Ambient Agent Research Articles

Task re-pricing model based on density-based spatial clustering of applications

In the retail market, gathering marketing data is essential at different stages of advertisement and promotion; currently, this is achieved via online crowdsourcing. The jobs involving such tasks must be reasonably priced to attract part-time employees depending on the retail budget. Herein, a new approach is presented to enhance the task repricing performance of online crowdsourcing platforms using the density-based spatial clustering of applications with noise (DBSCAN) algorithm, genetic general regression neural network (G-GRNN), and AdaBoost meta-algorithm. Initially, DBSCAN is used to analyze the agent task distribution, task density, and ambient agent credibility. Then, G-GRNN and AdaBoost are applied to reprice the tasks and evaluate the completeness of the repricing. Results show that the proposed method can optimize the repricing outcomes and enhance the efficiency of the repricing process. This study was conducted to address the crowdsourcing pricing problem from the perspective of firms. The results demonstrate the effectiveness of the machine learning methods (DBSCAN, G-GRNN, and AdaBoost) in solving the task repricing problem.

Agent-Based Modeling of Emotion Contagion in Groups

To avoid the development of negative emotion in their teams, team leaders may benefit from being aware of the emotional dynamics of the team members. To this end, the use of intelligent computer systems that analyze emotional processes within teams is a promising direction. As a first step toward the development of such systems, this paper uses an agent-based approach to formalize and simulate emotion contagion processes within groups, which may involve absorption or amplification of emotions of others. The obtained computational model is analyzed both by explorative simulation and by mathematical analysis. In addition, to illustrate the applicability of the model, it is shown how the model can be integrated within a computational ‘ambient agent model’ that monitors and predicts group emotion levels over time and proposes group support actions based on that. Based on this description, a discussion is provided of the main contribution of the model, as well as the next steps needed to incorporate it into real-world applications.

Formal specification and analysis of intelligent agents for model-based medicine usage management

A model-based agent system model for medicine usage management is presented and formally analysed. The model incorporates an intelligent ambient agent model that has an explicit representation of a dynamical system model to estimate the medicine level in the patient′s body by simulation, is able to analyse whether the patient intends to take the medicine too early or too late, and can take measures to prevent this.

An ambient agent system assisting humans in complex tasks by analysis of a human's state and performance

Human task performance varies depending on the task, environment, and states of the human over time. To ensure high effectiveness and efficiency in the execution of complex tasks, adaptive automated assistance of the human may be required. In this paper, a generic design for a multi-agent system architecture is presented and a personal assistant agent is described that makes use of the proposed architecture. The agent constantly monitors the task execution and well-being of the human via non-intrusive sensors, and intervenes when a problem is detected. A human is given a complex task, while the future performance is predicted using observations and a dynamical model for the human's work pressure and exhaustion. If the predicted exhaustion becomes too high, the ambient agent can assist the human in a number of ways. Experiments with humans show that the support system increases performance with around 13%, and that it enhances the feeling of control of the situation.

A computational model for dynamics of desiring and feeling

In this paper a computational model is presented for how a desire triggers responses and feelings. The model shows how these feelings can be biased, for example due to addicting experiences in the past. Both the strength of a response and of the associated feeling result from a converging dynamic pattern modeled by reciprocal causal interactions between the two. The model has been used to conduct a number of simulation experiments under varying circumstances. Moreover, it has been evaluated by formal analysis of emerging patterns entailed by the model. Furthermore, it has been pointed out how the computational model can be applied within an ambient agent system supporting a human in not being tempted. In a simple example scenario it is shown such an ambient agent system is able to predict and assess a human’s desire state, and use this assessment to suggest alternatives to avoid falling for certain temptations.

An ambient agent model for monitoring and analysing dynamics of complex human behaviour

In ambient intelligent systems, monitoring of a human could consist of more complex tasks than merely identifying whether a certain value of a sensor is above a certain threshold. Instead, such tas...

An ambient agent architecture exploiting automated cognitive analysis

In this paper an agent-based ambient agent architecture is presented based on monitoring human’s interaction with his or her environment and performing cognitive analysis of the causes of observed or predicted behaviour. Within this agent architecture, a cognitive model for the human is taken as a point of departure. From the cognitive model it is automatically derived how internal cognitive states affect human’s performance aspects. Furthermore, for these cognitive states representation relations are derived from the cognitive model, expressed by temporal specifications involving events that will be monitored. The representation relations are verified on the monitoring information automatically, resulting in the identification of cognitive states, which affect the performance aspects. In such a way the ambient agent model is able to provide a more in depth cognitive analysis of causes of (un)satisfactory performance and based on this analysis to generate interventions in a knowledgeable manner. The application of the architecture proposed is demonstrated by two examples from the ambient-assisted living domain and the computer-assisted instruction domain.

