• Nuclear Engineering and Technology
• /
• v.50 no.8
• /
• pp.1306-1313
• /
• 2018

The randomness and incipient nature of certain faults in reactor systems warrant a robust and dynamic detection mechanism. Existing models and methods for fault diagnosis using different mathematical/statistical inferences lack incipient and novel faults detection capability. To this end, we propose a fault diagnosis method that utilizes the flexibility of data-driven Support Vector Machine (SVM) for component-level fault diagnosis. The technique integrates separately-built, separately-trained, specialized SVM modules capable of component-level fault diagnosis into a coherent intelligent system, with each SVM module monitoring sub-units of the reactor coolant system. To evaluate the model, marginal faults selected from the failure mode and effect analysis (FMEA) are simulated in the steam generator and pressure boundary of the Chinese CNP300 PWR (Qinshan I NPP) reactor coolant system, using a best-estimate thermal-hydraulic code, RELAP5/SCDAP Mod4.0. Multiclass SVM model is trained with component level parameters that represent the steady state and selected faults in the components. For optimization purposes, we considered and compared the performances of different multiclass models in MATLAB, using different coding matrices, as well as different kernel functions on the representative data derived from the simulation of Qinshan I NPP. An optimum predictive model - the Error Correcting Output Code (ECOC) with TenaryComplete coding matrix - was obtained from experiments, and utilized to diagnose the incipient faults. Some of the important diagnostic results and heuristic model evaluation methods are presented in this paper.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.64 no.3
• /
• pp.1-8
• /
• 2022

In this study, a farm map utilization strategy for sustainable agricultural environmental resource management was derived. In addition, it is intended to present an efficient method of providing farm map-related services. As a result of the demand survey, the additional information required for the farm map includes 29% of information on crops grown on farmland, 21% of management-related information such as the owner or business entity, 17% of topographical information including slope, 15% of agricultural water information, 17% of land status information, and the addition of functions. 2% was investigated. As a result of intensive interview survey, it was found that it can be used for information on crops cultivated by agricultural businesses, actual cultivated area by township, arable land consolidation division boundary, and management of agricultural promotion zones. The farm map can be used as basic data to efficiently manage agricultural environmental resources. Since the status of support for individual farms or lots, such as soil improvement agent support and organic fertilizer support, may belong to personal information, it can be processed and provided in units required by administration or policies, such as administrative boundaries, subwatersheds, and watersheds. It can serve as a basis for executing the direct payment currently supported only by individual farms, even in a community unit that manages environmental direct payments.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.21 no.11
• /
• pp.997-1004
• /
• 2011

A fault detection algorithm of a charge and discharge system to ensure the safe use of hybrid electric vehicle is proposed in this paper. This algorithm can be used as a complementary way to existing fault detection technique for a charge and discharge system. The proposed algorithm uses a SVDD technique, which additionally utilizes two methods for learning a large amount of data; one is to incrementally learn a large amount of data, the other one is to remove the data that does not affect the next learning using a new data reduction technique. Removal of data is selected by using lines connecting support vectors. In the proposed method, the data processing speed is drastically improved and the storage space used is remarkably reduced than the conventional methods using the SVDD technique only. A battery data and speed data of a commercial hybrid electrical vehicle are utilized in this study. A fault boundary is produced via SVDD techniques using the input and output in normal operation of the system without using mathematical modeling. A fault detection simulation is performed using both an artificial fault data and the obtained fault boundary via SVDD techniques. In the fault detection simulation, fault detection time via proposed algorithm is compared with that of the peak-peak method. Also the proposed algorithm is revealed to detect fault in the region where conventional peak-peak method is never able to do.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.16 no.1
• /
• pp.171-180
• /
• 2013

As the second-largest 1st degree of ecological zone in Kangwon Province, Pyeongchang County is expected to play an important role in expanding the protected areas of the Republic of Korea. However, Pyoungchang County is expected to experience an increase in demand for development due to the 2018 Winter Olympics. Problems related to various stakeholders and limited budget will arise regarding the issue of expanding the protected areas. In this study, in order to effectively control these problems, we designed expansion plans for the 1st degree ecological zoning map areas and the observed data of threatened species I and II in Pyoungchang County by using the MARXAN Software. As for the methods, we first set the planning units(PUs) for the spatial analysis. The PUs include boundary length, land cost, land status, etc. Then, we made the input data by controlling the conservation features, BLM(Boundary Length Modifier) and iteration numbers. There are two measures for the establishment of the protected areas, one of which only concerns with the ecological priority, and the other with combining the land cost on forest. The one illustrated shows that the larger patches that include the conservation feature was selected as a candidate of the protected areas. The other one presented shows that inexpensive land cost areas were selected. As this study produces visual results and enables an efficient application of various values in selecting protected areas, we believe that it will be useful to various stakeholders in spatial decision-making process.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.11
• /
• pp.31-38
• /
• 2013

Feature normalization as a pre-processing step has been widely used in classification problems to reduce the effect of different scale in each feature dimension and error as a result. Most of the existing methods, however, assume some distribution function on feature distribution. Even worse, existing methods do not use the labels of data points and, as a result, do not guarantee the optimality of the normalization results in classification. In this paper, proposed is a supervised rank normalization which combines rank normalization and a supervised learning technique. The proposed method does not assume any feature distribution like rank normalization and uses class labels of nearest neighbors in classification to reduce error. SVM, in particular, tries to draw a decision boundary in the middle of class overlapping zone, the reduction of data density in that area helps SVM to find a decision boundary reducing generalized error. All the things mentioned above can be verified through experimental results.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.7
• /
• pp.37-45
• /
• 2013

Context dependent fusion (CDF) is a fusion algorithm that combines multiple outputs from different classifiers to achieve better performance. CDF tries to divide the problem context into several homogeneous sub-contexts and to fuse data locally with respect to each sub-context. CDF showed better performance than existing methods, however, it is sensitive to noise due to the large number of parameters optimized and the innate linearity limits the application of CDF. In this paper, a variant of CDF using support vector machines (SVMs) for fusion and kernel principal component analysis (K-PCA) for context extraction is proposed to solve the problems in CDF, named CDF-SVM. Kernel PCA can shape irregular clusters including elliptical ones through the non-linear kernel transformation and SVM can draw a non-linear decision boundary. Regularization terms is also included in the objective function of CDF-SVM to mitigate the noise sensitivity in CDF. CDF-SVM showed better performance than CDF and its variants, which is demonstrated through the experiments with a landmine data set.

