Sundar S

Dr. Sundar S

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 June 2022 in International Journal of Wireless Information Networks
Verified
Journal Article
Closed access
PDF file
MMM A Matheen
M A Matheen
SSSundar S
Sundar S

18 October 2023 in IEEE Access
Verified
Journal Article
Open access
MRM. Rajeswara Rao
M. Rajeswara Rao
SSSundar S
Sundar S
In Wide Area Networks (WANs), resource allocation is essential since computer networks manage complex optimization difficulties. The goal of optimal resource allocation is to improve total computing productivity. Distributing numerous specialized data and communication technology services inside aWAN can be challenging due to a wide range of application demands. A system to provide enhanced data transfer rate with minimum power transmission in a Low PowerWide Area Network (LPWAN) with the utilization of reinforcement learning technique is developed in this work. Here, the reinforcement learning method is used to determine the parameters involved for minimizing the transmission power. The resources in the networks, like the channel, spreading factor, and transmission power in the LPWAN is optimized. These parameters optimization is aided with the help of the newly developed Hybrid Coati with Energy Valley Optimization Algorithm (HC-EVOA). A large number of reinforcement learning agents are generated that match the terminal hubs in the server of the LPWAN. Once the reinforcement agent is generated, then the optimized transmission parameter is given to these terminal hubs of the network. The optimization is carried out to enhance the throughput and reduce the energy consumption rate by the equipment in the network.Simulations are conducted on the developed model to prove the system’s effectiveness. Based on our analysis, at transmission power of 8, the developed HC-EVOA-based optimal resource allocation system obtains energy consumption as 12.86% lower than GSO, 19.29% lower than ROA, 2.76% lower than COA, and 2.81% lower than EVO.

29 February 2024 in Engineering Proceedings
Verified
Conference Paper
Open access
PDF file
SBSiddharth Bhattacharya
Siddharth Bhattacharya
AKAshwini Kumar
Ashwini Kumar
KKKumar Krishav
Kumar Krishav
SPSourav Panda
Sourav Panda
VCVidhyapathi CM
Vidhyapathi CM
KBKarthikeyan Balasubramaniyan
Karthikeyan Balasubramaniyan
This research presents a novel Self-Adaptive Waste Management System (SAWMS) that integrates advanced technology to address the pressing challenges of waste sorting and classification. SAWMS leverages Convolutional Neural Networks (CNNs) in conjunction with conveyor belt technology to achieve real-time object classification and self-training capabilities. The system utilizes sensors for object detection and a camera for image capture, enabling an accurate initial classification of waste objects into predefined categories such as food waste, metal, and plastic bottles. Notably, our proposed system sets itself apart by its unique ability to adapt and self-train based on classification errors, ensuring ongoing accuracy even in the face of changing waste compositions. Through dynamic adjustments of the conveyor belt’s destination, it efficiently directs waste objects to their appropriate bins for disposal or recycling. This research demonstrates the potential of SAWMS to revolutionize waste management practices, offering an agile and sustainable solution to the evolving challenges of waste sorting and disposal.

29 May 2024 in IEEE Access
Verified
Journal Article
Open access
MRM. Rajeswara Rao
M. Rajeswara Rao
SSSundar S
Sundar S
Wireless Sensor Networks (WSN) are adopting low-power wide area networks (LPWAN), such as long-range (LoRa) wide area networks, to increase communication standards. LoRa has been used to gather sensor data for many applications, such as environmental monitoring. The existing LoRa system faces degradation in network performance because of interference and congestion with the development of Internet-of-Things (IoT) devices. More than the device parameters and algorithms must be improved in large IoT applications. In massive LoRa systems, resource allocation is effectively performed using new reinforcement learning and machine learning approaches. These approaches have proven to be quite effective. Hence, this work implements an efficient optimal resource allocation scheme for effective data transmission over the LoRa with the minor power requirement with the aid of Deep Adaptive Reinforcement Learning (DARL). The parameters required to minimize the power requirement while transmitting the data are estimated with the help of this DARL model. The variables in the DARL are optimally selected by using a new optimization algorithm named Integrated Remora with Lotus Effect Optimization Algorithm (IR-LEOA) that is executed by combining Remora Optimization Algorithm (ROA) with the Lotus Effect Optimization Algorithm (LEA). The network parameters, such as the transmission power, channel, and spreading factor, are tuned using the same IR-LEOA. The server in the LoRa is matched by the agents generated by the DARL model. Then, the transmission parameters are given to the network’s terminal hub after the agents in the DARL are generated. Throughput, energy efficiency, latency, and transmission rate are analyzed using this optimization strategy. The effectiveness of the model is proved by conducting extensive experimentation.

16 February 2023 in Sensors
Verified
Journal Article
Open access
PDF file
MMM A Matheen
M A Matheen
SSSundar S
Sundar S
Wireless Multimedia Sensor Network (WMSN) is a powerful technology that is widely used to gather data and monitor the actual environment for analysis. Furthermore, multimedia applications’ needs and the features, such as constrained latency and high bandwidth consumption, complicate the design of WMSN routing protocols. Despite several methods, the trouble of designing WMSNs routing protocol remains a hurdle. The miniaturization and enhancement of hardware facilitate an extensive range of applications in the military and public sectors. On the contrary, the streaming of multimedia content is captured and generated due to some event-triggered surveillance for a long duration of time. Hence, it is necessary for wireless multimedia sensor network (WMSN) to provide a strong hardware foundation, thereby satisfying Quality of Service (QoS) requirements. Initially, the network is clustered into several clusters and the nodes with rich resources are chosen as cluster heads. The significant intention of this paper is to eliminate data redundancy and to select optimal cluster heads, thereby minimizing the energy consumption. Therefore, this paper proposes a novel Fuzzy Criminal Search Ebola Optimization (FCSEO) algorithm for optimal selection of cluster heads. In addition to this, the data redundancy present in the proposed algorithm is mitigated and thus the network lifetime is enhanced. Finally, extensive experimentation is carried out for various performance measures to determine the efficiency of the proposed approach.

24 October 2024 in Results in Engineering
Verified
Journal Article
Open access
ARA. Hena Rubavathy
A. Hena Rubavathy
SSSundar S
Sundar S