Nikhil Kumar Singh
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
Nikhil Kumar Singh has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
Deepak Singh Tomar
Maulana Azad National Institute of Technology
3 shared publications- Joohyung Lee
Department of Computing, Gachon Univ, Seongnam, Rep. of Korea
3 shared publications - Deepak Singh Tomar
Maulana Azad National Institute of Technology
2 shared publications - Ismail Keshta
Department of Computer Science and Information Systems, College of Applied Sciences, AlMaarefa University, Riyadh, Saudi Arabia
2 shared publications - Mohammad Shabaz
Marwadi University
2 shared publications - Mukesh Soni
Division of Research and Development, Lovely Professional University, Phagwara, India
2 shared publications
Latest Publications
- 26 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. PP (00983063) , 1
Federated Learning Privacy-Preserving Approach for Consumer-Centric Multimodal Healthcare Data
Electronic Health Records (EHR) data have become a valuable resource for biomedical research. By leveraging federated learning (FL), the potential of EHR data can be used without compromising privacy. However, most existing studies focus on privacy protection methods for device-centric distributed healthcare EHRs. The diverse modalities of EHR, such as consumer-centric clinical notes, lab results, and imaging data, limit the unimodal ability to capture complex relationships. FL models designed for unimodal data struggle to integrate these heterogeneous sources, resulting in suboptimal performance and increased risk of privacy breaches. This paper proposes a FL privacy protection method for multimodal data to address these limitations. The proposed method effectively handles diverse data types while ensuring robust privacy protection across the entire FL lifecycle. To prevent adversaries from stealing original data through reverse attacks, differential privacy perturbation is applied to the model parameters uploaded by each participant. Additionally, the Paillier cryptosystem is utilized for homomorphic encryption of local model parameters to protect local model information during training. Experimental results demonstrate that the proposed method provides comprehensive privacy protection for training data and models with minimal performance loss, making it suitable for federated learning scenarios involving multimodal EHR data.
- 26 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. PP (00983063) , 1
Federated Learning Privacy-Preserving Approach for Consumer-Centric Multimodal Healthcare Data
Electronic Health Records (EHR) data have become a valuable resource for biomedical research. By leveraging federated learning (FL), the potential of EHR data can be used without compromising privacy. However, most existing studies focus on privacy protection methods for device-centric distributed healthcare EHRs. The diverse modalities of EHR, such as consumer-centric clinical notes, lab results, and imaging data, limit the unimodal ability to capture complex relationships. FL models designed for unimodal data struggle to integrate these heterogeneous sources, resulting in suboptimal performance and increased risk of privacy breaches. This paper proposes a FL privacy protection method for multimodal data to address these limitations. The proposed method effectively handles diverse data types while ensuring robust privacy protection across the entire FL lifecycle. To prevent adversaries from stealing original data through reverse attacks, differential privacy perturbation is applied to the model parameters uploaded by each participant. Additionally, the Paillier cryptosystem is utilized for homomorphic encryption of local model parameters to protect local model information during training. Experimental results demonstrate that the proposed method provides comprehensive privacy protection for training data and models with minimal performance loss, making it suitable for federated learning scenarios involving multimodal EHR data.
- 7 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (2) , 4867-4882
Federated Learning-Based Secure Computing Mechanism for Consumer Internet of Vehicles-Based Transportation Cyber-Physical Systems
Ensuring reliable and efficient transportation in Cyber-Physical Systems (CPS) requires effective model training across distributed Consumer Internet of Vehicles (CIOV)-based Transportation CPS (TCPS). However, the high mobility of transportation terminals and frequent domain switching during training degrade global model accuracy, while malicious terminals uploading erroneous data further compromise system reliability. To address these challenges, this paper proposes Fed-ECC, a two-tier federated learning (FL)-based edge collaborative computing mechanism for dynamic CIOV-based TCPS. The first tier employs a deep reinforcement learning (DRL)-based clustering algorithm to form edge collaborative computing domains, optimizing terminal selection based on mobility, computational capability, and reliability. The second tier integrates a semi-asynchronous local aggregation mechanism with adaptive aggregation factors and an asynchronous regional aggregation mechanism based on data volume, improving aggregation efficiency and model convergence. Simulation results demonstrate that Fed-ECC enhances global model accuracy by 58.7%, accelerates convergence speed by 57.6%, and achieves 95% accuracy in traffic safety tasks, significantly improving obstacle detection and service reliability. These findings underscore the effectiveness, scalability, and robustness of Fed-ECC in addressing the challenges of high-mobility, large-scale CIOV-based TCPS.
