• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.8
• /
• pp.243-252
• /
• 2023

Satellite imageries are at a greatest importance for land cover examining. Numerous studies have been conducted with satellite images and uses semantic segmentation techniques to extract information which has higher altitude viewpoint. The device which is taking these images must employee wireless communication links to send them to receiving ground stations. Wireless communications from a satellite are inevitably affected due to transmission errors. Evidently images which are being transmitted are distorted because of the information loss. Current semantic segmentation techniques are not made for segmenting distorted images. Traditional image enhancement methods have their own limitations when they are used for satellite images enhancement. This paper proposes an auto-encoder based image pre-enhancing method for satellite images. As a distorted satellite images dataset, images received from a real radio transmitter were used. Training process of the proposed auto-encoder was done by letting it learn to produce a proper approximation of the source image which was sent by the image transmitter. Unlike traditional image enhancing methods, the proposed method was able to provide more applicable image to a segmentation model. Results showed that by using the proposed pre-enhancing technique, segmentation results have been greatly improved. Enhancements made to the aerial images are contributed the correct assessment of land resources.

• Journal of Creative Information Culture
• /
• v.5 no.3
• /
• pp.245-253
• /
• 2019

To evaluate the achievements of the Solar School Project that has been implemented in twelve African countries since 2013, a case study was implemented in Kenya and in Uganda to investigate networking activities, student accessibility to computers, the frequency of student computer use, the extent to which teaching quality was improved by the enhanced accessibility to ICT-based teaching and learning practices. The results showed the followings. First, Solar Schools have significantly improved the rates of enrollment, transferring, and school attendance. Second, Solar Schools have organized local and invitational training programs to build the capacities of teachers. Third, Solar Schools have facilitated change in neighboring schools and local communities. Fourth, the participants are required to have a clear vision, take ownership of the project, and make a commitment to continuing their individual efforts toward empowerment.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1769-1776
• /
• 2022

Automatically summarizing long sentences is an important technique. The BART model is one of the widely used models in the summarization task. In general, in order to generate a summarization model of a specific domain, fine-tuning is performed by re-training a language model trained on a large dataset to fit the domain. The fine-tuning is usually done by changing the number of nodes in the last fully connected layer. However, in this paper, we propose a fine-tuning method by adding an attention layer, which has been recently applied to various models and shows good performance. In order to evaluate the performance of the proposed method, various experiments were conducted, such as accumulating layers deeper, fine-tuning without skip connections during the fine tuning process, and so on. As a result, the BART model using two attention layers with skip connection shows the best score.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.6
• /
• pp.1-7
• /
• 2023

This paper developed a training model to classify normal roads and flooded roads using artificial intelligence technology. We expanded the diversity of learning data using various data augmentation techniques and implemented a model that shows good performance in various environments. Transfer learning was performed using the CNN-based Resnet152v2 model as a pre-learning model. During the model learning process, the performance of the final model was improved through various parameter tuning and optimization processes. Learning was implemented in Python using Google Colab NVIDIA Tesla T4 GPU, and the test results showed that flooding situations were detected with very high accuracy in the test dataset.

• Journal of the Health Care and Life Science
• /
• v.10 no.2
• /
• pp.169-178
• /
• 2022

The purpose of this study was to examine the level of awareness of the importance of work ability and their final school contribution and the difference between them among health care workers', and to explore the direction of the health care training curriculum by analyzing using IPA. As for the analysis data, the response data of a total of 465 health care workers among the original data of the 14th (2020) Youth Panel Survey were used. As a result of the analyzing using IPA, concentrate here area was none, and the keep up the good work area was specialized knowledge, practical knowledge in the field of expertise, communication, ability to cooperate with others, customer response capability, ability to learn for oneself, deliberate lifestyle, ability to adapt to change, good job perspective and business manners, understanding documents. Low priority area was computer literacy, ability to creative problem solving, reading and writing in a foreign language, solving math problems, foreign language conversation, and the possible overkill area was creating a document. Based on the these results, implications for effective curriculum development to cultivate health care workers were suggested.

• Journal of Practical Engineering Education
• /
• v.16 no.4
• /
• pp.499-512
• /
• 2024

In this study, we diagnosed the results and achievements of pilot operation of high-skilled meister course in degree-linked work-study in parallel, which has been carried out, and suggested of direction for improvement and desirable implementation. In the achievement diagnosis, the results of training served by the university operating this course, the performance and recognition of expert activities after graduation, the self-efficacy in the degree of strengthening one's capabilities as a corporate field teacher, and the self-efficacy for the degree of strengthening the company's human capabilities, and the government performance was diagnosed. Based on the analysis, various operational improvement directions were derived to revitalize high-skilled meister courses in degree-linked work-study in parallel. This study increased the reliability of the study by diagnosing and examining the empirical performance of the entire Advanced Meister Course pilot project through actual performance aggregate data and graduates who participated in the project. It also provides a theoretical basis for policy decisions by verifying implications and desirable directions for improvement through expert advice.

