• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.7
• /
• pp.680-688
• /
• 2001

In this paper, we propose a reliable method for searching the optimally performing generalized brain-state-in-a-box (GBSB) neural associative memory using an evolution program (EP) given a set of prototype patterns to be stored as stable equilibrium points. First, we exploit some qualitative guidelines necessary to synthesize the GBSB model. Next, we parameterize the solution space utilizing the limited number of parameters to represent the solution space. Then, we recast the synthesis of GBSB neural associative memories as two constrained optimization problems, which are equivalent to finding a solution to the original synthesis problem. Finally, we employ an evolution program (EP), which enables us to find an optimal set of parameters related to the size of domains of attraction (DOA) for prototype patterns. The validity of this approach is illustrated by a design example and computer simulations.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2002.05a
• /
• pp.195-200
• /
• 2002

ART (Adaptive Resonance Theory [1]) neural network and its variations perform non-hierarchical clustering by unsupervised learning. We propose a scheme "arboART" for hierarchical clustering by using several ART1.5-SSS networks. It classifies multidimensional vectors as a cluster tree, and finds features of clusters. The Basic idea of arboART is to use the prototype formed in an ART network as an input to other ART network that has looser distance criteria (Ishihara, et al., [2,3]). By sending prototype vectors made by ART to one after another, many small categories are combined into larger and more generalized categories. We can draw a dendrogram using classification records of sample and categories. We have confirmed its ability using standard test data commonly used in pattern recognition community. The clustering result is better than traditional computing methods, on separation of outliers, smaller error (diameter) of clusters and causes no chaining. This methodology is applied to Kansei evaluation experiment data analysis.

• The Journal of the Korea Contents Association
• /
• v.5 no.1
• /
• pp.109-116
• /
• 2005

This paper is to develop the prototype of a decision making for loan granting system at banks and to evaluate the effectiveness of it. The prototype is called at FENET-LG in this paper. The decision to grant a loan is an unstructured and vagueness task because it is required a tremendous amount of data and many complex relationships among them. Evaluating these many data and relationships is a difficult task even for most experienced decision maker of bank. Therefore, where complex judgement is required, the decision maker of bank may benefit from the use of fuzzy expert network to support the evaluation of ability to pay back. Given the characteristics of decision maker of banking facilities judgement task about ability to pay back, the prototype system named FENET-LG is constructed by integration of fuzzy expert system and neural network. The FENET-LG takes advantage of both the deductive approach of fuzzy expert system and the inductive approach of a neural network to provide a decision aid designed to support and facilitate the process of conducting a judgement of ability to pay back.

• Journal of Biosystems Engineering
• /
• v.26 no.2
• /
• pp.147-154
• /
• 2001

In Korea and Japan, dried oak mushrooms are classified into 12 to 16 different categories based on its external visual quality. And grading used to be done manually by the human expert and is limited to the randomly sampled oak mushrooms. Visual features of dried oak mushrooms dominate its quality and are distributed over both sides of the gill and the cap. The 2nd prototype computer vision based automatic grading and sorting system for dried oak mushrooms was developed based on the 1st prototype. Sorting function was improved and overall system for grading was simplified to one stage grading instead of two stage grading by inspecting both front and back sides of mushrooms. Neuro-net based side(gill or cap) recognition algorithm of the fed mushroom was adopted. Grading was performed with both images of gill and cap using neural network. A real time simultaneous discharge algorithm, which is good for objects randomly fed individually and for multi-objects located along a series of discharge buckets, was developed and implemented to the controller and the performance was verified. Two hundreds samples chosen from 10 samples per 20 grade categories were used to verify the performance of each unit such as feeding, reversing, grading, and discharging unites. Test results showed that success rates of one-line feeding, reversing, grading, and discharging functions were 93%, 95%, 94%, and 99% respectively. The developed prototype revealed successful performance such as the approximate sorting capability of 3,600 mushrooms/hr per each line i.e. average 1sec/mushroom. Considering processing time of approximate 0.2 sec for grading, it was desired to reduce time to reverse a mushroom to acquire the reversed surface image.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.05d
• /
• pp.1040-1045
• /
• 2002

This paper described the developed website usability evaluation system in terms of Kansei engineering using neural network. Developed system simultaneously operates with the MS Internet Explorer by entering the target URL for usability evaluation, and the results are learned using neural network. We firstly derived the Kansei adjectives and website usability factors and they were matched by the correspondence analysis. Then, highly corresponded adjectives were implemented on the system for the Kansei evaluation. Finally, the results showed the appropriate efficiency of developed algorithm and system for the website evaluation. If more subjects were used for the system learning, the efficiency of system could be improved.

