• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.165-165
• /
• 2023

Streamflow prediction is a critical task in water resources management and essential for planning and decision-making purposes. However, the streamflow prediction is challenging due to the complexity and non-linear nature of hydrological processes. The transfer learning is a powerful technique that enables a model to transfer knowledge from a source domain to a target domain, improving model performance with limited data in the target domain. In this study, we apply the transfer learning using the Informer model, which is a state-of-the-art deep learning model for streamflow prediction. The model was trained on a large-scale hydrological dataset in the source basin and then fine-tuned using a smaller dataset available in the target basin to predict the streamflow in the target basin. The results demonstrate that transfer learning using the Informer model significantly outperforms the traditional machine learning models and even other deep learning models for streamflow prediction, especially when the target domain has limited data. Moreover, the results indicate the effectiveness of streamflow prediction when knowledge transfer is used to improve the generalizability of hydrologic models in data-sparse regions.

• Journal of Korean Society for Quality Management
• /
• v.36 no.4
• /
• pp.1-6
• /
• 2008

As more and more data are collected one may ask whether the data collected within a short period of time are same. In this case traditional hypothesis testing of $H_o:{\mu}_1={\mu}_2$ vs $H_1:{\mu}_1{\neq}{\mu}_2$ is used to determine whether the data are same when there is no knowledge about equivalence testing. However, this type of hypothesis testing has the undesirable property of penalizing higher precision. So TOST is to be performed in the event of equivalence testing. In this study equivalence testing is introduced where one can find the applications in industry. Traditional two sample t testing is to be compared with the equivalent testing and the procedure to perform the equivalence testing is to be presented along with an example. Finally equivalence testing in terms of the other parameters such as variance, proportion or failure rate is to be sought.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.4
• /
• pp.193-202
• /
• 2017

Development of Intelligent Systems involves effective integration of large-scaled knowledge processing and understanding, human-machine interaction, and intelligent services. Especially, in our project for development of a self-growing knowledge-based system with inference methodologies utilizing the big data technology, we are building a platform called WiseKB as the central knowledge base for storing massive amount of knowledge and enabling question-answering by inferences. WiseKB thus requires an effective methodology to analyze diverse requirements convoluted with the integration of various components of knowledge representation, resource management, knowledge storing, complex hybrid inference, and knowledge learning, In this paper, we propose an integrated requirement analysis method that blends the traditional sequential method and the iterative-incremental method to achieve an efficient requirement analysis for large-scale systems.

• Korean Journal of Remote Sensing
• /
• v.21 no.5
• /
• pp.393-404
• /
• 2005

As multi-source spatial data fusion mainly deal with various types of spatial data which are specific representations of real world with unequal reliability and incomplete knowledge, proper data representation and uncertainty analysis become more important. In relation to this problem, this paper presents and applies an advanced data representation methodology for different types of spatial data such as categorical and continuous data. To account for the uncertainties of both categorical data and continuous data, fuzzy boundary representation and smoothed kernel density estimation within a fuzzy logic framework are adopted, respectively. To investigate the effects of those data representation on final fusion results, a case study for landslide hazard mapping was carried out on multi-source spatial data sets from Jangheung, Korea. The case study results obtained from the proposed schemes were compared with the results obtained by traditional crisp boundary representation and categorized continuous data representation methods. From the case study results, the proposed scheme showed improved prediction rates than traditional methods and different representation setting resulted in the variation of prediction rates.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.8
• /
• pp.3841-3850
• /
• 2012

Objective: The objective of this study was to explore the knowledge and perceptions of Malaysian tradition healers towards cancer and cancer prevention. Methodology: A total of 25 participants agreed to participate in this qualitative study during the period from $20^{th}$ July 2011 until $24^{th}$ of September 2011. The proposal of this study was approved by the Ethics Committee of Management and Science University (MSU). Once the participant agreed to be interviewed, date, time and place of the interviews were determined. Consent form was obtained from participants before the interview began. Participants were briefed about the study and its purpose, and after asking their permissions, their replies were recorded. The data was organized into themes and analyzed manually. Results: Twenty-five Malaysian traditional healers participated in this qualitative study. The age of participants ranged between 26 to 78 years old. The majority were in the age group of 31-60 years old, male, Chinese, degree holders with a monthly income ranging from 1,000-5,000 Ringgit Malaysia (RM) and were married (56%, 80%, 48%, 52%, 68%, 84% respectively). The majority defined cancer as having high cholesterol or abscess accumulation. A few of them defined cancer as a type of cell growth. The majority mentioned that food and unhealthy lifestyles are the primary causes of cancer. Surprisingly some of them mentioned that cancer is caused by interference by ghosts. Regarding the diagnosis of cancer, the majority mentioned that they refer their patients to modern physicians' medical report when it comes to diagnosing or treating patients with cancer. The most common cancers that many patients came to seek treatment were breast cancers, followed by colon cancers, liver and lung cancers. Conclusions: Despite good knowledgeabout the causes of cancer among traditional healers, misconceptions still exist. Insufficient knowledge about the definition of cancer was noted among the traditional healers. This urges immediate action by the Ministry of Health of Malaysia to set up a strict regulation and regular monitoring of the traditional healers nationally. Traditional and Complementary Medicine may be integrated into the healthcare system and need to have sustained cooperation for the benefit of patients since about 80% of patients use traditional medicines.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.10
• /
• pp.3419-3437
• /
• 2022

