• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.6
• /
• pp.852-859
• /
• 2009

Normally, to extract the defect in TFT-LCD inspection system, the image is obtained by using line scan camera or area scan camera which is achieved by CCD or CMOS sensor. Because of the limited dynamic range of CCD or CMOS sensor as well as the effect of the illumination, these images are frequently degraded and the important features are hard to decern by a human viewer. In order to overcome this problem, the feature vectors in the image are obtained by using the average intensity difference between defect and background based on the weber's law and the standard deviation of the background region. The defect detection method uses non-linear SVM (Supports Vector Machine) method using the extracted feature vectors. The experiment results show that the proposed method yields better performance of defect classification methods over conveniently method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.2
• /
• pp.212-217
• /
• 2009

There are rule-based learning method and statistic based learning method and so on which represent learning method for hierarchy relation between domain term. In this paper, we propose to leveling and similarity measure using the extended AHP of fuzzy term in Information system. In the proposed method, we extract fuzzy term in document and categorize ontology structure about it and level priority of fuzzy term using the extended AHP for specificity of fuzzy term. the extended AHP integrates multiple decision-maker for weighted value and relative importance of fuzzy term. and compute semantic similarity of fuzzy term using min operation of fuzzy set, dice's coefficient and Min+dice's coefficient method. and determine final alternative fuzzy term. after that compare with three similarity measure. we can see the fact that the proposed method is more definite than classification performance of the conventional methods and will apply in Natural language processing field.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.2
• /
• pp.191-196
• /
• 2009

In this paper, we proposed a feature selection method using Binary Particle Swarm Optimization(BPSO) and Mutual information. This proposed method consists of the feature selection part for selecting candidate feature subset by mutual information and the optimal feature selection part for choosing optimal feature subset by BPSO in the candidate feature subsets. In the candidate feature selection part, we computed the mutual information of all features, respectively and selected a candidate feature subset by the ranking of mutual information. In the optimal feature selection part, optimal feature subset can be found by BPSO in the candidate feature subset. In the BPSO process, we used multi-object function to optimize both accuracy of classifier and selected feature subset size. DNA expression dataset are used for estimating the performance of the proposed method. Experimental results show that this method can achieve better performance for pattern recognition problems than conventional ones.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.6
• /
• pp.586-591
• /
• 2014

In this study, we introduce Radial Basis Function Neural Networks(RBFNNs) classifier using Artificial Bee Colony(ABC) algorithm in order to classify between precipitation event and non-precipitation event from given radar data. Input information data is rebuilt up through feature analysis of meteorological radar data used in Korea Meteorological Administration. In the condition phase of the proposed classifier, the values of fitness are obtained by using Fuzzy C-Mean clustering method, and the coefficients of polynomial function used in the conclusion phase are estimated by least square method. In the aggregation phase, the final output is obtained by using fuzzy inference method. The performance results of the proposed classifier are compared and analyzed by considering both QC(Quality control) data and CZ(corrected reflectivity) data being used in Korea Meteorological Administration.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.2
• /
• pp.172-177
• /
• 2013

With Brain Computer Interface (BCI) system, a person with disabled limb could use this direct brain signal like electroencephalography (EEG) to control a device such as the artifact arm. The precise force control for the artifact arm is necessary for this artificial limb system. To understand the relationship between control EEG signal and the gripping force of hands, We proposed a study by measuring EEG changes of three grades (25%, 50%, 75%) of hand grip MVC (Maximal Voluntary Contract). The acquired EEG signal was filtered to obtain power of three wave bands (alpha, beta, gamma) by using fast fourier transformation (FFT) and computed power spectrum. Then the power spectrum of three bands (alpha, beta and gamma) of three classes (MVC 25%, 50%, 75%) was classified by using PCA (Principal Component Analysis) and LDA (Linear Discriminant Analysis). The result showed that the power spectrum of EEG is increased at MVC 75% more than MVC 25%, and the correct classification rate was 52.03% for left hand and 77.7% for right hand.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.13 no.2
• /
• pp.1-11
• /
• 2014

