• Journal of Intelligence and Information Systems
• /
• v.27 no.2
• /
• pp.1-15
• /
• 2021

If it is difficult for us to make decisions, we ask for advice from friends or people around us. When we decide to buy products online, we read anonymous reviews and buy them. With the advent of the Data-driven era, IT technology's development is spilling out many data from individuals to objects. Companies or individuals have accumulated, processed, and analyzed such a large amount of data that they can now make decisions or execute directly using data that used to depend on experts. Nowadays, the recommender system plays a vital role in determining the user's preferences to purchase goods and uses a recommender system to induce clicks on web services (Facebook, Amazon, Netflix, Youtube). For example, Youtube's recommender system, which is used by 1 billion people worldwide every month, includes videos that users like, "like" and videos they watched. Recommended system research is deeply linked to practical business. Therefore, many researchers are interested in building better solutions. Recommender systems use the information obtained from their users to generate recommendations because the development of the provided recommender systems requires information on items that are likely to be preferred by the user. We began to trust patterns and rules derived from data rather than empirical intuition through the recommender systems. The capacity and development of data have led machine learning to develop deep learning. However, such recommender systems are not all solutions. Proceeding with the recommender systems, there should be no scarcity in all data and a sufficient amount. Also, it requires detailed information about the individual. The recommender systems work correctly when these conditions operate. The recommender systems become a complex problem for both consumers and sellers when the interaction log is insufficient. Because the seller's perspective needs to make recommendations at a personal level to the consumer and receive appropriate recommendations with reliable data from the consumer's perspective. In this paper, to improve the accuracy problem for "appropriate recommendation" to consumers, the recommender systems are proposed in combination with context-based deep learning. This research is to combine user-based data to create hybrid Recommender Systems. The hybrid approach developed is not a collaborative type of Recommender Systems, but a collaborative extension that integrates user data with deep learning. Customer review data were used for the data set. Consumers buy products in online shopping malls and then evaluate product reviews. Rating reviews are based on reviews from buyers who have already purchased, giving users confidence before purchasing the product. However, the recommendation system mainly uses scores or ratings rather than reviews to suggest items purchased by many users. In fact, consumer reviews include product opinions and user sentiment that will be spent on evaluation. By incorporating these parts into the study, this paper aims to improve the recommendation system. This study is an algorithm used when individuals have difficulty in selecting an item. Consumer reviews and record patterns made it possible to rely on recommendations appropriately. The algorithm implements a recommendation system through collaborative filtering. This study's predictive accuracy is measured by Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). Netflix is strategically using the referral system in its programs through competitions that reduce RMSE every year, making fair use of predictive accuracy. Research on hybrid recommender systems combining the NLP approach for personalization recommender systems, deep learning base, etc. has been increasing. Among NLP studies, sentiment analysis began to take shape in the mid-2000s as user review data increased. Sentiment analysis is a text classification task based on machine learning. The machine learning-based sentiment analysis has a disadvantage in that it is difficult to identify the review's information expression because it is challenging to consider the text's characteristics. In this study, we propose a deep learning recommender system that utilizes BERT's sentiment analysis by minimizing the disadvantages of machine learning. This study offers a deep learning recommender system that uses BERT's sentiment analysis by reducing the disadvantages of machine learning. The comparison model was performed through a recommender system based on Naive-CF(collaborative filtering), SVD(singular value decomposition)-CF, MF(matrix factorization)-CF, BPR-MF(Bayesian personalized ranking matrix factorization)-CF, LSTM, CNN-LSTM, GRU(Gated Recurrent Units). As a result of the experiment, the recommender system based on BERT was the best.

