• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.9
• /
• pp.117-123
• /
• 1996

In this paper, we present a new learning method for the fuzzy ARTMAP which is effective for the noisy input patterns. Conventional fuzzy ARTMAP employs only fuzzy AND operation between input vector and weight vector in learning both top-down and bottom-up weight vectors. This fuzzy AND operation causes excessive update of the weight vector in the noisy input environment. As a result, the number of spurious categories are increased and the recognition ratio is reduced. To solve these problems, we propose a new method in updating the weight vectors: the top-down weight vectors of the fuzzy ART system are updated using weighted average of the input vector and the weight vector itself, and the bottom-up weight vectors are updated using fuzzy AND operation between the updated top-down weitht vector and bottom-up weight vector itself. The weighted average prevents the excessive update of the weight vectors and the fuzzy AND operation renders the learning fast and stble. Simulation results show that the proposed method reduces the generation of spurious categories and increases the recognition ratio in the noisy input environment.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.42 no.1
• /
• pp.68-72
• /
• 2009

To gain a greater understanding of the potential for future harmful algal bloom (HAB) outbreaks and to trace the dispersal paths of dinoflagellates, sediment samples were collected from 13 stations in the southeastern Yellow Sea. 23 different types of dinoflagellate resting cysts were identified from the samples. Protoceratium reticulatum (1-391 cells/g dry weight), Gonyaulax scrippsae (0-254 cells/g dry weight), G. spinifera (0-301 cells/g dry weight) and Alexandrium spp. (ellipsoidal type) (0-76 cells/g dry weight) were the dominant species at all surveyed stations. The overall distribution pattern demonstrated that the resting cyst densities were highest in the offshore area and decreased gradually toward the Korean coast. On the other hand, the composition rate of resting cysts of the heterotrophic dinoflagellate species to the total dinoflagellates was higher in the Korean coast region than in the offshore area. We supposed that this distribution pattern of dinoflagellate resting cysts appeared to be influenced by the hydrographic features and environmental conditions of the Yellow Sea.

• Journal of the Korean Society of Food Culture
• /
• v.13 no.3
• /
• pp.207-214
• /
• 1998

This study was undertaken to assess eating habits and food consumption pattern of 365 adolescent girls in Kwangju area. Subjects were divided into 3 groups based on relative body weight as obesity index. Anthropometric data showed that mean height and weight were $161.9{\pm}19.0cm$ and $53.3{\pm}7.2kg$ respectively which are similar to those in the Korean Standard Growth data. Mean BMI and relative body weight were 20.50 and 97.1%. Age of menarche in the subjects significantly influenced the obesity index. Food habit score in the underweight group was significantly lower than that in the normal group at ${\alpha}=0.2$ level by multiple range test. Obesity was significantly associated with more frequent and irregular eating. It seems that students in the obese group were concerned on their body weight and tended to consume much vegetable. Obese group consumed more fruits, less butter and fruit juice compared to other groups. It might be suggested that more effective nutrition program might be developed and implemented to ensure good food habit of adolescent girls including obese as well as underweight group.

• Asian-Australasian Journal of Animal Sciences
• /
• v.8 no.1
• /
• pp.67-73
• /
• 1995

This study showed that models of energy utilization(EU) developed for grazing cattle in oil palm plantations is valid as the simulated results shows an agreement with actual data of calves and cows body weight changes collected from Brahman x Kedah-Kelantan herd on Pengeli Timor Plantation. Simulation runs on EU models demonstrated that the growth pattern of male and female calves and the weight changes of cows are similar and showed slight variation from the actual data but with no significant difference (p > 0.05). Parameter values such as metabolizability (q), dry matter digestibility(DMD) of herbage and voluntary intake of grazing cattle (VIG) and faecal output/body weight ratio (F) of the animals which were collected from the field are essential in bearing the pattern of body weight changes of the calves and cows in relation to increase in time, physiological status and quality of herbage grazed by these animals in the production system. The EU models is suitable for determining the metabolizable energy requirements and to predict the production of grazing cattle according to quality of the feed on offer.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.40 no.2
• /
• pp.224-233
• /
• 1991

The multilayer expanson of single layer NN (Neural Network) was needed to solve the linear seperability problem as shown by the classic example using the XOR function. The EBP (Error Back Propagation ) learning rule is often used in multilayer Neural Networks, but it is not without its faults: 1)D.Rimmelhart expanded the Delta Rule but there is a problem in obtaining Ca from the linear combination of the Weight matrix N between the hidden layer and the output layer and H, wich is the result of another linear combination between the input pattern and the Weight matrix M between the input layer and the hidden layer. 2) Even if using the difference between Ca and Da to adjust the values of the Weight matrix N between the hidden layer and the output layer may be valid is correct, but using the same value to adjust the Weight matrixd M between the input layer and the hidden layer is wrong. Recognitron III was proposed to solve these faults. According to simulation results, since Recognitron III does not learn the three layer NN itself, but divides it into several single layer NNs and learns these with learning patterns, the learning time is 32.5 to 72.2 time faster than EBP NN one. The number of patterns learned in a EBP NN with n input and output cells and n+1 hidden cells are 2**n, but n in Recognitron III of the same size. [5] In the case of pattern generalization, however, EBP NN is less than Recognitron III.

