• Korean Journal of Acupuncture
• /
• v.40 no.4
• /
• pp.156-168
• /
• 2023

Objectives : This study aimed to determine the status of thermal stimulation devices approved in Korea for medical applications over the past 10 years, and based on this, to obtain insight for future thermal treatment in Korean medical institutions. Methods : We searched the item classification list entitled "Regulations on Medical Device Items and Rating by Item" from the Ministry of Food and Drug Safety Notice No. 2021-24, 2021 (Enforced March 19, 2021; www.mfds.go.kr) for individually licensed heaters using the terms "heat" and "heating". Results : We identified 17 items of thermal stimulation product group, of which 1,308 devices were licensed by February 4, 2022, and 53.2% of them (n=696) were devices with valid permits for distribution in Korea. Among the licensed devices, heating pad systems under/overlay (electric, home use) were approved the most, but combinational stimulator (for medical use, home use; Grade 2) accounted for the highest percentage among the current valid permission. Moxibustion apparatuses were licensed separately for electrical use and non-electrical use, and occupied a low percentage of the total devices. We analyzed 307 devices that were accompanied by technical documents and found that the heat sources were wires in 145 (47.2%), infrared rays in 44 (14.3%) and ultrasonic waves in 42 (13.7%) devices. Most (83.1%) devices were used for pain relief, while other applications included beauty, cancer treatment, maintenance of infant body temperature, and healing fractures. Conclusions : Thermal stimulation devices accounted for about 0.9% of all medical devices, and among them, combinational stimulators and heating pad systems under/overlay had the most valid permits. Thermal stimulation devices using heating wires and infrared rays were the most prevalent, and most were used to relieve pain. In order to develop a range of thermal stimulation devices that can be utilized in Korean medical institutions, it is imperative that they have potential applications beyond pain management, addressing various medical purposes. To achieve this, foundational research is necessary to effectively apply diverse heat sources based on medical objectives.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.22 no.3
• /
• pp.21-36
• /
• 2019

Dead fuel moisture content is a key variable in fire danger rating as it affects fire ignition and behavior. This study evaluates simple regression models estimating the moisture content of standardized 10-h fuel stick (10-h FMC) at three sites with different characteristics(urban and outside/inside the forest). Equilibrium moisture content (EMC) was used as an independent variable, and in-situ measured 10-h FMC was used as a dependent variable and validation data. 10-h FMC spatial distribution maps were created for dates with the most frequent fire occurrence during 2013-2018. Also, 10-h FMC values of the dates were analyzed to investigate under which 10-h FMC condition forest fire is likely to occur. As the results, fitted equations could explain considerable part of the variance in 10-h FMC (62~78%). Compared to the validation data, the models performed well with R2 ranged from 0.53 to 0.68, root mean squared error (RMSE) ranged from 2.52% to 3.43%, and bias ranged from -0.41% to 1.10%. When the 10-h FMC model fitted for one site was applied to the other sites, $R^2$ was maintained as the same while RMSE and bias increased up to 5.13% and 3.68%, respectively. The major deficiency of the 10-h FMC model was that it poorly caught the difference in the drying process after rainfall between 10-h FMC and EMC. From the analysis of 10-h FMC during the dates fire occurred, more than 70% of the fires occurred under a 10-h FMC condition of less than 10.5%. Overall, the present study suggested a simple model estimating 10-h FMC with acceptable performance. Applying the 10-h FMC model to the automatic mountain weather observation system was successfully tested to produce a national-scale 10-h FMC spatial distribution map. This data will be fundamental information for forest fire research, and will support the policy maker.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.67-83
• /
• 2018

