Arti Gupta
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
Arti Gupta has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Vijay Kumar Chaurasiya
Department of Information Technology, IIIT Allahabad, Prayagraj, India
4 shared publications - Manish Kumar Maurya
IIIT Allahabad
2 shared publications Khyati Dhere
Department of Information Technology, Indian Institute of Information Technology at Allahabad, Allahabad, Uttar Pradesh, India
1 shared publication- Nikhil Goyal
IT Department, IIIT Allahabad, Prayagraj, India
1 shared publication Ritwik
Department of Information Technology, Indian Institute of Information Technology, Allahabad, Uttar Pradesh, India
1 shared publication- Vijay Kumar Chaurasiya
IT Department, IIIT Allahabad, Prayagraj, India
1 shared publication
Latest Publications
- 23 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Green Communications and Networking
- Vol. 10, 1308-1321
Adaptive Low-Latency Split Federated Learning With Dynamic Model Partitioning in Resource-Constrained Healthcare IoT
Federated Learning (FL) provides a platform that shows promise for healthcare applications, allowing users to train machine learning models on Internet of Things (IoT) devices. Nevertheless, the integration of FL with IoT encounters significant obstacles because of the limited processing capacity and the substantial computational demands of deep neural networks (DNNs) on IoT devices. In order to overcome these difficulties, Split Federated Learning (SFL) has been proposed as a feasible solution. The SFL framework allows for concurrent training on peripheral devices while transferring parts of the model to a server through a predetermined partition point. However, the existence of various devices, unpredictable channel conditions, and restricted resources diminishes the suitability of this strategy for reducing training delays on the device and communication delays between the client and server. This paper presents a resource-aware SFL scheme that intelligently chooses split points for devices and efficiently allocates computing resources for the server in wireless edge networks. To optimize efficiency, a quantization technique is utilized during the second phase to reduce communication latency. The challenge of reducing communication and on-device training delays is reframed as a contextual-bandit problem, and a dynamic split federated learning (DSFL) is introduced to resolve it, ensuring optimal performance and resource utilization. The proposed DSFL framework has been evaluated end-to-end on a real-time testbed and a physical platform. Experimental results demonstrate that the DSFL scheme reduces overall delay by 40% without affecting accuracy, compared to the existing FL approach.
- 23 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Green Communications and Networking
- Vol. 10, 1308-1321
Adaptive Low-Latency Split Federated Learning With Dynamic Model Partitioning in Resource-Constrained Healthcare IoT
Federated Learning (FL) provides a platform that shows promise for healthcare applications, allowing users to train machine learning models on Internet of Things (IoT) devices. Nevertheless, the integration of FL with IoT encounters significant obstacles because of the limited processing capacity and the substantial computational demands of deep neural networks (DNNs) on IoT devices. In order to overcome these difficulties, Split Federated Learning (SFL) has been proposed as a feasible solution. The SFL framework allows for concurrent training on peripheral devices while transferring parts of the model to a server through a predetermined partition point. However, the existence of various devices, unpredictable channel conditions, and restricted resources diminishes the suitability of this strategy for reducing training delays on the device and communication delays between the client and server. This paper presents a resource-aware SFL scheme that intelligently chooses split points for devices and efficiently allocates computing resources for the server in wireless edge networks. To optimize efficiency, a quantization technique is utilized during the second phase to reduce communication latency. The challenge of reducing communication and on-device training delays is reframed as a contextual-bandit problem, and a dynamic split federated learning (DSFL) is introduced to resolve it, ensuring optimal performance and resource utilization. The proposed DSFL framework has been evaluated end-to-end on a real-time testbed and a physical platform. Experimental results demonstrate that the DSFL scheme reduces overall delay by 40% without affecting accuracy, compared to the existing FL approach.
