ABAnkur Bansal

Ankur Bansal

*This is an algorithmically generated author record based on publicly available information.

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


Ankur Bansal has a total of 42 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Hypergraph Convolutional Refinement in Latent Space for Underwater Digital Twins

    by Meghna Kapoor, Badri Narayan Subudhi, Thierry Bouwmans, Ankur Bansal

  • Open Access

    Joint Transmit and Jamming Power Optimization for Secrecy in Energy Harvesting Networks: A Reinforcement Learning Approach

    by Shalini Tripathi, Chinmoy Kundu, Animesh Yadav, Ankur Bansal, Holger Claussen, Lester Ho

    In this paper, we address the problem of joint allocation of transmit and jamming power at the source and destination, respectively, to enhance the long-term cumulative secrecy performance of an energy-harvesting wireless communication system until it stops functioning in the presence of an eavesdropper. The source and destination have energy-harvesting devices with limited battery capacities. The destination also has a full-duplex transceiver to transmit jamming signals for secrecy. We frame the problem as an infinite-horizon Markov decision process (MDP) problem and propose a reinforcement learning (RL)-based optimal joint power allocation (OJPA) algorithm that employs a policy iteration (PI) algorithm. Since the optimal algorithm is computationally expensive, we develop a low-complexity sub-optimal joint power allocation (SJPA) algorithm, namely, reduced state joint power allocation (RSJPA). Two other SJPA algorithms, the greedy algorithm (GA), and the naive algorithm (NA) are implemented as benchmarks. In addition, the OJPA algorithm outperforms the individual power allocation (IPA) algorithms termed individual transmit power allocation (ITPA) and individual jamming power allocation (IJPA), where the transmit and jamming powers, respectively, are optimized individually. The results show that the OJPA algorithm is also more energy efficient. Results also show that the OJPA algorithm significantly improves the secrecy performance compared to all SJPA algorithms. The OJPA algorithm also outperforms the secrecy performance of a genetic algorithm-based RL algorithm and a finite-horizon RL algorithm. The proposed RSJPA algorithm achieves nearly optimal performance with significantly less computational complexity marking it the balanced choice between the complexity and the performance. We find that the computational time for the RSJPA algorithm with considering only 50 percent of the total number of states is around 75 percent less than the OJPA algorithm.


  • Open Access

    Graph-based Moving Object Segmentation for underwater videos using semi-supervised learning

    by Meghna Kapoor, Wieke Prummel, Jhony H. Giraldo, Badri Narayan Subudhi, Anastasia Zakharova, Thierry Bouwmans, Ankur Bansal


  • Principal Graph Neighborhood Aggregation for Underwater Moving Object Detection

    by Meghna Kapoor, Badri Narayan Subudhi, Vinit Jakhetiya, Ankur Bansal


  • RIS-Assisted Multi-Aperture FSO Communication Network for High-Speed Train: Second-Order Statistical Analysis

    by Amina Girdher, Ankur Bansal

    This paper considers an optical reconfigurable intelligent surface (ORIS)-assisted free space optical (FSO) communication network to provide internet connectivity to the high speed train (HST). To maintain reliable FSO communication and compensate for severe pointing losses caused due to misalignment, we utilize a multi-aperture HST receiver that performs selection combining while achieving spatial diversity. In particular, we analyze the second-order statistics (SOS) at the HST receiver in the presence of atmospheric turbulence, foggy conditions, and misalignment error. We specifically develop the closed-form analytical expressions for the level crossing rate (LCR) and the average fade duration (AFD) of the system using the signal-to-noise ratio stochastic process under non-isotropic scattering environment. The effect of various system and channel parameters, including number of ORIS elements, number of receiving apertures, speed of the HST, misalignment error and fog parameters, mean angle-of-arrival, and degree of non-isotropic scattering, has been demonstrated on the LCR and AFD performances of the considered network. Further, by using finite-state Markov channel (FSMC) model, we derive packet error rate (PER) using the derived LCR expression. In order to analytically evaluate the optimum packet length for the FSMC model, we employ stop-and-wait automatic repeat request (SW-ARQ) protocol and maximize the system throughput. Additionally, it is shown numerically how different system settings affect the PER and throughput performances of the FSO-based HST communication network.