- 7 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (2) , 4867-4882
Federated Learning-Based Secure Computing Mechanism for Consumer Internet of Vehicles-Based Transportation Cyber-Physical Systems
Ensuring reliable and efficient transportation in Cyber-Physical Systems (CPS) requires effective model training across distributed Consumer Internet of Vehicles (CIOV)-based Transportation CPS (TCPS). However, the high mobility of transportation terminals and frequent domain switching during training degrade global model accuracy, while malicious terminals uploading erroneous data further compromise system reliability. To address these challenges, this paper proposes Fed-ECC, a two-tier federated learning (FL)-based edge collaborative computing mechanism for dynamic CIOV-based TCPS. The first tier employs a deep reinforcement learning (DRL)-based clustering algorithm to form edge collaborative computing domains, optimizing terminal selection based on mobility, computational capability, and reliability. The second tier integrates a semi-asynchronous local aggregation mechanism with adaptive aggregation factors and an asynchronous regional aggregation mechanism based on data volume, improving aggregation efficiency and model convergence. Simulation results demonstrate that Fed-ECC enhances global model accuracy by 58.7%, accelerates convergence speed by 57.6%, and achieves 95% accuracy in traffic safety tasks, significantly improving obstacle detection and service reliability. These findings underscore the effectiveness, scalability, and robustness of Fed-ECC in addressing the challenges of high-mobility, large-scale CIOV-based TCPS.
- 31 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (2) , 4292-4303
Federated Learning-Based Energy-Efficient Consumer-Centric Access Strategy for Cell-Free MIMO in 6G Wireless Networks
With the rapid expansion of consumer-centric 6G mobile communication networks, ensuring efficient consumer access and minimizing energy consumption in cell-free massive multiple-input multiple-output (CF-mMIMO) systems have become significant challenges. Selecting optimal consumer access points (APs) is complex due to varying channel conditions, energy demands, and privacy concerns in densely populated network environments. To address these challenges, this paper proposes a channel ranking-based poor-consumer-first access strategy, where consumers evaluate and rank their channel quality based on channel state information. The strategy enables consumers to select suitable APs, prioritizing those with poorer channel quality to ensure reliable communication. Additionally, a federated learning framework is introduced to strengthen data privacy, and an energy consumption optimization-based alternating optimization algorithm is developed to adjust multidimensional variables such as transmission power, time allocation, and learning accuracy, thus minimizing the system’s overall energy consumption. Simulation results indicate that, compared to traditional user-centric access strategies in massive MIMO, the proposed approach improves the average uplink achievable rate by 20% and doubles the rate for users with poorer channel conditions, while also reducing total energy consumption by over 50%.
- 31 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (2) , 4292-4303
Federated Learning-Based Energy-Efficient Consumer-Centric Access Strategy for Cell-Free MIMO in 6G Wireless Networks
With the rapid expansion of consumer-centric 6G mobile communication networks, ensuring efficient consumer access and minimizing energy consumption in cell-free massive multiple-input multiple-output (CF-mMIMO) systems have become significant challenges. Selecting optimal consumer access points (APs) is complex due to varying channel conditions, energy demands, and privacy concerns in densely populated network environments. To address these challenges, this paper proposes a channel ranking-based poor-consumer-first access strategy, where consumers evaluate and rank their channel quality based on channel state information. The strategy enables consumers to select suitable APs, prioritizing those with poorer channel quality to ensure reliable communication. Additionally, a federated learning framework is introduced to strengthen data privacy, and an energy consumption optimization-based alternating optimization algorithm is developed to adjust multidimensional variables such as transmission power, time allocation, and learning accuracy, thus minimizing the system’s overall energy consumption. Simulation results indicate that, compared to traditional user-centric access strategies in massive MIMO, the proposed approach improves the average uplink achievable rate by 20% and doubles the rate for users with poorer channel conditions, while also reducing total energy consumption by over 50%.
