SSSumathi Sokkalingam

Sumathi Sokkalingam

*This is an algorithmically generated author record based on publicly available information.

Sumathi Sokkalingam has a total of 14 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Data-centric context-aware intrusion detection and mitigation framework for cloud security

    by S. Sumathi

    1. The rising need for cloud computing together with data-intensive applications has created a situation that requires organisations to build Cloud Data Centres (CDC) for their digital infrastructu...

  • Metaheuristic optimization based improved neural network for the timely prediction of paddy leaf diseases

    by G. Ponseka, S. Sumathi

    Rice is a fundamental dietary staple that embodies cultural identity, culinary diversity, food security and economic stability, providing a significant portion of daily caloric intake for considerable portion of world populace. However, vulnerability of rice crops to various leaf diseases poses a considerable concern to its productivity and quality, which in turnemphasizes the need for an effective disease prediction technique. This research focuses on prompt detection of pathogenic threats to paddy leaves through image analysis. The inputs are pre-processed using an Adaptive Gabor Filter (AGF), for improving the quality and reducing the noise from the image. Subsequently, using a Histogram of Oriented Gradient (HOG), the extraction of relevant disease-related information is assured. For the classification stage, an OptimizedCapsule Networks (CapsNet) is employed for identifying diseases affecting paddy foliage with high accuracy. The proposed CapsNet achieves improved generalization and robustness by integrating the Glow Worm Swarm Algorithm (GWSA) for parameter optimization. In addition to disease prediction, the proposed system integrates a Fertilizer-Based Disease Management (FBDM) approach, which suggests precise fertilization strategies based on the identified disease. By analysing disease symptoms, the system recommends optimal nutrient applicationssuited to enhance plant resistance and recovery. This integration of disease prediction with precision agriculture techniques enables site-specific fertilizer application, preventing overuse and reducing environmental impact.


  • Intelligent Intrusion Detection System for IoT Networks: A Feature Enhanced Deep Belief Network Approach

    by S. Sumathi, R. Rajesh, Sangsoon Lim

    This study presents a novel and resilient intrusion detection system (IDS) designed to address the various challenges posed by Internet of Things (IoT) systems. The proposed model utilizes a deep belief network (DBN) for feature selection (FS) in conjunction with mean shift clustering (MSC), enhancing detection accuracy. Additionally, the system utilizes adaptive drift detection to efficiently manage high-dimensional and dynamic IoT networks. Evaluation of the IoT-20 dataset demonstrates that the proposed DBN IDS achieves a root mean square error (RMSE) of 0.025, with a precision of 97.8% and a recall of 98.1%. The model also boasts an $F1$ score of 97.9% and a specificity of 98.7%. Qualitative analysis reveals an area under the curve (AUC) of 0.98 for the receiver operating characteristic (ROC) curves, indicating near-perfect classification performance. Other performance metrics of the IDS are favorable, with reconstruction error limiting factors reported at 0.022, suggesting a reliable model for normal behavior and accurate anomaly detection. The model’s accuracy for inference and evaluation stands at 96% and 97%, respectively, illustrating the consistency of the studied model across different data segregations. These results highlight that the proposed DBN-based IDS is a reliable solution that goes beyond current threats in the IoT landscape, effectively detecting both existing and emerging threats.


  • The Role of Speech Processing in the Metaverse

    by Daniel Raj K., Robinson Joel M., Benitlin Subha K., L. Jenefas, G. Ponseka, A. Ananthakumari, S. Sumathi

    The metaverse, blending AR, VR, and persistent digital spaces, is reshaping how people interact and communicate. Speech processing covering ASR, NLP, and TTS is vital in enabling intuitive, voice-driven experiences like real-time translation, smart agents, and personalized avatars. This chapter explores these technologies' impact on user experience while addressing critical ethical concerns such as voice data privacy, surveillance, bias, and synthetic voice misuse. It highlights challenges in digital identity and accessibility, especially for marginalized users. With real-world case studies, it advocates for transparent, inclusive, and ethical voice tech governance in virtual spaces.


  • Frameworks and Standards for Educational Gamification and Virtual Reality

    by K. DanielRaj, M. Robinson Joel, S. Sumathi, G. Ponseka, A. Ananthakumari, J. Grace Priyanka

    The increasing integration of gamification and virtual reality (VR) into education is transforming the ways students learn, engage, and interact with knowledge. While these innovations promote motivation, creativity, and experiential learning, they also introduce new governance challenges related to privacy, ethics, and access. This chapter explores the policy frameworks and standards essential for ensuring safe, equitable, and responsible use of gamified and VR-based educational technologies. Through a qualitative and comparative policy analysis, it examines global and regional regulatory approaches, identifies existing gaps, and highlights the need for adaptive governance mechanisms that align with rapid technological advancements. Key focus areas include data protection, ethical design, digital equity, and institutional accountability. The chapter concludes by proposing a multi-stakeholder policy model that promotes innovation while safeguarding learner rights, fostering inclusive participation, and supporting sustainable digital transformation in education.


