A fuzzy logic control in adjustable autonomy of a multi-agent system for an automated elderly movement monitoring application
Introduction
Many studies have reported a great increase in the median age of the humans, especially those who are living in developed economies [[1], [2]]. For instance, 17.4% of the population in the European Union have been classified as elderly (aged 65 years and above) in 2010, and this ratio is expected to reach 28.8% in 2050 [3]. As the world population continues to age, the number of elderly who are living independently or are left on their own at daytime has also been rising [4]. Some elderly people are facing health problems and require medical attention. To address the special needs of this population, many elderly remote care systems have been proposed, and some examples of these systems are presented in [5]. The elderly tend to show trembling, rigidity, and sluggishness in their movement which expose them to the risks of falling. This problem affects their ability to live independently, reduces their quality of life and can be hazardous and fatal [[1], [6]]. Several elderly remote care systems have been proposed in the attempt to solve or mitigate this problem, and some examples of these systems are presented in [2]. These systems monitor the elderly’s movement activities and daily routine patterns to prevent and detect fall situations.
Autonomous agents and multi-agent technologies have significant roles and contributions in many healthcare and elderly remote care systems [7]. For example, Kaluža et al. [3] propose an agent-based elderly remote care system that supports the independent living of the elderly. The system monitors their movement activities and automatically notifies medical personnel in case of a fall. Typically, agents in discrete and deterministic environments autonomously complete a substantial amount of tasks due to their prior knowledge about their surroundings. However, agents in complex environments that have the characteristics of uncertain, highly dynamic, or irregular workload tend to make decisions that lead to unwanted consequences [8]. These agents are deployed to handle some primitive, deducible, or critical tasks [9]. To make appropriate decisions amid such problems, agents must operate at different autonomy levels and with different autonomy properties [[10], [11], [12]]. In response to this need, several studies have attempted to model adjustable autonomy, which enables agents to operate at different autonomy levels. Some of these works have been reviewed in [8]. The adjustable autonomy in a multi-agent system is managed by grading the modifiable autonomy of agents within a specified range [11]. The grading process involves measuring the boundaries of autonomy parameters and estimating the extent to which autonomy is distributed and adjusted among the agents [[13], [14]].
In this paper, we propose the fuzzy-logic-based adjustable autonomy (FLAA) model to manage the autonomy of agents in multi-agent systems that operate in complex environments. This model employs fuzzy logic to linearly measure the autonomy of the agents. We implement and test this model in the automated elderly movements monitoring (AEMM-Care) system. The system observes the movement activities of the elderly to detect or prevent a fall. Given the intricate nature of fall detection and prevention tasks, the ambiguity of sensory data, and other challenges related to the application domain, we prove that the FLAA model improves the performance of the agents and the accuracy of the AEMM-Care system.
The rest of this paper is organized in the following order. Section 2 reviews the literature on agent-based elderly remote care systems, cites some previous attempts in applying fuzzy logic to manage the autonomy of agents and describes the needs and necessities of using adjustable autonomy. Section 3 illustrates the proposed FLAA model for multi-agent systems which includes the representation, measurement, distribution, and adjustment of autonomy. Section 4 discusses the prototype design, implementation, and application of the adjustable FLAA model in the AEMM-Care system. Section 5 presents the AEMM-care system test results and discusses the research outcomes. Section 6 concludes the paper and offers recommendations for future work.
Section snippets
Literature review
Our literature review reveals that the agent-based healthcare systems being used today are not using fuzzy logic to control the autonomous behavior of agents. Previous studies have also largely ignored the possible application of this technique in managing adjustable autonomy in multi-agent systems. To address these gaps, our literature review focuses on three topics of multi-agent elderly remote care systems, the use of fuzzy logic to control agents' autonomy, and a brief study of adjustable
The fuzzy logic-based adjustable autonomy model
This section explains how autonomy is represented, measured, distributed, and adjusted in the FLAA model. It also explains the architecture and operational behaviors of the agents that work according to the FLAA model.
The AEMM-Care system
The proposed FLAA model is implemented and tested in the AEMM-Care system, which detects and prevents fall incidents among the elderly by tracking their daily activities [25]. The system architecture, the testing scenario settings, and the falling situations that are investigated in the test are all adapted from [[1], [3]] and [6]. The AEMM-Care system is situated in an environment filled with uncertainty, which can be attributed to several factors. First, both the sensory data and the data
Results and discussion
The AEMM-Care system achieves irregular success rates in the fully autonomous mode (i), and such irregularity can be ascribed to the variances in the random forest agent’s learning of different cross-validation folds. t1 and its actions have much lower success rates than t2 and its actions because predicting those movement activity patterns that lead to fall situations is a complex process. The success rates of both t1 and t2 also do not change after multiple runs. The success rate of t1
Conclusion and future work
We perform this research with an aim to develop a model for managing the adjustable autonomy of multi-agent systems that are operating in complex environments. The FLAA model quantifies the autonomy of agents based on knowledge and authority criteria, sets proper autonomy levels for these agents, and manages adjustable autonomy of the agents based on their performance. The autonomy management helps the agents to make highly flexible and efficient decisions and guides them toward achieving
Authors contributions
The contributions of this work are represented by the following points:
- •
The first contribution of this work lies in its development of the FLAA model, which uses fuzzy logic to formulate the adjustable autonomy of a multi-agent system. This model is applied in a remote elderly movement monitoring system.
