Kapil Juneja
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
Kapil Juneja has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
Chhavi Rana
Department of Computer Science and Engineering, University Institute of Engineering and Technology, Maharshi Dayanand University, Rohtak, India
11 shared publicationsNasib Singh Gill
Department of Computer Science & Applications, Maharshi Dayanand University, Rohtak 124001, Haryana, Rohtak
4 shared publications- Chhavi Rana
Department of Computer Science and Engineering, University Institute of Engineering and Technology, Maharshi Dayanand University
2 shared publications - Anupriya Jangra
BPS Mahila Vishwavidyalaya, Khanpur kalan, Gohana, Sonipat, India
1 shared publication - Arvind Mewada
Bennett University
1 shared publication Deexa Jamwal
Panjab University Swami Sarvanand Giri Regional Centre,Department of Computer Science and Engineering,Jalandhar,India
1 shared publication
Latest Publications
- 16 July 2026
- Published by Wiley
- p. 73-88
A Transfer Learning Baseline and a GAN ‐augmentation Perspective for MRI ‐based Alzheimer's Disease Detection
- 16 July 2026
- Published by Wiley
- p. 73-88
A Transfer Learning Baseline and a GAN ‐augmentation Perspective for MRI ‐based Alzheimer's Disease Detection
- Open Access
- 5 December 2024
- Published by Springer Nature in International Journal of Networked and Distributed Computing
- Vol. 13 (1) , 1-14
Design of a Quaternary Component and Wallace Tree Integrated Baugh-Wooley Multiplier
- 5 December 2024
- Published by Springer Nature in International Journal of Networked and Distributed Computing
- Vol. 13 (1) , 1-14
Open AccessDesign of a Quaternary Component and Wallace Tree Integrated Baugh-Wooley Multiplier
- 25 February 2023
- Published by Springer Nature in Wireless Personal Communications
- Vol. 129 (2) , 1315-1341
Design of a new CPEDSR Protocol for Optimizing the Communication in Mobile Network
- 25 February 2023
- Published by Springer Nature in Wireless Personal Communications
- Vol. 129 (2) , 1315-1341
Design of a new CPEDSR Protocol for Optimizing the Communication in Mobile Network
- 23 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Weighted Cause-Reward Analysis-based Reinforcement Learning Method for Optimizing the Sentiment Prediction
In online markets or shops, the products are purchased by people based on their visual appearance and textual description. These ecommerce systems also collect user views or feedback about the sold product or services. The user also submits his complaints, reaction, and opinion including his sentiments. These reviews can be processed by ecommerce sites to rank their products and identify the features and flaws of products. In this paper, a weighted cause-reward analysis-based reinforcement learning method is proposed to optimize the sentiment classification. The model first transformed the input reviews to the weighted features by identifying the frequency and boundness with product. These weighted features are processed by the reinforcement learning method to classify the sentiments. The model is applied on the reviews collected from amazon reviews dataset. The analysis results are compared against machine learning and deep learning methods. The results shows that the proposed model achieved the average accuracy rate of 94.60% which is significantly better than existing methods. The performance and reliability of the system are improved by the proposed model.
- 23 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Weighted Cause-Reward Analysis-based Reinforcement Learning Method for Optimizing the Sentiment Prediction
In online markets or shops, the products are purchased by people based on their visual appearance and textual description. These ecommerce systems also collect user views or feedback about the sold product or services. The user also submits his complaints, reaction, and opinion including his sentiments. These reviews can be processed by ecommerce sites to rank their products and identify the features and flaws of products. In this paper, a weighted cause-reward analysis-based reinforcement learning method is proposed to optimize the sentiment classification. The model first transformed the input reviews to the weighted features by identifying the frequency and boundness with product. These weighted features are processed by the reinforcement learning method to classify the sentiments. The model is applied on the reviews collected from amazon reviews dataset. The analysis results are compared against machine learning and deep learning methods. The results shows that the proposed model achieved the average accuracy rate of 94.60% which is significantly better than existing methods. The performance and reliability of the system are improved by the proposed model.
