• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.79-104
• /
• 2020

Recently, as deep learning has attracted attention, the use of deep learning is being considered as a method for solving problems in various fields. In particular, deep learning is known to have excellent performance when applied to applying unstructured data such as text, sound and images, and many studies have proven its effectiveness. Owing to the remarkable development of text and image deep learning technology, interests in image captioning technology and its application is rapidly increasing. Image captioning is a technique that automatically generates relevant captions for a given image by handling both image comprehension and text generation simultaneously. In spite of the high entry barrier of image captioning that analysts should be able to process both image and text data, image captioning has established itself as one of the key fields in the A.I. research owing to its various applicability. In addition, many researches have been conducted to improve the performance of image captioning in various aspects. Recent researches attempt to create advanced captions that can not only describe an image accurately, but also convey the information contained in the image more sophisticatedly. Despite many recent efforts to improve the performance of image captioning, it is difficult to find any researches to interpret images from the perspective of domain experts in each field not from the perspective of the general public. Even for the same image, the part of interests may differ according to the professional field of the person who has encountered the image. Moreover, the way of interpreting and expressing the image also differs according to the level of expertise. The public tends to recognize the image from a holistic and general perspective, that is, from the perspective of identifying the image's constituent objects and their relationships. On the contrary, the domain experts tend to recognize the image by focusing on some specific elements necessary to interpret the given image based on their expertise. It implies that meaningful parts of an image are mutually different depending on viewers' perspective even for the same image. So, image captioning needs to implement this phenomenon. Therefore, in this study, we propose a method to generate captions specialized in each domain for the image by utilizing the expertise of experts in the corresponding domain. Specifically, after performing pre-training on a large amount of general data, the expertise in the field is transplanted through transfer-learning with a small amount of expertise data. However, simple adaption of transfer learning using expertise data may invoke another type of problems. Simultaneous learning with captions of various characteristics may invoke so-called 'inter-observation interference' problem, which make it difficult to perform pure learning of each characteristic point of view. For learning with vast amount of data, most of this interference is self-purified and has little impact on learning results. On the contrary, in the case of fine-tuning where learning is performed on a small amount of data, the impact of such interference on learning can be relatively large. To solve this problem, therefore, we propose a novel 'Character-Independent Transfer-learning' that performs transfer learning independently for each character. In order to confirm the feasibility of the proposed methodology, we performed experiments utilizing the results of pre-training on MSCOCO dataset which is comprised of 120,000 images and about 600,000 general captions. Additionally, according to the advice of an art therapist, about 300 pairs of 'image / expertise captions' were created, and the data was used for the experiments of expertise transplantation. As a result of the experiment, it was confirmed that the caption generated according to the proposed methodology generates captions from the perspective of implanted expertise whereas the caption generated through learning on general data contains a number of contents irrelevant to expertise interpretation. In this paper, we propose a novel approach of specialized image interpretation. To achieve this goal, we present a method to use transfer learning and generate captions specialized in the specific domain. In the future, by applying the proposed methodology to expertise transplant in various fields, we expected that many researches will be actively conducted to solve the problem of lack of expertise data and to improve performance of image captioning.

• Korean Security Journal
• /
• no.59
• /
• pp.133-159
• /
• 2019

The free semester system, introduced on a trial basis in 2013, has been fully implemented in all middle schools since 2016. The free semester system for middle school students is divided into subject activities and free semester activities with the purpose of students' dream and career exploration. While the activities of various vocational groups linked to subjects during the free semester are discussed, studies on the industrial security career education in middle schools are hard to find. In addition, the career sites that provide diverse information on career path for teachers, students and parents with support from the Ministry of Education have not established any program regarding industrial security. This study aims to look at the status of career education by the analysis of keywords for industrial security in the career experience network currently operated by the Ministry of Education and in-depth interview with career education teachers, students and parents, and industrial security experts. Based on such analysis, this study attempts to figure out a comprehensive understanding of the free semester system and to explore strategies for promoting industrial security education. The results of this study found that the activation plan for industrial security education requires the industry security education through career network, development of industrial security education program, training and placement of professional industrial security lecturer, and establishment of support systems for experience in industrial security.

