A Comparative Study on Sensor Displacement Effect on Realistic Sensor Displacement Benchmark Dataset

Punchoojit, Lumpapun; Hongwarittorrn, Nuttanont

doi:10.1007/978-3-319-19024-2_10

Cited by 3 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This dataset has permitted several HAR works focused on different aspects. One interesting aspect has been the degradation suffered on the HAR accuracy depending on the sensor placement or the number of displacements (wrong placements) [23][24][25]. Other analyzed aspects have been the window size [24,26], and the detection of activities transitions [27].…”

Section: Introductionmentioning

confidence: 99%

Feature extraction for robust physical activity recognition

Zhu

San-Segundo

Pardo

2017

Hum. Cent. Comput. Inf. Sci.

View full text Add to dashboard Cite

IntroductionWith information obtained from sensors, computer based system can make more intelligent actions by adapting their behavior to the context conditions. These days, thanks to the development of multi-sensor networks, related research areas have increased rapidly. Among those areas, Human Activity Recognition (HAR) based on wearable sensors (accelerometer, gyroscope, magnetometer, etc.) has recently received lots of attention due to its large number of promising applications. One of the most interesting HAR applications is ubiquitous identification of physical activity. As we know, over-weighting is a general human problem as a result of a physical inactivity habit. A Lancet publication [1] estimates that physical inactivity causes 9% of all premature deaths worldwide. By monitoring physical activity, we can help people to learn the calories they consumed or gained during the day in a much more precise way and Abstract This paper presents the development of a Human Activity Recognition (HAR) system that uses a network of nine inertial measurement units situated in different body parts. Every unit provides 3D (3-dimension) acceleration, 3D angular velocity, 3D magnetic field orientation, and 4D quaternions. This system identifies 33 different physical activities (walking, running, cycling, lateral elevation of arms, etc.). The system is composed of two main modules: a feature extractor for obtaining the most relevant characteristics from the inertial signals every second, and a machine learning algorithm for classifying between the different activities. This paper focuses on the feature extractor module, evaluating several types of features and proposing different normalization approaches. This paper also analyses the performance of every sensor included in the inertial measurement units. The main experiments have been done using a public available dataset named REALDISP Activity Recognition dataset. This dataset includes recordings from 17 subjects performing 33 different activities in three different scenarios. Final results demonstrate that the proposed HAR system significantly improves the classification accuracy compared to previous works on this dataset. For the best configuration, the system accuracy is 99.1%. This system has been also evaluated with the OPPORTUNITY dataset obtaining competitive results.

show abstract