• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.7
• /
• pp.1588-1593
• /
• 2005

In coagulant control of water treatment plants, rule extraction, one of datamining categories, was performed for coagulant control of a water treatment plant. Clustering methods were applied to extract control rules from data. These control rules can be used for fully automation of water treatment plants instead of operator's knowledge for plant control. To perform fuzzy clustering, there are some coefficients to be determined and these kinds of studies have been performed over decades such as clustering indices. In this study, statistical indices were taken to calculate the number of clusters. Simultaneously, seed points were found out based on hierarchical clustering. These statistical approaches give information about features of clusters, so it can reduce computing cost and increase accuracy of clustering. The proposed algorithm can play an important role in datamining and knowledge discovery.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.466-467
• /
• 2018

Recently, artificial intelligence has been applied to various fields such as image recognition, image recognition speech recognition, and natural language processing, and interest in Deep Learning technology is increasing. Many researches on Convolutional Neural Network(CNN), which is one of the most representative algorithms among Deep Learning, have strong advantages in image recognition and classification and are widely used in various fields. In this paper, we propose a new network structure that transforms the general CNN structure. A typical CNN structure consists of a convolution layer, ReLU layer, and a pooling layer. Therefore in this paper, We intend to construct a new network by adding fully connected layer inside a general CNN structure. This modification is intended to increase the learning and accuracy of the convoluted image by including the generalization which is an advantage of the neural network.

• Journal of KIISE:Software and Applications
• /
• v.37 no.11
• /
• pp.803-811
• /
• 2010

Since protein subcellular location and biological function are highly correlated, the prediction of protein subcellular localization can provide information about the function of a protein. In order to enhance the prediction performance, external information other than amino acids sequence information is actively exploited in many researches. This paper compares the prediction capabilities resided in amino acid sequence similarity, protein profile, gene ontology, motif, and textual information. In the experiments using PLOC dataset which has proteins less than 80% sequence similarity, sequence similarity information and gene ontology are effective information, achieving a classification accuracy of 94.8%. In the experiments using BaCelLo IDS dataset with low sequence similarity less than 30%, using gene ontology gives the best prediction accuracies, 93.2% for animals and 86.6% for fungi.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.4
• /
• pp.201-208
• /
• 2015

This paper proposes a method for detecting the direction indicator shown in the road surface efficiently from the black box system installed on the vehicle. In the proposed method, the direction indicators are detected by inverse perspective mapping(IPM) and bag of visual features(BOF)-based NN classifier. In order to apply the proposed method to real-time environments, the candidated regions of direction indicator in an image only performs IPM, and BOF-based NN is used for the classification of feature information from direction indicators. The results of applying the proposed method to the road surface direction indicators detection and recognition, the detection accuracy was presented at least about 89%, and the method presents a relatively high detection rate in the various road conditions. Thus it can be seen that the proposed method is applied to safe driving support systems available.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.9
• /
• pp.345-350
• /
• 2018

This study is an algorithm for detecting vein pattern features important for finger vein recognition. The feature detection algorithm is important because it greatly affects recognition results in pattern recognition. The recognition rate is degraded because the reference is changed according to the finger position change. In addition, the image obtained by irradiating the finger with infrared light is difficult to separate the image background and the blood vessel pattern, and the detection time is increased because the image preprocessing process is performed. For this purpose, the presented algorithm can be performed without image preprocessing, and the detection time can be reduced. SWDA (Down Slope Trace Waveform) algorithm is applied to the finger vein images to detect the fingertip position and vein pattern. Because of the low infrared transmittance, relatively dark vein images can be detected with minimal detection error. In addition, the fingertip position can be used as a reference in the classification stage to compensate the decrease in the recognition rate. If we apply algorithms proposed to various recognition fields such as palm and wrist, it is expected that it will contribute to improvement of biometric feature detection accuracy and reduction of recognition performance time.

• Journal of Convergence for Information Technology
• /
• v.8 no.1
• /
• pp.201-206
• /
• 2018

Recently, as technologies for realizing artificial intelligence have become more common, machine learning is widely used. Machine learning provides insight into collecting large amounts of data, batch processing, and taking final action, but the effects of the work are not immediately integrated into the learning process. In this paper proposed an adaptive learning model to improve the performance of real-time stream analysis as a big business issue. Adaptive learning generates the ensemble by adapting to the complexity of the data set, and the algorithm uses the data needed to determine the optimal data point to sample. In an experiment for six standard data sets, the adaptive learning model outperformed the simple machine learning model for classification at the learning time and accuracy. In particular, the support vector machine showed excellent performance at the end of all ensembles. Adaptive learning is expected to be applicable to a wide range of problems that need to be adaptively updated in the inference of changes in various parameters over time.

