• Journal of Broadcast Engineering
• /
• v.23 no.6
• /
• pp.855-865
• /
• 2018

Sound event detection is one of the research areas to model human auditory cognitive characteristics by recognizing events in an environment with multiple acoustic events and determining the onset and offset time for each event. DCASE, a research group on acoustic scene classification and sound event detection, is proceeding challenges to encourage participation of researchers and to activate sound event detection research. However, the size of the dataset provided by the DCASE Challenge is relatively small compared to ImageNet, which is a representative dataset for visual object recognition, and there are not many open sources for the acoustic dataset. In this study, the sound events that can occur in indoor and outdoor are collected on a larger scale and annotated for dataset construction. Furthermore, to improve the performance of the sound event detection task, we developed a dual CNN structured sound event detection system by adding a supplementary neural network to a convolutional neural network to determine the presence of sound events. Finally, we conducted a comparative experiment with both baseline systems of the DCASE 2016 and 2017.

• Journal of Korea Technology Innovation Society
• /
• v.21 no.3
• /
• pp.1155-1178
• /
• 2018

Future automobiles are evolving into movable living spaces capable of eco-friendly autonomous driving. The role of electrically processing, controlling, and commanding various information in the vehicle is essential. It is expected that the automotive semiconductor will play a key role in the future automobile such as self-driving and eco-friendly automobile. In order to foster the automotive semiconductor industry, it is necessary to grasp technology trends and to acquire technology and quality that reflects the requirements in advance, thereby achieving technological innovation with industrial competitiveness. However, there is a lack of systematic analysis of technology trends to date. In this study, we analyzed the technology trends of automotive semiconductors using patent analysis and topic model, and confirmed technologies such as electric cars, driving assistance, and digital manufacturing. The technology trends showed that element technology and technical characteristics change according to technology convergence, market needs, and government regulations. Through this research, it is expected that it will help to make R&D policy for automotive semiconductor industry and to make decision for industrial technology strategy establishment. In addition, it is expected that it will be used effectively in detail research direction and patent strategy establishment by providing detailed classification of technology and trend analysis result of technology.

• Korean Journal of Heritage: History & Science
• /
• v.45 no.3
• /
• pp.174-193
• /
• 2012

This study focused on distribution ratio of stone properties based on material characteristic analysis, provenance presumption and transportation route interpretation of the Sungnyemun stone block foundation. The stone block foundation is composed of pinkish granite (56.0%), reddish granite (4.5%) and leucocratic granite (26.2%) of original stones and pinkish granite of new stones(13.3%). The rock-forming minerals for granites are consisted mainly of quartz, alkali-feldspar, plagioclase and biotite, and are similar geochemical evolution trend of major, rare earth, compatible and incompatible elements. Therefore, it is clear that the rocks are genetically same origin. As a result of magnetic susceptibility measurement, the pinkish and reddish granite of original stones and pinkish granite of new stones showed normal distribution around about 4.00(${\times}10^{-3}SI\;unit$). But the leucocratic granite of original stones were confirmed ilmenite series under about 1.00(${\times}10^{-3}SI\;unit$). As a result of provenance interpretation and transportation route analysis based on the petrological results, the provenance of pinkish granite and reddish granite of original stones are presumed the north slope in Namsan mountain and Naksan mountain. Also, the leucocratic granite of original stones and the pinkish granite of new stones are strongly possible furnished from the south and north slope in Namsan mountain and Naksan mountain, respectively.

• The Journal of Society for e-Business Studies
• /
• v.24 no.1
• /
• pp.105-120
• /
• 2019

The World Health Organization (WHO) and other government agencies aroundthe world have warned against antibiotic-resistant bacteria due to abuse of antibiotics and are strengthening their care and monitoring to prevent infection. However, it is highly necessary to develop an expeditious and accurate prediction and estimating method for preemptive measures. Because it takes several days to cultivate the infecting bacteria to identify the infection, quarantine and contact are not effective to prevent spread of infection. In this study, the disease diagnosis and antibiotic prescriptions included in Electronic Health Records were embedded through neural embedding model and matrix factorization, and deep learning based classification predictive model was proposed. The f1-score of the deep learning model increased from 0.525 to 0.617when embedding information on disease and antibiotics, which are the main causes of antibiotic resistance, added to the patient's basic information and hospital use information. And deep learning model outperformed the traditional machine hospital use information. And deep learning model outperformed the traditional machine learning models.As a result of analyzing the characteristics of antibiotic resistant patients, resistant patients were more likely to use antibiotics in J01 than nonresistant patients who were diagnosed with the same diseases and were prescribed 6.3 times more than DDD.

• Journal of Korean Society of Disaster and Security
• /
• v.12 no.1
• /
• pp.45-56
• /
• 2019

In this study, the seismic risk has been evaluated by setting the bedrock acceleration to 0.154g which, was taking into consideration that the earthquake return period for the buried electric power tunnels in the metropolitan area to be 1,000 years. In this case, the risk assessment during the earthquake was carried out in three stages. In the first stage, the site classification was performed based on the site investigation data of the target area. Then, the LPI(Liquefaction Potential Index) was applied using the site amplification factor. After, candidates were selected using a hazard map. In the second stage, risk assessment analysis of seismic response are evaluated thoroughly after the recalculation of the LPI based on the site characteristics from the boring logs around the electric power area that are highly probable to be liquefied in the first stage. The third Stage visited the electric power tunnels that are highly probable of liquefaction in the second stage to compensate for the limitations based on the borehole data. At this time, the risk of liquefaction was finally evaluated based off of the reinforcement method used at the time of construction, the application of seismic design, and the condition of the site.