The Korean film industry with significant increase every year exceeded the number of cumulative audiences of 200 million people in 2013 finally. However, starting from 2015 the Korean film industry entered a period of low growth and experienced a negative growth after all in 2016. To overcome such difficulty, stakeholders like production company, distribution company, multiplex have attempted to maximize the market returns using strategies of predicting change of market and of responding to such market change immediately. Since a film is classified as one of experiential products, it is not easy to predict a box office record and the initial number of audiences before the film is released. And also, the number of audiences fluctuates with a variety of factors after the film is released. So, the production company and distribution company try to be guaranteed the number of screens at the opining time of a newly released by multiplex chains. However, the multiplex chains tend to open the screening schedule during only a week and then determine the number of screening of the forthcoming week based on the box office record and the evaluation of audiences. Many previous researches have conducted to deal with the prediction of box office records of films. In the early stage, the researches attempted to identify factors affecting the box office record. And nowadays, many studies have tried to apply various analytic techniques to the factors identified previously in order to improve the accuracy of prediction and to explain the effect of each factor instead of identifying new factors affecting the box office record. However, most of previous researches have limitations in that they used the total number of audiences from the opening to the end as a target variable, and this makes it difficult to predict and respond to the demand of market which changes dynamically. Therefore, the purpose of this study is to predict the weekly number of audiences of a newly released film so that the stakeholder can flexibly and elastically respond to the change of the number of audiences in the film. To that end, we considered the factors used in the previous studies affecting box office and developed new factors not used in previous studies such as the order of opening of movies, dynamics of sales. Along with the comprehensive factors, we used the machine learning method such as Random Forest, Multi Layer Perception, Support Vector Machine, and Naive Bays, to predict the number of cumulative visitors from the first week after a film release to the third week. At the point of the first and the second week, we predicted the cumulative number of visitors of the forthcoming week for a released film. And at the point of the third week, we predict the total number of visitors of the film. In addition, we predicted the total number of cumulative visitors also at the point of the both first week and second week using the same factors. As a result, we found the accuracy of predicting the number of visitors at the forthcoming week was higher than that of predicting the total number of them in all of three weeks, and also the accuracy of the Random Forest was the highest among the machine learning methods we used. This study has implications in that this study 1) considered various factors comprehensively which affect the box office record and merely addressed by other previous researches such as the weekly rating of audiences after release, the weekly rank of the film after release, and the weekly sales share after release, and 2) tried to predict and respond to the demand of market which changes dynamically by suggesting models which predicts the weekly number of audiences of newly released films so that the stakeholders can flexibly and elastically respond to the change of the number of audiences in the film.

• Korean Journal of Environment and Ecology
• /
• v.31 no.6
• /
• pp.508-519
• /
• 2017

There have been many studies on monitoring of biodiversity changes and preservation of Gwangneung Forest Biosphere Reserve (GFBR) in South Korea in recognition of the rare ecosystem that has been preserved for a long period. However, there are few studies on diversity and community characteristics of benthic macroinvertebrates as an indicator of stream health of GFBR. The purpose of this study was to assess the water quality of Bongseonsa Stream that penetrated through Gwangneung Forest and the nearby torrents by analyzing the benthic macroinvertebrates community during April to September 2016. The investigation collected a total of 114 species of benthic macroinvertebrates belonging to 56 families, 17 orders, 8 classes, and 5 phyla from the Bongseonsa Stream and Kwangneung Stream. Ephemeroptera and Trichoptera were the largest groups in species diversity with 30 species (32.3%) and 16 species (17.2%), respectively, and Tubificidae sp., Baetis fuscatus, Antocha KUa, and Cheumatopsyche brevilineata, which usually habit in contaminated streams, appeared frequently. Among the feeding function groups, the gatherers and hunters appeared relatively frequently, and the shredders and scrapers appeared frequently in the torrents. Among the habitat oriented groups, the clingers and burrower appeared more frequently and represented the microhabitats in the shallow areas. The result of the analysis of benthic macroinvertebrates community showed that the dominant index was $0.48{\pm}0.10$ in average while it was lowest with 0.33 in GS 8 of the Gwangneung Forest torrent and highest in BS 1 of Bongseonsa Stream. The diversity and richness indices were inversely proportional to the dominant index and were 2.53 and 4.22, respectively, in GS 8 where the dominant index was low. The result of the analysis of community stability showed that area I, which had high resistance and restoration, was high in Bongseonsa Stream while the area III, which had low resistance and restoration, was high in Gwangneung Forest, indicating that the water system in Gwangneung Forest had a wider distribution of specifies sensitive to agitation. The biological water quality assessment showed ESB of $50.88{\pm}17.69$, KSI of $1.11{\pm}0.57$, and BMI of $78.55{\pm}11.05$. GS 8 of Gwangneung Forest torrent was judged to be the highest priority protective water area with the best water environment and I class water quality with ESB of 63, KSI of 0.55, and BMI of 89.9. On the contrary, BS 1 of Bongseonsa Stream was judged to be the high priority improvement area that had the lowest water quality rating of III with ESB of 25, KSI of 2.13, and BMI of 62.7. Although the diversity of water beetle was higher in the water system of nearby Bongseonsa Stream than the water system inside the Gwangneung Forest, the annual community structure appeared to have distinct differences.

