Unified problem modeling language for knowledge engineering of complex systems

Abstract

The 90's has seen the emergence of hybrid configurations of four most commonly used intelligent methodologies, namely, symbolic knowledge based systems (e.g. expert systems), artificial neural networks, fuzzy systems and genetic algorithms. These hybrid configurations are used for different problem solving tasks/situations. In this paper we describe unified problem modeling language at two different levels, the task structure level for knowledge engineering of complex data intensive domains, and the computational level of the task level hybrid architecture. Among other aspects, the unified problem modeling language considers various intelligent methodologies and their hybrid configurations as technological primitives used to accomplish various tasks defined at the task structure level. The unified problem modeling language is defined in the form of five problem solving adapters. The problem solving adapters outline the goals, tasks, percepts/inputs, and hard and soft computing methods for modeling complex problems. The task structure level has been applied in modeling several applications in e-commerce, image processing, diagnosis, and other complex, time critical, and data intensive domains. We also define a layered intelligent multi-agent, operating system processes, intelligent technologies with the task structure level associative hybrid architecture. The layered architecture also facilitates component based software modeling process.Keywords Soft computing, Knowledge engineering, Multilayered agents, Unified problem modeling language IntroductionTasks and methods can be considered as mediating concepts in problem solving (Chandersekaran, 1990;Chandrasekaran et al., 1992). Artificial intelligence and computational intelligence researchers have been involved in developing problem solving architectures for complex tasks. These two areas have also come to represent the macro and microstructure levels of intelligence as described by Bezdek (1994). Bezdek (1994) in a model of intelligent systems has outlined three levels of intelligent activity, namely, computational, artificial, and biological.The computational level (or the lowest level), according to the model, deals with numeric data and involves pattern recognition, whereas the artificial intelligence level augments the computational level by adding small pieces of knowledge to the computational processes. The biological intelligence level (the highest level) processes sensory inputs and, through associate memory, links many subdomains of biological neural networks to recall knowledge (Bezdek 1994;Medskar, 1995). The computational and the artificial levels according to Bezdek (1994) lead to the biological level. An integration of the computational and artificial intelligence levels can thus be considered as a way of modeling biological intelligence. The computational intelligence is also known as the soft computing level with intelligent soft computing methodologies like fuzzy systems, artificial neural networks and genetic algorithms. These different levels ...

Performance optimization of data mining applications using a multi-layered multi-agent data mining architecture

“…The problem solving ontology layer is to conceptualise any specific problems to be solved in a construct of five phases, which are preprocessing, decomposition, control decision, and post-processing. Further details can be found in [1], [4], and [2]. The optimization layer, which is focused on this paper, is discussed in the next section.…”