• Advanced Industrial SCIence
• /
• v.3 no.2
• /
• pp.8-16
• /
• 2024

This paper shows the system of drug classification, the goal of this is to foretell the apt drug for the patients based on their demographic and physiological traits. The dataset consists of various attributes like Age, Sex, BP (Blood Pressure), Cholesterol Level, and Na_to_K (Sodium to Potassium ratio), with the objective to determine the kind of drug being given. The models used in this paper are K-Nearest Neighbors (KNN), Logistic Regression and Random Forest. Further to fine-tune hyper parameters using 5-fold cross-validation, GridSearchCV was used and each model was trained and tested on the dataset. To assess the performance of each model both with and without hyper parameter tuning evaluation metrics like accuracy, confusion matrices, and classification reports were used and the accuracy of the models without GridSearchCV was 0.7, 0.875, 0.975 and with GridSearchCV was 0.75, 1.0, 0.975. According to GridSearchCV Logistic Regression is the most suitable model for drug classification among the three-model used followed by the K-Nearest Neighbors. Also, Na_to_K is an essential feature in predicting the outcome.

• Journal of The Korean Association For Science Education
• /
• v.28 no.6
• /
• pp.579-591
• /
• 2008

Recently, there have been studies about Typically- Perceived-Situations (TPSs) and about critical examples as a way to understand students' preconceptions with context. TPS is a situation arising immediately in one's mind when he or she thinks about the concept, while a critical example is an example that becomes the most helpful in learning the concept. We might explore how the context is involved in the process of students' conceptual understanding by examining TPSs and critical examples together. This study analyzed, through questionnaires and interviews, the characteristics of TPSs and those of critical examples that secondary students hold about 'force' and 'mechanical energy conversion.' Students' TPSs and critical examples showed different characteristics according to the concept. In a case of force that is related to everyday life, there were various situations as TPSs and critical examples. Unlike force, there were a few situations as TPSs and critical examples such as a falling ball in the case of mechanical energy conversion. Students tended to regard situations that are usually experienced and understood easily as TPSs or critical examples. On the basis of the results of this study, it is concluded that it would be a good strategy to teach science concepts for teachers to start with the TPS of a concept, to introduce the concept, and then to expose the attributes of the concept with critical examples.

• Economic and Environmental Geology
• /
• v.57 no.1
• /
• pp.51-71
• /
• 2024

Seismic exploration is one of the widely used geophysical exploration methods with various applications such as resource development, geotechnical investigation, and subsurface monitoring. It is essential for interpreting the geological characteristics of subsurface by providing accurate images of stratum structures. Typically, geological features are interpreted by visually analyzing seismic sections. However, recently, quantitative analysis of seismic data has been extensively researched to accurately extract and interpret target geological features. Seismic attribute analysis can provide quantitative information for geological interpretation based on seismic data. Therefore, it is widely used in various fields, including the analysis of oil and gas reservoirs, investigation of fault and fracture, and assessment of shallow gas distributions. However, seismic attribute analysis is sensitive to noise within the seismic data, thus additional noise attenuation is required to enhance the accuracy of the seismic attribute analysis. In this study, four kinds of seismic noise attenuation methods are applied and compared to mitigate random noise of poststack seismic data and enhance the attribute analysis results. FX deconvolution, DSMF, Noise2Noise, and DnCNN are applied to the Youngil Bay high-resolution seismic data to remove seismic random noise. Energy, sweetness, and similarity attributes are calculated from noise-removed seismic data. Subsequently, the characteristics of each noise attenuation method, noise removal results, and seismic attribute analysis results are qualitatively and quantitatively analyzed. Based on the advantages and disadvantages of each noise attenuation method and the characteristics of each seismic attribute analysis, we propose a suitable noise attenuation method to improve the result of seismic attribute analysis.

• Information Systems Review
• /
• v.25 no.1
• /
• pp.111-128
• /
• 2023

With the development of artificial intelligence technology, interest in data-based product preference estimation and personalized recommender systems is increasing. However, if the recommendation is not suitable, there is a risk that it may reduce the purchase intention of the customer and even extend to a huge financial loss due to the characteristics of the financial product. Therefore, developing a recommender system that comprehensively reflects customer characteristics and product preferences is very important for business performance creation and response to compliance issues. In the case of financial products, product preference is clearly divided according to individual investment propensity and risk aversion, so it is necessary to provide customized recommendation service by utilizing accumulated customer data. In addition to using these customer behavioral characteristics and transaction history data, we intend to solve the cold-start problem of the recommender system, including customer demographic information, asset information, and stock holding information. Therefore, this study found that the model proposed deep learning-based collaborative filtering by deriving customer latent preferences through characteristic information such as customer investment propensity, transaction history, and financial product information based on customer transaction log records was the best. Based on the customer's financial investment mechanism, this study is meaningful in developing a service that recommends a high-priority group by establishing a recommendation model that derives expected preferences for untraded financial products through financial product transaction data.

• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.1-13
• /
• 2015

As opinion mining in big data applications has been highlighted, a lot of research on unstructured data has made. Lots of social media on the Internet generate unstructured or semi-structured data every second and they are often made by natural or human languages we use in daily life. Many words in human languages have multiple meanings or senses. In this result, it is very difficult for computers to extract useful information from these datasets. Traditional web search engines are usually based on keyword search, resulting in incorrect search results which are far from users' intentions. Even though a lot of progress in enhancing the performance of search engines has made over the last years in order to provide users with appropriate results, there is still so much to improve it. Word sense disambiguation can play a very important role in dealing with natural language processing and is considered as one of the most difficult problems in this area. Major approaches to word sense disambiguation can be classified as knowledge-base, supervised corpus-based, and unsupervised corpus-based approaches. This paper presents a method which automatically generates a corpus for word sense disambiguation by taking advantage of examples in existing dictionaries and avoids expensive sense tagging processes. It experiments the effectiveness of the method based on Naïve Bayes Model, which is one of supervised learning algorithms, by using Korean standard unabridged dictionary and Sejong Corpus. Korean standard unabridged dictionary has approximately 57,000 sentences. Sejong Corpus has about 790,000 sentences tagged with part-of-speech and senses all together. For the experiment of this study, Korean standard unabridged dictionary and Sejong Corpus were experimented as a combination and separate entities using cross validation. Only nouns, target subjects in word sense disambiguation, were selected. 93,522 word senses among 265,655 nouns and 56,914 sentences from related proverbs and examples were additionally combined in the corpus. Sejong Corpus was easily merged with Korean standard unabridged dictionary because Sejong Corpus was tagged based on sense indices defined by Korean standard unabridged dictionary. Sense vectors were formed after the merged corpus was created. Terms used in creating sense vectors were added in the named entity dictionary of Korean morphological analyzer. By using the extended named entity dictionary, term vectors were extracted from the input sentences and then term vectors for the sentences were created. Given the extracted term vector and the sense vector model made during the pre-processing stage, the sense-tagged terms were determined by the vector space model based word sense disambiguation. In addition, this study shows the effectiveness of merged corpus from examples in Korean standard unabridged dictionary and Sejong Corpus. The experiment shows the better results in precision and recall are found with the merged corpus. This study suggests it can practically enhance the performance of internet search engines and help us to understand more accurate meaning of a sentence in natural language processing pertinent to search engines, opinion mining, and text mining. Naïve Bayes classifier used in this study represents a supervised learning algorithm and uses Bayes theorem. Naïve Bayes classifier has an assumption that all senses are independent. Even though the assumption of Naïve Bayes classifier is not realistic and ignores the correlation between attributes, Naïve Bayes classifier is widely used because of its simplicity and in practice it is known to be very effective in many applications such as text classification and medical diagnosis. However, further research need to be carried out to consider all possible combinations and/or partial combinations of all senses in a sentence. Also, the effectiveness of word sense disambiguation may be improved if rhetorical structures or morphological dependencies between words are analyzed through syntactic analysis.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.34 no.2
• /
• pp.27-34
• /
• 2016

