Smartphone‐based activity recognition independent of device orientation and placement

Abstract

SUMMARYTraditional activity recognition methods based on accelerometers generally assume that the orientation and placement of sensing devices are fixed. However, the orientation and placement of smartphones, the most widely used sensing devices, usually cannot be controlled in daily lives. As a result, the activity recognition performance would be greatly affected. Aiming at this problem, this paper proposes a smartphone-based activity recognition method, which is independent of device orientation and placement. First, the original 3D acceleration signals are mapped into a uniform reference coordinate system. Then, we apply multidimensional motif discovery techniques for the smartphone-based activity recognition problem. Experimental results show that our method can achieve better performance (with 85.2% precision and 82.9% recall) than other methods under the condition of unfixed orientation and placement.

Sensor‐based activity recognition independent of device placement and orientation

“…Although variety of studies focus on device placement and orientation change, they mainly based on a complete priori information. Guo et al and Chen et al needed information on the final device placement. However, our algorithm is more suitable for random device distortion.…”

“…Studies of device placement and orientation independence attempt to correct the source data by rotation matrix to eliminate the negative effects caused by device deflection . For example, Guo et al set two coordinate systems, ie, the device coordinate system and the global coordinate system, and corrected device orientation. However, this approach is based on prior information that the device orientation is known and do not take random orientation changes into consideration during data collection process.…”

“…Förster et al used GA to extract orientation and location independent features for HAR. In this paper, we use similar ideas to solve the issue on device placement and orientation invariance, so we compare recognition results with the approach of in later section.…”

“…To tackle this issue, some efforts have been made. For example, Guo et al divided the orientation of smartphone into several situations and used the rotation matrix to transform and correct data. Yurtman and Bashan proposed two alternative heuristic orientation‐independent algorithms to remove the impact caused by changes on the sensor orientation.…”

A Travel Route Recommendation System Based on Smart Phones and IoT Environment

“…Meanwhile, current smartphones generally equip a camera and diverse sensors, which could be used to sense multiple dimensional onsite behaviors of tourists so as to explore high-level tourist preferences and recommend personalized tangible travel route. Although some previous researches have investigated the human activity recognition based on smartphone sensors [21,53], there is no study on learning user preferences directly by smartphones. To the best of our knowledge, our proposed system is the first work of leveraging smartphones and IoT environment to recommend tangible travel route within POIs based on onsite travel behavior sensing and mining methods.…”