• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.5
• /
• pp.195-200
• /
• 2021

Due to the development of video sharing platforms, the amount of video uploads is exploding. Such videos often include various types of music, among which cover songs are included. In order to protect the copyright of music, an algorithm to find the original song of the cover song is essential. However, it is not easy to find the original song because the cover song is a modification of the composition, speed and overall structure of the original song. So far, there is no known effective algorithm for searching the original song of the cover song. In this paper, we propose an algorithm for searching the original song of the cover song using the inflection points of the melody line. Inflection points represent the characteristic points of change in the melody sequence. The proposed algorithm compares the original song and the cover song using the sequence of inflection points for the representative phrase of the original song. Since the characteristics of the representative phrase are used, even if the cover song is a song made by modifying the overall composition of the song, the algorithm's search performance is excellent. Also, since the proposed algorithm uses only the features of the inflection point sequence, the memory usage is very low. The efficiency of the algorithm was verified through performance evaluation.

• Journal of Cadastre & Land InformatiX
• /
• v.50 no.2
• /
• pp.155-168
• /
• 2020

Open source is a key growth engine of the 4th industrial revolution, and the continuous development and use of various algorithms for image processing is expected. The purpose of this study is to examine the effectiveness of the UAS image processing open source based algorithm by comparing and analyzing the water reproduction and moving object filtering function and the time required for data processing in 3D reproduction. Five matching algorithms were compared based on recall and processing speed through the 'ANN-Benchmarks' program, and HNSW (Hierarchical Navigable Small World) matching algorithm was judged to be the best. Based on this, 108 algorithms for image processing were constructed by combining each methods of triangulation, point cloud data densification, and surface generation. In addition, the 3D reproduction and data processing time of 108 algorithms for image processing were studied for UAS (Unmanned Aerial System) images of a park adjacent to the sea, and compared and analyzed with the commercial image processing software 'Pix4D Mapper'. As a result of the study, the algorithms that are good in terms of reproducing water and filtering functions of moving objects during 3D reproduction were specified, respectively, and the algorithm with the lowest required time was selected, and the effectiveness of the algorithm was verified by comparing it with the result of 'Pix4D Mapper'.

• Journal of Korean Academy of Oral Health
• /
• v.41 no.4
• /
• pp.290-295
• /
• 2017

Objectives: Dental plaque emits red fluorescence under a visible blue light near the ultra-violet end of the light spectrum. The fluorescence characteristics of each microorganism have been reported in several studies. The aim of this study was to evaluate changes in red fluorescence of oral microorganisms that is affected by blood in the culture media. Methods: The gram-positive Actinomyces naeslundii (AN, KCTC 5525) and Lactobacillus casei (LC, KCTC 3109) and gram negative Prevotella intermedia (PI, KCTC 3692) that are known to emit red fluorescence were used in this study. Each bacterium was activated in broth and cultivated in different agar media at $37^{\circ}C$ for 7 days. Tryptic soy agar with hemin and vitamin $K_3$ (TSA), TSA with sheep blood (TSAB), basal medium mucin (BMM) medium, and BMM with sheep blood (BMMB) were used in this study. Fluorescence due to bacterial growth was observed under 405-nm wavelength blue light using the quantitative light-induced fluorescence-digital (QLF-D) device. The red, green, and blue fluorescence values of colonies were obtained using image-analysis software and the red to green ratio (R/G value) and red to total RGB ratio (R/RGB value) were calculated for quantitative comparison. Results: The QLF-D images of the AN, LC, and PI colonies showed red fluorescence in all media, but the fluorescence of all bacteria was reduced in TSA and BMM media, compared with in TSAB and BMMB media. Both the R/G and the R/RGB values of all bacteria were significantly reduced in growth media without blood (P<0.001). Conclusions: Based on this in vitro study, it can be concluded that red fluorescence of oral bacteria can be affected by growth components, especially blood. Blood-containing medium could be a significant factor influencing red fluorescence of oral bacteria. It can be further hypothesized that bleeding in the oral cavity can increase the red fluorescence of dental plaque.

