SRIRAJARAJESWARI THOTA

@lbrce.ac.in

Senior Assistant Professor, Artificial Intelligence & Data Science
Lakireddy Bali Reddy College of Engineering

SRIRAJARAJESWARI THOTA


               Download Compact PDF  
https://researchid.co/thrajeswari

EDUCATION

Master of Technology
JNTUH College of Engineering Hyderabad

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Engineering, Artificial Intelligence, Computer Science Applications, Computer Vision and Pattern Recognition
12

Scopus Publications

Scopus Publications

  • Spatiotemporal Forecasting of Ocean Surface Currents using ConvLSTM Networks on OSCAR Data
    T.S.RajaRajeswari, T.Malleshwari, K.Sudheer, R Gopi
    Proceedings of 3rd International Conference on Sustainable Computing and Data Communication Systems Icscds 2025, 2025
    Abstract-This study proposes a deep learning framework using Convolutional Long Short-Term Memory (ConvLSTM) networks to forecast ocean surface currents based on the Ocean Surface Current Analysis Real-time (OSCAR) dataset. OSCAR generates gridded global surface velocity fields from satellite altimetry, wind, and temperature with useful spatiotemporal information. The model forecasts future zonal (u) and meridional (v) current components based on past current patterns learned. Data normalization, sequence generation, ConvLSTM training, and performance measurement constitute the workflow. The architecture accommodates both space structure and temporal change, for which it is ideally suited for forecasting ocean currents. Aside from forecasting, the model identifies high-velocity events that may indicate turbulence or hazardous marine conditions. Performance is assessed using RMSE, MAE, and correlation coefficients, with visualizations provided through quiver plots and heatmaps. Results demonstrate accurate short-term forecasts and effective detection of dynamic events. This work highlights ConvLSTM’s potential for real-time ocean monitoring and improved marine forecasting under complex environmental variability.
  • Grid-Based Dynamic Password Authentication for Enhanced Security
    T.S. RajaRajaswari, Shaik Abu Saif, Baswa Rudra Teja, Saggurti Srujan Chowdary
    2025 IEEE International Conference on Blockchain and Distributed Systems Security Icbds 2025, 2025
    In the current digitally inclined age, application of the traditional password authentication mechanisms are grave security hazards. Conventional systems are more vulnerable to attacks such as phishing, keylogging, and shoulder surfing, all of which can leave static passwords open to attackers. These dangers highlight the necessity need for a more secure and adaptive authentication mechanism that reconciles user convenience and security threats. To address these problems, this project suggests a new Grid-Based Dynamic Password Authentication System that will enhance security in user authentication by creating dynamic passwords from user-specified trends in a randomly ordered grid. Unlike the traditional methods where users memorize and input static passwords, such a mechanism allows the users to specify beforehand a pattern or sequence of positions on a <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$9 \times 9$</tex> dynamic grid. Every time the user logs in, the system generates a new grid with random numerical values, and the user fills in the values at their previously chosen pattern positions. Since the grid values continuously change with every login attempt, the resulting password also changes dynamically, hence making intercepted passwords unavailable in the future attempts. This constantly changing nature of the password makes it more safe against such simple attacks such as keylogging (since the keystrokes are constantly changing), shoulder surfing (since attackers cannot know what grid values are being selected), and phishing (because the actual password values vary). The website integrates strong security features with simplicity design, so that it can be utilized for practical reasons such as banking, online payment, confidential data access, and e-commerce websites, where secure authentication is mandatory. In addition, utilization of AES-192 encryption to store user patterns and Firebase cloud integration for backup as well as data management purposes, the system is also very secure and tamper-proof. The proposed method thus integrates usability with security, providing a robust solution to today's authentication issues.
  • Enhanced Diabetes Detection with Deep Learning: An Iris Image Analysis Approach
    T.S. RajaRajeswari, Beeram Snehanjali, Rapthadu Kasi Rizwana, Bethi Phanindra Vardhan
    5th International Conference on Sustainable Communication Networks and Application Icscna 2024 Proceedings, 2024
