Boosting Fault-Tolerant Scheduling with Smart Resource Management for Industrial Cyber-Physical Systems K.V.S. Prasad, Ravi Varman, KDV Prasad, D. Praveena, P. Chinniah, Sathyakala S 6th International Conference on Mobile Computing and Sustainable Informatics Icmcsi 2025 Proceedings, 2025 Industrial Cyber-Physical Systems (ICPS) are integral to modern industrial automation, where precise scheduling, efficient resource allocation, and robust fault tolerance are paramount. As the complexity of ICPS grows, so do the challenges of maintaining system resilience and network performance under dynamic and potentially unpredictable conditions. Traditional scheduling and resource management techniques in ICPS often fall short of meeting the stringent requirements of real-time responsiveness and fault tolerance. Existing methods struggle to optimize performance while simultaneously managing system faults, which can lead to significant operational downtime. This research is driven by the need to create a more robust approach that not only enhances scheduling efficiency but also integrates fault detection and network performance optimization in a resource-constrained environment. This study aims to boost fault-tolerant scheduling by integrating Reinforcement Q-Learning Using LSTM Attention mechanisms for optimized resource allocation and scheduling. Additionally, it incorporates Slimmable Pruned Neural Networks for efficient fault detection and a Modified Crayfish Optimization technique to enhance network performance. The proposed model achieved a scheduling accuracy exceeding 99.5%, fault detection precision above 99.2%, and stability of the network throughput more than 99.7 % compared to the traditional approaches. These metrics highlight the model's high performance and capability to adapt dynamically to ICPS requirements. By fusing advanced reinforcement learning, neural pruning for fault detection, and optimized network strategies, this research presents a transformative approach for ICPS. The presented method demonstrate a significant leap in scheduling reliability, fault resilience, and overall network efficiency, marking a critical advancement in fault-tolerant industrial system design.
Enhanced Spectrum Distribution for 5G and Future: Employing Deep Reinforcement Learning Algorithms and Cognitive Radio S. Varalakshmi, Mohammad Omar Sabri, D. Praveena, M. Ashok Babu, Logitha. S, B. Uma Maheswari 2025 2nd Asia Pacific Conference on Innovation in Technology Apcit 2025, 2025 The fifth generation (5G) wireless network introduces new challenges to the radio frequency (RF) spectrum which will revolutionize the way that this spectrum has been used before, due to an explosive growth in both the number of users and the diversity of user requirement, also questing for higher data rates. Conventional static spectrum allocation schemes have become less and less efficient, leading to spectrum underuse and overcrowding. In this work, we set a dynamic and intelligent spectrum allocation strategy by combining Cognitive Radio (CR) technology and Deep Reinforcement Learning (DRL) algorithm, and realize dynamic, autonomous, and efficient utilization of spectral resources in real time. Cognitive Radio allows unlicensed users (secondary users) to opportunistically use underutilized licensed spectrum bands without causing interference to primary users. However, in dynamic environments, the decision process for spectrum sensing, allocation and switching needs to be made in real-time and thus will be a challenging task. For this purpose, we use DRL methods including DQN, Double DQN, as well as PPO to design agents who can learn appropriate spectrum policies by interacting with the wireless environment. The framework models the spectrum allocation as a Markov Decision Process (MDP), in which the agent observes channel parameters such as LSD, interference, and the availability of bands to determine the frequency bands. Theai (TD) function approximator of the mean reward of theh-hop network in terms of spectral efficiency, QoS and minimum interference. Simulations in 5G-like environments demonstrate the superior adaptivity of DRL-empowered CR systems over rule-based and myopic approaches to responding to rapid variations in real-time network conditions. This line of thought is especially relevant for ultra-dense network (UDN) deployment, Internet of Things (IoT) application, as well as the potential 6G era, where the issue of spectrum shortage and interference control will be even more serious. Also, the DRL-based paradigm is scalable in multi-TVWS agents environment where cooperative decision can be made by the distributed base stations and edge devices. The research is a substantial step forward in developing cognitive spectrum access in future wireless networks. By integrating the flexibility of CR with the learning ability of DRL, our system achieves efficient spectrum utilization, reduces collisions and achieves QoS-aware communication. The invention provides the foundation for cognitive, self-optimizing wireless structures, which can meet the fidelity and quality of service requirements of 5G and its successors.