• Structural Engineering and Mechanics
• /
• v.78 no.1
• /
• pp.41-52
• /
• 2021

Inelastic static pushover analysis has been used in the academic-research widely for seismic analysis of structures. Nowadays, the variety pushover analysis methods have been developed, including Modal pushover, Adaptive pushover, and Cyclic pushover, in which some weaknesses of the conventional pushover method have been rectified. In the conventional pushover analysis method, the effects of cumulative growth of cracks are not considered on the reduction of strength and stiffness of RC members that occur during earthquake or cyclic loading. Therefore, the Cyclic Pushover Analysis Method (CPA) has been proposed. This method is a powerful technique for seismic evaluation of regular reinforced concrete buildings in which the first mode of them is dominant. Since the bridges have different structures than buildings, their results cannot necessarily be attributed to bridges, and more research is needed. In this study, a cyclic pushover analysis with four loading protocols (suggested by valid references) by the Opensees software was conducted for seismic evaluation of two regular reinforce concrete bridges. The modeling method was validated with the comparison of the analytical and experimental results under both cyclic and dynamic loading. The failure mode of the piers was considered in two-mode of flexural failure and also a flexural-shear failure. Along with the cyclic analysis, conventional analysis has been studied. Also, the nonlinear incremental dynamic analysis (IDA) method has been used to examine and compare the results of pushover analyses. The time history of 20 far-field earthquake records was used to conduct IDA. After analysis, the base shear vs. displacement in the middle of the deck was drawn. The obtained results show that the cyclic pushover analysis method is able to evaluate an accurate seismic behavior of the reinforced concrete piers of the bridges. Based on the results, the cyclic pushover has proper convergence with IDA. Its accuracy was much higher than the conventional pushover, in which the bridge piers failed in flexural-shear mode. But, in the flexural failure mode, the results of each two pushover methods were close approximately. Besides, the cyclic pushover method with ACI loading protocol, and ATC-24 loading protocol, can provided more accurate results for evaluating the seismic investigation of the bridges, specially if the bridge piers are failed in flexural-shear failure mode.

• Tuberculosis and Respiratory Diseases
• /
• v.84 no.2
• /
• pp.159-166
• /
• 2021

Background: E-cigarettes are steadily gaining popularity in Korea. However, the characteristics of e-cigarette smokers, especially nicotine dependence and stress susceptibility, have not been evaluated in comparison to those of nonsmokers or combustible cigarette smokers in Korea. Methods: In this study, 28,059 participants from the Korea National Health and Nutrition Examination Survey (2013-2017) were classified into the following three groups: non-smokers, smokers (current smokers and ex-smokers of combustible cigarettes only), and e-smokers (current smokers and ex-smokers of e-cigarettes regardless of combustible cigarette use). Results: Among the participants, 16,980 (60.5%), 9,247 (33.0%), and 1,832 (6.4%) subjects were non-smokers, smokers, and e-smokers, respectively. E-smokers were younger, more educated, and had a higher household income than non-smokers or smokers. The number of e-smokers who smoked within 5 minutes of waking up (31.5% vs. 19.8%, p<0.001) and who planned to quit smoking within 6 months (39.1% vs. 35.7%, p<0.05) was greater than that of smokers. E-smokers perceived stress as "very much" (7.0% vs. 4.4%, p<0.001) and "a lot" (29.1% vs. 20.5%, p<0.001) compared to non-smokers. Suicidal ideation (6.5% vs. 4.7%, p<0.001), plans (2.4% vs. 1.3%, p<0.001), and attempts (1.1% vs. 0.5%, p<0.001) were higher in e-smokers than in non-smokers. Depressive episodes in 1 year (14.2% vs. 11.4%, p<0.05) and suicidal plans (2.4% vs. 1.8%, p<0.05) were more frequent among e-smokers than among smokers. Conclusion: E-smokers were younger, more educated, and had a higher income, but they were more dependent on nicotine and susceptible to stress than non-smokers and smokers. Smoking cessation counseling should be tailored according to the characteristics of e-smokers.

• Journal of Korea Society of Industrial Information Systems
• /
• v.26 no.4
• /
• pp.19-32
• /
• 2021

It is well known that any maintenance works for aircrafts must be carried out strictly in accordance with the specified maintenance manuals, especially for military airplanes. According to our previous studies, the largest portion of the maintenance jobs for military aircrafts is found to be related to the assembly/disassembly of various parts, which requires precise understanding of the work procedures as well as correlation between interconnected parts let alone grasping of the exact shapes of parts involved. However, the conventional manuals for aircraft maintenance have failed to provide enough information required for the efficient maintenance except for simple texts and vague pictures, which are far from being sufficient sets of information. On the contrary, unlike incomplete conventional manuals with poor contents, 3D modeling SW could provide us with not only powerful visualization tool even to see through inside any assembly but also freedom to watch parts under test from any angle we want. In addition, the maintenance personnels could learn the precise maintenance procedures through repeatedly watching 3D animated version of the maintenance work as if they were on the field. In this study, we have suggested the efficient procedures to develop 3D manual for aircraft maintenance using 3D modeling SW, Solidworks and implemented a 3D maintenance manual for Integrated Drive Generator(IDG) in Boeing 747. Characteristics of the developed 3D manual has been analyzed in comparison with the conventional ones as well. It is shown that the suggested method could be easily applied to develop a 3D maintenance manual for commercial airplanes since the maintenance works involving assembly/disassembly of major parts are very similar regardless of aircraft types.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.133-140
• /
• 2022