An ambient agent model for monitoring and analysing dynamics of complex human behaviour

In ambient intelligent systems, monitoring of a human could consist of more complex tasks than merely identifying whether a certain value of a sensor is above a certain threshold. Instead, such tasks may involve monitoring of complex dynamic interactions between human and environment. In order to enable such more complex types of monitoring, this paper presents a generic agent-based framework. The framework consists of support on various levels of system design, namely: (1) the top level, including the interaction between agents, (2) the agent level, providing support on the design of individual agents, and (3) the level of monitoring complex dynamic behaviour, allowing the specification of the aforementioned complex monitoring properties within the agents. The approach is exemplified by a large case study concerning the assessment of driving behaviour, and is applied to two smaller cases as well (concerning fall detection of elderly, and assistance of naval operations, respectively), which are briefly described. These case studies have illustrated that the presented framework enables developers within ambient intelligence to build systems with more expressiveness regarding their monitoring focus. Moreover, they have shown that the framework is easy to use and applicable in a wide variety of domains.

A software environment for a human-aware ambient agent supporting attention-demanding tasks

Abstract This paper presents a software environment for a human-aware ambient agent providing support for a human performing an attention-demanding task. The agent obtains human attention-awareness by use of a dynamical model of human attention, gaze sensoring by an eye-tracker, and information about features of the objects in the environment. It has been implemented in a component-based, event-driven manner within the Adobe ® Flex ® environment, thereby also integrating the Tobii ® eye-tracker. It has been applied in a setup for a task where the human has to identify enemies and allies, and eliminate the enemies.

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.

Designing human-awareness for ambient agents: A human mindreading perspective

Ambient Intelligence (AmI) [1] has the vision to make Information and Communication Technologies disappear into the environment thus creating an ergonomic space for the inhabitant, encompassing an active living environment around us. To bring this goal to realization, devices need to be built possessing knowledge about humans enabling these devices to show a more human-like understanding. For this, we need assistance of human-directed disciplines such as cognitive science, psychology and biomedical sciences that develop models for many different aspects of human functioning. By representing these models in a formal and computational format, and incorporating them in these devices, these devices can be made more sensitive and responsive to humans [3]. The integration of these models within AmI applications is becoming more widely known as human-aware ambient agent modelling. Theory of Mind (ToM), or mindreading, is an ability to attribute mental states such as, beliefs, intentions, desires, pretending, knowledge, emotion etc, to others and to understand that those states may be similar or different from one's own. The work presented in this thesis makes contributions in the area of modelling and simulation by analysing and designing ambient agent models integrating concepts of Theory of Mind, to make these models human-aware. To explore the applicability of the approach proposed in this thesis, it has been applied in different specializations addressing integrated approaches to, for example, emotion generation and reading, emotion contagion, believing, desiring, feeling, decision making, and attention [2].

Ambient Heat and Nerve Agent Antidotes: Effects on Soldier Performance with the Usariem Performance Inventory

The tactical significance of chemical weapons in future warfare demands that nerve agent antidotes be available for troops exposed to chemical attack. Since future combat operations will likely occur in desert and tropical areas, chemical attacks in such areas could lead to situations involving the use of nerve agent antidotes by troops during exposure to hot weather conditions. This study assessed, both independently and in combination, the effects of heat exposure (95°F, 60%RH) and US Army standard dosages of nerve agent antidotes (2 mg atropine and 600 mg 2-PAM chloride) on the performance of a variety of tasks selected from the USARIEM Performance Inventory (UPI). The UPI tasks selected for inclusion assessed sensory functioning, perceptual-cognitive functioning, sensorimotor skill, subjective reactions, and M16 rifle marksmanship. Fifteen soldier volunteers were first trained to asymptotic performance on the UPI task battery. Then, over a period of four test days, they completed a counterbalanced schedule of the drug/no drug and heat/no heat conditions while outfitted in the Battle Dress Uniform. On each test day, the tests from the UPI were administered once during each of the three 2-hour test cycles. Compared to the placebo condition, a single dose of nerve agent antidote significantly impaired soldier performance such that visual reaction time was 5 to 11% slower, gross body mobility was 12% poorer, rifle marksmanship (pop-up targets) was 3% less accurate, and verbal reasoning was 6% slower. Compared to the 70°F condition, the 95°F ambient condition significantly impaired soldier performance such that arm-hand steadiness was 10% poorer, manual dexterity was 2% poorer, and rifle marksmanship (tightness of shot group) was 13% less accurate. Nerve agent antidote and ambient heat did not interact to further impair soldier performance.