• Journal of Environmental Policy
• /
• v.13 no.4
• /
• pp.3-49
• /
• 2014

Growing interest of stakeholders on corporate responsibilities for environment and tightening environmental regulations are highlighting the importance of environmental management more than ever. However, companies' awareness of the importance of environment is still falling behind, and related academic works have not shown consistent conclusions on the relationship between environmental performance and economic performance. One of the reasons is different ways of measuring these two performances. The evaluation scope of economic performance is relatively narrow and the performance can be measured by a unified unit such as price, while the scope of environmental performance is diverse and a wide range of units are used for measuring environmental performances instead of using a single unified unit. Therefore, the results of works can be different depending on the performance indicators selected. In order to resolve this problem, generalized and standardized performance indicators should be developed. In particular, the performance indicators should be able to cover the concepts of both environmental and economic performances because the recent idea of environmental management has expanded to encompass the concept of sustainability. Another reason is that most of the current researches tend to focus on the motive of environmental investments and environmental performance, and do not offer a guideline for an effective implementation strategy for environmental management. For example, a process improvement strategy or a market discrimination strategy can be deployed through comparing the environment competitiveness among the companies in the same or similar industries, so that a virtuous cyclical relationship between environmental and economic performances can be secured. A novel method for measuring eco-efficiency by utilizing Data Envelopment Analysis (DEA), which is able to combine multiple environmental and economic performances, is proposed in this report. Based on the eco-efficiencies, the environmental competitiveness is analyzed and the optimal combination of inputs and outputs are recommended for improving the eco-efficiencies of inefficient firms. Furthermore, the panel analysis is applied to the causal relationship between eco-efficiency and economic performance, and the pooled regression model is used to investigate the relationship between eco-efficiency and economic performance. The four-year eco-efficiencies between 2010 and 2013 of 23 companies are obtained from the DEA analysis; a comparison of efficiencies among 23 companies is carried out in terms of technical efficiency(TE), pure technical efficiency(PTE) and scale efficiency(SE), and then a set of recommendations for optimal combination of inputs and outputs are suggested for the inefficient companies. Furthermore, the experimental results with the panel analysis have demonstrated the causality from eco-efficiency to economic performance. The results of the pooled regression have shown that eco-efficiency positively affect financial perform ances(ROA and ROS) of the companies, as well as firm values(Tobin Q, stock price, and stock returns). This report proposes a novel approach for generating standardized performance indicators obtained from multiple environmental and economic performances, so that it is able to enhance the generality of relevant researches and provide a deep insight into the sustainability of environmental management. Furthermore, using efficiency indicators obtained from the DEA model, the cause of change in eco-efficiency can be investigated and an effective strategy for environmental management can be suggested. Finally, this report can be a motive for environmental management by providing empirical evidence that environmental investments can improve economic performance.

• Geophysics and Geophysical Exploration
• /
• v.13 no.1
• /
• pp.80-87
• /
• 2010

This study was conducted to develop a reservoir modelling workflow to reproduce the heterogeneous distribution of effective permeability that impacts on the performance of SAGD (Steam Assisted Gravity Drainage), the in-situ bitumen recovery technique in the Athabasca Oil Sands. Lithologic facies distribution is the main cause of the heterogeneity in bitumen reservoirs in the study area. The target formation consists of sand with mudstone facies in a fluvial-to-estuary channel system, where the mudstone interrupts fluid flow and reduces effective permeability. In this study, the lithologic facies is classified into three classes having different characteristics of effective permeability, depending on the shapes of mudstones. The reservoir modelling workflow of this study consists of two main modules; facies modelling and permeability modelling. The facies modelling provides an identification of the three lithologic facies, using a stochastic approach, which mainly control the effective permeability. The permeability modelling populates mudstone volume fraction first, then transforms it into effective permeability. A series of flow simulations applied to mini-models of the lithologic facies obtains the transformation functions of the mudstone volume fraction into the effective permeability. Seismic data contribute to the facies modelling via providing prior probability of facies, which is incorporated in the facies models by geostatistical techniques. In particular, this study employs a probabilistic neural network utilising multiple seismic attributes in facies prediction that improves the prior probability of facies. The result of using the improved prior probability in facies modelling is compared to the conventional method using a single seismic attribute to demonstrate the improvement in the facies discrimination. Using P-wave velocity in combination with density in the multiple seismic attributes is the essence of the improved facies discrimination. This paper also discusses sand matrix porosity that makes P-wave velocity differ between the different facies in the study area, where the sand matrix porosity is uniquely evaluated using log-derived porosity, P-wave velocity and photographically-predicted mudstone volume.

