Azhana Ahmad

Bio: Azhana Ahmad is an academic researcher from Universiti Tenaga Nasional. The author has contributed to research in topics: Software agent & Multi-agent system. The author has an hindex of 14, co-authored 72 publications receiving 467 citations. Previous affiliations of Azhana Ahmad include National Defence University of Malaysia & College of Information Technology.

A Dynamically Adjustable Autonomic Agent Framework

Abstract: 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.

A Conceptual Model of Layered Adjustable Autonomy

Abstract: 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 dynamic measurement of agent autonomy in the layered adjustable autonomy model

Abstract: In a dynamically interactive systems that contain a mix of humans’ and software agents’ intelligence, managing autonomy is a challenging task. 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. In this paper, we propose an autonomy measurement mechanism and its related formulae for the Layered Adjustable Autonomy (LAA) model. Our model provides a mechanism that optimizes autonomy distribution, consequently, enabling global control of the autonomous agents that guides or even withholds them whenever necessary. This is achieved by formulating intervention rules on the agents’ decision-making capabilities through autonomy measurement criteria. Our aim is to create an autonomy model that is flexible and reliable.

A norms mining approach to norms detection in multi-agent systems

Abstract: In this paper, we propose a norms mining technique for a visitor agent to detect the norms of a community of local agents to comply with the community's normative protocol. In this technique, the visitor agent is equipped with an algorithm, which detects the potential norms through the system's log file, interactions with the local agents, and observing the local agents in action. The visitor agent detects the norms from these sources depending on their availability. Due to security issues, access is prevented to one or more of these sources. The norms mining technique entails the process of data formatting and filtering and identifying the norms' components that contribute to the strength of the norms. The results of an example mining operation show that the technique is successful in discovering the potential norms.

Defining Tasks and Actions Complexity-Levels via Their Deliberation Intensity Measures in the Layered Adjustable Autonomy Model

Abstract: In Multi-agent Systems (MAS), agents perform a variety of actions to autonomously complete a number of tasks. In this paper, we describe a mechanism to measure a task's deliberation intensity and apply the mechanism in the Layered Adjustable Autonomy (LAA) model. Basically, the number of actions that the agents need to do to complete a particular task determines the task's deliberation intensity. Consequently, each of the actions deliberation intensity determines its complexity-level. Actions complexity levels are categorized as high-level if the action is deliberative, intermediate-level if the action pseudo-deliberative and low-level if the action is non-deliberative. Ultimately, the deliberation intensity measure of a task and its actions identify different aspects of the agents' and the actions' parameters including the deliberation length and the autonomy configuration of the LAA model.

Blockchain technology the identity management and authentication service disruptor: A survey

Abstract: The Internet today lacks an identity protocol for identifying people and organizations. As a result, service providers needed to build and maintain their own databases of user information. This solution is costly to the service providers, inefficient as much of the information is duplicated across different providers, difficult to secure as evidenced by recent large-scale personal data breaches around the world, and cumbersome to the users who need to remember different sets of credentials for different services. Furthermore, personal information could be collected for data mining, profiling and exploitation without users' knowledge or consent. The ideal solution would be self-sovereign identity, a new form of identity management that is owned and controlled entirely by each individual user. This solution would include the individual's consolidated digital identity as well as their set of verified attributes that have been cryptographically signed by various trusted issuers. The individual provides proof of identity and membership by sharing relevant parts of their identity with the service providers. Consent for access may also be revoked hence giving the individual full control over its own data. This survey critically investigates different blockchain based identity management and authentication frameworks. A summary of the state-of-the-art blockchain based identity management and authentication solutions from year 2014 to 2018 is presented. The paper concludes with the open issues, main challenges and directions highlighted for future work in this area. In a nutshell, the discovery of this new mechanism disrupted the existing identity management and authentication solutions and by providing a more promising secure platform.