Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition
Abstract
Human activity recognition (HAR) tasks have traditionally been solved using engineered features obtained by heuristic processes. Current research suggests that deep convolutional neural networks are suited to automate feature extraction from raw sensor inputs. However, human activities are made of complex sequences of motor movements, and capturing this temporal dynamics is fundamental for successful HAR. Based on the recent success of recurrent neural networks for time series domains, we propose a generic deep framework for activity recognition based on convolutional and LSTM recurrent units, which: (i) is suitable for multimodal wearable sensors; (ii) can perform sensor fusion naturally; (iii) does not require expert knowledge in designing features; and (iv) explicitly models the temporal dynamics of feature activations. We evaluate our framework on two datasets, one of which has been used in a public activity recognition challenge. Our results show that our framework outperforms competing deep non-recurrent networks on the challenge dataset by 4% on average; outperforming some of the previous reported results by up to 9%. Our results show that the framework can be applied to homogeneous sensor modalities, but can also fuse m...Continue Reading
References
Citations
Shoulder physiotherapy exercise recognition: machine learning the inertial signals from a smartwatch
Methods Mentioned
Software Mentioned
Related Concepts
Related Feeds
Cell Checkpoints & Regulators
Cell cycle checkpoints are a series of complex checkpoint mechanisms that detect DNA abnormalities and ensure that DNA replication and repair are complete before cell division. They are primarily regulated by cyclins, cyclin-dependent kinases, and the anaphase-promoting complex/cyclosome. Here is the latest research.