• Elastomers and Composites
• /
• v.57 no.4
• /
• pp.157-164
• /
• 2022

Representative bulletproof materials, such as aramid or ultra-high molecular weight polyethylene(UHMWPE), have excellent strength and modulus in the plane direction but are very vulnerable to forces applied in the thickness direction. This paper reports a study on the effects of reinforcement in the thickness direction when bulletproof composite fabrics are prepared to improve their performance. Aramid and UHMWPE fabrics were combined using the film-bonding, needle-punching, or stitching methods and then subjected to low-velocity projectile and ball-drop impact tests. The results of the low-velocity projectile test indicated that the backface signature(BFS) decreased by up to 29.2% in fabrics obtained via the film-bonding method. However, the weight of the film-bonded fabric increased by approximately 23% compared with that obtained by simple lamination, and the fabric stiffened on account of the binder. Flexibility, light weight for wearability, and excellent bulletproof performance are very important factors in the development of bulletproof materials. When the needle-punching method was used, the BFS increased as the fibers sustained damage by the needle. When the composite fabrics were combined by stitching, no significant difference in weight and thickness was observed, and the BFS showed similar results. When a diagonal stitching pattern was employed, the BFS decreased as the stitching density increased. By contrast, when a diamond stitching pattern was used, the fabric fibers were damaged and the BFS increased as the stitching density increased.

• Physical Therapy Korea
• /
• v.10 no.1
• /
• pp.29-35
• /
• 2003

Body weight support treadmill training is a new and promising therapy in gait rehabilitation of patients with hemiplegia. The purpose of this study was to identify the effects of body weight support treadmill training on gait and standing balance in patients with hemiplegia. Eighteen patients with hemiplegia participated in the study. A 10 m-timed walk test, measurements of step length and standing balance score were administered. Intervention consisted of body weight support treadmill training five times a week for 2 weeks. The data were analyzed by paired t-test. Body weight support treadmill training scoring of standing balance, step length and 10 m-timed walk test showed a definite improvement. Body weight support treadmill training offers the advantages of task-oriented training with numerous repetitions of a supervised gait pattern. The outcomes suggest that patients with hemiplegia can improve their gait ability and standing balance through body weight support treadmill training.

• Korean Journal of Community Nutrition
• /
• v.7 no.4
• /
• pp.495-505
• /
• 2002

A study was performed to develop as a screening tool the Simple Evaluation Questionnaire for Screening the Over-weight-type Dietary Pattern in 30 to 49 Year Old Adults. We used the data from the 30 to 49 year old subjects who participated in the three surveys - the health behavior survey, the dietary habit survey and the food intake survey - as the National Health and Nutrition Survey 1998. The 3,598 adults were classified into to two body fatness groups of normal (including underweight) and overweight (including obese) on the basis of their relative body weight (RBW) When comparing variables between the two groups, significant differences were found in gender, education, job, employment status, perceived health status, sadness / depression state, stress level, age, number of diseases, age when overweightedness started, maximum body weight, sleep length, drinking pattern (yes/no) , amount of alcoholic drinks, frequency of intoxication or drunkeness, amount of alcoholic drinks when drunk, intensity of exercise, frequency of exercise, exercise duration, skipped meals, small meals and drug supplements. In terms of food intake, there were significant differences in the daily food intake in terms of breakfast, dinner, daily kimchi and dairy products. In terms of mealtimes, we found differences in the amount of cooked rice at breakfast, kimchi at lunch, soup / kuk at dinner, fresh vegetables for snacks, fried foods for snacks between breakfast and lunch, and fruits /juices for snacks between lunch and dinner. After developing questions with indicators and analyzing the indicators by logistic regression analysis three times, we chose 10 questions for a simple evaluation of dietary patterns for the overweight-type category in order to give one point each. Among them we selected two questions to add one additional point and one question to add two additional points. The average scores of the overweight and normal groups, as shown by the developed questionnaire, were $5.97 \pm 2.36 \pm 7.36 \pm 2.21$, respectively. A score of seven points was selected as the cut-off point. We examined the sensitivity, specificity and positive predictive value of the questionnaire to the results of 67%, 59% and 62%, respectively.

• Journal of Korean Medicine Rehabilitation
• /
• v.24 no.4
• /
• pp.71-82
• /
• 2014

Objectives The purpose of this study was to investigate the effect of BMI (body mass index), blood parameters and life pattern on KOQOL (Korean version of obesity-related quality-of-life scale) in Health checkup examinees of college students. Methods A group of 2992 test subjects took their medical examination. With their height and weight, we diagnosed obesity according to BMI. KOQOL was measured by survey conducted using self-report questionnaires, after excluding sexual life related question. We analysed relationship between KOQOL and BMI, blood parameters, life pattern using SPSS version 21.0. Results 1. There were significant differences in KOQOL according to BMI, gender, creatinine. 2. Female showed higher KOQOL than male. 3. Normal weight group showed lowest KOQOL in male, but underweight group showed lowest KOQOL in female. 4. Group who had more than 6 breakfast, lunch and dinner each in a week showed significantly lower KOQOL than that who didn't. Conclusions Obesity has significant influence on quality of life, so therefore there is a need for correct weight perception in weight control program, and KOQOL can be used in evaluating patients mental and social health.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.2
• /
• pp.161-165
• /
• 2014

In this paper, we proposed the fuzzy prototype pattern classifier. In the proposed classifier, each prototype is defined to describe the related sub-space and the weight value is assigned to the prototype. The weight value assigned to the prototype leads to the change of the boundary surface. In order to define the prototypes, we use Fuzzy C-Means Clustering which is the one of fuzzy clustering methods. In order to optimize the weight values assigned to the prototypes, we use the Differential Evolutionary Algorithm. We use Linear Discriminant Analysis to estimate the coefficients of the polynomial which is the structure of the consequent part of a fuzzy rule. Finally, in order to evaluate the classification ability of the proposed pattern classifier, the machine learning data sets are used.