- 3 April 2024
- Published by Springer Nature
- p. 1-22
Blockchain-Based Privacy-Protected Reputation Model for Internet of Vehicles
- 3 April 2024
- Published by Springer Nature
- p. 1-22
Blockchain-Based Privacy-Protected Reputation Model for Internet of Vehicles
- 23 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 12 (3) , 1307-1318
Deep Learning Model for Interpretability and Explainability of Aspect-Level Sentiment Analysis Based on Social Media
The interactive attention graph convolution network (IAGCN), a novel model proposed in this article, will revolutionize aspect-level sentiment analysis (SA). IAGCN effectively addresses these key features, in contrast to prior research that ignored the meaning of aspect terms and their relationship with context. The model combines a modified dynamic weighting layer with bidirectional long short-term memory (BiLSTM) to accurately acquire context. It takes use of graph convolutional networks (GCNs) to encrypt syntactic information from the syntactic dependency tree. Furthermore, a method for interactive attention is employed to discover the intricate relationships between context and aspect terms, which results in the reconstruction of those terms’ representations. Comparing the proposed IAGCN model to baseline models, impressive gains are made. Across five datasets, the model beats previous methods with an amazing improvement in F1 scores that ranges from 1.34% to 4.04% and an impressive improvement in accuracy that ranges from 0.56% to 1.75%. Additionally, the IAGCN model outperforms the global vectors (GloVe)-based strategy when the potent pretrained model bidirectional encoder representations from transformers (BERT) is included in the challenge, resulting in even greater improvements. The F1 score considerably increases from 2.59% to 7.55%, and accuracy increases from 1.47% to 3.95%, making the IAGCN model a standout performer in aspect-level SA.
- 23 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 12 (3) , 1307-1318
Deep Learning Model for Interpretability and Explainability of Aspect-Level Sentiment Analysis Based on Social Media
The interactive attention graph convolution network (IAGCN), a novel model proposed in this article, will revolutionize aspect-level sentiment analysis (SA). IAGCN effectively addresses these key features, in contrast to prior research that ignored the meaning of aspect terms and their relationship with context. The model combines a modified dynamic weighting layer with bidirectional long short-term memory (BiLSTM) to accurately acquire context. It takes use of graph convolutional networks (GCNs) to encrypt syntactic information from the syntactic dependency tree. Furthermore, a method for interactive attention is employed to discover the intricate relationships between context and aspect terms, which results in the reconstruction of those terms’ representations. Comparing the proposed IAGCN model to baseline models, impressive gains are made. Across five datasets, the model beats previous methods with an amazing improvement in F1 scores that ranges from 1.34% to 4.04% and an impressive improvement in accuracy that ranges from 0.56% to 1.75%. Additionally, the IAGCN model outperforms the global vectors (GloVe)-based strategy when the potent pretrained model bidirectional encoder representations from transformers (BERT) is included in the challenge, resulting in even greater improvements. The F1 score considerably increases from 2.59% to 7.55%, and accuracy increases from 1.47% to 3.95%, making the IAGCN model a standout performer in aspect-level SA.
- 10 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 70 (1) , 2687-2695
Self-Attention Mechanism-Based Federated Learning Model for Cross Context Recommendation System
The traditional single-context recommendation algorithm is constrained by the sparse connection between users and items and a user/item cold start problem. Based on the review, the text-based cross-context recommendation algorithm extracts user/item comment information in the auxiliary context to alleviate the target context’s data sparsity problem and improve recommendation accuracy. A cross-context recommendation strategy based on self-attention-based federated learning (SAFL) is suggested in this work. In contrast to current algorithms, SAFL fully mixes the target and auxiliary background information. Federated learning addresses crucial challenges including data privacy, data security, data access rights, and access to heterogeneous data by allowing several players to develop a single, strong machine learning model without sharing data. To begin, self-attention mechanism is introduced to model the user’s preference information; then, the information from one field is used to improve the recommendation accuracy of another area; and finally, the information from the two contexts is integrated into the knowledge fusion module and the score prediction module to predict the score. Experiments on the Amazon dataset indicate that MAE and MSE values of SAFL are higher when compared to the current cross-context recommendation model, MAE values rose by 8.4%, 13.2%, and 19.4% across three cross-context datasets.
