Real-time human activity recognition from accelerometer data using Convolutional Neural Networks

By Andrey D. Ignatov. Applied Soft Computing, 2018

745 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Surgery

View Paper: https://www.semanticscholar.org/paper/07642da3907fc400d7c5894e6885ee086ea88036

How researchers see this paper

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

In Biomedical Engineering

1. Hossein Rahmani
2. Qiuhong Ke
3. Jun Liu
4. Zehua Sun
5. Sakorn Mekruksavanich
6. Anuchit Jitpattanakul
7. Thinagaran Perumal
8. S. Padmavathi

In Computer Vision and Pattern Recognition

1. Jun Liu
2. Hossein Rahmani
3. Qiuhong Ke
4. Zehua Sun
5. Luc Van Gool
6. Radu Timofte
7. G. Wang
8. Ming-Hsuan Yang

In Surgery

1. Sakorn Mekruksavanich
2. Anuchit Jitpattanakul
3. Jun Liu
4. Qiuhong Ke
5. Hossein Rahmani
6. Zehua Sun

Citations in the corpus

• Human Activity Recognition With Smartphone and Wearable Sensors Using Deep Learning Techniques: A Review (2021, background): “Ignatov [34] has proposed a CNN for the local feature extraction along with statistical features such as mean, variance, sum of absolute values and histogram of each input to preserve information about global features of raw signals.”
• 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.”
• LSTM Networks Using Smartphone Data for Sensor-Based Human Activity Recognition in Smart Homes (2021, methodology): “These DL approaches are now being used to construct a resilient smartphone-based HAR [23,24].”
• A survey on wearable sensor modality centred human activity recognition in health care (2019, background): “The value for k is common to fix to 5 or 10, since these values have been shown empirically yielding a model performance estimate with low bias and a modest variance (James, et al., 2013, Biswas, et al., 2014, Ignatov, 2018).”
• A Survey of Deep Learning and Its Applications: A New Paradigm to Machine Learning (2019, background): “Ignatov [22] presented an online human activity recognition and classification system based on the accelerometer.”
• Deep learning for time series classification: a review (2018, background): “In fact, most of the deep learning approaches for TSC with some hand engineered features are present in human activity recognition tasks (Ignatov, 2018).”
• Human Activity Recognition using Inertial, Physiological and Environmental Sensors: A Comprehensive Survey (2020, neutral): “[99], [100], [104], [106], [108], [112], [119], [120], [125], [126], [141], [143], [146], [147], [149], [150], [153], [154], FIGURE 9.”
• AI Benchmark: Running Deep Neural Networks on Android Smartphones (2018, background): “ completion [20,21], sentence sentiment analysis [22,23] or interactive chatbots [24]. A separte group deals with on-line sensor data processing for human activity recognition from accelerometer data [25,26], gesture recognition [27] or sleep monitoring [28]. Several other deep learning problems on ”
• Multi-head CNN-RNN for multi-time series anomaly detection: An industrial case study (2019, neutral): “Unlike other CNN’s for time series classification [78, 32, 79], no sub-sampling layer is used after the convolution.”