  • Energy Efficient NOMA for Mixed FSO-RF Communication System With IRS-Aided SLIPT

    by Amina Girdher, Ankur Bansal, Ankit Dubey

    This paper proposes a novel relay-based mixed free space optical-radio frequency (FSO-RF) communication system utilizing non-orthogonal multiple access (NOMA) to assist two users over RF-hop. Assuming non-availability of direct FSO-link, we consider the deployment of an optical intelligent reflecting surface (OIRS). Moreover, we deploy an RF intelligent reflecting surface (RIRS) in the vicinity of far user to improve its performance. We adopt simultaneous lightwave-information and power transfer (SLIPT) technology to harvest energy at relay node, which is utilized to forward the information signal over RF-hop and thus, makes the signal-to-noise ratio (SNR) of RF-hop dependent on the FSO-channel coefficients. For the proposed system with generalized Malaga ( $\mathcal {M}$ )-distributed FSO-link with pointing error and Nakagami- $m$ faded RF-link, we evaluate the system's performance in terms of outage probability (OP), coverage probability (CP), and throughput (TP). We also derive asymptotic outage at high SNR and obtain diversity order analytically. Moreover, we propose an efficient algorithm for designing of reflection coefficients of RIRS elements to maximize the downlink SNR of far user. Numerical results are provided to see the impact of system and channel parameters including imperfect SIC conditions, imperfect CSI of far-user channel, and power allocation coefficients on system's performance. Simulations are given to show the extension of the proposed system to multiple user scenario. The integration of OIRS and RIRS exhibits significant improvement in the performance of the considered NOMA-based system.


  • Fairness-Aware Energy Harvesting in RSMA-Aided MU-MISO VLC Network

    by Amina Girdher, Nishant Gupta, Ankur Bansal

    This letter studies rate-splitting multiple access (RSMA)-based visible light communication (VLC) network employing simultaneous light-wave information and power transfer (SLIPT) technology to assist multiple Internet of Things (IoT) devices while achieving self-sustainability. We formulate a fairness problem to maximize the minimum harvested energy among IoT devices to maximize network longevity by jointly optimizing the precoding matrix and direct current bias vector, subject to information flow control and total transmit power. An iterative approach is proposed to obtain a sub-optimal solution. Simulation results reveal the superiority of the proposed RSMA-based network over existing schemes under different network load scenarios, including underloaded and overloaded conditions.


  • Uplink NOMA With QoS-Based SIC for Mixed Underwater-Terrestrial Communication System

    by Nikhil Sharma, Amina Girdher, Ankur Bansal

    This work investigates the outage behavior of an uplink decode-and-forward (DF) based mixed underwater optical wireless-RF communication (UOW-RFC) system utilizing non-orthogonal multiple access (NOMA) for underwater transmission. A water surface vehicle (WSV), acting as relay, forwards the data of the underwater devices (UDs) to a terrestrial access point (AP) by utilizing the quality of service (QoS) based successive interference cancellation (SIC) schemes. In particular, we consider three different QoS-based SIC schemes at the WSV, namely (i) Basic QoS-based SIC (BQ-SIC), (ii) Advanced QoS-based SIC (AQ-SIC), and (iii) Enhanced QoS-based SIC (EQ-SIC), which are different from conventional channel state information (CSI)-based SIC. Moreover, we employ partial relaying over the RF hop, i.e., the relay forwards the data to AP even if it is able to decode the data of one UD only. Considering the mixture-Extended Generalized Gamma (mEGG) distribution with lab channel scenario and non-zero boresight pointing error model for underwater links and Nakagami- m distribution for RF link, we obtain the expressions for outage probability under all the three QoS-based SIC schemes in terms of bivariate and multivariate Fox-H functions. It is shown through the numerical results that, in comparison with the BQ-SIC scheme, the AQ-SIC scheme provides significant improvement in the outage performance of low-QoS UD only, whereas the EQ-SIC scheme outperforms both BQ-SIC and AQ-SIC schemes for high-QoS and low-QoS UDs. The numerical results also reveal that employing EQ-SIC at WSV enables to overcome the error floor problem of UL-NOMA. Further, we perform the asymptotic outage analysis and derive analytical diversity order for all the QoS-based SIC schemes considered in this work. We also compare the proposed DF-based system with its AF counterpart to demonstrate the superiority of the proposed model. The impact of various other system and underwater channel parameters such as, threshold, bubble level, salinity, temperature gradient, and link lengths is shown on the outage performance of UDs. The derived results have also been compared with the benchmark scheme without partial relaying.