Deep Neural Networks for Sensor-Based Human Activity Recognition Using Selective Kernel Convolution

Gao, Wenbin; Zhang, Lei; Huang, Wenbo; Min, Fuhong; He, Jun; Song, Aiguo

doi:10.1109/tim.2021.3102735

Cited by 53 publications

(34 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To discover the relationship between the number of layers, the kernel size, and the complexity level of the tasks, we picked and summarized several typical studies in Table 2. A majority of the CNNs consist of five to nine layers [23,63,64,113,114,[165][166][167][168], usually including two to three convolutional layers, two to three max-pooling layers, followed by one to two fully connected layers before feeding the feature representation into the output layer (softmax layer in most cases). Dong et al [169] demonstrated performance improvements by leveraging both handcrafted time and frequency domain features along with features generated from a CNN, called HAR-Net, to classify six locomotion activities using accelerometer and gyroscope signals from a smartphone.…”

Section: Convolutional Neural Network (Cnn)mentioning

confidence: 99%

Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances

Zhang

et al. 2022

Sensors

216

View full text Add to dashboard Cite

Mobile and wearable devices have enabled numerous applications, including activity tracking, wellness monitoring, and human–computer interaction, that measure and improve our daily lives. Many of these applications are made possible by leveraging the rich collection of low-power sensors found in many mobile and wearable devices to perform human activity recognition (HAR). Recently, deep learning has greatly pushed the boundaries of HAR on mobile and wearable devices. This paper systematically categorizes and summarizes existing work that introduces deep learning methods for wearables-based HAR and provides a comprehensive analysis of the current advancements, developing trends, and major challenges. We also present cutting-edge frontiers and future directions for deep learning-based HAR.

show abstract

Section: Convolutional Neural Network (Cnn)mentioning

confidence: 99%

Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances

Zhang

et al. 2022

Sensors

216

View full text Add to dashboard Cite

show abstract

“…Gao et al [27] introduced a new approach-attention for learning multiscale features among multiple kernels of 1D convolution layers in HAR issues. In a similar way, the signals were preprocessed to zero mean and one standard deviation, but their focus was on using special 1D convolution layers for the prediction of one label for the entire time series (window).…”

Section: Introductionmentioning

confidence: 99%

Wearable Sensor-Based Human Activity Recognition with Transformer Model

Ľuptáková

Kubovčík

Pospı́chal

2022

Sensors

View full text Add to dashboard Cite

Computing devices that can recognize various human activities or movements can be used to assist people in healthcare, sports, or human–robot interaction. Readily available data for this purpose can be obtained from the accelerometer and the gyroscope built into everyday smartphones. Effective classification of real-time activity data is, therefore, actively pursued using various machine learning methods. In this study, the transformer model, a deep learning neural network model developed primarily for the natural language processing and vision tasks, was adapted for a time-series analysis of motion signals. The self-attention mechanism inherent in the transformer, which expresses individual dependencies between signal values within a time series, can match the performance of state-of-the-art convolutional neural networks with long short-term memory. The performance of the proposed adapted transformer method was tested on the largest available public dataset of smartphone motion sensor data covering a wide range of activities, and obtained an average identification accuracy of 99.2% as compared with 89.67% achieved on the same data by a conventional machine learning method. The results suggest the expected future relevance of the transformer model for human activity recognition.

show abstract

“…The paper [4] introduced a new approach -attention for learning multiscale features among multiple kernels of 1D convolution layers in HAR issues. In a similar way, the signals were preprocessed to 0 mean and 1 standard deviation, but the focus was on using special 1D convolution layers for the prediction of one label for the entire time series (window).…”

Section: Introductionmentioning

confidence: 99%

Wearable Sensor Based Human Activity Recognition with Transformer

Ľuptáková¹,

Kubovčík²,

Pospı́chal³

2022

Preprint

View full text Add to dashboard Cite

This paper describes the successful application of the Transformer model used in the natural language processing and vision tasks as a means of processing the time series of signals from gyroscope and accelerometer sensors for the classification of human activities. The Transformer model is based on deep neural networks with many layers which can generalize well on signals. All measured signals come from a smartphone placed in a waist bag. Activity prediction is sequence-to-sequence, each time step of the signal is assigned a designation of the performed activity. Emphasis is placed on attention mechanisms, which express individual dependencies between signal values within a time series. In comparison with another recent result, the recognition precision was improved from 89.67 percent to 99.2 percent. The transformer model should in the future be included among the top options in machine learning methods for human activity recognition.

show abstract

Deep Neural Networks for Sensor-Based Human Activity Recognition Using Selective Kernel Convolution

Cited by 53 publications

References 37 publications

Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances

Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances

Wearable Sensor-Based Human Activity Recognition with Transformer Model

Wearable Sensor Based Human Activity Recognition with Transformer

Contact Info

Product

Resources

About