• Journal of Computational Design and Engineering
• /
• v.3 no.1
• /
• pp.53-62
• /
• 2016

The current trends of product customization and repair of high value parts with individual defects demand automation and a high degree of flexibility of the involved manufacturing process chains. To determine the corresponding requirements this paper gives an overview of manufacturing process chains by distinguishing between horizontal and vertical process chains. The established way of modeling and programming processes with CAx systems and existing approaches is shown. Furthermore, the different types of possible adaptions of a manufacturing process chain are shown and considered as a cascaded control loop. Following this it is discussed which key requirements of repair process chains are unresolved by existing approaches. To overcome the deficits this paper introduces repair features which comprise the idea of geometric features and defines analytical auxiliary geometries based on the measurement input data. This meets challenges normally caused by working directly on reconstructed geometries in the form of triangulated surfaces which are prone to artifacts. Embedded into function blocks, this allows the use of traditional approaches for manufacturing process chains to be applied to adaptive repair process chains.

• The Journal of Society for e-Business Studies
• /
• v.19 no.2
• /
• pp.95-108
• /
• 2014

Opinion Mining is one of the application domains of text mining which extracting opinions from documents, and much researches are currently underway. Most of related researches focused on the sentiment classification which classifies the documents into positive/negative opinions. However, there is a little interest in extracting the features characterizing the individual product. In this paper, we propose the technique classifying the opinion documents according to the product features, and selecting the those features characterizing each product. In the proposed method, we utilize the document clustering technique and develope a new algorithm for evaluating the similarity between documents. In addition, through experiments, we prove the usefulness of proposed method.

• Journal of the Korean housing association
• /
• v.26 no.6
• /
• pp.181-190
• /
• 2015

This study emphasizes a new senior housing type which can provide individual housing units and common facilities for retirees, particularly who will be retired from universities. It is called a university-based retirement community. This study conducted a questionnaire survey to investigate future residents' needs for architectural environments that included housing types, common facility features, and proximity, and also development methods in response to the university involvement levels. The survey questionnaire was administered in one national university in Korea. A total of 214 responses were valid for statistical analyses. Major findings are as follows: Over 65% of the respondents were willing to live in the university-based retirement community. Regarding the location of the community, they responded the community would not need to be located on campus. Preferred common facilities in the UBRC were indoor fitness centers, the shuttle bus stops connecting to the adjacent areas, and bath and sauna facilities. The respondents emphasized university's contribution toward offering educational programs for UBRC residents. Lastly, their responses to the university role and involvement in the development and construction process were identified. This study results are expected to provide essential information for facilitating the Korean model of university-based retirement communities in the future.

• Journal of Communications and Networks
• /
• v.7 no.3
• /
• pp.353-366
• /
• 2005

In future telecommunications systems, behaviour will be defined by inexperienced users for many different purposes, often by specifying requirements in the form of policies. The call processing language (CPL) was developed by the IETF in order to make it possible to define telephony policies in an Internet telephony environment. However, user-defined policies can hide inconsistencies or feature interactions. In this paper, a method and a tool are proposed to flag inconsistencies in a set of policies and to assist the user in correcting them. These policies can be defined by the user in a user-friendly language or derived automatically from a CPL script. The approach builds on a pre-existing logic programming tool that is able to identify inconsistencies in feature definitions. Our new tool is capable of explaining in user-oriented terminology the inconsistencies flagged, to suggest possible solutions, and to implement the chosen solution. It is sensitive to the types of features and interactions that will be created by naive users. This tool is also capable of assembling a set of individual policies specified in a user-friendly manner into a single CPL script in an appropriate priority order for execution by telecommunication systems.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.7
• /
• pp.3427-3430
• /
• 2012

Aim: The significance of the mucinous adenocarcinoma in TNM staging and prognosis for colorectal tumor patients is still controversial. The aim was to provide a meta-analysis for TNM staging and prognostic features of colorectal tumors. Methods: 30 individual case-control studies were finally included into this meta-analysis, involving a total of 444,489 cancer cases and 45,050 mucinous adenocarcinomas, of relations with TNM staging and prognostic features. Results: Compared to non-mucinous adenocarcinoma patients, the TNM IV stage accounted for a larger percentage of mucinous adenocarcinomas (OR=1.48, 95%CI 1.28-1.71, POR<0.001) and the prognosis was significantly poor (HR=1.06, 95%CI 1.04-1.08, P<0.001). After heterogeneity testing, the results was similar to the holistic approach outcome (HR=1.48, 95%CI 1.35-1.62, P<0.001). Conclusion: Compared to patients with non-mucinous adenocarcinomas, mucinous adenocarcinoma patients with later TNM staging make up a big percentage, and mucinous adenocarcinoma is an independent risk factor for poor prognosis.

