• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.3
• /
• pp.87-94
• /
• 2024

We investigated the feasibility of utilizing Large Language Models (LLMs) to perform text-based games without training on game data in advance. We adopted ChatGPT-3.5 and its state-of-the-art, ChatGPT-4, as the systems that implemented LLM. In addition, we added the persistent memory feature proposed in this paper to ChatGPT-4 to create three game player agents. We used Zork, one of the most famous text-based games, to see if the agents could navigate through complex locations, gather information, and solve puzzles. The results showed that the agent with persistent memory had the widest range of exploration and the best score among the three agents. However, all three agents were limited in solving puzzles, indicating that LLM is vulnerable to problems that require multi-level reasoning. Nevertheless, the proposed agent was still able to visit 37.3% of the total locations and collect all the items in the locations it visited, demonstrating the potential of LLM.

• Journal of Hospice and Palliative Care
• /
• v.27 no.1
• /
• pp.1-10
• /
• 2024

This article underscores the importance of integrating comprehensive palliative care for noncancer patients who are undergoing hemodialysis, with an emphasis on the aging populations in Asian nations such as Taiwan, Japan, the Republic of Korea, and China. As the global demographic landscape shifts towards an aging society and healthcare continues to advance, a marked increase has been observed in patients undergoing hemodialysis who require palliative care. This necessitates an immediate paradigm shift to incorporate this care, addressing the intricate physical, psychosocial, and spiritual challenges faced by these individuals and their families. Numerous challenges impede the provision of effective palliative care, including difficulties in prognosis, delayed referrals, cultural misconceptions, lack of clinician confidence, and insufficient collaboration among healthcare professionals. The article proposes potential solutions, such as targeted training for clinicians, the use of telemedicine to facilitate shared decision-making, and the introduction of time-limited trials for dialysis to overcome these obstacles. The integration of palliative care into routine renal treatment and the promotion of transparent communication among healthcare professionals represent key strategies to enhance the quality of life and end-of-life care for people on hemodialysis. By embracing innovative strategies and fostering collaboration, healthcare providers can deliver more patient-centered, holistic care that meets the complex needs of seriously ill patients within an aging population undergoing hemodialysis.

• Korean Journal of Clinical Laboratory Science
• /
• v.56 no.1
• /
• pp.89-98
• /
• 2024

Gross examination techniques (GETs) of specimens collected from cancer surgery or endoscopy comprise the act of recording visual information about cancer for accurate histopathological diagnosis and collecting sections of the lesion to create microscopic specimens. GETs must include concise and accurate expressions, appropriate structuring, sufficient resections, error-free standardization of important information, and photo-diagramming of complex specimens. To increase the satisfaction of pathological interpretation, it is a task that must be performed accurately and carefully to gain confidence on a theoretical and practical basis with a sufficient understanding of gross examination. Based on the experience of clinical pathologists in the field of GETs, additional specimen types should be identified as viable candidates. Also, their needs and concerns regarding treatment should be carefully considered. In addition, departments at each institution should review the national focus on clinical partnerships, continuous professional training, diagnostic errors, and value-based healthcare provision.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.1
• /
• pp.143-156
• /
• 2024

Federated Learning (FL) has emerged as a potent methodology for decentralized model training across multiple collaborators, eliminating the need for data sharing. Although FL is lauded for its capacity to preserve data privacy, it is not impervious to various types of privacy attacks. Differential Privacy (DP), recognized as the golden standard in privacy-preservation techniques, is widely employed to counteract these vulnerabilities. This paper makes a specific contribution by applying an existing, task-specific adaptive DP mechanism to the FL environment. Our comprehensive analysis evaluates the impact of this mechanism on the performance of a shared global model, with particular attention to varying data distribution and partitioning schemes. This study deepens the understanding of the complex interplay between privacy and utility in FL, providing a validated methodology for securing data without compromising performance.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.44 no.3
• /
• pp.397-405
• /
• 2024

In order to improve the visibility of nighttime thermal infrared images, a simulation method with daytime color images was proposed. As a simulation method consisting of two steps, the daytime thermal infrared image was simulated by learning the unpaired nighttime thermal infrared image and daytime thermal infrared image, then the result was translated into a daytime color image. A temperature change regression equation was constructed and applied to reflect the systematic characteristics of temperature changes in daytime and nighttime images, and day and night simulation and colorization were trained and modeled by CycleGAN. For the experimental area, 100 images were captured and used for training. As a result, the simulation showed an average SSIM of 0.2449 and a PSNR of 51.2254. It was confirmed that the method could simulate complex and detailed features such as vegetation.

