• Journal of the Korean Home Economics Association
• /
• v.35 no.4
• /
• pp.139-148
• /
• 1997

The rates of subcutaneos fat on the system of clothing weights including clothing microclimate subjective sensations were measured to get basic data to develop guideline for healthy clothing life. for this study skinfold thickness the rate of subcutaneos fot clothing microclimate subjective sensations and clothing weights were measured from 85 male and 105 female colligians. The results were as follows: 1. The rate of subcutaneos fat showed negative correlation with the temperature inside clothing in chest but not with the temperatures in back and thigh. The correlation was not significant between the rate of subcutaneos fat and humidity inside clothing 2. The correlation between the rate of subcutaneos fat and thermal sensations was positively significant at 5% level. However no correlation was found between the rate of subcutaneos fat and humid sensations. 3. There was significant correlation between the rate of subcutaneos fat and under clothing weights and total clothing weights.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.6
• /
• pp.1213-1220
• /
• 2011

In this paper, a new ensemble system using dynamic weighting method with added weight information into classifiers is proposed. The weights used in the traditional ensemble system are those after the training phase. Once extracted, the weights in the traditional ensemble system remain fixed regardless of the test data set. One way to circumvent this problem in the gating networks is to update the weights dynamically by adding processes making architectural hierarchies, but it has the drawback of added processes. A simple method to update weights dynamically, without added processes, is proposed, which can be applied to the already established ensemble system without much of the architectural modification. Experiment shows that this method performs better than AdaBoost.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.10 no.1
• /
• pp.43-48
• /
• 2010

This article presents the experimental studies of controlling angle and position of the inverted pendulum system using neural network to compensate for errors caused due to fuzzy controller. Although fuzzy control method can deal with nonlinearities of the system, fixed fuzzy rules may not work and result in tracking errors in some cases. First, a nominal Takagi-Sugeno (TS) type fuzzy controller with fixed weights is used for controlling the inverted pendulum system. Then the neural network is added at the reference input to form the reference compensation technique (RCT)control structure. Neural network modifies the input trajectories to improve system performances by updating internal weights in on-line fashion. The back-propagation learning algorithm for neural network is derived and used to update weights. Control hardware of a DSP 6713 board to have real time control is implemented. Experimental results of controlling inverted pendulum system are conducted and performances are compared.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1074-1077
• /
• 1993

The objective of this paper is to develop a fuzzy logic based decision-making system to detect low current faults using multiple detection algorithms. This fuzzy system utilizes a fuzzy expert model which executes an operation without complicated mathematical models. This fuzzy system decides the performance weights of the detection algorithms. The weights and the turnouts of the detection algorithms discriminate faults from normal events. This system can also be a generic group decision-making tool for other areas of power system protection.

• Journal of Korean Society for Quality Management
• /
• v.27 no.4
• /
• pp.95-113
• /
• 1999

This paper is to propose an evaluation model of quality system using the concept from the evaluation method of each stage in QFD(Quality Function Deployment). The data of the performance level and weights for the quality system and the job on quality loop in each enterprise has been obtained from the 8 experts who are in charge of quality system construction. Here, the weights were computed by means of the eigenvector method. In this paper, we can acquire the evaluated score for the present level of the quality system. This method will help to manage and improve the quality system. We show the efficiency of this method by illustrating case studies.

• Journal of the Korean Mathematical Society
• /
• v.45 no.5
• /
• pp.1203-1220
• /
• 2008

Let V be an arbitrary system of weights on an open connected subset G of ${\mathbb{C}}^N(N{\geq}1)$ and let B (E) be the Banach algebra of all bounded linear operators on a Banach space E. Let $HV_b$ (G, E) and $HV_0$ (G, E) be the weighted locally convex spaces of vector-valued analytic functions. In this paper, we characterize self-analytic mappings ${\phi}:G{\rightarrow}G$ and operator-valued analytic mappings ${\Psi}:G{\rightarrow}B(E)$ which generate weighted composition operators and invertible weighted composition operators on the spaces $HV_b$ (G, E) and $HV_0$ (G, E) for different systems of weights V on G. Also, we obtained compact weighted composition operators on these spaces for some nice classes of weights.

