• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.1555-1558
• /
• 2012

제품 라인 공학의 핵심은 여러 제품 개발에 쉽게 재사용 될 수 있는 핵심 자산의 개발과 산출된 핵심자산을 이용하여 원하는 제품을 생산함에 있다. 그렇기 때문에 제품 라인 공학에서 원하는 제품 모델을 적기에 생산해내도록 도와주기 위하여, 제품 라인 모델의 자산으로부터 제품 모델을 추출해주는 도구를 필요로하게 된다. 사용자가 필요로하는 제품 라인 산출물의 추출을 도와주기 위해서는 제품 라인 모델로 산출될 수 있는 모든 모델을 고려할 필요가 있다. 하지만 모든 제품 라인 모델로부터 제품 모델을 추출하는 모듈을 개별적으로 구현하는 것은 비생산적이다. 따라서 본 연구에서는 사용자 맞춤형 제품 모델 추출 도구의 구현을 위해, 오픈 소스인 StarUML을 이용하여 제품 모델 추출 기법의 일반화를 제안한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.832-854
• /
• 2019

Action recognition has been studied in computer vision field for years. We present an effective approach to recognize actions using a dimension reduction method, which is applied as a crucial step to reduce the dimensionality of feature descriptors after extracting features. We propose to use sparse matrix and randomized kd-tree to modify it and then propose modified Local Fisher Discriminant Analysis (mLFDA) method which greatly reduces the required memory and accelerate the standard Local Fisher Discriminant Analysis. For feature encoding, we propose a useful encoding method called mix encoding which combines Fisher vector encoding and locality-constrained linear coding to get the final video representations. In order to add more meaningful features to the process of action recognition, the convolutional neural network is utilized and combined with mix encoding to produce the deep network feature. Experimental results show that our algorithm is a competitive method on KTH dataset, HMDB51 dataset and UCF101 dataset when combining all these methods.

• Proceedings of the PSK Conference
• /
• 2003.10b
• /
• pp.221.1-221.1
• /
• 2003

Armeniacae Semen is a seed of Prunus armeniaca Linne var. ansu Maximowicz, which belongs to Rosaceae family. It contains amygdalin and fatty oil and is widely used to treat asthma, dysponea and edema. It was reported that D-amygdalin in Armeniacae Semen undergoes hydrolytic reaction by emulsin when using water, and esecially it is almost decomposed when extracting from powder type. we set up a condition where we can achieve the maximun extraction yield through the study of the methods to rstrain emulsin from causing hydrolysis of D-amygdalin in Armeniacae Semen in the aqueous solution and to prevent D-amygdalin from being converted into neoamygdalin. (omitted)

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.4
• /
• pp.1553-1567
• /
• 2021

Steganography is a current hot research topic in the area of information security and privacy protection. However, most previous steganography methods are not effective against steganalysis and attacks because they are usually carried out by modifying covers. In this paper, we propose an improved coverless text steganography algorithm based on pretreatment and Part of Speech (POS), in which, Chinese character components are used as the locating marks, then the POS is used to hide the number of keywords, the retrieval of stego-texts is optimized by pretreatment finally. The experiment is verified that our algorithm performs well in terms of embedding capacity, the embedding success rate, and extracting accuracy, with appropriate lengths of locating marks and the large scale of the text database.

• The Journal of Information Systems
• /
• v.30 no.2
• /
• pp.57-78
• /
• 2021

Purpose In this study, first, we try to make embedding results that reflect the characteristics of both professional and general documents. In addition, when disparate documents are put together as learning materials for natural language processing, we try to propose a method that can measure the degree of reflection of the characteristics of individual domains in a quantitative way. Approach For this study, the Korean Supreme Court Precedent documents and Korean Wikipedia are selected as specialized documents and general documents respectively. After extracting the most similar word pairs and similarities of unique words observed only in the specialized documents, we observed how those values were changed in the process of embedding with general documents. Findings According to the measurement methods proposed in this study, it was confirmed that the degree of specificity of specialized documents was relaxed in the process of combining with general documents, and that the degree of dissolution could have a positive correlation with the size of general documents.