    Diabetes is a chronic and progressive condition that, if not diagnosed early, can lead to serious health complications, often we will see that patients learn they have diabetes only years after its emergence this points out the significance of precise and early identification. Thus, diabetes is a global health issue that requires timely detection. Traditional methods for diagnosing diabetes often involve expensive procedures, which can lead to delays in diagnosis. Using iris images for diabetes detection through deep learning algorithms offers a more accurate and cost-effective alternative. In general, a person with diabetes may experience changes in the iris, such as alterations in pattern, texture, or pigmentation. To identify these altered features, high-resolution observation is required. For this purpose, we use advanced imaging techniques and deep learning algorithms to analyze and interpret the changes in iris characteristics. CNN's, known for their powerful feature extraction capabilities, effectively captured and analyzed complex details in iris patterns. This approach utilizes several types of algorithms available in deep learning like Convolutional Neural Networks (CNNs), MobileNetV2, InceptionV3, ResNet50 and CNNs along with transformers. All these algorithms are widely known for their efficiency in image analyzing applications. Thus, we have chosen to implement the same procedural approach but for different algorithms. Finally, we had found an efficient algorithm in such a way that it gives the highest accuracy for the same dataset as compared with the other algorithms. It proved that CNNs are effective in identifying features and patterns in images and it gave the accuracy of about 93.91 % showing its effectiveness. Thus, ultimate aim of this approach is to provide an accurate, non-invasive and cost-effective way of diabetes disease diagnosis.
  • Convolution Neural Network Versus Transfer Learning in Image Classification
    O. Rama Devi, U. Surya Venkata Sekhar, S. Siva Rama Krishna, T. S. Rajarajeswari
    Lecture Notes in Networks and Systems, 2024
  • Clothes donation using mobile application development
    T. S. Raja Rajeswari, Peneti Subhashini, S. Navya
    Aip Conference Proceedings, 2023
  • Under water image enhancement technique
    T. S. Raja Rajeswari.Thota, M. Srinivasa Rao, N. Sandhya Rani
    Aip Conference Proceedings, 2023
  • Analysis of women safety in Indian cities using machine learning
    K. Pushpa Rani, T. Raja Rajeswari, N. Thulasi Chitra, B. Devananda Rao
    Aip Conference Proceedings, 2023
  • Crop Recommendation System using Random Forest Algorithm in Machine Learning
    Siva Ramakrishna Sani, Surya Venkata Sekhar Ummadi, SriRajarajeswari Thota, Nikitha Muthineni, Varun Sai Srinivas Swargam, Teja Sree Ravella
    Proceedings of the 2nd International Conference on Applied Artificial Intelligence and Computing Icaaic 2023, 2023
    The crop recommendation system employing machine learning methods will be covered in this study. For sustainable agricultural practices to be followed and to increase crop yields, crop advice is crucial. Based on several factors, including nitrogen (N), phosphorus (P), potassium (K), and humidity, we will advise the best crop for the given site. We analyzed various algorithms like KNN, Decision Tree, Random Forest, SVM etc. But based on various accuracy levels we committed to random forest implementation. Means, In this paper we are going implement crop recommendation system using random forest algorithm. The model allowed to train upon large dataset and the performance of the recommendation system is measured using accuracy score. Finally, Using the trained model we are going to predict suitable crop for land according to the given parameters. Our proposed approach can be helpful for farmers, researchers, and policymakers in making informed decisions regarding crop managementand planning.
  • IoT Based Smart Notice Board for Smart Cities
    P. Chinnasamy, T.S. RajaRajeswari, P. Subhasini, S. K. Lokesh Naik, A. Ashwini, T. Sivaprakasam
    2022 International Conference on Computer Communication and Informatics Iccci 2022, 2022
    Smart Web based notice board can be implemented in many fields like schools, institutions, banking, medical field, and railway stations etc. This will be a simple process as it need not require any paper information to be displayed. Especially, if this project is implemented in our institution, then it will be easy for the administration block, to easily pass the important information immediately to the staff or students within minutes. A webserver can be used, if the admin gives any information, then it will be displayed on the liquid crystal display. Here, we used microcontroller, Node MCU will read the data from the webpage and then can be seen on the notice board.
  • IoT based Smart Gardening for Smart Cities using Blockchain Technology
    T.S. RajaRajeswari, P. Chinnasamy, K. Pushparani, N. Thulasichitra, N.Sandhya Rani, T. Sivaprakasam
    2022 International Conference on Computer Communication and Informatics Iccci 2022, 2022
    The automation of agriculture is growing and thrust areas in a technological world. Previously, the data's are monitored in simple LCD screen, but in our article, we are introducing a novel idea to continue monitoring of the water level in an area and pumping the water, and we can also send it by GSM, then the analyzed data can send to gardener or the person who monitors the area using GSM Technology. A smart gardening is an electronic device designed to assist in alerting somebody in the situations where there is no water or water were filled in the garden/smart cities which is implemented by blockchain technology. The alarm can be used to request emergency assistance from local services or emergency services.
  • E-Library Implementation Using Android Studio
    T.S. RajaRajeswari, K. PushpaRani, Nimmy Ann Jose, K. Preethi, T.Naga Santhosh, V.Akhil Reddy
    Proceedings of the 6th International Conference on Communication and Electronics Systems Icces 2021, 2021
  • Generating and Validating Certificates Using Blockchain
    T.S.Raja Rajeswari, Sk Khaja Shareef, Sameer Khan, N Venkatesh, Akhtar Ali, V. Sri Monika Devi
    Proceedings of the 6th International Conference on Communication and Electronics Systems Icces 2021, 2021