Intelligent Agent Architecture Research Articles

Artificial Intelligent Agent Architecture and Clinical Decision-Making in the Healthcare Sector.

This paper examines the decision-making processes of physicians and intelligent agents within the healthcare sector, particularly focusing on their characteristics, architectures, and approaches. We provide a theoretical insight into the evolving role of artificial intelligence (AI) in healthcare, emphasizing its potential to address various healthcare challenges. Defining features of intelligent agents are explored, including their perceptual abilities and behavioral properties, alongside their architectural frameworks, ranging from reflex-based to general learning agents, and contrasted with the rational decision-making structure employed by physicians. Through data collection, hypothesis generation, testing, and reflection, physicians exhibit a nuanced approach informed by adaptability and contextual understanding. A comparative analysis between intelligent agents and physicians reveals both similarities and disparities, particularly in adaptability and contextual comprehension. While intelligent agents offer promise in enhancing clinical decisions, challenges with types of dataset biases pose significant hurdles. Informing and educating physicians about AI concepts can build trust and transparency in intelligent programs. Such efforts aim to leverage the strengths of both human and AI toward improving healthcare delivery and outcomes.

Reinforcing Cyber Defense: Generative AI Powered Intelligent Agent Architecture for Enhanced Security Operations

Reinforcing Cyber Defense: Generative AI Powered Intelligent Agent Architecture for Enhanced Security Operations

Principles of ontophylogenetic development of artificial general intelligence systems based on multi-agent neurocognitive architectures

The purpose of the study is to study the possibilities of multigenerational optimization of behavior control systems for agents of general artificial intelligence capable of independently solving a universal range of tasks in a real environment. The main principles of ontophylogenetic synthesis of control systems for agents of general artificial intelligence based on multi-agent neurocognitive architectures have been developed. Methods and algorithms for synthesizing the phenotypes of control systems of intelligent agents according to their genotypes are proposed. A software package for simulating the processes of ontophylogenetic synthesis of multi-agent neurocognitive architectures has been developed and experiments have been carried out to create phenotypes of intelligent agents based on them. A complex genome of an intelligent agent has been developed, the features of a multichromosome genetic algorithm for organizing calculations in the paradigm of multigenerational optimization of multiagent neurocognitive architectures have been established and substantiated. It is shown that multigenerational optimization of the multi-agent neurocognitive architecture of intelligent agents can contribute to the achievement of adaptive resistance to the operating conditions of a general artificial intelligence agent, provide the synthesis of its suboptimal structural and functional scheme, accelerate learning and algorithms for finding solutions to a universal range of problems solved by this agent in its ecological niche.

APIA: An Architecture for Policy-Aware Intentional Agents

This paper introduces the APIA architecture for policy-aware intentional agents. These agents, acting in changing environments, are driven by intentions and yet abide by domain-relevant policies. This work leverages the AIA architecture for intention-driven intelligent agents by Blount, Gelfond, and Balduccini. It expands AIA with notions of policy compliance for authorization and obligation policies specified in the language AOPL by Gelfond and Lobo. APIA introduces various agent behavior modes, corresponding to different levels of adherence to policies. APIA reasoning tasks are reduced to computing answer sets using the Clingo solver and its Python API.

Autonomous Agents in 3D Crowd Simulation Through BDI Architecture

Agent based simulation (ABS) is a paradigm to modelling systems included of autonomous and interacting agents. ABS has been tremendous growth and used by researchers in the social sciences to study socio-environmental complex systems. To date, various platforms have been introduced for agent-based social simulation. They are rule based in any logic, python based in SPADE and etc. Although those platforms have been introduced, there is still an insufficient to develop a crowd simulation in 3D platform. Having a 3D platform is needed to enabling the crowd simulation for training purposes. However, the current tools and platform still lack features to develop and simulate autonomous agents in the 3D world. This paper introduced a BDI plug in at Unity3D for crowd simulation. BDI is an intelligent agent architecture and it is able to develop autonomous agents in crowd environment. In this paper, we present the BDI plug with a case study of Australia bush fire and discuss a method to support autonomous agents' development in 3D crowd simulation. The tool allows the modeller to develop autonomous agents in 3D world by taking the advantages of Unity3D.