• Journal of Intelligence and Information Systems
• /
• v.17 no.3
• /
• pp.25-41
• /
• 2011

Recently, support vector machines (SVMs) are being recognized as competitive tools as compared with other data mining techniques for solving pattern recognition or classification decision problems. Furthermore, many researches, in particular, have proved them more powerful than traditional artificial neural networks (ANNs) (Amendolia et al., 2003; Huang et al., 2004, Huang et al., 2005; Tay and Cao, 2001; Min and Lee, 2005; Shin et al., 2005; Kim, 2003).The classification decision, such as a binary or multi-class decision problem, used by any classifier, i.e. data mining techniques is so cost-sensitive particularly in financial classification problems such as the credit ratings that if the credit ratings are misclassified, a terrible economic loss for investors or financial decision makers may happen. Therefore, it is necessary to convert the outputs of the classifier into wellcalibrated posterior probabilities-based multiclass credit ratings according to the bankruptcy probabilities. However, SVMs basically do not provide such probabilities. So it required to use any method to create the probabilities (Platt, 1999; Drish, 2001). This paper applied AdaBoost algorithm-based support vector machines (SVMs) into a bankruptcy prediction as a binary classification problem for the IT companies in Korea and then performed the multi-class credit ratings of the companies by making a normal distribution shape of posterior bankruptcy probabilities from the loss functions extracted from the SVMs. Our proposed approach also showed that their methods can minimize the misclassification problems by adjusting the credit grade interval ranges on condition that each credit grade for credit loan borrowers has its own credit risk, i.e. bankruptcy probability.

• The Korean Journal of Pain
• /
• v.6 no.2
• /
• pp.192-198
• /
• 1993

In 1984, a magnetic resonance spectrometer(magnetic resonance analyser, MRA $I_{TM}$) was developed by Sigrid Lipsett and Ronald J. Weinstock in the USA, Biomedical applications of the spectrometer have been examined by Dr. Hoang Van Duc(pathologist, USC), and Nakamura, et al(Japan). From their theoretical views, the biophysical functions of this machine are to analyse and synthesize a healthy tissue and organ resonance pattern, and to detect and correct an abnormal tissue and organ resonance pattern. All of the above functions are based on Quantum physics. The healthy tissue and organ resonance patterns are predetermined as standard magnetic resonance patterns by digitizing values based on peak resonance emissions(response levels or high pitched echo-sounds amplified via human body). In clinical practice, a counter or neutralizing resonance pattern calculated by the spectrometer can correct a phase-shifted resonance pattern(response levels or low pitched echo-sounds) of a diseased tissue and organ. By administering the counter resonance pattern into the site of pain and trigger point, it is possible to readjust the phase-shifted resonance pattern and then to alleviate pain through regulation of the neurotransmitter function of the nervous system. For assessing clinical effectiveness of pain relief with MRA $I_{TM}$ this study was designed to estimate pain intensity by the patient's subjective verbal rating scale(VRS such as graded to no pain, mild, moderate and severe) before application of it, to evaluate an amount of pain relief as applied the spectrometer by the patients subjective pain relief scale(visual analogue scale, VAS, 0~100%), and then to observe a continuation of pain relief following its application for managing acute and chronic pain in the 102 patients during an 8 months period beginning March, 1993. An application time of the spectrometer ranged from 15 to 30 minutes daily in each patient at or near the site of pain and trigger point when the patient wanted to be treated. The subjects consisted of 54 males and 48 females, with the age distribution between 23~40 years in 29 cases, 41~60 years in 48 cases and 61~76 years in 25 cases respectively(Table 1). The kinds of diagnosis and the main site of pain, the duration of pain before the application, and the frequency of it's application were recorded on the Table 2, 3 and 4. A distinction between acute and chronic pain was defined according to both of the pain intervals lasting within and over 3 months. The results of application of the spectrometer were noted as follows; In 51 cases of acute pain before the application, the pain intensities were rated mild in 10 cases, moderate in 15 cases and severe in 26 cases. The amounts of pain relief were noted as between 30~50% in 9 cases, 51~70% in 13 cases and 71~95% in 29 cases. The continuation of pain relief appeared between 6~24 hours in two cases, 2~5 days in 10 cases, 6~14 days in 4 cases, 15 days in one case, and completely relived of pain in 34 cases(Table 5~7). In 51 cases of chronic pain before the application, the pain intensities were rated mild in 12 cases, moderate in l8 cases and severe in 21 cases. The amounts of pain relief were noted as between 0~50% in 10 cases, 51~70% in 27 cases and 71~90% in 14 cases. The continuation of pain relief appeared to have no effect in two cases. The level of effective duration was between 6~12 hours in two cases, 2~5 days in 11 cases, 6~14 days in 14 cases, 15~60 days in 9 cases and in 13 cases the patient was completely relieved of pain(Table 5~7). There were no complications in the patients except a mild reddening and tingling sensation of skin while applying the spectrometer. Total amounts of pain relief in all of the subjects were accounted as poor and fair in 19(18.6%) cases, good in 40(39.2%) cases and excellent in 43(42.2%) cases. The clinical effectiveness of MRA $I_{TM}$ showed variable distributions from no improvements to complete relief of pain by the patient's assessment. In conclusion, we suggest that MRA $I_{TM}$ may be successful in immediate and continued pain relief but still requires several treatments for continued relief and may be gradually effective in pain relief while being applied repeatedly.

