• Journal of the Korea Society of Computer and Information
• /
• v.3 no.2
• /
• pp.131-138
• /
• 1998

In usual statistical data analysis, we describe statistical data by exact values. However, in modem complex and large-scale systems, it is difficult to treat the systems using only exact data. In this paper, we define these data as fuzzy data(ie. Linguistic variable applied to make the member-ship function.) and Propose a new method to get an analysis of fuzzy survey data based on the maximum entropy Principle. Also, we propose a new method of discrimination by measuring distance between a distribution of the stable state and estimated distribution of the present state using the Kullback - Leibler information. Furthermore, we investigate the validity of our method by computer simulations under realistic situations.

• The KIPS Transactions:PartB
• /
• v.16B no.3
• /
• pp.247-256
• /
• 2009

Typical pseudo-relevance feedback methods assume the top-retrieved documents are relevant and use these pseudo-relevant documents to expand terms. The initial retrieval set can, however, contain a great deal of noise. In this paper, we present a cluster-based resampling method to select better pseudo-relevant documents based on the relevance model. The main idea is to use document clusters to find dominant documents for the initial retrieval set, and to repeatedly feed the documents to emphasize the core topics of a query. Experimental results on large-scale web TREC collections show significant improvements over the relevance model. For justification of the resampling approach, we examine relevance density of feedback documents. The resampling approach shows higher relevance density than the baseline relevance model on all collections, resulting in better retrieval accuracy in pseudo-relevance feedback. This result indicates that the proposed method is effective for pseudo-relevance feedback.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.2
• /
• pp.87-92
• /
• 2024

In this paper, a RAG system was implemented using an existing Large Language Model (LLM) and Langchain library to develop a dental consultation chatbot. For this purpose, we collected contents from the webpage bulletin boards of domestic dental university hospitals and constructed consultation data with the advice and supervision of dental specialists. In order to divide the input consultation data into appropriate sizes, the chunk size and the size of the overlapping text in each chunk were set to 1001 and 100, respectively. As a result of the simulation, the Retrieval Augmented LLM searched for and output the consultation content that was most similar to the user input. It was confirmed that the accessibility of dental consultation and the accuracy of consultation content could be improved through the built chatbot.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.4
• /
• pp.73-79
• /
• 2022

The Python language widely used in artificial intelligence (AI) projects is an interpreter language, and errors occur at runtime. In order to prevent project failure due to errors, it is necessary to handle exceptions in code that can cause exceptional situations in advance. In particular, in AI projects that require a lot of resources, exceptions that occur after long execution lead to a large waste of resources. However, since exception handling depends on the developer's experience, developers have difficulty determining the appropriate exception to catch. To solve this need, we propose an approach that recommends exceptions to catch to developers during development by learning the existing exception handling statements. The proposed method receives the source code of the try block as input and recommends exceptions to be handled in the except block. We evaluate our approach for a large project consisting of two frameworks. According to our evaluation results, the average AUPRC is 0.92 or higher when performing exception recommendation. The study results show that the proposed method can support the developer's exception handling with exception recommendation performance that outperforms the comparative models.

• The KIPS Transactions:PartD
• /
• v.15D no.1
• /
• pp.147-154
• /
• 2008

Along with the trend of internet use, various web application developments have been performed to provide information that was managed in the internal database on the web by making a web server page. However, in most cases, a direct program was made without a systematic developmental methodology or with the application of a huge developmental methodology that is inappropriate and decreased the efficiency of the development. A web application that fails to follow a systematic developmental methodology and uses a script language can decrease the productivity of the program development, maintenance, and reuse. In this thesis, the auto writing tool for a dynamic web server page was designed and established by using a database for web application development based on a fast and effective script. It suggests a regularized script model and makes a standardized script for the data bound control tag creator by analyzing a dynamic web server page pattern with the database in order to contribute to productivity by being used in the web application development and maintenance.

• The KIPS Transactions:PartD
• /
• v.14D no.2
• /
• pp.181-190
• /
• 2007

In component based development, component modeling for understanding and analyzing is the important part and is used to improve reusability. Generally, components are need to be divided into two types according to their usages, where the developer and assembler are usually different. To make a good component model, a complete component and interface specification for those components are needed. And the component model needs to adept two different views of developer and assembler. In this paper, we suggest two different views of component model that is related to views from developer and assembler, and we expand UML. Also we validate the efficiency of the suggested model by developing and applying a tool for building, managing and automatic transformation.

