• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.39-70
• /
• 2017

Data-drive analytics techniques have been recently applied to public surveys. Instead of simply gathering survey results or expert opinions to research the preference for a recently launched product, enterprises need a way to collect and analyze various types of online data and then accurately figure out customer preferences. In the main concept of existing data-based survey methods, the sentiment lexicon for a particular domain is first constructed by domain experts who usually judge the positive, neutral, or negative meanings of the frequently used words from the collected text documents. In order to research the preference for a particular product, the existing approach collects (1) review posts, which are related to the product, from several product review web sites; (2) extracts sentences (or phrases) in the collection after the pre-processing step such as stemming and removal of stop words is performed; (3) classifies the polarity (either positive or negative sense) of each sentence (or phrase) based on the sentiment lexicon; and (4) estimates the positive and negative ratios of the product by dividing the total numbers of the positive and negative sentences (or phrases) by the total number of the sentences (or phrases) in the collection. Furthermore, the existing approach automatically finds important sentences (or phrases) including the positive and negative meaning to/against the product. As a motivated example, given a product like Sonata made by Hyundai Motors, customers often want to see the summary note including what positive points are in the 'car design' aspect as well as what negative points are in thesame aspect. They also want to gain more useful information regarding other aspects such as 'car quality', 'car performance', and 'car service.' Such an information will enable customers to make good choice when they attempt to purchase brand-new vehicles. In addition, automobile makers will be able to figure out the preference and positive/negative points for new models on market. In the near future, the weak points of the models will be improved by the sentiment analysis. For this, the existing approach computes the sentiment score of each sentence (or phrase) and then selects top-k sentences (or phrases) with the highest positive and negative scores. However, the existing approach has several shortcomings and is limited to apply to real applications. The main disadvantages of the existing approach is as follows: (1) The main aspects (e.g., car design, quality, performance, and service) to a product (e.g., Hyundai Sonata) are not considered. Through the sentiment analysis without considering aspects, as a result, the summary note including the positive and negative ratios of the product and top-k sentences (or phrases) with the highest sentiment scores in the entire corpus is just reported to customers and car makers. This approach is not enough and main aspects of the target product need to be considered in the sentiment analysis. (2) In general, since the same word has different meanings across different domains, the sentiment lexicon which is proper to each domain needs to be constructed. The efficient way to construct the sentiment lexicon per domain is required because the sentiment lexicon construction is labor intensive and time consuming. To address the above problems, in this article, we propose a novel product reputation mining algorithm that (1) extracts topics hidden in review documents written by customers; (2) mines main aspects based on the extracted topics; (3) measures the positive and negative ratios of the product using the aspects; and (4) presents the digest in which a few important sentences with the positive and negative meanings are listed in each aspect. Unlike the existing approach, using hidden topics makes experts construct the sentimental lexicon easily and quickly. Furthermore, reinforcing topic semantics, we can improve the accuracy of the product reputation mining algorithms more largely than that of the existing approach. In the experiments, we collected large review documents to the domestic vehicles such as K5, SM5, and Avante; measured the positive and negative ratios of the three cars; showed top-k positive and negative summaries per aspect; and conducted statistical analysis. Our experimental results clearly show the effectiveness of the proposed method, compared with the existing method.

• Korean Journal of Biological Psychiatry
• /
• v.6 no.2
• /
• pp.153-160
• /
• 1999

