• Journal of Information Technology and Architecture
• /
• v.9 no.4
• /
• pp.413-422
• /
• 2012

Many researchers have been studied to reveal human natural language to let machine understand its meaning by text based, page rank based or more. Particularly, it has been considered that URL and HTML Tag information in web documents are attracting people' attention again to analyze huge amount of web document automatically. In this paper, we propose a STW (Semantic Term Weight) approach based on syntactic and linguistic structure of web documents in order to classify what genres are. For the evaluation, we analyzed more than 1,000 documents from 20-Genre-collection corpus for training the documents based on SVM algorithm. Afterwards, we tested KI-04 corpus to evaluate performance of our proposed method. This paper measured their accuracy by classifying them into an experiment using STW and one without u sing STW. As the results, the proposed STW based approach showed approximately 10.2% which Is higher than one without use of STW.

• Journal of the Korean Geotechnical Society
• /
• v.34 no.12
• /
• pp.43-58
• /
• 2018

In this study, the load-transfer behavior along the shaft of the prebored and precast piles was investigated by pile loading tests. Special attention was given to quantifying the skin frictions developed between the pile-soil interfaces of the 14 instrumented test piles. Based on this detailed field tests, the load - settlement curves and axial load distributions of piles were obtained and the load-transfer curves (t-z curves) for the test piles were proposed. As such, it is found that the test results show two different load transfer behaviors; ductile and brittle behavior curves. The corresponding t-z curves are proposed based on the hyperbolic- and sawtooth-shape, respectively. By validating the accuracy of the proposed curves, it is also found that the prediction results based on the proposed load-transfer curve are in good agreement with the general trends observed by the field loading tests.

• Journal of Internet Computing and Services
• /
• v.22 no.5
• /
• pp.79-86
• /
• 2021

As the usefulness of big data analysis has been drawing attention, many studies in the business research area begin to use big data to predict firm performance. Previous studies mainly rely on data outside of the firm through news articles and social media platforms. The voices within the firm in the form of employee satisfaction or evaluation of the strength and weakness of the firm can potentially affect firm value. However, there is insufficient evidence that online employee reviews are valid to predict firm value because the data is relatively difficult to obtain. To fill this gap, from 2014 to 2019, we employed 97,216 reviews collected by JobPlanet, an online firm review website in Korea, and developed a machine learning-based predictive model. Among the proposed models, the LSTM-based model showed the highest accuracy at 73.2%, and the MAE showed the lowest error at 0.359. We expect that this study can be a useful case in the field of firm value prediction on domestic companies.

• Journal of Digital Convergence
• /
• v.19 no.4
• /
• pp.25-31
• /
• 2021

Moving toward an aged society, traffic accidents involving elderly drivers have also attracted broader public attention. A rapid increase of senior involvement in crashes calls for developing appropriate crash-severity prediction models specific to senior drivers. In that regard, this study leverages machine learning (ML) algorithms so as to predict the severity of vehicle-pedestrian collisions induced by elderly drivers. Specifically, four ML algorithms (i.e., Logistic model, K-nearest Neighbor (KNN), Random Forest (RF), and Support Vector Machine (SVM)) have been developed and compared. Our results show that Logistic model and SVM have outperformed their rivals in terms of the overall prediction accuracy, while precision measure exhibits in favor of RF. We also clarify that driver education and technology development would be effective countermeasures against severity risks of senior driver-induced collisions. These allow us to support informed decision making for policymakers to enhance public safety.

• Structural Engineering and Mechanics
• /
• v.81 no.3
• /
• pp.293-303
• /
• 2022

As infrastructure ages and traffic load increases, serious public concerns have arisen for the well-being of bridges. The current health monitoring practice focuses on large-scale bridges rather than short span bridges. However, it is critical that more attention should be given to these behind-the-scene bridges. The relevant information about the construction methods and as-built properties are most likely missing. Additionally, since the condition of a bridge has unavoidably changed during service, due to weathering and deterioration, the material properties and boundary conditions would also have changed since its construction. Therefore, it is not appropriate to continue using the design values of the bridge parameters when undertaking any analysis to evaluate bridge performance. It is imperative to update the model, using finite element (FE) analysis to reflect the current structural condition. In this study, a FE model is established to simulate a concrete culvert bridge in New South Wales, Australia. That model, however, contains a number of parameter uncertainties that would compromise the accuracy of analytical results. The model is therefore updated with a neural network (NN) optimisation algorithm incorporating Monte Carlo (MC) simulation to minimise the uncertainties in parameters. The modal frequency and strain responses produced by the updated FE model are compared with the frequency and strain values on-site measured by sensors. The outcome indicates that the NN model updating incorporating MC simulation is a feasible and robust optimisation method for updating numerical models so as to minimise the difference between numerical models and their real-world counterparts.