• Journal of Information Processing Systems
• /
• v.10 no.3
• /
• pp.443-458
• /
• 2014

An extreme learning machine (ELM) is a recently proposed learning algorithm for a single-layer feed forward neural network. In this paper we studied the ensemble of ELM by using a bagging algorithm for facial expression recognition (FER). Facial expression analysis is widely used in the behavior interpretation of emotions, for cognitive science, and social interactions. This paper presents a method for FER based on the histogram of orientation gradient (HOG) features using an ELM ensemble. First, the HOG features were extracted from the face image by dividing it into a number of small cells. A bagging algorithm was then used to construct many different bags of training data and each of them was trained by using separate ELMs. To recognize the expression of the input face image, HOG features were fed to each trained ELM and the results were combined by using a majority voting scheme. The ELM ensemble using bagging improves the generalized capability of the network significantly. The two available datasets (JAFFE and CK+) of facial expressions were used to evaluate the performance of the proposed classification system. Even the performance of individual ELM was smaller and the ELM ensemble using a bagging algorithm improved the recognition performance significantly.

• Journal of Korea Multimedia Society
• /
• v.11 no.6
• /
• pp.764-776
• /
• 2008

Image identification is the process of checking whether the query image is the transformed version of the specific original image or not. In this paper, image identification method based on feature composition is proposed. Used features include color distance, texture information and average pixel intensity. We extract color characteristics using color distance and texture information by Modified Generalized Symmetry Transform as well as average intensity of each pixel as features. Individual feature is quantized adaptively to be used as bins of histogram. The histogram is normalized according to data type and it is used as the signature in comparing the query image with database images. In matching part, Manhattan distance is used for measuring distance between two signatures. To evaluate the performance of the proposed method, independent test and accuracy test are achieved. In independent test, 60,433 images are used to evaluate the ability of discrimination between different images. And 4,002 original images and its 29 transformed versions are used in accuracy test, which evaluate the ability that the proposed algorithm can find the original image correctly when some transforms was applied in original image. Experiment results show that the proposed identification method has good performance in accuracy test. And the proposed method is very useful in real environment because of its high accuracy and fast matching capacity.

• Journal of Korean language education
• /
• v.23 no.1
• /
• pp.123-159
• /
• 2012

This study investigates relationships between TOPIK ratings and measures of grammaticality judgement competence in the acquisition of Korean as a second language. Data were collected on the linguistic abilities of learners' at 3 to 6 on the TOPIK scale, focusing on perception in grammar-mostly morphology and syntax, some lexis, and a few of collocation. The results show that (i) proficiency and grammaticality judgement competence show high correlation, (ii) individual accuracy scores correlate strongly with levels on the TOPIK proficiency scale on most linguistic features in the test, and (iii) Japanese speakers outperform Chinese speakers at the same levels of proficiency on most linguistic features. The findings indicate that global proficiency scales like the TOPIK can be deconstructed using grammaticality judgement test that provides detailed measures of learners' control of linguistic features.

• Journal of the Korean Society of Safety
• /
• v.36 no.5
• /
• pp.52-60
• /
• 2021

As the prevention of fatal accidents is considered an essential part of social responsibilities, both government and individual have devoted efforts to mitigate the unsafe conditions and behaviors that facilitate accidents. Several studies have analyzed the factors that cause fatal accidents and compared them to those of non-fatal accidents. However, studies on mathematical and systematic analysis techniques for identifying the features of fatal accidents are rare. Recently, various industrial fields have employed machine learning algorithms. This study aimed to apply machine learning algorithms for the classification of fatal and non-fatal accidents based on the features of each accident. These features were obtained by text mining literature on accidents. The classification was performed using four machine learning algorithms, which are widely used in industrial fields, including logistic regression, decision tree, neural network, and support vector machine algorithms. The results revealed that the machine learning algorithms exhibited a high accuracy for the classification of accidents into the two categories. In addition, the importance of comparing similar cases between fatal and non-fatal accidents was discussed. This study presented a method for classifying accidents using machine learning algorithms based on the reports on previous studies on accidents.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.7
• /
• pp.4508-4515
• /
• 2014

Real-time body detection has been researched actively. On the other hand, the detection rate of color distorted images is low because most existing detection methods use static skin color model. Therefore, this paper proposes a new method for detecting the skin color region using a gradient map and saturation features. The basic procedure of the proposed method sequentially consists of creating a gradient map, extracting a gradient feature of skin regions, noise removal using the saturation features of skin, creating a cluster for extraction regions, detecting skin regions using cluster information, and verifying the results. This method uses features other than the color to strengthen skin detection not affected by light, race, age, individual features, etc. The results of the detection rate showed that the proposed method is 10% or more higher than the traditional methods.