• The Journal of the Korea Contents Association
• /
• v.15 no.3
• /
• pp.101-113
• /
• 2015

This study aims to prepare countermeasures to prevent and minimize drowning accident in inland waters by examining the current status of inland water safety management in Korea and diagnosing the defects. The defects in current inland water safety management is analyzed in four aspects. First is the legal defect that includes the absence of legislation that directs the inland water safety management. Second is the instructional defect such as the absence of educational program for prevention of inland water accidents and lack of professional water rescue experts. Third is cooperation defect such as dispersed reporting system and lack of private-public partnership in accident response. Fourth is the defect of emergency response ability, professionalism and accident response skills due to the dispersion and overlaps of safety management systems. In order to improve these defects, this study finds the countermeasures based on the survey of water sports professions and users and its analysis as follows: legislation of '(tentatively named) special act for water safety management in inland waters' is suggested in the legal aspects. A development of inland waters safety education program and training of water accident experts are suggested in the instructional aspects. Integrated operational system for water accident management, activation of safety network and re-establishment of private-public partnership are suggested in the cooperation aspects. Systematic and efficient inland water safety management plans such as enhancement of accident response skills and expertise and integrated inland water safety management with fire department-centered system were suggested in the aspects of emergency response ability.

• International Commerce and Information Review
• /
• v.14 no.2
• /
• pp.29-52
• /
• 2012

Since diplomatic relations with China in 1992, many Korean companies have entered into China and that expansion is currently continuing. But now, many of Korean enterprises tend to withdraw and return to the domestic, this is because that major factors are too much fast increasing in labor costs and the difficulty of local workforce management. In this study, it is researched that the type of human resource management of Korean firms entering into Heilongjiang Province, Harbin and the similarities and differences were investigated by comparing the form of personnel management of existing areas and Harbin area, and then this study was conducted the survey and interview of domestic companies operating in Harbin, to pursuit the efficient way to manage the workforce development and management strategies. The result of researches and workforce development strategies of entering firms are as follows; First, it is required to establish a human resource discovery system for entering companies in focusing on managerial work ability and on blue-collar which is separated by professional and technical experts and a simple blue-collar people. Second, it is required to entering companies that they have to grow up the promotion and exchange of the Department of Korean Studies in Harbin and have to build the industry and universities training programs to promote needed experts, and have to establish the expert pool systems to support the flexible labor supply.

• Journal of Biomedical Engineering Research
• /
• v.42 no.4
• /
• pp.150-158
• /
• 2021

Intracranial hemorrhage (ICH) refers to acute bleeding inside the intracranial vault. Not only does this devastating disease record a very high mortality rate, but it can also cause serious chronic impairment of sensory, motor, and cognitive functions. Therefore, a prompt and professional diagnosis of the disease is highly critical. Noninvasive brain imaging data are essential for clinicians to efficiently diagnose the locus of brain lesion, volume of bleeding, and subsequent cortical damage, and to take clinical interventions. In particular, computed tomography (CT) images are used most often for the diagnosis of ICH. In order to diagnose ICH through CT images, not only medical specialists with a sufficient number of diagnosis experiences are required, but even when this condition is met, there are many cases where bleeding cannot be successfully detected due to factors such as low signal ratio and artifacts of the image itself. In addition, discrepancies between interpretations or even misinterpretations might exist causing critical clinical consequences. To resolve these clinical problems, we developed a diagnostic model predicting intracranial bleeding and its subtypes (intraparenchymal, intraventricular, subarachnoid, subdural, and epidural) by applying deep learning algorithms to CT images. We also constructed a visualization tool highlighting important regions in a CT image for predicting ICH. Specifically, 1) 27,758 CT brain images from RSNA were pre-processed to minimize the computational load. 2) Three different CNN-based models (ResNet, EfficientNet-B2, and EfficientNet-B7) were trained based on a training image data set. 3) Diagnosis performance of each of the three models was evaluated based on an independent test image data set: As a result of the model comparison, EfficientNet-B7's performance (classification accuracy = 91%) was a way greater than the other models. 4) Finally, based on the result of EfficientNet-B7, we visualized the lesions of internal bleeding using the Grad-CAM. Our research suggests that artificial intelligence-based diagnostic systems can help diagnose and treat brain diseases resolving various problems in clinical situations.