- 10 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 70 (1) , 2687-2695
Self-Attention Mechanism-Based Federated Learning Model for Cross Context Recommendation System
The traditional single-context recommendation algorithm is constrained by the sparse connection between users and items and a user/item cold start problem. Based on the review, the text-based cross-context recommendation algorithm extracts user/item comment information in the auxiliary context to alleviate the target context’s data sparsity problem and improve recommendation accuracy. A cross-context recommendation strategy based on self-attention-based federated learning (SAFL) is suggested in this work. In contrast to current algorithms, SAFL fully mixes the target and auxiliary background information. Federated learning addresses crucial challenges including data privacy, data security, data access rights, and access to heterogeneous data by allowing several players to develop a single, strong machine learning model without sharing data. To begin, self-attention mechanism is introduced to model the user’s preference information; then, the information from one field is used to improve the recommendation accuracy of another area; and finally, the information from the two contexts is integrated into the knowledge fusion module and the score prediction module to predict the score. Experiments on the Amazon dataset indicate that MAE and MSE values of SAFL are higher when compared to the current cross-context recommendation model, MAE values rose by 8.4%, 13.2%, and 19.4% across three cross-context datasets.
- Retracted
- 19 October 2023
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 34 (1)
RETRACTED: Multiencoder‐based federated intelligent deep learning model for brain tumor segmentation
Glioma, a primary tumor derived from brain glial cells, is around 45% of all intracranial tumors. Magnetic resonance imaging's (MRI's) precise glioma segmentation is crucial for clinical purposes. This article presents a novel automatic brain tumor segmentation approach based on a multi‐encoder‐based federated intelligent deep learning framework. The suggested method uses a U‐shaped network design that multiplies the single contraction path into several paths to explore semantic information modalities deeply. The basic convolutional layer uses an Inception module and dilated convolutions to extract multi‐scale features from the images using artificial intelligent. To emphasize segmentation‐related information while ignoring redundant channel dimension information and improving the accuracy of network segmentation, lightweight channel attention efficient channel attention (ECA) modules are inserted into the bottleneck layer and decoder. The collection of data for the 2018 Brain Tumor Segmentation Challenge (BraTS 2018) is used to test the effectiveness of the suggested structure, and the findings indicate that the growth core, for the entire tumor and the augmented tumor regions, respectively, the average Dice coefficients are 0.880, 0.784, and 0.757. These findings support the proposed algorithm's ability to accurately and successfully segregate multimodal MRI brain tumors.
- 19 October 2023
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 34 (1)
RetractedRETRACTED: Multiencoder‐based federated intelligent deep learning model for brain tumor segmentation
Glioma, a primary tumor derived from brain glial cells, is around 45% of all intracranial tumors. Magnetic resonance imaging's (MRI's) precise glioma segmentation is crucial for clinical purposes. This article presents a novel automatic brain tumor segmentation approach based on a multi‐encoder‐based federated intelligent deep learning framework. The suggested method uses a U‐shaped network design that multiplies the single contraction path into several paths to explore semantic information modalities deeply. The basic convolutional layer uses an Inception module and dilated convolutions to extract multi‐scale features from the images using artificial intelligent. To emphasize segmentation‐related information while ignoring redundant channel dimension information and improving the accuracy of network segmentation, lightweight channel attention efficient channel attention (ECA) modules are inserted into the bottleneck layer and decoder. The collection of data for the 2018 Brain Tumor Segmentation Challenge (BraTS 2018) is used to test the effectiveness of the suggested structure, and the findings indicate that the growth core, for the entire tumor and the augmented tumor regions, respectively, the average Dice coefficients are 0.880, 0.784, and 0.757. These findings support the proposed algorithm's ability to accurately and successfully segregate multimodal MRI brain tumors.
