• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.10
• /
• pp.934-940
• /
• 1991

A modified quantizing method is introduced to teach single layer learning algorithm, which is implemented optically. The proposed optical system consists of input masks, holographic diffraction grating. LCD and CCD camera. The 2 dimensional interconnections between input neurons and output neurons are realized using holographic phase grating, which is fabricated for equal intensity distribution of diffraction orders. The two gray levels of LCD act as binary weights for each interconnection. The weights are compensated according to the learning algorithm in which the amount of weights to be compensated is determined by comparing the output patterns with target patterns. The learning process is iterated until the predetermined conditions are satisfied. Optical experiments are performed for two learning rates, 0.5 and 0.9 and the experimental results show that the proposed system is useful for optical neural networks.

• Nuclear Engineering and Technology
• /
• v.50 no.5
• /
• pp.767-772
• /
• 2018

Public acceptance is a major issue that will determine the future of nuclear energy. In this article, we review relevant studies and identify several common patterns of nuclear public acceptance. Based on these patterns and four categories of factors, we propose hypotheses on the impact of different socioeconomic factors on the public opinion of nuclear energy. These factors were demographic and social influences, politico-economic, energy conditions, and nuclear accidents and natural risks. We tested these hypotheses using a data set including survey results on public opinion of nuclear energy in 59 countries from 1987 to 2014. Results of the regression analysis generally verified the proposed hypotheses, especially regarding the positive impact of education or geological suitability and the negative effect of improved living standards and democracy on nuclear acceptance. We propose policy recommendations, including a better focus on education and communication and a thorough consideration of the social and geological conditions a country needs to make before deciding to go nuclear. Potential weaknesses of this study are also discussed, including the possible causal relation between independent variables and the binary nature of the dependent variable.

• Geomechanics and Engineering
• /
• v.38 no.6
• /
• pp.633-645
• /
• 2024

Disc cutters, used as excavation tools for rocks in a Tunnel Boring Machine (TBM), naturally undergo wear during the tunneling process, involving crushing and cutting through the ground, leading to various wear types. When disc cutters reach their wear limits, they must be replaced at the appropriate time to ensure efficient excavation. General disc cutter life prediction models are typically used during the design phase to predict the total required quantity and replacement locations for construction. However, disc cutters are replaced more frequently during tunneling than initially planned. Unpredictable disc cutter replacements can easily diminish tunneling efficiency, and abnormal wear is a common cause during tunneling in complex ground conditions. This study aims to overcome the limitations of existing disc cutter life prediction models by utilizing machine data generated during tunneling to predict disc cutter wear patterns and determine the need for replacements in real-time. Artificial intelligence classification algorithms, including K-nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree (DT), and Stacking, are employed to assess the need for disc cutter replacement. Binary classification models are developed to predict which disc cutters require replacement, while multi-class classification models are fine-tuned to identify three categories: no replacement required, replacement due to normal wear, and replacement due to abnormal wear during tunneling. The performance of these models is thoroughly assessed, demonstrating that the proposed approach effectively manages disc cutter wear and replacements in shield TBM tunnel projects.

• The Journal of Korean Medicine
• /
• v.25 no.4
• /
• pp.171-179
• /
• 2004

Objective : This study was undertaken for discovering the characteristics of sleep in ordinary symptoms based on the Sasang Constitution. The result of this study could be helpful to understand and to identify patients such as Taeumin, Soyangin Soeumin or Taeyangin. Methods : There were 1,229 patients (529 men), who answered the questionnaire about their ordinary sleeping patterns. They were diagnosed, including their clinical Sasang Constitution, by the Sasang Constitution specialist at Bundang Oriental Hospital of Dongguk University. By applying the multinomial and binary logistic regression analysis to those collected materials, we can measure the characteristics and the influence of ordinary sleeping patterns to the dependent variable (Sasang Constitution). Results : In order of the item's influence that had decided one's constitution, between Taeumin and Soeumin, Taeumin snored frequently or well more than Soeumin, Soeumin had more dreams and more sleeping times than Taeumin, and Taeumin struggled frequently or well more than Soeumin. Between Soyangin and Soeumin, Soeumin dreams more frequently than Soyangin, Soyangin snored frequently or well more than Soeumin, and Soeumin has more sleeping times than Taeumin. Between Taeumin and Soyangin, Taeumin snored frequently or well more than Soyangin. Between Taeyangin and a group of the other constitutions, Taeyangin felt unwell after sleeping more than the other constitutions, the other constitutions awaked frequently more than Taeyangin during sleeping. Conclusion : This study will be used for identifying patients as Taeumin, Soyangin, Soeumin or Taeyangin by contrast with each other.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.4
• /
• pp.227-236
• /
• 2003