Animal models can provide a useful tool for the study of some aspects of psychiatric disorders and their treatment. The four criteria for the evaluation of animal models of psychiatric disorders are as following : 1) similarity of inducing conditions 2) similarity of behavioral state 3) common underlying neurobiological mechanisms 4) reversal by clinically effective treatment techniques. Several animal models have been proposed for schizophrenia : phenylethylamine model, L-dopa model, hallucinogen model, cocaine model, amphetamine model, phencyclidine model, noradrenergic reward system lesion model, reticular stimulation model, social isolation model, conditioned avoidance reaction, catalepsy test, paw test, self-stimulation paradigms, latent inhibition paradigms, blocking paradigms, prepulse inhibition of the startle reflex, rodent interaction, social behavior in monkeys, hippocampal damage, high ambient pressure, and models using selective breeding. Among them, animals with bilateral lesion of the hippocampus may provide an adequate animal model for several symptoms of schizophrenia, and ketamine model can reproduce negative symptoms and cognitive deficits as well as positive symptoms of schizophrenia. In conclusion, no model of schizophrenia is entirely representative of the disease, and findings gleaned from model systems must be cautiously interpreted. Furthermore, the process of developing and validating animal models must work in concert with the process to identify reliable measures of human phenomenology.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.25 no.1
• /
• pp.48-57
• /
• 2015

In a sodium-cooled fast reactor, which is a Generation-IV reactor, refueling is conducted by rotating, but not opening, the reactor head to prevent a reaction between the sodium, water and air. Therefore, an inspection technique that checks for the presence of any obstacles between the reactor core and the upper internal structure, which could disturb the rotation of the reactor head, is essential prior to the refueling of a sodium-cooled fast reactor. To this end, an ultrasound-based inspection technique should be employed because the opacity of the sodium prevents conventional optical inspection techniques from being applied to the monitoring of obstacles. In this study, a ranging inspection technique using a plate-type ultrasonic waveguide sensor was developed to monitor the presence of any obstacles between the reactor core and the upper internal structure in the opaque sodium. Because the waveguide sensor installs an ultrasonic transducer in a relatively cold region and transmits the ultrasonic waves into the hot radioactive liquid sodium through a long waveguide, it offers better reliability and is less susceptible to thermal or radiation damage. A 10 m horizontal beam waveguide sensor capable of radiating an ultrasonic wave horizontally was developed, and beam profile measurements and basic experiments were carried out to investigate the characteristics of the developed sensor. The beam width and propagation distance of the ultrasonic wave radiated from the sensor were assessed based on the experimental results. Finally, a feasibility test using cylindrical targets (corresponding to the shape of possible obstacles) was also conducted to evaluate the applicability of the developed ranging inspection technique to actual applications.

• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.121-139
• /
• 2014

Predicting corporate failure has been an important topic in accounting and finance. The costs associated with bankruptcy are high, so the accuracy of bankruptcy prediction is greatly important for financial institutions. Lots of researchers have dealt with the topic associated with bankruptcy prediction in the past three decades. The current research attempts to use ensemble models for improving the performance of bankruptcy prediction. Ensemble classification is to combine individually trained classifiers in order to gain more accurate prediction than individual models. Ensemble techniques are shown to be very useful for improving the generalization ability of the classifier. Bagging is the most commonly used methods for constructing ensemble classifiers. In bagging, the different training data subsets are randomly drawn with replacement from the original training dataset. Base classifiers are trained on the different bootstrap samples. Instance selection is to select critical instances while deleting and removing irrelevant and harmful instances from the original set. Instance selection and bagging are quite well known in data mining. However, few studies have dealt with the integration of instance selection and bagging. This study proposes an improved bagging ensemble based on instance selection using genetic algorithms (GA) for improving the performance of SVM. GA is an efficient optimization procedure based on the theory of natural selection and evolution. GA uses the idea of survival of the fittest by progressively accepting better solutions to the problems. GA searches by maintaining a population of solutions from which better solutions are created rather than making incremental changes to a single solution to the problem. The initial solution population is generated randomly and evolves into the next generation by genetic operators such as selection, crossover and mutation. The solutions coded by strings are evaluated by the fitness function. The proposed model consists of two phases: GA based Instance Selection and Instance based Bagging. In the first phase, GA is used to select optimal instance subset that is used as input data of bagging model. In this study, the chromosome is encoded as a form of binary string for the instance subset. In this phase, the population size was set to 100 while maximum number of generations was set to 150. We set the crossover rate and mutation rate to 0.7 and 0.1 respectively. We used the prediction accuracy of model as the fitness function of GA. SVM model is trained on training data set using the selected instance subset. The prediction accuracy of SVM model over test data set is used as fitness value in order to avoid overfitting. In the second phase, we used the optimal instance subset selected in the first phase as input data of bagging model. We used SVM model as base classifier for bagging ensemble. The majority voting scheme was used as a combining method in this study. This study applies the proposed model to the bankruptcy prediction problem using a real data set from Korean companies. The research data used in this study contains 1832 externally non-audited firms which filed for bankruptcy (916 cases) and non-bankruptcy (916 cases). Financial ratios categorized as stability, profitability, growth, activity and cash flow were investigated through literature review and basic statistical methods and we selected 8 financial ratios as the final input variables. We separated the whole data into three subsets as training, test and validation data set. In this study, we compared the proposed model with several comparative models including the simple individual SVM model, the simple bagging model and the instance selection based SVM model. The McNemar tests were used to examine whether the proposed model significantly outperforms the other models. The experimental results show that the proposed model outperforms the other models.

