Deepak Kumar Anandhan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Deepak Kumar Anandhan has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Kochupillai Selvaraj Arikumar
Department of Data Science and Business Systems, College of Engineering and Technology, SRM Institute of Science and Technology (SRMIST), Kattankulathur, India
5 shared publications - Sahaya Beni Prathiba
Centre for Cyber Physical Systems, School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India
5 shared publications - Joel Jose Puga Coelho Rodrigues
Federal University of Piau (UFPI), Teresina - PI, Brazil
2 shared publications - Thippa Reddy Gadekallu
Lovely Professional University
2 shared publications - Aditya Saran Shyam Kumar
School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India
1 shared publication - C. Ashokkumar
Department of Computing Technologies, SRM Institute of Science and Technology, Chennai, India, India
1 shared publication
Latest Publications
- 11 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (5) , 8296-8308
QuaRTA-6G: Unified Post-Quantum Security and Quantum Learning for UAVs in 6G IoT
Unmanned aerial vehicles (UAVs), as key enablers of 6G-enabled Internet of Things (IoT) ecosystems, facilitate dynamic aerial coverage, seamless edge intelligence, and adaptive routing. However, despite these advantages, the reliability and trustworthiness of UAV swarms in 6G remain critical concerns due to rising quantum threats and limitations of traditional machine learning approaches. This article presents QuaRTA-6G, a quantum-resilient, trust-aware, and accountable framework that provides a unified solution for 6G UAV swarms. QuaRTA-6G achieves security, trust, and efficiency by seamlessly combining post-quantum cryptography (PQC) for secure communication, a decentralized ledger for identity and trust management, and variational quantum federated learning (VQFL) for efficient swarm intelligence. For quantum-resistant authentication and immutable UAV identity verification, QuaRTA-6G leverages CRYSTALS-Kyber with blockchain. Through simulations, QuaRTA-6G achieves secure authentication handshakes in under 2 ms and scales robustly to swarms of more than 100 UAVs, keeping high integrity even under 20% packet loss. Experiments demonstrate that, even under strong data poisoning attacks, the framework achieves 92% accuracy and 85% mission success rate, while comprehensive resource analysis confirms its feasibility across both standard and resource-constrained UAV platforms. Furthermore, an ablation study demonstrates that each module of QuaRTA-6G is essential for ensuring a responsible and trustworthy 6G UAV framework.
- 11 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (5) , 8296-8308
QuaRTA-6G: Unified Post-Quantum Security and Quantum Learning for UAVs in 6G IoT
Unmanned aerial vehicles (UAVs), as key enablers of 6G-enabled Internet of Things (IoT) ecosystems, facilitate dynamic aerial coverage, seamless edge intelligence, and adaptive routing. However, despite these advantages, the reliability and trustworthiness of UAV swarms in 6G remain critical concerns due to rising quantum threats and limitations of traditional machine learning approaches. This article presents QuaRTA-6G, a quantum-resilient, trust-aware, and accountable framework that provides a unified solution for 6G UAV swarms. QuaRTA-6G achieves security, trust, and efficiency by seamlessly combining post-quantum cryptography (PQC) for secure communication, a decentralized ledger for identity and trust management, and variational quantum federated learning (VQFL) for efficient swarm intelligence. For quantum-resistant authentication and immutable UAV identity verification, QuaRTA-6G leverages CRYSTALS-Kyber with blockchain. Through simulations, QuaRTA-6G achieves secure authentication handshakes in under 2 ms and scales robustly to swarms of more than 100 UAVs, keeping high integrity even under 20% packet loss. Experiments demonstrate that, even under strong data poisoning attacks, the framework achieves 92% accuracy and 85% mission success rate, while comprehensive resource analysis confirms its feasibility across both standard and resource-constrained UAV platforms. Furthermore, an ablation study demonstrates that each module of QuaRTA-6G is essential for ensuring a responsible and trustworthy 6G UAV framework.
