Weather Forecasting Using Machine Learning Guhan Thangavelu, Gowtham Ponnusamy, Keerthick Ravikumar, Mohamed Ashik Bajurulla, Mukhesh Ganesan Aip Conference Proceedings, 2025 : A lot of businesses, especially those in the agriculture sector, depend a lot on certain weather patterns to run their operations. But the effects of climate change make earlier climate models outdated, so weather forecasts must constantly be improved. The ramifications of imprecise forecasts surpass their impact on enterprises; they also have an effect on individuals’ livelihoods and the country’s economy. By improving the forecasting of the weather, this project seeks to address these problems, with an emphasis on delivering trustworthy forecasts for remote locations. The strategy makes use of machine learning and data analysis methods, like using random forest classification to forecast weather
Urinary Bladder Cancer Detection using U-NET and SVM Algorithm 16th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2025, 2025
Classification of Knee Osteoarthritis Using R-CNN Algorithm T. Guhan, RM. Abiraj, M. Muneshwaran, V. Sowndharya Lakshmi, M. Suriyanarayanan Proceedings of the International Conference on Multi Agent Systems for Collaborative Intelligence Icmsci 2025, 2025 Age-related factors affecting the knee joints are the main cause of knee osteoarthritis (OA), a chronic disorder. It takes a lot of time to make an accurate diagnosis, which is usually done by medical specialists utilizing X-ray imaging. This study explores the use of explainable artificial intelligence (XAI) to improve the interpretability of deep learning (DL) models, specifically convolutional neural networks (R-CNNs), in order to automate the diagnosis of knee OA. To increase interpretability, the research employs a divide-and-conquer technique that moves from multi-class to binary classification using state-of-the-art pre-trained DL models to categorize instances of knee OA. Using Kellgren-Lawrence (KL) graded X-ray images, five refined DL models are assessed. Gradient-weighted Class Activation Mapping (GradCAM) is used for interpretability. According to the results, EfficientNetb7 can differentiate between normal and severe cases with a classification accuracy of above 90%. Its performance drops to 67% for other classes, though, highlighting how challenging it is to match medical professionals' diagnostic accuracy.
AN IMPLEMENTATION OF ENHANCED INCEPTION-RESIDUAL CONVOLUTIONAL NEURAL NETWORK IN LUNG CANCER PREDICTION Journal of Theoretical and Applied Information Technology, 2025
Financial and economic analysis on serverless computing sytem services T. Guhan, G. Chandra Sekhar, N. Revathy, K. Baranidharan, H. Mickle Aancy Essential Information Systems Service Management, 2024 In this chapter, the economic implications of serverless computing for enhancing human living experiences are exemplified. The infrastructure expenses, pay-per-use pricing models, and operational overhead have been elaborated. The cost efficiencies and allocation of resources towards innovation and growth initiatives have been achieved by eliminating the need for provisioning, managing, and scaling servers. The impact of serverless computing on business operations, market dynamics, and industry competitiveness is economically analyzed. However, the challenges (vendor lock-in, security concerns, and performance optimization complexities) have been considered.
RETRACTION:Long-term and short-term rainfall forecasting using deep neural network optimized with flamingo search optimization algorithm S. Vidya, Veeraraghavan Jagannathan, T. Guhan, Jogendra Kumar Journal of Intelligent and Fuzzy Systems, 2024 Rainfall forecasting is essential because heavy and irregular rainfall creates many impacts like destruction of crops and farms. Here, the occurrence of rainfall is highly related to atmospheric parameters. Thus, a better forecasting model is essential for an early warning that can minimize risks and manage the agricultural farms in a better way. In this manuscript, Deep Neural Network (DNN) optimized with Flamingo Search Optimization Algorithm (FSOA) is proposed for Long-term and Short-term Rainfall forecasting. Here, the rainfall data is obtained from the standard dataset as Sudheerachary India Rainfall Analysis (IRA). Moreover, the Morphological filtering and Extended Empirical wavelet transformation (MFEEWT) approach is utilized for pre-processing process. Also, the deep neural network is utilized for performing rainfall prediction and classification. Additionally, the parameters of the DNN model is optimizing by Flamingo Search Optimization Algorithm. Finally, the proposed MFEEWT-DNN- FSOA approach has effectively predict the rainfall in different locations around India. The proposed model is implemented in Python tool and the performance metrics are calculated. The proposed MFEEWT-DNN- FSOA approach has achieved 25%, 26%, 25.5% high accuracy and 35.8%, 24.7%, 15.9% lower error rate for forecasting rainfall in Cannur at Kerala than the existing Map-Reduce based Exponential Smoothing Technology for rainfall prediction (MR-EST-RP), modular artificial neural networks with support vector regression for rainfall prediction (MANN-SVR-RP), and biogeography-based extreme learning machine (BBO-ELM) (BBO-ELM-RP) methods respectively.
Chronic Illness Detection using Gradient Boosting Algorithm 15th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2024, 2024
Stress Detection using CNN Algorithm 15th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2024, 2024
Evolutionary algorithm for target tracking adaptive pigeon inspired optimization based on energy proficient steering in wireless sensor networks Internet of Everything Smart Sensing Technologies, 2022