• Clinical and Experimental Pediatrics
• /
• v.49 no.6
• /
• pp.635-642
• /
• 2006

Purpose : The purpose of this study is to determine whether the new pulmonary valve reconstruction technique prevents short-term postoperative pulmonary regurgitation and improves early and mid-term clinical outcome. Methods : We reviewed postoperative echocardiographic variables and chest X-ray films from 31 patients who had undergone valve reconstruction(pulmonary valve reconstruction group : PVR) for the repair of TOF between April 2000 and August 2004. We compared the clinical data of these patients with those from 47 patients who had right ventricular outflow tract reconstruction with a monocusp valve(monocusp ventricular outflow patch group : MVOP) and 22 patients who had a transannular patch repair without a monocusp valve(transannular patch group : TAP). Results : In the PVR group, 25 patients(81 percent) had trivial or mild pulmonary regurgitation in their early post operative echocardiogram. Only 12 patients(26 percent) in the MVOP group had mild pulmonary regurgitation; and no patient in the TAP group had it. Pulmonary valve function was good in 96 percent of the PVR group, 36 percent of the MVOP group, and none in the TAP group in early post-operative echocardiogram. Follow-up echocardiogram(1, 2, 3, 4 years later) of the MVOP and TAP groups showed moderate pulmonary regurgitation and severely decreased valve function in almost all cases. However, in the PVR group 54 percent(16/28), 50 percent(14/28), 37 percent(9/24), and 31 percent(5/16) of the patients had trivial or mild pulmonary regurgitation 1, 2, 3 and 4 years after operation, respectively. The valve function remained good in 80 percent(24/30), 64 percent(18/28), 57 percent(12/21), and 31 percent(5/16) of the patients 1, 2, 3 and 4 years after operation respectively. Conclusion : Pulmonary valve reconstruction is effective in reducing pulmonary regurgitation and right ventricular dilatation in the repair of TOF, even though regurgitation increases with time. Further study is needed to determine long-term results.

• Clinical and Experimental Pediatrics
• /
• v.49 no.12
• /
• pp.1282-1286
• /
• 2006

