Multi-resident type recognition based on ambient sensors activity

Abstract

With the development of sensing and intelligent technologies, ambient sensor-based activity recognition is attracting more attention for a wide range of applications. One of the technology challenges is the recognition of the activity performer in a multi-occupancy scenario. This paper proposes a multilabel Markov Logic Network classification method to recognize resident types based on their activity habits and preference. The activity preference mainly includes time sequence preference, duration and period preference, and the location preference of a basic entity or action events. According to the resident type (gender, age bracket, job), the further reasoning work is the family role (mother, father, daughter and so on.) recognition. We have designed simple and combined preferences to test and evaluate our proposed method. Initial experiments have produced good performance in many cases proving this solution is an efficient and feasible method for resident type recognition which could be applied to real-world scenarios.

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

“…In conclusion, the terms indicate a latent reference to a private sphere, which needs to be protected. For example, the technological systems must not disturb the “the people’s environment but making easy their daily activities” (Rodríguez et al 2015 , p. 43) or must not “interfere” with the activities and the “traditional life” (Li et al 2020 , p. 108) of the users. The low intrusiveness is also seen as a possibility for an “easier adaption” by the users and their acceptability (Olaru and Florea 2014 , p. 14).…”

“…Another variation of privacy can be found in limited interaction requirements with the system (Mollaret et al 2016 ; Li et al 2020 ; Sarabia-Jácome et al 2020 ), which is also often described as non-intrusiveness or unobtrusiveness This includes hiding technical processes as much as possible so as not to overwhelm people who lack technical expertise. Ghidoni et al ( 2014 , 1317) refer to this requirement as allowing the system to work with “non-cooperating” people.…”

Future Activities Prediction Framework in Smart Homes Environment

“…Consequently, recognition and prediction of human activities has become an important research field with a wide range of applications. One of these applications presented in [25] used Markov Logic Network to recognize the residents' profiles based on their activities and preference. A resident's profile might contain: resident role (father, mother, son...), gender (male or female), age range (young, middle-age, etc.…”

A Multi-Resident Number Estimation Method for Smart Homes

“…A recent paper [43], focuses on the recognition of some daily activities in a multiresident family home. The recognition of daily activities is a specialized task that requires to precisely identify the type of resident.…”