healthDataScience / Deep Learning Har
Convolutional and LSTM networks to classify human activity
Stars: ✭ 395
Labels
Projects that are alternatives of or similar to Deep Learning Har
Pattern classification
A collection of tutorials and examples for solving and understanding machine learning and pattern classification tasks
Stars: ✭ 3,880 (+882.28%)
Mutual labels: jupyter-notebook
Comma2k19
A driving dataset for the development and validation of fused pose estimators and mapping algorithms
Stars: ✭ 391 (-1.01%)
Mutual labels: jupyter-notebook
Workshopscipy
A workshop for scientific computing in Python. ( December 2017 )
Stars: ✭ 391 (-1.01%)
Mutual labels: jupyter-notebook
Zhihu Text Classification
[2017知乎看山杯 多标签 文本分类] ye组(第六名) 解题方案
Stars: ✭ 392 (-0.76%)
Mutual labels: jupyter-notebook
Production Data Science
Production Data Science: a workflow for collaborative data science aimed at production
Stars: ✭ 388 (-1.77%)
Mutual labels: jupyter-notebook
Megvii Pku Dl Course
Homepage for the joint course of Megvii Inc. and Peking University on Deep Learning.
Stars: ✭ 393 (-0.51%)
Mutual labels: jupyter-notebook
Open source demos
A collection of demos showcasing automated feature engineering and machine learning in diverse use cases
Stars: ✭ 391 (-1.01%)
Mutual labels: jupyter-notebook
Deepnetsforeo
Deep networks for Earth Observation
Stars: ✭ 393 (-0.51%)
Mutual labels: jupyter-notebook
Graph transformer networks
Graph Transformer Networks (Authors' PyTorch implementation for the NeurIPS 19 paper)
Stars: ✭ 387 (-2.03%)
Mutual labels: jupyter-notebook
User Machine Learning Tutorial
useR! 2016 Tutorial: Machine Learning Algorithmic Deep Dive http://user2016.org/tutorials/10.html
Stars: ✭ 393 (-0.51%)
Mutual labels: jupyter-notebook
Learning Deep Learning
Paper reading notes on Deep Learning and Machine Learning
Stars: ✭ 388 (-1.77%)
Mutual labels: jupyter-notebook
Nmtpytorch
Sequence-to-Sequence Framework in PyTorch
Stars: ✭ 392 (-0.76%)
Mutual labels: jupyter-notebook
Ephemera Miscellany
Ephemera and other documentation associated with the 1337list project.
Stars: ✭ 395 (+0%)
Mutual labels: jupyter-notebook
Motion Cosegmentation
Reference code for "Motion-supervised Co-Part Segmentation" paper
Stars: ✭ 393 (-0.51%)
Mutual labels: jupyter-notebook
Examples
Example deep learning projects that use wandb's features.
Stars: ✭ 391 (-1.01%)
Mutual labels: jupyter-notebook
Human Activity Recognition (HAR)
In this part of the repo, we discuss the human activity recognition problem using deep learning algorithms and compare the results with standard machine learning algorithms that use engineered features.
The data can be downloaded from the UCI repository.
Also see G.Chevalier's repo and A. Saeed's blog where I have got lots of inspiration.
Contents
The utils folder contains the code for reading and processing the data into a tensor form. The generated tensors
have the dimensions
(batch, seq_len, n_channels)
where batch is the number of training examples in each batch, seq_len is the number of steps in the time series (128) and
n_channels is the number of channels where observations are made (9).
The aim is to clasify the activities correctly, which are
1 WALKING
2 WALKING_UPSTAIRS
3 WALKING_DOWNSTAIRS
4 SITTING
5 STANDING
6 LAYING
Below are the architectures used for training
| Notebook | Description |
|---|---|
| explore_data | Data exploration |
| HAR-LSTM | LSTM network |
| HAR-CNN | Convolutional neural network(CNN) |
| HAR-CNN-LSTM | CNN + LSTM hybrid |
| HAR-CNN-Inception | CNN with inception module |
Results
| Method | Test accuracy |
|---|---|
| CNN | 93% |
| LSTM | 88% |
| CNN+LSTM | 88% |
| CNN+Inception | 89% |
| Xgboost | 96% |
CNN architecture
LSTM architecture
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].