IoT cloud integration with EfficientNet-B7 for real-time pest monitoring and leaf-based classification Sabapathi Shanmugam, Vijayalakshmi Natarajan International Journal of Reconfigurable and Embedded Systems, 2026 The increasing prevalence of pest infestations poses a significant threat to global agricultural productivity, often resulting in substantial yield losses and economic damage. To address this challenge, this paper proposes an intelligent, cloud-enabled pest detection and classification framework leveraging state-of-the-art deep learning techniques. The proposed system integrates YOLOv8 for rapid and accurate pest detection with EfficientNet-B7 for fine-grained species-level classification. The framework is trained and evaluated using the Pestopia dataset, which contains annotated images representing diverse pest species. To enhance data diversity, robustness, and model generalization, data augmentation techniques such as center cropping and horizontal flipping are applied during preprocessing. YOLOv8 is employed to detect and localize pest instances within images, while EfficientNet-B7 extracts high-level discriminative features from detected regions to enable precise species identification. Furthermore, the system incorporates cloud-based real-time monitoring through Adafruit IO, enabling scalable, remote access to pest information for timely decision-making. The performance of the proposed framework is evaluated using standard metrics, including accuracy, precision, recall, and F1-score, achieving values of 97.8%, 98.9%, 98.4%, and 98.9%, respectively. The experimental results demonstrate the effectiveness and reliability of the proposed approach for real-time pest management. The cloud-integrated architecture facilitates proactive pest control strategies, supporting smarter, data-driven agricultural practices, and improved crop protection.
A weighted ensemble model combining ARIMA, LSTM, and GBM for robust time series prediction A. Vignesh, N. Vijayalakshmi Scientific and Technical Journal of Information Technologies Mechanics and Optics, 2025 Time series forecasting has been used in research and applications in a number of domains such as environmental forecasting, healthcare, finance, supply chain management, and energy consumption. Accurate prediction of future values is necessary for strategic planning operational efficiency and well-informed decision-making regarding time-dependent variables. A hybrid time series forecasting architecture is proposed that combines the strengths of machine learning and statistical models, in particular Gradient Boosting Machines (GBM), Auto-Regressive Integrated Moving Average (ARIMA), and Long Short-Term Memory (LSTM) networks. While LSTM networks and GBM are able to capture complex dependencies and nonlinear patterns, the ARIMA model captures the linear components within the time series. The hybrid model exploits ARIMA interpretability, LSTM temporal memory ability, and GBM ensemble learning efficiency by integrating these three models. Comprehensive experiments conducted on benchmark data sets have shown that the accuracy and reliability of predictions of the proposed hybridization significantly exceeds both individual models and traditional baseline models. The results show that for a variety of real-world applications, hybrid architectures can deliver reliable and accurate time series predictions.
Early Detection of Brain Tumors Using SOLOv3 Algorithm for Enhanced Diagnostic Accuracy Sindhu S, Vijayalakshmi N Informatica Slovenia, 2025 The brain tumor is various types occur in the human brain sometime it affects the human quality of life. The deep learning algorithms gives the better detection of the tumor cell with highly positive result in the earlier stage. In the previous work, the customized Segmenting Objects by Locations Vector 3(SOLOv3) algorithm has been approached, this approach gives the better result compared with the previous algorithms. In the medical field the radiographic images are plays the vital role for identifying the disease from the human body at the same time helps to give the proper treatment on time for avoiding the death ratio. There are many automatic image reorganization techniques were developed in deep learning algorithms. Since the proposed idea is to classify the images based on the plasma level and also detect the levels of infection specified as stage1 to stage 5. To use the Magnetic Resonance Images (MRI) for identifying the tissues which present the human organ with the neoplasm type and size. This kind of information’s are helpful to treat the patient on time and also reduce the death rate due this late treatment or detection of the which level the person may affected. The aim of the proposed article is to develop the customized SOLOv3 algorithm with DESNET201 for improved image segmentation and classification. The real time images were taken from the prescribed reputed Neurological diagnosis center in Chennai. Totally 18759 images were collected under all four categories of tumor and non tumor. Which included 13257 images are tumor images under the category of glioma, meningioma and pituitary and remains comes under non tumor category. The implemented model is to customize the final layer of the neural network form with four different classes will give the better result as 91% in the training set and scored 89% as in the phase of test. This improved model that could combine the SOLOv3 and Desnet201 with customized layer classes for extracting the features used to classify the tumor cells with their different types. The tumor may have more than 150 types of tissues, but gradually these four kinds of classes are very dangerous about to increase the death and spreadable to other body organ. These techniques also able to detect the improved automation for the tumor in Indian children and adults.
