• 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.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.1
• /
• pp.1-8
• /
• 2021

In the political field of news articles, there are polarized and biased characteristics such as conservative and liberal, which is called political bias. We constructed keyword-based dataset to classify bias of news articles. Most embedding researches represent a sentence with sequence of morphemes. In our work, we expect that the number of unknown tokens will be reduced if the sentences are constituted by subwords that are segmented by the language model. We propose a document embedding model with subword tokenization and apply this model to SVM and feedforward neural network structure to classify the political bias. As a result of comparing the performance of the document embedding model with morphological analysis, the document embedding model with subwords showed the highest accuracy at 78.22%. It was confirmed that the number of unknown tokens was reduced by subword tokenization. Using the best performance embedding model in our bias classification task, we extract the keywords based on politicians. The bias of keywords was verified by the average similarity with the vector of politicians from each political tendency.

• Animal Systematics, Evolution and Diversity
• /
• v.36 no.4
• /
• pp.354-362
• /
• 2020

A common snapping turtle Chelydra serpentina inhabiting North America is internationally protected as an endangered species. It is known that the individuals of common snapping turtles were imported to South Korea as pets, and after being abandoned, some inhabit the natural ecosystem of South Korea like wild animals. No genetic survey has yet been performed for the common snapping turtles imported to South Korea. Hereby, cytochrome c oxidase subunit I (COI) information, which is 594 bp long, was determined for a total of 16 C. serpentina individuals, of which one was found in nature, twelve legally imported and their descendants, and the other three were provided from the Kansas Herpetological Society, USA. The obtained data were combined with thirteen COI sequences of C. serpentina retrieved from NCBI GenBank for the subsequent population genetic analyses. The results showed that there exist five haplotypes with high sequence similarity (only three parsimoniously informative sites). In the TCS and phylogenetic analyses, all the examined C. serpentina samples coincidently formed a strong monoclade with those collected mostly from Kansas State, USA, indicating that the imported ones to South Korea are from the central North America. In addition, there found the amino acid changes and the high degree of nucleotide sequence differences between C. serpentina and C. rossignoni with some important morphological characters. It is expected that the present results could provide an important framework for systematic management and control of exotic snapping turtles imported and released to nature of South Korea.

• Journal of Marine Life Science
• /
• v.6 no.2
• /
• pp.97-105
• /
• 2021

Tegillarca granosa, is one of the most important fishery resources throughout Asia. However, due to industrialization factories, marine environmental pollution, and global warming, the marine fishery production has drop sharply. In order to understand the genetic factors of the blood clam, which is a major fishery resource on the southern coast of Korea, the whole genome of blood clam was studied. The assembled genome of T. granosa was 915.4 Mb, and 19 chromosomes were identified. 25,134 genes were identified, and 22,745 genes were functionally annotated. As a result of performing gene gain and loss analysis between the blood clam genome and eight other types of shellfish, it was confirmed that 725 gene groups were expanded, and 479 gene groups were contracted. The homeobox gene cluster of blood clam showed a well-preserved genetic structure within lophotrochozoan ancestor. T. granosa genome showed high similarity between three hemoglobin genes with Scarpharca broughtonii. The blood clam genome will provide information for the genetic and physiological characteristics of blood clam adaptation, evolution, and the development of aquaculture industry.

• Journal of Life Science
• /
• v.31 no.7
• /
• pp.671-676
• /
• 2021

A cDNA encoding the protein lethal (2) essential for life [l(2)efl] was cloned from Gryllus bimaculatus and named GBl(2)efl. This protein is composed of 189 amino acids, including an N-glycosylation site and 15 phosphorylation sites. Its predicted molecular mass is 21.19 kDa, with a theoretical isoelectric point of 6.2. The secondary structure of GBl(2)efl was predicted from the identification of random coils (56.08%), alpha helices (22.22%), extended strands (17.99%), and beta turns (3.7%) through sequence analyses. A homology analysis revealed that GBl(2)efl exhibited a high similarity with other species at the amino acid level, ranging from 52% to 69%. While GBl(2)efl mRNA expression was higher in the dorsal longitudinal flight muscle following a three-day starvation and in the Malpighian tubules following a one-day starvation, no changes in expression were detected in other tissues. Furthermore, tunicamycin-induced endoplasmic reticulum (ER) stress resulted in an approximately 1.8-fold higher expression in the fat body compared with the wild type.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.6
• /
• pp.1137-1144
• /
• 2022

In this study, an artificial intelligence(AI) was developed to help with facial expression practice in order to express emotions. The developed AI used multimodal inputs consisting of sentences and facial images for deep neural networks (DNNs). The DNNs calculated similarities between the emotions predicted by the sentences and the emotions predicted by facial images. The user practiced facial expressions based on the situation given by sentences, and the AI provided the user with numerical feedback based on the similarity between the emotion predicted by sentence and the emotion predicted by facial expression. ResNet34 structure was trained on FER2013 public data to predict emotions from facial images. To predict emotions in sentences, KoBERT model was trained in transfer learning manner using the conversational speech dataset for emotion classification opened to the public by AIHub. The DNN that predicts emotions from the facial images demonstrated 65% accuracy, which is comparable to human emotional classification ability. The DNN that predicts emotions from the sentences achieved 90% accuracy. The performance of the developed AI was evaluated through experiments with changing facial expressions in which an ordinary person was participated.

