• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.1017-1018
• /
• 2006

We measured EEG, extracted the feature vectors using alpha and beta rhythm from the measured EEG and pattern recognition was simulated by using the feature vector and the algorithms which are conventional LVQ and Forward only Counter Propagation Networks. And then the successful rate of pattern class of EEG data had about 76 %.

• Journal of Ocean Engineering and Technology
• /
• v.14 no.1
• /
• pp.80-87
• /
• 2000

Despite many combined research efforts outstanding needs exist to develop robust safety-estimation methods for large complex structures. This paper presents a practical damage identification scheme which can be applied to truss structures using only limited modal responses. firstly a theory of pattern recognition (PR) is described. Secondly existing damage-detection algorithms are outlined and a newly-derived algorithms for truss structures. Finally the feasibility of the proposed scheme is evaluated using numerical examples of plane truss structures.

• Proceedings of the Optical Society of Korea Conference
• /
• 1989.02a
• /
• pp.95-98
• /
• 1989

A new associative memory model using the SDF filter, one of the multiple filter for pattern recognition, is suggested in this paper. The SDF filter characteristics such as pattern classification lets the memorized patterns have orthogonal characteristics one another, so that enhances the associative memory's retrieval ability to the original pattern. The computer simulation shows that this new model is very useful in case that the imput patterns are seriously distorted and the cross-correlation between the memorized patterns is very high.

• Journal of Korea Multimedia Society
• /
• v.22 no.11
• /
• pp.1233-1241
• /
• 2019

The goal of the sound-based mechanical fault diagnosis technique is to automatically find abnormal signals in the machine using acoustic emission. Conventional methods of using mathematical models have been found to be inaccurate due to the complexity of industrial mechanical systems and the existence of nonlinear factors such as noise. Therefore, any fault diagnosis issue can be treated as a pattern recognition problem. We propose an automatic fault diagnosis method using discrete wavelet transform and power spectrum density using multi pattern recognition. First, we perform DWT-based filtering analysis for noise cancelling and effective feature extraction. Next, the power spectral density(PSD) is performed on each subband of the DWT in order to effectively extract feature vectors of sound. Finally, each PSD data is extracted with the features of the classifier using multi pattern recognition. The results show that the proposed method can not only be used effectively to detect faults as well as apply to various automatic diagnosis system based on sound.

• Journal of Fashion Business
• /
• v.11 no.6
• /
• pp.101-114
• /
• 2007

This research aimed to identify the differences, in terms of the pattern, of using wool and jersey for designing jackets and to provide a theorized solution. The object of this study is development of women's tailored jacket pattern by the traits of fabrics with fabrics those are generally used to develop the power of manufacturing technique about fit of jacket. Basic bodies prototype, graphics of sleeves prototype and graphics of jacket pattern those a clothing company at present(on&on, a brand of Beaucre Merchandising Co.,Ltd) is using were used as basics of tailored jacket pattern. Three kinds of fabric(wool, polyester, jersey) were chosen, we made jackets in the same manufacturing process of the clothing company, modified and made up for the weak points and then we compared and analyzed differences of pattern by the traits of fabrics, the results are as follows: 1) We drafted basic tailored style jacket pattern, made a jacket with wool fabric, made wearing experiment, modified and made up for the weak points by the trend, then developed JacketⅠ for study; 2) With JacketⅠ for study as the basic, we made a jacket with polyester fabric, made wearing experiment, modified and made up for the weak points, then developed Jacket II for study; 3) With JacketⅠ for study as the basic, we made a jacket with jersey fabric, made wearing experiment, modified and made up for the weak points, then developed Jacket III for study; 4) We presented final degree of polymerization of pattern with Jacket I II III for study; 5) We compared and analyzed the differences of pattern with the degree of polymerization of pattern with Jacket I(Wool) for study and Jacket II(Polyester), there was no change of size overall except extra amount which happens because of the trait of the fabric in 20 items of body format pattern, there were differences of size in 3 items(height of a sleeve, width of a sleeve, length of a sleeve) among 5 items of sleeves pattern; 6) We compared and analyzed the differences of pattern with the degree of polymerization of pattern with Jacket I(Wool) for study and Jacket III(Jersey) for study, there were differences of size by the kinds of fabric in 11 items(neck point to shoulder point length, Bishoulder point length, back interscye length, front interscye length, armhole circumference, depth of armhole, chest circumference, bust circumference, waist circumference, hip circumference, waist dart) among 20 items of body format pattern, there were differences of size by the kinds of fabric in 5 items(height of a sleeve, circumference of a sleeve, width of a sleeve, length of a sleeve, width of bottom of a sleeve) among 5 items of sleeves pattern.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.05b
• /
• pp.374-379
• /
• 2003