- 2 December 2022
- Published by Taylor & Francis in IETE Journal of Research
- Vol. 70 (2) , 1622-1637
Ontology-Assisted and Autonomic Testing Verified Model for Automated and Reliable Web Development
This paper proposed a web engineering architecture based on three main phenomena called Structured Development, high reliability, and multi-level flexibility. The ontology is formed and mapped to generate a structured and user-assisted design. The user requirements are captured in this model based on an ontology map. Web engineering is applied to capture the various elements of web development including the functional features. In the development phase, the captured inputs and features are processed for designing the static and active web pages. The functional interconnectivity, validations, and security are integrated for all pages. The second important aspect of high reliability is achieved by managing the control level validations, BlackBox testing, cookies control, and session tracking. Multi-level flexibility is achieved at each level of this model including requirement gathering, ontology formation, webpage development, control validations, and testing. The XML files are generated at different levels to manage and control user responses. The proposed model is verified on seven case studies and the analysis is done in terms of design time and the number of cycles required for finalizing the website. The qualitative evaluation of the proposed model is done against 11 existing web designing tools. The project development is accomplished from 15 to 70 s based on the project size. The number of change cycles of different projects lies between 4 and 12. The analytical study identified that the proposed model is effective and reliable enough against template support, requirement gathering, customization, control validation, testing, and security.
- 2 December 2022
- Published by Taylor & Francis in IETE Journal of Research
- Vol. 70 (2) , 1622-1637
Ontology-Assisted and Autonomic Testing Verified Model for Automated and Reliable Web Development
This paper proposed a web engineering architecture based on three main phenomena called Structured Development, high reliability, and multi-level flexibility. The ontology is formed and mapped to generate a structured and user-assisted design. The user requirements are captured in this model based on an ontology map. Web engineering is applied to capture the various elements of web development including the functional features. In the development phase, the captured inputs and features are processed for designing the static and active web pages. The functional interconnectivity, validations, and security are integrated for all pages. The second important aspect of high reliability is achieved by managing the control level validations, BlackBox testing, cookies control, and session tracking. Multi-level flexibility is achieved at each level of this model including requirement gathering, ontology formation, webpage development, control validations, and testing. The XML files are generated at different levels to manage and control user responses. The proposed model is verified on seven case studies and the analysis is done in terms of design time and the number of cycles required for finalizing the website. The qualitative evaluation of the proposed model is done against 11 existing web designing tools. The project development is accomplished from 15 to 70 s based on the project size. The number of change cycles of different projects lies between 4 and 12. The analytical study identified that the proposed model is effective and reliable enough against template support, requirement gathering, customization, control validation, testing, and security.
- Open Access
- 1 November 2022
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 34 (10) , 10339-10355
Two-phase fuzzy feature-filter based hybrid model for spam classification
- 1 November 2022
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 34 (10) , 10339-10355
Open AccessTwo-phase fuzzy feature-filter based hybrid model for spam classification
- Open Access
Patron–Prophet Artificial Bee Colony Approach for Solving Numerical Continuous Optimization Problems
The swarm-based Artificial Bee Colony (ABC) algorithm has a significant range of applications and is competent, compared to other algorithms, regarding many optimization problems. However, the ABC’s performance in higher-dimension situations towards global optima is not on par with other models due to its deficiency in balancing intensification and diversification. In this research, two different strategies are applied for the improvement of the search capability of the ABC in a multimodal search space. In the ABC, the first strategy, Patron–Prophet, is assessed in the scout bee phase to incorporate a cooperative nature. This strategy works based on the donor–acceptor concept. In addition, a self-adaptability approach is included to balance intensification and diversification. This balancing helps the ABC to search for optimal solutions without premature convergence. The first strategy explores unexplored regions with better insight, and more profound intensification occurs in the discovered areas. The second strategy controls the trap of being in local optima and diversification without the pulse of intensification. The proposed model, named the PP-ABC, was evaluated with mathematical benchmark functions to prove its efficiency in comparison with other existing models. Additionally, the standard and statistical analyses show a better outcome of the proposed algorithm over the compared techniques. The proposed model was applied to a three-bar truss engineering design problem to validate the model’s efficacy, and the results were recorded.
Open AccessPatron–Prophet Artificial Bee Colony Approach for Solving Numerical Continuous Optimization Problems
The swarm-based Artificial Bee Colony (ABC) algorithm has a significant range of applications and is competent, compared to other algorithms, regarding many optimization problems. However, the ABC’s performance in higher-dimension situations towards global optima is not on par with other models due to its deficiency in balancing intensification and diversification. In this research, two different strategies are applied for the improvement of the search capability of the ABC in a multimodal search space. In the ABC, the first strategy, Patron–Prophet, is assessed in the scout bee phase to incorporate a cooperative nature. This strategy works based on the donor–acceptor concept. In addition, a self-adaptability approach is included to balance intensification and diversification. This balancing helps the ABC to search for optimal solutions without premature convergence. The first strategy explores unexplored regions with better insight, and more profound intensification occurs in the discovered areas. The second strategy controls the trap of being in local optima and diversification without the pulse of intensification. The proposed model, named the PP-ABC, was evaluated with mathematical benchmark functions to prove its efficiency in comparison with other existing models. Additionally, the standard and statistical analyses show a better outcome of the proposed algorithm over the compared techniques. The proposed model was applied to a three-bar truss engineering design problem to validate the model’s efficacy, and the results were recorded.