- 8 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (6) , 7833-7842
Enhanced Surface Reconstruction and Semantic Segmentation of LiDAR Data in Autonomous Vehicle Perception Systems
Autonomous Vehicles (AVs) are redefining the transportation sector through their ability to navigate, make decisions, and complete autonomous tasks. For accurate perception and comprehension of the surroundings, the AVs heavily rely on segmenting high-resolution 3D point cloud data provided by Light Detection and Ranging (LiDAR) sensors for discerning objects and other environmental features. However, the current vehicular segmentation approaches experience shortcomings in data insufficiency, computational performance, and precision concerns. Hence, to counteract these limitations, the paper proposes a Semantic Segmentation approach using Ball-Pivoting Algorithm and U-Net (SSBU) that harmoniously combines the Ball-Pivoting surface reconstruction algorithm and 3D U-Net to enhance image characteristics, leading to highly accurate outcomes with optimal cost efficiency. This SSBU integration involves carrying out augmentations and pre-processing of the raw LiDAR data to transform them into voxels through the process of Voxelization. The voxels are further improved through a surface reconstruction technique that utilizes the Ball Pivoting Algorithm (BPA). The resulting 3D model is analyzed using 3D U-Net deep learning architecture for robust and real-time interpretation. The implementation has produced a mean Intersection Over Union (IoU) of 83.3 over the NuScenes data and 69.7 on the KITTI dataset, outperforming the state-of-the-art.
- 8 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (6) , 7833-7842
Enhanced Surface Reconstruction and Semantic Segmentation of LiDAR Data in Autonomous Vehicle Perception Systems
Autonomous Vehicles (AVs) are redefining the transportation sector through their ability to navigate, make decisions, and complete autonomous tasks. For accurate perception and comprehension of the surroundings, the AVs heavily rely on segmenting high-resolution 3D point cloud data provided by Light Detection and Ranging (LiDAR) sensors for discerning objects and other environmental features. However, the current vehicular segmentation approaches experience shortcomings in data insufficiency, computational performance, and precision concerns. Hence, to counteract these limitations, the paper proposes a Semantic Segmentation approach using Ball-Pivoting Algorithm and U-Net (SSBU) that harmoniously combines the Ball-Pivoting surface reconstruction algorithm and 3D U-Net to enhance image characteristics, leading to highly accurate outcomes with optimal cost efficiency. This SSBU integration involves carrying out augmentations and pre-processing of the raw LiDAR data to transform them into voxels through the process of Voxelization. The voxels are further improved through a surface reconstruction technique that utilizes the Ball Pivoting Algorithm (BPA). The resulting 3D model is analyzed using 3D U-Net deep learning architecture for robust and real-time interpretation. The implementation has produced a mean Intersection Over Union (IoU) of 83.3 over the NuScenes data and 69.7 on the KITTI dataset, outperforming the state-of-the-art.
- 20 November 2024
- Published by Springer Nature
- p. 363-373
Machine Learning Based Earlier Identification of Liver Disease Using Ultrasound Images
- 20 November 2024
- Published by Springer Nature
- p. 363-373
Machine Learning Based Earlier Identification of Liver Disease Using Ultrasound Images
- 13 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 70 (3) , 6131-6139
Co-Training-Based Personalized Federated Learning With Generative Adversarial Networks for Enhanced Mobile Smart Healthcare Diagnosis
The widespread implementation of Artificial Intelligence (AI) has led to significant advancements in disease diagnosis. Personalized Federated Learning (FL) trains models tailored to each patient’s needs but often overlooks model architecture heterogeneity. We propose a novel Co-training-based personalized FL with Generative Adversarial Networks (GANs) for Smart Healthcare Diagnosis (CFG-SHD). This approach allows privacy-preserving participation in FL by enabling patients to keep their model architectures and parameters private. Key contributions include integrating co-training into FL for leveraging multiple data views and using GANs to generate synthetic data, ensuring data privacy. By addressing model architecture heterogeneity our approach offers a robust solution for personalized healthcare diagnostics, aligning with the diverse needs of modern healthcare systems and advancing patient-centric AI applications. CFG-SHD enhances personalized diagnosis accuracy, achieving 97.16%, 98.04%, and 97.88% on the PAD-UFES-20, HAM10000, and PH datasets, respectively.