• The Journal of Engineering Geology
• /
• v.28 no.4
• /
• pp.673-686
• /
• 2018

The physical properties of rocks constituting the rock mass were analyzed by using various methods such as 7 kinds of physical properties of about 2,400 data. The correlation equation was derived from the correlation equation with the dependent variables by screening independent variables through the significance level using multiple regression analysis. In order to verify the reliability of this equation, verification was performed through comparison with actual data using artificial neural network learning. The analysis results by petrogenesis and strength confirmed that the elastic wave velocity (compressional wave) and elastic modulus as the main influence factors for the independent variables affecting the dependent variables. This proves that most of the correlation equations using the above items are found in existing studies. And through this study, it is confirmed whether the rock classification is based on the above items in various standards. In addition, the analysis results of representative rocks showed a high correlation as the equation for estimating unconfined compressive strength and elastic modulus exceeds the coefficient of determination 0.8.

• Journal of Korean Society of Forest Science
• /
• v.110 no.2
• /
• pp.155-164
• /
• 2021

Many studies have been conducted on developing automatic plant identification algorithms using machine learning to various plant features, such as leaves and flowers. Unlike other plant characteristics, barks show only little change regardless of the season and are maintained for a long period. Nevertheless, barks show a complex shape with a large variation depending on the environment, and there are insufficient materials that can be utilized to train algorithms. Here, in addition to the previously published bark image dataset, BarkNet v.1.0, images of barks were collected, and a dataset consisting of 53 tree species that can be easily observed in Korea was presented. A convolutional neural network (CNN) was trained and tested on the dataset, and the factors that interfere with the model's performance were identified. For CNN architecture, VGG-16 and 19 were utilized. As a result, VGG-16 achieved 90.41% and VGG-19 achieved 92.62% accuracy. When tested on new tree images that do not exist in the original dataset but belong to the same genus or family, it was confirmed that more than 80% of cases were successfully identified as the same genus or family. Meanwhile, it was found that the model tended to misclassify when there were distracting features in the image, including leaves, mosses, and knots. In these cases, we propose that random cropping and classification by majority votes are valid for improving possible errors in training and inferences.

• Journal of Korea Foundry Society
• /
• v.41 no.1
• /
• pp.26-38
• /
• 2021

The status of Ppuri industry, including foundry industry was analyzed through statistical surveys over the past 10 years from 2009 to 2018, and summarized for each six Ppuri industries' points of view. Various statistics of Ppuri industry defined by the KSIC (Korean Standard Industry Classification) was obtained, and the status of Ppuri industry was identified through a sample survey of 5,000 companies from more than 30,000 target business companies of Ppuri industry. Throughout the analyzing process, we presented a variety of indicators, such as the number of the Ppuri companies and its ratio, regional distribution through Korean provinces, number of workers, characteristics by age group, sales, profit rates, etc. By devising a comparative method to measure the relative strength of Ppuri industry in Korea, Germany, and Japan, we have presented the competitiveness index change over the 10 years of time. The competitiveness index can be effectively and meaningfully used during various activities of the development of Ppuri industry in the forth coming future. With the current obtained data, we figured out the status of each 6 Ppuri industries, regional distribution, status of workers, sales and profit rates. We also suggested various proposals for strategy and policy making for each sector with urging voluntary response from Ppuri industry.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.651-658
• /
• 2021

Because bolts with anti-loosening coatings are used mainly for joining safety-related components in automobiles, accurate automatic screening of these coatings is essential to detect defects efficiently. The performance of the convolutional neural network (CNN) used in a previous study [Identification of bolt coating defects using CNN and Grad-CAM] increased with increasing number of data for the analysis of image patterns and characteristics. On the other hand, obtaining the necessary amount of data for coated bolts is difficult, making training time-consuming. In this paper, resorting to the same VGG16 model as in a previous study, transfer learning was applied to decrease the training time and achieve the same or better accuracy with fewer data. The classifier was trained, considering the number of training data for this study and its similarity with ImageNet data. In conjunction with the fully connected layer, the highest accuracy was achieved (95%). To enhance the performance further, the last convolution layer and the classifier were fine-tuned, which resulted in a 2% increase in accuracy (97%). This shows that the learning time can be reduced by transfer learning and fine-tuning while maintaining a high screening accuracy.

• Journal of Korean Library and Information Science Society
• /
• v.51 no.4
• /
• pp.313-332
• /
• 2020

The purpose of this study is to compare motivations for self-archiving across disciplines on an academic social networking site. We carried out an online survey with ResearchGate(RG) users, testing 18 motivational factors that we developed from a previous study (enjoyment, personal/professional gain, reputation, learning, self-efficacy, altruism, reciprocity, trust, community interest, social engagement, publicity, accessibility, self-archiving culture, influence of external actors, credibility, system stability, copyright concerns, additional time, and effort). We adapted Biglan's classification system of academic disciplines and compared motivations across different categories of discipline. First, we compared motivations across the four combined categories by the two dimensions - hard-pure, hard-applied, soft-pure, and soft-applied. We also performed a motivation comparison across each dimension between soft and hard disciplines and between pure and applied disciplines. We examined investigated statistical differences in motivations by demographic characteristics and RG usage of participants across categories as well. Findings showed that there were differences of motivations, such as enjoyment, accessibility, influence of external actors and additional time and effort, and personal/professional gains, for self-archiving across disciplines. For example, RG users in the hard-applied were more highly motivated by enjoyment than others; RG users in the soft-pure were more highly motivated by personal/professional gains than others. It is expected that findings could be used to develop strategies encouraging researchers in various disciplines contributing to share their data and publications in ASNSs.