KNN-Based Decision Model for Device Argumentation in Ambient Assisted Living

Kumar, G. S. Madhan; Prakash, S. P. Shiva; Krinkin, Kirill

doi:10.1007/978-981-19-6581-4_38

Cited by 2 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It highlights the importance of architecture in supporting their unique needs. The k-nearest neighbors (KNN) approach for making device-related decisions in AAL environments was proposed in [23]. The model effectively addresses the challenge of device selection and enhances the quality of life for individuals in need of assistance.…”

Section: Introductionmentioning

confidence: 99%

Gated recurrent unit decision model for device argumentation in ambient assisted living

Kumar,

Prakash,

Krinkin

2024

IJECE

View full text Add to dashboard Cite

The increasing elderly population worldwide is facing a variety of social, physical, and cognitive issues, such as walking problems, falls, and difficulties in performing daily activities. To support elderly people, continuous monitoring and supervision are needed. Due to the busy modern lifestyle of caretakers, taking care of elderly people is difficult. As a result, many elderly people prefer to live independently at home without any assistance. To help such people, an ambient assisted living (AAL) environment is provided that monitors and evaluates the daily activities of elderly individuals. An AAL environment has heterogeneous devices that interact, and exchange information of the activities performed by the users. The devices can be involve in an argumentation about the occurrence of an activity thus leading to generate conflicts. To address this issue, the paper proposes a gated recurrent unit (GRU) learning techniques to facilitate decision-making for device argumentation during activity occurrences. The proposed model is used to initially classify user activities and each sensor value status. Then a novel method is used to identify argumentation among devices for activity occurrences in the classified user activities. Later, the GRU decision making model is used to resolve the argumentation and to identify the target activity that occurred. The result of the proposed model is compared with other existing techniques. The proposed model outperformed the other existing methods with an accuracy of 85.45%, precision of 72.32%, recall of 65.83%, and F1-Score of 60.22%.

show abstract

Section: Introductionmentioning

confidence: 99%