• Computers and Concrete
• /
• v.34 no.2
• /
• pp.247-265
• /
• 2024

Measuring the fracture toughness of concrete in laboratory settings is challenging due to various factors, such as complex sample preparation procedures, the requirement for precise instruments, potential sample failure, and the brittleness of the samples. Therefore, there is an urgent need to develop innovative and more effective tools to overcome these limitations. Supervised learning methods offer promising solutions. This study introduces seven machine learning algorithms for predicting concrete's effective fracture toughness (K-eff). The models were trained using 560 datasets obtained from the central straight notched Brazilian disc (CSNBD) test. The concrete samples used in the experiments contained micro silica and powdered stone, which are commonly used additives in the construction industry. The study considered six input parameters that affect concrete's K-eff, including concrete type, sample diameter, sample thickness, crack length, force, and angle of initial crack. All the algorithms demonstrated high accuracy on both the training and testing datasets, with R² values ranging from 0.9456 to 0.9999 and root mean squared error (RMSE) values ranging from 0.000004 to 0.009287. After evaluating their performance, the gated recurrent unit (GRU) algorithm showed the highest predictive accuracy. The ranking of the applied models, from highest to lowest performance in predicting the K-eff of concrete, was as follows: GRU, LSTM, RNN, SFL, ELM, LSSVM, and GEP. In conclusion, it is recommended to use supervised learning models, specifically GRU, for precise estimation of concrete's K-eff. This approach allows engineers to save significant time and costs associated with the CSNBD test. This research contributes to the field by introducing a reliable tool for accurately predicting the K-eff of concrete, enabling efficient decision-making in various engineering applications.

• Journal of Intelligence and Information Systems
• /
• v.20 no.3
• /
• pp.77-92
• /
• 2014

Recently, numerous documents including unstructured data and text have been created due to the rapid increase in the usage of social media and the Internet. Each document is usually provided with a specific category for the convenience of the users. In the past, the categorization was performed manually. However, in the case of manual categorization, not only can the accuracy of the categorization be not guaranteed but the categorization also requires a large amount of time and huge costs. Many studies have been conducted towards the automatic creation of categories to solve the limitations of manual categorization. Unfortunately, most of these methods cannot be applied to categorizing complex documents with multiple topics because the methods work by assuming that one document can be categorized into one category only. In order to overcome this limitation, some studies have attempted to categorize each document into multiple categories. However, they are also limited in that their learning process involves training using a multi-categorized document set. These methods therefore cannot be applied to multi-categorization of most documents unless multi-categorized training sets are provided. To overcome the limitation of the requirement of a multi-categorized training set by traditional multi-categorization algorithms, we propose a new methodology that can extend a category of a single-categorized document to multiple categorizes by analyzing relationships among categories, topics, and documents. First, we attempt to find the relationship between documents and topics by using the result of topic analysis for single-categorized documents. Second, we construct a correspondence table between topics and categories by investigating the relationship between them. Finally, we calculate the matching scores for each document to multiple categories. The results imply that a document can be classified into a certain category if and only if the matching score is higher than the predefined threshold. For example, we can classify a certain document into three categories that have larger matching scores than the predefined threshold. The main contribution of our study is that our methodology can improve the applicability of traditional multi-category classifiers by generating multi-categorized documents from single-categorized documents. Additionally, we propose a module for verifying the accuracy of the proposed methodology. For performance evaluation, we performed intensive experiments with news articles. News articles are clearly categorized based on the theme, whereas the use of vulgar language and slang is smaller than other usual text document. We collected news articles from July 2012 to June 2013. The articles exhibit large variations in terms of the number of types of categories. This is because readers have different levels of interest in each category. Additionally, the result is also attributed to the differences in the frequency of the events in each category. In order to minimize the distortion of the result from the number of articles in different categories, we extracted 3,000 articles equally from each of the eight categories. Therefore, the total number of articles used in our experiments was 24,000. The eight categories were "IT Science," "Economy," "Society," "Life and Culture," "World," "Sports," "Entertainment," and "Politics." By using the news articles that we collected, we calculated the document/category correspondence scores by utilizing topic/category and document/topics correspondence scores. The document/category correspondence score can be said to indicate the degree of correspondence of each document to a certain category. As a result, we could present two additional categories for each of the 23,089 documents. Precision, recall, and F-score were revealed to be 0.605, 0.629, and 0.617 respectively when only the top 1 predicted category was evaluated, whereas they were revealed to be 0.838, 0.290, and 0.431 when the top 1 - 3 predicted categories were considered. It was very interesting to find a large variation between the scores of the eight categories on precision, recall, and F-score.