• Journal of Korean Academy of Nursing Administration
• /
• v.1 no.1
• /
• pp.97-111
• /
• 1995

In our society today, a variety of medical caring system, along with a scientific development in the area of oriental medical science plus national demand, has increased the augmentation and the opening of oriental wards and hospitals (Han Bang), which has come to create an additional requirement of nursing activity at oriental medicine wards should be different from that of the general wards or the same as the other. In view of this, various studies need to be made in this connection. The purpose of this study is to comprehend the number of nurses who want to work at oriental medicine wards and measure job satisfaction in nursing as compared with those working at general wards so as to provide basic materials for future assignment and supplementary training for the nurses. An attempt was made to contribute toward nursing administration on the one hand improving nursing training course on the other hand. A total of 72 nurses currently working at two oriental medicine hospitals available in Seoul and 82 general nurses were selected for this study using the questionaire from December 1993 to January 1994. An instrument for the study was based on the measurement of work satisfaction developed by Paula L. Stamps including 37 questions complemented by Kim for revision (1993) and 14 questions regarding general characteristics and oriental medicine wards. The instrument to test dependability showed Cronbach's=0.7711. The collected data have been processed by computer package SPSS. General characteristics of the two groups and the matters involved in oriental medicine wards were calculated into real figure and percentage an similarities between the two groups were analyzed by t-test and F-test according to the characteristics of variables. The comparative test on work satisfaction among the two groups including general characteristics and work factors were conducted by t-test and F-test. The major findings as a result of the study are as follows : 1. As general characteristics, age group of $26{\sim}30$ years are more than any segment of age. As to marital status, the number of those in single status is slightly higher than the married. Approximately 80% of them are graduates of nursing schools and nursing colleges. They are mostly in service for one to three years. There is no significant difference between the two groups. 2. The number of those who want to work at oriental medicine wards represents 40.3% against 58.4%, being in favor of general wards. 3. The reason for service at oriental medicine wards is that "there is room for potential research" which happened to rank first, followed by "easy job," "good working atmosphere" and "growing interest in oriental medicine." 4. Work satisfactions among nurses who work at oriental medicine wards prove greater than that of nurses who work at general wards. 5. Work satisfaction between the two groups by work factors is reflected with significant difference statistically on task requirement, interaction and doctor-nurse relationships. 6. The general charcateristics and the work satisfaction by work factors prove that there are significant difference in age, marital status, education and the period of work. They tend to be more satisfied with the work as they grow in age. Significant differneces are found in the work factors such as autonomy, adiministration and professional job in the relationship with doctor-nurse. As to marital status, the married are more satisfied than the unmarried. There are significant differneces in the factors respecting administration and doctor-nurse college graduates are highly satisfied with task requirement. However, satisfaction with the professional level has proven the highest degree for those having master degree. The period of work and satisfaction : There are significant differneces in task requirement, administration, interactions, professional level and doctor-nurse relationships. As a general rule, the degree of satisfactions is in proportion to the lengrh of service. The following conclusions are drawn based on the fndings mentioned above. Even though the work satisfaction of the nurse who work at oriental medicine ward is relatively high, it is desired that personal consultation be given as to disposition of nurses when they are assigned to oriental medicine wards. It is also recommended that lectures on oriental medicine be conducted through supplementary training and/or basic nursing course in order that they may be motivated for ingenious activities with an increasing sense of self-esteem which will eventually enhance positive changes for the patients who are in need of oriental medicine nursing and for the medical teams. In addition, joint reseaches involvingclinical care and education should be in constant process for unique and scientific development for those who are subject to oriental medicine nursing care.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.5
• /
• pp.530-536
• /
• 2021

Recently, due to the development of deep learning, end-to-end speech recognition, which directly maps graphemes to speech signals, shows good performance. Especially, among the end-to-end models, conformer shows the best performance. However end-to-end models only focuses on the probability of which grapheme will appear at the time. The decoding process uses a greedy search or beam search. This decoding method is easily affected by the final probability output by the model. In addition, the end-to-end models cannot use external pronunciation and language information due to structual problem. Therefore, in this paper conformer with lexicon transducer is proposed. We compare phoneme-based model with lexicon transducer and grapheme-based model with beam search. Test set is consist of words that do not appear in training data. The grapheme-based conformer with beam search shows 3.8 % of CER. The phoneme-based conformer with lexicon transducer shows 3.4 % of CER.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.3
• /
• pp.9-15
• /
• 2019

Large global online shopping malls, such as Amazon, offer services in English or in the language of a country when their products are sold. Since many customers purchase products based on the product reviews, the shopping malls actively utilize the sentimental analysis technique in judging preference of each product using the large amount of review data that the customer has written. And the result of such analysis can be used for the marketing to look the potential shoppers. However, it is difficult to apply this English-based semantic analysis system to different languages used around the world. In this study, more than 500,000 data from Amazon fine food reviews was used for training a deep learning based system. First, sentiment analysis evaluation experiments were carried out with three models of English test data. Secondly, the same data was translated into seven languages (Korean, Japanese, Chinese, Vietnamese, French, German and English) and then the similar experiments were done. The result suggests that although the accuracy of the sentimental analysis was 2.77% lower than the average of the seven countries (91.59%) compared to the English (94.35%), it is believed that the results of the experiment can be used for practical applications.

• Journal of Korea Water Resources Association
• /
• v.56 no.10
• /
• pp.641-653
• /
• 2023

As climate change and urbanization are causing unprecedented natural disasters in urban areas, it is crucial to have urban flood predictions with high fidelity and accuracy. However, conventional physically- and deep learning-based urban flood modeling methods have limitations that require a lot of computer resources or data for high-resolution flooding analysis. In this study, we propose and implement a method for improving the spatial resolution of urban flood analysis using a deep learning based super-resolution technique. The proposed approach converts low-resolution flood maps by physically based modeling into the high-resolution using a super-resolution deep learning model trained by high-resolution modeling data. When applied to two cases of retrospective flood analysis at part of City of Portland, Oregon, U.S., the results of the 4-m resolution physical simulation were successfully converted into 1-m resolution flood maps through super-resolution. High structural similarity between the super-solution image and the high-resolution original was found. The results show promising image quality loss within an acceptable limit of 22.80 dB (PSNR) and 0.73 (SSIM). The proposed super-resolution method can provide efficient model training with a limited number of flood scenarios, significantly reducing data acquisition efforts and computational costs.