• 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.

• Economic and Environmental Geology
• /
• v.55 no.6
• /
• pp.571-582
• /
• 2022

In this study, the raw material and tempers of bricks used in three brick tombs built in Gongju, during the Ungjin period of Baekje were investigated. The royal tomb of King Muryeong, the 6th tomb in the royal tombs, and Kyochonri brick tomb remained in Gongju and the bricks of each site had different shape and physical properties despite their similarity in raw materials. As the results of the mineralogical and microstructural analysis, the bricks of the royal tombs were made of refined raw materials, and were infrequently added crushed bricks(grogs) as a tempering material. On the other hand, thick and elongated pores of bricks from the Kyochonri brick tomb were frequently found, and the remains of plant carbonization are observed in their microstructures. Since the pores are mainly distributed in a thickness of 0.3 to 1 mm, it is estimated that bricks were produced by adding a certain size of the plant to refined soil, and grogs also were added as a tempering material. In particular, it was found that adding plants and grogs in raw materials of bricks caused thick pores or cracks in the internal structure. Since the bricks of the Kyochonri brick tomb have internal cracks and low firing temperature, the ultrasonic velocity of the bricks was lower than that of the royal tomb bricks. It means that the mechanical strength of these bricks were relatively low. Accordingly, it is estimated that the tempering materials, firing temperature, and internal structures of bricks can affect durability of the brick, and it can be thought as a difference in the manufacturing technology of brick making.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.11 no.1
• /
• pp.89-96
• /
• 2023

In this paper, a ferrosilicon by-product was evaluated to confirm the feasibility of recycling it as supplementary cementitious material of ordinary Portland cement in concrete. Three different levels of replacement ratio (10 %, 20 % and 30 % of total binder) were applied to find which is the most beneficial to be used as a binder. Ferrosilicon concrete was initially assessed at setting time and compressive strength. Durability was evaluated by the resistance to chloride penetration test(RCPT) and alkali-silica reaction(ASR) with a comparison to silica fume concrete due to their similarity in chemical composition. The porosimetry and X-ray diffraction analysis along with energy dispersive X-ray spectroscopy give information on the microstructural characteristics of the ferrosilicon concrete. It was found that 10 % ferrosilicon concrete has higher strength while 20 %, 30 % have lower strength than OPC concrete. However, chemical resistance to chloride attack is higher when replacement is increased. Compared to silica fume, the durability of ferrosilicon might be less efficient however, it is obviously beneficial than OPC. High SiO₂ content in ferrosilicon results in producing more C-S-H gel which could make denser pore structure. Most of the risk of alkali silica reaction to silicate binders through length change tests was less than 0.2 %, and both mortar using ferrosilicon and silica fume showed better resistance to alkali silica reaction as the substitution rate increased.Reuse of industrial waste rather than producing highly refined additives might reduce environmental load during manufacture and save costs.

• Economic and Environmental Geology
• /
• v.56 no.6
• /
• pp.817-830
• /
• 2023

This study investigates the age of the surficial rocks in the Arunta region using Uranium-Lead (U-Pb) geochronological dating. Rock samples were collected at four locations, Cattle-Water Pass (CP 1610), Gough Dam (GD 1622 and GD 1610), and London-Eye (LE 1601), within the Strangways Metamorphic Complex and crushed by selFragging. Subsequently, the zircon grains were imaged using Cathodoluminescence (CL) analysis and the U-Pb (uranium and lead) isotope ratios and the chrono-stratigraphy were measured. The imaged zircon revealed an anomalous heterogeneous crystal structure. Ellipses of the samples at locations GD1601, CP1610, and GD1622 fall below the intercept indicating the ages produced discordant patterns, whereas LE1601 intersects the Concordia curve at two points, implying the occurrence of an event of significant impact. For the rock sample at CP1610, the estimated mean age is 1742.2 ± 9.2 Ma with mean squared weighted deviation (MSWD) = 0.49 and probability of equivalence of 0.90; 1748 ± 15 Ma - MSWD = 1.02 and probability of equivalence of 0.40 for GD1622; and 1784.4 ± 9.1 Ma with MSWD of 1.09 and probability of equivalence of 0.37 for LE1601. But for samples at GD1601, two different age groups with different means occurred: 1) below the global mean (1792.2 ± 32 Ma) estimated at 1738.2 ± 14 Ma with MSWD of 0.109 and probability of equivalence of 0.95 and 2) above it with mean of 1838.22 ± 14 Ma, MSWD of 1.6 and probability of equivalence of 0.95. Analysis of the zircon grains has shown a discrepancy in the age range between 1700 Ma and 1800 Ma compared to the ASO dated to have occurred between 440 and 300 Ma. Moreover, apparent similarity in age of the core and rim means that the mineral crystallized relatively quickly without significant interruptions and effect on the isotopic system. This may have constraint the timing and extent of geological events that might have affected the mineral, such as metamorphism or hydrothermal alteration.