An introductory preview of Autonomous Intelligent Cyber-defense Agent reference architecture, release 2.0

The North Atlantic Treaty Organization (NATO) Research Task Group IST-152 developed a concept and a reference architecture for intelligent software agents performing active, largely autonomous cyber-defense actions on military assets. The group released a detailed report, briefly reviewed in this article, where such an agent is referred to as an Autonomous Intelligent Cyber-defense Agent (AICA). In a conflict with a technically sophisticated adversary, NATO military networks will operate in a heavily contested battlefield. Enemy malware will likely infiltrate and attack friendly networks and systems. Today’s reliance on human cyber defenders will be untenable on the future battlefield. Instead, artificially intelligent agents, such as AICAs, will be necessary to defeat the enemy malware in an environment of potentially disrupted communications where human intervention may not be possible. The IST-152 group identified specific capabilities of AICA. For example, AICA will have to be capable of autonomous planning and execution of complex multi-step activities for defeating or degrading sophisticated adversary malware, with the anticipation and minimization of resulting side effects. It will have to be capable of adversarial reasoning to battle against a thinking, adaptive malware. Crucially, AICA will have to keep itself and its actions as undetectable as possible, and will have to use deceptions and camouflage. The report identifies the key functions and components and their interactions for a potential reference architecture of such an agent, as well as a tentative roadmap toward the capabilities of AICA.

Approaches to cognitive architecture of autonomous intelligent agent

Abstract Taking into account that the human intelligence is the only available intelligence we will find the functional relationship between neuronal processes and psychic phenomena to reproduce intelligence in artificial system. The autonomous behavior of an agent may be the consequence of a gap between physical processes and self-referential meaningful processing of information which is related but not determined by physical processes. This indeterminism can be reproduced in a cognitive architecture through the self-referential processing of information with consideration of itself as a meaningful model. We propose embodiment of cognitive architecture of autonomous intelligent agent as an artificial neural network with a feedback loop in meaningful processing of information.

A Framework for Demand Bidding to Achieve Demand Response Objectives by EVs Charging and Heating Loads

Energy markets which are based on fixed day-ahead energy prices could face bottlenecks due to the simultaneous activation of flexible loads in the system and hence causing power imbalances and possibly also causing congestion in the distribution network. In order to mitigate these problems a suitable scheme is required to reschedule the flexible loads based on incentives for the end users for changing their demand from their day-ahead optimized demand pattern. This paper proposes a three-layer architecture of intelligent agents for scheduling of flexible loads which implies a demand bidding strategy. A real case study is considered from Nordpool spot prices for four different seasons of the year to show case the rationality of the study. Two flexible loads, Electric Vehicles (EVs) and Storage Space Heating (SSH) are considered in this scenario, while other loads are assumed non-flexible. Analysis of energy cost based on flexibility indices of loads is studied, which shows that flexibility of loads not only supports the power network capacity in congestion situation but it also benefits the consumers with cost effective use of energy. From aggregator’s perspective, the system resources are utilized optimally hence reducing the need for running extra generators and the spikes at the cheap price hours are mitigated. From the results, it is noted that the proposed bidding scheme has benefited the households up to 60% of the energy cost saving by participating in the demand response. The number of times each household wins a bid depends on the flexibility of loads and in this particular simulation scenario most of the households are able to win the bids 2 times in a day.

From Activity Recognition to Intention Recognition for Assisted Living Within Smart Homes

The global population is aging; projections show that by 2050, more than 20% of the population will be aged over 64. This will lead to an increase in aging related illness, a decrease in informal support, and ultimately issues with providing care for these individuals. Assistive smart homes provide a promising solution to some of these issues. Nevertheless, they currently have issues hindering their adoption. To help address some of these issues, this study introduces a novel approach to implementing assistive smart homes. The devised approach is based upon an intention recognition mechanism incorporated into an intelligent agent architecture. This approach is detailed and evaluated. Evaluation was performed across three scenarios. Scenario 1 involved a web interface, focusing on testing the intention recognition mechanism. Scenarios 2 and 3 involved retrofitting a home with sensors and providing assistance with activities over a period of 3 months. The average accuracy for these three scenarios was 100%, 64.4%, and 83.3%, respectively. Future will extend and further evaluate this approach by implementing advanced sensor-filtering rules and evaluating more complex activities.

