Malliga Subramanian

Dr. Malliga Subramanian

Department of Computer Science and Engineering, Kongu Engineering College, Perundurai, Tamilnadu, India

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 December 2022 in Electronics
Verified
Journal Article
Open access
PDF file
PMPrakash Mohan
Prakash Mohan
Sathishkumar Veerappampalayam EaswaramoorthySathishkumar Veerappampalayam Easwaramoorthy
Sathishkumar Veerappampalayam Easwaramoorthy
Neelakandan SubramaniNeelakandan Subramani
Neelakandan Subramani
Malliga SubramanianMalliga Subramanian
Malliga Subramanian
SMSangeetha Meckanzi
Sangeetha Meckanzi
An abnormal growth of cells in the brain, often known as a brain tumor, has the potential to develop into cancer. Carcinogenesis of glial cells in the brain and spinal cord is the root cause of gliomas, which are the most prevalent type of primary brain tumor. After receiving a diagnosis of glioblastoma, it is anticipated that the average patient will have a survival time of less than 14 months. Magnetic resonance imaging (MRI) is a well-known non-invasive imaging technology that can detect brain tumors and gives a variety of tissue contrasts in each imaging modality. Until recently, only neuroradiologists were capable of performing the tedious and time-consuming task of manually segmenting and analyzing structural MRI scans of brain tumors. This was because neuroradiologists have specialized training in this area. The development of comprehensive and automatic segmentation methods for brain tumors will have a significant impact on both the diagnosis and treatment of brain tumors. It is now possible to recognize tumors in photographs because of developments in computer-aided design (CAD), machine learning (ML), and deep learning (DL) approaches. The purpose of this study is to develop, through the application of MRI data, an automated model for the detection and classification of brain tumors based on deep learning (DLBTDC-MRI). Using the DLBTDC-MRI method, brain tumors can be detected and characterized at various stages of their progression. Preprocessing, segmentation, feature extraction, and classification are all included in the DLBTDC-MRI methodology that is supplied. The use of adaptive fuzzy filtering, often known as AFF, as a preprocessing technique for photos, results in less noise and higher-quality MRI scans. A method referred to as “chicken swarm optimization” (CSO) was used to segment MRI images. This method utilizes Tsallis entropy-based image segmentation to locate parts of the brain that have been injured. In addition to this, a Residual Network (ResNet) that combines handcrafted features with deep features was used to produce a meaningful collection of feature vectors. A classifier developed by combining DLBTDC-MRI and CSO can finally be used to diagnose brain tumors. To assess the enhanced performance of brain tumor categorization, a large number of simulations were run on the BRATS 2015 dataset. It would appear, based on the findings of these trials, that the DLBTDC-MRI method is superior to other contemporary procedures in many respects.

10 December 2022 in Electronics
Verified
Journal Article
Open access
PDF file
Malliga SubramanianMalliga Subramanian
Malliga Subramanian
VRVani Rajasekar
Vani Rajasekar
Sathishkumar Veerappampalayam EaswaramoorthySathishkumar Veerappampalayam Easwaramoorthy
Sathishkumar Veerappampalayam Easwaramoorthy
KSKogilavani Shanmugavadivel
Kogilavani Shanmugavadivel
PNP. S. Nandhini
P. S. Nandhini
Deep learning-based medical image analysis is an effective and precise method for identifying various cancer types. However, due to concerns over patient privacy, sharing diagnostic images across medical facilities is typically not permitted. Federated learning (FL) tries to construct a shared model across dispersed clients under such privacy-preserving constraints. Although there is a good chance of success, dealing with non-IID (non-independent and identical distribution) client data, which is a typical circumstance in real-world FL tasks, is still difficult for FL. We use two FL algorithms, FedAvg and FedProx, to manage client heterogeneity and non-IID data in a federated setting. A heterogeneous data split of the cancer datasets with three different forms of cancer—cervical, lung, and colon—is used to validate the efficacy of the FL. In addition, since hyperparameter optimization presents new difficulties in an FL setting, we also examine the impact of various hyperparameter values. We use Bayesian optimization to fine-tune the hyperparameters and identify the appropriate values in order to increase performance. Furthermore, we investigate the hyperparameter optimization in both local and global models of the FL environment. Through a series of experiments, we find that FedProx outperforms FedAvg in scenarios with significant levels of heterogeneity.

Verified
Journal Article
Open access
PDF file
Neelakandan SubramaniNeelakandan Subramani
Neelakandan Subramani
Sathishkumar Veerappampalayam EaswaramoorthySathishkumar Veerappampalayam Easwaramoorthy
Sathishkumar Veerappampalayam Easwaramoorthy
PMPrakash Mohan
Prakash Mohan
Malliga SubramanianMalliga Subramanian
Malliga Subramanian
VSVelmurugan S
Velmurugan S
Twitter, Instagram and Facebook are expanding rapidly, reporting on daily news, social activities and regional or international actual occurrences. Twitter and other platforms have gained popularity because they allow users to submit information, links, photos and videos with few restrictions on content. As a result of technology advances (“big” data) and an increasing trend toward institutionalizing ethics regulation, social network analysis (SNA) research is currently confronted with serious ethical challenges. A significant percentage of human interactions occur on social networks online. In this instance, content freshness is essential, as content popularity declines with time. Therefore, we investigate how influencer content (i.e., posts) generates interactions, as measured by the number of likes and reactions. The Gradient Boosted Decision Tree (GBDT) and the Chaotic Gradient-Based Optimizer are required for estimation (CGBO). Using earlier group interactions, we develop the Influencers Prediction issue in this study’s setting of SN-created groups. We also provide a GBDT-CGBO framework and an efficient method for identifying users with the ability to influence the future behaviour of others. Our contribution is based on logic, experimentation and analytic techniques. The goal of this paper is to find domain-based social influencers using a framework that uses semantic analysis and machine learning modules to measure and predict users’ credibility in different domains and at different times. To solve these problems, future research will have to focus on co-authorship networks and economic networks instead of online social networks. The results show that our GBDT-CGBO method is both useful and effective. Based on the test results, the GBDT-CGBO model can correctly classify unclear data, which speeds up processing and makes it more efficient.