• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.461-467
• /
• 2020

In noisy and multi-speaker environments, the performance of speech recognition is unavoidably lower than in a clean environment. To improve speech recognition, in this paper, the signal of the speaker of interest is extracted from the mixed speech signals with multiple speakers. The VoiceFilter model is used to effectively separate overlapped speech signals. In this work, clustering by Probabilistic Linear Discriminant Analysis (PLDA) similarity score was employed to detect the speech signal of the interested speaker, which is used as the reference speaker to VoiceFilter-based separation. Therefore, by utilizing the speaker feature extracted from the detected speech by the proposed clustering method, this paper propose a speaker diarization system using only the mixed speech without an explicit reference speaker signal. We use phone-dataset consisting of two speakers to evaluate the performance of the speaker diarization system. Source to Distortion Ratio (SDR) of the operator (Rx) speech and customer speech (Tx) are 5.22 dB and -5.22 dB respectively before separation, and the results of the proposed separation system show 11.26 dB and 8.53 dB respectively.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.1
• /
• pp.135-145
• /
• 2020

This research is mainly aimed at finding out about the effects of the safety and health management system on corporate performance through systematic operation by efficiently allocating material and human resources within the company by participating all employees and stakeholders in order to prevent and maintain industrial accidents and the optimal working environment, and how to maintain and activate the safety and health management system at the center of electric contractors.The analysis results are as follows. First, management, organizational management and resource preparation will have a positive impact on the management capability of the electric power corporation. It was assessed that the more well-transmitted and understood within the organization, the better the construction plan, the better the equipment management status, the more positively the management capability of electric works was to be achieved. Second, management, organizational management and resource preparation will have a positive impact on corporate management performance.This seems to have a positive effect on a company's business performance when the standards of OHSAS are met with construction plan and construction equipment management are high as related information such as industrial safety and health laws are strengthened and companies' safety and health activities, advanced safety and culture are released to facilitate organizational management.Third, the management ability of the electric power corporation will have a mediated effect on the effect of management, organization management and resource preparation on the performance of the enterprise. This means that the direct effect of the independent variable management organization on corporate management performance is .401 The indirect effect is .168.658 shows that the direct effect of resource preparation on corporate management performance is .423, the indirect effect is .178 and the total effect.It was analyzed at 643.

• The Korean Journal of Archival Studies
• /
• no.15
• /
• pp.219-262
• /
• 2007

Business organization have developed in close association with the society afterward. Moreover, under capitalism business archives, though they are created in private sector, have started to have public characteristics and be used in public domain beyond internal use in business organization. Records and Archives management at a corporate level increasingly become indispensible. Business organization can use archive management to improve job efficiency and customer service and to facilitate legal matters, marketing, advertising, property management, personnel management and publicity. Additionally, They can secure corporate identity and social reliability as well as transparency in management. This is turn helps secure corporate competitiveness to play as a medium for creating new profit, which will enhance corporate brands. The records and Archives management, which recently kicks off among business organization, are to collect scattered archives and seek systemic management through archives management systems. This study present ways to collect archives scattered before archives management systems were adopted according to archives management. As a prior investigation, the scope and characteristics of business archives are defined. Visit to business organization to collect data and interview with officials responsible were carried out as a preliminary investigation to conduce acquisition policy. Based on the results of the investigation, acquisition policy of Meritz was conducted. into internal and external collection activities, event collection activities. Value appraisal and display appraisal of archives were established as a appraisal policy for efficient management and utilization of collected business archives. This study takes the case of Metitz Fire & Marine Insurance Co, Ltd (Meritz) as a example to present ways to manage business archives specifically.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.177-190
• /
• 2021