• Journal of the HCI Society of Korea
• /
• v.8 no.1
• /
• pp.1-9
• /
• 2013

This is to develop a new way of testing self-esteem by adopting DAP(Draw a Person) test and to make a platform to digitalize it for young people in the adolescent stage. This approach is to get high effectiveness of the self-esteem measurement using DAP test, including some personal inner situations which can be easily missed in the large statistical analysis. The other objective of this study is digitalize to recover limits of DAP test in the subjective rating standard. It is based on the distribution of the figure drawing expressed numerically by the anxiety index of Handler. For these two examinations, we made experiment through 4 stages with second grade middle school 73 students from July 30th to October 31th in 2009 during 4 months. Firstly, we executed 'Self Values Test' for all 73 people, and divided them into two groups; one is high self-esteem group of 36 people, the other is low self-esteem group of 37 people. Secondly, we regrouped them following D (Depression), Pd (Psychopathic Deviate), Sc (Schizophrenia) scales of MMPI; one is high self-esteem group of 7 people, the other is low self-esteem group of 13 people. Thirdly, we conducted DAP test separately for these 20 people. We intended to verify necessity and appropriateness of direction of 'Digitalizing Measurement System' by comparing and analyzing relation between DAP and Self-esteem following evaluation criteria which has similarity in 3 tests, after executing DAP to reflect peculiarity of adolescents sufficiently. We compared and analyzed result abstracted by sampling DAP test of two groups; One is high self-esteem group of 2 people, the other is low self-esteem group of 2 people; to confirm whether we can improve limitation that original psychological testing has by comparing mutual reliance of measurement test. Finally, with DAP test gained from correlations between self-esteem and melancholia following as above-mentioned steps, we discovered possibility of realization to get a concrete and individual criteria of evaluation based on Expert System as a way of enhancing accessibility in quantitative manner. 'Digitalizing Measurement Program' of DAP test suggested in this study promote results' reliability based on existing tests and measurement.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.97-113
• /
• 2016

