• Smart Structures and Systems
• /
• v.2 no.3
• /
• pp.253-274
• /
• 2006

The structural monitoring of multi-wire strands is of importance to prestressed concrete structures and cable-stayed or suspension bridges. This paper addresses the monitoring of strands by ultrasonic guided waves with emphasis on the signal processing and automatic defect classification. The detection of notch-like defects in the strands is based on the reflections of guided waves that are excited and detected by magnetostrictive ultrasonic transducers. The Discrete Wavelet Transform was used to extract damage-sensitive features from the detected signals and to construct a multi-dimensional Damage Index vector. The Damage Index vector was then fed to an Artificial Neural Network to provide the automatic classification of (a) the size of the notch and (b) the location of the notch from the receiving sensor. Following an optimization study of the network, it was determined that five damage-sensitive features provided the best defect classification performance with an overall success rate of 90.8%. It was thus demonstrated that the wavelet-based multidimensional analysis can provide excellent classification performance for notch-type defects in strands.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.11a
• /
• pp.204-209
• /
• 1999

In general, neural networks are widely used for the category classification. But when low contrast images, such as multispectral images, are used as the input of neural networks, neural networks converge very slowly and are of bad performance. To overcome this problem, we propose a new image enhancement method which consists of smoothing process, finding the main valley and enhancement process. And the enhanced images by the proposed method are used as the input of neural networks for the category classification. When the new category classification method is applied to multispectral LANDSAT TM images, we verified that neural networks converge very fast and overall category classification performance is improved.

• Journal of the Korean Wood Science and Technology
• /
• v.47 no.4
• /
• pp.385-392
• /
• 2019

In our previous study, we investigated the use of ensemble models based on LeNet and MiniVGGNet to classify the images of transverse and longitudinal surfaces of five Korean softwoods (cedar, cypress, Korean pine, Korean red pine, and larch). It had accomplished an average F1 score of more than 98%; the classification performance of the longitudinal surface image was still less than that of the transverse surface image. In this study, ensemble methods of two different convolutional neural network models (LeNet3 for smartphone camera images and NIRNet for NIR spectra) were applied to lumber species classification. Experimentally, the best classification performance was obtained by the averaging ensemble method of LeNet3 and NIRNet. The average F1 scores of the individual LeNet3 model and the individual NIRNet model were 91.98% and 85.94%, respectively. By the averaging ensemble method of LeNet3 and NIRNet, an average F1 score was increased to 95.31%.

• Asia pacific journal of information systems
• /
• v.29 no.4
• /
• pp.771-788
• /
• 2019

Deep learning techniques such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) show superior performance in text classification than traditional approaches such as Support Vector Machines (SVMs) and Naïve Bayesian approaches. When using CNNs for text classification tasks, word embedding or character embedding is a step to transform words or characters to fixed size vectors before feeding them into convolutional layers. In this paper, we propose a parallel word-level and character-level embedding approach in CNNs for text classification. The proposed approach can capture word-level and character-level patterns concurrently in CNNs. To show the usefulness of proposed approach, we perform experiments with two English and three Korean text datasets. The experimental results show that character-level embedding works better in Korean and word-level embedding performs well in English. Also the experimental results reveal that the proposed approach provides better performance than traditional CNNs with word-level embedding or character-level embedding in both Korean and English documents. From more detail investigation, we find that the proposed approach tends to perform better when there is relatively small amount of data comparing to the traditional embedding approaches.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2005.11a
• /
• pp.666-669
• /
• 2005

Social noise survey and auditory experiment on residential noises such as floor impact, air-borne, bathroom, drainage and traffic noises were conducted to classily a noise insulation Performance in apartment building. The survey results showed that annoyance among subjective responses to residential noises was most greatly affecting to satisfaction with noises. In the survey, boundary limit between satisfaction and dissatisfaction was also determined. Auditory experiments was also undertaken to determine noise insulation performance according to the percent of satisfaction for individual noise source. Result of auditory experiment showed that the noise insulation performance for floor impact, airborne, drainage and traffic noise corresponding to 40 % satisfaction is 49 dB (L$_{i,Fmax,AW}$), 48 dB (R'w), N-41, and N-40, respectively. Finally, classes of noise insulation performance in apartment building were proposed according to satisfaction with noises

