• Knowledge Management Research
• /
• v.5 no.1
• /
• pp.69-82
• /
• 2004

Prior research on knowledge management focused more on the experiential knowledge based on individual's experience or knowhow than on the analytical knowledge extracted from corporate data. This study examines the effects of the data warehouse technology, especially OLAP(on line analytical processing) and data mining techniques, on the analytical knowledge creation in organizations, linking analytical knowledge creation to data analysis method through real world case studies.

• Journal of the Korean Data and Information Science Society
• /
• v.17 no.1
• /
• pp.149-160
• /
• 2006

Association rule mining searches for interesting relationships among items in a given large data set. Association rules are frequently used by retail stores to assist in marketing, advertising, floor placement, and inventory control. There are three primary threshold measures in association rule; support and confidence and lift. In the case of appling real world to association rules, we have some difficulties in data interpretation because we obtain many rules. In this paper, we develop the model of association rules using latent variables for environmental survey data.

• Journal of Korea Multimedia Society
• /
• v.8 no.6
• /
• pp.844-855
• /
• 2005

This paper proposes a human action recognition scheme for Intelligent Web Browser. Based on the principle that a human action can be defined as a combination of multiple articulation movements, the inference of stochastic grammars is applied to recognize each action. Human actions in 3 dimensional (3D) world coordinate are measured, quantized and made into two sets of 4-chain-code for xy and zy projection planes, consequently they are appropriate for applying the stochastic grammar inference method. We confirm this method by experiments, that various physical actions can be classified correctly against a set of real world 3D temporal data. The result revealed a comparatively successful achievement of $93.8\%$ recognition rate through the experiments of 8 movements of human head and $84.9\%$ recognition rate of 60 movements of human upper body. We expect that this scheme can be used for human-machine interaction commands in a web browser.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.3
• /
• pp.186-197
• /
• 2023

In this study, we focus on the improvement of data quality transmitted from a weather buoy that guides a route of ships. The buoy has an Internet-of-Thing (IoT) including sensors to collect meteorological data and the buoy's status, and it also has a wireless communication device to send them to the central database in a ground control center and ships nearby. The time interval of data collected by the sensor is irregular, and fault data is often detected. Therefore, this study provides a framework to improve data quality using machine learning models. The normal data pattern is trained by machine learning models, and the trained models detect the fault data from the collected data set of the sensor and adjust them. For determining fault data, interquartile range (IQR) removes the value outside the outlier, and an NGBoost algorithm removes the data above the upper bound and below the lower bound. The removed data is interpolated using NGBoost or long-short term memory (LSTM) algorithm. The performance of the suggested process is evaluated by actual weather buoy data from Korea to improve the quality of 'AIR_TEMPERATURE' data by using other data from the same buoy. The performance of our proposed framework has been validated through computational experiments based on real-world data, confirming its suitability for practical applications in real-world scenarios.

• 한국데이터정보과학회:학술대회논문집
• /
• 2005.10a
• /
• pp.177-188
• /
• 2005

Association rule mining searches for interesting relationships among items in a given large data set. Association rules are frequently used by retail stores to assist in marketing, advertising, floor placement, and inventory control. There are three primary threshold measures in association rule; support and confidence and lift. In the case of appling real world to association rules, we have some difficulties in data interpretation because we obtain many rules. In this paper, we develop the model of association rules using latent variables for environmental survey data.

• Korean Journal of Clinical Pharmacy
• /
• v.21 no.3
• /
• pp.249-255
• /
• 2011

Objective: To examine the drug use (prescribing) pattern of serious drug-drug interactions (DDIs, contraindicated drug interactions) using real world data. Prescription patterns were examined in terms of dispensing types. Method: Retrospective drug utilization review (DUR) study was performed. One hundred and six datasets of serious DDIs (DDI pairs) were determined among DDI datasets that Ministry of Health & Welfare announced for the DUR system from 2004 to 2005. Electronically transacted ambulatory patients' prescription database to Health Insurance Assessment and Review Services (HIRA) from July, 2005 to June, 2006 was collected with personal information deidentified and analyzed in terms of types of dispensing as a contributing factor. Results: After prescription data analysis per each patient, total number of DDI cases using 95 DDI pairs was 5,511, which accounted for 2.6 cases per patients. DDI cases between two drugs from each of community pharmacy dispensing- type prescription were considerable (63% vs. 24% in those from each of in-institutional dispensing-type prescription and vs. 13% in those from a community pharmacy dispensing-type prescription and an in-institutional dispensingtype prescription). Conclusions: DDI cases from different prescribers were found to be significant. Thus, the concurrent DUR process between prescriptions from different physicians and institutions should be implemented for the safe drug use.

