i Ab Aziz

An integrative ambient agent model for unipolar depression relapse prevention

One of the challenges for persons with a history of unipolar depression is to stay healthy throughout their lifetime. In principle, having more severe prior onset cases escalates the risk to fall into a relapse. In this article, first a domain model of the process of depression, recovery and relapse is presented, and second an integrative ambient agent model to support persons from relapse is described. Based on several personal characteristics and a representation of events (i.e., life events or daily hassles) the domain model can simulate whether a human that recovered from a depression will fall into a relapse or recurrence. A number of well-known relations between events and the course of depression are summarized from the literature and it is shown that the domain model exhibits those patterns. The domain model has been mathematically analyzed to find out which stable situations exist. Second, by incorporating this domain model into an ambient agent system, the resulting integrative ambient agent model is able to reason about the state of the human and the effect of possible actions. Several simulation experiments have been conducted to illustrate the functioning of the proposed model in different scenarios. In addition, an automated verification method using Temporal Trace Language (TTL) is used to verify that the ambient agent model satisfies a number of relevant properties. Finally, it is pointed out how this model can be used in depression therapy, supported by an ambient agent.

Modelling Dynamics of Social Support Networks for Mutual Support in Coping with Stress

This paper presents a computational multi-agent model of support receipt and provision to cope during stressful event within social support networks. The underlying agent model covers support seeking behavior and support provision behaviour. The multi-agent model can be used to understand human interaction and social support within networks, when facing stress. Simulation experiments under different negative events and personality attributes for both support receipt and provision pointed out that the model is able to produce realistic behavior to explain conditions for coping with long term stress by provided mutual support. In addition, by a mathematical analysis, the possible equilibria of the model have been determined.

An Agent Model of Temporal Dynamics in Relapse and Recurrence in Depression

This paper presents a dynamic agent model of recurrences of a depression for an individual. Based on several personal characteristics and a representation of events (i.e. life events or daily hassles) the agent model can simulate whether a human agent that recovered from a depression will fall into a relapse or recurrence. A number of well-known relations between events and the course of depression are summarized from the literature and it is shown that the model exhibits those patterns. In addition, the agent model has been mathematically analyzed to find out which stable situations exist. Finally, it is pointed out how this model can be used in depression therapy, supported by a software agent.

An Ambient Intelligent Agent for Relapse and Recurrence Monitoring in Unipolar Depression

Mental healthcare is a prospective area for applying AI techniques. For example, a computerized system could support individuals with a history of depression in maintaining their well-being throughout their lifetime. In this paper, the design of an ambient intelligent agent to support these individuals is presented. It incorporates an analysis and support model for diagnostics based on observed features and for suggested actions. The model used is based on dynamic relations that describe the occurrence of relapse in unipolar depression. By incorporating this model into an ambient agent system, the agent is able to reason about the state of the human and the effect of possible actions. Several simulation experiments have been conducted to illustrate the functioning of the proposed model in different scenarios.

Development of an adaptive business insolvency classifier prototype (AVICENA) using hybrid intelligent algorithms

Confronted by an increasingly competitive environment and chaotic economic conditions, businesses are faced with the need to accept greater risk. Businesses do not become insolvent overnight, rather creditors, investors and the financial community will receive either direct or indirect indications that a company is experiencing financial distress. Thus, this paper analyzed the ability of AVICENA to classify business insolvency performance events. Neural networks (multilayer perceptron-backpropagation) serves as a classifier mechanism while a priori algorithms (auto association rules) support the decision made by the neural networks, in which rules are generated. The conventional model for predicting business performance, the Altman-Z scores model, is used for performance comparison.

Design of an intelligent support agent model for people with a cognitive vulnerability

This paper presents the design of an intelligent agent application aimed at supporting people with a cognitive vulnerability to prevent the onset of a depression. For this, a computational model of the cognitive processes around depression is used. The agent application uses the principles of Rational Emotive Behavioural Therapy. The effect of the application is studied using software simulation. The simulation shows that a person that responds to REBT therapy develops less cognitive vulnerability than people that are not supported.

Modeling an Ambient Agent to Support Depression Relapse Prevention

One of the challenges for the patients with a history of unipolar depression is to stay healthy throughout their lifetime. In principle, with more prior onset cases, it escalates the risk of the patients to fall into a relapse. In this paper, an ambient agent based model to support patients from relapse is presented. Theories and related works in depression relapse prevention provide a foundation for the formalization of the temporal properties to describe the model. This model was analyzed under several scenarios using simulation and automated verification.

Designing a robot-assisted therapy for individuals with anxiety traits and states

The recent trend towards developing a new generation of robots capable of operating in human-centered environments, and participating in and assisting our daily lives has introduced the need for robotic systems capable to communicate and to react to their users in a social and engaging way. This type of robot could play essential roles to help individuals with severe cognitive problems. In this paper, several core components to design a robotic assisted therapy to support individuals with anxiety traits and states are presented.

A Multi-agent Model for Supporting Exchange Dynamics in Social Support Networks during Stress

Humans are social creatures, and when facing certain level of events, they to seek for support from others and vice versa. In this paper, a multi-agent model for simulating the dynamics of support provision and receipt interaction among different individuals is presented. Important concepts in social support network and stress buffering studies were used as the basis for model design and verification. Simulation experiments under several cases pointed out that the model is able to reproduce interaction among social support network members during stress. Mathematical analysis was conducted to determine possible equillibria of the model. The model was verified using an automated verification tool against generated traces.

Incorporating an Ambient Agent to Support People with a Cognitive Vulnerability

This article presents the design of an intelligent agent application aimed at supporting people with a cognitive vulnerability to prevent the onset of a depression. For this, a computational model of the cognitive processes around depression is used. The agent application uses the principles of Rational Emotive Behavioural Therapy (RBET). The effect of the application is studied using software simulation. The simulation shows that a person that responds to REBT therapy develops less cognitive vulnerability than people that are not supported.