• Molecules and Cells
• /
• v.46 no.2
• /
• pp.74-85
• /
• 2023

Single-cell research has provided a breakthrough in biology to understand heterogeneous cell groups, such as tissues and organs, in development and disease. Molecular barcoding and subsequent sequencing technology insert a single-cell barcode into isolated single cells, allowing separation cell by cell. Given that multimodal information from a cell defines precise cellular states, recent technical advances in methods focus on simultaneously extracting multimodal data recorded in different biological materials (DNA, RNA, protein, etc.). This review summarizes recently developed single-cell multiomics approaches regarding genome, epigenome, and protein profiles with the transcriptome. In particular, we focus on how to anchor or tag molecules from a cell, improve throughputs with sample multiplexing, and record lineages, and we further discuss the future developments of the technology.

• International conference on construction engineering and project management
• /
• 2015.10a
• /
• pp.486-490
• /
• 2015

SWOT model was used to develop strategies for the Korean construction firms in entering the global construction market. Literature review, official statistics survey and other research methods were utilized in order to extract internal and external environmental factors of both the firm and local area. By extracting strength, weakness, opportunity and threat factors, a total of 12 strategies were produced: SO (Strengths-Opportunities), ST (Strengths-Threats), WT (Weaknesses-Threats), and WO (Weaknesses-Opportunities). The result of the study can be utilized as a basic data in developing a strategy for the Korean construction firms to penetrate into the global construction market.

• Journal of Practical Engineering Education
• /
• v.15 no.2
• /
• pp.419-427
• /
• 2023

In this study, optimal adhesion conditions to alleviate defects caused by heat shrinkage with FDM type 3D printers with machine learning are researched. Machine learning is one of the "statistical methods of extracting the law from data" and can be classified as supervised learning, unsupervised learning and reinforcement learning. Among them, a function model for adhesion between the bed and the output is presented using supervised learning specialized for optimization, which can be expected to reduce output defects with FDM type 3D printers by deriving conditions for optimum adhesion between the bed and the output. Machine learning codes prepared using Python generate a function model that predicts the effect of operating variables on adhesion using data obtained through adhesion testing. The adhesion prediction data and verification data have been shown to be very consistent, and the potential of this method is explained by conclusions.

• Journal of Information Science Theory and Practice
• /
• v.11 no.4
• /
• pp.14-39
• /
• 2023

Cybercrime is a significant threat to Internet users, involving crimes committed using computers or computer networks. The landscape of cyberspace presents a complex terrain, making the task of tracing the origins of sensitive data a formidable and often elusive endeavor. However, tracing the source of sensitive data in online cyberspace is critically challenging, and detecting cyber-criminals on the other hand remains a time-consuming process, especially in social networks. Cyber-criminals target individuals for financial gain or to cause harm to their assets, resulting in the loss or theft of millions of user data over the past few decades. Forensic professionals play a vital role in conducting successful investigations and acquiring legally acceptable evidence admissible in court proceedings using modern techniques. This study aims to provide an overview of forensic investigation methods for extracting digital evidence from computer systems and mobile devices to combat persistent cybercrime. It also discusses current cybercrime issues and mitigation procedures.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.5
• /
• pp.225-231
• /
• 2023

With the recent surge in the autonomous driving market, the significance of lane detection technology has escalated. Lane detection plays a pivotal role in autonomous driving systems by identifying lanes to ensure safe vehicle operation. Traditional lane detection models rely on engineers manually extracting lane features from predefined environments. However, real-world road conditions present diverse challenges, hampering the engineers' ability to extract adaptable lane features, resulting in limited performance. Consequently, recent research has focused on developing deep learning based lane detection models to extract lane features directly from data. In this paper, we classify lane detection models into four categories: cluster-based, curve-based, information propagation-based, and anchor-based methods. We conduct an extensive analysis of the strengths and weaknesses of each approach, evaluate the model's performance on an embedded board, and assess their practicality and effectiveness. Based on our findings, we propose future research directions and potential enhancements.