• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.29-40
• /
• 2022

In this paper, we studied a system that detects and analyzes the pathological features of diabetic retinopathy using Mask R-CNN and a Random Forest classifier. Those are one of the deep learning techniques and automatically diagnoses diabetic retinopathy. Diabetic retinopathy can be diagnosed through fundus images taken with special equipment. Brightness, color tone, and contrast may vary depending on the device. Research and development of an automatic diagnosis system using artificial intelligence to help ophthalmologists make medical judgments possible. This system detects pathological features such as microvascular perfusion and retinal hemorrhage using the Mask R-CNN technique. It also diagnoses normal and abnormal conditions of the eye by using a Random Forest classifier after pre-processing. In order to improve the detection performance of the Mask R-CNN algorithm, image augmentation was performed and learning procedure was conducted. Dice similarity coefficients and mean accuracy were used as evaluation indicators to measure detection accuracy. The Faster R-CNN method was used as a control group, and the detection performance of the Mask R-CNN method through this study showed an average of 90% accuracy through Dice coefficients. In the case of mean accuracy it showed 91% accuracy. When diabetic retinopathy was diagnosed by learning a Random Forest classifier based on the detected pathological symptoms, the accuracy was 99%.

• Journal of Industrial Convergence
• /
• v.21 no.1
• /
• pp.187-192
• /
• 2023

In this study, trends in ICT education were investigated by analyzing the frequency of appearance of keywords related to machine learning and using conversion of iteration correction(CONCOR) techniques. A total of 304 papers from 2018 to the present published in registered sites were searched on Google Scalar using "ICT education" as the keyword, and 60 papers pertaining to ICT education were selected based on a systematic literature review. Subsequently, keywords were extracted based on the title and summary of the paper. For word frequency and indicator data, 49 keywords with high appearance frequency were extracted by analyzing frequency, via the term frequency-inverse document frequency technique in natural language processing, and words with simultaneous appearance frequency. The relationship degree was verified by analyzing the connection structure and centrality of the connection degree between words, and a cluster composed of words with similarity was derived via CONCOR analysis. First, "education," "research," "result," "utilization," and "analysis" were analyzed as main keywords. Second, by analyzing an N-GRAM network graph with "education" as the keyword, "curriculum" and "utilization" were shown to exhibit the highest correlation level. Third, by conducting a cluster analysis with "education" as the keyword, five groups were formed: "curriculum," "programming," "student," "improvement," and "information." These results indicate that practical research necessary for ICT education can be conducted by analyzing ICT education trends and identifying trends.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.3 no.1
• /
• pp.48-69
• /
• 2001

A lot of clones of the genus Dioscorea have been introduced from some tropical and subtropical regions since 1997. In 33 clones of water yams (Dioscorea alata L.), some morphological characteristics were investigated at the field. Variation ranges of the total weight and tuber number per stump were within the ranges from 90 to 2,147 g with an average of 610 g ; and 1.3-4.7 with an average of 2.8, respectively. The color tones observed on the tuber-flesh were sorted into 3 color-categories, i.e., white, pale brown and pale purple, and those on leaves were sorted into 3 color-categories, i.e., green, heavy green and purplish green. Intraspecific genetic relationship of 19 variation types of the Yam classified by their external morphological characteristics such as leaf and tuber shape was assessed by DNA using random and specific primers. Twenty two out of 113 primers (100 random[10-mer] primers, two 15 mer [M13 core sequence, and (GGAT)4 sequence]) had been used in PCR-amplification. Only 12 primers, however, were successful in DNA amplification in all of the analyzed plants, resulting in 93 randomly and specifically amplified DNA fragments. The analyzed taxa showed very high polymorphisms(69 bands, 71.0%), allowing individual taxon to be identified based on DNA fingerprinting. Monomorphic bands among total amplified DNA bands of each primer was low under the 50%. Similarity indices between accessions were computed from PCR(polymerase chain reaction) data, and genetic relationships among intraspecific variations were closely related at the levels ranging from 0.66 to 0.90.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.2
• /
• pp.305-318
• /
• 2023

The complexity of software products led many manufacturers to stitch open-source software for composing a product. Using open-source help reduce the development cost, but the difference in the different development life cycles makes it difficult to keep the product up-to-date. For this reason, even the patches for known vulnerabilities are not adopted quickly enough, leaving the entire product under threat. Existing studies propose to use binary differentiation techniques to determine if a product is left vulnerable against a particular vulnerability. Despite their effectiveness in finding real-world vulnerabilities, they often fail to locate the evidence of a vulnerability if it is a small function that usually is inlined at compile time. This work presents our tool FunRank which is designed to identify the short functions. Our experiments using synthesized and real-world software products show that FunRank can identify the short, inlined functions that suggest that the program is left vulnerable to a particular vulnerability.