A modular architecture for intelligent agents in the evented web

A modular architecture for intelligent agents in the evented web

A Distributed Multi-Agent Based Emergency Control Approach Following Catastrophic Disturbances in Interconnected Power Systems

This paper presents a decentralized emergency control approach for preventing voltage instability by controlling the reactive power and voltage of the system. The proposed control algorithm is based on a distributed architecture of intelligent agents to identify the affected region and to activate timely countermeasures to achieve a fast and accurate response. By dividing the network into several areas, the voltage instability problem can be localized and countermeasures can be directed to the most affected area by the authorized local agent. This facilitates quick decision making within the system. To achieve effective voltage and reactive power support, a sensitivity based zone formation is proposed. The Nordic32 74-bus test system has been used for testing the proposed multi-agent emergency control (MAEC). The results from the case studies demonstrate the effectiveness of the proposed MAEC approach.

A Bayesian Ensemble Regression Framework on the Angry Birds Game

In this paper, we introduce AngryBER, an intelligent agent architecture on the Angry Birds domain that employs a Bayesian ensemble inference mechanism to promote decision-making abilities. It is based on an efficient tree-like structure for encoding and representing game screenshots, where it exploits its enhanced modeling capabilities. This has the advantage to establish an informative feature space and translate the task of game playing into a regression analysis problem. A Bayesian ensemble regression framework is presented by considering that every combination of objects’ material and bird type has its own regression model. We address the problem of action selection as a multiarmed bandit problem, where the upper confidence bound (UCB) strategy has been used. An efficient online learning procedure has been also developed for training the regression models. We have evaluated the proposed methodology on several game levels, and compared its performance with published results of all agents that participated in the 2013 and 2014 Angry Birds AI competitions. The superiority of the new method is readily deduced by inspecting the reported results.

Behavior control as a function of consciousness. II. Synthesis of a behavior plan

Procedures for forming an element of an actor's world model (sign) introduced in the first part of this study are considered. The process of forming the pair image---sign significance taking into account the modern understanding of the human brain cortex operation is investigated. An algorithm for synthesizing a behavior plan is constructed, and a novel architecture of intelligent agents that are able, among other things, to distribute roles in coalitions is proposed.

Now All Together: Overview of Virtual Health Assistants Emulating Face-to-Face Health Interview Experience

We discuss a large research project aimed at building socially expressive virtual health agents or assistants (VHA) that can deliver brief motivational interventions (BMI) for behavior change, in a communication style that individuals and patients not only accept, but also find emotionally supportive and socially appropriate. Because of their well-defined sequential structure, BMIs lend themselves well to automation, and are adaptable to address a variety of target behaviors, from obesity, to alcohol and drug use, to lack treatment adherence, among others. We discuss the advantages that VHAs provide for the delivery of health interventions. We describe components of our intelligent agent architecture that enables our virtual health agents to dialogue with users in realtime while delivering the appropriate intervention based on the patient’s specific needs at the time. We conclude by identifying open research challenges in developing virtual health agents.

A Decentralized Multiagent-Based Voltage Control for Catastrophic Disturbances in a Power System

In this paper, a multiagent-based voltage and reactive power control in the case of a multiple contingency is presented. Incorporating the agent-based autonomous feature to the intelligence of the remote terminal units, the present power system control structure can be used to help in preventing system voltage collapse during catastrophic disturbances. The control algorithm is based on a decentralized architecture of intelligent agents and the determination of a local zone that can carry out quick countermeasures in a decentralized manner as a multiagent system (MAS) during an emergency situation. An adaptive determination of the local zones undergoing voltage collapse has been developed based on the electrical distances among the generators and loads. Once assigned, the elements of the Jacobian matrix can be used to determine the optimum actions that need to be carried out at each power system element (such as increasing the voltages of generators and load shedding) within the assigned local zone. The contract net protocol is used for agent interactions. Simulation results using the IEEE-57 bus system show that the proposed method can act quickly to respond to emergency conditions to ensure that voltage collapse can be avoided.