Purpose : The causes of prolonged fever have changed during the years and are influenced by age, geographic location and availability of diagnostic facilities/techniques. The aim of the present study was to determine the causes of prolonged fever, to know the proportion and outcomes of undiagnosed children. Methods : We reviewed patients with fever persisting for more than 2 weeks in duration, with documented temperatures of $38^{\circ}C$ on several occasions, or uncertain diagnosis after intensive study of 1 week duration in other hospitals who were admitted to Pusan National University Hospital during the period from July 1999 to June 2004. Results : Fifty-four (59.0 percent) were boys and thirty-seven (41 percent) were girls. Forty-six cases were less than 6 years and 45 cases were more than 6 years; the mean age was $6.48{\pm}6.56years$. In 62 cases (68.1 percent), the fever had persisted for 2 to 3 weeks before admission and in 26 cases (28.6 percent), had lasted longer than a month. Final diagnosis had been reached in 66 of 91 children (72.5 percent). The most common cause was infection (38/91), followed by collagen vascular disease (12/91), immune deficiency (3/91), neoplasia (2/91), and miscellaneous disease. Tuberculosis was the most common infectious cause. The causes of fever were not revealed in 25 cases. Outcome on discharge were as follows; 77 cases (84.6 percent) were improved, 10 cases (11.0 percent) discharged without improvement and 4 cases (4.4 percent) expired. Conclusion : The most common cause of prolonged fever in Korean children remains infection, but the incidence of infection was decreased as compared with previous studies. Tuberculosis is the most common among infectious causes. As Kikuchi disease (subacute necrotizing lymphadenitis) represented a significant cause of prolonged fever, it should be considered if a patient has neutropenia with lymphadenopathy. Undiagnosed patients with prolonged fever (27.5 percent) have increased over previous studies.

• Clinical and Experimental Pediatrics
• /
• v.51 no.10
• /
• pp.1047-1051
• /
• 2008

Purpose : This study aims to evaluate the efficacy and safety of sedatives for pediatric patients using noninvasive procedures. Methods : We performed a prospective study in 446 (aged 1 month-21 y) consecutive pediatric patients undergoing sedation to study noninvasive sedation techniques from February to August 2007. We reviewed demographic data, sedative drugs, dosage, complications, and successful rates of sedation according to the underlying diseases. Results : The overall successful rate of sedation was 435/446 (97.5%). The overall rate of successful sedation using chloral hydrate was 99.1% (420/424), and was 70.6% (12/17) and 60.0% (3/5) with ketamine and midazolam, respectively. Of the neurologic patients (n=172, aged 1 month to 21 years), 136 patients were sedated for EEGs, 5 patients for renal scans, and 31 patients for neuroimaging studies such as brain CT or MRI. All non-neurological patients (n=274, aged 1 month to 5 years) were diagnosed with urinary tract infection and sedated for renal scan. The overall success rate of sedation for this group was 99.6% (273/274). A total of 14 adverse events were observed (3.1%). Most adverse reactions were mild in severity and clinically insignificant. Conclusion : Using chloral hydrate alone has enough effect to sedate non-neurologic patients. However, neurologic patients in the severe course group, especially those suffering from intractable epilepsy, autism, or severe cerebral palsy, must be medicated with chloral hydrate 2 times at most; instead, injections of ketamine or midazolam in the early stage may result in a more promising outcome.

• Progress in Medical Physics
• /
• v.23 no.3
• /
• pp.177-187
• /
• 2012

Magnetic resonance angiography (MRA) techniques are widely used in diagnosis of vascular disorders such as hemadostenosis and aneurism. Especially, phase contrast (PC) MRA technique, which is a typical non contrast-enhanced MRA technique, provides not only the anatomy of blood vessels but also flow velocity. In this study, we developed the 2- and 3-dimensional PC MRA pulse sequences for a low magnetic field MRI system. Vessel images were acquired using 2D and 3D PC MRA and the velocities of the blood flow were measured in the superior sagittal sinus, straight sinus and the confluence of the two. The 2D PC MRA provided the good quality of vascular images for large vessels but the poor quality for small ones. Although 3D PC MRA gave more improved visualization of small vessels than 2D PC MRA, the image quality was not enough to be used for diagnosis of the small vessels due to the low SNR and field homogeneity of the low field MRI system. The measured blood velocities were $25.46{\pm}0.73cm/sec$, $24.02{\pm}0.34cm/sec$ and $26.15{\pm}1.50cm/sec$ in the superior sagittal sinus, straight sinus and the confluence of the two, respectively, which showed good agreement with the previous experimental values. Thus, the developed PC MRA technique for low field MRI system is expected to provide the useful velocity information to diagnose the large brain vessels.

