Dr.R.Lathamanju

@srmrmp.edu.in

Associate Professor,ECE Department,Faculty of Engineering and Technology
SRM Institute of Science and Technology,Ramapuram Campus

Dr.R.Lathamanju


               Download Compact PDF  
https://researchid.co/lathamanju

RESEARCH INTERESTS

Wireless Sensor Networks,Internet of Things,Cloud Computing
17

Scopus Publications

Scopus Publications

  • A Performance Analysis on Load Balancing in Cloud Computing with Hybrid Approach
    V. Arulkumar, R. Lathamanju, K. Durga Devi, A. Raja
    Journal of Circuits Systems and Computers, 2025
    An Effective Load Balancing in Cloud Computing is a complex problem and optimization techniques are employed to allocate resources intelligently, balance workloads and optimize task scheduling, enhancing the overall performance and resource utilization in cloud environments. This research introduces the Jaguar Algorithm — Improved Reptile Search Optimization model, a hybrid approach combining the strengths of two nature-inspired metaheuristic techniques. The Jaguar Algorithm is utilized for load balancing and Improved Reptile Search Optimization is employed for task scheduling, which improves the resource utilization and reduction in wastage. The proposed JA-IRSO model has superior performance for load balancing, task scheduling mechanism, and robust and consistent task execution in Cloud Computing. The proposed JA-IRSO model attains an average execution time of 16[Formula: see text]s, a makespan of 45[Formula: see text]s, 70% of CPU utilization memory usage and 99% of average throughput for minor operations. These results showcase the proposed model performance that can manage medium-size workloads while ensuring higher reliability and efficient resource allocation. Overall, the proposed JA-IRSO model has the potential to address the complex challenges and enhance efficiency, reliability and user satisfaction.
  • RED-SM: A reinforced encoder–decoder transformer for unsupervised video summarization
    Venkatachalam ARULKUMAR, Rajendran LATHAMANJU, Rajamani THANGAM, Krishnamoorthy DURGA DEVI
    Revista Romana De Informatica Si Automatica, 2025
    The rapid growth of the video content across online platforms has made it increasingly important to generate concise summaries that help users quickly understand and navigate long videos. However, creating high-quality video summaries typically requires large amounts of annotated data, which is costly and often unavailable. To address this challenge, the authors propose a fully unsupervised approach to video summarization built on Transformer architectures. The method introduces the Reinforced Encoder-Decoder Summarizer Model (RED-SM), which uses multi-head self-attention and feature extraction to identify informative video segments without human labels. RED-SM incorporates sparsity-promoting penalties and a reinforcement learning reward that balances diversity, representativeness, and temporal smoothness to guide frame selection. To further enhance the summarization quality, the RED-SM with a BERT-based text extractor is integrated, enabling multimodal fusion of visual and textual cues. The approach is evaluated on the SumMe and TVSum datasets, as well as a newly curated dataset of 30 categories of short videos. The experiments show that the method consistently produces concise and high-quality summaries across diverse domains. These results highlight the RED-SM as an effective and scalable solution for unsupervised video summarization in real-world applications.
  • Enhancing Task Scheduling Process in Fog Computing using GTO-SSSA: A Metaheuristic Approach
    V. Arulkumar, R. Lathamanju, T. Nithya, T. Rajendran
    Journal of Intelligent Systems and Internet of Things, 2025
    Task scheduling (TS) in fog computing (FC) involves efficiently allocating computing tasks to fog nodes,
  • Implementing Deep Learning Techniques into AI-Powered Internet of Things Healthcare Devices for Precise EEG and ECG Signal Interpretation
    Y. Mary Reeja, R. Lathamanju, V. Arulkumar, V. Samuthira Pandi, B Yamini, T.C. Manjunath
    2025 International Conference on Engineering Innovations and Technologies Icoeit 2025, 2025
    Continuous monitoring and real-time analysis of essential physiological signals, such electroencephalography (EEG) and electrocardiography (ECG), has become possible due to the fast development of healthcare technologies, especially in the field of wearable devices. A wide range of neurological and cardiovascular diseases rely on these signals for diagnosis and monitoring. The intricacy, unpredictability, and noise that are intrinsic to electrocardiogram (ECG) and electroencephalogram (EEG) readings make accurate interpretation of these signals a significant challenge. This study investigates the feasibility of incorporating deep learning methods into AI-driven IoT healthcare devices in order to improve the accuracy and efficiency of EEG and ECG signal interpretation. The study's overarching goal is to automate and enhance the real-time detection, categorization, and analysis of these signals by integrating powerful machine learning models, particularly deep learning algorithms, into healthcare devices that are enabled by the Internet of Things (IoT). To manage the complex patterns in EEG and ECG signals, the suggested method makes use of hybrid deep learning architectures, recurrent neural networks (RNNs), and convolutional neural networks (CNNs). The benefit of these models is that they can be easily linked into Internet of Things (IoT) devices, allowing for continuous, remote patient monitoring. Arrhythmias, epileptic seizures, and other crucial events can be detected by these AI-powered devices through real-time data processing, allowing for timely medical interventions. In order to guarantee accurate signal interpretation in real-world settings, the research also explores the difficulties of noise reduction, signal pre-processing, and model optimization. Scalability and the capacity to collect massive datasets for additional model improvement are additional benefits of integrating IoT devices with cloud computing. This study's results demonstrate that Internet of Things (IoT) healthcare devices supplemented with deep learning can greatly boost the precision, accessibility, and accuracy of EEG and ECG data processing, which in turn improves patient outcomes by allowing for faster and more accurate diagnoses. In addition, the study demonstrates the promise of personalized healthcare by paving the way for adaptive treatments that are specific to each patient and continuous, real-time monitoring.
