• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.95-112
• /
• 2021

In university education, the choice of major class plays an important role in students' careers. However, in line with the changes in the industry, the fields of major subjects by department are diversifying and increasing in number in university education. As a result, students have difficulty to choose and take classes according to their career paths. In general, students choose classes based on experiences such as choices of peers or advice from seniors. This has the advantage of being able to take into account the general situation, but it does not reflect individual tendencies and considerations of existing courses, and has a problem that leads to information inequality that is shared only among specific students. In addition, as non-face-to-face classes have recently been conducted and exchanges between students have decreased, even experience-based decisions have not been made as well. Therefore, this study proposes a recommendation system model that can recommend college major classes suitable for individual characteristics based on data rather than experience. The recommendation system recommends information and content (music, movies, books, images, etc.) that a specific user may be interested in. It is already widely used in services where it is important to consider individual tendencies such as YouTube and Facebook, and you can experience it familiarly in providing personalized services in content services such as over-the-top media services (OTT). Classes are also a kind of content consumption in terms of selecting classes suitable for individuals from a set content list. However, unlike other content consumption, it is characterized by a large influence of selection results. For example, in the case of music and movies, it is usually consumed once and the time required to consume content is short. Therefore, the importance of each item is relatively low, and there is no deep concern in selecting. Major classes usually have a long consumption time because they have to be taken for one semester, and each item has a high importance and requires greater caution in choice because it affects many things such as career and graduation requirements depending on the composition of the selected classes. Depending on the unique characteristics of these major classes, the recommendation system in the education field supports decision-making that reflects individual characteristics that are meaningful and cannot be reflected in experience-based decision-making, even though it has a relatively small number of item ranges. This study aims to realize personalized education and enhance students' educational satisfaction by presenting a recommendation model for university major class. In the model study, class history data of undergraduate students at University from 2015 to 2017 were used, and students and their major names were used as metadata. The class history data is implicit feedback data that only indicates whether content is consumed, not reflecting preferences for classes. Therefore, when we derive embedding vectors that characterize students and classes, their expressive power is low. With these issues in mind, this study proposes a Net-NeuMF model that generates vectors of students, classes through network analysis and utilizes them as input values of the model. The model was based on the structure of NeuMF using one-hot vectors, a representative model using data with implicit feedback. The input vectors of the model are generated to represent the characteristic of students and classes through network analysis. To generate a vector representing a student, each student is set to a node and the edge is designed to connect with a weight if the two students take the same class. Similarly, to generate a vector representing the class, each class was set as a node, and the edge connected if any students had taken the classes in common. Thus, we utilize Node2Vec, a representation learning methodology that quantifies the characteristics of each node. For the evaluation of the model, we used four indicators that are mainly utilized by recommendation systems, and experiments were conducted on three different dimensions to analyze the impact of embedding dimensions on the model. The results show better performance on evaluation metrics regardless of dimension than when using one-hot vectors in existing NeuMF structures. Thus, this work contributes to a network of students (users) and classes (items) to increase expressiveness over existing one-hot embeddings, to match the characteristics of each structure that constitutes the model, and to show better performance on various kinds of evaluation metrics compared to existing methodologies.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.16 no.2
• /
• pp.106-115
• /
• 2011

The aim of this study is to assess the importance of ballast water discharge as a vector for the introduction of exotic species into Pusan and Daesan Ports, Korea. We also examined to understand the impacts of environmental factors on the survival success of introduced species by ship's ballast water in laboratory experiments. Seven ship's ballast water originated from the coastal water of China (Taicang, Ningbo and Jinshan), Japan (Tokuyama, Moji and Akita), and Singapore. According to PCA (principal components analysis) analysis, environmental factor in the each ballast and shipside waters were different by bioregion. Based on cluster analysis, the phytoplankton community structures were distinguished for ballast water origin. Most of the major taxonomic groups were diatoms and, the others were dinoflagellate, silcoflagellate and several fresh-waters species. In particular, species number and standing crops of phytoplankton in the ballast tanks decreased with the increasing age ofballast water(r = -0.35 for standing crop; r = -0.63 for species number). In the laboratory study, although phytoplankton in ballast water treatment did not survive even in optimal temperature, the in vivo fluorescence of phytoplankton viability increased under the nutrient typical of shipside water and F/2 medium at $15^{\circ}C$ and $20^{\circ}C$. The diatoms species such as Skeletonema costatum and Thalassiosira pseudonana in ballast water were successfully regrown. On the salinity gradient experiments for Shui Shan (2) vessel, several freshwater species, brackish and marine species were successfully adapted. Of these, S.costatum was able to tolerate a wide range of salinities (10 to 30 psu) and its species-specific viability was suitable for colonization.

