An Architecture for Adaptive Intelligent Systems.

Abstract

We identify a class of niches to be occupied by 'adaptive intelligent sy^ms (AISs)'. In contrast with niches occupied by typ ical AI agents, AIS niches present situations that vary dynamically along several key dimensions: different combinations of required tasks, different configurations of available resources, contextual conditions ranging from benign to stressful, and different performance criteria. We present a small class hierarchy of AIS niches that exhibit these dimensions of variability and describe a particular AIS niche, ICU (intensive care unit) patient monitoring, which we use for illustration throughout the paper. We have designed and implemented an agent architecture that supports all of different kinds o adaptation by exploiting a single underlying t heoretical concept: An agent dynamicallA co n structs explicit control plans to guide its choices among situation-triggered behaviors. We illustrate the architecture and its support for adaptation with examples from Guardian, an experimental agent for ICU monitoring. AbstractOur goal is to understand and build comprehensive agents that function effectively in challenging niches. In particular, we identify a class of niches to be occupied by "adaptive intelligent systems (AISs)." In contrast with niches occupied by typical Al

Investigation of public’s perception towards rural sustainable development based on a two-level expert system

“…Normally, knowledge could be extracted through identification, conceptualization, filtration, and induction from various sources including experts, journal papers, reports, textbooks, and related databases. Knowledge acquisition is a difficult and time-consuming process and is commonly recognized as a bottleneck in the development of an expert system (Hayes-Roth, 1995). Consequently, effective methods of knowledge acquisition are critical in building an expert system (Huang et al, 2005).…”

Agents: Agenthood, Agent Architectures, and Agent Taxonomies

“…In contrast, (Hayes-Roth, 1995) emphasizes the traditional artificial intelligence view on agents by assuming that all agents use explicitly reasoning mechanisms: "Intelligent agents continuously perform three functions: perception of dynamic conditions in the environment; action to affect conditions in the environment; and reasoning to interpret perceptions, solve problems, draw inferences, and determine actions. ".…”

“…We already used several of their arguments to define agenthood. Franklin and Graesser analyzed several approaches to agent definitions; among those are the same definitions we referred to earlier in this chapter: Wooldridge and Jennings (Wooldridge and Jennings, 1995) and Hayes-Roth (Hayes-Roth, 1995). They use the following working definition: "An autonomous agent is a system situated within and a part of an environment that senses that environment and acts on it, over time, in pursuit of its own agenda and so as to affect what it senses in the future".…”

Concurrent Metareasoning

“…One may classify metareasoning by considering its role to increase the speed of reasoning [27], to improve the quality of results (see the case study in Section 4), and to change the functionality of the reasoner [18,40]. These aspects are related to and evaluated by the outcome of metareasoning.…”