Pushpendra Kumar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Pushpendra Kumar has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
Ramjeevan Singh Thakur
Maulana Azad National Institute of Technology, India
8 shared publications- Kanojia Sindhuben Babulal
Department of Computer Science and Engineering, Central University of Jharkhand, Ranchi, India
5 shared publications - Ahmed J. Obaid
University of Kufa
2 shared publications Anup Bihari Gaurav
Maulana Azad National Institute of Technology, India
2 shared publications- Harshita Patel
School of Computer Science Engineering and Information Systems, Vellore Institute of Technology, Vellore, India
2 shared publications Ram Kishun Mahto
Department of Computer Science and Engineering, Central University of Jharkhand
2 shared publications
Latest Publications
- 9 September 2026
- Published by Taylor & Francis in International Journal of Computers and Applications
- Vol. 48 (10) , 841-862
PSASNet: sarcasm detection through polarity shift-aware sentiment encoding with explainability
1. Sarcasm is considered as a complex form of figurative language in which the intended meaning differs from its literal meaning [1]. This feature of sarcasm makes Natural language processing's fai...
- 9 September 2026
- Published by Taylor & Francis in International Journal of Computers and Applications
- Vol. 48 (10) , 841-862
PSASNet: sarcasm detection through polarity shift-aware sentiment encoding with explainability
1. Sarcasm is considered as a complex form of figurative language in which the intended meaning differs from its literal meaning [1]. This feature of sarcasm makes Natural language processing's fai...
- 14 July 2026
- Published by Taylor & Francis in Journal of Medical Engineering & Technology
- p. 1-16
Chronic renal disease classification using the AL-5-ENeT-B4 model from CT images
1. The CRD is a gradual and irreversible condition that affects the renal organs’ structure and function over time, eventually resulting in decreased renal functions and an increase in cardiovascul...
- 14 July 2026
- Published by Taylor & Francis in Journal of Medical Engineering & Technology
- p. 1-16
Chronic renal disease classification using the AL-5-ENeT-B4 model from CT images
1. The CRD is a gradual and irreversible condition that affects the renal organs’ structure and function over time, eventually resulting in decreased renal functions and an increase in cardiovascul...
- Open Access
- 24 March 2025
- Published by Springer Nature in Discover Computing
- Vol. 28 (1) , 1-12
Interpolation of Erythrocytes and Leukocytes Microscopic image using MsR-CNN with Yolo v9 Model
- 24 March 2025
- Published by Springer Nature in Discover Computing
- Vol. 28 (1) , 1-12
Open AccessInterpolation of Erythrocytes and Leukocytes Microscopic image using MsR-CNN with Yolo v9 Model
- Open Access
- 21 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 17068-17082
Premier Dynamic Bandwidth Management and Tensile Wavelength Selection Ensuring QoS for NG-EPONs
Next Generation Ethernet Passive Optical Networks (NG-EPONs) have emerged as a leading choice for global network connectivity due to their cost-effectiveness, enhanced security, and energy efficiency. As data demands continue to surge with technological advancements, the need for efficient bandwidth management and wavelength selection in NG-EPONs becomes paramount. This paper presents two innovative algorithms—Tensile Wavelength and Dynamic Bandwidth Allocation (TW-DBA) and Premier Dynamic Bandwidth Allocation (PDBA)—designed to optimize bandwidth allocation and maintain Quality of Service (QoS) under varying network conditions. The TW-DBA algorithm achieves a remarkable throughput of 2.34 Gbps, driven by its dynamic wavelength selection mechanism that accounts for factors such as ONU-OLT distance, power availability, and bandwidth demand. Comparative analysis reveals that TW-DBA outperforms existing algorithms like Flexible Wavelength (FW), First-Fit, and Water Filled, both in computational efficiency and resource allocation. Furthermore, the PDBA algorithm demonstrates a minimum blockage probability of 0.0025 for limited ONU scenarios and 0.005 in unlimited scenarios, ensuring uniform bandwidth distribution. Simulation results confirm the superior performance and effectiveness of the proposed models, positioning them as robust solutions for the evolving demands of NG-EPONs.