• Journal of Digital Contents Society
• /
• v.19 no.6
• /
• pp.1177-1183
• /
• 2018

Recent developments in machine learning have attracted a lot of attention for techniques such as machine learning and deep learning that implement artificial intelligence. In this paper, binary malicious code using deep learning based R-CNN is imaged and the feature is extracted from the image to classify the family. In this paper, two steps are used in deep learning to image malicious code using CNN. And classify the characteristics of the family of malicious codes using R-CNN. Generate malicious code as an image, extract features, classify the family, and automatically classify the evolution of malicious code. The detection rate of the proposed method is 93.4% and the accuracy is 98.6%. In addition, the CNN processing speed for image processing of malicious code is 23.3 ms, and the R-CNN processing speed is 4ms to classify one sample.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.21 no.2
• /
• pp.169-176
• /
• 2001

In modern industry, the accuracy and the sulfate-finish requirements for machined parts have been becoming ever more stringent. In addition, the measurement and understanding of surface topography is rapidly attracting the attention of the physicist and chemist as well as the engineer. Optical measuring method is used in vibration measurement, crack and defect detection with the advent of opto-mechatronics, and it is expected to play an important role in surface topography. In this study, the principle of confocal microscope is described, and the advanced 3-D surface measuring system that has better performance than the traditional confocal microscope is developed. Suitable fixtures arc developed and integrated with the computer system for generating 3-D surface and form data. Software for data acquisition and analysis of various parameters in surface geometrical features has been developed.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.5A
• /
• pp.423-430
• /
• 2010

The performances of turbo-coded space-time block coding (STBC) schemes are subject to how soft decision detection (SDD) information are generated from the STBC decoder. For this reason, we have to pay particular attention to estimation of SDD. In this paper, we evaluate the performance of a turbo coded STBC scheme depending on the accuracy of the SDD. Recently, a new quasi orthogonal STBC (QO-STBC) scheme using a noise whitened filter was proposed in order to reduce noise enhancing effect of zero forcing detection process. This QO-STBC scheme was proven to be efficient in computational complexity compared to the other conventional QO-STBC schemes. In this paper, we first present detailed mathematical analysis on the noise whitened QO-STBC scheme, and by using the result we propose the optimum SDD method.

• Journal of Korean Society for Geospatial Information Science
• /
• v.20 no.4
• /
• pp.67-75
• /
• 2012

For the last few years, LBS has attracted considerable attention from many industries and societies as a result of propagated smart devices. LBS has a high utilization of mobile users as it uses user positions as a significant factor. Current LBS has only taken user position into account and it makes some limits. So, it is necessarily suggested that support for personalized services which consider user's motion, traffic condition, weather condition, time, personal information and preferences that have a huge impact on the accuracy. The purpose of this study is to design the inference systems with user's motion, preferences and schedules and provide users with the personalized information. To achieve this, Movement Ontology, User Profile Ontology, Schedule Ontology and Work Ontology should be constructed and based on this, smart applications were developed. Developed applications induced appropriately recommended results according to user's preference, motion and directions.

• Journal of Korean Society for Geospatial Information Science
• /
• v.19 no.1
• /
• pp.79-86
• /
• 2011

Recently, aerial laser scanning technology has received full attention in constructing DEM(Digital Elevation Model). It is well known that the quality of DEM is mostly influenced by the accuracy of DTD(Digital Terrain Data) extracted from LiDAR(Light Detection And Ranging) raw data. However, there are always misclassified data in the DTD generated by automatic filtering process due to the limitation of automatic filtering algorithm and intrinsic property of LiDAR raw data. In order to eliminate the misclassified data, a manual filtering process is performed right after automatic filtering process. In this study, an algorithm that detects automatically possible misclassified data included in the DTD from automatic filtering process is proposed, which will reduce the load of manual filtering process. The algorithm runs on 2D grid data structure and makes use of several parameters such as 'Slope Angle', 'Slope DeltaH' and 'NNMaxDH(Nearest Neighbor Max Delta Height)'. The experimental results show that the proposed algorithm quite well detected the misclassified data regardless of the terrain type and LiDAR point density.