Human activity recognition with inertial sensors using a deep learning approach

Zebin, Tahmina; Scully, Patricia; Ozanyan, Krikor B.

doi:10.1109/icsens.2016.7808590

Cited by 122 publications

(75 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…3) Weight-sharing. Weight sharing (Zebin et al, 2016;Sathyanarayana et al, 2016) is an efficient method to speed up the training process on a new task. (Zeng et al, 2014) utilized a relaxed partial weight sharing technique since the signal appeared in different units may behave differently.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

Deep learning for sensor-based activity recognition: A survey

Wang

Chen

Hao

et al. 2019

Pattern Recognition Letters

1,555

927

View full text Add to dashboard Cite

Research Highlights (Required)To create your highlights, please type the highlights against each \item command.It should be short collection of bullet points that convey the core findings of the article. It should include 3 to 5 bullet points (maximum 85 characters, including spaces, per bullet point.)• We survey deep learning based HAR in sensor modality, deep model, and application.• We comprehensively discuss the insights of deep learning models for HAR tasks.• We extensively investigate why deep learning can improve the performance of HAR.• We also summarize the public HAR datasets frequently used for research purpose.• We present some grand challenges and feasible solutions for deep learning based HAR. ABSTRACTSensor-based activity recognition seeks the profound high-level knowledge about human activities from multitudes of low-level sensor readings. Conventional pattern recognition approaches have made tremendous progress in the past years. However, those methods often heavily rely on heuristic hand-crafted feature extraction, which could hinder their generalization performance. Additionally, existing methods are undermined for unsupervised and incremental learning tasks. Recently, the recent advancement of deep learning makes it possible to perform automatic high-level feature extraction thus achieves promising performance in many areas. Since then, deep learning based methods have been widely adopted for the sensor-based activity recognition tasks. This paper surveys the recent advance of deep learning based sensor-based activity recognition. We summarize existing literature from three aspects: sensor modality, deep model, and application. We also present detailed insights on existing work and propose grand challenges for future research.

show abstract

Section: Convolutional Neural Networkmentioning

confidence: 99%

Deep learning for sensor-based activity recognition: A survey

Wang

Chen

Hao

et al. 2019

Pattern Recognition Letters

1,555

927

View full text Add to dashboard Cite

show abstract

“…Their proposed model was tested on skin conductance and blood volume pulse signals. Recent studies show the advantageous of applying CNN on accelerometer signals for human activity recognition [48,49,50].…”

Section: Discussionmentioning

confidence: 99%

Deep learning for automatic stereotypical motor movement detection using wearable sensors in autism spectrum disorders

et al. 2018

View full text Add to dashboard Cite

Autism Spectrum Disorders are associated with atypical movements, of which stereotypical motor movements (SMMs) interfere with learning and social interaction. The automatic SMM detection using inertial measurement units (IMU) remains complex due to the strong intra and inter-subject variability, especially when handcrafted features are extracted from the signal. We propose a new application of the deep learning to facilitate automatic SMM detection using multiaxis IMUs. We use a convolutional neural network (CNN) to learn a discriminative feature space from raw data. We show how the CNN can be used for parameter transfer learning to enhance the detection rate on longitudinal data. We also combine the long short-term memory (LSTM) with CNN to model the temporal patterns in a sequence of multi-axis signals. Further, we employ ensemble learning to combine multiple LSTM learners into a more robust SMM detector. Our results show that: 1) feature learning outperforms handcrafted features; 2) parameter transfer learning is beneficial in longitudinal settings; 3) using LSTM to learn the temporal dynamic of signals enhances the detection rate especially for skewed training data; 4) an ensemble of LSTMs provides more accurate and stable detectors. These findings provide a significant step toward accurate SMM detection in real-time scenarios.

show abstract

“…In their works, they decrease the computation cost by limiting the connections from the input nodes in order to extract features efficiently through fewer nodes and levels. The works of Tahmina Zebin et al show that the performance is noticeably enhanced when the third convolution layer is added [1].…”

Section: Related Workmentioning

confidence: 99%

“…Smartphones are usually embedded with various sensors gathering data for smart security, user authentication, intelligent health monitoring, human activity recognition (HAR) and so on. HAR has been widely used in intelligent wearable device, human computer interaction, athletic training and competition, military, healthcare domains such as health assisted diagnosis and treatment, cognitive disorder recognition systems, elder care support, rehabilitation assistance and so on [1].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Smartphone-Based Human Activity Recognition Using CNN in Frequency Domain

Jiang

et al. 2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Human activity recognition (HAR) based on smartphone sensors provides an efficient way for studying the connection between human physical activities and health issues. In this paper, three feature sets are involved, including tri-axial angular velocity data collected from gyroscope sensor, triaxial total acceleration data collected from accelerometer sensor, and the estimated tri-axial body acceleration data. The FFT components of the three feature sets are used to divide activities into six types like walking, walking upstairs, walking downstairs, sitting, standing and lying. Two kinds of CNN architectures are designed for HAR. The one is Architecture A in which only one set of features is combined at the first convolution layer; and the other one is Architecture B in which two sets of the features are combined at the first convolution layer. The validation data set is used to automatically determine the iteration number during the training process. It is shown that the performance of Architecture B is better compared to Architecture A. And the Architecture B is further improved by varying the number of the features maps at each convolution layer and the one producing the best result is selected. Compared with five other HAR methods using CNN, the proposed method could achieve a better recognition accuracy of 97.5% for a UCI HAR dataset.

show abstract

Human activity recognition with inertial sensors using a deep learning approach

Cited by 122 publications

References 14 publications

Deep learning for sensor-based activity recognition: A survey

Deep learning for sensor-based activity recognition: A survey

Deep learning for automatic stereotypical motor movement detection using wearable sensors in autism spectrum disorders

Smartphone-Based Human Activity Recognition Using CNN in Frequency Domain

Contact Info

Product

Resources

About