- 26 August 2022
- Published by Wiley in International Journal of Communication Systems
- Vol. 35 (17)
Design of a novel micro‐Zone adaptive Energy‐Trust evaluation Active On‐Demand Vector protocol to optimize communication in challenging and attacked mobile network
Summary: High congestion, mobility, and energy restrictions are the critical challenges to mobile networks. The conventional routing protocols are unable to ensure effective and reliable communication in such dynamic and unpredictable situations. In this paper, a novel micro‐Zone adaptive Energy‐Trust evaluation Active On‐Demand Vector (mZ‐ETAODV) protocol is designed to provide routing solutions in extreme conditions. In this work, the complete network is divided into smaller zones of nxn. The extreme zone position‐based evaluation is conducted to handle the stability and to identify the next intermediate node. The zone‐covered neighbors are further computed under energy and trust measures to identify the most reliable neighbor. The proposed protocol is simulated under high mobility, congestion and man‐in‐middle attack situations. The analytical observations are recorded in terms of Packet Delivery Ratio (PDR) ratio, energy consumption, delay and communication loss parameters. The comparative results are generated against AODV, SAODV, PSAODV, PDS‐AODV, NVS‐AODV, iNVS‐AODV, Tripathy et al., DFMCRP, FBSSR, MBDP‐AODV, AGHA, and Singh et al. protocols. The experimentation is conducted in a highly challenging mobile network with high congestion, high mobility, energy restriction, existence of blackhole, grayhole, DDOS, and mixed attacks. These attacks are performed with 0% to 10% density, and analysis is conducted against PDR ratio, communication delay, route switching, dead node count, remaining energy, and attack detection rate measures. The analysis results identified that the proposed protocol reduced the communication delay and energy consumption and achieved significant gain in attack detection rate, network life and PDR ratio.
- 26 August 2022
- Published by Wiley in International Journal of Communication Systems
- Vol. 35 (17)
Design of a novel micro‐Zone adaptive Energy‐Trust evaluation Active On‐Demand Vector protocol to optimize communication in challenging and attacked mobile network
Summary: High congestion, mobility, and energy restrictions are the critical challenges to mobile networks. The conventional routing protocols are unable to ensure effective and reliable communication in such dynamic and unpredictable situations. In this paper, a novel micro‐Zone adaptive Energy‐Trust evaluation Active On‐Demand Vector (mZ‐ETAODV) protocol is designed to provide routing solutions in extreme conditions. In this work, the complete network is divided into smaller zones of nxn. The extreme zone position‐based evaluation is conducted to handle the stability and to identify the next intermediate node. The zone‐covered neighbors are further computed under energy and trust measures to identify the most reliable neighbor. The proposed protocol is simulated under high mobility, congestion and man‐in‐middle attack situations. The analytical observations are recorded in terms of Packet Delivery Ratio (PDR) ratio, energy consumption, delay and communication loss parameters. The comparative results are generated against AODV, SAODV, PSAODV, PDS‐AODV, NVS‐AODV, iNVS‐AODV, Tripathy et al., DFMCRP, FBSSR, MBDP‐AODV, AGHA, and Singh et al. protocols. The experimentation is conducted in a highly challenging mobile network with high congestion, high mobility, energy restriction, existence of blackhole, grayhole, DDOS, and mixed attacks. These attacks are performed with 0% to 10% density, and analysis is conducted against PDR ratio, communication delay, route switching, dead node count, remaining energy, and attack detection rate measures. The analysis results identified that the proposed protocol reduced the communication delay and energy consumption and achieved significant gain in attack detection rate, network life and PDR ratio.
- 29 July 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (4) , 5627-5662
Design of a multi-stage hybrid model for face recognition in varied illumination conditions
- 29 July 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (4) , 5627-5662
Design of a multi-stage hybrid model for face recognition in varied illumination conditions
- 18 July 2022
- Published by Springer Nature in Wireless Personal Communications
- Vol. 126 (2) , 1843
Correction to: Expanded and Filtered Features Based ELM Model for Thyroid Disease Classification
- 18 July 2022
- Published by Springer Nature in Wireless Personal Communications
- Vol. 126 (2) , 1843
Correction to: Expanded and Filtered Features Based ELM Model for Thyroid Disease Classification