Power distribution system service restoration bases on a committee-based intelligent agent architecture

Multi-agent technology is applied in this paper to solve the distribution system service restoration problems. Specifically, switches in the distribution systems are modeled as intelligent agents and organized as local power committees in a distribution system. The advantage of this approach is to utilize the solving ability of a local committee of agents who could coordinate with neighboring committees to achieve an agreement that satisfies the global objective of the power distribution system service restoration problems without relying on a pre-determined centralized optimization algorithm as traditional approaches. The proposed coordination method helps switches in the distributed local power committees to reach a consensus among many proposed service restoration solutions after faults are detected and isolated. We also take the voltage violations into consideration in the search of solutions. Two examples of different power distribution systems are presented to demonstrate how the algorithms of the coordination method can identify the best restoration solution among many proposed local candidate solutions. The simulation results show that the proposed committee-based multi-agent approach yields better performance than the previous methods.

Simulation of an Organization of Spatial Intelligent Agents in the Visual C#.NET Framework

 Abstract—Problem: This paper investigates the simulation of a community of spatial intelligent agents, an important issue for the implementation and evaluation of distributed algorithms. The research question is how to simulate this organization using Visual C#.NET. Objective: This paper intends to use the C# programming language to develop a simulator. In a simulated environment, a social agent needs to communicate with other agents and respond to received messages. Method: Our approach is to integrate the thread and delegate methods provided by the .NET framework. We enhance the architecture of a spatial intelligent agent in order to embed several in a simulated society. A basic C# program is presented to demonstrate how to implement a contract net protocol (CNP) among three simple agents. Results: Two results were achieved: 1) the responses and actions of three agents during a simulated CNP and 2) a simulated environment that contains distributed spatial intelligent agents that can interact with each other and a human user. Conclusion: The proposed methodology and presented code provide a flexible and efficient framework for C# developers to develop, simulate, and evaluate a society of advanced software agents using the .NET platform.

Agent-based Virtual Society Polygon for Simulation and Evaluation in Massive Mobile Services

Since there are phenomena that are too perplex to be observed through using traditional techniques of scientific investigation, there are tools allowing reconstructing them in a simplified form. Agent-Based modeling has established itself as one of these tools. Though the major analytical principle remains the same – decomposition of the complex object into primitive particles, models themselves are fluctuating from the simple ones (e.g. spatial segregation models) to those able to propose reproduction of crowds, transport/pedestrian flows and other interactions by implementing sophisticated intelligent agent architectures. However, the utilization of agent-based modeling is not limited to satisfying sole scientific interest, but may be used for the resolution of applied issues as well. A polygon focused on performing both investigative and practical tasks has been introduced to simulate collective response to the changing environmental conditions (e.g. in the course of the natural disaster). The model originally designed to be incorporated into the mobile service computational infrastructure to constitute a massive mobile service for decision-making support is described throughout the paper. The potential use of the obtained simulation results in the analysis of emerging issues under conditions of social and infrastructural disorder is discussed with special reference to natural disasters. Further perspectives of implementation of present model in decision-making assistance are outlined as well.

Intelligent machine agent architecture for adaptive control optimization of manufacturing processes

Intelligent agents have been earmarked as the key enabling technology to provide the flexibility required by modern, competitive, customer-orientated manufacturing environments. Rational agent behavior is of paramount importance when interacting with these environments to ensure significant losses are not incurred. To achieve rationality, intelligent agents must constantly balance technical (process) and economic (enterprise wide) trade-offs through co-operation, learning and autonomy. The research presented in this manuscript integrates methodological commonalities in intelligent manufacturing research and prognostics to design and evaluate a generic architecture for the core services of self-learning, rational, machining process regulation agents. The proposed architecture incorporates learning, flexibility and rational decision making through the integration of heterogeneous intelligent algorithms (i.e. neural networks and genetic algorithms) from fields such as machine learning, data mining and statistics. The architecture’s ability to perceive, learn and optimize is evaluated on a high-volume industrial gun drilling process.

Identification of Relations between BDI Logic and BDI Agents

Identification of Relations between BDI Logic and BDI AgentsBDI (Beliefs, Desires, Intentions) is one of the most popular intelligent agent architectures which was inspired by multi-modal BDI logics. The main idea behind BDI is to implement system's behaviour by specifying it as a set of mental objects. This allows designing systems at a high level of abstraction which come closer to a human-like thinking. Although this architecture has been rapidly developing for about 20 years, its relevance to BDI logic is still arguable. This paper describes the basics of modal logic and main inference algorithms. Main concepts of BDI agents are presented and their relationships with BDI logic are discussed. Finally advantages and disadvantages of implementing BDI interpreter as a theorem prover are discussed.