• Journal of the Korea Institute of Construction Safety
• /
• v.6 no.1
• /
• pp.27-32
• /
• 2024

In this study, based on accident cases of manned and unmanned tower cranes, the types and causes of accidents were analyzed and tower crane accident prevention measures were proposed accordingly. As a result, 'lack of communication' was commonly analyzed as the biggest cause of accidents. Therefore, in this study, we investigated domestic and international systems and laws regarding signalmen responsible for communication between tower crane operators and workers and proposed the following three improvement methods. First, the signalman system must be legally and institutionally reestablished. Second, national agencies and private organizations with expertise should create standardized training manuals and distribute them to signalman educators, and create checklists to manage educators. Third, in the case of a site using a tower crane, the employer must mandatorily deploy a signalman with professional qualifications. Lastly, the results of this study are expected to highlight the differences in accident types and causes of manned and unmanned tower cranes and the need for legal and institutional improvement in the signal system.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.16 no.4
• /
• pp.106-119
• /
• 2013

As open source can reduce costs and apply to various fields rapidly, many countries have actively adopted open source. However, geo-spatial open source in Korea is not actively promoted yet comparing to other countries having similar infra environments. In this study, we analyzed the perception of geo-spatial open source, utilization status, the development possibility and future direction using questionnaire survey completed by experts dealing with spatial information. The survey result shows that many experts have experiences of using geo-spatial open source but they got a lack of understanding about open source license or regulations and only a few people got professional training. Insufficient references, the difficulty of maintenance, lack of support and low technical reliability have hindered the adoption of geo-spatial open source. Only some part of geo-spatial open source software or libraries in some field have been used in the country. However, many researchers rate highly development potential and plan to use geo-spatial open source soon. If user's convenience, reference materials, technical trust and policy support are improved, open source field for spatial information will be developed greatly in the future.

• Journal of the Society of Disaster Information
• /
• v.19 no.2
• /
• pp.395-410
• /
• 2023

Purpose: The purpose of this study was to analyze the current state of drone terrorism response at such critical national facilities and derive improvements, especially to identify problems in laws and systems to effectively utilize the anti-drone system and present directions for improvement. Method: A qualitative research method was used for this study by analyzing a variety of issues not discussed in existing research papers and policy documents through in-depth interviews with subject matter experts. In-depth interviews were conducted based on 12 semi-structured interviews by selecting 16 experts in the field of anti-drone and terrorism in Korea. The interview contents were recorded with the prior consent of the study participants, transcribed back to the Korean file, and problems and improvement measures were derived through coding. For this, the threats and types were analyzed based on the cases of drone terrorism occurring abroad and measures to establish anti-drone system were researched from the perspective of laws and systems by evaluating the possibility of drone terrorism in the Republic of Korea. Result: As a result of the study, improvements to some of the problems that need to be preceded in order to effectively respond to drone terrorism at critical national facilities in the Republic of Korea, have been identified. First, terminologies related to critical national facilities and drone terrorism should be clearly defined and reflected in the Integrated Defense Act and the Terrorism Prevention Act. Second, the current concept of protection of critical national facilities should evolve from the current ground-oriented protection to a three-dimensional protection concept that considers air threats and the Integrated Defense Act should reflect a plan to effectively install the anti-drone system that can materialize the concept. Third, a special law against flying over critical national facilities should be enacted. To this end, legislation should be enacted to expand designated facilities subject to flight restrictions while minimizing the range of no fly zone, but the law should be revised so that the two wings of "drone industry development" and "protection of critical national facilities" can develop in a balanced manner. Fourth, illegal flight response system and related systems should be improved and reestablished. For example, it is necessary to prepare a unified manual for general matters, but thorough preparation should be made by customizing it according to the characteristics of each facility, expanding professional manpower, and enhancing response training. Conclusion: The focus of this study is to present directions for policy and technology development to establish an anti-drone system that can effectively respond to drone terrorism and illegal drones at critical national facilities going forward.

