• Journal of Industrial Technology
• /
• v.33 no.A
• /
• pp.31-39
• /
• 2013

There are two methods to make a distinction of deterioration of high-speed railway track. One is that an administrator checks for each attribute value of track induction data represented in graph and determines whether maintenance is needed or not. The other is that an administrator checks for monthly trend of attribute value of the corresponding section and determines whether maintenance is needed or not. But these methods have a weak point that it takes longer times to make decisions as the amount of track induction data increases. As a field of artificial intelligence, the method that a computer makes a distinction of deterioration of high-speed railway track automatically is based on machine learning. Types of machine learning algorism are classified into four type: supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning. This research uses supervised learning that analogizes a separating function form training data. The method suggested in this research uses SVM classifier which is a main type of supervised learning and shows higher efficiency binary classification problem. and it grasps the difference between two groups of data and makes a distinction of deterioration of high-speed railway track.

• Journal of KIBIM
• /
• v.7 no.1
• /
• pp.18-27
• /
• 2017

Although Industry Foundation Classes (IFC) provide standards for exchanging Building Information Modeling (BIM) data, authoring tools still require manual mapping between BIM entities and IFC classes. This leads to errors and omissions, which results in corrupted data exchanges that are unreliable and thus compromise the validity of IFC. This research explored precedent work by Krijnen and Tamke, who suggested ways to automate the mapping of IFC classes using a machine learning technique, namely anomaly detection. The technique incorporates geometric features of individual components to find outliers among entities in identical IFC classes. This research primarily focused on applying this approach on two architectural BIM models and determining its feasibility as well as limitations. Results indicated that the approach, while effective, misclassified outliers when an IFC class had several dissimilar entities. Another issue was the lack of entities for some specific IFC classes that prohibited the anomaly detection from comparing differences. Future research to improve these issues include the addition of geometric features, using novelty detection and the inclusion of a probabilistic graph model, to improve classification accuracy.

• Journal for History of Mathematics
• /
• v.17 no.3
• /
• pp.109-120
• /
• 2004

This study investigated three pre-service teachers' mathematical problem solving among hand-in-write-ups and final projects for each subject. All participants' activities and computer explorations were observed and video taped. If it was possible, an open-ended individual interview was performed before, during, and after each exploration. The method of data collection was observation, interviewing, field notes, students' written assignments, computer works, and audio and videotapes of pre- service teachers' mathematical problem solving activities. At the beginning of the mathematical problem solving activities, all participants did not have strong procedural and conceptual knowledge of the graph, making a model by using data, and general concept of a sine function, but they built strong procedural and conceptual knowledge and connected them appropriately through mathematical problem solving activities by using the computer technology.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.9
• /
• pp.49-61
• /
• 1996

Back-propagation(BP) algorithm needs a lot of time to train the artificial neural network (ANN) to get high accuracy level in classification tasks. So there have been extensive researches to process back-propagation algorithm on parallel processors. This paper prsents a linear systolic array which calculates forward-backward propagation of BP algorithm at the same time using effective space-time transformation and PE structure. First, we analyze data flow of forwared and backward propagations and then, represent the BP algorithm into data dapendency graph (DG) which shows parallelism inherent in the BP algorithm. Next, apply space-time transformation on the DG of ANN is turn with orthogonal direction projection. By doing so, we can get a snakelike systolic array. Also we calculate the interval of input for parallel processing, calculate the indices to make the right datas be used at the right PE when forward and bvackward propagations are processed in the same PE. And then verify the correctness of output when forward and backward propagations are executed at the same time. By doing so, the proposed system maximizes parallelism of BP algorithm, minimizes th enumber of PEs. And it reduces the execution time by 2 times through making idle PEs participate in forward-backward propagation at the same time.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.2
• /
• pp.55-62
• /
• 2022

A smart tourism chatbot is needed as a user interface to efficiently provide smart tourism services such as recommended travel products, tourist information, my travel itinerary, and tour guide service to tourists. We have been developed a smart tourism app and a smart tourism information system that provide smart tourism services to tourists. We also developed a smart tourism chatbot service consisting of khaiii morpheme analyzer, rule-based intention classification, and tourism information knowledge base using Neo4j graph database. In this paper, we develop the Korean and English smart tourism Name Entity (NE) datasets required for the development of the NER model using the pre-trained language models (PLMs) for the smart tourism chatbot system. We create the tourism information NER datasets by collecting source data through smart tourism app, visitJeju web of Jeju Tourism Organization (JTO), and web search, and preprocessing it using Korean and English tourism information Name Entity dictionaries. We perform training on the KoBERT-CRF NER model using the developed Korean and English tourism information NER datasets. The weight-averaged precision, recall, and f1 scores are 0.94, 0.92 and 0.94 on Korean and English tourism information NER datasets.

• Journal of Multimedia Information System
• /
• v.9 no.3
• /
• pp.177-182
• /
• 2022

A deep neural network (DNN) includes variables whose values keep on changing with the training process until it reaches the final point of convergence. These variables are the co-efficient of a polynomial expression to relate to the feature extraction process. In general, DNNs work in multiple 'dimensions' depending upon the number of channels and batches accounted for training. However, after the execution of feature extraction and before entering the SoftMax or other classifier, there is a conversion of features from multiple N-dimensions to a single vector form, where 'N' represents the number of activation channels. This usually happens in a Fully connected layer (FCL) or a dense layer. This reduced 2D feature is the subject of study for our analysis. For this, we have used the FCL, so the trained weights of this FCL will be used for the weight-class correlation analysis. The popular DNN models selected for our study are ResNet-101, VGG-19, and GoogleNet. These models' weights are directly used for fine-tuning (with all trained weights initially transferred) and scratch trained (with no weights transferred). Then the comparison is done by plotting the graph of feature distribution and the final FCL weights.

