Intelligent temporal data driven world actuation in ambient environments: Case study: Anomaly recognition and assistance provision in smart home

Amirjavid, Farzad; Bouzouane, Abdenour; Bouchard, Bruno

doi:10.1109/icis.2013.6607856

Cited by 8 publications

(14 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In other words, activity recognition techniques are applied to find justifications for the observations, so if no explanation for observations is found then the anomaly 1 is recognized. Moreover, activity recognition may address inference of appropriate automatic assistance in smart home [10]. Out of all possible activities that may be realized in smart home, parallel social activities make a specific group that cause normal world states but are not paid enough attention by the activity recognition researchers.…”

Section: A Activity Recognitionmentioning

confidence: 99%

“…At the highest level, there is NWGF, which represents the simultaneous realization of all activities in smart home. This high-level concept represents all knowledge at a glance and may be applied for a fast reasoning in anomaly recognition [10].…”

Section: Hierarchy Of Concepts In Smart Homementioning

confidence: 99%

“…In order to provide technological automatic assistance to the smart home resident, the activities are observed through embedded sensors of smart home and applying artificial intelligence techniques the observations are analyzed, so as the result, the information that supports decision making for provision of appropriate assistance is discovered in a data-driven manner [10].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Data driven conceptual structures for simultaneous activities

Amirjavid

Bouzouane

Bouchard

2013

2013 IEEE/ACIS 12th International Conference on Computer and Information Science (ICIS)

Self Cite

View full text Add to dashboard Cite

An activity is a chain of fuzzy events that occur in an environment caused by an intelligent system in order to achieve a goal. A goal may be achieved by effort of more than one individual. Regardless from the physical entity (modality and location) of the intelligence source and the quantity of individuals who perform the activities; per each possible goal or activity, we consider a source of intelligence who directs the order of fuzzy events that occur in the world. By frequently observation of the world, the plan behind world actuations is modeled applying extensions of the fuzzy logic. The main key point that we deal with is the analysis of the observations in order to make inferences about possible simultaneous activities that may be planned and realized by one or more individuals. A fuzzy conceptual structure for each individual and simultaneous activity is formalized; however, the model tolerates partial deviations from the activity structure.

show abstract

Section: A Activity Recognitionmentioning

confidence: 99%

Section: Hierarchy Of Concepts In Smart Homementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Data driven conceptual structures for simultaneous activities

Amirjavid

Bouzouane

Bouchard

2013

2013 IEEE/ACIS 12th International Conference on Computer and Information Science (ICIS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…(Amirjavid, Bouzouane, & Bouchard, ) designed an anomalies recognition and assistance provision system based on a fuzzy temporal data‐driven technique. In their work, each activity is defined as a fuzzy conceptual structure represented as a hierarchy of concepts in smart homes.…”

Section: Background and Related Workmentioning

confidence: 99%

“…In this paper, we argue that a true human-centered system should be able to infer the intention of inhabitant by analyzing minimal sets of behavior and context values at any given time and also preempt any abnormal activities that may compromise the safety of the resident. (Amirjavid, Bouzouane, & Bouchard, 2013) designed an anomalies recognition and assistance provision system based on a fuzzy temporal datadriven technique. In their work, each activity is defined as a fuzzy conceptual structure represented as a hierarchy of concepts in smart homes.…”

mentioning

confidence: 99%

Situation‐centered goal reinforcement of activities of daily living in smart home environments

2019

View full text Add to dashboard Cite

Older adults with early‐stage dementia (ED) can experience confusion or lack clarity when performing routine activities of daily living (ADLs). These circumstances predispose the older adult to safety‐critical and often risky situations. A safety‐critical risky situation is one that constitutes a hazard. To support independent living, a sensor‐laden smart environment can be employed to mitigate such hazards. In this paper, we propose a situation‐centered goal reinforcement framework that supports older adults with ED in their decision making, and guides them through their ADL in order to fulfill their goal or intention and avoid hazards. First, we employ an LSTM (Long Short‐Term Memory) model to infer the current goal of the resident, using their previously observed normal ADL patterns. Secondly, we identify potentially risky situations in their currently observed goal path. We then incorporate a situ‐learning agent (SLA) that helps an inhabitant to make the right decision, thus preventing adverse events while guiding her through the task sequence that leads to her goal state. In addition, we use a naïve agent to simulate episodes of confusion similar to those that might be experienced by older adults with ED. We validated our method against an open‐source dementia dataset (Quesada et al., 2015) by considering four types of ADLs as case studies. We achieved an accuracy of 90.1% for our goal inference model, higher than the accuracies reported by related studies. We also reported other metrics including precision, recall and f1‐score for goal inference model. Finally, SLA's action recommendations relevance was evaluated accordingly.

show abstract