Browsing by Author "Sharma, K."

Now showing 1 - 11 of 11

Accurate detection of congestive heart failure using electrocardiomatrix technique
(Springer, 2022) Sharma, K.; Mohan Rao, B.M.; Marwaha, P.; Kumar, A.
Congestive Heart Failures (CHFs) are prevalent, expensive, and deadly, causing damage or overload to the pumping power of the heart muscles. These leads to severe medical issues amongst humans and contribute to a greater death risk of numerous diseases at a later stage. We need accurate and less difficult techniques to detect these problems in our world with a growing population which will prevent many diseases and reduce deaths. In this work, we have developed a technique to diagnose CHF using the Electrocardiomatrix (ECM) technique. The 1-D ECG signals are transformed to a colourful 3D matrix to diagnose CHF. The detection of CHF using ECM are then compared with annotated CHF Electrocardiogram (ECG) signals manually. It has been found that ECM is able to detect the affected CHF duration from the ECG signals. Also, the ECM provides the reduction in both false positive and false negative which in turn improves the detection accuracy. The performance of the proposed approach has been tested on BIDMC CHF database. The proposed method achieved an accuracy of 97.6%, sensitivity of 98.0%, specificity of 97.0%, precision of 99.4%, and F1-Score of 98.3%. From this study, it has been revealed that the ECM technique allows the accurate, intuitive, and efficient detection of CHF and using ECM practitioners can diagnose the CHF without sacrificing the accuracy. © 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
Broad band parasitically coupled concentric semi circular elliptically ring antenna surrounding an elliptical patch with air gap
(2009) Bhardwaj, D.; Sharma, K.; Bhatnagar, D.; Sancheti, S.
The paper presents the performance of a parasitically coupled semi circular elliptical ring antenna surrounding elliptical patch geometry having air gap between conducting patch and ground plane. With proposed modifications in the conventional circular patch geometry, the bandwidth of modified antenna with an air gap is around seven times higher than that of a simple circular patch antenna. The gain, directivity and efficiency of modified circular patch antenna with air gap is also improved to some extent but still these are less than desired values. The E and H plane radiation patterns presented by antenna in the frequency range where broadband performance is obtained are identical in shape and nature. Direction of maximum intensity retained by antenna at both frequencies is normal to patch geometry. �2009 IEEE.
Broad band parasitically coupled concentric semi circular elliptically ring antenna surrounding an elliptical patch with air gap
(2009) Bhardwaj, D.; Sharma, K.; Bhatnagar, D.; Sancheti, S.
The paper presents the performance of a parasitically coupled semi circular elliptical ring antenna surrounding elliptical patch geometry having air gap between conducting patch and ground plane. With proposed modifications in the conventional circular patch geometry, the bandwidth of modified antenna with an air gap is around seven times higher than that of a simple circular patch antenna. The gain, directivity and efficiency of modified circular patch antenna with air gap is also improved to some extent but still these are less than desired values. The E and H plane radiation patterns presented by antenna in the frequency range where broadband performance is obtained are identical in shape and nature. Direction of maximum intensity retained by antenna at both frequencies is normal to patch geometry. Â©2009 IEEE.
Design and analysis of a gap coupled split circular patch with elliptical slot filled with elliptical patch
(2010) Bhardwaj, D.; Sharma, K.; Bhatnagar, D.; Sancheti, S.; Soni, B.
The paper presents radiation performance of a gap coupled split circular patch with elliptical slot filled with elliptical patch. Initially, a circular elliptical ring slot antenna is taken and it is modified step by step to achieve an end product with desired performance. The performance of designed antenna after each step is presented systematically. The simulated and measured results of proposed antenna are compared with that of a circular elliptical ring slot antenna. The gap between two gap-coupled semi circular elliptical ring structures and the length of major and minor axis of inserted inner elliptical patch are optimized to achieve best performance. It is observed that with proposed modifications in circular patch geometry, impedance bandwidth, gain and radiation efficiency of antenna are improved considerably. The resonance frequency of end product is lower than that of a circular elliptical ring slot antenna which indicates that for achieving identical resonance frequencies from circular elliptical ring slot antenna and modified circular patch geometry, effective patch size of modified antenna must be reduced. The outcome results into a further compact circular patch antenna with much improved performance.
Design and analysis of a gap coupled split circular patch with elliptical slot filled with elliptical patch
(2010) Bhardwaj, D.; Sharma, K.; Bhatnagar, D.; Sancheti, S.; Soni, B.
