Given the set of minimal paths between two vertices in a network, this paper shows that the system reliability can be obtained by using a Binary Decision Digram. It can be done by transforming a Boolean sum of products into a Binary Decision Diagram and the reliability can be directly derived from it. The resulting reliability expression is compact and requires relatively fewer arithmetic opersations in its evaluation. Several examples are given to show that the method using Binary Decision Diagram is conceptually casy, simple and efficient.

In this Paper, a rule-based method for the phenomenon of Korean vocal sound change is proposed. This method could be used to solve a problem between symbolic(Hangul)and phonetic language(Korean) for the study of Korean speech processing. A rule on the phenomenon of vocal sound rearranged for the rule base with a end-consonents on the authority of standard pronunciation rule. The proposed rule base system is simplified by the implementation for the vocal sound change. Also, it is useful to create the data base with phonetic value for the Korean voice processing by syllable unit.

In this paper, we give a structure algorithm for the synthesis problems of the nonlinear system via dynamic feedback. Using our algorithm, sufficient conditions for the input-output synthesis problems are discussed. The problems we consider in this paper include dynamic input-output decoupling input-output linearization, and immersion into a linear system.

In this paper, the novel PLD (Preceding Layer Driven) MLP (Multi Layer Perceptron) neural network model and its learning algorithm is described. This learning algorithm is different from the conventional. This integer weights and hard limit function are used for synaptic weight values and activation function, respectively. The entire learning process is performed by layer-by-layer method. the number of layers can be varied with difficulty of training data. Since the synaptic weight values are integers, the synapse circuit can be easily implemented with CMOS. PLD MLP neural network was applied to English Characters, arbitrary waveform generation and spiral problem.

A current-controlled scheme of pulse width modulation voltage source inverter (PWM VSI) has attracted considerable attention due to its fast response with current limit and especially suitable for potentially high performance applications such as AC motor drives and UPS systems. These features yield near-sinusoidal currents in the load with reduced current peaks, lower inverter switching frequency and reduce inverter and load stresses. A high performance current-controlled inverter must have a quick response in transient state and low harmonic current in steady state. This paper compares and shows the controlled-characteristics with hysteresis controller(HC), ramp comparison controller(RCC) and predictive controller(PC) of PWM inverter to control actual current of VSI-IM.

In this paper, we propose a multiresolution edge detection method which selects the edge detection window size and scale automatically by using the local variance information as an edgeness measure of a region. The mode of the local variance distribution which is calculated over the (2p + 1) x (2p + 1) windows is used to determine the resolution of the given pixel and the edge operator with different scale can be applied to the pixel depending on its resolution. The combination of the resolution determination scheme with the conventional Canny and LOG edge detectors gives the proposed multiresolution edge detection schemes. The effectness of the proposed schemes is shown via computer simulation.

In this paper, we aimed to develop associative pattern recognizer based on neural network for aircraft identification. For obtaining invariant feature space description of an object regardless of its scale change and rotation, Log-polar sampling technique recently developed partly due to its similarity to the human visual system was introduced with Fourier transform post-processing. In addition to the recognition results, image recall was associatively performed and also used for the visualization of the recognition reliability. The multilayer perceptron model was learned by backpropagation algorithm.

This paper proposes a HMM model based on fuzzy, as a method on the speech recognition of speaker-independent. In this recognition method, multi-observation sequences which give proper probabilities by fuzzy rule according to order of short distance from VQ codebook are obtained. Thereafter, the HMM model using this multi-observation sequences is generated, and in case of recognition, a word that has the most highest probability is selected as a recognized word. The vocabularies for recognition experiment are 146 DDD are names, and the feature parameter is 10S0thT LPC cepstrum coefficients. Besides the speech recognition experiments of proposed model, for comparison with it, we perform the experiments by DP, MSVQ and general HMM under same condition and data. Through the experiment results, it is proved that HMM model using fuzzy proposed in this paper is superior to DP method, MSVQ and general HMM model in recognition rate and computational time.

We proposed an optimal parallel implementation of an optimization neural network with linear increase of speedup by using multicomputer system and presented performance analysis model of the system. We extracted the temporal-and the spatial-parallelism from the optimization neural network and constructed a parallel pipeline processing model using the parallelism in order to achieve the maximum speedup and efficiency on the CSP architecture. The results of the experiments for the TSP using the Transputer system, show that the proposed system gives linear increase of speedup proportional to the size of the optimization neural network for more than 140 neurons, and we can have more than 98% of effeciency upto 16-node system.