Due to the development of the fourth industrial revolution technology, efforts are being made to improve areas that humans cannot handle by utilizing artificial intelligence techniques such as machine learning. Although on-demand production companies also want to reduce corporate risks such as delays in delivery by predicting total production time for orders, they are having difficulty predicting this because the total production time is all different for each order. The Theory of Constraints (TOC) theory was developed to find the least efficient areas to increase order throughput and reduce order total cost, but failed to provide a forecast of total production time. Order production varies from order to order due to various customer needs, so the total production time of individual orders can be measured postmortem, but it is difficult to predict in advance. The total measured production time of existing orders is also different, which has limitations that cannot be used as standard time. As a result, experienced managers rely on persimmons rather than on the use of the system, while inexperienced managers use simple management indicators (e.g., 60 days total production time for raw materials, 90 days total production time for steel plates, etc.). Too fast work instructions based on imperfections or indicators cause congestion, which leads to productivity degradation, and too late leads to increased production costs or failure to meet delivery dates due to emergency processing. Failure to meet the deadline will result in compensation for delayed compensation or adversely affect business and collection sectors. In this study, to address these problems, an entity that operates an order production system seeks to find a machine learning model that estimates the total production time of new orders. It uses orders, production, and process performance for materials used for machine learning. We compared and analyzed OLS, GLM Gamma, Extra Trees, and Random Forest algorithms as the best algorithms for estimating total production time and present the results.

• Archives of design research
• /
• v.13 no.2
• /
• pp.73-80
• /
• 2000

In this study design information was separately defined form general product information and thus factors reflected in product design ion the basis of values and roles were extracted. The following is a classification of 5 different types of design factors divided according to their disposition. ·Innovation factor - element which previously did not exist or element related with explicit reformation ·Open factor - active element which not only improves current performance but also induces new functions through understanding of usage situations and new possibilities. ·Anterior factor - element which prolongs and develops the early development requirements of products through C.I. and P.I. related elements and characteristics of previous models and design strategy. Self-evidence factor - element related with function visualization through product structure which may make possible the consolidation of shape and function. Rigid factor - element, based on the human factors engineering, related with the safety and efficiency of users. This classification was obtained by defining major characteristics of products considering the target consumer and market characteristics. In this classification factor structuring design process which efficiently deducted a differentiated final product by synthesizing factors of higher importance as dominant factors was proposed. With this kind of factor structuring process, product differentiation may be achieved by bestowing individual characteristics to each product by combining design dominant factors associated with the product for a specific purpose from the stages of product concept development. Moreover, this may be used as an approach to actively correspond to the various and specific demands of the comsumer.

• Korean Security Journal
• /
• no.46
• /
• pp.7-30
• /
• 2016

This study found the strategies for activating the security industry to utilize social network services based on the platform business model. This research was utilized for in-depth interview and IPA analysis. And use it was to check the contents and strategic improvement projects that can actually materialize and direction of the strategy. First, run a priority need area is a private center of community policing related portal development and operation, universal social networking service(SNS) utilizing expanded, professional training, IT-based security content management and operation of IT infrastructure security guards and security professionals up educational content development, online security guards and security professionals-up refresher training program development. Second, the area over the inventory capabilities increase the effectiveness of the security guards was constructed open-type comprehensive public information system. Third, the area needed to be reviewed are the individual security industry experts workers operating information channels, dedicated customer service and expanding the event of a private security guard & security service providers up. Fourth, the effectiveness of the insufficient area are discuss system improvements, the sharing of community policing closed Cameras for proposals for the expanded utilization of social networking services, private development organizations Social Network Service(SNS).

• The KIPS Transactions:PartD
• /
• v.16D no.3
• /
• pp.395-406
• /
• 2009

Korean government has operated EA by the act on efficient introduction of information system and operation, etc. But the evaluation system for EA and the criteria don't prepare well. Particularly, There is no model for EA performance measurement and the way is insufficient. In this study, we derived 8 areas and 17 criteria for the performance evaluation based on the Performance Reference Model of U.S FEA and Korea. And we also derived 8 areas and 10 criteria for it based on the OMB EA Assessment Framework and the EA maturity model in Korea. We propose the performance evaluation model of the five areas that consists of the business performance, customer performance, process, human resource and the technology for EA performance evaluation. To verify the model, we applied the model to three organizations and evaluated EA performance. In addition, we compared the performance result with the performance evaluation area of EA maturity model of Korea to verify the result. We also analyzed the criteria of the proposed performance evaluation model with the current EA maturity model and Performance Reference Model of Korea. As a result of the evaluation, we verified of the proposed performance evaluation model, too.

