Hacker News new | past | comments | ask | show | jobs | submit login
LSTM for Human Activity Recognition (github.com/guillaume-chevalier)
88 points by GChevalier on Nov 27, 2016 | hide | past | favorite | 7 comments

So, did the LSTM find out what the human was doing?

Why haven't any HAR's become commercially popular?

Activity trackers like Fitbit can do this to some extent

No gyro, not enough information.

I also tried my code without the gyro, and incredibly, the accuracy is still pretty high (86.90% rather than 90.77%).

Have you tried your classifier with a different accelerometer dataset? That will be a good test of generalization.

I am co-writing a paper with a Ph.D. student and he is currently working on trying with other datasets. We are also trying different architectures, combining multiple LSTMs (stacked, residual connections + batch normalization, bidirectional LSTMs, and on)

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact