Projects
Deep Learning and Computer Vision
Deep Learning and Computer Vision
Time Series Classification
Bio-signals processing
Speech Processing
Mobile Sensors data
Computer Vision and Deep learning
Object Detection
Image Classification
Federated Learning
FedAvg, MSFedGKT
Meta-Learning
MAML, Prototypical Networks
DL Model Optimization
Sparse learning
Network pruning
Knowledge distillation
Multimodal Fusion
Early/Mid-level/late
Python Programming
TensorFlow / Keras
PyTorch
SK-Learn
OpenCV
Numpy
MatplotLib
Pandas
Flask for Web development projects based on Python
Tkinter for GUI development in Python
MATLAB
C/C++ Programming
Familiar with NVIDIA Docker Env
Jetson Xavier, Nano, Tx2
Container deployment
Kubernetes Orchestration
Biosignal Acquisitions Platforms
OpenBCI Cyton board
EMG, EEG
Biopac 150m
EMG, EEG, EoG
Mindwave Mobile2
EEG
Shimmer
PPG, GSR
Facial Expressions Recognition
Drowsiness Detection Using Face Images
Pose Estimation using open-pose
Image classification using Pretrained Networks on
ImageNet
Object detection using Yolov3,4
Counting and Tracking using Deep sort
Object detection using SSDMobileNet v2,v3
Point cloud classification using
PointNet
Image Classification using
Federated Learning
MAML for few-shot classification
Driver Profiling /Identification using CAN bus sensors data
Human Activity Recognition Using Wearable sensors data
Anomaly Detection
One-class SVM
Kalman Filtering
Feature engineering
PCA
LDA
Noise removals
Filters
Gaze detection using EoG
Drowsiness detection using EEG + PPG
Silent Speech voicing (speech synthesis) using EMG
Transduction (EMG to MFCC)
Speech Synthesis
WaveNet (MFCC to audio), HiFiGANs, etc.
DeepSpeech(Audio to Text)