U-Net Model-Based Classification and Description of Brain Tumor in MRI Images
    P. Prakash Tunga, Vipula Singh, V. Sri Aditya, N. Subramanya
    International Journal of Image and Graphics, 2021
    In this paper, we discuss the classification of the brain tumor in Magnetic Resonance Imaging (MRI) images using the U-Net model, then evaluate parameters that indicate the performance of the model. We also discuss the extraction of the tumor region from brain image and description of the tumor regarding its position and size. Here, we consider the case of Gliomas, one of the types of brain tumors, which occur in common and can be fatal depending on their position and growth. U-Net is a model of Convolutional Neural Network (CNN) which has U-shaped architecture. MRI employs a non-invasive technique and can very well provide soft-tissue contrast and hence, for the detection and description of the brain tumor, this imaging method can be beneficial. Manual delineation of tumors from brain MRI is laborious, time-consuming and can vary from expert to expert. Our work forms a computer aided technique which is relatively faster and reproducible, and the accuracy is very much on par with ground truth. The results of the work can be used for treatment planning and further processing related to storage or transmission of images.
  • Compression of MRI brain images based on automatic extraction of tumor region
    Prakash Tunga P., Vipula Singh
    International Journal of Electrical and Computer Engineering, 2021
    In the compression of medical images, region of interest (ROI) based techniques seem to be promising, as they can result in high compression ratios while maintaining the quality of region of diagnostic importance, the ROI, when image is reconstructed. In this article, we propose a set-up for compression of brain magnetic resonance imaging (MRI) images based on automatic extraction of tumor. Our approach is to first separate the tumor, the ROI in our case, from brain image, using support vector machine (SVM) classification and region extraction step. Then, tumor region (ROI) is compressed using Arithmetic coding, a lossless compression technique. The non-tumorous region, non-region of interest (NROI), is compressed using a lossy compression technique formed by a combination of discrete wavelet transform (DWT), set partitioning in hierarchical trees (SPIHT) and arithmetic coding (AC). The classification performance parameters, like, dice coefficient, sensitivity, positive predictive value and accuracy are tabulated. In the case of compression, we report, performance parameters like mean square error and peak signal to noise ratio for a given set of bits per pixel (bpp) values. We found that the compression scheme considered in our setup gives promising results as compared to other schemes.
  • Brain Tumor Extraction from MRI Using Clustering Methods and Evaluation of Their Performance
    P Prakash Tunga, Vipula Singh
    Proceedings 2018 4th International Conference on Computing Communication Control and Automation Iccubea 2018, 2018
    In this paper, we consider the extraction of brain tumor from MRI (Magnetic Resonance Imaging) images using K-means, Fuzzy c-means and Region growing clustering methods. After extraction, various parameters related to performance of clustering methods, and also, parameters related to description of tumor are calculated. MRI is a non-invasive method which provides the view of structural features of tissues in the body at very high resolution (typically on $100 \\mu \\text{m}$ scale). Therefore, it will be advantageous if the detection and segmentation of brain tumors are based on MRI. This work is in the direction of replacing the manual identification and separation of tumor structures from brain MRI by computer aided techniques, which would add great value with respect to accuracy, reproducibility, diagnosis and treatment planning. The brain tumor separated from original image is referred as Region of Interest (ROI) and remaining portion of original image is referred as Non-region of Interest (NROI).
  • Extraction and description of tumour region from the brain MRI image using segmentation techniques
    P Prakash Tunga, Vipula Singh
    2016 IEEE International Conference on Recent Trends in Electronics Information and Communication Technology Rteict 2016 Proceedings, 2017
    Image segmentation refers to partitioning of image into multiple regions (segments) eventually leading to meaningful representation of image through which information can be extracted. Magnetic Resonance Imaging (MRI) is a non-invasive method which provides the detailed view of internal structure of tissues in the body at very high resolution. This paper focuses on extraction of brain tumor and its region description through segmentation from the brain MRI image. At first, pre-processing step for noise removal is carried out. Brain tumor extraction is done by considering the methods based on k-means clustering, morphological operations and region growing. A comparative analysis of the three methods is done for various brain MR images. Here we refer the tumor in the brain MRI as region of interest (ROI) and rest of the image is referred as Non-region of interest (NROI).