• Journal of Korean Society for Geospatial Information Science
• /
• v.14 no.4 s.38
• /
• pp.71-77
• /
• 2006

Support Vector Machine (SVM) which has roots in a statistical learning theory is a training algorithm based on structural risk minimization. Generally, SVM algorithm uses the kernel for determining a linearly non-separable boundary and classifying the data. But, classical kernels can not apply to effectively the hyperspectral image classification because it measures similarity using vector's dot-product or euclidian distance. So, This paper proposes the spectral similarity kernel to solve this problem. The spectral similariy kernel that calculate both vector's euclidian and angle distance is a local kernel, it can effectively consider a reflectance property of hyperspectral image. For validating our algorithm, SVM which used polynomial kernel, RBF kernel and proposed kernel was applied to land cover classification in Hyperion image. It appears that SVM classifier using spectral similarity kernel has the most outstanding result in qualitative and spatial estimation.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.8 no.2
• /
• pp.27-33
• /
• 2004

Dynamic response analysis is conducted for a floating bridge subjected to multiple support earthquake excitation. The floating bridge used in this study is supported by discrete floating pontoons and horizontal pretension cables supported at both ends of the bridge. The bridge is modeled with finite elements and the hydrodynamic added mass and added damping due to the surrounding fluid around pontoons are obtained using boundary elements. During the analysis the concept of retardation function is utilized to consider the frequency dependency of the hydrodynamic coefficients. Multiple support excitation is introduced at both ends of the bridge and the time history response is compared to that of a simultaneous excitation. The results show that the multiple support excitation yields larger values in some responses. for example in cable tensions. than the sumultaneous excitation.

• Journal of Korean Academy of Nursing
• /
• v.52 no.2
• /
• pp.187-201
• /
• 2022

Purpose: This study discovered a substantive theory of the experience and process of peer support work among people with mental illness. Methods: The participants were members of community-based mental health facilities and had been working as peer supporters for more than six months. The data were collected through in-depth interviews with twelve participants and analyzed using Corbin and Strauss's grounded theory approach. Results: The core category was "becoming a healer going with patients in the journey of recovery," and the core phenomenon was "identity confusion as a peer supporter." The causal conditions were "starting peer support work without certainty" and "standing at the boundary between the therapist and patient." The intervening conditions were "willingness to become a successful peer supporter," "feeling a sense of homogeneity with the patient," "accepting the mental illness," and "support from people around." The action and interaction strategies were "letting go of greed," "being open about oneself," "developing professional skills," "maintaining wellness in the body and mind," and "being with the patient." The consequences were "becoming a useful person," "changing attitude toward life," "expansion of the sense of self-existence," "recovering from mental illness," and "discovering a role as peer supporter." Finally, the substantive theory of "becoming a healer going with patients in the journey of recovery" was derived. Conclusion: This study provides a holistic understanding of peer support work and the implications of interventions to help people with mental illness in a person-centered recovery process.

• Asia Marketing Journal
• /
• v.15 no.2
• /
• pp.49-73
• /
• 2013

In this study, the author develops and tests a model that incorporates the mediating effects of two frontline employee psychological variables (emotional exhaustion and intrinsic motivation) based on job demand and resource model. As a form of environmental resource, person-organization fit was proposed as a leading factor of frontline employee boundary spanning behavior through emotional exhaustion and intrinsic motivation. All measures were adapted from or developed based on prior research. Data for the study were collected from a cross-sectional sample of retail bank employees in South Korea. Questionnaires were distributed to 500 frontline employees across several banks. Of these, 322 usable questionnaires were returned. To analyze the data, a structural equation model procedure using LISREL 8.5 was employed. Results show that an employee's perceived fit with his/her organization enhances intrinsic motivation and reduces emotional exhaustion. These mechanisms, in turn, increase the employee's boundary spanning behavior. These results support the notion that person-organization fit should be one of the factors affecting motivation, affect and attachment, and extends such an understanding to a purely service-based environment among customer contact employees. Results also confirms that P-O fit can be viewed as environmental resources, and the JD-R model provides a theoretical base in further studying the antecedent role of P-O fit on frontline employees's boundary spanning behavior through intrinsic motivation and emotional exhaustion. These results suggest that organizations have to do their best to manage P-O fit, be it through employee screening or training and workshops to try and align organization and employee values and objectives. If managers of organizations are positively evaluated by the employees, it will be easier for them to, give things of value to employees, such as sense of direction, values, and recognition, and receive other things in return such as esteem and responsiveness. Consequently, organizational leaders are not only able to manage employee experiences, but also their fit with the organization. Even if a manager cannot control employee P-O fit, this research suggests, that a focus on reducing emotional exhaustion rather than increasing intrinsic motivation seems optimal. This research also supports the idea that motivation has a direct association with a frontline employee's boundary spanning behavior. Even in situations where emotional exhaustion cannot be reduced, organizations may still influence frontline behaviors through motivation.