AI-Powered Enhanced Student Performance Detection Using Deep Optimal Feature Engineering with LSTM Gated Hyper Capsuled Generative Adversarial Neural Network Nisha Raveendran, N Vijayalakshmi 2025 International Conference on Information Implementation and Innovation in Technology I2itcon 2025, 2025 This paper introduces an AI method to detect student performance enhancements by implementing Deep Optimal Feature Engineering through LSTM Gated Hyper Capsuled Generative Adversarial Neural Network (LSTM-HCGAN). A research dataset about 2392 high school students incorporates demographic, academic, and behavioural measurement variables. Z-score Min-Max normalization acts as a preprocessing technique to normalize features while standardizing important metrics to achieve better model performance. Two methods support the feature engineering procedure: Student Concert Behavior Impact Margin Rate (SCBIR) and Spider Swarm Optimization Feature Selection (SSOFS) which help find the most important features to predict academic results. Predictive modeling occurs through LSTM-HCGAN which allocates Long Short-Term Memory (LSTM) networks to handle sequence modeling alongside Generative Adversarial Networks (GAN) to generate hyperfeatures. The proposed model outperforms other models by delivering an accuracy rate of 92% with a precision of 0.90 and recall of 0.88 and F1-score measurement of 0.91. These performance metrics surpass those of SVM (accuracy: 85%), Random Forest (accuracy: 87%) and Linear Regression (accuracy: 80%). Research data confirm that LSTM-HCGAN demonstrates excellent ability to forecast student academic outcomes which makes it valuable for educational predictive tasks.
Advancing Health Diagnostics: AI-Powered CVD-REF Framework for Precise and Early Risk Assessment Vishnu Priyan S, Vijayalakshmi N, Suresh G, Rajesh K Journal of Machine and Computing, 2025 Deprivation of Critical Care systems are a major cause of fatality worldwide, highlighting it’s need for saving human lives. This study proposes a novel hybrid ensemble model, which integrates Random Forests, Gradient Boosting Machines (GBM), and Neural Networks to enhance the predictive accuracy diagnostics. The methodology combines data pre-processing, feature selection, and ensemble learning, ensuring robust and reliable predictions. Comprehensive data pre-processing includes K-Nearest Neighbours (KNN) imputation for missing values, Z-Score normalization for scaling, and Polynomial Feature Generation for non-linear feature interactions. Feature selection performed using Recursive Feature Elimination (RFE) and Mutual Information relevant variable retention. The proposed model produces 98.55% accuracy, very surpassing nine baseline models, that includes XGBoost, Random Forests, and Neural Networks. Additional metrics such as precision (97.80%), recall (98.12%), F1-Score (98.00%), and ROC-AUC (99.12%) further validate the model's robustness. This framework not only demonstrates superior accuracy but also ensures computational efficiency, making it viable for deployment in real-world healthcare settings.
Deep Reinforcement Learning Based Secure Transmission for UAV-Assisted Mobile Edge Computing N. Vijayalakshmi, Sagar Gulati, B. Ben Sujin, B. Madhav Rao, K. Kiran Kumar International Journal of Interactive Mobile Technologies, 2024 The increasing computational demand for real-time mobile applications has led to the development of mobile edge computing (MEC), with support from unmanned aerial vehicles (UAVs), as a promising paradigm for constructing high-throughput line-of-sight links for ground users and pushing computational resources to network edges. Users can reduce processing latency and the load on their local computers by delegating tasks to the UAV in its role as an edge server. The coverage capacity of a single UAV is, however, very limited. Moreover, it will be easy to intercept the data that is transferred to the unmanned aerial vehicle. Thus, for UAV-assisted mobile edge computing, we proposed a transmission technique based on multi-agent deep reinforcement learning in this study. The recommended approach to maximize UAV deployment first applies the particle swarm optimization algorithm. Then, deep reinforcement learning is utilized to optimize the secure offloading to maximize the system utility and minimize the quantity of information eavesdropping, taking into consideration different user task types with diverse preferences for processing time and residual energy of computing equipment. The results of the simulation demonstrate that, in comparison to the single-agent strategy and the benchmark, the multi-agent approach can optimize offloading more successfully and produce higher system utility.