• Journal of Internet of Things and Convergence
• /
• v.9 no.6
• /
• pp.45-50
• /
• 2023

In software development, the elicitation and analysis of requirements is a crucial phase, and it involves considerable time and effort due to the involvement of various stakeholders. ChatGPT, having been trained on a diverse array of documents, is a large language model that possesses not only the ability to generate code and perform debugging but also the capability to be utilized in the domain of software analysis and design. This paper proposes a method of requirements engineering that leverages ChatGPT's capabilities for eliciting software requirements, analyzing them to align with system goals, and documenting them in the form of use cases. In software requirements engineering, it suggests that stakeholders, analysts, and ChatGPT should engage in a collaborative model. The process should involve using the outputs of ChatGPT as initial requirements, which are then reviewed and augmented by analysts and stakeholders. As ChatGPT's capability improves, it is anticipated that the accuracy of requirements elicitation and analysis will increase, leading to time and cost savings in the field of software requirements engineering.

• Journal of KIBIM
• /
• v.13 no.3
• /
• pp.21-29
• /
• 2023

ChatGPT, a chatbot based on GPT large language models, has gained immense popularity among the general public as well as domain professionals. To assess its proficiency in specialized fields, ChatGPT was tested on mainstream exams like the bar exam and medical licensing tests. This study evaluated ChatGPT's ability to answer questions related to Building Information Modeling (BIM) by testing it on Korea's BIM expertise exam, focusing primarily on multiple-choice problems. Both GPT-3.5 and GPT-4 were tested by prompting them to provide the correct answers to three years' worth of exams, totaling 150 questions. The results showed that both versions passed the test with average scores of 68 and 85, respectively. GPT-4 performed particularly well in categories related to 'BIM software' and 'Smart Construction technology'. However, it did not fare well in 'BIM applications'. Both versions were more proficient with short-answer choices than with sentence-length answers. Additionally, GPT-4 struggled with questions related to BIM policies and regulations specific to the Korean industry. Such limitations might be addressed by using tools like LangChain, which allow for feeding domain-specific documents to customize ChatGPT's responses. These advancements are anticipated to enhance ChatGPT's utility as a virtual assistant for BIM education and modeling automation.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.129-164
• /
• 2023

In a situation where the use and introduction of Large Language Models (LLMs) is expanding due to recent developments in generative AI technology, it is difficult to find actual application cases or implementation methods for the use of internal company data in existing studies. Accordingly, this study presents a method of implementing generative AI services using the LLM application architecture using the most widely used LangChain framework. To this end, we reviewed various ways to overcome the problem of lack of information, focusing on the use of LLM, and presented specific solutions. To this end, we analyze methods of fine-tuning or direct use of document information and look in detail at the main steps of information storage and retrieval methods using the retrieval augmented generation (RAG) model to solve these problems. In particular, similar context recommendation and Question-Answering (QA) systems were utilized as a method to store and search information in a vector store using the RAG model. In addition, the specific operation method, major implementation steps and cases, including implementation source and user interface were presented to enhance understanding of generative AI technology. This has meaning and value in enabling LLM to be actively utilized in implementing services within companies.

• Journal of Internet Computing and Services
• /
• v.8 no.3
• /
• pp.75-83
• /
• 2007

Multithreaded model is an effective parallel system in that it can reduce the long memory reference latency time and solve the synchronization problems. When compiling the non-strict functional programs for the multithreaded parallel machine, the most important thing is to find an set of sequentially executable instructions and to partitions them into threads. The existing partitioning algorithm partitions the condition of conditional expression, true expression and false expression into the basic blocks and apply local partitioning to these basic blocks. We can do the better partitioning if we modify the definition of the thread and allow the branching within the thread. The branching within the thread do not reduce the parallelism, do not increase the number of synchronization and do not violate the basic rule of the thread partitioning. On the contrary, it can lengthen the thread and reduce the number of synchronization. In the paper, we enhance the method of the partition of threads by combining the three basic blocks into one of two blocks.