• Journal of Arbitration Studies
• /
• v.12 no.1
• /
• pp.271-321
• /
• 2002

Every year, many million of business transactions take place. Ocassionally, disagreements develop over these business transactions. Many of these disputes are resolved by mediation, arbitration and out-of-court settlement options. The American Arbitration Association(AAA) helps resolve a wide range of disputes through mediation, arbitration, elections and other out-of-court settlement procedures. The AAA offers a broad range of dispute resolution services to business executives, attorneys, individuals, trade associations, unions, management, consumers, families, communities, and all level of governments. The 198,491 cases composed of the 194,303 arbitration cases and the 4,188 mediation cases, were filed with the AAA in 2000. These case filings represent a full range of matters, including commercial finance, construction, labor and employment, environmental, health care, insurance, real state, securities, and technology disputes. The Korean Commercial Arbitration Board (KCAB) does more than render arbitration services. It helps facilitate settlements and guarantee implementation thereof between trading partners at home and abroad involving disputes related to such areas as the sale of commodities, construction, joint venture agreements, technical assistance, agency agreements, and maritime transport. The 643 cases composed of the the 197 arbitration cases and the 446 mediation cases, were filed with the KCAB in 2001. There are some differences between the AAA and the KCAB regarding the number and the area of mediation and arbitration case filings, the breath of service offerings, the scope of alternative dispute resolution, and the education and training. In order to apply to the proceedings of the commercial mediation and arbitration, the AAA has the Commercial Mediation Rules, the Commercial Arbitration Rules, the Expedited Procedures, the Optional Procedures for Large, Complex Commerical Dispute, and the Optional Rules for Emergency Measures of Protection as amended and effective on September 1, 2000. In order to apply to the proceedings of commercial arbitration, the KCAB has the Arbitration Rules as amended by the Supreme Court on April 27, 2000, which have been changed to incorporate the revisions of the Arbitration Act that went into effect on December 31, 1999. There are some differences between the AAA's commercial Arbitration Rules and the KCAB's Arbitration Rules regarding the clauses of jurisdiction and administrative conference, number of arbitrators, communication with arbitrator, vacancies, preliminary hearing, exchange of information, oaths, evidence by affidavit and posthearing filing of documents or others, interim measures, serving of notice, form of award, scope of award, delivery of award to parties, modification of award, release of liability, administrative fees, neutral arbitrator's compensation, and expedited procedures. In conclusion, for the vitalization of KCAB and its ADR system, the following measures should be taken : the effective case management, the development of on0-line ADR, the establishment of ADR system of electronic commerce disputes, and the variety of dispute resolution rules in each expert field.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.2
• /
• pp.244-251
• /
• 2007

Intention reading technique is essential to provide personalized services toward more convenient and human-friendly services in complex ubiquitous environment such as a smart home. If a system has knowledge about an user's intention of his/her behavioral pattern, the system can provide mote qualified and satisfactory services automatically in advance to the user's explicit command. In this sense, learning capability is considered as a key function for the intention reading technique in view of knowledge discovery. In this paper, ore introduce a personalized media control method for a possible application iii a smart home. Note that data pattern such as human behavior contains lots of inconsistent data due to limitation of feature extraction and insufficiently available features, where separable data groups are intermingled with inseparable data groups. To deal with such a data pattern, we introduce an effective engineering approach with the combination of fuzzy logic and probabilistic reasoning. The proposed learning system, which is based on IFCS (Iterative Fuzzy Clustering with Supervision) algorithm, extract probabilistic fuzzy rules effectively from the given numerical training data pattern. Furthermore, an extended architectural design methodology of the learning system incorporating with the IFCS algorithm are introduced. Finally, experimental results of the media contents recommendation system are given to show the effectiveness of the proposed system.

• Journal of Advanced Marine Engineering and Technology
• /
• v.39 no.6
• /
• pp.626-632
• /
• 2015

The International Maritime Organization (IMO) has adopted several regulations for the prevention of air pollution from ships. In addition, there is a requirement for shipping liners to reduce greenhouse gas emissions. Accordingly, we need to take measurements to ensure that the steps taken are both efficient and environmentally friendly. It has been determined that the application of the Miller cycle in diesel engines has the effect of both reducing the amount of NOx and improving thermal efficiency. However, this method requires a considerably larger charge air pressure. Therefore, we consider a two-stage turbo-charging system, which not only results in a high charging pressure, but also improves the part load performance with an exhaust-gas bypass system or the application of the Miller cycle. Because of complications associated with the two-stage turbo-charging system, it is complex and difficult to realize a design that optimizes matching between diesel engine and turbo-chargers. Accordingly, it is necessary to perform a quantitative analysis to determine the effects and optimal conditions of these different systems in the early stage of system design. In this paper, we develop a simulation program to model these systems, and we verify that the results of this program are reliable. Further, we discuss methods that can be employed to improve its efficiency.