Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
3 results
Search Results
Item Deep Neural Network Models for Detection of Arrhythmia based on Electrocardiogram Reports(Institute of Electrical and Electronics Engineers Inc., 2020) Ghuge, S.; Kumar, N.; Shenoy, T.; Kamath S․, S.Electrocardiogram (ECG) is an indicative technique using which the heartbeat time series of a patient is recorded on the moving strip of paper or line on the screen, for irregularity analysis by experts, which is a time-consuming manual process. In this paper, we proposed a deep neural network for the automatic, real-time analysis of patient ECGs for arrhythmia detection. The experiments were performed on the ECG data available in the standard dataset, MIT-BID Arrhythmia database. The ECG signals were processed by applying denoising, detecting the peaks, and applying segmentation techniques, after which extraction of temporal features was performed and fed into a deep neural network for training. Experimental evaluation on a standard dataset, using the evaluation metrics accuracy, sensitivity, and specificity revealed that the proposed approach outperformed two state-of-the-art models with an improvement of 2-7% in accuracy and 11-16% in sensitivity. © 2020 IEEE.Item BEV Detection and Localisation using Semantic Segmentation in Autonomous Car Driving Systems(Institute of Electrical and Electronics Engineers Inc., 2021) Ashwin Nayak, U.; Naganure, N.; Kamath S․, S.In autonomous vehicles, the perception system plays an important role in environment modeling and object detection in 3D space. Existing perception systems use various sensors to localize and track the surrounding obstacles, but have some limitations. Most existing end-to-end autonomous systems are computationally heavy as they are built on multiple deep networks that are trained to detect and localize objects, thus requiring custom, high-end computation devices with high compute power. To address this issue, we propose and experiment with different semantic segmentation-based models for Birds Eye View (BEV) detection and localization of surrounding objects like vehicles and pedestrians from LiDAR (light detection, and ranging) point clouds. Voxelisation techniques are used to transform 3D LiDAR point clouds to 2D RGB images. The semantic segmentation models are trained from the ground up on the Lyft Level 5 dataset. During experimental evaluation, the proposed approach achieved a mean average precision score of 0.044 for UNET, 0.041 for SegNet and 0.033 for FCN, while being significantly less compute-intensive when compared to the state-of-the-art approaches. © 2021 IEEE.Item Reducing False Prediction on COVID-19 Detection Using Deep Learning(Institute of Electrical and Electronics Engineers Inc., 2021) Bhowmik, B.; Varna, S.A.; Kumar, A.; Kumar, R.This paper proposes a custom deep neural network-based scheme for coronavirus disease 2019 (COVID-19) detection. The proposed method takes X-ray images that use transfer learning techniques on pre-trained models. One objective of this work is to quickening the detection of the virus. Another goal is to reduce the number of falsely detected cases by a significant margin. The experimental setup demonstrates promising results on the selected dataset, which achieve up to 99.74%, 99.69%, 98.80% as classification, precision, and recall accuracy. © 2021 IEEE.