• Language and Information
• /
• v.9 no.1
• /
• pp.69-92
• /
• 2005

Pattern recognition in cognitive agents is based on (i) the uninterpreted input data (e.g. parameter values) provided by the agent's hardware devices and (ii) and interpreted patterns (e.g. templates) provided by the agent's memory. Computationally, the task consists in finding the memory data corresponding best to the input data, for any given input. Once the best fitting memory data have been found, the input is recognized by applying to it the interpretation which happens to be stored with the memorized pattern. This paper presents a fast converging procedure which starts from a few initially recognized items and then analyzes the remainder of the input by systematically checking for items shown by memory to have been related to the initial items in previous encounters. In this way, known patterns are tried first, and only when they have been exhausted, an elementary exploration of the input is commenced. Efficiency is improved further by choosing the candidate to be tested next according to frequency.

• Communications of the Korean Mathematical Society
• /
• v.10 no.3
• /
• pp.561-573
• /
• 1995

A matrix whose entries consist of the symbols +, - and 0 is called a sign pattern matrix. In [1], a graph theoretic characterization of sign idempotent pattern matrices was given. A question was given for the sign patterns which allow idempotence. We characterized the sign patterns which allow idempotence in the sign idempotent pattern matrices.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.31A no.6
• /
• pp.159-168
• /
• 1994

Stochastic computation is adopted to reduce the silicon area of the multipliers in implementing neural network in VLSI. In addition to this advantage, the stochastic computation has inherent random errors which is required for implementing Boltzmann machine. This random noise is useful for the simulated annealing which is employed to achieve the global minimum for the Boltzmann Machine. In this paper, we propose a method to implement the Boltzmann machine with stochastic computation and discuss the addition problem in stochastic computation and its simulated annealing in detail. According to this analysis Boltzmann machine using stochastic computation is suitable for the pattern recognition/completion problems. We have verified these results through the simulations for XOR, full adder and digit recognition problems, which are typical of the pattern recognition/completion problems.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06b
• /
• pp.352-354
• /
• 2006

패턴완성(Pattern Completion)은 사용되는 패턴 성분들 사이의 higher-order correlation 정보가 중요한 의미를 가질 수 있는 기계학습 문제 중 하나이다. higher-order correlation은 확률라이브러리모델(Probabilistic Library Model)로 구현되는 hypernetwork 개념을 도입해서 나타낼 수 있다. 하지만 확률라이브러리모델을 사용하여 higher-order 정보를 나타내려할 때 초기라이브러리가 모든 가능한 조합의 원소들을 가지도록 구성하기는 쉽지 않다. 그 대안으로 초기라이브러리 구성 시 학습패턴들을 subsampling하여 적은 숫자의 원소들만으로 higher-order correlation의 근사치를 나타내게 할 수 있다. 본 논문에서는 이와 같이 subsampling이 사용되어 구성된 확률라이브러리모델을 이용한 패턴완성시의 correlation의 order에 따른 효과를 분석하여 본다.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.35 no.11
• /
• pp.1271-1284
• /
• 2011

This study improves the fitness of Air Force winter service uniforms through the development of a shirt pattern drafting method and automatic pattern drafting program for MTM production. A calculation formula is formed through a correlation analysis and regression analysis using Size Korea 2004 3D measurement data after analyzing 4 kinds of existing shirt pattern drafting methods and 3 types of shirt patterns currently used for the Air Force service uniform. The results of this study are as follows: The developed pattern drafting method has 4 parts that use calculated dimensions: neck base width, front interscye, back interscye and scye depth. Other body measuring parts that have a high correlation with calculation parts are inserted into regression analysis as independent variables to create dimension calculation formulas. The result of the final study patterns were better than existing winter service uniforms in nearly all items for the appearance evaluation and motion adaptability evaluations. The method was converted into an automatic pattern drafting program using C++ after the completion of pattern drafting method development.

