Activity recognition in a smart home using local feature weighting and variants of nearest-neighbors classifiers

Abstract

Recognition of activities, such as preparing meal or watching TV, performed by a smart home resident, can promote the independent living of elderly in a safe and comfortable environment of their own homes, for an extended period of time. Different activities performed at the same location have commonalities resulting in less inter-class variations; while the same activity performed multiple times, or by multiple residents, varies in its execution resulting in high intra-class variations. We propose a Local Feature Weighting approach (LFW) that assigns weights based on both inter-class and intra-class importance of a feature in an activity. Multiple sensors are deployed at different locations in a smart home to gather information. We exploit the obtained information, such as frequency and duration of activation of sensors, and the total sensors in an activity for feature weighting. The weights for the same features vary among activities, since a feature may have more importance for one activity but less for the other. For the classification, we exploit the two variants of K-Nearest Neighbors (KNN): Evidence Theoretic KNN (ETKNN) and Fuzzy KNN (FKNN). The evaluation of the proposed approach on three datasets, from CASAS smart home project, demonstrates its ability in the correct recognition of activities compared to the existing approaches.

Lost in translation? Conceptions of privacy and independence in the technical development of AI-based AAL

“…Typical sentences in these contexts are e.g. : “[The technology] may help in preserving quality of life of older adults, allowing them to maintain their independence and live longer and safer in their own home” (Mora et al 2018 , p.13), “[it] contributes to elderly independent and more autonomous living” (Bleda et al 2019 , p. 12), or “[it] can promote the independent living of elderly in a safe and comfortable environment of their own homes, for an extended period of time.” (Fahad and Tahir 2020 , p. 1).…”

“…The high significance of independence manifests in the fact that it is explicitly named as crucial goal of AAL in 134 papers (e.g. Fahad and Tahir 2020 ; Guerra et al 2020 ; Tian and Zhang 2020 ). Independence tends to be used as a surrogate or even a synonym for autonomy and/or self-determination.…”

Die Vermessung des Alltags: Die Aktivitäten des täglichen Lebens in der Entwicklung von KI-gestützten Assistenzsystemen

“…z. B. die Studien vonDiraco et al 2017;Eisa/Moreira2 017;D iraco et al 2019;Gochoo et al 2019;Fahad/Tahir 2020;Golestan et al 2020). Mit der Erkennung der Aktivitäten soll ein indirektes Monitoring stattfinden: Anhand der unterschiedlichen Sensordaten soll der allgemeine Zustand der Nutzer:in gemessen und bewertet werden.…”

AtomGID: An Atomic Gesture Identifier for Qualitative Spatial Reasoning

“…Considering that qualitative spatial reasoning has, to the best of our knowledge, been infrequently explored by the research community focusing on Activities of Daily Living (ADLs) recognition, apart from the incorporation of limited location-related features [28], this paper introduces a straightforward yet highly efficient and effective algorithm for extracting spatial information. This algorithm capitalizes on the fuzzy tracking of everyday objects using passive Radio-Frequency Identification (RFID) technology.…”