Charulkumar Chodvadiya
Development
Gujarat, India
Skills
Machine Learning (ML)
About
Charulkumar Chodvadiya's skills align with IT R&D Professionals (Information and Communication Technology). Charulkumar also has skills associated with Programmers (Information and Communication Technology). Charulkumar Chodvadiya appears to be an entry-level candidate, with 9 months of experience.
View more
Work Experience
Telangana
June 2023 - March 2024
- Aug 2020 - Mar 2021 Gujarat, India Mar 2019 - Feb 2020 Gujarat, India Projects EEG Signal Analysis Applied machine learning algorithms to identify and classify distinctive patterns within EEG signals, enhancing accu- • racy in pattern recognition tasks. Hate Speech Detection Developing a hate speech detection algorithm utilizing unsupervised machine learning techniques, for cluster analysis • methods like K-means and hierarchical clustering. Employed anomaly detection within identified clusters, allowing the algorithm to recognize potential hate speech • patterns without relying on pre-labeled datasets. Brain Tumor Segmentation Using Federated Learning Developed a Federated Learning approach to segment brain tumor images across three diverse datasets. • Developed custom aggregation strategies to address diverse dataset gradients and enhance server aggregation. • The core objective was to improve the precision of medical image segmentation by implementing a self-designed loss • function that incorporates spatial and feature losses from both the local model training and server model, ensuring a comprehensive refinement of the segmentation process. Palm Print Detection And Identification Utilized transfer learning to improve the precision of a deep learning model for contactless biometric identification. • Captured a diverse palm print dataset, including left and right hands from 15 individuals, with variations in distance, • orientation, finger positioning, and deformation. Night Vision Face Detection Leveraged YoloV5, YoloV8, HoG, SVM, and CNN methodologies to enhance precision. Achieved robust results by • combining cutting-edge technologies for efficient face detection even in challenging lighting scenarios. Predicting Solar Power Generation With Its Maintenance Activities Employed Deep Learning models, statistical time series data analysis concepts, and mathematical operations to fore- • cast solar power generation and maintenance activities. Leveraging a customized dataset sourced from our university's solar plant, improved forecasting precision and enabled • proactive maintenance strategies, enhancing overall system efficiency.
Education
Pandit Deendayal Energy University
M.Tech