• Journal of Intelligence and Information Systems
• /
• v.14 no.1
• /
• pp.1-17
• /
• 2008

Data mining is defined as the process of discovering meaningful and useful pattern in large volumes of data. In particular, finding associations rules between items in a database of customer transactions has become an important thing. Some data structures and algorithms had been proposed for storing meaningful information compressed from an original database to find frequent itemsets since Apriori algorithm. Though existing method find all association rules, we must have a lot of process to analyze association rules because there are too many rules. In this paper, we propose a new data structure, called a Frequent Pattern Network (FPN), which represents items as vertices and 2-itemsets as edges of the network. In order to utilize FPN, We constitute FPN using item's frequency. And then we use a clustering method to group the vertices on the network into clusters so that the intracluster similarity is maximized and the intercluster similarity is minimized. We generate association rules based on clusters. Our experiments showed accuracy of clustering items on the network using confidence, correlation and edge weight similarity methods. And We generated association rules using clusters and compare traditional and our method. From the results, the confidence similarity had a strong influence than others on the frequent pattern network. And FPN had a flexibility to minimum support value.

• The Journal of the Korea Contents Association
• /
• v.21 no.4
• /
• pp.77-87
• /
• 2021

Smart Factory refers to a factory that can be controlled by itself with an intelligent factory that improves productivity, quality and customer satisfaction by combining the entire process of manufacturing and production with digital automation solutions. The manufacturing industry around the world is rapidly changing, with Germany, Europe, and the United States at the center. In order to cope with such changes, the Korean government is also implementing a policy to spread the supply of smart factories for small and medium-sized companies, and related ministries and agencies such as the Ministry of Commerce, Industry and Energy, the Ministry of SMEs and Venture Business, the Korea Institute of Technology and Information Promotion, and local technoparks, as well as large companies such as Samsung, SK and LG are actively investing in smart manufacturing projects to support smart factories[1]. Factory Automation (FA) construction has many issues regarding the connection of heterogeneous equipment. The most difficult aspect of configuring various communications from various equipment is the reason. Although it may not be known if there are standards or products made up of the same company, it is not easy to build equipment that is old, up-to-date, and different use environments through a series of communications. To solve this problem, we would like to propose a method of communication using Modbus, one of FieldBus, which is one of the many industrial devices of PLC, a representative facility control system, and is used as a communication standard.

• Journal of Korea Society of Industrial Information Systems
• /
• v.19 no.2
• /
• pp.119-135
• /
• 2014

This study is aimed at understanding the factors behind deciding to accept a social network service (SNS) from the viewpoint of tourists who are users of tourism SNS. The study also seeks to clarify the effects these deduced factors have on the intention of users to continuously use SNS. To this end, individual properties (such as self-efficacy, socio-cultural effects, social presence and people's innovativeness), systematic properties (like system quality and information quality)and usefulness/availability were used as factors with regard to the decision to accept tourism SNS based on previous studies and efforts were made to structurally clarify the effects of such previous factors on people's intention to continuously use SNS through perceived value and satisfaction. SNS had significant effects on satisfaction and, furthermore, significantly affected tourists' intention to continuously use it. Based on such study results, factors behind deciding to accept SNS from the viewpoint of tourists affected customers' perceived value and satisfaction and ultimately affected their intention to continuously use SNS. To achieve the purpose of the study, a survey was conducted on about 250 Busan residents who had used SNS in relation to tourist activities, such as exhibitions, conventions, accommodation, trips, aviation service and transportation. According to an empirical study, factors behind deciding to accept tourism SNS, including individual properties, systematic properties and usefulness/availability had statistically significant effects on perceived value. The usefulness/availability factor had the largest influence, in particular, followed by the systematic factor and individual factor. The value perceived in the process of using tourism SNS had significant effects on satisfaction and, furthermore, significantly affected tourists' intention to continuously use it. Based on such study results, factors behind deciding to accept SNS from the viewpoint of tourists affected customers' perceived value and satisfaction and ultimately affected their intention to continuously use SNS.