Convolutional Neural Networks for human activity recognition using mobile sensors

By Mingzhi Zeng, Le T. Nguyen, Bo Yu, O. Mengshoel, Jiang Zhu, Pang Wu, Joy Ying Zhang. International Conference on Mobile Computing, Applications and Services, 2014

898 citations recorded by the source corpus.

A variety of real-life mobile sensing applications are becoming available, especially in the life-logging, fitness tracking and health monitoring domains. These applications use mobile sensors embedded in smart phones to recognize human activities in order to get a better understanding of human behavior. While progress has been made, human activity recognition remains a challenging task. This is partly due to the broad range of human activities as well as the rich variation in how a given activity can be performed. Using features that clearly separate between activities is crucial. In this paper, we propose an approach to automatically extract discriminative features for activity recognition. Specifically, we develop a method based on Convolutional Neural Networks (CNN), which can capture local dependency and scale invariance of a signal as it has been shown in speech recognition and image recognition domains. In addition, a modified weight sharing technique, called partial weight sharing, is proposed and applied to accelerometer signals to get further improvements. The experimental results on three public datasets, Skoda (assembly line activities), Opportunity (activities in kitchen), Actitracker (jogging, walking, etc.), indicate that our novel CNN-based approach is practical and achieves higher accuracy than existing state-of-the-art methods.

Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/8674a529943dec8eefd539517b73a513a5dc5a54

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Scaling Human Activity Recognition via Deep Learning-based Domain Adaptation (2018, background): “[16], [17] proposed convolutional neural network (CNN) based models”
Deep Learning for Sensor-based Human Activity Recognition (2020, methodology): “el" in CNNs, so we use the term "axis" instead in this paper. A commonly used AF strategy is to design a specific neural network for each univariate time series of each sensing channel [176, 191]. The information representations from all channels are concatenated at last for input int”
Human Action Recognition From Various Data Modalities: A Review (2020, methodology): “In [14], [271], [272], [273], the tri-axial acceleration data was fed to different CNN architectures for HAR.”
Human Activity Recognition using Inertial, Physiological and Environmental Sensors: A Comprehensive Survey (2020, background): “ing in an increase in recognition accuracy [5], [7].”
Deep Learning in Mobile and Wireless Networking: A Survey (2018, methodology): “[203] Activity recognition Cloud-based CNN, RBM Almaslukh et al.”
Learning Human Identity From Motion Patterns (2015, background): “e learning from accelerometer data, and [5], which proposed a data-adaptive sparse coding framework. Convolutional networks have been explored in the context of gesture and activity recognition [11], [34]. Lefebvre et al. [19] applied a bidirectional LSTM network to a problem of 14-class gesture cla”
Towards Environment Independent Device Free Human Activity Recognition (2018, methodology): “We employ CNNs to extract activity features, which are widely used in the human activity recognition task [58].”
Deep Learning for Health Informatics (2017, methodology): “[92] compared the performance of a CNN based method on three public human activity recognition datasets and found that their deep learning approach can obtain better overall classification accuracy across different human activities as the method is more generalizable.”
Deep Convolutional Neural Networks on Multichannel Time Series for Human Activity Recognition (2015, methodology): “The most related work is [Zeng et al., 2014], in which a shallow CNN is used and the HAR problem is restricted to the accelerometer data.”
Activity recognition in beach volleyball using a Deep Convolutional Neural Network (2017, positive): “Zeng et al. (2014) demonstrated the use of DCNNs for human activity recognition from tri-axial accelerometers.”
Deep Learning for Sensor-based Activity Recognition: A Survey (2017, methodology): “For multi-modal signals, it is better to use CNN since (Bhattacharya and Lane, 2016) Body-worn, ambiemt RBM Gesture, ADL, transportation Self, D01 (Chen and Xue, 2015) Body-worn CNN ADL Self (Chen et al., 2016b) Body-worn CNN ADL D06 (Edel and K¨oppe, 2016) Body-worn RNN ADL D01, D04, Self (Fang and”
Materials that couple sensing, actuation, computation, and communication (2015, background): “In [178], the authors note that the RBM approach does not capture local dependencies in the time series signal.”
BAT: Deep Learning Methods on Network Intrusion Detection Using NSL-KDD Dataset (2020, methodology): “In this paper, we use the Back Propagation Through Time (BPTT) algorithm to obtain the derivatives of the objective function with respect to all the weights, and minimize the objective function by stochastic gradient descent.”
IoT Wearable Sensor and Deep Learning: An Integrated Approach for Personalized Human Activity Recognition in a Smart Home Environment (2019, methodology): “Also in [29], the HAR task is carried out by convolutional neural network (CNN) that automatically extract human activ-”
Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition (2016, methodology): “, a sensor signal), often a 1D kernel is used in a temporal convolution [23].”