• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.28B no.9
• /
• pp.739-746
• /
• 1991

This paper develops a modified multilayer perceptron architecture which speeds up learning as well as the net's mapping accuracy. In Phase I, a cluster partitioning algorithm like the Kohonen's self-organizing feature map or the leader clustering algorithm is used as the front end that determines the cluster to which the input data belongs. In Phase II, this cluster selects a subset of the hidden layer nodes that combines the input and outputs nodes into a subnet of the full scale backpropagation network. The proposed net has been applied to two mapping problems, one rather smooth and the other highly nonlinear. Namely, the inverse kinematic problem for a 3-link robot manipulator and the 5-bit parity mapping have been chosen as examples. The results demonstrate the proposed net's superior accuracy and convergence properties over the original backpropagation network or its existing improvement techniques.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2005.11a
• /
• pp.233-237
• /
• 2005

It is increased electrical energy consumption with the development of intelligence society in the general hospitals and thus an energy conservation through efficient use of electricity became more important. This paper shows a reasonable design demand factor in office buildings, that was made by the systematic and statistical way considering actual conditions, such as investigated electric equipment capacity, peak power consumption, demand factor, etc., for 32 general hospitals and 9 electrical design offices. In this dissertation, it is necessary to analyse the key features and general trend from the investigated data. It made an analysis of the feature parameters, such as average, standard deviation, median, maximum, minimun and thus it was carried linear and nonlinear regression analysis.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.28 no.6
• /
• pp.85-90
• /
• 2014

This paper shows a reasonable demand power, that was made by the systematic and statistical way considering actual conditions, such as investigated transformer capacity and peak power for the last 6 years of subway substation customer as to AMR. In this dissertation, it is necessary to analyze the key features and general trend from the investigated data. It made an analysis of the feature parameters, such as average, standard deviation, median, maximum, minimum and thus it was carried by the linear and nonlinear regression analysis. And we studied on the application of a BESS. Analysis showed that the revulsion of capital is about 3 years and 4 months.

• Journal of information and communication convergence engineering
• /
• v.2 no.3
• /
• pp.177-181
• /
• 2004

In this paper, we suggest an Iris recognition system with an excellent recognition rate and confidence as an alternative biometric recognition technique that solves the limit in an existing individual discrimination. For its implementation, we extracted coefficients feature values with the wavelet transformation mainly used in the signal processing, and we used neural network to see a recognition rate. However, Scale Conjugate Gradient of nonlinear optimum method mainly used in neural network is not suitable to solve the optimum problem for its slow velocity of convergence. So we intended to enhance the recognition rate by using Levenberg-Marquardt Back-propagation which supplements existing Scale Conjugate Gradient for an implementation of the iris recognition system. We improved convergence velocity, efficiency, and stability by changing properly the size according to both convergence rate of solution and variation rate of variable vector with the implementation of an applied algorithm.

• Proceedings of the KIEE Conference
• /
• 2004.11b
• /
• pp.91-93
• /
• 2004

Load forecasting is essential in order to supply electrical energy stably and economically in power systems. ANNs have flexibility to predict a nonlinear feature of load profiles. In this paper, we selected just the necessary input variables used in the paper(2) which is based on the phase-space embedding of a load time-series and reviewing others. So only 5 input variables were selected to forecast for spring, fall and winter season and another input considering temperature sensitivity is added during the summer season. The training cases are also selected from all previous data composed training cases of a 7-day, 14-day and 30-day period. Finally, we selected the training case of a 7-day period because it can be used in STLF without sacrificing the accuracy of the forecast. This allows more compact ANNs, smaller training cases. Consequently, test results show that compact neural networks can be forecasted without sacrificing the accuracy.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.5
• /
• pp.179-186
• /
• 2021

For stereo matching based on deep learning, the design of network structure is crucial to the calculation of matching cost, and the time-consuming problem of convolutional neural network in image processing also needs to be solved urgently. In this paper, a method of stereo matching using sparse loss volume in parallax dimension is proposed. A sparse 3D loss volume is constructed by using a wide step length translation of the right view feature map, which reduces the video memory and computing resources required by the 3D convolution module by several times. In order to improve the accuracy of the algorithm, the nonlinear up-sampling of the matching loss in the parallax dimension is carried out by using the method of multi-category output, and the training model is combined with two kinds of loss functions. Compared with the benchmark algorithm, the proposed algorithm not only improves the accuracy but also shortens the running time by about 30%.

