Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Sannasi Chakravarthy Surulimani Ramaraj has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Impact analysis of SMS-triggered elephant activity alert lights

    by Sanjoy Deb, Sannasi Chakravarthy Surulimani Ramaraj, Sharmila Arumugam, Saravana Kumar Radhakrishnan

    Human-elephant negative interactions typically arise when elephants enter human settlements in search of food, water, migratory routes, or other resources. Each year, accidental encounters with elephants in areas near reserve forests result in the deaths of hundreds of people. To address this challenge, the Bannerghatta National Park Forest Department has implemented a solution based on a straightforward conflict management approach, utilizing an SMS-based light and sound alert system to notify locals of elephant activity. To help reduce the risk of such encounters, 40 SMS-triggered elephant activity alert lights have been strategically placed across four ranges. We have partnered as the technology provider for this initiative. This paper presents an overview of the system’s hardware architecture, the site selection process, the implementation strategy, and an evaluation of its technical performance and effectiveness over an eight-month period. This large-scale implementation of an elephant alert system offers valuable insights into potential usage in other conflict-prone areas.

  • Open Access

    Deep-learning based adaptive fusion of CC and MLO views for improved mammographic cancer diagnosis

    by Sannasi Chakravarthy Surulimani Ramaraj, Harikumar Rajaguru, Rajesh Kumar Dhanaraj, Anto Lourdu Xavier Raj Arockia Selvarathinam, Dragan Pamucar


  • Multi-scale temporal electroencephalography signal classification using a dynamic graph attention network framework

    by Sannasi Chakravarthy S R, Harikumar Rajaguru

    Electroencephalography (EEG)-based decoding is critical for brain–computer interface (BCI) applications, especially in motor imagery (MI) tasks. However, traditional convolutional neural networks often struggle in capturing long-range temporal dependencies due to limited receptive fields. To overcome this, a hybrid framework that combines temporal convolutional networks (TCNs) with graph attention networks (GATs) is proposed. This framework effectively models multi-scale temporal dynamics and inter-temporal dependencies in EEG signals. Herein, the TCN module is used for the extraction of rich short- and long-term temporal features. This is followed by dynamic graph construction, where each node represents a time step, and edge weights are adaptively learned. Then, the GAT module propagates temporal information by emphasizing the most relevant connections. In addition, the temporal slicing and shuffling data augmentation strategy is introduced to improve generalization. Evaluations on three benchmark motor imagery electroencephalography datasets, namely, BCIC-IV-2a, BCIC-IV-2b, and High Gamma Dataset (HGD), are carried out. The evaluations are performed using standard evaluation metrics, namely, classification accuracy and Cohen’s kappa coefficient across subjects. Accordingly, the experimental outcomes reveal that the proposed framework consistently outperforms state-of-the-art baselines across the three employed datasets. The findings highlight the importance of multi-scale temporal feature fusion using graph attention mechanisms for effective motor imagery EEG signal decoding.

  • Open Access

    Spectral-aware CNN with learnable biorthogonal units and depthwise convolutions for multi-class blood cell classification

    by Sannasi Chakravarthy Sr, Harikumar Rajaguru, Rajesh Kumar Dhanaraj, Feslin Anish Mon, Dragan Pamucar


  • Open Access

    MobileDANet integrating transfer learning and dynamic attention for classifying multi target histopathology images with explainable AI

    by Sannasi Chakravarthy S R, Harikumar Rajaguru

    Cancer is a life-threatening disease that affects several human lives all over the world. The classification of cancer severities utilizing histopathological images is vital for effective and timely diagnosis. This always creates a demandable requirement for promising and automated computer-aided diagnosis (CAD) frameworks in clinical analysis. In this direction, the study introduces a deep learning (DL) framework aimed at classifying renal cell carcinoma (RCC) into five distinct grades, and the work is also extended to include histopathology images of breast and colon cancer. The proposed architecture, MobileDANet, integrates a MobileNetV2 backbone with a dynamic attention (DA) block (multi-head attention + MLP) to capture both long and long-range dependencies efficiently and employs Grad-CAM for interpretability. On RCC (KMC dataset) data, MobileDANet attains 90.71% accuracy (F1 score as 90.94%); on BreakHis, it achieves a recognition rate of 88.16%; and on CRCH, it reaches a weighted F1-score of 99.08%, outperforming recent baselines. In future work, the framework will be extended to larger multi-institutional datasets, pursue model compression with automated hyperparameter optimization, and explore integration with clinical-decision support systems.


