• Journal of Chest Surgery
• /
• v.38 no.7 s.252
• /
• pp.496-500
• /
• 2005

There was no difference between the bileaflet mechanical valves on the midterm and longterm clinical outcome. We reviewed the hemodynamic comparison between recently available mechanical valves by Doppler Echocardiography. Material and Method: We retrospectively reviewed 396 postoperative hemodynamic datas (EOA, MDPG, and MSPG) by doppler echocardiography in 345 patients. Mechanical valves from 5 venders (Sorin Bicarbon, SJM, ATS, On-X, and Edward MIRA) were compared. There were 232 valves in mitral position, 162 in aortic, and 2 in tricuspid. Result: There were 178 men (mean age; $50.6\pm13.9$ years old) and 167 women $(52.6\pm,4.6)$. MDPG/EOA of 27 mm in mitral position was Sorin; $4.2\pm1.5 mmHg/3.0\pm0.9cm^2,\;SJM;\;2.3\pm1.2/3.5\pm0.6$. In 29mm, Sorin, SJM, ATS, On-X, MIRA revealed $3.4\pm1.2/3.1\pm0.6,\;3.3\pm1.1/2.7\pm0.4,\;3.8\pm0.8/3.2\pm0.6,\;4.0\pm3.0/3.1\pm0.9,\;2.9\pm0.9/3.0\pm0.8$ In 31mm, Sorin, SJM, ATS, MIRA revealed $3.9\pm1.9/2.9\pm0.6,\;3.5\pm1.2/3.0\pm0.6,\;3.4\pm0.8/2.8\pm0.2,\;3.7\pm1.5/2.7\pm0.7$. In 33mm, Sorin, SJM, MIRA revealed $4.4\pm0.9/2.5\pm0.4,\;3.4\pm1.5/3.3\pm0.5,\;4.7\pm2.4\3.0\pm0.3$. MSPG/EOA of 19mm aortic position was Sorin, SJM, ATS, On-X, MIRA $18.0 mmHg/1.2cm^2,\;25.6\pm8.7/1.1\pm0.3,\;25.9\pm12.6/1.2\pm0.3,\;23.0/1.3,\;27.9\pm7.1/1.2\pm0.1$ in that order. In 21mm, SJM, ATS, On-X, MIRA revealed $18.3\pm6.7/1.5\pm0.5,\;13.7\pm2.1/1.7\pm0.3,\;17.0/1.4,\;17.1\pm5.5/1.8\pm0.5$. In 23mm Sorin, SJM, ATS, On-X, MIRA revealed $14.0\pm4.6/1.7\pm0.6,\;12.8\pm3.2/2.0\pm0.2,\;16.8\pm12.2/2.1\pm0.9,\;14.0/1.5,\;15.0\pm5.5/1,8\pm0.5$. In 25mm, SJM and MIRA revealed $14.0\pm5.1/1.8\pm1.0,\;11.0/2.3$. There was no statistically significant difference in these values between the venders given the same position and size. 2 redo valve replacements were performed, 1 due to severe hemolysis in ATS and 1 due to leaflet immobilization in SJM. Conclusion: Postoperative hemodynamic comparison by doppler echocardiography shows no statistically significant difference between recently available mechanical valves in this country.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.12 no.3
• /
• pp.222-228
• /
• 2008

