S. Selva Kumar

S. Selva Kumar

Auto-generated profile, based on publicly available information

S. Selva Kumar

Affiliation School of Computer Science and Engineering, VIT-AP University, Beside AP Secretariat, Amaravati, Andhra Pradesh, India

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

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

Representative Publications

View All Publications
22 April 2025 in IEEE Access
Verified
Journal Article
Open access
VPVasudha Rani Patheda
Vasudha Rani Patheda
GLGunda Laxmisai
Gunda Laxmisai
BGB. V. Gokulnath
B. V. Gokulnath
SIS. P. Siddique Ibrahim
S. P. Siddique Ibrahim
SKS. Selva Kumar
S. Selva Kumar
Breast cancer is the most frequent type of cancer largely experienced by women currently, although it could happen to men also. It appears when abnormal breast tissue cells grow rapidly and form tumors. Mammogram is a technique that is employed by doctors to analyse the breast in the diagnosis of early cancer. These mammograms are classified into Benign and Malignant. This research addresses the variability and potential oversight in radiologists’ manual mammogram interpretations, aiming to enhance classification accuracy by combining Convolution Neural Networks (CNNs) and Vision Transformers (ViTs). CNN is a successful image classification that uses hierarchical feature extraction, ViTs capture the global context but require substantial data and computation. In this research, we have used CLAHE-enhanced mammogram images from Kaggle for training and applied a CNN+ViT model. We have also used a few pre-trained models such as DenseNet, Inception, SE Resnet, and XceptionNet for comparative analysis. The CNN+ViT model gave us an accuracy of 90.1% showing robust performance. Although XceptionNet achieved perfect accuracy, it may indicate overfitting.

1 January 2023 in Journal of Sensors
Verified
Journal Article
Open access
PDF file
LRLAVANYA Ra
LAVANYA Ra
DVD. Vidyabharathi
D. Vidyabharathi
SKS. Selva Kumar
S. Selva Kumar
MMManisha Mali
Manisha Mali
MAM. Arunkumar
M. Arunkumar
MTMiretab Tesfayohanis
Miretab Tesfayohanis
Internet of Things‐based smart healthcare systems have gained attention in recent years for improving healthcare services and reducing data management costs. However, there is a requirement for improving the smart healthcare system in terms of speed, accuracy, and cost. An intelligent and secure edge‐computing framework with wearable devices and sensors is proposed for cardiac arrhythmia detection and acute stroke prediction. Latency reduction is highly essential in real‐time continuous assessment, and classification accuracy has to be improved for acute stroke prediction. In this paper, preprocessing and deep learning‐based assessment is performed in the edge‐computing layer, and decisions are communicated instantly to the individuals. In this work, acute stroke prediction is performed by a deep learning model using heart rate variability features and physiological data. Classification accuracy is improved in this approach when compared to other machine learning approaches. Cloud servers are utilized for storing the healthcare data of individuals for further analysis. Analyzed data from these servers are shared with hospitals, healthcare centers, family members, and physicians. The proposed edge computing with wearable sensors approach outperforms existing smart healthcare‐based approaches in terms of execution speed, latency time, and power consumption. The deep learning method combined with DWT performs better than other similar approaches in the assessment of cardiac arrhythmia and acute stroke prediction. The proposed classifier achieves a sensitivity of 99.4%, specificity of 99.1%, and accuracy of 99.3% when compared with other similar approaches.

15 May 2021 in Wireless Personal Communications
Verified
Journal Article
Closed access
PDF file
SSS. Selvakumar
S. Selvakumar
SMS. S. Manivannan
S. S. Manivannan

23 January 2020 in Enterprise Information Systems
Verified
Journal Article
Closed access
SSSelvakumar S
Selvakumar S
MSManivannan Ss
Manivannan Ss
In next-generation high-speed networks, Elastic Optical Networks (EONs) play a promising role due to its more flexibility and optimal spectrum management. Some of the key facts of EON that have to be addressed are Routing and Spectrum allocation. In this paper, an efficient routing algorithm is proposed along with optimization of spectrum allocation for EON. Improved Bellman Floyd Warshall (IBFW) shortest path routing and Enhanced Shuffled Frog Leaping Algorithm (ESFLA) are used in our proposed work. Simulation results are compared with recent RSA algorithms with appropriate metrics where it achieves better spectrum utilisation and reduced number of blocking.

14 June 2024
Verified
Book Chapter
Closed access
SPSiddique Ibrahim S. P.
Siddique Ibrahim S. P.
SDSathya D.
Sathya D.
GVGokulnath B. V.
Gokulnath B. V.
SSSelva Kumar S.
Selva Kumar S.
JWJai Singh W.
Jai Singh W.
Thangavel MuruganThangavel Murugan
Thangavel Murugan
Natural catastrophes including hurricanes, floods, wildfires, and earthquakes can seriously harm people and property. Floods that destroy houses, businesses, government buildings, and other properties cause enormous economic losses in addition to human casualties. This loss cannot be recovered; however, flood damage can frequently be reduced by supporting suitable structural and non-structural solutions. Natural catastrophes have become more frequent and severe in recent years, primarily as a result of climate change. Due to the large number of small and low magnitude earthquakes, the hand-picked data used in manual approaches, and the possibility of some noisy disturbances in the background, the methods are not very dependable. As a result, automated techniques and algorithms are more effective when used for earthquake identification and detection. However, scientists and engineers can now more accurately and efficiently predict and avert natural disasters thanks to developments in machine learning and data analytics. By creating a deep learning model that can quickly determine an asset's structural status in the event of a seismic excitation, this study investigates the potential of artificial intelligence in various operational domains.

18 February 2021 in Research Square
Verified
Preprint
Open access
PDF file
SSSelvakumar S
Selvakumar S
SMS S Manivannan
S S Manivannan
The rapid growth of the technologies, high bandwidth applications and cloud data centers consume heavy internet service. So, the consumer of the internet expects a high capacity medium for communication. The Elastic Optical Network (EON) provides a flexible and reliable transmission service for the consumers. The spectrum fragmentation is a key challenge in EON. In simple terms, unaligned Frequency Slots (FSs) in the network are referred to as fragmented spectrum, while in defragmentation, the available FSs need to be rearranged to create room for the new connection requests. The problem in defragmentation occurs due to the lack of a continuous spectrum and it leads to depreciation in spectrum usage and simultaneously increasing the Blocking Probability (BP) which disrupts the majority of the existing connections in the network. Several techniques and approaches were suggested to reduce the possibility of disruption and reconfiguration in the network while defragmenting the frequency slots. This paper proposes a new algorithm to overcome the drawbacks and improvement in the quality of service of the network. The proposed algorithm holds the approach of proactive and reactive along with the meta-heuristic nature-inspired optimization technique called Jellyfish Search Optimization (JSO). The proposed combination, PR-DF-JFSO outperforms well in terms of spectrum utilization, network efficiency, and quality of service offered when compared to the state-of-the-art spectrum defragmentation algorithms according to the results of experiments done using standard quality metrics.