• Journal of Computing Science and Engineering
• /
• v.5 no.3
• /
• pp.197-209
• /
• 2011

The increasing popularity of graph data, such as social and online communities, has initiated a prolific research area in knowledge discovery and data mining. As more real-world graphs are released publicly, there is growing concern about privacy breaching for the entities involved. An adversary may reveal identities of individuals in a published graph, with the topological structure and/or basic graph properties as background knowledge. Many previous studies addressing such attacks as identity disclosure, however, concentrate on preserving privacy in simple graph data only. In this paper, we consider the identity disclosure problem in weighted graphs. The motivation is that, a weighted graph can introduce much more unique information than its simple version, which makes the disclosure easier. We first formalize a general anonymization model to deal with weight-based attacks. Then two concrete attacks are discussed based on weight properties of a graph, including the sum and the set of adjacent weights for each vertex. We also propose a complete solution for the weight anonymization problem to prevent a graph from both attacks. In addition, we also investigate the impact of the proposed methods on community detection, a very popular application in the graph mining field. Our approaches are efficient and practical, and have been validated by extensive experiments on both synthetic and real-world datasets.

• Journal of Auto-vehicle Safety Association
• /
• v.15 no.2
• /
• pp.6-12
• /
• 2023

For the commercialization and standardization of autonomous vehicles, demand for rigorous safety criteria has been increased over the world. In Korea, the number of extraordinary service permission for automated vehicles has risen since Hyundai Motor Company got its initial license in March 2016. Nevertheless, licensing standards and evaluation factors are still insufficient for operating on public roadways. To assure driving safety, it is significant to verify whether or not the vehicle's decision is similar to human driving. This paper validates the safety of the autonomous vehicle by drawing scenario-based comparisons between manual driving and autonomous driving. In consideration of real traffic situations and safety priority, seven scenarios were chosen and classified into basic and advanced scenarios. All scenarios and safety factors are constructed based on existing ADAS requirements and investigated via a computer simulation and actual experiment. The input data was collected by an experimental vehicle test on the SNU FMTC test track located at Siheung. Then the offline simulation was conducted to verify the output was appropriate and comparable to the manual driving data.

• Journal of Korea Multimedia Society
• /
• v.22 no.1
• /
• pp.1-9
• /
• 2019

Single image rain removal is a typical inverse problem which decomposes the image into a background scene and a rain streak. Recent works have witnessed a substantial progress on the task due to the development of convolutional neural network (CNN). However, existing CNN-based approaches train the network with synthetically generated training examples. These data tend to make the network bias to the synthetic scenes. In this paper, we present an unsupervised framework for removing rain streaks from real-world rainy images. We focus on the natural phenomena that static rainy scenes capture a common background but different rain streak. From this observation, we train siamese network with the real rain image pairs, which outputs identical backgrounds from the pairs. To train our network, a real rainy dataset is constructed via web-crawling. We show that our unsupervised framework outperforms the recent CNN-based approaches, which are trained by supervised manner. Experimental results demonstrate that the effectiveness of our framework on both synthetic and real-world datasets, showing improved performance over previous approaches.

• The Journal of Korea Robotics Society
• /
• v.16 no.1
• /
• pp.49-55
• /
• 2021

Recently, a smart farm technology is drawing attention as an alternative to the decline of farm labor population problems due to the aging society. Especially, there is an increasing demand for automatic harvesting system that can be commercialized in the market. Pre-harvest crop detection is the most important issue for the harvesting robot system in a real-world environment. In this paper, we proposed a real-time tomato instance tracking algorithm by using deep learning and probability models. In general, It is hard to keep track of the same tomato instance between successive frames, because the tomato growing environment is disturbed by the change of lighting condition and a background clutter without a stochastic approach. Therefore, this work suggests that individual tomato object detection for each frame is conducted by YOLOv3 model, and the continuous instance tracking between frames is performed by Kalman filter and probability model. We have verified the performance of the proposed method, an experiment was shown a good result in real-world test data.