SANTHOSH KUMAR C

@pmctech.org

Assistant Professor CSE
Er.Perumal Manimekalai College of Engineering

https://researchid.co/santhosh1988

C.Santhosh kumar is currently a Researcher , at PMC Tech , is having 10 years of Experience in Teaching. He graduated B.E. from SRM Easwari Engineering College , Chennai , PG Degree from Anna University Regional centre , Coimbatore .Presently he is pursuing his Ph.D. at Anna University, Chennai. His area of interest includes Soft Computing, Machine learning, Semantic web. He published a book"Problem solving and python programming" at Anuradha Publications and "Theory of Computation" at Bonfring publications . He is passionate in learning Soft Computing Techniques . He presented and published 17 research papers in International and National conferences. He is a Professional member of Association of Computing Machinery, Soft Computing Research Society and CSI. He is one of the Computer Science related Tamil Online Tutor under the youtube channel name santhosh kumar Study circle . His channel has 670 subscribers and 1,67,400 views.

EDUCATION

2017-2024 Doctor of Philosophy (I&C),Pursuing Ph.D. at Anna University, Chennai .
2010-2012 Master of Engineering ,M.E.(CSE), Anna University Regional Centre Coimbatore, Anna University Chennai , 2012;First Class.
2006-2010 Bachelor of Engineering ,B.E.(CSE), Easwari Engineering College Chennai, Anna University Chennai , 2010;First Class.

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Science, Artificial Intelligence

Scopus Publications

Scholar Citations

Scholar h-index

Scopus Publications

IoT and cloud computing-based automated epileptic seizure detection using optimized Siamese convolutional sparse autoencoder network
M. Ramkumar, S. Syed Jamaesha, M. S. Gowtham, and C. Santhosh Kumar
Springer Science and Business Media LLC

Enhanced QR CODE Scanning and Blockchain Technology for Drug Packaging System
Palanivel N, Esaiarasi. P, Madhan K, Sivashankar P T, Santhosh Kumar C, and Sarath Kumar R
IEEE
Scanning a QR code on pharmaceutical packaging discloses essential information such as the medication's name, batch number, expiration date, and manufacturing date. This connectivity, together with blockchain technology, guarantees both accessibility and security of the data. The objective is to provide an intuitive system that provides straightforward access to pharmaceutical information, facilitating informed decision-making in healthcare. The inclusion of QR codes on drug packaging facilitates access to essential information, including the medicine's name, batch number, expiry date, and manufacturing date. This novel method improves accessibility while also strengthening data security. The incorporation of blockchain technology enhances the system's integrity by utilizing the hashing idea to guarantee data tamper resistance. This increased security mechanism enables users to accurately track the progression of a tablet sheet from its original manufacturing phase to its final distribution stage. This comprehensive solution offers an intuitive platform for accessing medication information while enabling users to make informed healthcare decisions, hence fostering transparency and accountability within the pharmaceutical supply chain. Keywords: Blockchain, Medical Record, QR Code, Dataset.

Deficiencies Identification and Detection in Grape Plant Leaves Using LSTM and CNN Model
Priyaradhikadevi T, Santhosh Kumar C, Srivani A, Palanivel N, Madhan K, and Kavitha K
IEEE
To address mineral shortages in soils, modern fertilization methods identify nutritional deficits in plant foliage. To formulate a fertilization plan that delivers essential micronutrients without excessive production of others, it is crucial to ascertain the requisite quantities of vitamins and minerals. Nutritional inadequacies in agriculture are signaled by the leaves of plants. Physical examination of these leaves from the plant's morphological components provides sufficient information to determine nutritional deficiencies. The main aim of this study was to ascertain nutritional deficits in grapevine leaves. This research use Convolutional Neural Networks (CNNs) for model training. By inputting the model's output into an LSTM, we can categorize grape plant leaf images as healthy or exhibiting deficiencies in nitrogen, iron, phosphorus, manganese, potassium, zinc, calcium, boron, magnesium, or sulfur. Accuracy evaluates the model's efficacy. The data analysis indicated that the proposed model achieved an accuracy rate of 98.6 percent. The results indicate that convolution neural networks (CNNs) may be effective in detecting nutritional deficiencies in grape plant leaves.

Energy Efficient Routing Protocol in Manet using Eagle Search Algorithm
S. Vanarasan, V. Mathavan, N. Shanmugapriya, C. Santhosh Kumar, R. Sarath Kumar, and K. Madhan
IEEE
Mobile Adhoc Networks (MANETs) are overburdened with stagnant traffic. As a result, the routing protocol for energy-efficient with load balancing has become an urgent need for MANET, especially given the limited battery resources in the nodes. Most of the existing routing protocols are time-consuming because they consider power at the expense of time and over-routing. An energy-saving, meta-inference-based load balancing protocol is an alternative model that is more challenging than traditional routing schemes. Therefore, in this research activity, a meta-inference-based Bald Eagle Search (BES) approach is developed for an optimal routing protocol for balancing the load in energy usage. There are three major steps used in the BES, while hunting the fish. Initially, the location of the vast number of prey is selected by an eagle in the space selection stage; the searching process of prey is carried out by moving into the selected space during the space search stage. Finally, during the dive stage, the best point is identified for hunting by swings from the best position that are determined in the second stage. Therefore, the optimal path is identified by the proposed BES, while considering the parameters of energy, bandwidth, delay, reliability, and quality. Finally, the proposed algorithm supports Quality of Services (QoS) and finds the shortest path from one source to the destination with the lowest power consumption. When analyzing the results based on simulation, the proposed BES scheme showed a significant improvement in better battery life, less energy consumption, and high throughput.