Tools to create synthetic data for brain images S. Sindhu, N. Vijayalakshmi Applications of Synthetic High Dimensional Data, 2024 In the areas of neuroscience, medical imaging, and machine learning, the creation of synthetic data for brain scans has become a key approach. This chapter explores the concept and significance of synthetic data generation for brain images. In tasks like brain picture segmentation, disease detection, and image analysis, machine learning models perform better when using synthetic data as a catalyst for data augmentation. A wide range of methods and resources including MRI simulators, 3D modeling software, deep learning frameworks, and medical imaging software are used to create synthetic brain images. To guarantee the validity and applicability of synthetic data, however, ethical issues, data representativeness, and transparency in the generation process continue to be essential factors. Synthetic brain data are becoming more useful and realistic as technology develops, and this has the potential to completely change the fields of neuroscience and medical imaging.
Time Series Modeling and Forecasting Using Autoregressive Integrated Moving Average and Seasonal Autoregressive Integrated Moving Average Models Vignesh Arumugam, Vijayalakshmi Natarajan Instrumentation Mesure Metrologie, 2023 Time series analysis is pivotal in discerning temporospatial data patterns and facilitating precise forecasts. This study scrutinizes the cardinal challenges associated with time series modeling, namely stationarity, parsimony, and overfitting, focusing on the application of Autoregressive Integrated Moving Average (ARIMA) and Seasonal Autoregressive Integrated Moving Average (SARIMA) models. An examination of six datasets reveals that these models adeptly encapsulate underlying data trends, enabling reliable predictions and yielding insightful conclusions. Relative to baseline methods, the proposed models demonstrate superior performance, as indicated by five evaluation metrics: Mean Squared Error (MSE), Frantic, Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and Theil's U-statistics. The most parsimonious ARIMA or SARIMA model was selected for each dataset, with the resultant forecast summary graphically demonstrating the proximity between original and predicted observations. This study aims to contribute to the discourse on the validity and applicability of ARIMA and SARIMA models in time series analysis and forecasting.
Extended internet security with restricted client side scripts(rcss) from phishing attacks for qos improvement International Journal of Applied Engineering Research, 2014
An overview of route discovery mechanisms of multicast routing protocols for MANETs International Journal of Engineering and Technology, 2013
RECENT SCHOLAR PUBLICATIONS
A Multi-Layered Framework for Adaptive and Optimized Real-Time Data Processing in Edge-Fog IoT Environments GSP Ghantasala, I Ioannou, T Kolla, P Vidyullatha, N Vijayalakshmi, ... IEEE Internet of Things Journal , 2026 2026
Early Diagnosis of Skin Cancer Through IoT Devices and Deep Convolutional Neural Networks T Kolla, GSP Ghantasala, N Vijayalakshmi 2025 1st International Conference on Advancement in Futuristic Technologies … , 2025 2025
Early Detection of Brain Tumors Using SOLOv3 Algorithm for Enhanced Diagnostic Accuracy S Sindhu, N Vijayalakshmi Informatica 49 (27) , 2025 2025
Pattern Discovery in Genomic Sequences Using Advanced Data Mining Algorithms GGS Pradeep, T Kolla, N Vijayalakshmi, U Ananthanagu, ... World Conference on Information Systems for Business Management, 440-449 , 2025 2025
Fuzzy-Neural Hybrid Models for Early Detection of Neurodegenerative Disorders Using Multimodal Medical Data and Temporal Pattern Analysis GGS Pradeep, T Kolla, R Rajesh Sharma, A Sungheetha, ... World Conference on Information Systems for Business Management, 174-183 , 2025 2025