Decision Support System based on Industry 5.0 in Artificial Intelligence International Journal of Intelligent Systems and Applications in Engineering, 2024
Pattern-Aware Indoor Semantic Segmentation Based on Visual Optimization Learning Sathish Kumar Kannaiah, Bhavani M, Praveena D 2024 International Conference on Integration of Emerging Technologies for the Digital World Icietdw 2024, 2024 Semantic segmentation of indoor scenes plays a pivotal role in various applications such as indoor navigation systems, creating detailed and accurate indoor maps, and optimizing route planning for both humans and robots. However, effectively integrating RGB (color) and HHA (depth) images for indoor semantic segmentation poses both promise and challenge due to the diverse textures and structures present in indoor environments, coupled with the varying significance of different modalities. Traditionally, tasks like semantic segmentation and depth estimation have been treated as separate entities in computer vision. However, recent advancements in research have explored the potential benefits of combining these tasks into a unified framework. The rationale behind this exploration lies in the inherent correlation between semantic understanding and depth perception, suggesting that integrating these tasks could lead to more accurate estimations. Our approach diverges from conventional segmentation methods by proposing the integration of two neural network models to achieve precise semantic segmentation specifically tailored for mobile robot mapping applications. Initially, we employ a model to identify salient objects within the scene, which are then delineated in grayscale. Subsequently, the contours of these salient objects, along with their semantic labels, are projected onto the corresponding RGB image, resulting in the segmentation of important objects within the indoor environment. By focusing on salient objects rather than considering the entirety of the scene, our method streamlines the segmentation process, simplifying the consideration of background elements. This targeted approach is particularly advantageous in scenarios where efficient and accurate segmentation of relevant objects is paramount, such as in robotic navigation tasks within complex indoor environments.
Evolutionary Approach-Based Hybrid CNN and SVM for Effective Plant Disease Classification Senthil Pandi S, Praveena D, Vaijayanthi. S, Muthu Kumar S 2024 IEEE International Conference on Communication Computing and Signal Processing Iicccs 2024, 2024 Agriculture is one of the prime factors that form the backbone of the economy of India. Also, with its rapidly growing population, the demand for food is increasing manifold. Thus, there arises a dire need to augment agricultural productivity to meet this ever-growing demand. One of the highest challenges that prevents quite ideal crop yields from being acquired is the prevalence of plant diseases, which could be due to many kinds and types of pathogens. For example, bacteria, viruses, fungi, and others are at fault. Thus, the discovery of effective detection systems becomes essential to combat their ill effects. One of the most promising strategies for plant disease identification is using machine learning algorithms. These techniques have proved to be effective in analysis resulting from big data, mainly due to their focus on reaching specific specified results that come out perfectly for identifying plant diseases. Worth noting is that the successful application of machine learning in this setting often requires feature engineering. This is a process that involves the choice and modification of data features likely to enhance the performance of the model. In this paper, we would like to propose a different method of plant disease recognition using convolutional neural networks. The modification of the last layer of the conventional Softmax CNN model opens up an opportunity for enhancing the precision of the approach, done by substituting the usually used Softmax classifier with one based on the k-nearest neighbors algorithm. This will lead us toward better results. The modification uses the ability of this K-NN classifier to work along the labels of the neighboring data points, thus giving better accuracy in decision-making concerning disease detection. Moreover, we have developed an evolutionary algorithm to adjust the parameters of the network for the improvement of accuracy in CNN's performance. This systematic searching technique is one kind of evolutionary technique that seeks to find the appropriate configuration of CNN parameters, which maximizes the model efficiency on plant disease identification tasks.
Air-Writing Recognition System S.Thanga Ramya, R Sakthi, B Rohitha, D. Praveena International Interdisciplinary Humanitarian Conference for Sustainability Iihc 2022 Proceedings, 2022 Air-Writing is the use of an object or finger movements to create linguistic characters or words in free space. Writing in the air with fingers/using an object is practically a metaphor of pen-based writing. Detecting intended writing among extraneous finger/object movements entirely irrelevant to letters or words poses a challenge which should be addressed in the common pattern recognition methods. We propose a system that writes the exact mean of the motion that is drawn in front of the sensor using Hidden Markov Algorithm and OpenCV. This system draws the exact motion and is also used for virtual key generation. The output is shown like 2D trajectory and we will recognize the word error of the exact drawing. We will also analyze the 6-DOF (Degree Of Freedom) motion of the recognition. The findings of the experiments indicate that the average rate of recognition of digits and numbers is 98.3% accurate.