- •
The second contribution of this work lies in its proposal of random forest agents with three adjustable autonomous run phases.
- •
The third contribution of this work lies in the recognition of
Conflict of interest and authorship confirmation
- •
All authors have participated in (a) conception and design, or analysis and interpretation of the data; (b) drafting the article or revising it critically for important intellectual content; and (c) approval of the final version.
- •
The Article I have submitted to the journal for review is original, has been written by the stated authors and has not been published elsewhere.
- •
The Images that I have submitted to the journal for review are original, was taken by the stated authors, and has not been
Acknowledgements
This project is sponsored by the postdoctoral grant of Universiti Tun Hussein Onn Malaysia (UTHM) under Vot D004 and partially supported by the Tier 1 research grant scheme of UTHM under Vot U893.
References (27)
- et al.
A multi-agent system based on reactive decision rules for solving the caregiver routing problem in home health care
Simul. Modell. Pract. Theory
(2017) - et al.
A multi-agent based approach to support adaptability in home care applications
IFAC-PapersOnLine
(2015) - et al.
A fuzzified systematic adjustment of the robotic Darwinian PSO
Rob. Auton. Syst.
(2012) - et al.
Fall detection using location sensors and accelerometers
IEEE Pervasive Comput.
(2015) - et al.
Internet of things for remote elderly monitoring: a study from user-centered perspective
J. Ambient Intell. Hum. Comput.
(2017) - et al.
A multi-agent care system to support independent living
Int. J. Artif. Intell. Tools
(2014) - et al.
A panoramic study of fall detection technologies
Int. J. Comp. Sci. Issues (IJCSI)
(2016) - et al.
A systematic literature review of agents applied in healthcare
J. Med. Syst.
(2016) - et al.
Adapting activity recognition to a person with Multi-Classifier Adaptive Training
J. Ambient Intell. Smart Environ.
(2015) - et al.
Adjustable autonomy: a systematic literature review
Artif. Intell. Rev.
(2017)
Decision making method using fuzzy logic for autonomous agent navigation
Electr. J. Comp. Sci. Inf. Technol.
Defining tasks and actions complexity-levels via their deliberation intensity measures in the layered adjustable autonomy model
Dimensions of adjustable autonomy and mixed-initiative interaction
International Workshop on Computational Autonomy
Cited by (66)
Resolution strategies for cooperative vehicle fleets for reducing rear-end collision risks near recurrent freeway bottlenecks
2023, Journal of Intelligent Transportation Systems: Technology, Planning, and OperationsA fuzzy rule-based approach via MATLAB for the CDR instrument for staging the severity of dementia
2022, Computer Methods and Programs in Biomedicine UpdateLeader-following bipartite consensus with disturbance rejection for uncertain multiple Euler–Lagrange systems over signed networks
2021, Journal of the Franklin InstituteCitation Excerpt :In recent years, multi-agent systems(MASs) have always been a hot issue in the control fields and have aroused a storm of investigation because of their extensive applications [1–4].
Robustness analysis of classical and fuzzy decision trees under adversarial evasion attack
2021, Applied Soft ComputingCitation Excerpt :This study attempts to investigate whether and how fuzzifying a system affects its robustness against evasion attack in an adversarial environment. Classical and Fuzzy Decision Trees (DT and FDT) are the focus of this paper due to their popularity in broad applications, e.g.multi-agent systems [25], natural language process processing [26], diagnosis systems [27], malware detection [28,29], network intrusion detection [30] and spam filtering [31]. A fair comparison on the robustness of DT and FDT requires a general evasion attack which is able to attack both DT and FDT.
Agent architecture of an intelligent medical system based on federated learning and blockchain technology
2021, Journal of Information Security and ApplicationsCitation Excerpt :Solutions based on the operation of multiple agents boils down to modeling communication and information exchange mechanisms depending on the current goals. One such solution is to use a fuzzy logic controller for the adjustable autonomy of a multi-agent system (MAS) [8], where the main application of the described proposal was automated elderly movement monitoring application. This kind of research shows that an agent-based approach can be valuable due to analyzing data.
Artificial Intelligence and IoT in Elderly Fall Prevention: A Review
2024, IEEE Sensors Journal