Rajasekaran Thangaraj

ORCID: 0000-0003-0874-7638
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Smart Agriculture and AI
  • COVID-19 diagnosis using AI
  • Spectroscopy and Chemometric Analyses
  • Video Surveillance and Tracking Methods
  • Face recognition and analysis
  • Plant Disease Management Techniques
  • Date Palm Research Studies
  • Leaf Properties and Growth Measurement
  • IoT and Edge/Fog Computing
  • Customer churn and segmentation
  • Stock Market Forecasting Methods
  • Big Data and Business Intelligence
  • AI in cancer detection
  • Wildlife Ecology and Conservation
  • Anomaly Detection Techniques and Applications
  • Digital Imaging for Blood Diseases
  • Infection Control and Ventilation
  • Greenhouse Technology and Climate Control
  • Advanced Image and Video Retrieval Techniques
  • VLSI and Analog Circuit Testing
  • Embedded Systems Design Techniques
  • Interconnection Networks and Systems
  • Environmental DNA in Biodiversity Studies
  • Poxvirus research and outbreaks
  • Financial Markets and Investment Strategies

Goverment Siddha Medical College
2025

KPR Institute of Engineering and Technology
2019-2024

Prediction of Liquidation Stock is one the most difficult tasks in stock exchange since price a highly non-linear & to find. Several popular Machine Learning algorithms have been tested: Linear regression (LR), Decision Trees (DT), random forests (RF), Support Vector Machines (SVM), and Neural Networks (NN: Feed Forward Long Short-Term Memory; LSTM). Then, model validated against ground truth, set performance metrics (for example, those Mean Absolute Error (MAE), Root Squared (RMSE)...

10.2139/ssrn.5065582 article EN SSRN Electronic Journal 2025-01-01

Black gram is an essential pulse crop extensively cultivated across Asia, recognized for its nitrogen-fixing capabilities and importance as a dietary staple. However, production increasingly threatened by diseases such powdery mildew leaf spot, highlighting the need effective disease management strategies. This study investigates use of transfer learning algorithms to improve classification black diseases, with focus on achieving optimal accuracy. Four models were assessed: MobileNetv2,...

10.2139/ssrn.5082167 article EN SSRN Electronic Journal 2025-01-01

With offensive activities on the rise we have never needed safety measures more. Closed-circuit television (CCTV) is now being deployed regularly in public spaces these days where better need to be taken such as shopping malls, banks and other high-traffic places. But manually watching cameras too complicated one must keep their eyes it every single minute all suspicious are hard catch. In addressing this problem, present research offers a fully functional system popularly referred...

10.2139/ssrn.5082217 article EN SSRN Electronic Journal 2025-01-01

The COVID-19 pandemic has infected tens of millions individuals around the world, and it is currently posing a worldwide health calamity. Wearing face mask in public places one most effective protection strategies, according to World Health Organization (WHO). Moreover, their effectiveness declined due incorrect use mask. In this scenario, recognition systems are anticipated ensure that people's faces covered with masks locations. Many people do not correctly wear inadequate practices,...

10.1504/ijahuc.2023.128499 article EN International Journal of Ad Hoc and Ubiquitous Computing 2023-01-01

Plant diseases are regarded as one of the major variables affecting food production and reducing losses. Early identification disease diagnosis fruit crops essential for industry to increase production. The development healthy sector is highly dependent on plant diseases. Guava a good source fiber, calcium, pectins, vitamin C. has become issue guava production, which negative impact farmers' socioeconomic growth. Infections that harm plants fruits pose greatest obstacles, although they can...

10.1109/icaect57570.2023.10117860 article EN 2023-01-05

COVID-19 is a virus that can cause severe pneumonia, and the severity varies based on patient's immune system. The rapid spread of disease be mitigated through automated detection, addressing shortage radiologists in medicine. This paper introduces Modified-Inception V3 (MIn-V3) model, which utilizes feature fusion from internal layers Inception to classify different diseases, including normal cases, positivity, viral bacterial pneumonia. Additionally, transfer learning fine-tuning...

10.1016/j.health.2023.100278 article EN cc-by Healthcare Analytics 2023-11-08

The global economy has been affected enormously due to the spread of coronavirus (COVID-19). Even though, there is availability vaccines, social distancing in public places one viable solutions reduce spreading COVID-19 suggested by World Health Organization (WHO) for fighting against pandemic. This paper presents a YOLO v3 object detection model automate monitoring among persons through CCTV surveillance camera. Furthermore, this research work used detect and track person, measure...

