• The KIPS Transactions:PartB
• /
• v.10B no.3
• /
• pp.281-286
• /
• 2003

A large number of features are collected for problem solving in real life, but to utilize ail the features collected would be difficult. It is not so easy to collect of correct data about all features. In case it takes advantage of all collected data to learn, complicated learning model is created and good performance result can't get. Also exist interrelationships or hierarchical relations among the features. We can reduce feature's number analyzing relation among the features using heuristic knowledge or statistical method. Heuristic technique refers to learning through repetitive trial and errors and experience. Experts can approach to relevant problem domain through opinion collection process by experience. These properties can be utilized to reduce the number of feature used in learning. Experts generate a new feature (highly abstract) using raw data. This paper describes machine learning model that reduce the number of features used in learning using heuristic function and use abstracted feature by neural network's input value. We have applied this model to the win/lose prediction in pro-baseball games. The result shows the model mixing two techniques not only reduces the complexity of the neural network model but also significantly improves the classification accuracy than when neural network and heuristic model are used separately.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.201-220
• /
• 2019

Fake news has emerged as a significant issue over the last few years, igniting discussions and research on how to solve this problem. In particular, studies on automated fact-checking and fake news detection using artificial intelligence and text analysis techniques have drawn attention. Fake news detection research entails a form of document classification; thus, document classification techniques have been widely used in this type of research. However, document summarization techniques have been inconspicuous in this field. At the same time, automatic news summarization services have become popular, and a recent study found that the use of news summarized through abstractive summarization has strengthened the predictive performance of fake news detection models. Therefore, the need to study the integration of document summarization technology in the domestic news data environment has become evident. In order to examine the effect of extractive summarization on the fake news detection model, we first summarized news articles through extractive summarization. Second, we created a summarized news-based detection model. Finally, we compared our model with the full-text-based detection model. The study found that BPN(Back Propagation Neural Network) and SVM(Support Vector Machine) did not exhibit a large difference in performance; however, for DT(Decision Tree), the full-text-based model demonstrated a somewhat better performance. In the case of LR(Logistic Regression), our model exhibited the superior performance. Nonetheless, the results did not show a statistically significant difference between our model and the full-text-based model. Therefore, when the summary is applied, at least the core information of the fake news is preserved, and the LR-based model can confirm the possibility of performance improvement. This study features an experimental application of extractive summarization in fake news detection research by employing various machine-learning algorithms. The study's limitations are, essentially, the relatively small amount of data and the lack of comparison between various summarization technologies. Therefore, an in-depth analysis that applies various analytical techniques to a larger data volume would be helpful in the future.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.36 no.4
• /
• pp.58-69
• /
• 2018

The purpose of this study was to present specific standards for landscape planning and construction applicable to landscaping areas in various historical sites. The results are as follows: First, the types of historical sites are classified according to their preservation status and processing techniques, and the classification according to their status is divided into those that have been buried underground, such as those that have been exposed to the ground, such as buildings and structures, and those that have a reputation or a record of the sites. The classification according to the wartime processing technique was classified by such techniques as closures that isolate the site, penetration that can be seen on the site, and overlays where a separate protection facility is installed on the site. Second, the principles of landscape planning for display of historical sites are divided into the items that make up the historical site, surface treatment of the sites, tree planting, and installation of facilities. If the site is not a circular space, the area separating the space by different materials between the components is required. In the event that preservation of the historical site is required, it is deemed desirable to use the soil, and to do so, the use of grasses and shrubs is effectively considered to be effective. The introduction of plants and plants should be considered according to the nature of the space. Depending on the area and nature of the monument, the facility is required to take a cautious approach by reviewing its influence on the landscape and the additional excavation of the monument. Third, the readjustment method derived as a result of looking at the landscaping principle in the historical site space was classified as conservation of status, installation of protection facilities, burial, restoration, relocation, and reproduction. Preservation of the status quo is essential for limited landscape planning and should not affect the prototype of existing relics. The protection facility shall be installed where necessary to protect the relics, and when the soil is formed, the surface treatment shall be required to remove trees that could damage the site and prevent soil and soil oil from being lost after the site. The restoration shall establish a landscaping plan according to the circular preservation based on the clues to the circle. The transfer requires a landscaping plan to create an environment similar to the outer space of an existing site and should be able to highlight the value or location of the original site. The reenactment should have a landscaping plan to revive the landscape and atmosphere of the past for the now-defunct remains. Fourth, landscaping can simultaneously satisfy the preservation of excavation sites and the increase in exhibition effects. In order to protect the traces of the past and vitalize the site of the ruins today, specific measures are required, the creation of a park for historical sites that preserve the functions and value of the relics, and the formation of a shape of linked contents can be suggested as alternatives.