Optimizing Feature Selection for Medical Diagnosis Systems Using Differential Evolution GGS Pradeep, T Kolla, N Vijayalakshmi, R Sharma R World Conference on Information Systems for Business Management, 213-222 , 2025 2025
Temporal Pattern Recognition in IoT Sensor Streams Using Spatio-Temporal Reasoning GGS Pradeep, T Kolla, RR Sharma, A Sungheetha, N Vijayalakshmi, ... World Conference on Information Systems for Business Management, 390-399 , 2025 2025
Adaptive Ambient Intelligence: Machine Learning Models for Context Prediction in Ubiquitous Systems GGS Pradeep, T Kolla, RS R, A Sungheetha, N Vijayalakshmi, ... World Conference on Information Systems for Business Management, 256-265 , 2025 2025
RNN-based Prediction and Risk Classifcation for Improving Endometrial Cancer Diagnosis using Clinical and Imaging Data GSP Ghantasala, K Thrilok, P Vidyullatha, N Vijayalakshmi, R Sharma, ... 2025 5th International Conference on Soft Computing for Security … , 2025 2025
Surgical Strategies in Primary Fallopian Tube Cancer: A Gynecologic Oncology Perspective T Kolla, GSP Ghantasala, P Vidyullatha, R Sharma, N Vijayalakshmi, ... 2025 5th International Conference on Soft Computing for Security … , 2025 2025
AI-Powered Enhanced Student Performance Detection Using Deep Optimal Feature Engineering with LSTM Gated Hyper Capsuled Generative Adversarial Neural Network N Raveendran, N Vijayalakshmi 2025 International Conference on Information, Implementation, and Innovation … , 2025 2025
Intelligent Solar Panel Monitoring Using Machine Learning and Cloud-Based Predictive Analytics J Dhilipan, N Vijayalakshmi, DB Shanmugam, SS Maidin, WL Shing Journal of Applied Data Sciences 6 (3), 1599-1610 , 2025 2025 Citations: 3
Artificial Intelligence and Human-Centered in Linguistic Analysis: Self-Regulated Learning and Development R N., Vijayalakshmi, N. , R., Saravanan, R. , R., Jayalakshmi, R. , R., Rekha Journal of Information Systems Engineering and Management, 10 (11), 361-370 , 2025 2025
A weighted ensemble model combining ARIMA, LSTM, and GBM for robust time series prediction A Vignesh, N Vijayalakshmi Научно-технический вестник информационных технологий, механики и оптики 25 … , 2025 2025 Citations: 1
Prediction of electricity consumption using an innovative deep energy predictor model for enhanced accuracy and efficiency C Ragupathi, S Dhanasekaran, N Vijayalakshmi, AO Salau Energy Reports 12, 5320-5337 , 2024 2024 Citations: 31
Adaptive Vehicle Control System for Improved Safety With Image Processing N Vijayalakshmi, L Priya, S Ramaraj, M Nanjundan, SK Palanisamy, ... 2024 IEEE 5th International Conference on Electro-Computing Technologies for … , 2024 2024
Review on Student Performance Evaluation System for E-Learning N Raveendran, N Vijayalakshmi Human Machine Interaction in the Digital Era, 161-170 , 2024 2024
Design and Development of a Shamrock Leaf-Shaped Fractal Antenna with Integrated Filtering for WLAN/WiMAX Applications SK Palanisamy, N Sathishkumar, T Nivethitha, N Vijayalakshmi, ... University of Bahrain , 2024 2024
Deep Reinforcement Learning Based Secure Transmission for UAV-Assisted Mobile Edge Computing KKK N. Vijayalakshmi1, Sagar Gulati, B. Ben Sujin, B. Madhav Rao International journal of Interactive Mobile Technologies 18 (17), 154-169 , 2024 2024 Citations: 3
The elevation of efficacy identifying pituitary tissue abnormalities within brain images by employing memory contrast learning techniques S Sindhu, N Vijayalakshmi Journal of applied mathematics & informatics, 931-943 , 2024 2024 Citations: 1
MOST CITED SCHOLAR PUBLICATIONS
Prediction of Students Performance using Machine learning SS N.Vijayalakshmi,J.Dhilipan IOP Conf. Series: Materials Science and Engineering, 1-8 , 2021 2021 Citations: 72