• Proceedings of the KIEE Conference
• /
• 1997.07c
• /
• pp.1130-1132
• /
• 1997

This paper proposed an application of artificial neural networks to security assessment(SA) in power system. The SA is a important factor in power system operation, but conventional techniques have not achieved the desired speed and accuracy. Since the SA problem involves classification, pattern recognition, prediction, and fast solution, it is well suited for Kohonen neural network application. Self organizing feature map(SOFM) algorithm in this paper provides two dimensional multi maps. The evaluation of this map reveals the significant security features in power system. Multi maps of multi prototype states are proposed for enhancing the versatility of SOFM neural network to various operating state.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.22 no.3
• /
• pp.66-73
• /
• 2008

This paper presents a position sensorless control system of SRM over wide speed range. Due to the doubly salient structure of the SRM, the phase inductance varies along with the rotor position. Most of the sensorless control techniques are based on the fact that the magnetic status of the SRM is a function of the angular rotor position. The rotor position estimation of the SRM is somewhat difficult because of its highly nonlinear magnetizing characteristics. In order to estimate more accurate rotor position over wide speed range, Neural Network is used for this highly nonlinear function approximation. Magnetizing data patterns of the prototype 1-hp SRM are obtained from locked rotor test, and used for the Neural Network training data set. Through measurement of the flux-linkage and phase currents, rotor position is able to estimate from current-flux-rotor position lookup table which is constructed from trained Neural Network. Experimental results for a 1-hp SRM over 16:1 speed range are presented for the verification of the proposed sensorless control algorithm.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.10
• /
• pp.963-968
• /
• 2010

This paper handles ZMP based control that is inspired by neural networks for humanoid robot walking on varying sloped surfaces. Humanoid robots are currently one of the most exciting research topics in the field of robotics, and maintaining stability while they are standing, walking or moving is a key concern. To ensure a steady and smooth walking gait of such robots, a feedforward type of neural network architecture, trained by the back propagation algorithm is employed. The inputs and outputs of the neural network architecture are the ZMPx and ZMPy errors of the robot, and the x, y positions of the robot, respectively. The neural network developed allows the controller to generate the desired balance of the robot positions, resulting in a steady gait for the robot as it moves around on a flat floor, and when it is descending slope. In this paper, experiments of humanoid robot walking are carried out, in which the actual position data from a prototype robot are measured in real time situations, and fed into a neural network inspired controller designed for stable bipedal walking.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.4C
• /
• pp.185-190
• /
• 2005

In IS-95 and IMT-2000 systems using variable code rates and constraint lengths, this paper limits code rate 1/2 and constraint length 3 and realizes forward real-time decoder using Sliding-Window with decoding length 6 and PVSL(Prototype Vector Selecting Logic), LVQ(Learning Vector Quantization) in Neural Network. In comparison condition to theoretically constrained AWGN channel environment at $S/(N_{0}/2)=1$ I verified the superiority of forward real-time decoder through hard-decision and soft-decision comparison between Viterbi decoder and forward real-time decoder such as BER and Secure Communication and H/W Structure.

• Agricultural and Biosystems Engineering
• /
• v.4 no.1
• /
• pp.8-15
• /
• 2003

In Korea, quality evaluation of dried oak mushrooms are done first by classifying them into more than 10 different categories based on the state of opening of the cap, surface pattern, and colors. And mushrooms of each category are further classified into 3 or 4 groups based on its shape and size, resulting into total 30 to 40 different grades. Quality evaluation and sorting based on the external visual features are usually done manually. Since visual features of mushroom affecting quality grades are distributed over the entire surface of the mushroom, both front (cap) and back (stem and gill) surfaces should be inspected thoroughly. In fact, it is almost impossible for human to inspect every mushroom, especially when they are fed continuously via conveyor. In this paper, considering real time on-line system implementation, image processing algorithms utilizing artificial neural network have been developed for the quality grading of a mushroom. The neural network based image processing utilized the raw gray value image of fed mushrooms captured by the camera without any complex image processing such as feature enhancement and extraction to identify the feeding state and to grade the quality of a mushroom. Developed algorithms were implemented to the prototype on-line grading and sorting system. The prototype was developed to simplify the system requirement and the overall mechanism. The system was composed of automatic devices for mushroom feeding and handling, a set of computer vision system with lighting chamber, one chip microprocessor based controller, and pneumatic actuators. The proposed grading scheme was tested using the prototype. Network training for the feeding state recognition and grading was done using static images. 200 samples (20 grade levels and 10 per each grade) were used for training. 300 samples (20 grade levels and 15 per each grade) were used to validate the trained network. By changing orientation of each sample, 600 data sets were made for the test and the trained network showed around 91 % of the grading accuracy. Though image processing itself required approximately less than 0.3 second depending on a mushroom, because of the actuating device and control response, average 0.6 to 0.7 second was required for grading and sorting of a mushroom resulting into the processing capability of 5,000/hr to 6,000/hr.