• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.10
• /
• pp.3972-3988
• /
• 2020

Existing methods always rely on statistical features to extract local words for microblog user geolocation. There are many non-local words in extracted words, which makes geolocation accuracy lower. Considering the statistical and semantic features of local words, this paper proposes a microblog user geolocation method by extracting local words based on word clustering and wrapper feature selection. First, ordinary words without positional indications are initially filtered based on statistical features. Second, a word clustering algorithm based on word vectors is proposed. The remaining semantically similar words are clustered together based on the distance of word vectors with semantic meanings. Next, a wrapper feature selection algorithm based on sequential backward subset search is proposed. The cluster subset with the best geolocation effect is selected. Words in selected cluster subset are extracted as local words. Finally, the Naive Bayes classifier is trained based on local words to geolocate the microblog user. The proposed method is validated based on two different types of microblog data - Twitter and Weibo. The results show that the proposed method outperforms existing two typical methods based on statistical features in terms of accuracy, precision, recall, and F1-score.

• The KIPS Transactions:PartB
• /
• v.17B no.4
• /
• pp.309-316
• /
• 2010

This paper introduces a new model based method for facial expression recognition that uses facial grid angles as feature space. In order to be able to recognize the six main facial expression, proposed method uses a grid approach and therefore it establishes a new feature space based on the angles that each gird's edge and vertex form. The way taken in the paper is robust against several affine transformations such as translation, rotation, and scaling which in other approaches are considered very harmful in the overall accuracy of a facial expression recognition algorithm. Also, this paper demonstrates the process that the feature space is created using angles and how a selection process of feature subset within this space is applied with Wrapper approach. Selected features are classified by SVM, 3-NN classifier and classification results are validated with two-tier cross validation. Proposed method shows 94% classification result and feature selection algorithm improves results by up to 10% over the full set of feature.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.415-417
• /
• 2005

레거시 시스템을 컴포넌트화 하기 위해 시스템을 서브 시스템으로 계층화하고, 각각의 서브 시스템을 객체 기반으로 변형한 후, 래퍼(Wrapper)를 이용하여 컴포넌트화 한다. 이런 절차 중 Wrapper컴포넌트를 도출하는 방법 중 UML Component방법론을 사용, 컴포넌트 도출 중 여러 핵심타입(Core Type) 객체가 하나의 객체와 연관관계를 가지고 있는 경우 경험이나 직관을 최소화하여 의존성을 최소할 수 있는 개선된 컴포넌트 도출방법을 제안한다.

• Journal of KIISE:Software and Applications
• /
• v.28 no.10
• /
• pp.785-794
• /
• 2001

Since there is no compatability between primitive types and class types in Java, values of primitive types cannot be assigned to variables of class types cannot be assigned to variables of primitive types. Primitive values must be converted to objects of wrapper classes and special methods must be called in order to extract the primitive values from those objects. In this paper we propose there methods which provide automatic transformation between primitive types and class types for their compatability. Those methods support compatability not only between primitive types but also between wapper classes. The first method utilizes the hierarchy of wrapper classes, the second utilizer java.lang.Number class, and the third utilizes the hierarchy of wrapper interfaces. Through comparison and performance measurement. we confirm that the third method works better than the others.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.12
• /
• pp.5685-5700
• /
• 2018

Cyber intelligence, surveillance, and reconnaissance (ISR) has become more important than traditional military ISR. An agent used in cyber ISR resides in an enemy's networks and continually collects valuable information. Thus, this agent should be able to determine what is, and is not, useful in a short amount of time. Moreover, the agent should maintain a classification rate that is high enough to select useful data from the enemy's network. Traditional feature selection algorithms cannot comply with these requirements. Consequently, in this paper, we propose an effective hybrid feature selection method derived from the filter and wrapper methods. We illustrate the design of the proposed model and the experimental results of the performance comparison between the proposed model and the existing model.