• Tuberculosis and Respiratory Diseases
• /
• v.44 no.5
• /
• pp.1072-1082
• /
• 1997

Background : To characterize the clinical features and determine the prognostic factors of severe community-acquired pneumonia. This study is the first of its kind in Korea. Methods : Recruited were 40 patients diagnosed as severe community-acquired pneumonia in Hallym University Hospital from January 1, 1989 through July 31, 1996. Patients were analysed retrospectively for age, sex, underlying disease, respiration rate, hypoxemia, requirement of mechanical ventilation, involvement on chest radiograph, shock, and the serum concentration of BUN and albumin. All parameters were compared between survived and dead group. Results : Male to female ratio was 2.07 : 1. The mean age was $63.1{\pm}17.5$years(range 25~90years) with 65% of patients aged equal to or more than 60. The major underlying diseases were old pulmonary tuberculosis(12.5%), chronic obstructive pulmonary disease(7.5%), bronchial asthma(5%), bronchiectasis(2.5%), and diabetes mellitus(22.5%). Microbiologic diagnosis was made in 26 out of 40 patients(65%). The most common causative organism was S. pneumoniae(17.5%, 7/40) followed by S. aureus(15.0%, 6/40), K. Pneumoniae(12.5%, 5/40), M. tuberculosis(7.5%, 3/40), H. influenzae(2.5%, 1/40), coagulase negative staphylococcus(2.5%, 1/40), P. aeruginosa(2.5%. 1/40), E. cloaceae(2.5%, 1/40), and E. coli(2.5%, 1/40). M. pneumoniae was detected in no patient. The most frequent drugs administered in single or combination therapy were aminoglycosides(75%, 30/40), second- and third-generation cephalosporin(40%, 16/40 and 27.5%, 11/40), macrolides(27.5%, 11/40), and amoxicillin/clavulanic acid(22.5%, 9/40). Of the 40 patients, 14 died of severe community-acquired pneumonia(37.5%). Among them, seven patients (50%) expired within 72h of hospital arrival. According to multivariate analysis, mortality was significantly associated with requirement of mechanical ventilation, bilateral pulmonary involvement, and serum albumins$\leq$3.0g/dl. Conclusion : An understanding of the clinical characteristics and prognostic factors in severe community-acquired pneumonia identified in this study will optimize therapeutic approach in this disease and help decreasing its notorious mortality rate.

• Journal of Embryo Transfer
• /
• v.16 no.3
• /
• pp.183-191
• /
• 2001

This study was designed to establish the superior method for IVF embryos from DNA marker-proved Hanwoo cattle. DNA markers related to marbling score were identified using DNA fingerprinting with Ml3 probe and restriction enzyme Hae III. Oocytes were aspirated from unstimulated. immature ovarian follicles using a combined method of rectal ovarian-palpation and transvaginal ultrasound-guidance(6.5MHz) under local abesthesia. The aspirated oocytes were washed twice with fresh D-PBS containing 5% FBS and were rewashed 4 to 5 times with TCM-199 containing 5% FBS. A morphological grade of I to IV was assigned to each oocyte. Data were analysed using the GLM procedure of SAS. Mean number of follicles identified on ultrasound was 5.5 $\pm$2.9 in right and 4.3 $\pm$2.8 in left ovaries, respectively. The highest follicles(16.6$\pm$2.6) were found in 5101 cow compared to others. Recovery rate of follicular oocytes in individual cow was highest in 5101 cow with 89.3% in > 2mm and 94.0% in $\leq$ 2mm follicles. Total recovery rate was significantly(P<0.01) higher in $\leq$ 2mm(85.7%, 130/154) than > 2mm follicles(74.2%, 201/271). Significantly more oocytcs of Grade IV were recovered from > 2mm follicles. Mean number follicles recovered was 4.8$\pm$3.7. 3.0$\pm$3.4 and 0.3$\pm$0.6 in $\leq$2mm, 2~6mm and $\geq$6mm follicles. respectively. Our results imply that the more fertilizablc oocytes can be recovered from invisible-immature follicles by the combination of simultaneous rectal ovarian-palpation and ultrasound-guided approach in Hanwoo cattle.