A Improved Training Method for Deep Learning Based Anatomical Classification of X-Rays
P. Arangarajan, C. Santhosh Kumar, N. Shunmugakarpagam, R. Vijayabhasker, and C. Gayathri
IEEE

Heart Disease Prediction Using Linear Regression Techniques
S. Vanakovarayan, C. Santhosh Kumar, A. Raj Ganesh, P. Yogananth, T. Ragupathi, and N. Palanivel
IEEE
The Internet of Things plays a prominent role in the development of health applications. Smart gadgets and wireless sensor networks are used to track patients' various health markers in real time. Every day, the number of heart diseases increases at a rapid rate, which makes it very imperative to predict any such diseases in advance. In order to accurately diagnose heart diseases, researchers are utilizing machine learning algorithms, backed up by electronic health data, to develop smart systems. Based on a variety of medical attributes, we employ Machine Learning algorithms to identify potential heart disease in people. This paper presents an IoT- based prediction system for heart disease diagnosis using Logistic Regression (LR) Random Forest (RF)and Support Vector Machines (SVM) to predict and classify patients with heart disease. Ultimately, the aim of our project is to develop a set of modules for tele-monitoring that doctors can employ to diagnose their patients more accurately. This system uses UCI repository datasets for training and testing. Based on comparisons with existing classifiers, the proposed

Securing IoT-Based Home Automation Systems Through Blockchain Technology: Implementation
N. Palanivel, K. Madhan, C. Santhosh Kumar, R. SarathKumar, T. Ragupathi, and Deivanai S
IEEE
Cybersecurity is the large subject matter that connects everything, processes, units and technologies. Network safety is a set of policies and settings. They are the integrity, accessibility and availability of facts and networks. Confidentiality of Software and Hardware Use. Today's community threats are continuously evolving and the surroundings is an increasing number of complex. Similarly, the clever domestic has emerge as a low-security threat. That's why it is so vital to remain secure online. Due to the vulnerability of the clever domestic network, there are purposes in many areas, such as users, locations, data, etc. Some clever units may additionally be lacking from your clever home. The machine has been hardened so that passwords can be scrambled. Unencrypted passwords can be searched on the machine or in the software. The safety of the clever domestic community is pretty high. Prioritize linked gadgets to forestall hackers from gaining access to them. Access to touchy or private data. Failure to do so should put your complete clever domestic community at risk. This learn about builds a mannequin to analyze specific protection problems in clever domestic conversation networks. This lookup wants to use qualitative methods, such as anecdotes. A lookup evaluation was once fundamental to raise out this study. and Other applicable records on the secondary facts series techniques used. Several research have been carried out on the protection threats associated to clever domestic networks and the use of applied sciences derived from block chain technology. Reduce protection troubles and defend your intelligence. Secure your domestic network.

Smart Parking and Parking Guidance Using ECNN Algorithm in Convolution Neural Network
V. Mathavan, P. Sumathi, C. Gayathri, C. Santhosh Kumar, T. Ragupathi, and N. Palanivel
IEEE
Smart Parking and Parking Guidance finding parking methods are in demand in modern megacities. This will reduce traffic, air pollution, driver strain and wasted parking time. This paper presents the design and implementation of an improved version of a CNN based on a parking dataset for finding free parking spaces in parking images. The purpose of this paper is to produce a reliable version with fast generalization that can get information about parking, but it is intended for use with technical cameras that display the number of new parking spaces. This paper provides 94% application accuracy when advertising multiple parking lots. This version also achieved an overall accuracy of 94% while receiving single parking and testicle parking information with a digital camera at an alternative parking lot. Previous reasoning suggests that these pictures should have strong generalizability. These generalizations allow the expert version to be deployed in real parking management structures. It can also serve as the basis for a study to gather new information about parking volumes or add more layers to refine and improve versions.

Design and Implementation of Solar Powered Smart Irrigation Using IoT
C. Santhosh Kumar, S. Brindasri, J. Krishnamoorthy, B. Vidhya, G. Saranya, and K. Madhan
IEEE
The farming is one concerning the indispensable assets due to the fact of advent of ingredients but assumes sizeable portion about the economic regulation about each and every United States on America via which include after Today, coast owners hold a snack troubles within agribusiness appropriate according to the fact of non-appearance about downpours after shortage about water. So, between that task, we wish raise external computerized wind law case due to the fact bank lords as like intention maintain time, value then after on Manual inclusion is wished due to the fact the farmland strategies. By construction use over soil humidity sensor degrees involving ground dampness/mugginess may additionally keep checked. At some also is an harmony the trade yet sends signal in conformity over the microcontroller or relying upstairs that the cloud provision framework works. Robotized cloud government litigation uses valves in accordance in accordance with Engines work continue to be robotized effectively by using construction use of regulators yet no assistance over guide intervention among accordance about flirt apparatus ON then OFF.