• Journal of the Korea Convergence Society
• /
• v.9 no.7
• /
• pp.1-7
• /
• 2018

Feature selection, one of data preprocessing techniques, is one of major research areas in many applications dealing with large dataset. It has been used in pattern recognition, machine learning and data mining, and is now widely applied in a variety of fields such as text classification, image retrieval, intrusion detection and genome analysis. The proposed method is based on a genetic algorithm which is one of meta-heuristic algorithms. There are two methods of finding feature subsets: a filter method and a wrapper method. In this study, we use a wrapper method, which evaluates feature subsets using a real classifier, to find an optimal feature subset. The training dataset used in the experiment has a severe class imbalance and it is difficult to improve classification performance for rare classes. After preprocessing the training dataset with SMOTE, we select features and evaluate them with various machine learning algorithms.

• Journal of KIISE:Software and Applications
• /
• v.32 no.8
• /
• pp.704-716
• /
• 2005

Assembling new software systems from Prepared components is an attractive alternative to traditional software development method to reduce development cost and schedule dramatically. However, if separately developed components are tested, integrated and verified with unreasonable effort and high cost, it would not be an effective way to software development. Components are not distributed in the shape of white-box source code so that should be hard to validate and test in new application environment. For solving this problem, built-in tester components are suggested to check the contract-compliance of their server components. If components have various and complex function, built-in tester should be heavy and unflexible to test in composition of components. This paper suggests enhancing automated wrapper technique which substitutes with built-in tester components and shows the usability of the wrapper by design and implementation. Component testing in this way reduces the cost and effort associated with preparation of component testing and makes the various test experiments in components assembly.

• Journal of Information Technology Services
• /
• v.19 no.3
• /
• pp.139-149
• /
• 2020

There are now many different commercial weather sensors suitable for smart farms, and various smart farm devices are being developed and distributed by companies participating in the government-led smart farm expansion project. However, most do not comply with standard specifications and are therefore limited to use in smart farms. This paper proposed the connecting structure of operating non-standard node devices in smart farms following standard specifications supporting smart greenhouse. This connecting structure was proposed as both a virtual node module method and a virtual node wrapper method. In addition, the SoftFarm2.0 system was experimentally operated to analyze the performance of the implementation of the two methods. SoftFarm2.0 system complies with the standard specifications and supports non-standard smart farm devices. According to the analysis results, both methods do not significantly affect performance in the operation of the smart farm. Therefore, it would be good to select and implement the method suitable for each non-standard smart farm device considering environmental constraints such as power, space, distance of communication between the gateway and the node of the smart farm, and software openness. This will greatly contribute to the spread of smart farms by maximizing deployment cost savings.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.8 no.5
• /
• pp.384-393
• /
• 2015

This paper proposes an optimized classifier based on feature elimination (OCFE) for gene selection with combining two feature elimination methods, ReliefF and SVM-RFE. ReliefF algorithm is filter feature selection which rank the data by the importance of the data. SVM-RFE algorithm is a wrapper feature selection which wrapped the data and rank the data based on the weight of feature. With combining these two methods we get less error rate average, 0.3016138 for OCFE and 0.3096779 for SVM-RFE. The proposed method also get better accuracy with 70% for OCFE and 69% for SVM-RFE.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.392-392
• /
• 2000

This study performs optimization of paper mill scheduling using MINLP(Mixed-Integer Non-Linear Programming) method and 2-step decomposing strategy. Paper mill process is normally composed of five units: paper machine, coater, rewinder, sheet cutter and roll wrapper/ream wrapper. Various kinds of papers are produced through these units. The bottleneck of this process is how to cut product papers efficiently from raw paper reel and this is called trim loss problem or cutting stock problem. As the trim must be burned or recycled through energy consumption, minimizing quantity of the trim is important. To minimize it, the trim loss problem is mathematically formulated in MINLP form of minimizing cutting patterns and trim as well as satisfying customer's elder. The MINLP form of the problem includes bilinearity causing non-linearity and non-convexity. Bilinearity is eliminated by parameterization of one variable and the MINLP form is decomposed to MILP(Mixed-Integer Linear programming) form. And the MILP problem is optimized by means of the optimization package. Thus trim loss problem is efficiently minimized by this 2-step optimization method.