Soham Kalghatgi's repositories
Image-reconstruction-and-Anomaly-detection
CNN autoencoder is trained on the MNIST numbers dataset for image reconstruction. Anomaly detection is carried out by calculating the Z-score. The framework used is Keras.
Analyzing-the-effects-of-Fault-Injection-into-a-camera-based-autonomous-vehicle-prototype
Identifying failure modes of vehicle cameras in the domain of autonomous driving (ADAS) and, designing a Fault Injection Module (FIM) to inject these faults through image processing into the autonomous vehicle system. Compassion between the faults to validate the robustness of an autonomous vehicle system.
Deep-Fake-Detection
Learning how to distinguish fake content from genuine content with machine learning . The Machine Learning framework used is PyTorch.
Image-denoising
DnCNN model trained by residual learning formulation to recover a clean image x from a noisy observation y. The noisy observation y is a combination of a clean image x and residual image v. y = x + v. The Machine Learning framework used is PyTorch.
Programmed-solutions-for-Gyroscope-and-Governor.-
Course project under Dynamics of Machines, formulating calculations on Gyroscope and Governor, through executable computer programs using source codes written in C and C++
Specially-Abled-Utility-vehicle-SAUV
A safe, ergonomic, detachable hand-controlled mechanism that allows full coordinated actuation of accelerator, brake, and clutch of a manual transmission vehicle, by just one hand without any -leg input from the driver.