Human activity recognition from accelerometer data using Convolutional Neural Network

Lee, Song-Mi; Yoon, Sang Min; Cho, Heeryon

doi:10.1109/bigcomp.2017.7881728

Cited by 140 publications

(68 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different positions of the mobile phone will cause the direction of the axis to change. In [32] and [33], the authors both eliminate the possible rotational interference by synthesizing the acceleration without considering the direction of the axis, which partly takes into account the relations between the three axes. By converting the time-series signal of the sensor into an active image containing the hidden relations between axes, the recognition accuracy of the model is obviously improved [14].…”

Section: Related Workmentioning

confidence: 99%

The Effect of Axis-Wise Triaxial Acceleration Data Fusion in CNN-Based Human Activity Recognition

Han

Luo

et al. 2020

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

The triaxial accelerometer is one of the most important sensors for human activity recognition (HAR). It has been observed that the relations between the axes of a triaxial accelerometer plays a significant role in improving the accuracy of activity recognition. However, the existing research rarely focuses on these relations, but rather on the fusion of multiple sensors. In this paper, we propose a data fusion-based convolutional neural network (CNN) approach to effectively use the relations between the axes. We design a single-channel data fusion method and multichannel data fusion method in consideration of the diversified formats of sensor data. After obtaining the fused data, a CNN is used to extract the features and perform classification. The experiments show that the proposed approach has an advantage over the CNN in accuracy. Moreover, the single-channel model achieves an accuracy of 98.83% with the WISDM dataset, which is higher than that of state-of-the-art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

The Effect of Axis-Wise Triaxial Acceleration Data Fusion in CNN-Based Human Activity Recognition

Han

Luo

et al. 2020

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…Differently, the authors of [44,82,91] recorded acceleration measurements from only one device, which is placed on the waist. The authors of [52,75,79] proposed using the magnitude of the acceleration vector from the three components x, y, and z. The authors of [86] used the logarithm magnitude of a two-dimensional Discrete Fourier Transform of IMU signals.…”

Section: Data Representationmentioning

confidence: 99%

“…The authors of [77] also used a small network with one temporal convolutional layer, one pooling and a MLP. The authors of [79] used a small tCNN with one conv layer, one pooling, one FC and a softmax layer. The authors of [83] used temporal convolutional networks.…”

Section: Deep Learningmentioning

confidence: 99%

See 1 more Smart Citation

Human Activity Recognition for Production and Logistics—A Systematic Literature Review

et al. 2019

View full text Add to dashboard Cite

This contribution provides a systematic literature review of Human Activity Recognition for Production and Logistics. An initial list of 1243 publications that complies with predefined Inclusion Criteria was surveyed by three reviewers. Fifty-two publications that comply with the Content Criteria were analysed regarding the observed activities, sensor attachment, utilised datasets, sensor technology and the applied methods of HAR. This review is focused on applications that use marker-based Motion Capturing or Inertial Measurement Units. The analysed methods can be deployed in industrial application of Production and Logistics or transferred from related domains into this field. The findings provide an overview of the specifications of state-of-the-art HAR approaches, statistical pattern recognition and deep architectures and they outline a future road map for further research from a practitioner's perspective.

show abstract

“…The size and type of this window varies depending on the type of input signal as well as the parameter to be identified. Prior to determining the window length for the analysis, two of the common windowing methods for activity monitoring were considered: the sliding windows and overlapping windows [312,313]. For the first method, data is grouped into windows of a specific size with no overlap or gap between each window, while in the second method a degree of overlap is permitted between consecutive segments.…”

Section: Optimal Window Calculationsmentioning

confidence: 99%

Using plantar pressure for free-living posture recognition and sedentary behaviour monitoring

Grajeda¹

View full text Add to dashboard Cite

They all have been extremely helpful and provided me invaluable guidance throughout my PhD project with their knowledge and expertise. I would also like to thank the Institute of Sports and Research, the Physical Activity and Public Health Research Group, both research staff and fellow PhD students, for their kind advice and assistance. I am also very grateful to both my friends and partner who not only helped me sail through difficult hard times but also helped me transform the process of working on this PhD into an amazing and joyful experience. Finally, my love and deep gratitude to my family for their sacrifice and unwavering support despite the distance. Without the unconditional love and encouragement of my parents the completion of this project would never have come to fruition.

show abstract

Human activity recognition from accelerometer data using Convolutional Neural Network

Cited by 140 publications

References 5 publications

The Effect of Axis-Wise Triaxial Acceleration Data Fusion in CNN-Based Human Activity Recognition

The Effect of Axis-Wise Triaxial Acceleration Data Fusion in CNN-Based Human Activity Recognition

Human Activity Recognition for Production and Logistics—A Systematic Literature Review

Using plantar pressure for free-living posture recognition and sedentary behaviour monitoring

Contact Info

Product

Resources

About