본 논문에서는 pattern recognition을 위하여 support vector fuzzy inference system을 제안하였다 Fuzzy inference system의 structure와 parameter를 identification 하기 위하여 Support vector machine을 이용하였으며 에러 최소화 기법으로는 gradient descent 방법을 사용하였다. 제안된 SVFIS 방법의 성능을 파악하고자 COIL 이미지를 이용한 3차원 물체 인식 실험을 수행하였다.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.24 no.6
• /
• pp.799-809
• /
• 2000

This study was designed for automated pattern drawing and grading a man's Durumagi, Korean traditional coat in order to reestablished and grade the pattern by Apparel CAD SYSTEM. For the study, AM-250 systems of Gerber as the computer and Macro program as the automated drawing were used. Also, PDS(Pattern Design System) was used for the grading of the original Durumagi pattern. Results were followings; First, the size data that could be standardized by reestablishing the pattern of a man's Durumagi by each size was presented. Second, The pattern was developed by each size. Third, new design was propose for mass production with the traditional design of the DURUMAGI Fourth, The time for making DURUMAGI pattern and the cost through the automated drawings by using the Macro program were reduced. Moreover, was presented the basic data for a ready to made garment like the Western garment. Five, A man's DURUMAGI by CAD System was graded that could be applied to ready to made Hanbok

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.14 no.3
• /
• pp.185-192
• /
• 2004

Vibration table is required to obtain high packing density in expendable pattern casting process. Packing density. which is an important manufacture factor, depends on the vibration pattern induced by vibration table. In general, circular vibration pattern is recognized as the best pattern. The existing vibration table is investigated to identify current vibration pattern and consider a countermeasure. Modal test is utilized to identify the dynamic characteristics of vibration table, and finite element method is used to propose the improved design. In simulation using finite element method, the position of stiffeners is obtained to satisfy the required dynamic characteristics.

• Transactions of Materials Processing
• /
• v.23 no.8
• /
• pp.507-512
• /
• 2014

The objective of the current investigation is to establish techniques in micro pattern forming operations of polymeric circular tubes by using hydrostatic pressing. This method was developed and successfully applied to the micro pattern forming on polymeric plates. The key idea of the new technique is to pressurize multiple vacuum-packed substrate-mold stacks above the glass transition temperature of the polymeric substrates. The new process is thought to be a promising micro-pattern fabrication technique for two reasons; first, (hydro-) isostatic pressing ensures a uniform micro-pattern replicating condition regardless of the substrate area and thickness. Second, multiple curved substrates can be patterned at the same time. With the prototype forming machine for the new process, micro prismatic array patterns, 25um in height and 90 degrees in apex angle, were successfully made on the PMMA circular tubes with diameters of 5~40mm. These results show that this process can be also used in the micro pattern forming process on curved plates such as circular tube.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.11
• /
• pp.3001-3011
• /
• 1996

In this paper, using DBNN algorithm which is used in the binary pattern classification or speech signal processing the digital DBNN circuit is designed having the variable expansion depending the size of input data and pattern type. The processing elemen(PE) of the proposed network consists of the synapse and MAXNET circuits for the similarity measurement between reference and input pattern. Global MAXNET selects the global winner among the local winners which is selected in each PE. Through the several simultions, and thus each PE and global MAXNET search the reference pattern that was the most simlar to input pattern for the discord of the pattern.