• Korean Security Journal
• /
• no.36
• /
• pp.349-386
• /
• 2013

This research analyzes and evaluates The Korean Security Industry Law(TKSIL) putting the regulation of the present government about the private security industry. It nowadays becomes the important axis of the police services offered in the aspect of 'the national life safety' in connection with 'the materialization of society which is safe from the crime'. TKSIL is one of the national administration strategies which Park Gun-hye government aims on supervision policy. After seeking out the core values of the private security industrial policy which sets up in order to approach the national life safety which Park Gun-hye government aims, we make some assessments of this revised security industry law systematically. Particularly all keynote of policy about the private security of the police tried to be confirmed and the desirable direction of policy tries to be presented as to the security industry law application and real operation. In the site of organized civil complaint, the revised security industry law was revised as the direction which intensifies the administrative regulation as to the partial regulation such as it established the reason of the introduction of the arrangement license system. And grounds for disqualification of security instructor and guard, and rules of punishment is intensified order to intercept previously illegal and violent act of the security company etc. However it has the feature that it accomplishes 'the law principle(principle of statute)' the substantial portion through the effort of them changing a lot the content for the form of the law when being the clauses of the fundamental human rights limit, although it has been prescribed in "the security industry law enforcement ordinance" or "the security industry law enforced regulation". The security industry law revised this time brought from the change of the sharp policy through the revision of 17 clauses or new establishment. It can divide into 4 categorizes. (1) strictness of punishment in the site of organized civil complaint (2) Intensification of throwing out for the violation person in the private security business market time-limitedly (3) Intensification of the legal guide supervision power of police (4) upstream of the capital, name tag attachment under compulsion and the limit about other equipment use etc. Essentially "the security industry law" cannot help regulating the national interference of the private security and regulation with this content. However as to this interference and regulation, the limit has to be possible within reasonable range. As the history proved, excessive regulation by the country is not only due to bring the distortion of the security system of nation but also provoke national social cost. It can't be disregards ever that it premises the harmony which appropriate as well as reasonable in the socio-economic dimension for drawing the best combination that all things which get the compulsory education, it limits the person providing the private security service to the corporation, or it limits to the certificate of qualification holder are the ultimate for 'the safety of the national life'.

• The Korean Journal of Nuclear Medicine
• /
• v.5 no.1
• /
• pp.49-64
• /
• 1971