10.1504/ijsnet.2022.121700 article EN International Journal of Sensor Networks 2022-01-01

Wild animal monitoring is one of the essential factors in balancing ecosystem protecting habitat. Camera traps are used to capture images, which play a vital role automatic wildlife owing their effectiveness collecting data. The images captured from camera large volumes nature, and they inexpensive. However, manual processing such number time-consuming, expensive, challenging task. Such kind process provides major hurdles ecologists wildlife. This paper evaluates deep learning models as...

10.1109/icaect57570.2023.10117922 article EN 2023-01-05

Sales fluctuation is the biggest problem faced by every retailer. The key to solving this issue finding invisible pattern of components that have an effect on sales prediction. Nowadays retailers require a 360-degree vision their customers compete in market. To achieve and marketing objectives, must build strong promotions offers. Retail companies employ data from previous year analyse predict for upcoming using analysis applications. Additionally, it provides with analytical insights,...

10.1109/icdate58146.2023.10248586 article EN 2023-07-14

Plant diseases are the most crucial factor in agriculture sector, which causes a reduction yield and economic loss. Therefore, early accurate detection of these can control infection spread to other crops minimize production Traditional methods use handcrafted features images detect part leaves type. Furthermore, extraction is expensive time-consuming. However, light recent advances agricultural technology, such as artificial intelligence diagnosing plant diseases, appropriate research must...

10.1109/gecost55694.2022.10010611 article EN 2022-10-26

Automatic object identification and recognition of the objects are done through CCTV cameras. In this approach, entire footage is stored which leads to more data storage requirements. Apparently, cost for more. This paper proposes technique in cameras record only when motion detected footage. Therefore, proposed algorithm reduces device will be implemented home, office, garden, cabin etc. Figure out unusual activity. Face Gender most basic information on human beings. It great significance...

10.1109/icaeca52838.2021.9675635 article EN 2021 International Conference on Advancements in Electrical, Electronics, Communication, Computing and Automation (ICAECA) 2021-10-08

Closed-circuit television (CCTV) systems are vital to prevent security threats public safety. Nowadays, the use of weapons causes a big threat in places and it creates lot violence. The quick detection handguns is very important avoid or reduce risks. Some world have crimes that committed with handguns, even though guns aren't allowed. has been used keep an eye on these situations; it's time images. This task typically carried out by human, who more prone forgetting them due fatigue being...

10.1109/icaaic53929.2022.9793288 article EN 2022 International Conference on Applied Artificial Intelligence and Computing (ICAAIC) 2022-05-09

Sales prediction is an important problem for businesses. A sales forecast can guide a company's production, pricing, and promotion strategies, help mitigate risks associated with under or overproduction. Traditional methods of utilized statistical techniques like regression analysis time series analysis, but these have certain limitations, including the need large clean data sets. This research work focuses on exploring patterns trends present in large-scale retail dataset through...

10.1109/icaaic56838.2023.10140416 article EN 2023-05-04

Plant diseases are a significant concern for the agricultural industry, as they can reduce crop yields and cause economic losses. Tea is popular widely consumed beverage in India, tea be affected by different leaf diseases. Early detection of essential to prevent spread other crops minimize production Traditional methods detecting involve manually interpreting images, which time-consuming laborious. To address this, artificial intelligence techniques, specifically deep learning models used...

10.1109/icdate58146.2023.10248508 article EN 2023-07-14

Weeds, pests, and other plant diseases are the leading causes of financial losses in agriculture farming industry worldwide. It is a critical factor since it reduces crop quality capacity significantly. As result, detecting classifying diverse critical, requires special attention. This impact can be reduced by diagnosing at an earlier stage. work will largely focus on detection cucumber leaf diseases. Manual methods identifying infections sometimes time-consuming, difficult, subjective....

10.1109/icaiss58487.2023.10250764 article EN 2023-08-23

The promising Network-on-Chip (NoC) model replaces the existing system-on-chip (SoC) for complex VLSI circuits. Testing embedded cores using NoC incurs additional costs in these SoC models. models consist of network interface controllers, Internet Protocol (IP) data centers, routers, and connections. Technological advancements enable production more chips, but longer testing times pose a potential problem. packet switching networks provide high-performance interconnection, significant...

10.3233/ida-240878 article EN Intelligent Data Analysis 2024-09-29
Coming Soon ...