• Korean Journal of Construction Engineering and Management
• /
• v.24 no.2
• /
• pp.88-97
• /
• 2023

The purpose of this study is to forecast future changes in the construction market following the reorganization of the construction production system by analyzing the possible market size in which general contractors and specialty contractors may participate in each other, and by carrying out a survey. The ratio of correlation between general construction and specialty construction industries was derived by analyzing the relevance of work area of general contractors and specialty contractors, the similarity of registration standards, and the market in which general contractors and specialty contractors may be able to mutually participate. In order to overcome the limitation of previous studies which analyze the changes in construction market based on the statistical data, and to analyze in more detail the impact of reorganization of construction production system from market participants' view, a survey targeting general contractors and specialty contractors for their willingness and method of participating in the mutual market was conducted. As a result of the survey, it was found that 52% of general contractors were willing to participate in the specialized construction market and 55.1% of specialty contractors were willing to participate in the general construction market. It was found that there was a high willingness to participate in the earthworks, reinforced concrete works, facility maintenance and management, water and sewage facility works, and interior works, and high competition is expected for projects with a scale of 500 million to less than 3 billion won. Through this study, it will be possible for general and specialty contractors to understand the changes in the construction market due to the reorganization of the construction industry production system, and to respond effectively to these changes.

• Safety and Health at Work
• /
• v.13 no.4
• /
• pp.493-499
• /
• 2022

Background: The purpose of this study is to construct a job-exposure matrix for lead that accounts for industry and work processes within industries using a nationwide exposure database. Methods: We used the work environment measurement data (WEMD) of lead monitored nationwide from 2015 to 2016. Industrial hygienists standardized the work process codes in the database to 37 standard process and extracted key index words for each process. A total of 37 standardized process codes were allocated to each measurement based on an automated key word search based on the degree of agreement between the measurement information and the standard process index. Summary statistics, including the arithmetic mean, geometric mean, and 95th percentile level (X95), was calculated according to industry, process, and industry process. Using statistical parameters of contrast and precision, we compared the similarity of exposure groups by industry, process, and industry process. Results: The exposure intensity of lead was estimated for 583 exposure groups combined with 128 industry and 35 process. The X95 value of the "casting" process of the "manufacture of basic precious and non-ferrous metals" industry was 53.29 ㎍/m³, exceeding the occupational exposure limit of 50 ㎍/m³. Regardless of the limitation of the minimum number of samples in the exposure group, higher contrast was observed when the exposure groups were by industry process than by industry or process. Conclusion: We evaluated the exposure intensities of lead by combination of industry and process. The results will be helpful in determining more accurate information regarding exposure in lead-related epidemiological studies.

• Korean Journal of Environmental Biology
• /
• v.41 no.1
• /
• pp.60-88
• /
• 2023

This study was conducted to investigate the vertical distribution and vascular plants in the Gakho mountain. Form the results of three field surveys from May 2022 to September 2022, a total of 478 total taxa, representing 426 species, 11 subspecies, 35 varieties, four forms, and two hybrids were identified, which were categorized in 282 genera and 94 families. We identified the elevational distribution ranges of 398 taxa of vascular plants. Among them, 19 taxa were endemic to Korea, one taxon was identified as a rare plant. The floristic target plants amounted to 72 taxa, specifically two taxa of grade V, two taxa of grade IV, 16 taxa of grade III, 27 taxa of grade II, and 25 taxa of grade I. Further, 71 taxa were identified as northern lineage plants. A total of 19 taxa of alien plants were identified, with a Naturalized Index of 4.0%, an Urbanization Index of 6.6%, and three plants that disturbed the ecosystem. The result of analyzing the pattern of species richness showed a reversed hump shape with minimum richness at mid-high elevation. A cluster analysis showed a high degree of similarity between adjacent elevation sections that are geographically adjacent with similar habitat environments. Warmth index in the Gakho mountain ranged from 57.2℃·month to 84.2℃·month. Our results provide basic data on vascular plants and valuable information on elevational distribution ranges of current plant species in the Gakho mountain, which could serve as a baseline for comparison of the shifts in elevation under future climate change.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.2
• /
• pp.95-107
• /
• 2023