- 21 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 17068-17082
Open AccessPremier Dynamic Bandwidth Management and Tensile Wavelength Selection Ensuring QoS for NG-EPONs
Next Generation Ethernet Passive Optical Networks (NG-EPONs) have emerged as a leading choice for global network connectivity due to their cost-effectiveness, enhanced security, and energy efficiency. As data demands continue to surge with technological advancements, the need for efficient bandwidth management and wavelength selection in NG-EPONs becomes paramount. This paper presents two innovative algorithms—Tensile Wavelength and Dynamic Bandwidth Allocation (TW-DBA) and Premier Dynamic Bandwidth Allocation (PDBA)—designed to optimize bandwidth allocation and maintain Quality of Service (QoS) under varying network conditions. The TW-DBA algorithm achieves a remarkable throughput of 2.34 Gbps, driven by its dynamic wavelength selection mechanism that accounts for factors such as ONU-OLT distance, power availability, and bandwidth demand. Comparative analysis reveals that TW-DBA outperforms existing algorithms like Flexible Wavelength (FW), First-Fit, and Water Filled, both in computational efficiency and resource allocation. Furthermore, the PDBA algorithm demonstrates a minimum blockage probability of 0.0025 for limited ONU scenarios and 0.005 in unlimited scenarios, ensuring uniform bandwidth distribution. Simulation results confirm the superior performance and effectiveness of the proposed models, positioning them as robust solutions for the evolving demands of NG-EPONs.
- Open Access
- 15 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 101842-101850
Human Brain Waves Study Using EEG and Deep Learning for Emotion Recognition
Emotion Recognition is a critical area of research including healthcare, human-computer interaction, and psychology. While traditional methods mainly rely on facial expressions and textual analysis, they also have inherent flaws and cannot be reliable. Facial expression-based emotion recognition assumes that it represents genuine internal emotions that may be inaccurate. Similarly, textual analysis depends on the available data and needs help accurately capturing subtle emotions in text. However, electroencephalography (EEG) has emerged as a rising alternative for objective and real-time emotion recognition. Unlike facial and textual methods, EEG directly measures brain activity and provides a reliable result. To address this researchers have used basic machine learning methods that need manual feature extraction, which might miss essential data and make the process slow and less accurate. In this study, we propose a comprehensive methodology for EEG-based emotion recognition that addresses the limitations of traditional methods and basic machine learning techniques. Our approach involves preprocessing EEG signals using a butter-worth bandpass filter to eliminate noise, followed by feature extraction techniques. We then employ Principal Component Analysis (PCA) for dimensionality reduction, ensuring efficient data representation. To further enhance the model performance we explore machine learning classifiers(GaussianNB, SVM, Random Forest) and proposed an EEG-LSTM and GRU model with an accuracy of 97% and 96% respectively, that gives better results than the basic machine learning models.
- 15 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 101842-101850
Open AccessHuman Brain Waves Study Using EEG and Deep Learning for Emotion Recognition
Emotion Recognition is a critical area of research including healthcare, human-computer interaction, and psychology. While traditional methods mainly rely on facial expressions and textual analysis, they also have inherent flaws and cannot be reliable. Facial expression-based emotion recognition assumes that it represents genuine internal emotions that may be inaccurate. Similarly, textual analysis depends on the available data and needs help accurately capturing subtle emotions in text. However, electroencephalography (EEG) has emerged as a rising alternative for objective and real-time emotion recognition. Unlike facial and textual methods, EEG directly measures brain activity and provides a reliable result. To address this researchers have used basic machine learning methods that need manual feature extraction, which might miss essential data and make the process slow and less accurate. In this study, we propose a comprehensive methodology for EEG-based emotion recognition that addresses the limitations of traditional methods and basic machine learning techniques. Our approach involves preprocessing EEG signals using a butter-worth bandpass filter to eliminate noise, followed by feature extraction techniques. We then employ Principal Component Analysis (PCA) for dimensionality reduction, ensuring efficient data representation. To further enhance the model performance we explore machine learning classifiers(GaussianNB, SVM, Random Forest) and proposed an EEG-LSTM and GRU model with an accuracy of 97% and 96% respectively, that gives better results than the basic machine learning models.