The results of investigation on the spatial composition and landscape characteristics of Shimwon-pavilion garden built and enjoyed by Jo Byeong-sun in 1937 during the period of Japanese colonialism based on 'Shimwon-pavilion Soosukgii(水石記)' and 'Shimwon-pavilion Poem of 25 Sceneries(二十五詠)' contained in 'Anthology of Giheon(寄軒)' are as follows. 1. Shimwon-pavilion garden is assumed as Byeol-Seo garden based on the planning background and contents of Gimun and the observations on spot. By its location, it is classified as 'Planted forest' with a pine forest in the north and 'Byeol-Seo of mooring type' with Guyacheon flowing in the garden. It is about 400m away from the main house in the straight-line distance. 2. The meaning and attributes of reclusiveness are well represented in the 'screening structures' all around Shimwon-pavilion garden with Hakrimsan, a Gasan(假山) in the north, vines on Chwibyeong(翠屛) in the east and west, Eunbyeong(隱屛) of stone walls along with Guyacheon in the south, which shows the spirit of Giheon who adored the Taoistic life. 3. Shimwon-pavilion garden, located in the Songrimsa, a temple of thousand years, is a place of consilience where Buddhism was accepted, Taoistic life was pursued with Tao Yuan-ming's philosophy regarding rural areas and romantic sensibilities of Li Po, called poem master(詩仙), the confucian values of Zhu Xi were realized. Giheon intended to build and enjoy this place as a microcosm and shelther where he unfolded his own view of learning and cultivated his mind. 4. 25 sceneries on Shimwon-pavilion consist of 5 sceneries in the space of pavilion(architecture) and 20 sceneries in the outer garden. First, 5 sceneries consist of ancillary rooms for various uses, including Jeongunru, Amsushil, Wiryujae, Iyeoldang, and Jeong-Gak Shimwon-pavilion embracing them, which shows that Shimwon-pavilion is a place to foster younger students. And 20 scenary is divided into 9 sceneries on the natural spaces and 11 artificially created facilities. 9 sceneries are engraved on the rocks as described in 'Seokgyeonggi'. 5. 4 sceneries of the indoor scenery lexemes(亭閣 心遠亭 怡悅堂 停雲樓 闇修室) were intended to be recognized by the framed pictures, 5 places among the scenery lexemes in garden(龜巖 醒石 隱屛 兩忘臺 東槃) by letters carved on the rocks, and 8 places(君子沼 杞泉 天光雲影橋 芳園 槐岡 柳堤 石扉 東翠屛) by sign stones, but signs of 8 sceneries are not currently identified because they have been be swept away and demolished. 6. A variety of plant landscapes with various meanings and water landscape with various types are contained in 25 sceneries - Sophora symbolizing a tree for scholar in Gehgang(槐岡), Willow symbolizing Tao Yuanming and continued vitality in Yooje(柳堤), Boxthorn symbolizing family togetherness in spring(杞泉), vines and herbal plants and waterfalls(隱瀑), shallow pond(君子沼), pond(湯池), water hole(杞泉), water flowing in the middle of rock(盤陀石), water flowing between the rocks(水口巖). 7. While Shimwon-pavilion garden is a garden near the water, the active involvements with 11 sceneries directly built is distinguished. The other pavilion gardens are faithful in engraving the names by setting the scenery lexemes of the nature-oriented Gyeong(景) and Gok(曲) near and far, but Shimwon-pavilion garden is a garden for active learning(修景) with the spaces built to match with the beautiful nature and to show the depths of space off.

• Journal of The Korean Association For Science Education
• /
• v.15 no.2
• /
• pp.173-184
• /
• 1995

The purpose of this study was to analyse the problems of 'Science Inquiry Experiment Contest(SIEC)' which was one of 8 programs of 'The 2nd Student Science Inquiry Olympic Meet(SSIOM)'. The results and conclusions of this study were as follows: 1. It needs to reconsider the role of practical work within science experiment because practical work skills form one of the mainstays in current science. But the assessment of students' laboratory skills in the contest was made little account of. It is necessary to remind of what it means to be 'good at science'. There are two aspects: knowing and doing. Both are important and, in certain respects, quite distinct. Doing science is more of a craft activity, relying more on craft skill and tacit knowledge than on the conscious application of explicit knowledge. Doing science is also divided into two aspects, 'process' and 'skill' by many science educators. 2. The report's and checklist's assessment items were overlapped. Therefore it was suggested that the checklist assessment items were set limit to the students' acts which can't be found in reports. It is important to identify those activities which produce a permanent assessable product, and those which do not. Skills connected with recording and reporting are likely to produce permanent evidence which can be evaluated after the experiment. Those connected with manipulative skills involving processes are more ephemeral and need to be assessed as they occur. The division of student's experimental skills will contribute to the accurate assess of student's scientific inquiry experimental ability. 3. There was a wide difference among the scores of one participant recorded by three evaluators. This means that there was no concrete discussion among the evaluators before the contest. Despite the items of the checklists were set by preparers of the contest experiments, the concrete discussions before the contest were necessary because students' experimental acts were very diverse. There is a variety of scientific skills. So it is necessary to assess the performance of individual students in a range of skills. But the most of the difficulties in the assessment of skills arise from the interaction between measurement and the use. To overcome the difficulties, not only must the mark needed for each skill be recorded, something which all examination groups obviously need, but also a description of the work that the student did when the skill was assessed must also be given, and not all groups need this. Fuller details must also be available for the purposes of moderation. This is a requirement for all students that there must be provision for samples of any end-product or other tangible form of evidence of candidates' work to be submitted for inspection. This is rather important if one is to be as fair as possible to students because, not only can this work be made available to moderators if necessary, but also it can be used to help in arriving at common standards among several evaluators, and in ensuring consistent standards from one evaluator over the assessment period. This need arises because there are problems associated with assessing different students on the same skill in different activities. 4. Most of the students' reports were assessed intuitively by the evaluators despite the assessment items were established concretely by preparers of the experiment. This result means that the evaluators were new to grasp the essence of the established assessment items of the experiment report and that the students' assessment scores were short of objectivity. Lastly, there are suggestions from the results and the conclusions. The students' experimental acts which were difficult to observe because they occur in a flash and which can be easily imitated should be excluded from the assessment items. Evaluators are likely to miss the time to observe the acts, and the students who are assessed later have more opportunity to practise the skill which is being assessed. It is necessary to be aware of these problems and try to reduce their influence or remove them. The skills and processes analysis has made a very useful checklist for scientific inquiry experiment assessment. But in itself it is of little value. It must be seen alongside the other vital attributes needed in the making of a good scientist, the affective aspects of commitment and confidence, the personal insights which come both through formal and informal learning, and the tacit knowledge that comes through experience, both structured and acquired in play. These four aspects must be continually interacting, in a flexible and individualistic way, throughout the scientific education of students. An increasing ability to be good at science, to be good at doing investigational practical work, will be gained through continually, successively, but often unpredictably, developing more experience, developing more insights, developing more skills, and producing more confidence and commitment.