The purpose of this study is to investigate the impact of export promotion programs (EPPs) on the export performance of small- and medium-sized enterprises (SMEs), with a specific focus on the influence of EPPs for promising SMEs in the export market. Using data on SMEs provided by the Industrial Bank of Korea (IBK), we conducted a fixed-effects model analysis from 2016 to 2019. Our study shows that EPPs have a positive and significant relationship with export intensity. Further analysis reveals that SMEs utilizing the financing support system provided by EPPs tend to improve their export growth and financial performance relative to their counterparts. While EPPs can assist SMEs with their internationalization efforts, their similarity and redundancy are recognized as potential limitations. This study complements the existing literature that has mainly focused on surveys and cross-sectional analysis by specifying the research subject to promising SMEs in export, and analyzing the effects of the export promotion program supported by IBK Industrial Bank. The results of this study are expected to provide implications for improving SMEs' export capabilities.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.6
• /
• pp.239-246
• /
• 2017

This paper compares the speech signal parameters between Korean and Chinese for Korean pronunciation /ㄹ/, which is caused many errors by Chinese leaners. Allophones of /ㄹ/ in Korean is divided into lateral group and tap group. It has been investigated the reasons for these errors by studying the similarity and the differences between Korean /ㄹ/ pronunciation and its corresponding Chinese pronunciation. In this paper, for the purpose of comparison the speech signal parameters such as energy, waveform in time domain, spectrogram in frequency domain, pitch based on ACF, Formant frequencies are used. From the phonological perspective the speech signal parameters such as signal energy, a waveform in the time domain, a spectrogram in the frequency domain, the pitch (F0) based on autocorrelation function (ACF), Formant frequencies (f1, f2, f3, and f4) are measured and compared. The data, which are composed of the group of Korean words by through a philological investigation, are used and simulated in this paper. According to the simulation results of the energy and spectrogram, there are meaningful differences between Korean native speakers and Chinese leaners for Korean /ㄹ/ pronunciation. The simulation results also show some differences even other parameters. It could be expected that Chinese learners are able to reduce the errors considerably by exploiting the parameters used in this paper.

• Animal Bioscience
• /
• v.36 no.10
• /
• pp.1517-1529
• /
• 2023

Objective: The objective of this study was to investigate the phylogenetic and expression analysis of the angiopoietin-like (ANGPTL) gene family and their role in lipid metabolism in pigs. Methods: In this study, the amino acid sequence analysis, phylogenetic analysis, and chromosome adjacent gene analysis were performed to identify the ANGPTL gene family in pigs. According to the body weight data from 60 Jinhua pigs, different tissues of 6 pigs with average body weight were used to determine the expression profile of ANGPTL1-8. The ileum, subcutaneous fat, and liver of 8 pigs with distinct fatness were selected to analyze the gene expression of ANGPTL3, ANGPTL4, and ANGPTL8. Results: The sequence length of ANGPTLs in pigs was between 1,186 and 1,991 bp, and the pig ANGPTL family members shared common features with human homologous genes, including the high similarity of the amino acid sequence and chromosome flanking genes. Amino acid sequence analysis showed that ANGPTL1-7 had a highly conserved domain except for ANGPTL8. Phylogenetic analysis showed that each ANGPTL homologous gene shared a common origin. Quantitative reverse-transcription polymerase chain reaction analysis showed that ANGPTL family members had different expression patterns in different tissues. ANGPTL3 and ANGPTL8 were mainly expressed in the liver, while ANGPTL4 was expressed in many other tissues, such as the intestine and subcutaneous fat. The expression levels of ANGPTL3 in the liver and ANGPTL4 in the liver, intestine and subcutaneous fat of Jinhua pigs with low propensity for adipogenesis were significantly higher than those of high propensity for adipogenesis. Conclusion: These results increase our knowledge about the biological role of the ANGPTL family in this important economic species, it will also help to better understand the role of ANGPTL3, ANGPTL4, and ANGPTL8 in lipid metabolism of pigs, and provide innovative ideas for developing strategies to improve meat quality of pigs.