• 디자인학연구
• /
• 제15권2호
• /
• pp.223-232
• /
• 2002

인터넷이 정보획득의 중요한 수단으로써 보편화되면서 인터넷상의 정보를 효율적으로 조직화하고 관리할 수 있는 시스템의 중요성이 점차 커지고 있다. 이에 따라 이용자의 정보검색효율성에 직접적인 영향을 기치는 디렉토리 분류체계에 대한 연구가 각 분야별로 활발히 진행되고 있다. 본 연구에서는 디자인 분야 디렉토리 분류체계에 의한 검색의 효율성을 높이기 위하여 문헌 분류체계에 대한 이론과 현재 서비스되어 지고 있는 디자인 포탈사이트들의 디렉토리 분류체계를 비교 분석하여 효율적인 분류체계 방안을 제안 하고자 한다.

• Asia Marketing Journal
• /
• 제20권1호
• /
• pp.49-68
• /
• 2018

It is appropriate and useful to interpret some product classification schemes as buyer behavior models; such classifications permit investigations of discrepancies between classification predictions and actual buyer behavior. We review existing product classifications and identify underlying behavioral assumptions of various classification schemes that have been used in the marketing discipline for more than nine decades. Recognizing the irrelevance of existing product classifications for current products, we propose a new reclassification framework by incorporating transparency concepts. Based on this extended product classification, we highlight the potential roles of product classification study as an important link between consumer research and marketing strategy, emphasizing behavioral implications.

• Geomechanics and Engineering
• /
• 제37권3호
• /
• pp.263-277
• /
• 2024

Artificial Neural Networks (ANNs) are artificial learning algorithms that provide successful results in solving many machine learning problems such as classification, prediction, object detection, object segmentation, image and video classification. There is an increasing number of studies that use ANNs as a prediction tool in soil classification. The aim of this research was to understand the role of hyperparameter optimization in enhancing the accuracy of ANNs for soil type classification. The research results has shown that the hyperparameter optimization and hyperparamter optimized ANNs can be utilized as an efficient mechanism for increasing the estimation accuracy for this problem. It is observed that the developed hyperparameter tool (HyperNetExplorer) that is utilizing the Covariance Matrix Adaptation Evolution Strategy (CMAES), Genetic Algorithm (GA) and Jaya Algorithm (JA) optimization techniques can be successfully used for the discovery of hyperparameter optimized ANNs, which can accomplish soil classification with 100% accuracy.

• 한국경영과학회지
• /
• 제32권1호
• /
• pp.61-75
• /
• 2007

The purpose of this paper is to develop a new group classification method based on genetic algorithm and to com-pare its prediction performance with those of existing methods in the area of bond rating. To serve this purpose, we conduct various experiments with pilot and general models. Specifically, we first conduct experiments employing two pilot models : the one searching for the cluster center of each group and the other one searching for both the cluster center and the attribute weights in order to maximize classification accuracy. The results from the pilot experiments show that the performance of the latter in terms of classification accuracy ratio is higher than that of the former which provides the rationale of searching for both the cluster center of each group and the attribute weights to improve classification accuracy. With this lesson in mind, we design two generalized models employing genetic algorithm : the one is to maximize the classification accuracy and the other one is to minimize the total misclassification cost. We compare the performance of these two models with those of existing statistical and artificial intelligent models such as MDA, ANN, and Decision Tree, and conclude that the genetic algorithm-based group classification method that we propose in this paper significantly outperforms the other methods in respect of classification accuracy ratio as well as misclassification cost.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권11호
• /
• pp.4246-4267
• /
• 2020

As the network goes deep into all aspects of people's lives, the number and the complexity of network traffic is increasing, and traffic classification becomes more and more important. How to classify them effectively is an important prerequisite for network management and planning, and ensuring network security. With the continuous development of deep learning, more and more traffic classification begins to use it as the main method, which achieves better results than traditional classification methods. In this paper, we provide a comprehensive review of network traffic classification based on deep learning. Firstly, we introduce the research background and progress of network traffic classification. Then, we summarize and compare traffic classification based on deep learning such as stack autoencoder, one-dimensional convolution neural network, two-dimensional convolution neural network, three-dimensional convolution neural network, long short-term memory network and Deep Belief Networks. In addition, we compare traffic classification based on deep learning with other methods such as based on port number, deep packets detection and machine learning. Finally, the future research directions of network traffic classification based on deep learning are prospected.

• International Journal of Railway
• /
• 제2권1호
• /
• pp.37-42
• /
• 2009

Information management of products and services in every industries is gaining importance for resource planning and maintenance. In this paper, we analyzed the information classification systems for railway industry. International and domestic classification systems, such as HS, UNSPSC, eCl@ss and ISIC, are reviewed; as a result this paper presents the findings and the various issues. We proposed to-be images in adopting and utilizing the classification systems. Using the integrative information classification systems could make efficient electronic procurement, supply chain management and e-Business of railway services.

