• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.24 no.2
• /
• pp.431-434
• /
• 2014

This paper shows the users' birthplace information can be inferred with only the public information in FaceBook SNS. Through experiments with various machine learning algorithms and various parameters, we have found that SVM algorithm with the location of the highschool, the current address, and the graduate year of highschool performs best for the inference, as this can infer 78% of users' birthplaces correctly. Since the birthplace information is used for various security purpose such as questions for getting the forgotten password and a part of korean residence registration number, this is a non-trival security breach and users need be cautious about it.

• Journal of KIISE
• /
• v.43 no.10
• /
• pp.1085-1093
• /
• 2016

Community-based Question Answering system is a system which provides answers for each question from the documents uploaded on web communities. In order to enhance the capacity of question analysis, former methods have developed specific rules suitable for a target region or have applied machine learning to partial processes. However, these methods incur an excessive cost for expanding fields or lead to cases in which system is overfitted for a specific field. This paper proposes a multiple machine learning method which automates the overall process by adapting appropriate machine learning in each procedure for efficient processing of community-based Question Answering system. This system can be divided into question analysis part and answer selection part. The question analysis part consists of the question focus extractor, which analyzes the focused phrases in questions and uses conditional random fields, and the question type classifier, which classifies topics of questions and uses support vector machine. In the answer selection part, the we trains weights that are used by the similarity estimation models through an artificial neural network. Also these are a number of cases in which the results of morphological analysis are not reliable for the data uploaded on web communities. Therefore, we suggest a method that minimizes the impact of morphological analysis by using character features in the stage of question analysis. The proposed system outperforms the former system by showing a Mean Average Precision criteria of 0.765 and R-Precision criteria of 0.872.

• The Journal of the Korea Contents Association
• /
• v.8 no.10
• /
• pp.11-19
• /
• 2008

In this paper, we propose a prediction method of lung cancer susceptibility using an importance evaluation of SNP data and the SVM learning, a gene data concerning getting sick with the lung cancer. Since the number of negative data is much larger that of positive data, which are to be used in the SVM learning, for each positive data, a negative data is first searched which has the same sex and the minimum age difference with the positive data. The searched negative data is then coupled with the positive data. For the importance evaluation of each SNP data, an equation which calculates the influence of each SNP data on the prediction of getting sick is adopted. The SNP data are sorted according to the evaluated importance. In experiments, we observed the prediction accuracy which varies according to the number of sorted SNP data used in the learning. LOOCV test results showed that the proposed method yields the prediction accuracy of maximum 65.0% for test data.

• Journal of KIISE:Software and Applications
• /
• v.36 no.8
• /
• pp.642-652
• /
• 2009

In order to improve the performance of the existing relation extraction approaches, we propose a method for combining two pivotal concepts which play an important role in classifying semantic relationships between entities in text. Having built a composite kernel-based relation extraction system, which incorporates both entity features and syntactic structured information of relation instances, we define nine classes of lexical features and synthetically apply them to the system. Evaluation on the ACE RDC corpus shows that our approach boosts the effectiveness of the existing composite kernels in relation extraction. It also confirms that by integrating the three important features (entity features, syntactic structures and contextual lexical features), we can improve the performance of a relation extraction process.

• Journal of KIISE:Software and Applications
• /
• v.36 no.6
• /
• pp.491-497
• /
• 2009

This paper proposes a new feature weighting method for document sentiment classification. The proposed method considers the difference of sentiment intensities among sentences in a document. Sentiment features consist of sentiment vocabulary words and the sentiment intensity scores of them are estimated by the chi-square statistics. Sentiment intensity of each sentence can be measured by using the obtained chi-square statistics value of each sentiment feature. The calculated intensity values of each sentence are finally applied to the TF-IDF weighting method for whole features in the document. In this paper, we evaluate the proposed method using support vector machine. Our experimental results show that the proposed method performs about 2.0% better than the baseline which doesn't consider the sentiment intensity of a sentence.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.915-916
• /
• 2014

With the upcoming era of internet of things, the study of sensor network has been paid attention. Raspberry pi is a tiny versatile computer system which is able to act as a sensor node in hadoop cluster network. In this paper, we deployed 5 Raspberry pi's to construct an experimental testbed of hadoop sensor network with 5-node map-reduce hadoop software framework. We compared and analyzed the network architecture in terms of efficiency, resource management, and throughput using various parameters. We used a learning machine with support vector machine as test workload. In our experiments, Raspberry pi fulfilled the role of distributed computing sensor node in the sensor network.

• Journal of the Korean Society for information Management
• /
• v.24 no.1 s.63
• /
• pp.251-271
• /
• 2007

This paper studies the problem of classifying documents with labeled and unlabeled learning data, especially with regards to using document similarity features. The problem of using unlabeled data is practically important because in many information systems obtaining training labels is expensive, while large quantities of unlabeled documents are readily available. There are two steps In general semi-supervised learning algorithm. First, it trains a classifier using the available labeled documents, and classifies the unlabeled documents. Then, it trains a new classifier using all the training documents which were labeled either manually or automatically. We suggested two types of semi-supervised learning algorithm with regards to using document similarity features. The one is one step semi-supervised learning which is using unlabeled documents only to generate document similarity features. And the other is two step semi-supervised learning which is using unlabeled documents as learning examples as well as similarity features. Experimental results, obtained using support vector machines and naive Bayes classifier, show that we can get improved performance with small labeled and large unlabeled documents then the performance of supervised learning which uses labeled-only data. When considering the efficiency of a classifier system, the one step semi-supervised learning algorithm which is suggested in this study could be a good solution for improving classification performance with unlabeled documents.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2015.07a
• /
• pp.310-311
• /
• 2015

Ships' tracking data are being monitored and collected by vessel traffic service center in real time. In this paper, we intend to contribute to vessel traffic service operators' decision making through extracting ships' tracking patterns and models based on these data. Support Vector Machine algorithm was used for vessel track modeling to handle and process the data sets and k-fold cross validation was used to select the proper parameters. Proposed data processing methods could support vessel traffic service operators' decision making on case of anomaly detection, calculation ships' dead reckoning positions and etc.

• The KIPS Transactions:PartB
• /
• v.17B no.1
• /
• pp.85-92
• /
• 2010

A shallow semantic parsing system analyzes the relationship that a syntactic constituent of the sentence has with a predicate. It identifies semantic arguments representing agent, patient, instrument, etc. of the predicate. In this study, we propose a two-phase shallow semantic parsing model which consists of the identification phase and the classification phase. We first find the boundary of semantic arguments from partial syntactic parsing results, and then assign appropriate semantic roles to the identified semantic arguments. By taking the sequential two-phase approach, we can alleviate the unbalanced class distribution problem, and select the features appropriate for each task. Experiments show the relative contribution of each phase on the test data.

• Journal of KIISE:Software and Applications
• /
• v.35 no.11
• /
• pp.681-691
• /
• 2008

In this paper, we have evaluated and compared each feature and feature combinations necessary for statistical Korean dialogue act classification. We have implemented a Korean dialogue act classification system by using the Support Vector Machine method. The experimental results show that the POS bigram does not work well and the morpheme-POS pair and other features can be complementary to each other. In addition, a small number of features, which are selected by a feature selection technique such as chi-square, are enough to show steady performance of dialogue act classification. We also found that the last eojeol plays an important role in classifying an entire sentence, and that Korean characteristics such as free order and frequent subject ellipsis can affect the performance of dialogue act classification.