• Journal of Multimedia Information System
• /
• v.9 no.3
• /
• pp.177-182
• /
• 2022

A deep neural network (DNN) includes variables whose values keep on changing with the training process until it reaches the final point of convergence. These variables are the co-efficient of a polynomial expression to relate to the feature extraction process. In general, DNNs work in multiple 'dimensions' depending upon the number of channels and batches accounted for training. However, after the execution of feature extraction and before entering the SoftMax or other classifier, there is a conversion of features from multiple N-dimensions to a single vector form, where 'N' represents the number of activation channels. This usually happens in a Fully connected layer (FCL) or a dense layer. This reduced 2D feature is the subject of study for our analysis. For this, we have used the FCL, so the trained weights of this FCL will be used for the weight-class correlation analysis. The popular DNN models selected for our study are ResNet-101, VGG-19, and GoogleNet. These models' weights are directly used for fine-tuning (with all trained weights initially transferred) and scratch trained (with no weights transferred). Then the comparison is done by plotting the graph of feature distribution and the final FCL weights.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.46 no.3
• /
• pp.204-213
• /
• 2010

Test fishing was carried out using six kinds of different mesh sizes (20, 22, 24, 28, 35, 40mm) for springnet-pot to study bycatches according to the mesh size and catches survey was done for another one (mesh size : 22mm, entrance round : 350mm) in Geo-je & Tong-young waters of Korea. On the first sea experiment, it was thought that suitable mesh size of spring-net-pot catching conger-eel over 35cm with decreasing the catches of conger-eel (Conger myriaster) below 35cm was 24mm. On the second sea experiment, commercial catches were crabs (Charybdis bimaculata), octopus minor (Octopus variabilis) and others including conger-eel, and catches proportion was 60% of total catches weights. There was no big difference for the monthly catches. Self-consumption catches were 9 species including conger-eel below 35cm holding 50% of catches in the side of weights. There were 40% of bycatches for the catches weights and 63% for catches numbers in the 22mm mesh size of spring-net-pot having entrance round over 140mm. It showed that 50% of catches weights were discarded.

• Proceedings of the KIEE Conference
• /
• 2002.07b
• /
• pp.1137-1139
• /
• 2002

In this paper, recurrent artificial neural network (RNN) based self tuning speed controller is proposed for the high performance drives of induction motor. RNN provides a nonlinear modeling of motor drive system and could give the information of the load variation, system noise and parameter variation of induction motor to the controller through the on-line estimated weights of corresponding RNN. Thus, proposed self tuning controller can change gains of the controller according to system conditions. The gain is composed with the weights of RNN. For the on-line estimation of the weights of RNN, extended kalman filter (EKF) algorithm is used. Self tuning controller that is adequate for the speed control of induction motor is designed. The availability of the proposed controller is verified through the MATLAB simulation with the comparison of conventional PI controller.

• KIEE International Transaction on Electrical Machinery and Energy Conversion Systems
• /
• v.3B no.2
• /
• pp.97-102
• /
• 2003

In this paper, a recurrent artificial neural network (RNN) based self-tuning speed controller is proposed for the high-performance drives of induction motors. The RNN provides a nonlinear modeling of a motor drive system and could provide the controller with information regarding the load variation system noise, and parameter variation of the induction motor through the on-line estimated weights of the corresponding RNN. Thus, the proposed self-tuning controller can change the gains of the controller according to system conditions. The gain is composed with the weights of the RNN. For the on-line estimation of the RNN weights, an extended Kalman filter (EKF) algorithm is used. A self-tuning controller is designed that is adequate for the speed control of the induction motor The availability of the proposed controller is verified through MATLAB simulations and is compared with the conventional PI controller.