- Open Access
- 17 March 2022
- Published by Society for Upliftment of Rural Economy (SURE) in Journal of AgriSearch
- Vol. 9 (01) , 12-15
Weed Management Practices on Crop Productivity and Economics in Dry-Direct Seeded Rice under Hill and Plateau Region of Eastern India
In direct seeded rice, weeds are the major problems limiting the crop productivity. Sesbania with direct seeded rice (DSR) as well as seeding rates of rice affects the weed density by smothering effect and therefore, it can be a better weed management practice. Two year on farm trials were conducted at the Kusma, Boarijore Block and Bhaluka, Sundarpahadi block of Godda from 2020 and 2021 to assess the effect of weed management on yields and economics in DSR. The results revealed that significantly the lowest density of grasses, broad leaved weeds (BLWs), sedges, total weed density, total weed dry weight and the highest weed control efficiency were recorded with the treatment of DSR + Sesbania over DSR (pre-sowing irrigation followed by tillage and rice seeding) followed by first post-sowing irrigation at 15 DAS and the farmer’s practice. Weed management practice, DSR + Sesbania was found significantly higher grain yield, gross returns, net returns, B: C ratio, production efficiency and economic efficiency over to followed by first post sowing irrigation at 15 DAS and farmer’s practice. While the farmer’s practice was recorded higher weed index and lowest weed control efficiency. Thus, on the basis present study it is concluded that weed management practice i.e. DSR + Sesbania could be a better option to reduced the weed infestation as well as improves the productivity of DSR in rainfed agro-ecosystem of Jharkhand.
- 17 March 2022
- Published by Society for Upliftment of Rural Economy (SURE) in Journal of AgriSearch
- Vol. 9 (01) , 12-15
Open AccessWeed Management Practices on Crop Productivity and Economics in Dry-Direct Seeded Rice under Hill and Plateau Region of Eastern India
In direct seeded rice, weeds are the major problems limiting the crop productivity. Sesbania with direct seeded rice (DSR) as well as seeding rates of rice affects the weed density by smothering effect and therefore, it can be a better weed management practice. Two year on farm trials were conducted at the Kusma, Boarijore Block and Bhaluka, Sundarpahadi block of Godda from 2020 and 2021 to assess the effect of weed management on yields and economics in DSR. The results revealed that significantly the lowest density of grasses, broad leaved weeds (BLWs), sedges, total weed density, total weed dry weight and the highest weed control efficiency were recorded with the treatment of DSR + Sesbania over DSR (pre-sowing irrigation followed by tillage and rice seeding) followed by first post-sowing irrigation at 15 DAS and the farmer’s practice. Weed management practice, DSR + Sesbania was found significantly higher grain yield, gross returns, net returns, B: C ratio, production efficiency and economic efficiency over to followed by first post sowing irrigation at 15 DAS and farmer’s practice. While the farmer’s practice was recorded higher weed index and lowest weed control efficiency. Thus, on the basis present study it is concluded that weed management practice i.e. DSR + Sesbania could be a better option to reduced the weed infestation as well as improves the productivity of DSR in rainfed agro-ecosystem of Jharkhand.
- 25 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Attacks on Vulnerable Web Applications
Web Application now days are an important part of our daily life. Attackers try to attack these web applications to gain valuable information about the users using these web applications. Attackers exploit vulnerabilities in a web application to gain user data. This paper describes in detail the most harmful attacks that occurs on vulnerable web applications that are: SQL Injection Attack, Cross-Site Scripting Attack (XSS) and Command Injection Attack and helps you understand mechanism for 3 different types of attacks how they take place, what threats they possess and what could be done to avoid them.
- 25 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Attacks on Vulnerable Web Applications
Web Application now days are an important part of our daily life. Attackers try to attack these web applications to gain valuable information about the users using these web applications. Attackers exploit vulnerabilities in a web application to gain user data. This paper describes in detail the most harmful attacks that occurs on vulnerable web applications that are: SQL Injection Attack, Cross-Site Scripting Attack (XSS) and Command Injection Attack and helps you understand mechanism for 3 different types of attacks how they take place, what threats they possess and what could be done to avoid them.
- Open Access
- 30 June 2017
- Published by ENGG Journals Publications in International Journal of Engineering and Technology
- Vol. 9 (3) , 2420-2434
Defacement of Colluding Attack Using Blowfish Algorithm
IJET is an international journal for the engineers and technologists. IJET publishes scholarly peer-reviewed research journal. The journal can be available online with full-text content freely.
- 30 June 2017
- Published by ENGG Journals Publications in International Journal of Engineering and Technology
- Vol. 9 (3) , 2420-2434
Open AccessDefacement of Colluding Attack Using Blowfish Algorithm
IJET is an international journal for the engineers and technologists. IJET publishes scholarly peer-reviewed research journal. The journal can be available online with full-text content freely.