• 한국정보과학회논문지:소프트웨어및응용
• /
• 제30권3_4호
• /
• pp.259-267
• /
• 2003

단순 베이지언 분류모형은 구현이 간단하고 효율적이기 때문에 실용적으로 사용하기에 적합하다. 그러나 이 분류모형은 많은 기계학습 도메인에서 우수한 성능을 보임에도 불구하고 문서분류에 적용되었을 경우에는 그 성능이 매우 낮은 것으로 알려져왔다. 본 논문에서는 단순 베이지언 분류모형중 가장 성능이 우수한 것으로 알려진 다항 시행접근 단순 베이지언 분류모형을 개선하는 세가지 방법을 제안한다. 첫 번째는 범주에 대한 단어의 확률추정방법을 문서모델에 기반하여 개선하는 것이고, 두 번째는 문서의 길이에 따라 범주와의 관련성이 선형적으로 증가하는 것을 억제하기 위해 길이에 대한 정규화를 수행하는 것이며, 마지막으로 범주판정에 중요한 역할을 하는 단어들의 영향력을 높여주기 위하여 상호정보가중 단순 베이지언 분류방법을 사용하는 것이다. 제안하는 방법들은 문서분류기의 성능 평가를 위한 벤치마크 문서집합인 Reuters21578과 20Newsgroup에서 기존의 방범에 비해 상당한 성능향상을 가져옴을 알 수 있었다.

• Journal of Multimedia Information System
• /
• 제6권4호
• /
• pp.165-172
• /
• 2019

Machine-learning techniques have been actively employed to information security in recent years. Traditional rule-based security solutions are vulnerable to advanced attacks due to unpredictable behaviors and unknown vulnerabilities. By employing ML techniques, we are able to develop intrusion detection systems (IDS) based on anomaly detection instead of misuse detection. Moreover, threshold issues in anomaly detection can also be resolved through machine-learning. There are very few datasets for network intrusion detection compared to datasets for malicious code. KDD CUP 99 (KDD) is the most widely used dataset for the evaluation of IDS. Numerous studies on ML-based IDS have been using KDD or the upgraded versions of KDD. In this work, we develop an IDS model using CSE-CIC-IDS 2018, a dataset containing the most up-to-date common network attacks. We employ deep-learning techniques and develop a convolutional neural network (CNN) model for CSE-CIC-IDS 2018. We then evaluate its performance comparing with a recurrent neural network (RNN) model. Our experimental results show that the performance of our CNN model is higher than that of the RNN model when applied to CSE-CIC-IDS 2018 dataset. Furthermore, we suggest a way of improving the performance of our model.

• 한국건축시공학회지
• /
• 제4권2호
• /
• pp.105-112
• /
• 2004

The objective of this study is to observe today's situation and direction in relation with the natural air-conditioning and heating system to expand the architectural utilization of natural management for human comfort and energy conservation in architectural design. Also this study to provide the fundamental knowledge and. design-techniques on environment-friendly architecture in connection with 'natural idea in architecture'. In accordance with this intention, this thesis is composed of the following contents : 1) to understand the fundermental concepts about natural air-conditioning and heating system, 2) to review the traditional characteristics in Korean and Southeast Asian architecture related to natural air-conditioning and heating system, 3) to examine modern design-techniques in relation with natural air-conditioning and heating system in the selected area, 4) to attempt to synthesize the whole situation. Environment-friendly architecture using natural ideas and design-techniques in architecture is very important architectural aspect in a current architecture, also for the future. In spite of general considerations, it is expected that this study is use to understand the principle and practical application of natural air-conditioning and heating system in architectural design.

• 한국멀티미디어학회논문지
• /
• 제23권2호
• /
• pp.376-382
• /
• 2020

In the 1970s and 1980s, space installations in films became a new approach to film research. Many film directors and theoretical scholars believe that the space setting in films, other than textual stories, is an important core of film narrative research. Early film scholars have proposed that the film space with sensory narrative mode as the core motive force can promote people's in-depth understanding of the film content. Therefore, many researchers have tried to emphasize the importance of space in films through Hitchcock's films, but have not analyzed the elements and techniques of film space performance in detail. Reviewing the Hitchcock's classic crime film, through the space set in the traditional film, we can discover the movie techniques and concepts related to space. Therefore, this study takes Hitchcock's classic crime film as an example, and through analysis of film space expression techniques, attempts to propose factors for film space creation and bring new spatial perception effects to the audience.

• Journal of Pharmaceutical Investigation
• /
• 제39권4호
• /
• pp.275-297
• /
• 2009

Herbal medicines have been used worldwide, particularly in the Far East countries, for thousands of years. Herbal medicines comprise complex mixtures of different phytochemical substances, and their nature may vary substantially depending on many factors related to the cultivation condition, area and harvest time. The processing of the herbal medicines significantly affects their pharmacological and toxicological properties. In this paper, we discuss current research that deals with the techniques for processing Chinese herbal medicines. These results will provide a scientific basis for developing new techniques for the processing of herbal medicines.