Efficient Composition Algorithm Strategies on Semantic Web Services Using Nature Inspired Approach
Santhosh Kumar C. and R. Vijayabhasker
The Electrochemical Society
Web services are used all around the world for commercial purposes. It works majorly by Universal Resource Locators, which are stored in the repository UDDI. The different web service has to be composed for creating new business services. It is time dependent for composing more web services, which is massive. A semantically described WSDL description solves automatic composition of web services. Also with ontological models and languages, such as RDF, OWL, and SWRL, the better automatic discovery, selecting, integration, and composition of services have been done. Service requirements, such as connectivity, quality-of-service properties, correctness, and scalability, need to be satisfied. For achieving these, many evolutionary algorithms will be used for improving quality of service parameters. This paper describes many optimizations algorithms which will be used efficiently in optimizing composition techniques in semantic web.

RECENT SCHOLAR PUBLICATIONS

Deficiencies Identification and Detection in Grape Plant Leaves Using LSTM and CNN Model
T Priyaradhikadevi, A Srivani, N Palanivel, K Madhan, K Kavitha
2024 International Conference on System, Computation, Automation and 2024

Revolutionizing Manufacturing using Machine Learning Method
CSK P.B.Senthil Kumar,Dr. N. Shunmuga Karpagam
Tuijin Jishu/Journal of Propulsion Technology 45 (4), 2772-2779 2024

IoT and cloud computing-based automated epileptic seizure detection using optimized Siamese convolutional sparse autoencoder network
M Ramkumar, SS Jamaesha, MS Gowtham, CS Kumar
Signal, Image and Video Processing 18 (4), 3509-3525 2024

Securing IoT-Based Home Automation Systems Through Blockchain Technology: Implementation
N Palanivel, K Madhan, CS Kumar, R SarathKumar, T Ragupathi
2023 International Conference on System, Computation, Automation and 2023

Smart Parking and Parking Guidance Using ECNN Algorithm in Convolution Neural Network
V Mathavan, P Sumathi, C Gayathri, CS Kumar, T Ragupathi, N Palanivel
2023 International Conference on System, Computation, Automation and 2023

Heart Disease Prediction Using Linear Regression Techniques
S Vanakovarayan, CS Kumar, AR Ganesh, P Yogananth, T Ragupathi, ...
2023 International Conference on System, Computation, Automation and 2023

A Improved Training Method for Deep Learning Based Anatomical Classification of X-Rays
P Arangarajan, CS Kumar, N Shunmugakarpagam, R Vijayabhasker, ...
2023 International Conference on System, Computation, Automation and 2023

Energy Efficient Routing Protocol in Manet using Eagle Search Algorithm
S Vanarasan, V Mathavan, N Shanmugapriya, CS Kumar, RS Kumar, ...
2023 IEEE Fifth International Conference on Advances in Electronics 2023

Diabetic Retinopathy Diagnosis Categorization Using Deep Learning.
KR Rajitha, CS Kumar
Journal of Advanced Zoology 44 (3) 2023

Design and Implementation of Solar Powered Smart Irrigation Using IoT
CS Kumar, S Brindasri, J Krishnamoorthy, B Vidhya, G Saranya, ...
2023 Eighth International Conference on Science Technology Engineering and 2023

A Survey paper on ARM based GPS Controlled Robot for Environment Monitoring using IoT
CA Bharateesh, CS Kumar, MR Soujanya, TS Ganashree, ...
Journal of IoT in Social, Mobile, Analytics, and Cloud 4 (4), 284-290 2023

Efficient Composition Algorithm Strategies on Semantic Web Services Using Nature Inspired Approach
R Vijayabhasker
ECS Transactions 107 (1), 17421 2022

Improving Vegetable Disease Detection using Modified K-Means Clustering Algorithm
CS Kumar, J Jenifer, G Vidhya, R Vijayabhasker
2021

IOT based Air and Sound Pollution Monitoring System
K Roja, S Kumar, PAP Suhi
2021

The Human Interactive Mobile Utilization by Touching Technology- A Simplified View
GC Seethalakshmi P,Santhosh Kumar C
Indian Journal of Innovations and Developments 1 (7), 542-548 2012

A Improved Training Method for Deep Learning Based Anatomical Classification of X-Rays
R Vijayabhasker, C Gayathri, T Nadu
International Conference on System 2, 0

MOST CITED SCHOLAR PUBLICATIONS

Efficient Composition Algorithm Strategies on Semantic Web Services Using Nature Inspired Approach
R Vijayabhasker
ECS Transactions 107 (1), 17421 2022
Citations: 1