Due to the growth of internet data and the rapid development of internet technology, "big data" analysis is actively conducted to analyze enormous data for various purposes. Especially in recent years, a number of studies have been performed on the applications of text mining techniques in order to overcome the limitations of existing structured data analysis. Various studies on sentiment analysis, the part of text mining techniques, are actively studied to score opinions based on the distribution of polarity of words in documents. Usually, the sentiment analysis uses sentiment dictionary contains positivity and negativity of vocabularies. As a part of such studies, this study tries to construct sentiment dictionary which is customized to specific data domain. Using a common sentiment dictionary for sentiment analysis without considering data domain characteristic cannot reflect contextual expression only used in the specific data domain. So, we can expect using a modified sentiment dictionary customized to data domain can lead the improvement of sentiment analysis efficiency. Therefore, this study aims to suggest a way to construct customized dictionary to reflect characteristics of data domain. Especially, in this study, movie review data are divided by genre and construct genre-customized dictionaries. The performance of customized dictionary in sentiment analysis is compared with a common sentiment dictionary. In this study, IMDb data are chosen as the subject of analysis, and movie reviews are categorized by genre. Six genres in IMDb, 'action', 'animation', 'comedy', 'drama', 'horror', and 'sci-fi' are selected. Five highest ranking movies and five lowest ranking movies per genre are selected as training data set and two years' movie data from 2012 September 2012 to June 2014 are collected as test data set. Using SO-PMI (Semantic Orientation from Point-wise Mutual Information) technique, we build customized sentiment dictionary per genre and compare prediction accuracy on review rating. As a result of the analysis, the prediction using customized dictionaries improves prediction accuracy. The performance improvement is 2.82% in overall and is statistical significant. Especially, the customized dictionary on 'sci-fi' leads the highest accuracy improvement among six genres. Even though this study shows the usefulness of customized dictionaries in sentiment analysis, further studies are required to generalize the results. In this study, we only consider adjectives as additional terms in customized sentiment dictionary. Other part of text such as verb and adverb can be considered to improve sentiment analysis performance. Also, we need to apply customized sentiment dictionary to other domain such as product reviews.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.157-173
• /
• 2021

With the development of information technology, the amount of available information increases daily. However, having access to so much information makes it difficult for users to easily find the information they seek. Users want a visualized system that reduces information retrieval and learning time, saving them from personally reading and judging all available information. As a result, recommendation systems are an increasingly important technologies that are essential to the business. Collaborative filtering is used in various fields with excellent performance because recommendations are made based on similar user interests and preferences. However, limitations do exist. Sparsity occurs when user-item preference information is insufficient, and is the main limitation of collaborative filtering. The evaluation value of the user item matrix may be distorted by the data depending on the popularity of the product, or there may be new users who have not yet evaluated the value. The lack of historical data to identify consumer preferences is referred to as data sparsity, and various methods have been studied to address these problems. However, most attempts to solve the sparsity problem are not optimal because they can only be applied when additional data such as users' personal information, social networks, or characteristics of items are included. Another problem is that real-world score data are mostly biased to high scores, resulting in severe imbalances. One cause of this imbalance distribution is the purchasing bias, in which only users with high product ratings purchase products, so those with low ratings are less likely to purchase products and thus do not leave negative product reviews. Due to these characteristics, unlike most users' actual preferences, reviews by users who purchase products are more likely to be positive. Therefore, the actual rating data is over-learned in many classes with high incidence due to its biased characteristics, distorting the market. Applying collaborative filtering to these imbalanced data leads to poor recommendation performance due to excessive learning of biased classes. Traditional oversampling techniques to address this problem are likely to cause overfitting because they repeat the same data, which acts as noise in learning, reducing recommendation performance. In addition, pre-processing methods for most existing data imbalance problems are designed and used for binary classes. Binary class imbalance techniques are difficult to apply to multi-class problems because they cannot model multi-class problems, such as objects at cross-class boundaries or objects overlapping multiple classes. To solve this problem, research has been conducted to convert and apply multi-class problems to binary class problems. However, simplification of multi-class problems can cause potential classification errors when combined with the results of classifiers learned from other sub-problems, resulting in loss of important information about relationships beyond the selected items. Therefore, it is necessary to develop more effective methods to address multi-class imbalance problems. We propose a collaborative filtering model using CGAN to generate realistic virtual data to populate the empty user-item matrix. Conditional vector y identify distributions for minority classes and generate data reflecting their characteristics. Collaborative filtering then maximizes the performance of the recommendation system via hyperparameter tuning. This process should improve the accuracy of the model by addressing the sparsity problem of collaborative filtering implementations while mitigating data imbalances arising from real data. Our model has superior recommendation performance over existing oversampling techniques and existing real-world data with data sparsity. SMOTE, Borderline SMOTE, SVM-SMOTE, ADASYN, and GAN were used as comparative models and we demonstrate the highest prediction accuracy on the RMSE and MAE evaluation scales. Through this study, oversampling based on deep learning will be able to further refine the performance of recommendation systems using actual data and be used to build business recommendation systems.