The paper presents radiation performance of a gap coupled split circular patch with elliptical slot filled with elliptical patch. Initially, a circular elliptical ring slot antenna is taken and it is modified step by step to achieve an end product with desired performance. The performance of designed antenna after each step is presented systematically. The simulated and measured results of proposed antenna are compared with that of a circular elliptical ring slot antenna. The gap between two gap-coupled semi circular elliptical ring structures and the length of major and minor axis of inserted inner elliptical patch are optimized to achieve best performance. It is observed that with proposed modifications in circular patch geometry, impedance bandwidth, gain and radiation efficiency of antenna are improved considerably. The resonance frequency of end product is lower than that of a circular elliptical ring slot antenna which indicates that for achieving identical resonance frequencies from circular elliptical ring slot antenna and modified circular patch geometry, effective patch size of modified antenna must be reduced. The outcome results into a further compact circular patch antenna with much improved performance.
Design and Development of an Emulation Model for VPN and VPN Bonding
(Institute of Electrical and Electronics Engineers Inc., 2024) Sharma, K.; Tahiliani, M.P.; Rathod, V.J.
Virtual Private Networks (VPNs) have become indispensable for organizations seeking secure remote network access, with a significant rise in their adoption. While the COVID-19 pandemic initially fueled the surge in remote work and VPN usage, the trend has continued post-pandemic as organizations increasingly opt for hybrid work models. VPNs allow users to establish secure connections to their organization's network from any location, ensuring the confidentiality of transmitted data. Moreover, VPN bonding, which combines multiple VPN connections into a unified interface, improves performance and reliability, particularly in areas with limited Internet connectivity. As the usage of VPN and VPN bonding technologies continues to expand, a growing demand arises for research in this field, and consequently, the need for robust emulators and simulators. However, existing network emulators or simulators currently lack comprehensive support for VPN-related technologies. To address these limitations, this paper aims to develop intuitive and user-friendly Application Programming Interfaces (APIs) for emulating VPN and VPN bonding in Network Stack Tester (NeST), a powerful Python package designed to facilitate network emulation for experienced researchers and individuals new to the field. This work utilizes OpenVPN, a secure tunneling daemon, to integrate the support of VPN emulation in NeST. By augmenting the capabilities of NeST, this work intends to provide researchers with a valuable toolset for exploring and testing VPN and VPN bonding technologies across diverse network environments. Â© 2024 IEEE.
Design and development of an experimental setup for nanofinishing of exhaust valves using magnetorheological finishing to enhance functional performance
(Springer-Verlag Italia s.r.l., 2025) Sharma, K.; Singh, V.K.; Singh Rajput, A.S.; Das, M.
Exhaust valves in high-performance and racing engines require ultra-smooth surfaces to improve durability and operational efficiency. This study investigates the application of Magnetorheological (MR) polishing for finishing exhaust valve seats. MR fluid, consisting of micron-sized magnetic particles suspended in a carrier liquid, forms a semi-solid structure under a magnetic field, enabling precise surface finishing. An in-house experimental setup was developed, and various magnet configurations were tested to optimize the polishing zone. Computational investigations were conducted to analyze magnetic field distribution for 2-bar, 3-bar, 4-bar, and 5-bar magnet systems, with results validated using a Gauss-meter. Unlike prior MR polishing studies that focused mainly on optical or biomedical components, our work emphasizes automotive engine applications and demonstrates the optimization of a 4-magnet system to achieve uniform magnetic field distribution. The novelty lies in developing a cost-effective, adaptable, and reproducible MR polishing arrangement tailored for curved valve geometries, while addressing reproducibility through detailed experimental parameters. The primary objective was to optimize process parameters for MR polishing. Under optimal conditions—spindle speed of 750 RPM, stand-off distance of 1.5 mm, and polishing time of 17.5 min—the surface roughness (Ra) improved significantly from 0.613 ?m to 0.115 ?m. Measurements were performed using a 3D profilometer. Further surface characterization via Atomic Force Microscopy (AFM) showed a reduction in surface asperities, while Field Emission Scanning Electron Microscopy (FE-SEM) revealed fewer surface scratches. These results confirm the potential of MR polishing as an effective technique for enhancing the surface finish of critical engine components. © The Author(s), under exclusive licence to Springer-Verlag France SAS, part of Springer Nature 2025.
Hybrid Genetic Algorithm and Machine Learning Approach for Software Reliability Assessment in Safety-Critical Systems
(Institute of Electrical and Electronics Engineers Inc., 2024) Goyal, G.; Sharma, K.; Anshuman; Mittal, V.; Singla, B.; Das, M.; Mohan, B.R.
Software reliability is a paramount determinant of software quality. In this research paper, we delve into utilizing Genetic Algorithms (GAs) for feature selection and classification. We undertake a comprehensive evaluation and comparative analysis of Machine Learning models, specifically Random Forest and Logistic Regression, both with and without Genetic Algorithmdriven feature selection. Our findings substantiate the significant impact of Genetic Algorithms in improving the accuracy of software reliability analysis. Â© 2024 IEEE.
