Human Activity Recognition using Deep Learning and Sensor Fusion
(2018) In Master's Theses in Mathematical Sciences FMAM05 20181Mathematics (Faculty of Engineering)
 Abstract
 The subject of this thesis is human activity recognition in health care. The data set used is the SBHAR data set. It contains accelerometer and gyroscope of 30 different individuals walking, walking upwards, walking downwards, sitting, standing and lying. The research questions is: How can we, using deep learning, understand more about and potentiallly improve Human activity recognition or HAR for assisted ambient living? To answer the question we take aim at three things. The first being a comparison of different deep learning methods and the SVM, to the best classifier in a review article from fall 2017. The results are that all the used supervised methods have> 90% accuracy in ten fold cross validation and display accuracies on par with... (More)
 The subject of this thesis is human activity recognition in health care. The data set used is the SBHAR data set. It contains accelerometer and gyroscope of 30 different individuals walking, walking upwards, walking downwards, sitting, standing and lying. The research questions is: How can we, using deep learning, understand more about and potentiallly improve Human activity recognition or HAR for assisted ambient living? To answer the question we take aim at three things. The first being a comparison of different deep learning methods and the SVM, to the best classifier in a review article from fall 2017. The results are that all the used supervised methods have> 90% accuracy in ten fold cross validation and display accuracies on par with the best classification result in the review article. Unsupervised methods all gave > 90% results for a 3 class problem.
Secondly we aim for possible cost reductions. What neural networks use to distinguish between the different human activity recognition classes might be close to some handcrafted feature, which can replace a larger neural network. To find such patterns we visualized activations in the code of a convolutional autoencoder trying to reconstruct its input for the different walking classes. The latent space representations images were not easily distinguishable from each other. But, further reduction of the code reveal that the walking classes are mapped to two discs and a torus.
Another possible cost reduction is replacing the less battery efficient gyroscope. With a regression network, We were able to reconstruct the gyroscope from the accelerometer with some likeness but without the faster fluctuations typically seen in gyroscope signals.
Thirdly we evaluate two novel approaches, the MLPHMM and SVMMLP. The MLPHMM and SVMMLP are hybrids having one classier generating classifications and then a add on trying to model its errors by incorporating some previous and some future classifications. The SVM MLP hybrid is a combination of a support vector machine generating guesses and a multi layer perceptron modelling the guesses. The MLPHMM hybrid uses a multi layer perceptron and a hidden markov model. The SVMMLP hybrid shows a higher accuracy and lower standard deviation in comparison to only using the SVM. But the MLPHMM hybrid gave worse results than if only using the MLP classier.
The results are then followed by a discussion, were several suggestions for future work can be found regarding applications, sparser models, improvements and new classifiers. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/studentpapers/record/8960055
 author
 Berggren, Klas ^{LU}
 supervisor

 Karl Åström ^{LU}
 Rikard Berthilsson ^{LU}
 organization
 course
 FMAM05 20181
 year
 2018
 type
 H2  Master's Degree (Two Years)
 subject
 publication/series
 Master's Theses in Mathematical Sciences
 report number
 LUTFMA33622018
 ISSN
 14046342
 other publication id
 2018:E62
 language
 English
 id
 8960055
 date added to LUP
 20181107 14:51:07
 date last changed
 20181107 14:51:07
@misc{8960055, abstract = {{The subject of this thesis is human activity recognition in health care. The data set used is the SBHAR data set. It contains accelerometer and gyroscope of 30 different individuals walking, walking upwards, walking downwards, sitting, standing and lying. The research questions is: How can we, using deep learning, understand more about and potentiallly improve Human activity recognition or HAR for assisted ambient living? To answer the question we take aim at three things. The first being a comparison of different deep learning methods and the SVM, to the best classifier in a review article from fall 2017. The results are that all the used supervised methods have> 90% accuracy in ten fold cross validation and display accuracies on par with the best classification result in the review article. Unsupervised methods all gave > 90% results for a 3 class problem. Secondly we aim for possible cost reductions. What neural networks use to distinguish between the different human activity recognition classes might be close to some handcrafted feature, which can replace a larger neural network. To find such patterns we visualized activations in the code of a convolutional autoencoder trying to reconstruct its input for the different walking classes. The latent space representations images were not easily distinguishable from each other. But, further reduction of the code reveal that the walking classes are mapped to two discs and a torus. Another possible cost reduction is replacing the less battery efficient gyroscope. With a regression network, We were able to reconstruct the gyroscope from the accelerometer with some likeness but without the faster fluctuations typically seen in gyroscope signals. Thirdly we evaluate two novel approaches, the MLPHMM and SVMMLP. The MLPHMM and SVMMLP are hybrids having one classier generating classifications and then a add on trying to model its errors by incorporating some previous and some future classifications. The SVM MLP hybrid is a combination of a support vector machine generating guesses and a multi layer perceptron modelling the guesses. The MLPHMM hybrid uses a multi layer perceptron and a hidden markov model. The SVMMLP hybrid shows a higher accuracy and lower standard deviation in comparison to only using the SVM. But the MLPHMM hybrid gave worse results than if only using the MLP classier. The results are then followed by a discussion, were several suggestions for future work can be found regarding applications, sparser models, improvements and new classifiers.}}, author = {{Berggren, Klas}}, issn = {{14046342}}, language = {{eng}}, note = {{Student Paper}}, series = {{Master's Theses in Mathematical Sciences}}, title = {{Human Activity Recognition using Deep Learning and Sensor Fusion}}, year = {{2018}}, }