Friends Forever: Social Relationships with a Fuzzy Agent-Based Model

Hassan, Samer; Salgado, Mauricio; Pavón, Juán

doi:10.1007/978-3-540-87656-4_65

Cited by 13 publications

(12 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Our findings suggest that our agent model otherwise referred to as Situ learning agent (SLA) is able to recommend appropriate action in a risky situation detected in an ADL goal sequence, thus, averting potential hazards from the performance of ADLs in smart home environments. Thus, this observation shows that our findings also agree with previous research that agent‐based models are useful to study emergent behaviors in a social system or an environment with uncertainty such as the smart home (Hassan et al, ; Vermeulen & Pyka, ;Oommen & Hashem, ; Vaandrager, ).…”

Section: Discussionsupporting

confidence: 92%

“…Uncertainty in sequential decision making is the lack of information on the options (now or in the future) or on the probability distributions of outcomes of actions (Vermeulen & Pyka, 2016). Agent-based models are useful to study emergent behavior in a social system, as these models possess the intelligence to cope with uncertainty when aware of the goal and decisions interaction (Hassan et al, 2008;Vermeulen & Pyka, 2016). As a result, these models are able to transform goals into action tasks (Chen, Li, Chen, & Wen, 2011).…”

Section: B Situ Learning Agent (Sla)mentioning

confidence: 99%

See 1 more Smart Citation

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

Section: Discussionsupporting

confidence: 92%

Section: B Situ Learning Agent (Sla)mentioning

confidence: 99%

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

2019

View full text Add to dashboard Cite

show abstract

“…Anyway, with the actual changes, the similarity operation has improved substancially its accuracy; the couples found are more "logical" (reaching a 22% of improvement), due to two facts: agents know more people than before thanks to the closure, and the cited improvement in the measure of similarity; and the friendship is more realistic: instead of being boolean, it is graded, and it considers more knowledge thanks to the T-transitive closure. For more information about this work and a deeper analysis of its results, including graphs and tables of results, please refer to the works of Hassan, Salgado & Pavon (2008).…”

Section: Results and Conclusionmentioning

confidence: 99%

Introducing uncertainty into social simulation: using fuzzy logic for agent-based modelling

Hassan

Garmendia

Pavón

2010

IJRIS

Self Cite

View full text Add to dashboard Cite

Agent based models are useful to study emergent behaviour in social systems. In general, existing agent models tend to be quite simple, but there are social problems that require the consideration of some aspects with uncertainty as human thinking does. Those characteristics can be addressed by using fuzzy sets theory in the specification of the attributes that describe agents representing individuals, and in the functions that model the evolution of individual change of mind, the relationships among individuals in a social network, the inheritance, and the similarity between individuals. This paper discusses the fuzzification of agent-based models and analyses experimentation results for a specific case of the study of the evolution of human values in a society.

show abstract

“…The exponent ϕ(ϕ > 1) controls the degree of this effect. Similar assumption can be seen in many studies on social network generation, such as [37] and [38]. Meanwhile, considering the law of diminishing marginal utility, we assume that w i,j (t) decreases with the increase in k i under the same baseline weight.…”

Section: A Social Relation Modelmentioning

confidence: 90%

Growing Spatially Embedded Social Networks for Activity-Travel Analysis Based on Artificial Transportation Systems

Chen

Zhu

Cao

2014

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Social activity-travel has gained more and more attention as it is a growing percentage of the whole travel. To study its generation mechanism and behavioral characteristics, social network data are usually essential. However, due to individual privacy, it is rather difficult for traditional methods such as questionnaires to collect abundant reliable data. Therefore, we propose a novel method to grow realistic social networks based on artificial transportation systems (ATS). By incorporating the activity-travel simulation provided by ATS and a new agent-based model for social interaction, the method takes into account human mobility to generate spatially embedded social networks. Human mobility shapes and impacts social networks dynamically but is usually ignored by related studies. A case study based on computational experiments is carried out to verify the method. The results indicate that the method can generate social networks with similar topological and spatial characteristics to real social networks.Index Terms-Activity-based traffic simulation, agent, artificial transportation systems (ATS), reinforcement learning, spatially embedded social networks.

show abstract

Friends Forever: Social Relationships with a Fuzzy Agent-Based Model

Cited by 13 publications

References 16 publications

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

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

Introducing uncertainty into social simulation: using fuzzy logic for agent-based modelling

Growing Spatially Embedded Social Networks for Activity-Travel Analysis Based on Artificial Transportation Systems

Contact Info

Product

Resources

About