- 13 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 70 (3) , 6131-6139
Co-Training-Based Personalized Federated Learning With Generative Adversarial Networks for Enhanced Mobile Smart Healthcare Diagnosis
The widespread implementation of Artificial Intelligence (AI) has led to significant advancements in disease diagnosis. Personalized Federated Learning (FL) trains models tailored to each patient’s needs but often overlooks model architecture heterogeneity. We propose a novel Co-training-based personalized FL with Generative Adversarial Networks (GANs) for Smart Healthcare Diagnosis (CFG-SHD). This approach allows privacy-preserving participation in FL by enabling patients to keep their model architectures and parameters private. Key contributions include integrating co-training into FL for leveraging multiple data views and using GANs to generate synthetic data, ensuring data privacy. By addressing model architecture heterogeneity our approach offers a robust solution for personalized healthcare diagnostics, aligning with the diverse needs of modern healthcare systems and advancing patient-centric AI applications. CFG-SHD enhances personalized diagnosis accuracy, achieving 97.16%, 98.04%, and 97.88% on the PAD-UFES-20, HAM10000, and PH datasets, respectively.
- 6 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (11) , 16277-16287
A Blockchain-Powered Malicious Node Detection in Internet of Autonomous Vehicles
The proliferation of Autonomous Vehicles (AVs) in recent times has opened up new possibilities for effective and secure transportation. However, with the increasing adoption of AVs, guaranteeing the accuracy and security of their sensory systems is becoming paramount. Specifically, the vulnerability of these systems to malware and sensor faults can pose significant risks to the dependable and secure operation of the vehicle. To identify and combat these issues we propose a stream-based Blockchain-powered Malicious Node Detection (BMND) method to analyze and report any malicious activity of the AV operating as a node on the Internet of Autonomous Vehicles (IoAV) network, wherein the existing solutions are at lower latency. BMND involves the detection of sensor anomalies and defects post-production of the AV. In the case that malware or any other malicious software is detected on the onboard compute unit it is isolated and contained, and the AV will be classified as malicious until appropriate remedial measures are taken to deter any sharing of erroneous or malicious data. When the AV is deemed safe from malware and defects in the system then a block is mined by the AV node and a unique ID is assigned to allow data transfers on the blockchain with other nodes. Only active nodes with assigned IDs and available blocks for transactions on the blockchain influence AV decision-making. BMND would allow modern AVs on the road to effectively communicate with reliable information. Experimental analysis shows that the malware detection in BMND is 4.4% more accurate with an F1-score of $\sim$ 0.99 as compared to previous and other current state-of-the-art methods, and the communication capabilities of BMND are also better regarding security and latency concerning proposed vanilla blockchain methods.
- 6 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (11) , 16277-16287
A Blockchain-Powered Malicious Node Detection in Internet of Autonomous Vehicles
The proliferation of Autonomous Vehicles (AVs) in recent times has opened up new possibilities for effective and secure transportation. However, with the increasing adoption of AVs, guaranteeing the accuracy and security of their sensory systems is becoming paramount. Specifically, the vulnerability of these systems to malware and sensor faults can pose significant risks to the dependable and secure operation of the vehicle. To identify and combat these issues we propose a stream-based Blockchain-powered Malicious Node Detection (BMND) method to analyze and report any malicious activity of the AV operating as a node on the Internet of Autonomous Vehicles (IoAV) network, wherein the existing solutions are at lower latency. BMND involves the detection of sensor anomalies and defects post-production of the AV. In the case that malware or any other malicious software is detected on the onboard compute unit it is isolated and contained, and the AV will be classified as malicious until appropriate remedial measures are taken to deter any sharing of erroneous or malicious data. When the AV is deemed safe from malware and defects in the system then a block is mined by the AV node and a unique ID is assigned to allow data transfers on the blockchain with other nodes. Only active nodes with assigned IDs and available blocks for transactions on the blockchain influence AV decision-making. BMND would allow modern AVs on the road to effectively communicate with reliable information. Experimental analysis shows that the malware detection in BMND is 4.4% more accurate with an F1-score of $\sim$ 0.99 as compared to previous and other current state-of-the-art methods, and the communication capabilities of BMND are also better regarding security and latency concerning proposed vanilla blockchain methods.