• 한국임상약학회지
• /
• 제15권2호
• /
• pp.139-148
• /
• 2005

Appropriate drug classification is important fur rational drug consumption. This study was conducted to evaluate the appropriateness of current drug classification system and suggest possible ways for improving the system. Nonprescription drug market has been decreased. Since total 27,962 products had been classified (prescription 17,187 vs. nonprescription 10,775 products, 61.5% vs. 38.5%) in July 2000 for implementing separation of drug prescribing and dispensing system, there are no classification changes. Reclassification is not motivated by product holder and regulatory system did not lead classification change either. Consumers' ease access to some nonprescription drugs is demanded. But point of public awareness and cultural and health environmental views, saff drug use rather than advantages from broad supply of nonprescription drugs is more critical. We concluded that current 2-categorized (prescription and nonprescription) drug classification system is appropriate, and addition of general sale category should be approached carefully with long term Preparations such as establishment of better nonprescription drug consuming infrastructure by public information provision and education for improving public medicinal knowledge and strengthening self medication guidance, and review of current classification status of marketed drugs and switching possibilities. For systemizing and encouraging reclassification, introduction of regulatory renewal system as a continuous reevaluation program which is the best way to review appropriateness of drug classification as well as provision of detailed guidance for industry including policy, requirement and process fer reclassification application, are necessary.

• 한국산업보건학회지
• /
• 제22권2호
• /
• pp.140-148
• /
• 2012

Objectives: This study was performed to provide harmonized guidelines on health and environmental classification criteria and its results of chemicals in Korea. Methods: Firstly, The history of GHS implementation in UN and Korea was reviewed. Secondly, the differences in classification criteria on health and environmental hazards among UN GHS and two Korean government agencies, Korea Ministry of Employment and Labour (KMoEL) and Korea Ministry of Environmental (KMoE). The classification results were compared between classifications of Korea Occupational Safety and Health Agency (KOSHA) based on KMoEL and classifications of Korea National Institute of Environmental Research (KNIER) based on KMoE. Finally, an inter-agency harmonization on the classification criteria and the results was suggested by comparing the classification results of 5 chemicals; Benzene, carbon disulfide, formaldehyde, toluene-2,4-diisocyanate, and trichloroethylene. Results: KMoEL and KMoE revised regulations on chemical management and published a Notices on GHS classification criteria according to UN GHS document. However, the hazard to the ozone layer contained in the latest edition of UN GHS document published in 2011 was not included yet. The differences in classifications of 5 chemicals between KOSHA and KNIER were 36.2% in health hazards and 23.4% in environmental hazards, respectively. In conclusion, we suggested that a new revision be needed to include newly contained hazard and inter-agency working party be organized to harmonize classification results.

• 대한원격탐사학회지
• /
• 제23권6호
• /
• pp.521-528
• /
• 2007

본 논문에서는 대상지역에 대한 영상을 다양한 가중치의 조합의 경우를 고려하여 객체 단위로 분할하게 되며 분할된 객체에 대하여 상호관계를 분석하여 수치적으로 표현하였다. 또한 최종적인 객체 기반영상분류에서 높은 정확도를 확보할 수 있는 가중치의 조합을 산정하였다. 연구에 사용된 영상은 Landsat-7/ETM 영상으로 대상 지역의 면적은 $11{\times}14$ Km이며 밴드 2, 3, 4의 조합을 사용하였다. 객체 간 계산은 Moran's I와 객체 내부 분산(Intrasegment Variance)을 이용하였다. 대상지역에 대하여 총 75개의 가중치 조합을 사용하여 75개의 객체 분할 영상을 생성하였다. 객체 분할 영상 중에 최종적인 영상 분류 시 높은 정확도가 예상되는 가중치 조합, 중간 정도 정확도가 예상되는 가중치 조합 그리고 낮은 정도 정확도가 예상되는 가중치 조합을 7개 선택하여 최종적인 객체기반 영상분류를 시행하고 그 정확도를 비교하였다. 정확도의 비교 결과, 가장 높은 정확도가 예상되는 가중치 조합의 객체 분할 영상의 경우 객체 기반 영상 분류 시 85% 이상의 정확도를 나타내었으며 반대로 낮은 경우는 분류 시 50% 정도의 분류 정확도를 나타내었다.

• International Journal of Computer Science & Network Security
• /
• 제24권2호
• /
• pp.79-88
• /
• 2024

The use of the social media has become part of our daily life activities. The social web channels provide the content generation facility to its users who can share their views, opinions and experiences towards certain topics. The researchers are using the social media content for various research areas. Sentiment analysis, one of the most active research areas in last decade, is the process to extract reviews, opinions and sentiments of people. Sentiment analysis is applied in diverse sub-areas such as subjectivity analysis, polarity detection, and emotion detection. Stance classification has emerged as a new and interesting research area as it aims to determine whether the content writer is in favor, against or neutral towards the target topic or issue. Stance classification is significant as it has many research applications like rumor stance classifications, stance classification towards public forums, claim stance classification, neural attention stance classification, online debate stance classification, dialogic properties stance classification etc. This research study explores different feature sets such as lexical, sentiment-specific, dialog-based which have been extracted using the standard datasets in the relevant area. Supervised learning approaches of generative algorithms such as Naïve Bayes and discriminative machine learning algorithms such as Support Vector Machine, Naïve Bayes, Decision Tree and k-Nearest Neighbor have been applied and then ensemble-based algorithms like Random Forest and AdaBoost have been applied. The empirical based results have been evaluated using the standard performance measures of Accuracy, Precision, Recall, and F-measures.