  • RETRACTION:Service application model design for users using fuzzy semantic ontology model in cloud computing
    V. Arulkumar, A. Sandana Karuppan, Sini Anna Alex, R. Lathamanju
    Journal of Intelligent and Fuzzy Systems, 2024
    In an era marked by the widespread adoption of cloud services, individuals and businesses face the daunting task of navigating a complex landscape to make informed choices. The inherent opacity of the cloud service environment underscores the need for methods that can effectively handle imprecise information. This research presents a novel and superior approach to aid customers in selecting the most suitable cloud services. Our work introduces a distinctive fuzzy decision-making paradigm, surpassing current methodologies. We leverage an innovative analytic hierarchy process technique to quantify the semantic similarity between concepts and employ a fuzzy ontology to elucidate the uncertain relationships among database items, facilitating precise service matching. Furthermore, we present a multi-faceted evaluation framework for ranking cloud services. To substantiate the efficacy of our similarity matching based on the fuzzy ontology, we conduct comprehensive testing. The results of our experiments provide compelling evidence of the viability and effectiveness of the proposed method. This research offers a valuable contribution to the challenging realm of cloud service selection, empowering individuals and organizations to make well-informed decisions amidst the cloud service abundance.
  • IMU based Inference System for Vehicles
    Vikram Adithya Anand, R Lathamanju, V Arulkumar
    2024 International Conference on Smart Technologies for Sustainable Development Goals Icstsdg 2024, 2024
    Roadways are the most commonly used channel of transport. Statistically, most transport related deaths are seen on roadways. This study is about an IMU based inferencing system that collects data through an inertial measurement unit and a GPS. The data is used to generate an inference. The IMU data (ie) the accelerometric and gyroscopic data are processed to generate tilt sensitive pitch and roll angles which are processed along with corresponding GPS data to survey a section of a roadway and assign it a suitable score based on the ease of travel in the corresponding channel. The scores generated are in comparison to other roads. Through data from multiple nodes which have employed the same channel, a comparative score is generated which can be used for route planning by businesses and civilians alike.
  • Real-Time Asset Tracking with IoT Core API and LORA Technology using Multiple Sensors
    Lathamanju R, Krishnavel K, Kishore G, VenkateshPrasath J
    2024 International Conference on Smart Technologies for Sustainable Development Goals Icstsdg 2024, 2024
    This project aims to create a robust real-time asset tracking system leveraging IoT and LoRa technology. By harnessing a suite of sensors-GPS for precise location tracking, accelerometers to detect speed and movement changes, gyroscopes for orientation and rotation data, alongside temperature and humidity sensors for environmental monitoring-the system collects comprehensive data from assets. This information is processed through microcontrollers and transmitted via LoRa transmitters for efficient long-range communication. Upon reception, the LoRa receiver forwards this data to another microcontroller, connecting to both an display and an IoT platform. This setup allows for immediate visualization of asset information, empowering users to monitor and manage assets effectively. The system's multifaceted sensor array and seamless communication architecture promise enhanced asset security, streamlined logistics, and the ability to respond proactively to environmental variations, ultimately optimizing asset management and ensuring the integrity of sensitive goods or environments.
  • Genetic-based Fuzzy IDS for Feature Set Reduction and Worm Hole Attack Detection
    M. Reji, Christeena Joseph, K. Thaiyalnayaki, R. Lathamanju
    Computer Systems Science and Engineering, 2023
    The wireless ad-hoc networks are decentralized networks with a dynamic topology that allows for end-to-end communications via multi-hop routing operations with several nodes collaborating themselves, when the destination and source nodes are not in range of coverage. Because of its wireless type, it has lot of security concerns than an infrastructure networks. Wormhole attacks are one of the most serious security vulnerabilities in the network layers. It is simple to launch, even if there is no prior network experience. Signatures are the sole thing that preventive measures rely on. Intrusion detection systems (IDS) and other reactive measures detect all types of threats. The majority of IDS employ features from various network layers. One issue is calculating a huge layered features set from an ad-hoc network. This research implements genetic algorithm (GA)-based feature reduction intrusion detection approaches to minimize the quantity of wireless feature sets required to identify worm hole attacks. For attack detection, the reduced feature set was put to a fuzzy logic system (FLS). The performance of proposed model was compared with principal component analysis (PCA) and statistical parametric mapping (SPM). Network performance analysis like delay, packet dropping ratio, normalized overhead, packet delivery ratio, average energy consumption, throughput, and control overhead are evaluated and the IDS performance parameters like detection ratio, accuracy, and false alarm rate are evaluated for validation of the proposed model. The proposed model achieves 95.5% in detection ratio with 96.8% accuracy and produces very less false alarm rate (FAR) of 14% when compared with existing techniques.