• Journal of Yeungnam Medical Science
• /
• v.12 no.2
• /
• pp.347-365
• /
• 1995

A survey was conducted to study perception and attitudes of health workers towards health center's activities and organization of health services, from August 15 to September 30, 1994. The study population was 310 health workers engaged in seven urban health centers in Taegu City area. A questionnaire method was used to collect data and response rate was 81.3 percent or 252 respondents. The following are summaries of findings: Profiles of study population: Health workers were predominantly female(62.3%); had college education(60.3%); and held medical and nursing positions(39.6%), technicians(30.6%) and public health/administrative positions(29.8%). Perceptions on health center's resources: Slightly more than a half(51.1%) of respondents expressed that physical facilities of the centers are inadequate; equipments needed are short(39.0%); human resource is inadequate(44.8%); and health budget allocated is insufficient(38.5%) to support the performance of health center's activities. Decentralization and health services: The majority revealed that the decentralization of government system would affect the future activities of health centers(51.9%) which may have to change. However, only one quarter of respondents(25.4%) seemed to view the decentralization positively as they expect that it would help perform health activities more effectively. The majority of the respondents(78.6%) insisted that the function and organization of the urban health centers should be changed. Target workload and job satisfaction: A large proportion (43.3%) of respondents felt that present target setting systems for various health activities are unrealistic in terms of community needs and health center's situation while only 11.1 percent responded it positively; the majority(57.5%) revealed that they need further training in professional fields to perform their job more effectively; more than one third(35.7%) expressed that they enjoy their professional autonomy in their job performance; and a considerable proportion (39.3%) said they are satisfied with their present work. Regarding the personnel management, more worker(47.3%) perceived it negatively than positive(11.5%) as most of workers seemed to think the personnel management practiced at the health centers is not fair or justly done. Health services rendered: Among health services rendered, health workers perceived the following services are most successfully delivered; they are, in order of importance, Tb control, curative services, and maternal and child health care. Such areas as health education, oral health, environmental sanitation, and integrated health services are needed to be strengthening. Regarding the community attitudes towards health workers, 41.3 percent of respondents think they are trusted by the community they serve. New areas of concern identified which must be included in future activities of health centers are, in order of priority, health care of elderly population, home health care, rehabilitation services, and such chronic diseases control programs as diabetes, hypertension, school health and mental health care. In conclusion, the study revealed that health workers seemed to have more negative perceptions and attitudes than positive ones towards organization and management of health services and activities performed by the urban health centers where they are engaged. More specifically, the majority of health workers studied revealed to have the following areas of health center's organization and management inadequate or insufficient to support effective performance of their health activities: Namely, physical facilities and equipments required are inadequate; human and financial resources are insufficient; personnel management is unsatisfactory; setting of service target system is unrealistic in terms of the community needs. However, respondents displayed a number of positive perceptions, particularly to those areas as further training needs and implementation of decentralization of government system which will bring more autonomy of local government as they perceived these change would bring the necessary changes to future activities of the health center. They also displayed positive perceptions in their job autonomy and have job satisfactions.

• Cartoon and Animation Studies
• /
• s.47
• /
• pp.31-52
• /
• 2017

NCS education was created to realize a society in which skills and abilities are respected, such as transcending specifications, establishing recruitment systems, and developing and disseminating national incompetence standards. At the university level, special lectures and job training are being strengthened to raise industrial experts. Especially, in the field of animation, new technologies are rapidly emerging and demanding convergent talents with various fields. In order to meet these social demands, there is a limit to the existing one-class teaching method. In order to solve this problem, it is necessary to participate in a variety of specialized teachers. In other words, rather than solving problems of students' job training and job creation, It is aimed to solve jointly, Team teaching was suggested as a method for this. The expected effects that can be obtained through this are as follows. First, the field of animation is becoming more diverse and complex. The ability to use NCS job-related skills pools can be matched with professors from other departments to enable a wider range of professional instruction. Second, it is possible to use partial professorships in other departments by actively utilizing professors in the university. This leads to the strengthening of the capacity of teachers in universities. Third, it is possible to build a broader and more integrated educational system through cooperative teaching of professors in other departments. Finally, the advantages of special lectures and mentor support of college professors' pools are broader than those of field specialists. A variety of guidance for students can be made with responsible professors. In other words, time and space constraints can be avoided because the mentor is easily met and guided by the university.