- Module-1: Digital Health: Introduction
Pre-requisites: Understanding of Digital Technology- Need, case studies, basics – mHealth and eHealth, Impact
- Informatics: Health Level Seven (HL7), Integrating the Healthcare Enterprise (IHE), Vendor Neutral Archives (VNAs)
- Open source/data/innovation – opportunities
- IT infrastructure (IoT/Cloud computing)
- Module-2: Wearable Devices and Physiological Signal Processing
Pre-requisites: Basics of Signals & Systems, Basics of Fourier Transforms and Z-Transforms, Basics of Physiology.- Signal Processing: Sampling, Basic Filters, Decimation, Interpolation, STFT, Wavelets
- Physiology: ECG Signal Acquisition (Electrical activity of heart, chest leads/montage, action potential in pacemaker and other regions; action potential relation to ECG Waveform; Reading ECG); EEG Signal Acquisition (Neural activity in the brain, Action potential, post-synaptic potential, Signal Propagation in the brain, EEG montage, EEG Signal Acquisition); EEG and ECG data processing
- Wearable Sensors for health monitoring: Accelerometers (data acquisition and interpretation), glucose sensing (acquisition methods and comparison), Wearable ECG & EEG based on dry electrodes
- Speech and audio signal processing: From signal capture to data pre-processing and feature modelling.
- Module-3: Machine Learning Basics for Real-world
Pre-requisites: Basic of Probability and Linear Algebra: Bayes Theorem, Random Variables, Expectation, Variance, Matrices, Inverse, Eigenvalues and Eigenvectors- Basic Mathematics for ML, What is Data and Model? Machine Learning Workflow and Applications
- Introduction to real-world signals – text, speech, image, video; Feature extraction and front-end signal processing – information-rich representations, robustness to noise and artifacts
- Learning as optimization, Linear Regression, Regularization and Logistic Regression
- Basics of pattern recognition, Generative modelling – Gaussian and mixture Gaussian models
- Machine Learning for physiological signal processing. Time series modelling
- Module-4: Deep Learning in Digital Health
Pre-requisites: Basic Machine Learning that is part of Module 3- Deep Learning: Basics, MLPs, Back propagation, CNNs
- Deep Learning for physiological signal processing. Recurrent neural models
- Discussion on Depth Versus Width. Practical considerations in Deep Learning. Avoiding Overfitting- Regularization, Dropout. Convolutional Neural Networks. Recurrent Neural Networks. Forward and Backward propagation. Various Architectures for sequence to sequence and sequence to vector mapping.
- Applications of Deep, Convolutional and Recurrent models in healthcare. (Instructor: SG)
- Nature Language Processing: LSTMs, Language Models, Knowledge Graphs, Q&A (Demo)
- Module-5: Deep Learning in Imaging/Vision
Pre-requisites: Modules-1,2,3, and 4- Medical Imaging Modalities: Introduction, Protocols, Work Flows, Applications
- Medical Image Analysis: Basics, Imaging Physics-Based Methods, and Need for Deep Learning & Neuroimaging: Introduction, Challenges
- Vision – Deep learning: Loss function, Optimization, CNNs, Training Convolutional Neural Networks, Object Detection, Segmentation
- Deep Learning models: AlexNet, VGG, GoogleNet, ResNet, RNN/LSTM
Get Appointment
- contact@wellinor.com
- +(123)-456-7890