• Journal of Acupuncture Research
• /
• v.18 no.4
• /
• pp.1-12
• /
• 2001

Study design : A retrospective study of lumbar disc herniations using results of follow-up computed tomographic scan examinations. Objective : Lumbar disc herniations is one of the cause low back pain and lower extremity pain. To clarify the lumbar disc herniations morphological changes over time(mean 5.3 years) in order to establish a strategy for treatment. Methods : Sixteen patients with lumbar disc herniations who underwent follow-up computed tomographic scan examinations were studied. The changes over time in herniated disc size(herniation ratio) were evaluated using this scan technique. The initial computed tomographic scan allowed classification of the herniations according to herniation ratio: small, medium and large. Results : Comparison with follow-up computed tomographic scans showed that of the 16 patients, in 14 patients(88%), the herniation ratio(HR) was decreased and among them, 8 patients had complet resolution of herniated disc. In 2 patients with small herniations, the HR of one case was increased, the other was decreased. In 8 patients with medium herniations, the HR of one case had no change, the others was decreased. In 6 patients with large herniation, the HR of all patients was decreased. Interestingly, 4 of the 16 patients showed calcification change of herniated disc. Conclusion : There is no doubt that herniated disc size is decreased over time. The largest herniations were those which had the greatest tendency to decrease in size. But in some cases, the HR was increased, or calcification change was showed.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.8 no.3
• /
• pp.11-22
• /
• 2005

It is necessary to arrange and analyze the collected research date to get regularity such as characteristics, merits and demerits, and possibility in city when constructing land information by analyzing linkage and utilization of cadastral information as the fundamental data for land information around the acreage of a lot and by expressing the purpose of each digital data construction with map. In short, that is the work to classify data, to make chart or map, or to analyze using statistical technique. Some information in land utilization had been used by computerization, but several problems were found in common use of total divisions. The most important problem is, in the case of drawing information, that topographical map with building boundary and land registration map with acreage boundary cannot be used together. In the case of property information, common utilization of property information that is basically needed and standard measurement of usage classification are necessary. The characteristics of the land usage data by the rearrangement of the cadastral information. etc. is presented as the basic data for the land information orientation, and the analyzing result of the data should be expressed and controlled on the map as the fundamental survey for the establishment of the land information oriented planning supports the physical space planning of the land cadaster finally. In this research, the problem in establishing current land information around acreage of a lot was found to research data to be needed in land information for utilizationof space based digital information, and was studied the method in relation to GIS.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.1
• /
• pp.141-149
• /
• 2020

The proportion of commercial vehicles currently used by the private sector among the vehicles operated by the military is very high at 58% and plans to increase further in the future. As the proportion of commercial vehicles in the military has increased, it is also an important issue to determine whether to disuse of commercial vehicles. At present, the decision of disuse of commercial vehicles is subjectively judged by vehicle technical inspector using design life and vehicle usage information. However, the difference according to the military operation environment is not reflected and objective judgment criteria are not presented. The purpose of this study is to develop a model to determine the disuse status of commercial vehicles in consideration of military operating environment. The data used in the study were 1,746 commercial vehicles of three types: cars, vans and trucks. Using the information of the operating area, climate characteristic, vehicle condition the decision model of disuse status was constructed using the classification machine learning technique. The proposed decision model of disuse status has an average accuracy of about 97% and can be used in the field. Based on the results of the study, the policy suggestions were proposed in the short and long term to improve the performance of decision model of disuse status of commercial vehicles in the future and to establish a new data construction method within the logistics information system.

