Modeling interaction in multi-resident activities

Abstract

In this paper we investigate the problem of modeling multi-resident activities. Specifically, we explore different approaches based on Hidden Markov Models (HMMs) to deal with parallel activities and cooperative activities. We propose an HMM-based method, called CL-HMM, where activity labels as well as observation labels of different residents are combined to generate the corresponding sequence of activities as well as the corresponding sequence of observations on which a conventional HMM is applied. We also propose a Linked HMM (LHMM) in which activities of all residents are linked at each time step. We compare these two models to baseline models which are Coupled HMM (CHMM) and Parallel HMM (PHMM). The experimental results show that the proposed models outperform CHMM and PHMM when tested on parallel and cooperative activities.

Human Activities Recognition Based on Neuro-Fuzzy Finite State Machine

“…Datasets representing human activities are often imbalanced where some activities appear much more frequently than others. It is evident that if the dominant activity is recognised with a high level of performance, the overall level of accuracy is high, even if all other activities are not well recognised [39]. Therefore, we did a cross-validation for each activity over the whole model.…”

Exploring Entropy Measurements to Identify Multi-Occupancy in Activities of Daily Living

“…Hence, Human Activity Recognition (HAR) has gained increasing attention in recent years [ 1 , 2 , 3 ]. So far, research related to HAR has devoted particular attention to monitoring and recognizing the human activities of a single occupant in a home environment, in which it is assumed that only one person is present at any given time [ 4 , 5 , 6 , 7 , 8 , 9 , 10 ]. However, living environments are commonly inhabited by more than one individual and/or with pet animals [ 7 , 10 , 11 ].…”

“…Additional challenges exist when dealing with such environments because existing sensors are incapable of distinguishing who has activated them in the absence of any tagging system [ 13 , 14 , 15 ]. Considering the negative connotations and privacy issues associated with wearable tags/sensors, the wearable sensors are not widely accepted by older adults [ 6 , 7 , 8 , 9 ]. It is always a preferred option to use ambient sensors to detect and recognize multi-occupancy in a home environment [ 8 , 16 ].…”

“…The current research acknowledges the challenges of multi-occupancy in HAR [ 5 , 7 , 17 ]. Such challenges are to find suitable models to represent the data association problem (i.e., the identification of the resident) and to find an activity recognition system that captures different interactions among residents [ 5 , 7 ].…”

“…The current research acknowledges the challenges of multi-occupancy in HAR [ 5 , 7 , 17 ]. Such challenges are to find suitable models to represent the data association problem (i.e., the identification of the resident) and to find an activity recognition system that captures different interactions among residents [ 5 , 7 ]. Previous studies report that detecting and identifying a visitor in a home environment based on only binary sensors is a primary challenge as binary sensors are not able to provide any information about the personal identity of who triggered the sensor [ 10 , 11 ].…”