• Journal of Life Science
• /
• v.23 no.11
• /
• pp.1325-1335
• /
• 2013

Working dogs, such as rescue dogs, military watch dogs, guide dogs, and search dogs, are selected by in-training examination of desired traits, including concentration, possessiveness, and boldness. In recent years, genetic information has been considered to be an important factor for the outstanding abilities of working dogs. To characterize the molecular features of the canine genes related to phenotypes for working dogs, we investigated the 24 previously reported genes (AR, BDNF, DAT, DBH, DGCR2, DRD4, MAOA, MAOB, SLC6A4, TH, TPH2, IFT88, KCNA3, TBR2, TRKB, ACE, GNB1, MSTN, PLCL1, SLC25A22, WFIKKN2, APOE, GRIN2B, and PIK3CG) that were categorized to personality, olfactory sense, and athletic/learning ability. We analyzed the chromosomal location, gene-gene interactions, Gene Ontology, and expression patterns of these genes using bioinformatic tools. In addition, variable numbers of tandem repeat (VNTR) or microsatellite (MS) polymorphism in the AR, MAOA, MAOB, TH, DAT, DBH, and DRD4 genes were reviewed. Taken together, we suggest that the genetic background of the canine genes associated with various working dog behaviors and skill performance attributes could be used for proper selection of superior working dogs.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.16 no.6
• /
• pp.17-29
• /
• 2021

Recently, as social distancing have been raised due to the re-spread of COVID-19, the number of serial entrepreneurs who are closing their business is rapidly increasing. Learning from failure is a source of success, but business failure can result in psychological and economic losses and negative emotions of the serial entrepreneur. At this point, it is very important to find a way to recover the negative emotions caused by business failures of serial entrepreneurs. Recently, a strategic model has emerged to deal with the negative emotions of grief caused by business failures of serial entrepreneurs. This study identified the recovery factors from the grief of business failures of serial entrepreneurs and analyzed Shepherd's(2003) three areas: loss orientation, restoration orientation, and dual process. To this end, individual in-depth interviews were conducted with 12 small business serial entrepreneurs who challenged re-startup to identify the attributes of recovery factors that were not identified with quantitative data. As a result of the study, first, recovery factors were investigated in three areas: individual orientation, family orientation, and network orientation. It was found to help improve recovery in nine categories: self-esteem, persistence, personal competence, hobbies, self-confidence, family support, networks, religion, and social support. Second, recovery obstacle factors were investigated in three areas: psychological, economic, and environmental factors. Nine categories including family, health, social network, business partner, competitor, partner, fund, external environment, and government policy were found to persist negative emotions. Third, the emotional processing process for grief was investigated in three areas: loss orientation, restoration orientation, and dual process. Ten categories such as family, partner support, social member support, government support, hobbies, networks, change of business field, moving, third-party perspective, and meditation were confirmed to enhance rapid recovery in the emotional processing process for grief. The implications of this study are as follows. The process of recovering from the grief caused by business failures of serial entrepreneurs was attempted by a qualitative study. By extending the theory of Shepherd(2003), This study can be applied to help with recovery research. In addition, conceptual models and propositions for future empirical research were presented, which can be discussed in carious academic ways.