No-Sweat Detective: No Effort Anomaly Detection for Wi-Fi-Based Localization
Kota Tsubouchi, Kohei Yamamoto (Ristumeikan University) ,and Nobuhiko Nishio (Ristumeikan University)
Tenth International Conference on Indoor Positioning and Indoor Navigation (IPIN2019), 2019/10
データサイエンス (Data Science) その他の取り組み (Misc.)
- Pedestrian dead reckoning (PDR) is easy to introduce because it requires no equipment for the environment. PDR results can provide an atomic physical behavior such as step detection and turning in walking, however providing a flexible response to a user’s daily actions other than walking like sitting, moving in a line or standing is tough. Our research objective is to make PDR more usable in spite of these daily actions by estimating the movement situation using the same sensor information as conventional PDR. We applied a state transition in the movement situation recognition using the transition restrictions existing between the moving situations. A new method for moving context recognition using machine learning with accelerometer and gyroscope feature vectors simultaneous with PDR is proposed herein. The experiments show that, the movement situation recognition and the state transition technique are efficient for the whole dead reckoning performance. The proposed method can also be applied to improve the PDR positioning accuracy.