RECENT SCHOLAR PUBLICATIONS

  • Design of medium grain integrated clock gater for low power clock network
    S Nagaraja, A Sathisha, M A Shivaraj, LB Nanjudappa, P P Tunga
    International Journal of Reconfigurable and Embedded Systems 14 (1), 117-125 , 2025
    2025
  • Physical Design Implementation to Enhance Performance of Ultra-Deep Sub-micron (UDSM) Hard Macro-based Design
    KS Nandini, P Prakash Tunga
    2024
  • RAKSHAK - An Energy Efficient Intelligent Helmet
    AV Sheshu, P Tunga P, S M, VK Kori
    2022 IEEE Pune Section International Conference (PuneCon) , 2022
    2022
    Citations: 3
  • U-net model-based classification and description of brain tumor in MRI images
    PP Tunga, V Singh, VS Aditya, N Subramanya
    International Journal of Image and Graphics 21 (05), 2140005 , 2021
    2021
    Citations: 3
  • Compression of MRI brain images based on automatic extraction of tumor region.
    P P Tunga, V Singh
    International Journal of Electrical & Computer Engineering (2088-8708) 11 (5) , 2021
    2021
    Citations: 14
  • Automatic Brain Tumor Segmentation using Dense-Net
    VS Vilas B M, Abhinav Narayan, Akshatha H, Manjushree M, Prakash Tunga P
    International Research Journal of Engineering and Technology (IRJET) 7 (6 … , 2020
    2020
    Citations: 2
  • Extraction of Tumor in Brain MRI using Support Vector Machine and Performance Evaluation
    P Tunga, V Singh
    VTU Journal of Engineering Sciences and Management 1 (3), 1-8 , 2019
    2019
    Citations: 2
  • Brain Tumor Extraction from MRI Using Clustering Methods and Evaluation of Their Performance
    PP Tunga, V Singh
    2018 Fourth International Conference on Computing Communication Control and … , 2019
    2019
    Citations: 3
  • Extraction and description of tumour region from the brain MRI image using segmentation techniques
    PP Tunga, V Singh
    2016 IEEE International Conference on Recent Trends in Electronics … , 2016
    2016
    Citations: 17

MOST CITED SCHOLAR PUBLICATIONS

  • Extraction and description of tumour region from the brain MRI image using segmentation techniques
    PP Tunga, V Singh
    2016 IEEE International Conference on Recent Trends in Electronics … , 2016
    2016
    Citations: 17
  • Compression of MRI brain images based on automatic extraction of tumor region.
    P P Tunga, V Singh
    International Journal of Electrical & Computer Engineering (2088-8708) 11 (5) , 2021
    2021
    Citations: 14
  • RAKSHAK - An Energy Efficient Intelligent Helmet
    AV Sheshu, P Tunga P, S M, VK Kori
    2022 IEEE Pune Section International Conference (PuneCon) , 2022
    2022
    Citations: 3
  • U-net model-based classification and description of brain tumor in MRI images
    PP Tunga, V Singh, VS Aditya, N Subramanya
    International Journal of Image and Graphics 21 (05), 2140005 , 2021
    2021
    Citations: 3
  • Brain Tumor Extraction from MRI Using Clustering Methods and Evaluation of Their Performance
    PP Tunga, V Singh
    2018 Fourth International Conference on Computing Communication Control and … , 2019
    2019
    Citations: 3
  • Automatic Brain Tumor Segmentation using Dense-Net
    VS Vilas B M, Abhinav Narayan, Akshatha H, Manjushree M, Prakash Tunga P
    International Research Journal of Engineering and Technology (IRJET) 7 (6 … , 2020
    2020
    Citations: 2
  • Extraction of Tumor in Brain MRI using Support Vector Machine and Performance Evaluation
    P Tunga, V Singh
    VTU Journal of Engineering Sciences and Management 1 (3), 1-8 , 2019
    2019
    Citations: 2
  • Design of medium grain integrated clock gater for low power clock network
    S Nagaraja, A Sathisha, M A Shivaraj, LB Nanjudappa, P P Tunga
    International Journal of Reconfigurable and Embedded Systems 14 (1), 117-125 , 2025
    2025
  • Physical Design Implementation to Enhance Performance of Ultra-Deep Sub-micron (UDSM) Hard Macro-based Design
    KS Nandini, P Prakash Tunga
    2024