• Journal of Sericultural and Entomological Science
• /
• v.16 no.1
• /
• pp.85-92
• /
• 1974

Many of studies on the transovarial transmission of occult virus and their activation due to various stresses such as cold or heat treatment, chemical feeding, and nutritional deficiency, etc., in the silkworm, Bombyx mori L. have been made, but any attempts have been not made to control virus diseases by detection of the occult virus-carried moths in the production of silkworm egg of hybrids, because of difficulty to detect occult virus in any stage. Therefore, it may be worth while to disclose whether a sublethal infection of the moths from which active virus are detectable, has the same level of induction rate as that of occult virus activation, thus to apply its results for the reduction of the occurence of virus diseases in silkworm rearing. For these purposes, the following experiment was conducted as one of preliminary steps. In this study, investigations on the generation-to-generation transmission of occult virus and a sublethal infection, and the role of chromosomal gene of the host, Jam 103 and Jam 104 in the Previous generation, and Jam 103 x Jam 103 and Jam 104 f Jam 104 in the next generation were made for the induction of virus diseases due to the transmitted virus. The frequency of cytoplasmic polyhedrosis due to the induction in the F$_1$ generation was markedly higher in the cross-batches, male$\times$female and male$\times$female in which inoculated individuals were used as fem ale parents than in the cross-batches, male$\times$female and male$\times$female in which virus has been not inoculated or inoculated only to male in the previous generation. The tendency of increasing rate was observed in any treatments; such as the inoculations of cytoplasmic polyhedrosis virus (10$\^$5/, 10$\^$6/ 10$\^$7, and 10$\^$8//ml ill different concentration of inocula) , cold-treatment (5$^{\circ}C$, 12hrs or 24hrs), and formalin-feeding treatment (2％ or 3％). The shape of polyhedra (tetragonal in outline) examined in the F, larvae was identified as that of the inoculated polyhedra with partial application of immunofluorescent techniques. These results suggests that the cytoplasmic polyhedrosis virus in B. meri L. are transmitted to the next generation through the egg, apparently in the occult state. And the experimental results of various cross-batches revealed the egg cytoplasm plays an important part i the transmission of the occult virus of the cytoplasmic polyhedrosis virus,

• Korean Journal of Soil Science and Fertilizer
• /
• v.45 no.6
• /
• pp.1173-1178
• /
• 2012

Water competition among domestic, industrial and agricultural sectors has been gradually heightened recently in Korea as the lack of water supply is expected in the near future. About 46% of nation's water use is consumed in paddy farming to produce rice. And the conservation of water resource and quality in agricultural sector is a pending issue in the nation's long term water management plan. New paddy rice farming techniques that use significantly less irrigation water are urgently required. System of Rice Intensification (SRI) that is now well known to produce more rice with less water consumption has not been tried in Korea yet. And environmental effect of SRI on greenhouse gases (GHGs) has not been well investigated. The objective of this study was to measure the effect of SRI on GHGs as well as water use and rice yield in a Korean paddy condition. Three experimental runoff plots $5{\times}15m$ in size were prepared at an existing paddy field. Runoff, GHGs emission and water quality were measured during the 2011 growing seasons while a Japonica rice variety was cultivated. Rice plants grew better and healthier in SRI plots than in continuously flooded (CF) and intermittently drained (ID) plots. Rice yield from SRI plots increased 112.8 (ID)~116.1 (CF)% compared with CF and ID plots. Irrigation requirement of SRI plots compared to CF plot reduced by 52.6% and ID plot reduced by 62.0%, meaning that about 37.9~47.4% of irrigation water could be saved. GHGs emission from SRI plots reduced by 71.8% compared to that from CF plot and by 18.4% compared to that from ID plot, meaning that SRI could help contribute to ease the greenhouse gas accumulation in the atmosphere. It was believed that SRI is a promising paddy farming technique that could increase rice yield, and reduce irrigation water requirement and GHGs emission not just in Korea but also other rice farming countries all over the world. However, it was recommended that long term studies under different conditions including rice variety, soil texture, water source, climate need to be conducted for reliable data for the development of environmental policies related to GHGs emission control and management.