  • HybGBS: A hybrid neural network and grey wolf optimizer for intrusion detection in a cloud computing environment

    by S Sumathi, R Rajesh

    Summary: The cloud computing environment is subject to unprecedented cyber‐attacks as its infrastructure and protocols may contain vulnerabilities and bugs. Among these, Distributed Denial of Service (DDoS) is chosen by most cyber extortionists, creating unusual traffic that drains cloud resources, making them inaccessible to customers and end users. Hence, security solutions to combat this attack are in high demand. The existing DDoS detection techniques in literature have many drawbacks, such as overfitting, delay in detection, low detection accuracy for attacks that target multiple victims, and high False Positive Rate (FPR). In this proposed study, an Artificial Neural Network (ANN) based hybrid GBS (Grey Wolf Optimizer (GWO) + Back Propagation Network (BPN) + Self Organizing Map (SOM)) Intrusion Detection System (IDS) is proposed for intrusion detection in the cloud computing environment. The base classifier, BPN, was chosen for our research after evaluating the performance of a comprehensive set of neural network algorithms on the standard benchmark UNSW‐NS 15 dataset. BPN intrusion detection performance is further enhanced by combining it with SOM and GWO. Hybrid Feature Selection (FS) is made using a correlation‐based approach and Stratified 10‐fold cross‐validation (STCV) ranking based on Weight matrix value (W). These selected features are further fine‐tuned using metaheuristic GWO hyperparameter tuning based on a fitness function. The proposed IDS technique is validated using the standard benchmark UNSW‐NS 15 dataset, which consists of 1,75,341 and 82,332 attack cases in the training and testing datasets. This study's findings demonstrate that the proposed ANN‐based hybrid GBS IDS model outperforms other existing IDS models with a higher intrusion detection accuracy of 99.40%, fewer false alarms (0.00389), less error rate (0.001), and faster prediction time (0.29 ns).


  • Top Cited Papers

    An intelligent intrusion detection system for distributed denial of service attacks: A support vector machine with hybrid optimization algorithm based approach

    by Sumathi Sokkalingam, Rajesh Ramakrishnan

    Summary: Cloud computing offers comfortable service to business sectors as they can concentrate on their products. Over the internet, cloud computing is liable to various security threats and attacks which is a primary obstacle to the growth of cloud computing services. Distributed denial of service (DDoS) is one such attack that exploits cloud computing services using compromised machines; hence, its detection is a significant field of research. Several DDoS detection schemes have been proposed in the past, but they fail to detect real‐time active DDoS attacks because of their growth in severity and volume. Machine learning (ML) techniques are efficient in making predictions; hence, in this study, a hybrid ML intrusion detection system (IDS) model is proposed. The performance of the proposed IDS model is improved by employing a 10‐fold cross‐validation technique to perform feature selection, reducing data dimensions on the publicly available benchmark NSL‐KDD dataset. Performance validation of the proposed hybrid IDS model is done using the confusion matrix. Support vector machine (SVM) parameters are fine‐tuned using hybrid Harris Hawks optimization (HHO) and particle swarm optimization (PSO) algorithms. The performance of these hybrid algorithms is compared with other classical algorithms such as C4.5, K‐nearest neighbor, and SVM using performance metrics such as precision, sensitivity, specificity, F1 score, and accuracy. From these comparisons, it can be inferred that the proposed SVM with hybrid optimization HHO‐PSO machine learning IDS model performs better DDoS detection with good performance metric values.


  • Open Access

    Recurrent and Deep Learning Neural Network Models for DDoS Attack Detection

    by S. Sumathi, R. Rajesh, Sangsoon Lim

    Distributed denial of service (DDoS) attack is a subclass of denial of service attack that performs severe attack in a cloud computing environment. It makes a malicious attempt to disturb the usual services of any network or server by using botnets. Hence, an efficient intrusion detection system (IDS) is essential to detect this attack. Some limitations in the existing IDS models for DDoS attack detection are delayed convergence, local stagnation issues, and local and global optimal trapping issues. These limitations are met by the recurrent neural network (RNN) and deep learning- (DL-) based proposed models that can utilize the previous states of the hidden neuron. The proposed research has used a long short-term memory (LSTM) recurrent neural network and autoencoder- and decoder-based deep learning strategy with gradient descent learning rule. The network parameters like weight vectors and bias coefficient are tuned optimally by employing the proposed a hybrid Harris Hawks optimization (HHO) and particle swarm optimization (PSO) algorithm. The proposed hybrid optimization algorithm selects the essential attributes, and the results obtained confirmed that the proposed LSTM and deep learning model outperformed all other models developed in the literature.