Anonymization technology is an important technology for privacy protection in the process of data release. Usually, before publishing data, the data publisher needs to use anonymization technology to anonymize the original data, and then publish the anonymized data. However, for data publishers who do not have or have less anonymized technical knowledge background, how to configure appropriate parameters for data with different characteristics has become a more difficult problem. In response to this problem, this paper adds a historical configuration scheme resource pool on the basis of the traditional anonymization process, and configuration parameters can be automatically recommended through the historical configuration scheme resource pool. On this basis, a privacy model hybrid recommendation algorithm for user satisfaction is formed. The algorithm includes a forward recommendation process and a reverse recommendation process, which can respectively perform data anonymization processing for users with different anonymization technical knowledge backgrounds. The privacy model hybrid recommendation algorithm for user satisfaction described in this paper is suitable for a wider population, providing a simpler, more efficient and automated solution for data anonymization, reducing data processing time and improving the quality of anonymized data, which enhances data protection capabilities.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.34 no.7
• /
• pp.1053-1064
• /
• 2010

This study investigates the Korean loungewear market and the traditional culture values of consumers related to loungewear to examine the preference of Korean traditional details, sewing techniques in loungewear design, and purchasing intentions. A survey method was used in this study. A total of 230 self-administered questionnaires were obtained from female consumers and 214 data sets were used for analysis. For the analysis, factor analysis, cluster analysis, and ANOVA were executed with PASW Statistics 18.0 and a structural equation model was estimated by Amos 18.0. The results are as follows. Traditional culture values were classified into two dimensions, traditional succession value and traditional design preference value. In the structure equation model, the traditional design preference value had a significant effect on the preference and the traditional culture succession value had significant effect on purchase intention. The results proved that the preference on loungewear with Korean traditional elements is closely related to purchase intention. Consumer groups were divided into three groups by traditional culture values factor; traditional culture succession group, traditional design preference group, and traditional culture indifference group. Style preference images showed significant differences in relation to traditional culture groups. This study is for use as fundamental knowledge on traditional loungewear brand development and strategy planning by offering specific traditional culture aspects associated with preference and purchase intentions.

• The Journal of Information Systems
• /
• v.18 no.4
• /
• pp.59-86
• /
• 2009

Data modeling can be regarded as a series of processes to abstract real-world business concerns. The conceptual modeling phase is often regarded as the most difficult stage in the entire modeling process, because quite different conceptual models may be produced even for similar business domains based on users' varying requirements and the data modelers' diverse perceptions of the requirements. This implies that an object considered as an entity in one domain may be considered as an attribute in another, and vice versa. However, many traditional knowledge-based automated database design systems unfortunately fail to construct appropriate Entity-Relationship Diagrams(ERDs) for a given set of requirements due to the rigid assumption that an object should be classified as an entity if it has been classified as an entity in previous applications. In this paper, we propose an alternative automation system which can generate ERDs from business descriptions using association rule mining technique. Our system can be differentiated from the traditional ones in that our system can perform data modeling only based on business description written by domain workers, rather than relying on any kind of knowledge base. Since the proposed system can produce various versions of ERDs from the same business descriptions simultaneously, users can have the opportunity to choose one of the ERDs as being the most appropriate, based on their business environment and requirements. We performed a case study for personnel management in a university to evaluate the practicability of the proposed system This paper summarizes the result of it in the experiment section.

• Korean Journal of Oriental Medicine
• /
• v.17 no.3
• /
• pp.69-76
• /
• 2011

Objectives : Our study aims to help users take the medicinal materials in a desirable manner by providing toxic and contraindicating information, based on the ontology of medicinal materials in traditional Korean medicine (TKM). Methods : The toxic and contraindicating data are extracted for 160 medicinal materials from 67 books published in Korea and China. The extracted data are linked to the medicinal material in the ontology, respectively. Results : We in this paper construct an ontology for toxic and contraindicating data of medicinal materials in traditional Korean medicine (TKM), extending our conventional ontology. Based on the ontology, we devised a web-based searching tool that enables users to share the toxic and contraindicating information of medicinal materials. Conclusions : The contents in our ontology are facts based on the books, while the addition of clinical knowledge may elaborate the ontology. Moreover, the addition of easy explanations for terminologies in our ontology is required to help users which are not familiar to TKM.

• Journal of Korean Medical classics
• /
• v.22 no.4
• /
• pp.15-28
• /
• 2009

Traditional korean medicine which has long history and many clinical experiments stands out in bold relief because the medicine's point of view has been changed from medical treatment to disease protection and the wellbeing life through health care and complementary alternative medicine has been emerged for the incurable disease. Many traditional korean medical research has been conducted in the fields of preventive medical application, leading material drawing and medical service upgrade through eastern and western medical treatment and the more advanced project are being studied as time goes by. But because we have the hardship of manifesting traditional korean medicine's knowledge into detailed data and information in the field of analytical science and we don't have well arranged research trend data of it, researchers are using much time to survey the preceding research and planners needing more accurate research trend data to protect duplication and raise efficiency. So we have studied the traditional korean medicine's research trend to solve this problems by the method of bibliography applied for the preceding project results. Through the analysis of traditional korean medicine's 370 project reports we came to a conclusion that the R&D investment is concentrated on the university and research institute, the utilization projects are lower than basic and applied research, regional snobbism is excessive than the whole nation's R&D and advanced project has been started since 2006.