Rule based

Hybrid systems. Depending on the problem to be solved, use can also be made of a combination of techniques leading to a hybrid system. For example, a rule-based system may use neural networks for solving classification subproblems (as is described in [Hopgood, 1993]), or a combination of a rule-based and a CBR system can be used as in the system for URS data interpretation described later in this paper. 

Expert systems. In situations where the statistical classifiers cannot be used, because of the complexity or inhomogeneity of the data, rule-based expert systems can sometimes be a solution. The complex images can be more readily described by rules than represented as simple feature vectors. Rules can be devised which cope with inhomogeneous data by, for example, triggering some specialised data-processing algorithms. 

Rule-based systems have the advantage that they usually report when they are incapable of recognising something. However, any disturbances in the inspection not foreseen during rule-hase construction will significantly lower the recognition ratio. 

Apart from the cost of knowledge acquisition, another disadvantage of rule-based systems is the difficulty of rule-base maintenance. Rule-base maintenance may be required when changes are made to the inspection system, the inspection procedures, or if differing constructions are inspected. The maintenance usually cannot be done by end-users. 

Tests were done on real data containing approx. 32(XX) nontrivial images. Of these approx. 25% were classified by the rule-based system and another 25% by the CBR system. The reliability was high - of 330 defects present in the data only two were classified as non-defects. We are currently working on further improving the recognition ratio and increasing the speed of the system. 

Figure 1 Schema of the hybrid rule-based/CBR system for interpretation of URS data.

The recognition ratios achieved by CBR systems developed as part of this project could not be bettered by either neural-network classifiers or rule-based expert system classifiers. In addition, CBR systems should be mote reliable than simple classifiers as they are programmed to recognise unknown data. The knowledge acquisition necessary to build CBR systems is less expensive than for expert systems, because it is simpler to describe the knowledge how to distinguish between certain types of data than to describe the whole data contents. 

The end users of CBR systems should in principle be able to maintain the case-bases themselves and use the systems for varying inspection types (within certain limits). Adaptation of neural-network based systems, though possible by end-users, is difficult to be done reliably. Adaptation of rule-based systems usually has to be done by the rule-base designer. 

DENDRAL proved to be fundamentally important in demonstrating how rule-based reasoning could be developed into powerful knowledge-engineering tools [93]. 

Metabolism is still a barrier to be overcome. Some QSAR, pharmacophore, protein, and rule-based models are available to predict substrates and inhibitors of a specific cytochrome P450 isoenzyme [47-55]. 

Rule-based Approaches Using Secondary Structure Prediction... 

Ihe rule-based approach to protein structure prediction is obviously very reliant on th quality of the initial secondary structure prediction, which may not be particularly accurate The method tends to work best if it is known to which structural class the protein belongs this can sometimes be deduced from experimental techniques such as circular dichroism... 

J1992. LUDI - Rule-Based Automatic Design of New Substituents for Enzyme Inhibitor Leads. mal of Computer-Aided Molecular Design 6 593-606. 

One variation of rule-based systems are fuzzy logic systems. These programs use statistical decision-making processes in which they can account for the fact that a specific piece of data has a certain chance of indicating a particular result. All these probabilities are combined in order predict a final answer. 

Rule-based systems try to identify certain subsequences of amino acids that tend to have a particular secondary structure, such as sheets, a-helices, (I-strands,... 

Isomeric alkenes may be either constitutional isomers or stereoisomers There is a sizable barrier to rotation about a carbon-carbon double bond which corresponds to the energy required to break the rr component of the double bond Stereoisomeric alkenes are configurationally stable under normal conditions The configurations of stereoisomeric alkenes are described according to two notational systems One system adds the prefix CIS to the name of the alkene when similar substituents are on the same side of the double bond and the prefix trans when they are on opposite sides The other ranks substituents according to a system of rules based on atomic number The prefix Z is used for alkenes that have higher ranked substituents on the same side of the double bond the prefix E is used when higher ranked substituents are on opposite sides... 

Rules. Rules, first pioneered by early appHcations such as Mycin and Rl, are probably the most common form of representation used in knowledge-based systems. The basic idea of rule-based representation is simple. Pieces of knowledge are represented as IE—THEN rules. IE—THEN rules are essentially association pairs, specifying that IE certain preconditions are met, THEN certain fact(s) can be concluded. The preconditions are referred to as the left-hand side (LHS) of the rule, while the conclusions are referred to as the right-hand side (RHS). In simple rule-based systems, both the... 

Rules may represent either guidelines based on experience, or compact descriptions of events, processes, and behaviors with the details and assumptions omitted. In either case, there is a degree of uncertainty associated with the appHcation of the rule to a given situation. Rule-based systems allow for expHcit ways of representing and dealing with uncertainty. This includes the representation of the uncertainty of individual rules, as weU as the computation of the uncertainty of a final conclusion based on the uncertainty of individual rules, and uncertainty in the data. There are numerous approaches to uncertainty within the rule-based paradigm (2,35,36). One of these approaches is based on what are called certainty factors. In this approach, a certainty factor (CF) can be associated with variable—value pairs, and with individual rules. The certainty of conclusions is then computed based on the CF of the preconditions and the CF for the rule. For example, consider the foUowing example. 

The certainty factor approach has been among the more popular rule-based approaches to uncertainty. However, although it is easy to apply given the individual CFs, acquiring the raw CFs from the experts is often quite difficult. Further, although the formulas for CF combination are mathematically appealing, they often have no relation to the ways in which experts combine evidence to arrive at conclusions. Some of the task-specific approaches discussed later address uncertainty combination in a more intuitive way (35). 

---