• Journal of Information Processing Systems
• /
• v.19 no.3
• /
• pp.310-322
• /
• 2023

Although the network environment is gradually improving, the virtual nature of the network is still the same fact, which has brought a great influence on the supervision of Weibo network public opinion dissemination. In order to reduce this influence, the user information of Weibo network public opinion dissemination is studied by using Python technology. Specifically, the 2019 "Ethiopian air crash" event was taken as the research subject, the relevant data were collected by using Python technology, and the data from March 10, 2019 to June 20, 2019 were constructed by using the implicit Dirichlet distribution topic model and the naive Bayes classifier. The Weibo network public opinion user identity graph model under the "Ethiopian air crash" on June 20 found that the public opinion users of ordinary netizens accounted for the highest proportion and were easily influenced by media public opinion users. This influence is not limited to ordinary netizens. Public opinion users have an influence on other types of public opinion users. That is to say, in the network public opinion space of the "Ethiopian air crash," media public opinion users play an important role in the dissemination of network public opinion information. This research can lay a foundation for the classification and identification of user identity information types under different public opinion life cycles. Future research can start from the supervision of public opinion and the type of user identity to improve the scientific management and control of user information dissemination through Weibo network public opinion.

• Asia pacific journal of information systems
• /
• v.29 no.4
• /
• pp.838-855
• /
• 2019

Online product reviews are a vital source for companies in that they contain consumers' opinions of products. The earlier methods of opinion mining, which involve drawing semantic information from text, have been mostly applied in one dimension. This is not sufficient in itself to elicit reviewers' comprehensive views on products. In this paper, we propose a novel approach in opinion mining by projecting online consumers' reviews in a multidimensional framework to improve review interpretation of products. First of all, we set up a new framework consisting of six dimensions based on a marketing management theory. To calculate the distances of review sentences and each dimension, we embed words in reviews utilizing Google's pre-trained word2vector model. We classified each sentence of the reviews into the respective dimensions of our new framework. After the classification, we measured the sentiment degrees for each sentence. The results were plotted using a radar graph in which the axes are the dimensions of the framework. We tested the strategy on Amazon product reviews of the iPhone and Galaxy smartphone series with a total of around 21,000 sentences. The results showed that the radar graphs visually reflected several issues associated with the products. The proposed method is not for specific product categories. It can be generally applied for opinion mining on reviews of any product category.

• Korean Journal of Remote Sensing
• /
• v.38 no.3
• /
• pp.283-298
• /
• 2022

As Synthetic Aperture Radar (SAR) image can be acquired regardless of the weather and day or night, it is highly recommended to be used for Automatic Target Recognition (ATR) in the fields of surveillance, reconnaissance, and national security. However, there are some limitations in terms of cost and operation to build various and vast amounts of target images for the SAR-ATR system. Recently, interest in the development of an ATR system based on simulated SAR images using a target model is increasing. Attributed Scattering Center (ASC) matching and template matching mainly used in SAR-ATR are applied to target classification. The method based on ASC matching was developed by World View Vector (WVV) feature reconstruction and Weighted Bipartite Graph Matching (WBGM). The template matching was carried out by calculating the correlation coefficient between two simulated images reconstructed with adjacent points to each other. For the performance analysis of the two proposed methods, the Synthetic and Measured Paired Labeled Experiment (SAMPLE) dataset was used, which has been recently published by the U.S. Defense Advanced Research Projects Agency (DARPA). We conducted experiments under standard operating conditions, partial target occlusion, and random occlusion. The performance of the ASC matching is generally superior to that of the template matching. Under the standard operating condition, the average recognition rate of the ASC matching is 85.1%, and the rate of the template matching is 74.4%. Also, the ASC matching has less performance variation across 10 targets. The ASC matching performed about 10% higher than the template matching according to the amount of target partial occlusion, and even with 60% random occlusion, the recognition rate was 73.4%.

• Journal of the Korea Institute of Building Construction
• /
• v.21 no.6
• /
• pp.701-712
• /
• 2021

As the domestic housing supply problem has been resolved, the apartment construction market has shifted to a consumer-oriented market that wants high quality, and in particular, expectations in the area of finishing quality have increased. Looking at the status of complaints regarding apartment housing defects supplied by Korea Land and Housing Corporation, tile-related complaints are the type occurring the most frequently. While the Ministry of Land, Infrastructure and Transport(MOLIT) is making an ongoing effort to reduce complaints related to defects, through approaches such as drafting amendments to 「Investigation of defects in apartment houses, calculation of repair costs, and standards for determining defects」, the provision of preventive measures has been insufficient. In addition, by reviewing studies, there has been insufficient research to construct a classification system after deriving the characteristics of each type using the qualitative knowledge of experts, various quantitative indicators, and suggesting measures for reduction according to the causes of each type. Therefore, this study will reflect qualitative indicators to use the AHP analysis that makes it easy to identify the relationship between defects by surveying construction experts. Then, by visualizing the weight of 'Possibility of recurrence after repair,' 'Degree of difficulty in repairing defects' and 'Fault frequency' using a radial graph, we will analyze the characteristics of each type of tile construction defect and establish measures for reduction according to the cause. This will improve the quality of the living environment and contribute to the establishment of a system for smooth defect management and reduction of defects in apartment tile construction.