The radioactive $^{131}I$-rose bengal serial scintiphotography was performed in 62 patients with the hepatobiliary diseases and in 20 normal subjects. This approach permitted visualization of the hepatic uptake of $^{131}I$-rose bengal from the circulation and its excretion into the biliary trees and the intestines. In some of these patients, gallbladder function was examined, using eggs as a gallbladder constrictor. The time of maximum hepatic uptake was well correlated to the conventional biochemical liver function tests. In addition to $^{131}I$-rose bengal scintiphotography, $^{198}Au$-colloid scintiphotography was also performed to make comparison of these two tests. The results obtained were as follows: 1. In normal subjects, the maximum hepatic uptake of $^{131}I$-rose bengal occurred at $23{\pm}2.9$ minutes, the initial hepatic excretion at $34{\pm}5.1$ minutes, the visualization of the gallbladder at $29{\pm}5.7$ minutes and the intestinal visualization at $54{\pm}25.8$ minutes. The radioactivity in the gallbladder decreased to $10.7{\pm}5.0%$ one hour after the ingestion of eggs. 2. In the patients with cirrhosis of the liver, there was a delayed and decreased hepatic uptake. The maximun hepatic upake occurred at $43{\pm}12.9$ minutes. The differences in the results of uptake between the cirrhotic and the normal group were statistically significant. The initial hepatic excretion occurred at $60{\pm}18.5$ minutes and had tendency of delaying compared with the normal controls. The gallbladder was visualized in 13 of 16 cases (81%) and its visualization occurred at $49{\pm}14.6$ minutes with a tendency to be delayed compared with the normal controls. The intestinal visualization occurred at $63{\pm}15.8$ minutes and its delaying tendency was somewhat more prominent. 3. In patients with hepatitis, the maximum hepatic uptake occurred at $59{\pm}21.4$ minutes and was significantly delayed. The initial hepatic excretion occurred at $82{\pm}34.3$ minutes and the results revealed a delaying tendency. The gallbladder was visualized in 15 of 20 cases (75%) at $57{\pm}18.7$ minutes, which was significantly delayed. The Intestinal visualization was noted in all cases with marked delay. 4. In patients with obstructive jaundice, the maximum hepatic uptake was noted at $83{\pm}14.7$ minutes, showing the most significant delay. The hepatic excretion into biliary trees and intestines was not entirely noted in all cases except the only one case with gallbladder visualization. 5. In patients with cholelithiasis, the maximum hepatic upake and the initial hepatic excretion were slightly delayed with mean times of $39{\pm}11.2\;and\;48{\pm}17.1$ minutes respectively. The visualization of the gallbladder was demonstrated in 10 of 17 cases (59%) and occurred at $52{\pm}25.6$ minutes with a slight delay. The intestinal visualization occurred at $67{\pm}47.7$ minutes and was slightly delayed. $^{131}I$-rose bengal in the gallbladder remained high, $49.3{\pm}21.3%$, which suggested quantitatively decreased power of gallbladder constriction. 6. The time of the maximum hepetic uptake was correlated well to BSP retention and serum alkaline phosphatase ativity. However, the maximum hepatic uptake had no definite correlation with serum albumin, serum globulin, TTT, serum cholesterol, SGPT or SGOT. 7. In the diagnosis of the hepatobiliary diseases with jaundice, $^{131}I$-rose bengel serial scintiphotography has proved to be more useful than $^{198}Au$-colloid scintiphotography. With these results, it could be justified that $^{131}I$-rose bengal scintiphotography is an excellent diagnostic aid for dynamic hepatobiliary function studies in the clinical practice.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• v.28 no.6
• /
• pp.511-519
• /
• 2006

Autogenous bone grafts have been considered the gold standard for maxillofacial bony defects. However, this procedure could entail a complicated surgical procedure as well as potential donor site morbidity. Possibly the best solution for bone-defect regeneration is a tissue engineering approach, i.e. the use of a combination of a suitable scaffold with osteogenic cells. A major source of osteogenic cells is the bone marrow. Bone marrow-derived mesenchymal stem cells are multipotent and have the ability to differentiate into osteoblastic, chondrocytic, and adipocytic lineage cells. However, the isolation of cells from bone marrow has someproblems when used in clinical setting. Bone marrow aspiration is sometimes potentially more invasive and painful procedure and carries of a risk of morbidity and infection. A minimally invasive, easily accessible alternative would be cells derived from periosteum. The periosteum also contains multipotent cells that have the potential to differentiate into osteoblasts and chondrocytes. In the present study, we evaluated the osteogenic activity and mineralization of cultured human periosteal-derived cells. Periosteal explants were harvested from mandibule during surgical extraction of lower impacted third molar. The periosteal cells were cultured in the osteogenic inductive medium consisting of DMEM supplemented with 10% fetal calf serum, 50g/ml L-ascorbic acid 2-phosphate, 10 nmol dexamethasone and 10 mM -glycerophosphate for 42 days. Periosteal-derived cells showed positive alkaline phosphatase (ALP) staining during 42 days of culture period. The formation of ALP stain showed its maximal manifestation at day 14 of culture period, then decreased in intensity during the culture period. ALP mRNA expression increased up to day 14 with a decrease thereafter. Osteocalcin mRNA expression appeared at day 7 in culture, after that its expression continuously increased in a time-dependent manner up to the entire duration of culture. Von Kossa-positive mineralization nodules were first present at day 14 in culture followed by an increased number of positive nodules during the entire duration of the culture period. In conclusion, our study showed that cultured human periosteal-derived cells differentiated into active osteoblastic cells that were involved in synthesis of bone matrix and the subsequent mineralization of the matrix. As the periosteal-derived cells, easily harvested from intraoral procedure such as surgical extraction of impacted third molar, has the excellent potential of osteogenic capacity, tissue-engineered bone using periosteal-derived cells could be the best choice in reconstruction of maxillofacial bony defects.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.3
• /
• pp.157-165
• /
• 2006