• Ocean Systems Engineering
• /
• v.13 no.2
• /
• pp.97-121
• /
• 2023

Through-the-thickness stress distribution in a tubular member has a profound effect on the fatigue behavior of tubular joints commonly found in steel offshore structures. This stress distribution can be characterized by the degree of bending (DoB). Although multi-planar joints are an intrinsic feature of offshore tubular structures and the multi-planarity usually has a considerable effect on the DoB values at the brace-to-chord intersection, few investigations have been reported on the DoB in multi-planar joints due to the complexity of the problem and high cost involved. In the present research, data extracted from the stress analysis of 243 finite element (FE) models, verified based on available parametric equations, was used to study the effects of geometrical parameters on the DoB values in two-planar tubular DYT-joints. Parametric FE study was followed by a set of nonlinear regression analyses to develop six new DoB parametric equations for the fatigue analysis and design of axially loaded two-planar DYT-joints.

• Nonlinear Functional Analysis and Applications
• /
• v.28 no.4
• /
• pp.1051-1067
• /
• 2023

In this paper, an algorithm for approximating zeros of sum of three monotone operators is introduced and its convergence properties are studied in the setting of 2-uniformly convex and uniformly smooth Banach spaces. Unlike the existing algorithms whose step-sizes usually depend on the knowledge of the operator norm or Lipschitz constant, a nice feature of the proposed algorithm is the fact that it requires only a diminishing and non-summable step-size to obtain strong convergence of the iterates to a solution of the problem. Finally, the proposed algorithm is implemented in the setting of a classical Banach space to support the theory established.

• Journal of Sensor Science and Technology
• /
• v.33 no.3
• /
• pp.119-124
• /
• 2024

Effective fire sensing is important to protect lives and property from the disaster. In this paper, we present an intelligent visual sensing method for detecting fires based on machine learning techniques. The proposed method involves a two-step process. In the first step, fire and non-fire images are used to train a convolutional neural network (CNN), and in the next step, feature vectors consisting of 256 values obtained from the CNN are used for the learning of a support vector machine (SVM). Linear and nonlinear SVMs with different parameters are intensively tested. We found that the proposed hybrid method using an SVM with a linear kernel effectively increased the recall rate of fire image detection without compromising detection accuracy when an imbalanced dataset was used for learning. This is a major contribution of this study because recall is important, particularly in the sensing of disaster situations such as fires. In our experiments, the proposed system exhibited an accuracy of 96.9% and a recall rate of 92.9% for test image data.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.8
• /
• pp.1947-1954
• /
• 2013

Previous works for detecting arrhythmia have mostly used nonlinear method such as artificial neural network, fuzzy theory, support vector machine to increase classification accuracy. Most methods require accurate detection of P-QRS-T point, higher computational cost and larger processing time. But it is difficult to detect the P and T wave signal because of person's individual difference. Therefore it is necessary to design efficient algorithm that classifies different arrhythmia in realtime and decreases computational cost by extrating minimal feature. In this paper, we propose arrhythmia detection based on binary coding using QRS feature varibility. For this purpose, we detected R wave, RR interval, QRS width from noise-free ECG signal through the preprocessing method. Also, we classified arrhythmia in realtime by converting threshold variability of feature to binary code. PVC, PAC, Normal, BBB, Paced beat classification is evaluated by using 39 record of MIT-BIH arrhythmia database. The achieved scores indicate the average of 97.18%, 94.14%, 99.83%, 92.77%, 97.48% in PVC, PAC, Normal, BBB, Paced beat classification.