- Open Access
- 16 December 2022
- Published by MDPI AG in Electronics
- Vol. 11 (24) , 4203
Real-Time 3D Object Detection and Classification in Autonomous Driving Environment Using 3D LiDAR and Camera Sensors
The rapid development of Autonomous Vehicles (AVs) increases the requirement for the accurate prediction of objects in the vicinity to guarantee safer journeys. For effectively predicting objects, sensors such as Three-Dimensional Light Detection and Ranging (3D LiDAR) and cameras can be used. The 3D LiDAR sensor captures the 3D shape of the object and produces point cloud data that describes the geometrical structure of the object. The LiDAR-only detectors may be subject to false detection or even non-detection over objects located at high distances. The camera sensor captures RGB images with sufficient attributes that describe the distinct identification of the object. The high-resolution images produced by the camera sensor benefit the precise classification of the objects. However, hindrances such as the absence of depth information from the images, unstructured point clouds, and cross modalities affect assertion and boil down the environmental perception. To this end, this paper proposes an object detection mechanism that fuses the data received from the camera sensor and the 3D LiDAR sensor (OD-C3DL). The 3D LiDAR sensor obtains point clouds of the object such as distance, position, and geometric shape. The OD-C3DL employs Convolutional Neural Networks (CNN) for further processing point clouds obtained from the 3D LiDAR sensor and the camera sensor to recognize the objects effectively. The point cloud of the LiDAR is enhanced and fused with the image space on the Regions of Interest (ROI) for easy recognition of the objects. The evaluation results show that the OD-C3DL can provide an average of 89 real-time objects for a frame and reduces the extraction time by a recall rate of 94%. The average processing time is 65ms, which makes the OD-C3DL model incredibly suitable for the AVs perception. Furthermore, OD-C3DL provides mean accuracy for identifying automobiles and pedestrians at a moderate degree of difficulty is higher than that of the previous models at 79.13% and 88.76%.
- 16 December 2022
- Published by MDPI AG in Electronics
- Vol. 11 (24) , 4203
Open AccessReal-Time 3D Object Detection and Classification in Autonomous Driving Environment Using 3D LiDAR and Camera Sensors
The rapid development of Autonomous Vehicles (AVs) increases the requirement for the accurate prediction of objects in the vicinity to guarantee safer journeys. For effectively predicting objects, sensors such as Three-Dimensional Light Detection and Ranging (3D LiDAR) and cameras can be used. The 3D LiDAR sensor captures the 3D shape of the object and produces point cloud data that describes the geometrical structure of the object. The LiDAR-only detectors may be subject to false detection or even non-detection over objects located at high distances. The camera sensor captures RGB images with sufficient attributes that describe the distinct identification of the object. The high-resolution images produced by the camera sensor benefit the precise classification of the objects. However, hindrances such as the absence of depth information from the images, unstructured point clouds, and cross modalities affect assertion and boil down the environmental perception. To this end, this paper proposes an object detection mechanism that fuses the data received from the camera sensor and the 3D LiDAR sensor (OD-C3DL). The 3D LiDAR sensor obtains point clouds of the object such as distance, position, and geometric shape. The OD-C3DL employs Convolutional Neural Networks (CNN) for further processing point clouds obtained from the 3D LiDAR sensor and the camera sensor to recognize the objects effectively. The point cloud of the LiDAR is enhanced and fused with the image space on the Regions of Interest (ROI) for easy recognition of the objects. The evaluation results show that the OD-C3DL can provide an average of 89 real-time objects for a frame and reduces the extraction time by a recall rate of 94%. The average processing time is 65ms, which makes the OD-C3DL model incredibly suitable for the AVs perception. Furthermore, OD-C3DL provides mean accuracy for identifying automobiles and pedestrians at a moderate degree of difficulty is higher than that of the previous models at 79.13% and 88.76%.