• Journal of Internet Computing and Services
• /
• v.20 no.4
• /
• pp.21-27
• /
• 2019

Selection of feature pattern gathered from the observation of the RNA sequencing data (RNA-seq) are not all equally informative for identification of differential expressions: some of them may be noisy, correlated or irrelevant because of redundancy in Big-Data sets. Variable selection of feature pattern aims at differential expressed gene set that is significantly relevant for a special task. This issues are complex and important in many domains, for example. In terms of a computational research field of machine learning, selection of feature pattern has been studied such as Random Forest, K-Nearest and Support Vector Machine (SVM). One of most the well-known machine learning algorithms is SVM, which is classical as well as original. The one of a member of SVM-criterion is Support Vector Machine-Recursive Feature Elimination (SVM-RFE), which have been utilized in our research work. We propose a novel algorithm of the SVM-RFE with Q-learning in reinforcement learning for better variable selection of feature pattern. By comparing our proposed algorithm with the well-known SVM-RFE combining Welch' T in published data, our result can show that the criterion from weight vector of SVM-RFE enhanced by Q-learning has been improved by an off-policy by a more exploratory scheme of Q-learning.

• 재활복지
• /
• v.21 no.3
• /
• pp.129-146
• /
• 2017

In an event of an emergency, such as fire in a building, visually impaired and blind people are prone to exposed to a level of danger that is greater than that of normal people, for they cannot be aware of it quickly. Current fire detection methods such as smoke detector is very slow and unreliable because it usually uses chemical sensor based technology to detect fire particles. But by using vision sensor instead, fire can be proven to be detected much faster as we show in our experiments. Previous studies have applied various image processing and machine learning techniques to detect fire, but they usually don't work very well because these techniques require hand-crafted features that do not generalize well to various scenarios. But with the help of recent advancement in the field of deep learning, this research can be conducted to help solve this problem by using deep learning-based object detector that can detect fire using images from security camera. Deep learning based approach can learn features automatically so they can usually generalize well to various scenes. In order to ensure maximum capacity, we applied the latest technologies in the field of computer vision such as YOLO detector in order to solve this task. Considering the trade-off between recall vs. complexity, we introduced two convolutional neural networks with slightly different model's complexity to detect fire at different recall rate. Both models can detect fire at 99% average precision, but one model has 76% recall at 30 FPS while another has 61% recall at 50 FPS. We also compare our model memory consumption with each other and show our models robustness by testing on various real-world scenarios.

• Journal of Korean Society of Archives and Records Management
• /
• v.19 no.2
• /
• pp.147-172
• /
• 2019

With the provision of the original text information disclosure service, the time spent on determining the disclosure of the original text information decreased, and the number of original text information disclosure significantly increased. In public institutions, the risk of the exposure of personal information also increased. In this study, the status of personal information protection in the original text information disclosure service was investigated. Moreover, the causes of the exposure of personal information were analyzed, and improvements were proposed. The survey presented the following results. First, 13% of the original text information collected contains personal information, which is the nondisclosure information. Second, among the original text information that includes personal information, the original text information, including the personal information of the public official, was the most important. In particular, many records about vacation and medical leaves were found. Third, there were many cases in which information about the individual of the representative was exposed in the agency that deals mainly with the contract work. Fourth, a large volume of personal information was not detected by filtering personal information. Upon analyzing the cause of the exposure of personal information, the following improvements are suggested. First, privacy guidelines should be redesigned. Second, the person in charge of the task of deciding whether or not to disclose original text information should be trained further. Third, the excessive disclosure of information based on the government's quantitative performance should be eased. Fourth, the filtering function of the personal information of the original text information disclosure system should be improved.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.7
• /
• pp.578-588
• /
• 2019

As the service industry develops, service quality, customer satisfaction, and human resource management are considered priorities in modern management to maintain a company's growth. Therefore, understanding the strategic importance of service marketing is an essential task for modern companies. This study examined the relationship between the internal service quality of employees in the organization and customer orientation through organizational effectiveness. In the case of an airline, a service can be defined as an interaction between an external customer and an internal customer service provider. This interaction significantly affects the behavior and attitude of the employees. Based on the results, empowerment has a significant influence on the internal service quality, but it has no significant effect on customer orientation. As the relationship between department and employees improved, the more confident staff showed an improved ability to perform their work. Therefore, it is important that the organizational structure and the reporting system are as concise and clear as possible to allow employees to accurately recognize the authorities and responsibilities assigned to them and have autonomy and discretion in the framework.

• Journal of the Korean Society for Library and Information Science
• /
• v.53 no.2
• /
• pp.5-27
• /
• 2019

The purpose of this study is to analyze the media of middle school social studies 1 textbooks with the information processing model and to suggest educational information services of teacher librarians under a collaborative Instruction. For this purpose, 1,089 inquiry tasks embedded in 8 types of textbooks for middle school social studies developed under the 2015 revised curriculum were analyzed. The media as an input element was analyzed by the type and the characteristic as a processing element was analyzed by the cognitive behavior types. And the aspect of the output factor of the media utilized the multiple intelligences. As a result of the analysis, the media in the inquiry task solving process mainly consisted of visual media based on photographs and illustrations and general reading materials. The processing method of media is understanding through analysis and inference through structuring. And the output utilized speaking and writing of the language intelligence. Based on the results, it is shown that educational information services that teacher librarians could provide for inquiry activities are composed of developing curriculum map, teaching inquiry processing and skills, and designing work sheets with graphic organizer and multiple intelligences under the information processing steps.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.6
• /
• pp.725-731
• /
• 2020