- Open Access
- 19 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 145054-145068
Privacy-Preserving Hybrid Federated Learning Framework for Mental Healthcare Applications: Clustered and Quantum Approaches
Privacy-preserving approaches are essential in health- care applications where sensitive data is involved. Federated learning (FL) has emerged as a widely adopted approach for collaboratively training decentralized models without sharing individual health records. However, ensuring privacy in health- care data, both during training and when clients exchange their models with a central server, remains a challenge. Bias, fairness, clients heterogeneity, and constrained computation are also challenging factors. To address this challenge, in this paper, a communication-efficient and privacy-preserving hybrid Federated learning (HFL) framework is specifically designed for mental healthcare applications. Two HFL approaches, namely Clustered Federated Learning (CFL) and Quantum Federated Learning (QFL), have been proposed. CFL focuses on leveraging the learning behaviour of clients and Conversely, QFL introduces a new phase to FL by incorporating a variational quantum classifier (VQC) for classification tasks. Angle encoding is used for a quantum state preparation to enhance data encoding and learning the quantum model. Experiments were conducted on independent and identically distributed (iid) and non-independent and identically distributed (non-iid) data to evaluate the performance of the proposed methods with state-of-the-art results available in the literature. The results demonstrate exceptional performance in the case of QFL, achieving an accuracy of 84.00%. CFL also exhibits promising results with an accuracy of 78.396%. Additionally, QFL achieves 18.75% better recall and CFL has 6.24% better precision than traditional FL. Nevertheless, it’s crucial to remember that every model has advantages and disadvantages of its own.
- 19 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 145054-145068
Open AccessPrivacy-Preserving Hybrid Federated Learning Framework for Mental Healthcare Applications: Clustered and Quantum Approaches
Privacy-preserving approaches are essential in health- care applications where sensitive data is involved. Federated learning (FL) has emerged as a widely adopted approach for collaboratively training decentralized models without sharing individual health records. However, ensuring privacy in health- care data, both during training and when clients exchange their models with a central server, remains a challenge. Bias, fairness, clients heterogeneity, and constrained computation are also challenging factors. To address this challenge, in this paper, a communication-efficient and privacy-preserving hybrid Federated learning (HFL) framework is specifically designed for mental healthcare applications. Two HFL approaches, namely Clustered Federated Learning (CFL) and Quantum Federated Learning (QFL), have been proposed. CFL focuses on leveraging the learning behaviour of clients and Conversely, QFL introduces a new phase to FL by incorporating a variational quantum classifier (VQC) for classification tasks. Angle encoding is used for a quantum state preparation to enhance data encoding and learning the quantum model. Experiments were conducted on independent and identically distributed (iid) and non-independent and identically distributed (non-iid) data to evaluate the performance of the proposed methods with state-of-the-art results available in the literature. The results demonstrate exceptional performance in the case of QFL, achieving an accuracy of 84.00%. CFL also exhibits promising results with an accuracy of 78.396%. Additionally, QFL achieves 18.75% better recall and CFL has 6.24% better precision than traditional FL. Nevertheless, it’s crucial to remember that every model has advantages and disadvantages of its own.
- 21 November 2023
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 80 (6) , 8406-8433
Integrating Healthcare 4.0 and WBAN: efficient redundancy reduction and adaptive packet scheduling using AR-DRL
- 21 November 2023
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 80 (6) , 8406-8433
Integrating Healthcare 4.0 and WBAN: efficient redundancy reduction and adaptive packet scheduling using AR-DRL
- 23 October 2023
- Published by Springer Nature in Applied Intelligence
- Vol. 53 (23) , 29153-29168
ISTGCN: Integrated spatio-temporal modeling for traffic prediction using traffic graph convolution network
- 23 October 2023
- Published by Springer Nature in Applied Intelligence
- Vol. 53 (23) , 29153-29168
ISTGCN: Integrated spatio-temporal modeling for traffic prediction using traffic graph convolution network
- 16 July 2023
- Published by Springer Nature in Wireless Networks
- Vol. 29 (8) , 3793-3808
QoS supported redundancy balanced data transmission scheme for wireless body area network based H-IoT
- 16 July 2023
- Published by Springer Nature in Wireless Networks
- Vol. 29 (8) , 3793-3808
QoS supported redundancy balanced data transmission scheme for wireless body area network based H-IoT