• Journal of Food Hygiene and Safety
• /
• v.33 no.4
• /
• pp.280-288
• /
• 2018

In this study, an approach for the analysis of the five cephalopod species (octopus, long-arm octopus, squid, wet-foot octopus, beka squid) consumed in the Republic of Korea is developed. The samples were collected from the Southeast Asian countries Thailand, Indonesia, Vietnam, and China. The SYBR-green-based real-time qPCR method, based on the mitochondrial DNA genome of the five cephalopods was developed and validated. The intergroup variations in the mitochondrial DNA are evident in the bioinformatic analysis of the mitochondrial genomic DNA sequences of the five groups. Some of the highly-conserved and slightly-variated regions are identified in the mitochondrial cytochrome-c-oxidase subunit I (COI) gene, 16s ribosomal RNA (16s rRNA) gene, and 12s ribosomal RNA (12s rRNA) gene of these groups. To specify each five cephalopod groups, specific primer sets were designed from the COI, 16s rRNA and 12s rRNA regions. The specific primer sets amplified the DNA using the SYBR-green-based real-time PCR system and 11 commercially secured animal tissues: Octopus vulgaris, Octopus minor, Todarodes pacificus, Dosidicus gigas, Sepia esculenta, Amphioctopus fangsiao, Amphioctopus aegina, Amphioctopus marginatus, Loliolus beka, Loligo edulis, and Loligo chinensis. The results confirmed by a conveient way to calculate relative amplification levels between different samples in that it directly uses the threshold cycles (Ct)-value range generated by the qPCR system from these samples. This genomic DNA-based molecular technique provides a quick, accurate, and reliable method for the taxonomic classification of the animal tissues using the real-time qPCR.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.13 no.1
• /
• pp.50-61
• /
• 2010

This study was carried out to find out the way to build a comprehensive wetland ecosystem database using the technique of remote sensing and Geographic Information System. A Landsat TM image (taken in Oct. 30, 2002), Kompsat-2 images (Jan. 17, 2008 & Nov. 20, 2008), LiDAR(Mar. 1, 2009) were used for the primary source for the image analysis. Field surveys were conducted March to August of 2009 to help image analysis and examine the results. An actual wetland vegetation map was created based on the field survey. Satellite images were analyzed by unsupervised and supervised classification methods and finally categorized into such classes as Phragmites australis community, mixed community, sand beach, Scirpus planiculmis community and non-vegetation intertidal area. The map of wetland productivity was developed based on the productivity of Phragmites australis and the relationship to the proximity of adjacent water bodies. The developed 3 dimensional wetland map showed such several potential applications as flood inundation, birds flyway viewsheds and benthos distribution. Considering these results, we concluded that it is possible to use the remote sensing and GIS techniques for producing wetland ecosystem spatial database and these techniques are very effective for the development of the national wetland inventory in Korea.

• International Commerce and Information Review
• /
• v.14 no.3
• /
• pp.159-183
• /
• 2012

Promoted in places like Korea, the central government and the local governments that can provide information on which to base investment policy to attract foreign direct mutation-specific gravity model (Shift-Share Model) In this study, the decrease of foreign direct investment performance using factors looked up in the industry. The sample period of 2009, 2010, 2011 nationwide (metropolitan and non-metropolitan separated) of foreign direct investment performance for Industry Standard Industrial Classification (Division) was conducted. Factors to look at the results of the National Growth Effect(NS), the industrial structure effect (IM), local allocation effect(RS) to decrease foreign direct investment in 2010 and 2011 non-metropolitan, metropolitan national growth effect(RS) is negative(-) has a value. Because it appears to be the aftermath of the global recession, the impact on the domestic economy Metropolitan area and the Industrial Mix Effect(IM) to the development of education, culture, business, and transportation, etc. in the development of service industries than in non-metropolitan valid environment. In the sector of services (food accommodation, business services, entertainment), We did it, was able to find the function. However, the Regional Share Effect(RS) be competitive in the manufacturing sector in metropolitan areas in the metal and chemical sectors have been identified. These results seems to enhance the competitiveness of the region, such as the metropolitan area's excellent workforce. Shift-Share analysis technique based on competitive factors of the region, to find the failure has limitations.

• Journal of the Korean earth science society
• /
• v.38 no.7
• /
• pp.535-545
• /
• 2017

Maritime accidents around the Korean Peninsula are increasing, and the ship detection research using remote sensing data is consequently becoming increasingly important. This study presented a new ship detection algorithm using hyperspectral images that provide the spectral information of several hundred channels in the ship detection field, which depends on high resolution optical imagery. We applied a spectral matching algorithm between the reflection spectrum of the ship deck obtained from two field observations and the ship and seawater spectrum of the hyperspectral sensor of an airborne visible/infrared imaging spectrometer. A total of five detection algorithms were used, namely spectral distance similarity (SDS), spectral correlation similarity (SCS), spectral similarity value (SSV), spectral angle mapper (SAM), and spectral information divergence (SID). SDS showed an error in the detection of seawater inside the ship, and SAM showed a clear classification result with a difference between ship and seawater of approximately 1.8 times. Additionally, the present study classified the vessels included in hyperspectral images by presenting the adaptive thresholds of each technique. As a result, SAM and SID showed superior ship detection abilities compared to those of other detection algorithms.