In mineral resource development, resource exploration is a task to find economical minerals on the surface and underground, and the success rate is low compared to the development and production stages, and it is necessary to collect a lot of data through exploration and accurately analyze the collected information. In this study, mine spatial information was constructed using a 3D (Three-dimensional) laser scanner, and accuracy evaluation was performed to obtain a maximum deviation of 0.140 m and an average of 0.095 m in the X, Y and Z directions, and the possibility of utilizing the construction of mine geospatial information through a 3D laser scanner could be presented. In addition, the ore body modeling was performed by applying the interpolation method of the ore body section using the resource exploration results. The ore body modeling result was superimposed with the modeling result of the mine geospatial information built through the 3D laser scanner to construct the ore body modeling result based on the precise mine geospatial information. The results of ore body modeling based on mine geospatial information built through research can increase the ease of data interpretation and the accuracy of the calculated data, which will greatly increase the efficiency of work related to mineral resource development and mine damage prevention in the future.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.1
• /
• pp.379-384
• /
• 2021

Despite the numerous graduates being produced in practical music and history, which have not been shorter than 30 years, the employment of students remains an unsolvable task. Most graduates are employed by private institutes as music instructors or got involved in band activities, which are non-regular work and not stable. The rapid development of K-pop along with national strength has changed our lives as well. As a result, the cultural and artistic fields, which were previously recognized only as luxury, have rapidly become popular. In the form of learning, internalized and experiencing, not just watching has a huge impact on improving the quality of our lives. This is reflected in national policies including the operation of cultural arts, education programs in elementary, middle, and high schools, and art programs designed to improve the welfare of residents at local community centers. It is time to expand its job-horizon to the relevant fields, and thus focus on promoting programs related to obtaining certificates to help our students find jobs. In addition, the government should create a course for music teacher certification in the field of practical music that differs from the current music teacher certification of secondary schools. It is very urgent to establish the teaching course in four-year universities or graduate schools of practical music education.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.1
• /
• pp.1-8
• /
• 2021

In the political field of news articles, there are polarized and biased characteristics such as conservative and liberal, which is called political bias. We constructed keyword-based dataset to classify bias of news articles. Most embedding researches represent a sentence with sequence of morphemes. In our work, we expect that the number of unknown tokens will be reduced if the sentences are constituted by subwords that are segmented by the language model. We propose a document embedding model with subword tokenization and apply this model to SVM and feedforward neural network structure to classify the political bias. As a result of comparing the performance of the document embedding model with morphological analysis, the document embedding model with subwords showed the highest accuracy at 78.22%. It was confirmed that the number of unknown tokens was reduced by subword tokenization. Using the best performance embedding model in our bias classification task, we extract the keywords based on politicians. The bias of keywords was verified by the average similarity with the vector of politicians from each political tendency.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.12 no.4
• /
• pp.41-53
• /
• 2002

Role Based Access Control (RBAC), which is a method, using role as an access control, has been popular with users and it is recognized as an effective method to replace the Discretionary Access Control and the Mandatory Access Control However, the existing Role Based Access Control Models have only been limited to the bureaucracy organization in which a distinctive hierarchy system was used, incorporating a stable structure and a standardized work system. Only in some parts, some access control models have been used, which supports 'Team' concept, such as Team Based Access Control Model. However, it did not incorporate the characteristics of the adhocracy organization, which is similar to the company's task force team, whose characteristics are organic, temporary, no standardized operation procedures, and many frequent changes. In this study, we have discussed the characteristics of the adhocracy organization which is different from the existing bureaucracy organization, and we have also discussed the problems related to when the existing access control models are used as the access control model for the adhocracy organization due to its characteristics. In addition, based on the problems, we have suggested an improved role based access control model for the adhocracy organization, and have come up with the solutions when any problems occur in the access control system.

• Journal of Korean Academy of Dental Administration
• /
• v.8 no.1
• /
• pp.15-23
• /
• 2020

The aim of this study is to identify future-oriented tasks for Korean dental hygienists based on a literature review. A literature search is performed using 14 keywords related to tasks carried out by dental hygienists, and included articles published from 2000 to 2019 in the databases KISS, RISS, DBpia, NDSL, Papersearch, Pubmed, and Google Scholar. Six reviewers assessed the titles and abstracts of articles, and an article was selected if the study was considered to cover future-oriented tasks for Korean dental hygienists. Based on the results six local studies and two foreign studies were used for literature review and data extraction. In total, 38 tasks were classified as future-oriented tasks of dental hygienists according to the following criteria: 1) tasks that were specifically referred to as future-oriented tasks, and 2) tasks that could be classified as future-oriented tasks although no specific reference was made. Of these, the most frequently mentioned tasks were measuring periodontal pocket depth, dental hygiene assessment, providing dietary advice, infiltration anesthesia, and root planing. These were extracted from five of the eight studies, including both local and foreign studies. Dental hygiene planning, emergency, emergency management, and smoking cessation were the next most common tasks based on four studies. Even though some of these future-oriented tasks for Korean dental hygienists are included in the dentistry curriculum, and are currently performed as clinical practice for dental hygienists. Nonetheless, the reference to the legal scope is unclear. It is necessary to reconsider the scope of tasks of dental hygienists to reflect changes in domestic and foreign dental care delivery, thereby contributing to the oral health promotion of the public, where safety is guaranteed under legal protection.