• Journal of Life Science
• /
• v.21 no.8
• /
• pp.1149-1155
• /
• 2011

Myostatin (MSTN) belongs to the transforming growth factor-${\beta}$ superfamily or growth and differentiation factor 8 (GDF-8), and functions as a negative regulator of skeletal muscle development and growth. Previous studies in mammals have suggested that myostatin knock-out increased muscle mass and decreased fat content compared to those of the wide type. Recently, several studies on myostatin have beenconducted on the block myostatin signal pathway with myostatin antagonists and the MSTN regulation with RNAi to control myostatin function. This study was performed to analyze growth and muscle alteration of Oncorhychus masou by treatment with recombinant myostatin prodomains derived from fish. We designed myostatin prodomains derived from P. olivaceus (pMALc2x-poMSTNpro) and S. schlegeli (pMALc2x-sMSTNpro) in a pMALc2x expression vector, and then purified the recombinant proteins using affinity chromatography. The purified recombinant proteins were treated in O. masou through an immersion method. Recombinant protein treated groups did not show a significant difference in weight, protein, or lipid composition compared to the control. However, there was a difference in the average number and area for histological analyses in the muscle fiber. At twelve and twenty-two weeks from the initial treatment, there were differences in averagefiber number and area between the 0.05 mg/l treated-group and the control, but the numbers were similar to those of the control during the same time period. At twelve weeks, however, 0.2 mg/l treated-group had an increase in average fiber number and decrease in average fiber area compared to the control. At twenty-two weeks, the pMALc2x-sMSTNpro 0.2 mg/l treated-group was induced and showed a decrease in average fiber number and increase in average fiber area. The results between twelve and twenty-two weeks showed that the fiber numbers had decreased, whereas average fiberarea had increased due to sMSTNpro. It is understood that the sMSTNpro induced only hyperplasia at twelve weeks, after which it induced hypertrophy. Recombinant myostatin prodomains derived from fish may induce hyperplasia and hypertrophy in O. masou depending upon the time that has elapsed.

• Proceedings of the Korean Society of Plant Pathology Conference
• /
• 1995.06b
• /
• pp.77-96
• /
• 1995

To obtain basic informations for the improvement of seed potato production in Korea, some etiological properties of potato virus Y(PVY) distributed in the major seed potato production area(Daekwanryeong) were characterized, and the nucleotide and amino acid sequences of the coat protein gene of the PVY strains isolated were analyzed. PVY strains in Daekwonryeong, an alpine area, were identified to be two strains, PVYo and PVYN by symptoms of indicator plants, and their distribution in potato fields was similar. Major symptom on potato varieties by PVY was grouped as either mosaic alone or mosaic accompanied with veinal necrosis in the lower leaves. The symptom occurrence of the two symptoms was similar with Irish Cobbler, but Superior showed a higher rate of mosaic symptom than the other. The PVY strain which was isolated from potato cv. Superior showing typical mosaic symptoms produced symptoms of PVY-O on the indicator plants of Chenopodium amaranticolor, Nicotiana tabacum cv. Xanthi nc and Physalis floridana, but no symptom o Capsicum annum cv. Ace. Moreover, results from the enzyme-linked immunosorbent assay with monoclonal and polyclonal antibodies showed that the isolated PVY reacts strongly with PYV-O antibodies but does not react specifically with PVY-T antibodies. The purified virus particles were flexious with a size of 730$\times$11nm. On the basis of the above characteristics, the strain was identified to be a PVY-O and named as of PVY-K strain. The flight of vector aphids was observed in late May, however, the first occurrence of infected plants was in mid June with the bait plants surrounded with PVY-infected potato plants and early July with the bait plants surrounded with PVY-free potato plants. PVY infection rates by counting symptoms on bait plants (White Burley) were 1.1% with the field surrounded with PVY-free potato plants and 13.7% the fields surrounded with PVY-infected potato plants, showing the effect of infection pressure. The propagated PVY-K strain on tobacco(N. sylvestris) was purified, and the RNA of the virus was extracted by the method of phenol extraction. The size of PVY-K RNA was measured to be 9, 500 nucleotides on agarose gel electrophoresis. The double-stranded cDNAs of PVY-K coat protein(CP) gene derived by the method of polymerase chain reaction were transformed into the competent cells of E. coli JM 109, and 2 clones(pYK6 and pYK17) among 11 clones were confirmed to contain the full-length cDNA. Purified plasmids from pYK17 were cut with Sph I and Xba I were deleted with exonuclease III and were used for sequencing analysis. The PVY-K CP gene was comprised of 801 nucleotides when counted from the clevage site of CAG(Gln)-GCA(Ala) to the stop codon of TGA and encoded 267 amino acids. The molecular weight of the encoded polypeptides was calculated to be 34, 630 daltons. The base composition of the CP gene was 33.3% of adenine, 25.2% of guanine, 20.1% of cytosine and 21.4% of uracil. The polypeptide encoded by PVY-K CP gene was comprised of 22 alanines, 20 threonines, 19 glutamic acids and 18 glycines in order. The homology of nucleotide sequence of PVY-K CP gene with those of PVY-O(Japan), PVY-T(Japan), PVY-TH(Japan), PVYN(the Netherlands), and PVYN(France) was represented as 97.3%, 88.9%, 89.3%, 89.6% and 98.5%, respectively. The amino acid sequence homology of the polypeptide encoded by PVY-K CP gene with those encoded by viruses was represented as 97.4%, 92.5%, 92.9%, 92.9%, and 98.5%, respectively.