• Journal of Convergence for Information Technology
• /
• v.8 no.5
• /
• pp.131-135
• /
• 2018

The heart disease taking the second place of the cause of the death of modern people is a terrible disease that makes sudden death without noticing. To judge the aortic valve disease of heart diseases a name of disease was diagnosed using psychological data provided from physioNet. Aortic valve is a valve of the area that blood is spilled from left ventricle to aorta. Aortic stenosis of heart troubles is a disease when the valve does not open appropriately in contracting the left ventricle to aorta due to narrowed aortic valve. In this paper, 3126 samples of cardiac sound data were used as an experiment data composed of 180 characteristics including normal people and aortic valve stenosis patients. To diagnose normal and aortic valve stenosis patients, NEWFM was utilized. By using an average method of weight as an feature selection method of NEWFM, the result shows 91.0871% accuracy.

• Journal of the Korean Wood Science and Technology
• /
• v.45 no.6
• /
• pp.797-808
• /
• 2017

Automatic wood species identification systems have enabled fast and accurate identification of wood species outside of specialized laboratories with well-trained experts on wood species identification. Conventional automatic wood species identification systems consist of two major parts: a feature extractor and a classifier. Feature extractors require hand-engineering to obtain optimal features to quantify the content of an image. A Convolutional Neural Network (CNN), which is one of the Deep Learning methods, trained for wood species can extract intrinsic feature representations and classify them correctly. It usually outperforms classifiers built on top of extracted features with a hand-tuning process. We developed an automatic wood species identification system utilizing CNN models such as LeNet, MiniVGGNet, and their variants. A smartphone camera was used for obtaining macroscopic images of rough sawn surfaces from cross sections of woods. Five Korean softwood species (cedar, cypress, Korean pine, Korean red pine, and larch) were under classification by the CNN models. The highest and most stable CNN model was LeNet3 that is two additional layers added to the original LeNet architecture. The accuracy of species identification by LeNet3 architecture for the five Korean softwood species was 99.3%. The result showed the automatic wood species identification system is sufficiently fast and accurate as well as small to be deployed to a mobile device such as a smartphone.

• The Journal of Information Systems
• /
• v.29 no.3
• /
• pp.145-157
• /
• 2020

Purpose This study proposed an approach for predicting the efficiency rating of the cultural tourism festivals using DEA and machine learning techniques. The cultural tourism festivals are selected for the best festivals through peer reviews by tourism experts. However, only 10% of the festivals which are held in a year could be evaluated in the view of effectiveness without considering the efficiency of festivals. Design/methodology/approach Efficiency scores were derived from the results of DEA for the prediction of efficiency ratings. This study utilized BCC models to reflect the size effect of festivals and classified the festivals into four ratings according the efficiency scores. Multi-classification method were considered to build the prediction of four ratings for the festivals in this study. We utilized neural networks and SVMs with OAO(one-against-one), OAR(one-against-rest), C&S(crammer & singer) with Korea festival data from 2013 to 2018. Findings The number of total visitors in low efficient rating of DEA is more larger than the number of total visitors in high efficient ratings although the total expenditure of visitors is the highest in the most efficient rating when we analyzed the results of DEA for the characteristics of four ratings. SVM with OAO model showed the most superior performance in accuracy as SVM with OAR model was not trained well because of the imbalanced distribution between efficient rating and the other ratings. Our approach could predict the efficiency of festivals which were not included in the review process of culture tourism festivals without rebuilding DEA models each time. This enables us to manage the festivals efficiently with the proposed machine learning models.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.26 no.5
• /
• pp.519-526
• /
• 2000

Osteoporosis has recently been recognized as a major health problem in the elderly population. The disorder is manifested as a loss of bone mass accompanied by structural alteration of bone and increased incidence of fracture. Mandible also may be affected. So, I evaluated panoramic views of 66 postmenopausal women for finding the possibility of useful diagnostic mandibular parmeters of osteoporosis. To know the correlationship between skeleton and mandible, the average of the bone mineral density of lumbar from 2nd to 4th by the dual energy X-ray absorptiometry(DEXA, LUNAR DPZ. USA), and age and mandibular parameters, that is, the number of residual teeth, alveolar ridge resorption ratio, panoramic mandibular index (PMI), mandibular cortical width (MCW), angular cortical thickness (ACT), ramus cortical thickness (RCT), morphology of mandibular inferior cortical (MIC) were compared. And I divided the all tested women to the osteoporotic group and non-osteoporotic group by the use of T-score -2.0, which was derived from skeletal bone mineral density (BMD). To find the correlationship of the each group with mandibular parameters, t-test and discriminant analysis were done. The results of the t-test were that all parameters were highly related with 2 groups (p<0.05). Especially ACT, MIC, age have had even higher correlationship than others (p<0.001). The results of the discriminant analysis by the use of these ACT, MIC and age were that the discriminant function was Z = -2.973+(-1.447)$\times$(ACT)+1.131$\times$(MIC score)+(0.052)$\times$(age), the cutting score was 0.257 and the classification accuracy was 84.8%. Therefore I suggest that the consideration of the angular cortical thickness (ACT), the age of patient and the morphology of mandibular inferior cortical(MIC) may help find the osteoporosis.