In this paper, travel speed patterns were deducted based on historical DSRC travel speed data using Decision Tree technique to improve availability of the massive amount of historical data. These patterns were designed to reflect spatio-temporal vicissitudes in reality by generating pattern units classified by months, time of day, and highway sections. The study area was from Seoul TG to Ansung IC sections on Gyung-bu highway where high peak time of day frequently occurs in South Korea. Decision Tree technique was applied to categorize travel speed according to day of week. As a result, five different pattern groups were generated: (Mon)(Tue Wed Thu)(Fri)(Sat)(Sun). Statistical verification was conducted to prove the validity of patterns on nine different highway sections, and the accuracy of fitting was found to be 93%. To reduce travel pattern errors against individual travel speed data, inclusion of four additional variables were also tested. Among those variables, 'traffic condition on previous month' variable improved the pattern grouping accuracy by reducing 50% of speed variance in the decision tree model developed.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.6
• /
• pp.1-15
• /
• 2017

Recently terrorism targets unspecified masses and causes massive destruction, which is so-called Super Terrorism. Many countries have tried hard to protect their citizens with various preparation and safety net. With inexpensive and advanced technologies of sensors, the surveillance systems have been paid attention, but few studies associated with the classification of the pedestrians' trajectories and the difference among themselves have attempted. Therefore, we collected individual trajectories at Samseoung Station using an analytical solution (system) of pedestrian trajectory by LiDAR sensor. Based on the collected trajectory data, a comprehensive framework of classifying the types of pedestrians' trajectories has been developed with data normalization and "trajectory association rule-based algorithm." As a result, trajectories with low similarity within the very same cluster is possibly detected.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.6
• /
• pp.761-766
• /
• 2011

A hedge is a linguistic device to express uncertainties. Hedges are used in a sentence when the writer is uncertain or has doubt about the contents of the sentence. Due to this uncertainty, sentences with hedges are considered to be non-factual. There are many applications which need to determine whether a sentence is factual or not. Detecting hedges has the advantage in information retrieval, and information extraction, and QnA systems, which make use of non-hedge sentences as target to get more accurate results. In this paper, we constructed Korean hedge corpus, and extracted generalized hedge cue-word patterns from the corpus, and then used them in detecting hedges. In our experiments, we achieved 78.6% in F1-measure.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.3
• /
• pp.294-299
• /
• 2012

This paper suggests a modeling technique for shape and volume prediction of fishes to cut them with identical weights for group meals. The measurement and prediction of frozen fishes for group meals are very difficult because they have a bending deformation occurring at frozen stage and a hollow by eliminating the internals. Besides there exist twinkles problem of surface caused by freeze and variable weights by moisture conditions. Therefore a complex estimation algorithm is necessary to predict the shape and volume prediction of fishes exactly. Hollow prediction, pattern classification and modeling for tails using neural network, integration based volume prediction algorithm are suggested and combined to solve those problems. In order to validate the proposed method, the experiments of 3-dimensional measurement, volume prediction and fish cutting for spanish mackerel, saury, and mackerel are executed. The cutting experiments for real fish are executed.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2005.05a
• /
• pp.266-273
• /
• 2005

Data mining techniques enable us to generate useful information for decision support from the data sources which are generated and accumulated in the process of routine organizational management activities. College administration system is a typical example that produces a warehouse of student records as each and every student enters a college and undertakes the curricular and extracurricular activities. So far, these data have been utilized to a very limited student service purposes, such as issuance of transcripts, graduation evaluation, GPA calculation, etc. In this paper, we utilize Holland career search test results, TOEIC score, course work list, and GPA score as the input for data mining and generation the student advisory information. Factor analysis, AHP(Analytic Hierarchy Process), artificial neural net, and CART(Classification And Regression Tree) techniques are deployed in the data mining process. Since these data mining techniques are very powerful in processing and discovering useful knowledge and information from large scale student databases, we can expect a highly sophisticated student advisory knowledge and services which may not be obtained with the human student advice experts.