• Journal of the Korea Convergence Society
• /
• v.6 no.1
• /
• pp.49-55
• /
• 2015

In the FTA environment, it is necessary to comply with the rules of origin in order to receive duty-free benefits. To do this, they have to precede the Harmonized System(HS) tariff classification of the goods and understand thoroughly the basic principles that constitute the tariff schedule of HS classification. For the correct classification, they should understand exactly the product name of "Heading" about the items, "Legal Note" in the relevant "Section" or "Chapter" as well as provisions of the commentary. Therefore, this paper proposes to develop a HS classification services based on the performance system of knowledge convergence of field terms commonly used in various industries. In result, our services can provide users the conveniences which users first selects one of seven decision elements of the classification and perform the classification easily and accurately.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.6
• /
• pp.792-798
• /
• 2007

In this paper, we propose a hierarchical fuzzy-rough classification method based on statistical information for maximizing the performance of pattern classification and reducing the number of rules without learning approaches such as neural network, genetic algorithm. In the proposed method, statistical information is used for extracting the partition intervals of antecedent fuzzy sets at each layer on hierarchical fuzzy-rough classification systems and rough sets are used for minimizing the number of fuzzy if-then rules which are associated with the partition intervals extracted by statistical information. To show the effectiveness of the proposed method, we compared the classification results(e.g. the classification accuracy and the number of rules) of the proposed with those of the conventional methods on the Fisher's IRIS data. From the experimental results, we can confirm the fact that the proposed method considers only statistical information of the given data is similar to the classification performance of the conventional methods.

• Journal of KIISE:Software and Applications
• /
• v.29 no.3
• /
• pp.192-201
• /
• 2002

Automated text classification is considered as an important method to manage and process a huge amount of documents in digital forms that are widespread and continuously increasing. Recently, text classification has been addressed with machine learning technologies such as k-nearest neighbor, decision tree, support vector machine and neural networks. However, only few investigations in text classification are studied on real problems but on well-organized text corpus, and do not show their usefulness. This paper proposes and analyzes text classification methods for a real application, email document classification task. First, we propose a combining method of multiple neural networks that improves the performance through the combinations with maximum and neural networks. Second, we present another strategy of combining multiple machine learning classifiers. Voting, Borda count and neural networks improve the overall classification performance. Experimental results show the usefulness of the proposed methods for a real application domain, yielding more than 90% precision rates.

• The Journal of the Korea Contents Association
• /
• v.12 no.12
• /
• pp.471-478
• /
• 2012

Various studies on sentiment classification of documents have been performed. Recently, they have been applied to twitter sentiment classification. However, they did not show good performances because they did not consider the characteristics of tweets such as tweet structure, emoticons, spelling errors, and newly-coined words. In this paper, we perform experiments on various input features (emoticon polarity, retweet polarity, author polarity, and replacement words) which affect twitter sentiment classification model based on machine-learning techniques. In the experiments with a sentiment classification model based on a support vector machine, we found that the emoticon polarity features and the author polarity features can contribute to improve the performance of a twitter sentiment classification model. Then, we found that the retweet polarity features and the replacement words features do not affect the performance of a twitter sentiment classification model contrary to our expectations.

• Explosives and Blasting
• /
• v.24 no.1
• /
• pp.63-69
• /
• 2006

Building tunnels means dealing with what rock is encountered. Relocation of the site of the underground structure is rarely possible. Tunneling engineers and miners have to cope with the quality of the rock mass as it is. Different tunneling philosophies and different rock classification methods have been developed in various countries. Most of the rock classification methods are based on the response of the rock mass to the excavation. Tunnel support requirements could be assessed analytically, supplemented by rock mass classification predictions, and verified by measurements during construction. Rock mass classifications on their own should only be used for preliminary, planning purposes and not for final tunnel support. Design of blast pattern in tunneling projects in Korea is also mostly prepared according to the general rock classification methods such as RMR or Q. They, however, do not take into account the blast performance, and as a consequence, produce poor blasting results. In this paper, the methods of general rock classification and blast design for tunnel excavation in Korea are reviewed, and efforts to develop a new classification method, reflecting the blasting performance, are presented.