Performance and efficiency of different types of solar cell material–A review J Dhilipan, N Vijayalakshmi, DB Shanmugam, RJ Ganesh, ... Materials Today: Proceedings 66, 1295-1302 , 2022 2022 Citations: 64
Time Series Modeling and Forecasting Using Autoregressive Integrated Moving Average and Seasonal Autoregressive Integrated Moving Average Models. VN Vignesh A Instrumentation Mesure Metrologie 22 (4), 161-168 , 2023 2023 Citations: 46
Prediction of electricity consumption using an innovative deep energy predictor model for enhanced accuracy and efficiency C Ragupathi, S Dhanasekaran, N Vijayalakshmi, AO Salau Energy Reports 12, 5320-5337 , 2024 2024 Citations: 31
Vehicle tracking and locking system based on gsm and gps N Vijayalakshmi, R Shrinithi, V Sanjana, T Sowmiya 2021 7th International Conference on Advanced Computing and Communication … , 2021 2021 Citations: 9
Network monitoring system using ping methodology and GUI J Dhillipan, N Vijayalakshmi, S Suriya Recent Trends and Advances in Artificial Intelligence and Internet of Things … , 2019 2019 Citations: 7
A Novel IoT Based Power Monitoring System JSD S.Suriya, Agusthiyar R ,N.Vijayalakshmi IOP Conf. Series: Materials Science and Engineering, 1-7 , 2021 2021 Citations: 6
Automatic vehicle number recognition system using character segmentation and morphological algorithm N Vijayalakshmi, S Sindhu, S Suriya 2020 IEEE International Conference on Advances and Developments in … , 2020 2020 Citations: 5
Automotive authentication using IoT N Vijayalakshmi, S Kiruthiga, AP Hariprasath, K Arunachalam, DR KK 2020 6th International Conference on Advanced Computing and Communication … , 2020 2020 Citations: 5
A Secure Wild Animals Alert System for Preventing the Farming Land using IoT DBS Dr.J.Dhillipan,Dr.N.Vijayalakshmi,S.Suriya International Journal of Recent Technology and Engineering 8 (5), 5585-5587 , 2020 2020 Citations: 5
Intelligent Solar Panel Monitoring Using Machine Learning and Cloud-Based Predictive Analytics J Dhilipan, N Vijayalakshmi, DB Shanmugam, SS Maidin, WL Shing Journal of Applied Data Sciences 6 (3), 1599-1610 , 2025 2025 Citations: 3
Deep Reinforcement Learning Based Secure Transmission for UAV-Assisted Mobile Edge Computing KKK N. Vijayalakshmi1, Sagar Gulati, B. Ben Sujin, B. Madhav Rao International journal of Interactive Mobile Technologies 18 (17), 154-169 , 2024 2024 Citations: 3
Approaches to Teaching Programming: a comprehensive review and analysis DB Shanmugam, N Vijayalakshmi, N Revathi Research in Multidisciplinary Subjects (Volume-2), 53 , 2023 2023 Citations: 3
An optimal low power digital controller for portable solar applications N Vijayalakshmi, P Maruthupandi Journal of Renewable and Sustainable Energy 10 (5) , 2018 2018 Citations: 3
Low energy adaptive clustering hierarchy--redundancy aware protocol (LEACH-RA) E Sivajothi, N Vijayalakshmi, A Swaminathan, P Vivekanandan Advances in Natural and Applied Sciences 9 (13), 1-7 , 2015 2015 Citations: 3
An Overview of Route Discovery Mechanisum of Multicast Routing Protocols for MANETs N Sivajothi, E, Vivekanandan, P & Vijayalakshmi International Journal of Engineering and Technology , 2013 2013 Citations: 3
Efficiency and Limitations of Secure Protocol in E-mail Services ES N.Vijayalakshmi, P.Vivekanandan International Journal of Engineering Sciences & Research Technology, 539-544 , 2012 2012 Citations: 3
Tools to Create Synthetic Data for Brain Images S Sindhu, N Vijayalakshmi Applications of Synthetic High Dimensional Data, 179-208 , 2024 2024 Citations: 2
Internet of Thing-Based Monitoring Systems and Their Applications N Vijayalakshmi, S Sindhu, J Dhilipan Smart Computing and Self-Adaptive Systems, 133-152 , 2021 2021 Citations: 2
A weighted ensemble model combining ARIMA, LSTM, and GBM for robust time series prediction A Vignesh, N Vijayalakshmi Научно-технический вестник информационных технологий, механики и оптики 25 … , 2025 2025 Citations: 1