The change of external/internal factors of the cell rquires specific biological functions to maintain life. Such functions encourage particular genes to jnteract/regulate each other in multiple ways. Accordingly, we applied a linear decomposition model IFSA, which derives hidden variables, called the 'expression mode' that corresponds to the functions. To interpret gene interaction/regulation, we used a cross-correlation method given an expression mode. Linear decomposition models such as principal component analysis (PCA) and independent component analysis (ICA) were shown to be useful in analyzing high dimensional DNA microarray data, compared to clustering methods. These methods assume that gene expression is controlled by a linear combination of uncorrelated/indepdendent latent variables. However these methods have some difficulty in grouping similar patterns which are slightly time-delayed or asymmetric since only exactly matched Patterns are considered. In order to overcome this, we employ the (IFSA) method of [1] to locate phase- and shut-invariant features. Membership scoring functions play an important role to classify genes since linear decomposition models basically aim at data reduction not but at grouping data. We address a new function essential to the IFSA method. In this paper we stress that IFSA is useful in grouping functionally-related genes in the presence of time-shift and expression phase variance. Ultimately, we propose a new approach to investigate the multiple interaction information of genes.

• Clinical and Experimental Pediatrics
• /
• v.49 no.5
• /
• pp.552-557
• /
• 2006

Purpose : The recent results observed in precocious puberty and the hope that interrupting puberty might increase adult height have led to an attempt to use GnRH agonist(GnRHa) in children with premature puberty and a poor growth prognosis. We aimed to analyze the growth promoting effect of GnRHa in girls with early puberty and low predicted adult height(PAH). Methods : Thirty six girls were recruited. They were grouped according to the GnRHa treatment period(group 1>6 mo, n=18; group 2<6 mo, n=18). The following variables were analyzed before and after GnRHa treatment : chronological age(CA), bone age(BA), ${\Delta}age$(CA-BA), height, target height (TH), PAH, serum IGF-1, IGFBP-3. Results : Duration of the GnRHa treatment was $0.89{\pm}0.81yr$($1.37{\pm}0.92yr$ in group 1, and $0.41{\pm}0.08yr$ in group 2). Before treatment, none of the variables were different between the two groups. There were no differences in the following variables the between two groups at the end of treatment : CA, BA, ${\Delta}age$, PAH, serum IGF-1, IGFBP-3. But, growth velocity(GV) and PAH increment during treatment were significantly reduced in group 1. Compared with initial PAH, PAH at the end of treatment was significantly increased($3.7{\pm}3.2cm$). The last serum levels of IGF-1 and IGFBP-3 were lower than those before treatment. Conclusion : Even though last PAH didn't approach TH, short term GnRHa administration in early puberty with low predicted PAH was somewhat effective. But, GnRHa administration suppressed the growth hormone-IGF-1 axis. Therefore, it is recommended that growth hormone(GH) should be used in combination with GnRHa.