Roadmap of integrated data analytics - practices, business strategies and approaches Demystifying Graph Data Science Graph Algorithms Analytics Methods Platforms Databases and Use Cases, 2022
Network Analysis of Social Media Networks for Influencer Identification P Kumar, D Praveena, S Karkuzhal 2026 International Conference on Intelligent and Innovative Technologies in … , 2026 2026.0
Improving Security and Communication Protocols in Smart Grid using Deep Learning to Ensure Data Privacy VA Sowbarnika, S Thanga Ramya, D Praveena, LD Issac, M Tiwari Proceedings of the 3rd International Conference on Optimization Techniques … , 2024 2024.0
Evolutionary Approach-Based Hybrid CNN and SVM for Effective Plant Disease Classification D Praveena 2024 IEEE International Conference on Communication, Computing and Signal … , 2024 2024.0 Citations: 3
Decision support system based on industry 5.0 in artificial intelligence S Srinivasan, DD Hema, B Singaram, D Praveena, KBK Mohan, ... International Journal of Intelligent Systems and Applications in Engineering … , 2024 2024.0 Citations: 33
Air-writing recognition system ST Ramya, R Sakthi, B Rohitha, D Praveena 2022 International Interdisciplinary Humanitarian Conference for … , 2022 2022.0 Citations: 3
Roadmap of integrated data analytics-practices business strategies and approaches ST Ramya, VPG Pushparathi, D Praveena, AS Begum, B Kalpana, ... Demystifying Graph Data Science: Graph Algorithms, Analytics Methods … , 2022 2022.0 Citations: 8
ADVANCED CAMPUS JOB RECRUITMENT SYSTEM WITH AUTOMATIC PROFILE FILTERING AND INSTANT PUSH NOTIFICATIONS FEATURES. B Kalpana, D Praveena, YVL Kumar, V NV, P AA International Journal of Early Childhood Special Education 14 (7) , 2022 2022.0 Citations: 1
Hybrid Cloud Data Protection Using Machine Learning Approach D Praveena, S Thanga Ramya, VP Gladis Pushparathi, P Bethi, ... Advanced Soft Computing Techniques in Data Science, IoT and Cloud Computing … , 2021 2021.0 Citations: 4
Roadmap to Biomedical Image Segmentation and Processing–Background and Approaches VPG Pushparathi, ST Ramya, D Praveena, AS Begum, K Illamathi Design Engineering, 8491-8504 , 2021 2021.0 Citations: 1
Enhanced Features based Private Virtual Card ST Ramya, D Praveena, B Kalpana, BN Kumar, P Muralidharan Annals of the Romanian Society for Cell Biology, 17867-17872 , 2021 2021.0
Smart Supermarket Billing Automation System Based On Barcode Recognition Using Canny Edge Detection. D Praveena, ST Ramya, V Shanmathi, S Ramya, TJ Ramyaa, R Shrish Annals of the Romanian Society for Cell Biology 25 (4) , 2021 2021.0 Citations: 1
Deep Learning for Big Data and its Applications including Clinical Image Processing using CNN Approach D Praveena International Journal of Biology, Pharmacy and Allied Sciences(IJBPAS) 10 (54) , 2021 2021.0
A machine learning application for reducing the security risks in hybrid cloud networks D Praveena, P Rangarajan Multimedia Tools and Applications 79 (7), 5161-5173 , 2020 2020.0 Citations: 30
Secured data transmission using modified LEHS algorithm in wireless sensor network CB Thangammal, D Praveena, P Rangarajan Circuits and Systems 7, 1190-1198 , 2016 2016.0 Citations: 2
Analysis of trend, service and deployment models in cloud computing with focus on hybrid cloud and its implementation D Praveena, P Rangarajan Research Journal of Applied Sciences 9 (4), 181-186 , 2014 2014.0 Citations: 8
Roadmap of integrated data analytics-practices, business strategies and approaches S Thanga Ramya, VPG Pushparathi, D Praveena, A Sumaiya Begum, ...