  • Open Access

    Optimized Extreme Learning Machine for Breast Tumor Classification Using Mammograms

    by Bharanidharan N, Sannasi Chakravarthy S R, Vinoth Kumar V

    Breast cancer is the most invasive cancer type for women, being the second leading cause of cancer-related deaths after lung cancer. Recently, many intelligent approaches have emerged for the effective classification of such deadly diseases; however, optimistic light of research is needed for improved diagnosis. Thus, the work proposed a novel methodology of combining the effective classification ability of extreme learning machine (ELM) with the efficient searching behavior of crowsearch optimization algorithm (CSOA). In this way, an improved crow-search optimization algorithm-based extreme learning machine (ImCSOA-ELM) is proposed for addressing the severity classification of breast tumors. Here, the novelty of the work lies in enhancing the generalization ability of the ELM by using the CSOA with chaotic-based controlled randomness for improved convergence. For the evaluation of the proposed algorithm, two different benchmark datasets namely MIAS and DDSM are used. Further, the proposed framework is validated using a larger FFDM dataset, VinDr-Mammo. The performance comparison of the proposed algorithm with existing classification models (SVM-RBF, ELM, particle swarm optimization-based ELM, and CSOA-based ELM) is done, in which the highest classification accuracy is obtained for the proposed algorithm is 90% (MIAS), 95.4% (DDSM), and 86.04% (VinDr-Mammo) respectively.


  • Investigation of Various Dimensionality Reduction and Feature Selection Techniques in Microarray Gene Data for Renal Cancer Diagnosis

    by Bharanidharan N., Sannasi Chakravarthy S. R., Vinoth Kumar V., Pratham Aggarwal, Harikumar Rajaguru

    Renal cancer is among the top 10 cancers in both genders. Microarray gene expression data is one of the effective modalities to diagnose renal cancer. The main objective of this work is to label the gene expression sample as either normal or clear cell renal cell carcinoma. To improve the classification performance and reduce the training time of the above-mentioned supervised classifiers, various feature selection and dimensionality reduction techniques are investigated. Feature selection techniques, namely variance filter, chi-square test, ANOVA test, and mutual information filter, are tested. In addition, principal component analysis, independent component analysis, and linear discriminant analysis are evaluated as dimensionality reduction techniques. Highest balanced accuracy score of 91.6% is attained for support vector machine classifier while it was increased to 94.4% through the usage appropriate dimensionality reduction or feature selection technique.

  • Open Access

    Multi-class Breast Cancer Classification Using CNN Features Hybridization

    by Sannasi Chakravarthy, N. Bharanidharan, Surbhi Bhatia Khan, V. Vinoth Kumar, T. R. Mahesh, Ahlam Almusharraf, Eid Albalawi

    Breast cancer has become the leading cause of cancer mortality among women worldwide. The timely diagnosis of such cancer is always in demand among researchers. This research pours light on improving the design of computer-aided detection (CAD) for earlier breast cancer classification. Meanwhile, the design of CAD tools using deep learning is becoming popular and robust in biomedical classification systems. However, deep learning gives inadequate performance when used for multilabel classification problems, especially if the dataset has an uneven distribution of output targets. And this problem is prevalent in publicly available breast cancer datasets. To overcome this, the paper integrates the learning and discrimination ability of multiple convolution neural networks such as VGG16, VGG19, ResNet50, and DenseNet121 architectures for breast cancer classification. Accordingly, the approach of fusion of hybrid deep features (FHDF) is proposed to capture more potential information and attain improved classification performance. This way, the research utilizes digital mammogram images for earlier breast tumor detection. The proposed approach is evaluated on three public breast cancer datasets: mammographic image analysis society (MIAS), curated breast imaging subset of digital database for screening mammography (CBIS-DDSM), and INbreast databases. The attained results are then compared with base convolutional neural networks (CNN) architectures and the late fusion approach. For MIAS, CBIS-DDSM, and INbreast datasets, the proposed FHDF approach provides maximum performance of 98.706%, 97.734%, and 98.834% of accuracy in classifying three classes of breast cancer severities.


  • Open Access

    Intelligent Recognition of Multimodal Human Activities for Personal Healthcare

    by S. R. Sannasi Chakravarthy, N. Bharanidharan, V. Vinoth Kumar, T. R. Mahesh, Surbhi Bhatia Khan, Ahlam Almusharraf, Eid Albalawi

    Nowadays, the advancements of wearable consumer devices have become a predominant role in healthcare gadgets. There is always a demand to obtain robust recognition of heterogeneous human activities in complicated IoT environments. The knowledge attained using these recognition models will be then combined with healthcare applications. In this way, the paper proposed a novel deep learning framework to recognize heterogeneous human activities using multimodal sensor data. The proposed framework is composed of four phases: employing dataset and processing, implementation of deep learning model, performance analysis, and application development. The paper utilized the recent KU-HAR database with eighteen different activities of 90 individuals. After preprocessing, the hybrid model integrating Extreme Learning Machine (ELM) and Gated Recurrent Unit (GRU) architecture is used. An attention mechanism is then included for further enhancing the robustness of human activity recognition in the IoT environment. Finally, the performance of the proposed model is evaluated and comparatively analyzed with conventional CNN, LSTM, GRU, ELM, Transformer and Ensemble algorithms. To the end, an application is developed using the Qt framework which can be deployed on any consumer device. In this way, the research sheds light on monitoring the activities of critical patients by healthcare professionals remotely. The proposed ELM-GRUaM model achieved supreme performance in recognizing multimodal human activities with an overall accuracy of 96.71% as compared with existing models.