Saraswathy Shamini Gunasekaran

A conceptual model of layered adjustable autonomy

Autonomy and autonomous agents are currently the most researched topics in autonomous systems. Issues like autonomy adjustment, autonomy level, and the required degree of autonomy to be performed are investigated. Abstracting an autonomy model poses the problem of identifying specific aspects that merit an autonomous system. In this paper, we propose another model of autonomy that conceptualizes autonomy as a spectrum, which is constructed in a layered structure of a multi-agent environment called Layered Adjustable Autonomy (LAA). The autonomy spectrum of the LAA is divided into adjustable-leveled layers. Each of which has distinct attributes and properties that assist an agent in managing the influences of the environment during its decision-making process. The LAA structure is designed to endorse an agent’s qualification to make a decision by setting the degree of autonomy to the agent’s choice of decision-making. An Autonomy Analysis Module (AAM) is also proposed to control and delegate the agent’s actions at specific autonomy levels. Hence, the AAM determines the threshold of the agent autonomy level to act in its qualified layer. Ultimately, the proposed LAA model will be implemented on an air drone for the purpose of testing and refinement.

A Dynamically Adjustable Autonomic Agent Framework

The design and development of autonomous software agents is still a challenging task and needs further investigation. Giving an agent the maximum autonomous capabilities may not necessarily produce satisfactory agent behavior. Consequently, adjustable autonomy has become the hallmark of autonomous systems development that influences an agent to exhibit satisfactory behavior. To perform such influences, however, a dynamic adjustment mechanism is needed to be configured. The influences are costly in time and implementation especially for systems with time-critical domain. They might negatively influence agent decisions and cause system disturbance. In this paper, we propose a framework to govern an agent autonomy adjustment and minimize system disturbance. The main components of the proposed framework are the Planner, Scheduler and Controller (PSC) that conform to the current trends in automated systems. Two modules are also suggested which are Autonomy Analysis Module (AAM) and Situation Awareness Module (SAM). They are accordingly used to distribute the autonomy and provide balance to the system so that it’s local and global desires do not conflict.

Formulating Dynamic Agents’ Operational State via Situation Awareness Assessment

Managing autonomy in a dynamic interactive system that contains a mix of human and software agent intelligence is a challenging task. In such systems, giving an agent a complete control over its autonomy is a risky practice while manually setting the agent’s autonomy level is an inefficient approach. This paper addresses this issue via formulating a Situation Awareness Assessment (SAA) technique to assist in determining an appropriate agents’ operational state. We propose four operational states of agents’ execution cycles; proceed, halt, block and terminate, each of which is determined based on the agents’ performance. We apply the SAA technique in a proposed Layered Adjustable Autonomy (LAA) model. The LAA conceptualizes autonomy as a spectrum and is constructed in a layered structure. The SAA and the LAA notions are applicable to humans’ and agents’ collaborative environment. We provide an experimental scenario to test and validate the proposed notions in a real-time application.

The emergence of collective intelligence

Intelligence is the logical ability of an entity to pursue its goal and ultimately achieving it successfully. Consequently, by comprehending and applying such ability in a collective environment, optimum results in goal attainment can be achieved. Such evidence is visible through the model of swarm intelligence in which entomological studies have been made to identify the social interactive behavior of ant and bee colonies. Harvesting successful collective behavior among these insects with such low level logical ability instigates further research on capturing the collective behavior of humans, who possess much higher state of intelligence. In this paper, we investigate and identify the emergence of collective intelligence amongst humans. This is done through the observation of face-to-face meetings in which two or more human entities are involved in formal and informal discussions. In this paper, the term personal intelligence is introduced to describe its influence in generating successful Collective Intelligence. Finally, a preliminary theory is introduced to support the concept of Collective Intelligence.

Knowledge Transfer Model in Collective Intelligence Theory

In a multi-agent environment, a series of interaction emerges that determines the flow of actions each agent should execute in order to accomplish its individual goal. Ultimately, each goal realigns to manifest the agents’ common goal. In a collective environment, these agents retain only one common goal from the start, which is achieved through a series of communication processes that involve discussions, group reasoning, decision-making and performing actions. Both the reasoning and decision-making phases diffuse knowledge in the form of proven beliefs between these agents. In this paper, we describe the concept of discussions, group reasoning and decision making, followed by its corresponding attributes in proposing a preliminary Collective Intelligence theory.