K, & Preetha, M.(2024),“ S Srinivasan, DD Hema, B Singaram, D Praveena, KB Mohan Decision Support System based on Industry 5 , 0 Citations: 7
Memory and Time aware Automated Job Ontology Construction with reduced Ontology Size Based Semantic Similarity N Kumaresh, SO Manoj, ST Ramya, VG Pushparathi, D Praveena
MOST CITED SCHOLAR PUBLICATIONS
Decision support system based on industry 5.0 in artificial intelligence S Srinivasan, DD Hema, B Singaram, D Praveena, KBK Mohan, ... International Journal of Intelligent Systems and Applications in Engineering … , 2024 2024.0 Citations: 33
A machine learning application for reducing the security risks in hybrid cloud networks D Praveena, P Rangarajan Multimedia Tools and Applications 79 (7), 5161-5173 , 2020 2020.0 Citations: 30
Roadmap of integrated data analytics-practices business strategies and approaches ST Ramya, VPG Pushparathi, D Praveena, AS Begum, B Kalpana, ... Demystifying Graph Data Science: Graph Algorithms, Analytics Methods … , 2022 2022.0 Citations: 8
Analysis of trend, service and deployment models in cloud computing with focus on hybrid cloud and its implementation D Praveena, P Rangarajan Research Journal of Applied Sciences 9 (4), 181-186 , 2014 2014.0 Citations: 8
K, & Preetha, M.(2024),“ S Srinivasan, DD Hema, B Singaram, D Praveena, KB Mohan Decision Support System based on Industry 5 , 0 Citations: 7
Hybrid Cloud Data Protection Using Machine Learning Approach D Praveena, S Thanga Ramya, VP Gladis Pushparathi, P Bethi, ... Advanced Soft Computing Techniques in Data Science, IoT and Cloud Computing … , 2021 2021.0 Citations: 4
Evolutionary Approach-Based Hybrid CNN and SVM for Effective Plant Disease Classification D Praveena 2024 IEEE International Conference on Communication, Computing and Signal … , 2024 2024.0 Citations: 3
Air-writing recognition system ST Ramya, R Sakthi, B Rohitha, D Praveena 2022 International Interdisciplinary Humanitarian Conference for … , 2022 2022.0 Citations: 3
Secured data transmission using modified LEHS algorithm in wireless sensor network CB Thangammal, D Praveena, P Rangarajan Circuits and Systems 7, 1190-1198 , 2016 2016.0 Citations: 2
ADVANCED CAMPUS JOB RECRUITMENT SYSTEM WITH AUTOMATIC PROFILE FILTERING AND INSTANT PUSH NOTIFICATIONS FEATURES. B Kalpana, D Praveena, YVL Kumar, V NV, P AA International Journal of Early Childhood Special Education 14 (7) , 2022 2022.0 Citations: 1
Roadmap to Biomedical Image Segmentation and Processing–Background and Approaches VPG Pushparathi, ST Ramya, D Praveena, AS Begum, K Illamathi Design Engineering, 8491-8504 , 2021 2021.0 Citations: 1
Smart Supermarket Billing Automation System Based On Barcode Recognition Using Canny Edge Detection. D Praveena, ST Ramya, V Shanmathi, S Ramya, TJ Ramyaa, R Shrish Annals of the Romanian Society for Cell Biology 25 (4) , 2021 2021.0 Citations: 1
Network Analysis of Social Media Networks for Influencer Identification P Kumar, D Praveena, S Karkuzhal 2026 International Conference on Intelligent and Innovative Technologies in … , 2026 2026.0
Improving Security and Communication Protocols in Smart Grid using Deep Learning to Ensure Data Privacy VA Sowbarnika, S Thanga Ramya, D Praveena, LD Issac, M Tiwari Proceedings of the 3rd International Conference on Optimization Techniques … , 2024 2024.0
Enhanced Features based Private Virtual Card ST Ramya, D Praveena, B Kalpana, BN Kumar, P Muralidharan Annals of the Romanian Society for Cell Biology, 17867-17872 , 2021 2021.0
Deep Learning for Big Data and its Applications including Clinical Image Processing using CNN Approach D Praveena International Journal of Biology, Pharmacy and Allied Sciences(IJBPAS) 10 (54) , 2021 2021.0
Roadmap of integrated data analytics-practices, business strategies and approaches S Thanga Ramya, VPG Pushparathi, D Praveena, A Sumaiya Begum, ...
Memory and Time aware Automated Job Ontology Construction with reduced Ontology Size Based Semantic Similarity N Kumaresh, SO Manoj, ST Ramya, VG Pushparathi, D Praveena