  • A secure and effective diffused framework for intelligent routing in transportation systems
    N. Bharathiraja, M. Shobana, M. Vijay Anand, R. Lathamanju, C. Shanmuganathan, V. Arulkumar
    International Journal of Computer Applications in Technology, 2023
    The consistently expanding traffic, different postponement delicate administrations and energy utilisation compelled prerequisites have carried gigantic difficulties to the ongoing correspondence networks in the transportation framework. Because of the great speed and repeating topological variations of Vehicular Sensor Networks, determining an associated course with sufficient idleness is a difficult task with many requirements and barriers. As a result, in order to combat this, we developed a measurable method for dealing with presumably determining the heap clog and energy utilisation during the lifespan of the sensor network for transportation framework. The paper proposes a Secure and Effective Diffused Framework that spotlights on lower energy use and secure correspondence. The least bounce include in coordinated dissemination is utilised as the rule for developing the slope in this system, which further develops security and dependability by adding the possibility of the angle to flag the course and pace of information transmission.
  • Empowering Agriculture: Classification of Diseases Affecting the Leaves and Spikes of Wheat Crop using Hybrid Deep Learning Methodology
    C. Sathish Kumar, Vijay Anand Kandaswamy, P. Sundara Bala Murugan, Srividhya S, P. Arivazhagi, R. Lathamanju
    IEEE 9th International Conference on Smart Structures and Systems Icsss 2023, 2023
    Worldwide, wheat ranks third in both harvesting and consumption of grains. Nevertheless, illnesses ruin a significant portion of wheat crops. Wheat crops are vulnerable to more than twenty different diseases. Consequently, it becomes exceedingly difficult to manually diagnose these disorders. Increases in both production and quality can be achieved via the use of automated disease categorization in wheat. Moreover, it has the potential to be a valuable tool for evaluating crop quality and setting prices. Disease diagnosis and categorization can benefit from image analysis based on deep learning. Among wheat plants, the spike and leaves take the biggest hit. These features are diagnostic for the vast majority of illnesses. This is due to a combination of reasons, including the fact that farm laborers are often illiterate and the wide variety of agricultural goods available. There have been a number of different models put out there as possible answers to the problem of wheat harvest disease detection. In order to detect and classify illnesses that impact wheat harvests, this study presented a new approach called Hybrid Learning for Wheat Crop Disease Detection (HLWCDD). This methodology combines Convolutional Neural Network (CNN) and Random Forest (RF) algorithms. Deep Classification Learning Model (DCLM), an existing deep learning model, is essentially a hybrid of Neural Networks and Support Vector Machines (SVMs). The suggested model is compared to this. In this study, we assess both models and demonstrate how effective the suggested method is. The programme makes use of trained models to detect important features in the images. Using the main criteria mentioned earlier, the proposed approach can distinguish between wheat harvests that have been impacted by disease and those that have not. After collecting 3,200 photos for this investigation, the dependability of the findings was determined to be 97.29%. Out of the total number of photos, eleven classes showed sick crops and one showed healthy crops. The photos that make up the collection were rotated at different angles so that the proposed model could detect and categorize illnesses from multiple viewpoints.
  • Design high efficiency sea-water antenna for maritime wireless communication
    V. Subashini, A. Raja, Lathamanju, S. Akshaya Kumar, A. Bhuvaneshwari, K. Himavarni
    Aip Conference Proceedings, 2022
  • Implementation of Goods Monitoring System Using Cloud
    V. Arulkumar, R. Lathamanju, V. Sundari, K. Thaiyalnayaki
    Lecture Notes in Networks and Systems, 2022
  • LOWER GRADE GLIOMA DETECTION USING MRI IMAGE
    Preetha R, S. Vanaja, S. Sudha, M. Vidyalakshmi, R. Lathamanju
    Proceedings of the 6th International Conference on Communication and Electronics Systems Icces 2021, 2021
  • Design of Dual Band Meander Line Scoop Antenna for ISM Bands
    A Iyswariya, R. Preetha, V. Chinnammal, R. Lathamanju, K. Durgadevi, Praveen Kumar V
    Proceedings of the 5th International Conference on I Smac Iot in Social Mobile Analytics and Cloud I Smac 2021, 2021
  • Improving elasticity in cloud with predictive algorithms
    Arulkumar Venkatachalam, R. Lathamanju, M. Shobana, A. Sandanakaruppan
    Proceedings of the International Conference on Smart Technologies in Computing Electrical and Electronics Icstcee 2020, 2020
  • Start to Finish Automation Achieve on Cloud with Build Channel: By DevOps Method
    V. Arulkumar, R. Lathamanju
    Procedia Computer Science, 2019
  • ECC-pattern based secure end to end data aggregation algorithm in WSN
    International Journal of Applied Engineering Research, 2015