Identifying variables dependency that influences a high level deliberation process in a CI-based Multi-agent System

Intelligence is the ability of using ones knowledge in solving a given problem in the most strategic manner. The efficiency of this logical ability is influenced by the knowledge depth that the individual had comprehended throughout his life experiences. The deeper knowledge the individual has about an event, the more confident the individual becomes at approaching at a successful outcome. In this paper, we describe the variables and their influence towards the knowledge depth of an agent in a multi agent system.

Personal and extended intelligence in collective emergence

Humans are biological agents that communicates formally and informally to execute task and solve problem. Seemingly, this collective composition of cognition and behavior formulates efficient solution thus optimizing problem solving techniques. However, there are limited systematical studies conducted to examine whether group effort is better than individual effort. In a study consisting of 240 people, working in groups of three and individually, we find that the collective effort derives a much more positive outcome in problem solving. In this paper, we explain the method of the experiment conducted and expose the outcome through a detailed analysis.

A Hybrid Algorithm for Improving the Quality of Service in MANET

A mobile ad-hoc network (MANET) exhibits a dynamic topology with flexible infrastructure. The MANET nodes may serve as both host and router functionalities. The routing feature of the MANET is a stand-alone multi-hop mobile network that can be utilized in many real-time applications. Therefore, identifying paths that ensure high Quality of Service (QoS), such as their topology and applications is a vital issue in MANET. A QoS-aware protocol in MANETs aims to find more efficient paths between the source and destination nodes of the network and, hence, the requirements of the QoS. This paper proposes a different hybrid algorithm that combines Cellular Automata (CA) with the African Buffalo Optimization (ABO), CAABO, to improve the QoS of MANETs. The CAABO optimizes the path selection in the ad-hoc on-demand distance vector (AODV) routing protocol. The test results show that with the aid of the CAABO, the AODV manifests energy and delay-aware routing protocol.

Self-reflective Visualizations of Patient-Centered Health Information Systems

Patient-centered systems have great potential to empower patients to take proactive actions in preventing or managing serious diseases and health problems and they can help to reduce healthcare costs. Commonly, these applications are equipped with visuals or graphical representations that enable users to comprehend their health progress. In this paper, we review and analyze the different types of health information visuals that are presented in popular self-monitoring applications and devices, i.e. web-based health support applications, mobile health support applications, stand-alone health monitoring devices, and wearable health monitoring devices. The aim is to gain better insights into designing self-reflective and comprehensible visualizations of health information in patient-centered systems. Results indicate that most of these applications present trends of monitored health data via visuals. Web-based applications feature more comprehensive and complex visuals than applications that are found in other platforms. Stand-alone and wearable devices are found to be more user-friendly and present data in the most simplified manner. There is a need to develop a guideline to aid developers to design effective visuals in patient-centered systems.

Review on the role of social support in health information systems

Social support is the physical and emotional comfort given to someone in times of need or crisis and it is exceptionally important for maintaining good physical and mental health. Despite the contribution and intelligence of technology, which has led to the availability and offer of various types of social support systems, they are still not widely known to many. These support systems are currently available in many versions such as in tablets and smartphones where many health information systems have been created specifically to accommodate to the necessity of current mobile healthcare consumers. This paper systematically reviews the role of social support provided via health information systems. Related studies found in different databases such as IEEE Xplore, ACM Digital Library, Springer, ScienceDirect, Cambridge University Press, John Wiley and Sons, were picked out for the review. A total of one hundred and forty four studies were evaluated and filtered in line with the objective of this study that is to analyze the types of social support provided and its role in health information systems. Results obtain from the study reveals that social support is a vital component to be incorporated in any novel health information system. The results from this study will be used to create a social support framework that could be useful to the health application developers and healthcare stakeholders in designing a social support based self-care application to manage more effectively specific diseases and medical conditions.