• ETRI Journal
• /
• v.36 no.6
• /
• pp.979-987
• /
• 2014

This paper describes new tactile feedback patterns and the effect of their input performance for a button GUI activated by a tap gesture on mobile touch devices. Based on an analysis of touch interaction and informal user tests, several tactile feedback patterns were designed. Using these patterns, three user experiments were performed to investigate appropriate tactile feedback patterns and their input performance during interaction with a touch button. The results showed that a tactile pattern responding to each touch and release gesture with a rapid response time and short falling time provides the feeling of physically clicking a button. The suggested tactile feedback pattern has a significantly positive effect on the number of typing errors and typing task completion time compared to the performance when no feedback is provided.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.524-543
• /
• 2022

Correct facade image parsing is essential to the semantic understanding of outdoor scenes. Unfortunately, there are often various occlusions in front of buildings, which fails many existing methods. In this paper, we propose an end-to-end deep network for facade parsing with occlusions. The network learns to decompose an input image into visible and invisible parts by occlusion reasoning. Then, a context aggregation module is proposed to collect nonlocal cues for semantic segmentation of the visible part. In addition, considering the regularity of man-made buildings, a repetitive pattern completion branch is designed to infer the contents in the invisible regions by referring to the visible part. Finally, the parsing map of the input facade image is generated by fusing the results of the visible and invisible results. Experiments on both synthetic and real datasets demonstrate that the proposed method outperforms state-of-the-art methods in parsing facades with occlusions. Moreover, we applied our method in applications of image inpainting and 3D semantic modeling.

• Journal of Korean Society of Environmental Engineers
• /
• v.29 no.8
• /
• pp.944-949
• /
• 2007

The profiles of on-line sensors such as DO, ORP and pH can provide useful information about pollutant removal reaction in sequencing batch reactor. For detection of denitrification completion, the nitrate hee point from ORP profile has been considered as a main indicator of denitrification completion. However, many researchers pointed out that the nitrate knee usually disappeared been the progress of denitrification is so fast and it makes the fault at detection of denitrification completion. In this paper, dynamic time warping(DTW) method and discriminant analysis were used to detect and isolate the profiles of two cases, denitrification completed and uncompleted. As the results, proposed methods can detect state of denitrification successfully.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.12 no.1 s.26
• /
• pp.93-114
• /
• 1988

The purpose of this study was to develop pattern drafting methods of bodice, sleeve and skirt for Korean women at the age of 18 to 34. The study procedures and results were as follows; 1. 305 women aged 18 to 34 were measured on 49 items. 56 items including 49 measured and 7 calculated items were analyzed statistically. 2. New pattern drafting methods were developed based on the results of the data analysis. Basic shells constructed from the patterns were examined through fitting tests for completion. 3. The sensory test was applied to evaluate the new pattern for women by comparing it with one of the most used conventional patterns. An original rating scale was developed and used for the evaluation. According to a statistical analysis of the result of the 53 items on the questionnaire, all the items showed significant difference ($\alpha{\leqq}0.01$ or $\alpha{\leqq}0.05$) between the two, with the new pattern having higher scores. The new drafting method proved to be better fitted at all 53 items, and to be comfortable.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.9 no.3
• /
• pp.17-26
• /
• 1985

The purpose of this study is to develop a bodice pattern drafting method for Korean elderly women over sixty years old on the basis of their physical characteristics which differ from those of adult women. The study is composed as follows; 1. One hundred and five elderly women were measured on 20 items. Twenty-five items including 20 measured items and 5 calculated items were analyzed statistically. 2. A new method was developed based on the results of data analysis. Basic shells constructed from the patterns were examined through three fitting tests for completion. 3. The sensory evaluation was applied to evaluate the new pattern for elderly women by comparing it with the conventional pattern for adult women. A five-point rating scale was developed for the evaluation. According to a statistical analysis of the result of the 20 items on the questionnaire, all the items showed significant differences (a$\leqq$0.01) between the two, with the new pattern having higher scores.