Improved cross sample entropy with error-metric based cardiac variability time series evaluation
(Springer Science and Business Media B.V., 2024) Sharma, K.; Sunkaria, R.K.; Marwaha, P.
The cardiac rate variability analysis is a tool used to diagnose pathological and physiological variations in subjects in the premature stages. The cross-sample entropy (CSE) measure is used to analyze cardiac variability to diagnose cardiovascular diseases. In the proposed work, CSE is evaluated to detect arrhythmia subjects. It has been observed that CSE is restricted by a fixed threshold and any distance measure for cardiac disorder detection. In the proposed work, a new measure, named the error-metric cross sample entropy (E-metricCSE), is introduced to detect various cardiac disorders by using dynamic threshold and an error metric, root mean square error (RMSE). It signifies that the use of the RMSE makes the proposed algorithm most convenient for noise free data when compared to a distance metric. Different sets of MIX (Q) processes are executed on both real and simulated data to test the effectiveness of the proposed method. It is further noticed that the proposed algorithm is more consistent and more effective to quantify pathological and physiological subjects than the original CSE. © Bharati Vidyapeeth's Institute of Computer Applications and Management 2024.
MSSEAG-UNet: A Novel Deep Learning Architecture for Cloud Segmentation in Fisheye Sky Images and Solar Energy Forecast
(Institute of Electrical and Electronics Engineers Inc., 2025) Kumar, A.; Kashyap, Y.; Sharma, K.; Vittal, K.; Shubhanga, K.N.
This study analyzes sky images captured using a ground-based fisheye camera, aiming to address the challenge of accurately segmenting clouds, which is difficult due to their fuzzy and indistinct boundaries and uneven lighting conditions. Accurate segmentation of clouds in ground-based sky images is crucial for accurate solar energy forecasting. Motivated by these challenges, this article has proposed a novel deep learning architecture called multispatial squeeze-and-excite attention gated U-Net (MSSEAG-UNet) for cloud segmentation in ground-based fisheye sky images. The proposed architecture integrates a multispatial convolutional (MS-CNN) block and squeeze-and-excitation (SE) blocks in the encoder path to improve multiscale feature extraction (MFF) and recalibrate feature maps, while an attention block is incorporated in the decoder path to emphasize key cloud features. The segmentation performance of the MSSEAG-UNet is compared with five benchmark models, and results show that the proposed model outperforms than all benchmarks models. Furthermore, the segmented cloud images produced by the MSSEAG-UNet are used to calculate the cloud percentage, which is then integrated with the original sky images using a multicolumn convolutional model for global horizontal irradiance (GHI) forecast. GHI forecast is conducted for 15-, 30-, and 60-min ahead timesteps, with the best results achieved for the 60-min forecast, yielding mean absolute error (MAE), mean square error (mse), and RMSE values of 6.245%, 0.683%, and 8.265%, respectively. These results highlight the effectiveness of the proposed approach in improving both cloud segmentation accuracy and short-term solar irradiance forecasting. © 1980-2012 IEEE.
Representation Learning in Continuous-Time Dynamic Signed Networks
(Association for Computing Machinery, 2023) Sharma, K.; Raghavendra, M.; Lee, Y.-C.; Anand Kumar, M.A.; Kumar, S.
Signed networks allow us to model conflicting relationships and interactions, such as friend/enemy and support/oppose. These signed interactions happen in real-time. Modeling such dynamics of signed networks is crucial to understanding the evolution of polarization in the network and enabling effective prediction of the signed structure (i.e., link signs) in the future. However, existing works have modeled either (static) signed networks or dynamic (unsigned) networks but not dynamic signed networks. Since both sign and dynamics inform the graph structure in different ways, it is non-trivial to model how to combine the two features. In this work, we propose a new Graph Neural Network (GNN)-based approach to model dynamic signed networks, named SEMBA: Signed link's Evolution using Memory modules and Balanced Aggregation. Here, the idea is to incorporate the signs of temporal interactions using separate modules guided by balance theory and to evolve the embeddings from a higher-order neighborhood. Experiments on 4 real-world datasets and 3 different tasks demonstrate that SEMBA consistently and significantly outperforms the baselines by up to 80% on the tasks of predicting signs of future links while matching the state-of-the-art performance on predicting existence of these links in the future. We find that this improvement is due specifically to superior performance of SEMBA on the minority negative class. Code is made available at https://github.com/claws-lab/semba. Â© 2023 Copyright held by the owner/author(s). ACM ISBN 979-8-4007-0124-5/23/10.