This paper proposes a modified jointly-blue noise mask (MJBNM) method using the S-CIELAB color measure as digital color halftoning method. Based on an investigation of the relation between the pattern visibility and the chromatic error, of a blue noise pattern, a halftoning method is proposed that reduces the chromatic error, while preserving a high quality blue noise pattern. Accordingly, to reduce the chrominance error, the low-pass filtered error and S-CIELAB chrominance error are both considered during the mask generation procedure and calculated for single and combined patterns. Using the calculated low-pass filtered error, the patterns are then updated by either adding or removing dots from the multiple binary patterns. Finally, the pattern exhibiting the lower S-CIELAB chrominance error is selected. Experimental results demonstrated that the proposed algorithm can produce a visually pleasing half toned image with a lower chrominance error than the JBNM method.

• Journal of the Korean Graphic Arts Communication Society
• /
• v.16 no.2
• /
• pp.45-59
• /
• 1998

Halftonig is a technique to create the appearance of intermideate tone levels by controlling the spatial distribution of the binary pixel values. Recently, many printing devices such as image setter, inkjet printer, laser printer and facsimile, generate image, they require the technique. Ordered dither is achieved comparing the gray scale image to periodic array. This method is fast, but it occurs periodic patterns. Conentional error diffusion generates a good image. But processing speed is very slow and appeares worm artifacts in middle tone scale. To improve it, Bns(Blue noise Screen) is developed based on Gaussian distribution. In this paper, we discribe methods to design BNS based human visual characteristics and to improve blue appearing at edge area of image by USM(using unsharp mask).

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.9 no.3
• /
• pp.13-20
• /
• 2013

In this paper, we propose a multi-scale crack detection method. This method uses decomposition, composition, and shape properties. It is based on morphology algorithm, crack features. We use a morphology operator which extracts patterns of crack. It segments cracks and background using opening and closing operations. Morphology based segmentation is better than existing integration methods using subtraction in detecting a crack it has small width. However, morphology methods using only one structure element could detect only fixed width crack. Thus, we use decomposition and composition methods. We use a decimation method for decomposition. After decomposition and morphology operation, we get edge images given by binary values. Our method calculates values of properties such as the number of pixels and the maximum length of the segmented region. We decide whether the segmented region belongs to cracks according to those data. Experimental results show that our proposed multi-scale crack detection method has better results than those of existing detection methods.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.2
• /
• pp.10-21
• /
• 1998

In this paper, we analyze the anynchrous cellular hybrid DS/FH spread spectrum system with diversity on nonselective Nakagami fading channel. Binary Psk scheme is considered and random spreading code sequences and random hopping patterns are used. We compare the performance of system using hard-limiting correlation receiver with diversity and linear corrleation receiver in Nakagami fading channel. We compute the average bit error probabilities with/without diversity according to spreading code sequence and the number of hop-ping frequencies under the same handwith espansion, and analyze near-far effect. The results show that hard-limiting correlation receiver with diversity gives a good performance over severe fading channel.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.6
• /
• pp.2368-2375
• /
• 2015

To accommodate various navigational commands, a humanoid should be able to change its walking motion in real time. Using the modifiable walking pattern generation (MWPG) algorithm, a humanoid can handle dynamic walking commands by changing its walking period, step length, and direction independently. If the humanoid is given a command to perform an infeasible movement, the algorithm substitutes the infeasible command with a feasible one using binary search. The feasible navigational command is subsequently translated into the desired center-of-mass (CM) state. Every sample time CM reference is generated using a zero-moment-point (ZMP) variation scheme. Based on this algorithm, various complex walking patterns can be generated, including backward and sideways walking, without detailed consideration of the feasibility of the navigational commands. In a previous study, the effectiveness of the MWPG algorithm was verified by dynamic simulation. This paper presents experimental results obtained using the small-sized humanoid robot platform DARwIn-OP.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.30 no.4
• /
• pp.27-43
• /
• 2005

This paper presents a new hybrid data mining technique using error pattern modeling to improve classification accuracy when the data type of a target variable is binary. The proposed method increases prediction accuracy by combining two different supervised learning methods. That is, the algorithm extracts a subset of training cases that are predicted inconsistently by both methods, and models error patterns from the cases. Based on the error pattern model, the Predictions of two different methods are merged to generate final prediction. The proposed method has been tested using practical 10 data sets. The analysis results show that the performance of proposed method is superior to the existing methods such as artificial neural networks and decision tree induction.