- 29 May 2024
- Published by Springer Nature
- p. 163-183
A Computer Vision Approach to Enhance Visual Data used to Overcome the Learning Disabilities in Higher Education
- 29 May 2024
- Published by Springer Nature
- p. 163-183
A Computer Vision Approach to Enhance Visual Data used to Overcome the Learning Disabilities in Higher Education
- 29 May 2024
- Published by Springer Nature
- p. 153-161
Deep Learning Approach for Detection of Learning Disabilities in Higher Education
- 29 May 2024
- Published by Springer Nature
- p. 153-161
Deep Learning Approach for Detection of Learning Disabilities in Higher Education
- 16 May 2023
- Published by Springer Nature
- p. 60-70
Analyzing Deep Neural Network Algorithms for Recognition of Emotions Using Textual Data
- 16 May 2023
- Published by Springer Nature
- p. 60-70
Analyzing Deep Neural Network Algorithms for Recognition of Emotions Using Textual Data
- Open Access
- 1 August 2022
- Published by IGI Global Scientific Publishing in International Journal of E-Health and Medical Communications
- Vol. 13 (4) , 1-13
Real-Time Surveillance System for Detection of Social Distancing
As the corona virus can mutate and due to other scientific factor associated to it, experts believe that COVID-19 will remain with us for decades. Therefore, one has to keep social distancing measures. Accepting the pandemic situation, the paper presents a mechanism for detecting violations of social distancing using deep learning to estimate the distance between individuals to diminish the influence of COVID-19. The focus of this paper is to understand the effect of social distancing on the spread of COVID-19 by using YOLOv3 and Faster-RCNN and proposes IFRCNN (improved faster region – convolution neural network). The proposed method IFRCNN is checked on a live streaming video of pedestrians walking on the street. This paper keeps the live updates of the recorded video along with social distancing violation records on a location, so how many people in a location are maintaining social distancing. Updates will be stored in a cloud-based storage system and any organization or firm can get live updates of that location in their digital devices.
- 1 August 2022
- Published by IGI Global Scientific Publishing in International Journal of E-Health and Medical Communications
- Vol. 13 (4) , 1-13
Open AccessReal-Time Surveillance System for Detection of Social Distancing
As the corona virus can mutate and due to other scientific factor associated to it, experts believe that COVID-19 will remain with us for decades. Therefore, one has to keep social distancing measures. Accepting the pandemic situation, the paper presents a mechanism for detecting violations of social distancing using deep learning to estimate the distance between individuals to diminish the influence of COVID-19. The focus of this paper is to understand the effect of social distancing on the spread of COVID-19 by using YOLOv3 and Faster-RCNN and proposes IFRCNN (improved faster region – convolution neural network). The proposed method IFRCNN is checked on a live streaming video of pedestrians walking on the street. This paper keeps the live updates of the recorded video along with social distancing violation records on a location, so how many people in a location are maintaining social distancing. Updates will be stored in a cloud-based storage system and any organization or firm can get live updates of that location in their digital devices.
- Open Access
- 1 August 2022
- Published by IGI Global Scientific Publishing in International Journal of E-Health and Medical Communications
- Vol. 13 (4) , 1-15
Categorical Data Clustering Using Harmony Search Algorithm for Healthcare Datasets
Healthcare analytics provide many benefits in healthcare dashboard systems. Healthcare datasets majorly contains categorical attributes. This paper proposed an optimized clustering for healthcare dataset named harmony search based categorical clustering (HSCC). The existing k-modes clustering algorithm is one of the well-known categorical data-clustering algorithm. Since the k-modes algorithm produces local optimal clusters. Generally, researchers use genetic algorithm (GA) based clustering algorithms to converge locally optimal solutions to global optimal solutions. GA has some deficiencies such as premature convergence with low speed. In this paper, harmony search (HS) optimization algorithm used to optimize clustering results. The result shows the proposed HSCC algorithm produced global optimized solution, unbiased and matured results. HSCC produces 98% accuracy for dental and 71% for lung cancer dataset. While GACC produces 95% and 65% accuracy for dental dataset and lung cancer dataset.
- 1 August 2022
- Published by IGI Global Scientific Publishing in International Journal of E-Health and Medical Communications
- Vol. 13 (4) , 1-15
Open AccessCategorical Data Clustering Using Harmony Search Algorithm for Healthcare Datasets
Healthcare analytics provide many benefits in healthcare dashboard systems. Healthcare datasets majorly contains categorical attributes. This paper proposed an optimized clustering for healthcare dataset named harmony search based categorical clustering (HSCC). The existing k-modes clustering algorithm is one of the well-known categorical data-clustering algorithm. Since the k-modes algorithm produces local optimal clusters. Generally, researchers use genetic algorithm (GA) based clustering algorithms to converge locally optimal solutions to global optimal solutions. GA has some deficiencies such as premature convergence with low speed. In this paper, harmony search (HS) optimization algorithm used to optimize clustering results. The result shows the proposed HSCC algorithm produced global optimized solution, unbiased and matured results. HSCC produces 98% accuracy for dental and 71% for lung cancer dataset. While GACC produces 95% and 65% accuracy for dental dataset and lung cancer dataset.