-
🔭 I’m currently working on Uncertainty in Neural Networks
-
🌱 I’m currently learning Flax, Jax
-
📫 How to reach me [email protected]
-
Find my resume here
- NILM Uncertainty : Accepted for BuildSys2022 (Core A)
- Custom Weighted Balanced Loss Function : Accepted for ICPR 2022 (Core B)
- SVD‑CLAHE Boosting & Balanced Loss Function : Accepted for CIBM Journal - Q1
- Canny Edge Detection : Implementation of Canny Edge Detection Algorithm from scratch.
- Geosis Conceptualised the website which makes location based prediction of annual forest cover. (Data : scraped from govt. sources for 20 years).Geographic Visual analysis dashboard was implemented to observe the NDVI change & climate change over years
- Indian Classical Dance forms, Indian classical dance (ICD) classification is an interesting subject because of its complex body posture. It provides a stage to experiment with various computer vision and deep learning concepts. The input to the proposed network is initially pre-processed using image thresholding and sampling. Next, a truncated DCNN based on ResNet50 is applied to the pre-processed samples. The proposed model gives an accuracy score of 0.911
- Covid-19 prioritizes people on the basis of their symptoms and locality. This tool helps us to identify priorities of need of vaccine in a city compared to others. Data Preprocessing, Feature selection, and unsupervised learning(KMeans) were used in a pipeline as the model design.