Falling Angel - a Wrist Worn Fall Detection System Using K-NN AlgorithmVisa övriga samt affilieringar
2016 (Engelska)Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]
A wrist worn fall detection system has been developed where the accelerometer data from an angel sensor is analyzed by a two-layered algorithm in an android phone. Here, the first layer uses a threshold to find potential falls and if the thresholds are met, then in the second layer a machine learning i.e., k-Nearest Neighbor (k-NN) algorithm analyses the data to differentiate it from Activities of Daily Living (ADL) in order to filter out false positives. The final result of this project using the k-NN algorithm provides a classification sensitivity of 96.4%. Here, the acquired sensitivity is 88.1% for the fall detection and the specificity for ADL is 98.1%.
Ort, förlag, år, upplaga, sidor
2016. Vol. 187, s. 148-151
Serie
Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST, ISSN 1867-8211
Nyckelord [en]
Fall Detection, Angel Device, K-Nearest Neighbor
Nationell ämneskategori
Elektroteknik och elektronik
Identifikatorer
URN: urn:nbn:se:mdh:diva-33803DOI: 10.1007/978-3-319-51234-1_25ISI: 000428954100025Scopus ID: 2-s2.0-85011312016ISBN: 9783319512334 (tryckt)OAI: oai:DiVA.org:mdh-33803DiVA, id: diva2:1048564
Konferens
The 3rd EAI International Conference on IoT Technologies for HealthCare HealthyIoT'16, 18 Oct 2016, Västerås, Sweden
Projekt
SafeDriver: A Real Time Driver's State Monitoring and Prediction System2016-11-212016-11-212018-07-27Bibliografiskt granskad