• ETRI Journal
• /
• 제32권5호
• /
• pp.784-794
• /
• 2010

Automatic facial expression recognition has many potential applications in different areas of human computer interaction. However, they are not yet fully realized due to the lack of an effective facial feature descriptor. In this paper, we present a new appearance-based feature descriptor, the local directional pattern (LDP), to represent facial geometry and analyze its performance in expression recognition. An LDP feature is obtained by computing the edge response values in 8 directions at each pixel and encoding them into an 8 bit binary number using the relative strength of these edge responses. The LDP descriptor, a distribution of LDP codes within an image or image patch, is used to describe each expression image. The effectiveness of dimensionality reduction techniques, such as principal component analysis and AdaBoost, is also analyzed in terms of computational cost saving and classification accuracy. Two well-known machine learning methods, template matching and support vector machine, are used for classification using the Cohn-Kanade and Japanese female facial expression databases. Better classification accuracy shows the superiority of LDP descriptor against other appearance-based feature descriptors.

• Journal of Electrical Engineering and Technology
• /
• 제11권1호
• /
• pp.192-199
• /
• 2016

With changes in insulated defects, the environment, and so on, new partial discharge (PD) data are highly different from the original samples. It leads to a decrease in on-line recognition rate. The UHF signal and pulse current signal of four kinds of typical artificial defect models in gas insulated switchgear (GIS) are obtained simultaneously by experiment. The relationship map of ultra-high frequency (UHF) cumulative energy and its corresponding apparent discharge of four kinds of typical artificial defect models are plotted. UHF cumulative energy and its corresponding apparent discharge are used as inputs. The support vector machine (SVM) incremental method is constructed. Examples show that the PD SVM incremental method based on simulated annealing (SA) effectively speeds up the data update rate and improves the adaptability of the classifier compared with the original method, in that the total sample is constituted by the old and new data. The PD SVM incremental method is a better pattern recognition technology for PD on-line monitoring.

• 반도체디스플레이기술학회지
• /
• 제19권3호
• /
• pp.7-11
• /
• 2020

Enormous methods have been proposed for the detection and segmentation of blur and non-blur regions of the images. Due to the limited available information about the blur type, scenario and the level of blurriness, detection and segmentation is a challenging task. Hence, the performance of the blur measure operators is an essential factor and needs improvement to attain perfection. In this paper, we propose an effective blur measure based on the local binary pattern (LBP) with the adaptive threshold for blur detection. The sharpness metric developed based on LBP uses a fixed threshold irrespective of the blur type and level which may not be suitable for images with large variations in imaging conditions and blur type and level. Contradictory, the proposed measure uses an adaptive threshold for each image based on the image and the blur properties to generate an improved sharpness metric. The adaptive threshold is computed based on the model learned through the support vector machine (SVM). The performance of the proposed method is evaluated using a well-known dataset and compared with five state-of-the-art methods. The comparative analysis reveals that the proposed method performs significantly better qualitatively and quantitatively against all the methods.

• 한국안전학회지
• /
• 제29권3호
• /
• pp.129-135
• /
• 2014

The number of abnormal operation procedures (AOPs) for mitigating a plant abnormal status amounts to about one hundreds for the most of 1000MWe optimized power plant (OPR1000) and it is expected that the number of AOPs would be increased to cope with an abnormal status occurred newly. However, it is not well organized for operators to select a proper AOP from alarms occurred in main control room (MCR) during a plant abnormal status. It may be a burden to operators since the selection of AOP to respond an abnormal status is authorized by operators. When multiple alarms occur in MCR, it would take more time to respond them than a single alarm. To reduce the efforts, various MCR operation support systems have been developed. The purpose of this study was to develop a multi-alarm pattern card to select an appropriate AOP effectively when multiple alarms occurs in a single upper layout (UL) of MCR. It can be applied for an operation support tool as well as an education tool.

• 한국전문물리치료학회지
• /
• 제28권1호
• /
• pp.13-17
• /
• 2021

A normal range of motion is essential for performing activities of daily living. The capsular pattern is the proportional motion restriction in range of motion during passive exercises due to tightness of the joint capsule. Although the capsular pattern is widely referred to in clinical practice, there is no scientific evidence to support the concept. In this review, the appropriateness of the capsular pattern for evaluation of joint pathology was assessed. In the Textbook of Orthopaedic Medicine written by Cyriax, the capsular pattern did not specify how much reduction in angular motion is considered motion restriction. As the definition proposed initially was unclear, different methods have been used in previous studies investigating capsular pattern. In addition, the capsular pattern described all the major joints of the human body, but only the hip joint, knee joint, and shoulder joint were studied in experimental studies. Sensitivity and specificity were reported in one study and were meaningful in specific pathologies (loss of extension to loss of flexion). There was no consensus on the reliability and validity. In summary, the capsular pattern suggested by Cyriax or Kaltenborn is not supported or applies only to certain conditions. Various components around a joint complement each other and provide stability to the joint. It is recommended that the therapist perform multiple assessments rather than rely on a single assessment when evaluating joints.

