No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

After more than twenty years of development effort in expert and knowledge-based applications, there are indications of a growing uncertainty in the practical potential of such systems, especially within medical domains. Many difficulties have arisen from attempting to model human experts. These are particularly evident when considering unformalised or nonstandardised domains which are common characteristics of many specialist medical fields. Moreover, little attention has been paid to the prospective users of these systems, the tasks which are routinely undertaken or the environment in which the users must operate. These factors have all contributed to the continued lack of success of such systems. This research reviews the difficulties encountered during the development of know ledgebased systems and conventional systems. From these studies, the importance of fully considering end-users and their needs became evident. It also became apparent that currently, there is a lack of techniques available to medical investigators which would allow them to quickly, easily and thoroughly analyse the information they collect during their research studies. However, the ability to undertake such reviews is crucial if consultants are not only to extend their knowledge of their domain through exploration but if they are also to evolve agreed operational practices. This standardisation of approach would lead to a rationalisation of the tests and procedures routinely undertaken, which in turn would result in the saving of time, money and patient discomfort. Consequently, this research also examines the intended user group, the typical procedures followed and the common tasks undertaken during clinical trials, as well as the environment in which the user group operates. These studies uncovered the typical facilities and assistance required by such investigators. From this information, a general methodology, characterising the processes involved in the construction of a generic Intelligent Database Decision Aid (IDDA), was developed. A suite of computer-based tools then evolved to facilitate the tailoring of such a system by a domain expert, who may be a naive computer user, for a specific investigation. These tools would thus give total control of a study to the domain expert and permit an IDDA system to be quickly and easily constructed for each new investigation. The approach was evaluated by utilising test cases drawn primarily from the medical domain. However, as the methodology was based upon commonly accepted investigative procedures, it was also reviewed in other domains to test its wider applicability. All of the IDDA systems were successfully constructed and the feedback obtained from the trials was very positive, both for the approach adopted and the various IDDA end-systems produced. Therefore, the general methodology proposed by this research has been shown to be effective and its benefits can now begin to be realized.

Theory of Artificial Neural Networks (ANNs) could not provide an exact method of weights training. The training is done mostly by iterative trial and error minimisation methods which do not enable the ANNs for time incremental learning. In this thesis, it is shown that the weights successfully produced by an error minimisation method are nothing more than the scaled versions of their respective components of the sample pattern and that the training methods leaves a chance for a neuron to be deceived. An exact method of weight construction is developed in the form of a system of linear equations. A new linear classifier ANN and a number of thresholding procedures are developed. It is proved that the Hopfield network and the Boltzmann machine do not qualify as the reasonable networks. A generalised multiclass linear classifier ANN is developed which is a combination of a newly developed multiclass linear ANN and a newly developed multiclass XOR classifier ANN. A biological neuromuscular system is interpreted as a multiclass linear classifier ANN. A new technique for pattern recognition. especially for images, has been presented with a software check. The technique minimises the design topology of ANNs and enables them to classify a scaled, a mirror image, and a noisy version of the sample pattern. The Continuous Wavelet Transform (CWT), the Discrete Wavelet Transform, and the Wavelet Decomposition has been connected by developing an extend-able and intensifyable system of particular six Gaussian wavelets. A binary transform applicable for every real function is developed. The confusing automatic nature of the CWT is explained along with presenting a new style of defining wavelets. Application of the wavelet transforms for noise reduction and data compression/expansion is explained and their performance is checked through the self developed software. A modification in the CWT is made in order to make their application easier through ANNs. The ANNs are developed and their performance is checked against the self developed software. A new multiresolution zoom-out wavelet transform is developed which expands data without smoothing it. A new wavelet is deduced from the smoothing average filter. Some twodimensional wavelets for noise reduction and data compression/expansion are developed on the same style and their performance is checked through the self developed software. An ANN for CWT using a newly developed two-dimensional wavelet is developed and its activation is explained. Data compression by locating peaks and bottoms of data and setting other elements equals zero is done with the guarantee of reconstruction. The new wavelet transform is modified to reconstruct the data between peaks and bottoms. Peaks and bottoms detecting ANNs are developed and their performance is checked against the self developed software. Procedures for classification are presented with self developed software check. The theory of ANNs requires bit-wise parallel adders and multiplexors. A parallel adder circuit is developed by combining some newly developed basic units for the purpose.