• 복식문화연구
• /
• 제28권5호
• /
• pp.607-620
• /
• 2020

The aim of this study is to define the new expressive techniques for multicolored clamp resist (hyuphill) dyeing, based on empirical verification on relics that are estimated to be dyed by the exchange of more than two wood blocks: a previously undiscovered technique. Clamp resist dyeing (assumed to be made by exchanging wood blocks) have uneven resist printing lines or cloudy gradation. These are reproduced as follows: first, they have uneven contour lines, particularly with the color blue. It is possible to exchange wood blocks separately on patterns with uneven resist printing lines, and it has been verified that the exchange of wood blocks makes these irregular resist printing lines. It has also been verified that exchanging the wood blocks according to the gradation (to emphasize the cubic effect on the patterns) yields clamp resist dyeing with no resist printing lines but with cloudy gradations that have accented borders. This study provides basic information that enables methods of multicolored clamp resist dyeing through wood block exchange to be deduced (something that has not been attempted for a long time). Thus, the revival of the modern Korean dyeing culture based on the conservation and perseverance of the traditional dyeing techniques can be achieved.

• Journal of Information Processing Systems
• /
• 제13권6호
• /
• pp.1496-1515
• /
• 2017

One of the most visible developments in Decision Support Systems (DSS) was the emergence of rule-based expert systems. Hence, despite their success in many sectors, developers of Medical Rule-Based Systems have met several critical problems. Firstly, the rules are related to a clearly stated subject. Secondly, a rule-based system can only learn by updating of its rule-base, since it requires explicit knowledge of the used domain. Solutions to these problems have been sought through improved techniques and tools, improved development paradigms, knowledge modeling languages and ontology, as well as advanced reasoning techniques such as case-based reasoning (CBR) which is well suited to provide decision support in the healthcare setting. However, using CBR reveals some drawbacks, mainly in its interrelated tasks: the retrieval and the adaptation. For the retrieval task, a major drawback raises when several similar cases are found and consequently several solutions. Hence, a choice for the best solution must be done. To overcome these limitations, numerous useful works related to the retrieval task were conducted with simple and convenient procedures or by combining CBR with other techniques. Through this paper, we provide a combining approach using the multi-criteria analysis (MCA) to help, the traditional retrieval task of CBR, in choosing the best solution. Afterwards, we integrate this approach in a decision model to support medical decision. We present, also, some preliminary results and suggestions to extend our approach.

• 대한원격탐사학회지
• /
• 제20권5호
• /
• pp.315-327
• /
• 2004

Nowadays, interests in land cover classification using not only multi-sensor images but also thematic GIS information are increasing. Often, although useful GIS information for the classification is available, the traditional MLE (maximum likelihood estimation techniques) does not allow us to use the information, due to the fact that it cannot handle the GIS data properly. This paper propose two extended MLE algorithms that can integrate both remote sensing images and GIS thematic data for land-cover classification. They include modified MLE and Bayesian predictive likelihood estimation technique (BPLE) techniques that can handle both categorical GIS thematic data and remote sensing images in an integrated manner. The proposed algorithms were evaluated through supervised land-cover classification with Landsat ETM+ images and an existing land-use map in the Gongju area, Korea. As a result, the proposed method showed considerable improvements in classification accuracy, when compared with other multi-spectral classification techniques. The integration of remote sensing images and the land-use map showed that overall accuracy indicated an improvement in classification accuracy of 10.8% when using MLE, and 9.6% for the BPLE. The case study also showed that the proposed algorithms enable the extraction of the area with land-cover change. In conclusion, land cover classification results produced through the integration of various GIS spatial data and multi-spectral images, will be useful to involve complementary data to make more accurate decisions.

• Journal of Multimedia Information System
• /
• 제8권2호
• /
• pp.101-110
• /
• 2021

In computer vision, single-image super resolution has been an area of research for a significant period. Traditional techniques involve interpolation-based methods such as Nearest-neighbor, Bilinear, and Bicubic for image restoration. Although implementations of convolutional neural networks have provided outstanding results in recent years, efficiency and single model multi-scalability have been its challenges. Furthermore, previous works haven't placed enough emphasis on real-number scalability. Interpolation-based techniques, however, have no limit in terms of scalability as they are able to upscale images to any desired size. In this paper, we propose a convolutional neural network possessing the advantages of the interpolation-based techniques, which is also efficient, deeming it suitable in practical implementations. It consists of convolutional layers applied on the low-resolution space, post-up-sampling along the end hidden layers, and additional layers on high-resolution space. Up-sampling is applied on a multiple channeled feature map via bicubic interpolation using a single model. Experiments on architectural structure, layer reduction, and real-number scale training are executed with results proving efficient amongst multi-scale learning (including scale multi-path-learning) based models.

• 유통과학연구
• /
• 제20권4호
• /
• pp.33-50
• /
• 2022

Purpose: This pilot study aims to conceptualize a new green marketing mix for retail consumers based on Stimulus-Organism-Response (SOR) model. Moreover, it also aims to conceptualize a testable research model of new green marketing mix with consumers' green purchasing behavior, and to validate the measurement model with traditional as well as modern suggested validating techniques. Research design, data and methodology: A pilot test data from 75 respondents of retail buyers of energy-efficient electric appliances in Pakistan were tested for the confirmatory factor analysis (CFA) by examining a measurement model of the construct through different validation techniques (like Composite Reliability, McDonald's Omega (ω), rho (ρA), HTMT, etc.) as heretofore these scales were not validated through these modern methods. Results: The results revealed that the instrument has a certain degree of reliability and validity through different validating techniques. All the measurement items reach the suggested threshold values. Conclusions: Therefore, this study conceptualized an integrated framework of all the three stakeholders of the environment (government, companies, and public or consumers) to achieve environmental sustainability. Hence, future studies can extend these findings and conduct a full-scale study to establish an empirical relationship between the 5G's of green marketing for retailing businesses and consumers' green purchase behavior.