• 멤브레인
• /
• 제3권1호
• /
• pp.22-28
• /
• 1993

Polyester, polyacrylics, nylon과 cotton을 이용해 이들의 막지지천으로의 사용가능성을 조사하였다. 압축률, membrane embossing, 유량과 물리적$\cdot$화학적 특성 등을 고려한 결과 50 번수의 polyester가 막지지천으로 적당함을 알았다. 이 polyester를 막지지천으로 사용해 압력 강하, 조업압력, 점도 등이 막지지천을 통한 유체 흐름에 미치는 영향을 조사하였는데, 이 막지지천을 통한 유체 흐름은 Darcy's law를 만족시켰다.

• Geomechanics and Engineering
• /
• 제14권5호
• /
• pp.429-437
• /
• 2018

In order to reduce deformation of roadway floor heave in deep underground soft rockmass, four support design patterns were analyzed using the Fast Lagrangian Analysis of Continua (FLAC)3D, including the traditional bolting (Design 1), the bolting with the backbreak in floor (Design 2), the full anchorage bolting with the backbreak in floor (Design 3) and the full anchorage bolting with the bolt-grouting backbreak in floor (Design 4). Results show that the design pattern 4, the full anchorage bolting with the bolt-grouting backbreak in floor, was the best one to reduce the deformation and failure of the roadway, the floor deformation was reduced at 88.38% than the design 1, and these parameters, maximum vertical stress, maximum horizontal displacement and maximum horizontal stress, were greater than 1.69%, 5.96% and 9.97%. However, it was perfectly acceptable with the floor heave results. The optimized design pattern 4 provided a meaningful and reliable support for the roadway in deep underground coal mine.

• Structural Monitoring and Maintenance
• /
• 제5권2호
• /
• pp.243-260
• /
• 2018

Detection of damages in fibre reinforced plastic (FRP) composite structures is important from the safety and serviceability point of view. Usually, damage is realized as a local reduction of stiffness and if dynamic responses of the structure are sensitive enough to such changes in stiffness, then a well posed inverse problem can provide an efficient solution to the damage detection problem. Usually, such inverse problems are solved within the framework of pattern recognition. Support Vector Machine (SVM) Algorithm is one such methodology, which minimizes the weighted differences between the experimentally observed dynamic responses and those computed using the finite element model- by optimizing appropriately chosen parameters, such as stiffness. A damage detection strategy is hereby proposed using SVM which perform stepwise by first locating and then determining the severity of the damage. The SVM algorithm uses simulations of only a limited number of damage scenarios and trains the algorithm in such a way so as to detect damages at unknown locations by recognizing the pattern of changes in dynamic responses. A rectangular fiber reinforced plastic composite plate has been investigated both numerically and experimentally to observe the efficiency of the SVM algorithm for damage detection. Experimentally determined modal responses, such as natural frequencies and mode shapes are used as observable parameters. The results are encouraging since a high percentage of damage cases have been successfully determined using the proposed algorithm.

• 한국주거학회:학술대회논문집
• /
• 한국주거학회 2009년도 추계학술발표대회 논문집
• /
• pp.146-150
• /
• 2009

Present family pattern of Korean society has been changed into nuclear family pattern based on the married couple from traditional expanded family pattern. As the entire social consciousness has been changed into private disposition, the number of independent household for 1 person has increases. Also, as the delivery age of first child became late according to the elongation of average period for the national education, the increment of average age for the first marriage and women's participation in the society, the family pattern of married couple lasts longer than used to be. Like this, considering the family formed period comprised from a household for 1 person to a household for 1married couple and senescence increase, as any response is inevitable for the requirement of residential space where 1~2 dwellers' life can be accepted economic and functionally within smaller scaled space, development and research on a plan system(flexible-typed plan) increasing the degree of freedom is required in developing plan of unit household. In the study for this, considering the change of population and social structure, I suggest the method in developing economic design responding to the differentiation, designing the change of support-system and infill-system based on the systemic comprehension about the residing environment in the family formation period and the research for main life pattern and residing environment in the family formation period in the present city life. I will set (family) composing system, develop basic and mixing typed standard model and establish the stage of applied development for the development of economic design.

• 치위생과학회지
• /
• 제2권2호
• /
• pp.75-83
• /
• 2002

By extracting the variables related to the work stress generated from dental hygiene, identifying their relationships, this study aims to contribute to academic progress on work stress. The test results of this study are as follows for each hypothesis: 1. Among the work stress sensing factors, role ambiguity showed correlation to the active coping strategy and the passive coping strategy, whereas it did not have any correlation to the evasive reation. However, the physical resource environmental factor showed correlation to the active coping strategy, whereas it did not have any correlation to the other reation. 2. The passive coping strategy, among the work stress coping strategies, influences the role ambiguity, B type, work ambiguity, physical resource environmental factor by about 18.7%. 3. The active coping strategy, among the work stress coping strategies, influences the social support, role ambiguity, work place of health center factor by about 18.9%. 4. The evasive reaction, among the work stress coping strategies, was influenced by only the 36 years old over factor by approximately 4.2%. 5. It was found in all work stress sensing factors that the group with lower social support had a more degree of experiencing stress than the group with higher social support. In case of the behavior pattern, the type A experienced more stress than the type B only in role ambiguity. 6. It was found that the group with the higher social support tended to choose more active coping strategy than the lower social support. In case of behavior pattern, the type B coped more actively than type A in the passive coping strategy.