We investigate the performance of deep learning-based Korean language models on a task of predicting the score range of Korean essays written by foreign students. We construct a data set containing a total of 304 essays, which include essays discussing the criteria for choosing a job ('job'), conditions of a happy life ('happ'), relationship between money and happiness ('econ'), and definition of success ('succ'). These essays were labeled according to four letter grades (A, B, C, and D), and a total of eleven essay score range prediction experiments were conducted (i.e., five for predicting the score range of 'job' essays, five for predicting the score range of 'happiness' essays, and one for predicting the score range of mixed topic essays). Three deep learning-based Korean language models, KoBERT, KcBERT, and KR-BERT, were fine-tuned using various training data. Moreover, two traditional probabilistic machine learning classifiers, naive Bayes and logistic regression, were also evaluated. Experiment results show that deep learning-based Korean language models performed better than the two traditional classifiers, with KR-BERT performing the best with 55.83% overall average prediction accuracy. A close second was KcBERT (55.77%) followed by KoBERT (54.91%). The performances of naive Bayes and logistic regression classifiers were 52.52% and 50.28% respectively. Due to the scarcity of training data and the imbalance in class distribution, the overall prediction performance was not high for all classifiers. Moreover, the classifiers' vocabulary did not explicitly capture the error features that were helpful in correctly grading the Korean essay. By overcoming these two limitations, we expect the score range prediction performance to improve.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.308-317
• /
• 2022

Researches are underway to efficiently reduce the size of video data transmitted and stored in the image analysis process using deep learning-based machine vision technology. MPEG (Moving Picture Expert Group) has newly established a standardization project called VCM (Video Coding for Machine) and is conducting research on video encoding for machines rather than video encoding for humans. We are researching a multitask that performs various tasks with one image input. The proposed pipeline does not perform all object detection of each task that should precede object detection, but precedes it only once and uses the result as an input for each task. In this paper, we propose a pipeline for efficient multitasking and perform comparative experiments on compression efficiency, execution time, and result accuracy of the input image to check the efficiency. As a result of the experiment, the capacity of the input image decreased by more than 97.5%, while the accuracy of the result decreased slightly, confirming the possibility of efficient multitasking.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.12
• /
• pp.569-578
• /
• 2021

Thanks to web development today, we can easily access online news via various media. As much as it is easy to access online news, we often face fake news pretending to be true. As fake news items have become a global problem, fact-checking services are provided domestically, too. However, these are based on expert-based manual detection, and research to provide technologies that automate the detection of fake news is being actively conducted. As for the existing research, detection is made available based on contextual characteristics of an article and the comparison of a title and the main article. However, there is a limit to such an attempt making detection difficult when manipulation precision has become high. Therefore, this study suggests using a verifying article to decide whether a news item is genuine or not to be affected by article manipulation. Also, to improve the precision of fake news detection, the study added a process to summarize a subject article and a verifying article through the summarization model. In order to verify the suggested algorithm, this study conducted verification for summarization method of documents, verification for search method of verification articles, and verification for the precision of fake news detection in the finally suggested algorithm. The algorithm suggested in this study can be helpful to identify the truth of an article before it is applied to media sources and made available online via various media sources.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.67 no.1
• /
• pp.67-75
• /
• 2022

Roots play important roles in water and nutrient uptake and in response to various environmental stresses. Investigating diversification of cultivars through root phenotyping is important for crop improvement in adzuki beans. Therefore, we analyzed the morphological and architectural root traits of 22 adzuki bean cultivars using 2-dimensional (2D) root imaging. Plants were grown in plastic tubes [6 cm (diameter) × 40 cm (height)] in a greenhouse from July 25^th to August 28^th. When the plants reached the 2^nd or 3^rd trifoliate leaf stage, the roots were removed and washed with tap water to remove soil particles. Clean root samples were scanned, and the scanned images were analyzed using the WinRHIZO Pro software. The cultivars were analyzed based on six root phenotypes [total root length (TRL), surface area (SA), average diameter (AD), and number of tips (NT) were included as root morphological traits (RMT); and link average length (LAL) and link average diameter (LAD) were included as root architectural traits (RAT)]. According to the analysis of variance (ANOVA), a significant difference was observed between the cultivars for all root morphological traits. Distribution analysis demonstrated that all root traits except LAL followed a normally distributed curve. In the correlation test, the most important morphological trait, TRL, showed a strong positive correlation with SA (r = 0.97^***) and NT (r = 0.94^***). In comparison, between RMT and RAT, TRL showed a significantly negative correlation with LAL (r = -0.50^***); however, TRL did not show a correlation with LAD. Based on RMT and RAT, we identified the cultivars that ranked 5% from the top and bottom. In particular, the cultivar "IT 236657" showed the highest TRL, SA, and NT, while the cultivar "IT 236169" showed the lowest values for TRL, SA, and NT. In addition, the coefficient of variance for the six tested root traits ranged from (14.26-40%) which suggested statistical variability in root phenotypes among the 22 adzuki bean varieties. Thus, this study will help to select target root traits for the adzuki bean breeding program in the future, generating climate-resilient adzuki beans, especially for drought stress, and may be useful for developing biotic and abiotic stress-tolerant cultivars based on better root trait attributes.