Purpose: The objectives of this study were to compare the left ventricle ejection fraction (LVEF) from gated cardiac blood pool scan (GCBP) for analysis auto-drawing region of interest mode (AROI) and manual-drawing region of interest mode (MROI), respectively. To evaluation the relationships between values produced by both ROI modes. Materials and Methods: Gated cardiac blood pool scan using in vivo method Tc-99m Red Blood Cell were performed for 33 patients (mean age: $53.2{\pm}13.2\;y$) with objective of chemotherapy using single head gamma camera (ADAC Laboratories, Milpitas, CA). Left ventricular ejection fraction was automatically and manually measured, respectively. Results: There was significant difference statistically between AROI and MROI ($LVEF^{AROI}$: $71.4{\pm}12.4%$ vs. $LVEF^{MROI}$: $65.8{\pm}5.9%$, p=0.003). Intra-observer agreements in AROI was higher than MROI ($\gamma^{AROI}=0.964$, Cronbach's $\alpha^{AROI}=0.986$ vs. $\gamma^{MROI}=0.793$, Cronbach's $\alpha^{MROI}=0.911$), either. Additionally, there was no significant difference statistically at best septal view (${\Delta}LVEF^{BSV}=0.7{\pm}2.3%$, p=0.233), however statistically significant difference was found at badly separated septal view (${\Delta}LVEF=10.9{\pm}11.4%$, p=0.001). Moreover, Intra-observer agreements in best septal view was higher than badly separated septal view ($\gamma^{BSV}=0.939$, Cronbach's $\alpha^{BSV}=0.978$; $\gamma=0.948$, Cronbach's $\alpha=0.981$ at AROI, $\gamma^{BSV}=0.836$, Cronbach's $\alpha^{BSV}=0.936$; $\gamma=0.748$, Cronbach's $\alpha=0.888$ at MROI). Conclusion: When best septal view was acquired, LVEF by AROI and MROI indicated not different. Comparing Intra-observer agreements with AROI and MROI, the AROI tended to show higher. Therefore, it is considered that the AROI than MROI is valuable in reproducibility and objective when ROI analysis by acquire left ventricular of best septal view.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.5 no.2
• /
• pp.105-118
• /
• 2000

Anchored measurements (12.5 hr) of suspended sediment concentration and other hydrodynamic parameters were carried out at two stations located at the entrance to Hampyung Bay in summer (August 1999). Tidal variations in water temperature and salinity were in the range of 26.0-27.9$^{\circ}C$ and 30.9-31.5, respectively, indicating exchange offshore and offshore water mass. Active tidal mixing processes at the entrance appear to destroy the otherwise vertical stratification in temperature and salinity in spite of strong solar heating in summer. On the contrary, suspended sediment concentrations show a marked stratification with increasing concentrations toward bottom layer. Clastic particles in suspended sediments consist mostly of very fine to fine silt (4-16 ${\mu}$m) with a poorly-sorted value of 14.7-25.9 ${\mu}$m. However, at slack time with less turbulent energy, flocs larger than 40 ${\mu}$m are formed by cohesion and inter-collision of particles, resulting in a higher settling velocity. Strong ebb-dominated and weak flood dominated tidal currents, in the southwestern and the northeastern part, respectively, result in a seaward residual flow of -10${\sim}$-20 cm $s^{-1}$ at station H1 and a bayward residual flow less than 5.0 cm $s^{-1}$ at station H2. However, mean concentration of suspended sediments at station H1 is higher at flood (95.0-144.1 mg $1^{-1}$) than in ebb (75.8-120.9 mg $1^{-1}$). On the contrary, at the station H2, the trend is reversed with higher concentration at the ebb (84.7-158.4 mg $1^{-1}$) than that at the flood (53.0-107.9 mg $1^{-1}$). As a result, seaward net suspended sediment fluxes ($f_{s}$) are calculated to be -1.7 ${\sim}$-$15.610^{3}$ kg $m^{-2}$ $s^{-1}$ through the whole water column. However, the stations H1 and H2 show definitely different values of the flux with higher ones in the former than in the latter. Alternatively, depth-integrated net suspended sediment loads ($\c{Q}_{s}$) for one tidal cycle are also toward the offshore with ranges of 0.37${\times}$$10^{3}$ kg $m^{-1}$ and 0.21${\times}$$10^{3}$ kg $m^{-1}$, at station H1 and H2, respectively. This seaward transport of suspended sediment in summer suggests that summer-time erosion in the Hampyung muddy tidal flats is a rather exceptional phenomenon compared to the general deposition reported for many other tidal flats on the west coast of Korea.

• Korean Journal of Ecology and Environment
• /
• v.45 no.2
• /
• pp.158-173
• /
• 2012

The objectives of this study were to analyze the longitudinal gradient and temporal variations of water quality in Daecheong Reservoir in relation to the major inflowing streams from the watershed, during 2001~2010. For the study, we selected 7 main-stream sites of the reservoir along the main axis of the reservoir, from the headwater to the dam and 8 tributary streams. In-reservoir nutrients of TN and TP showed longitudinal declines from the headwater to the dam, which results in a distinct zonation of the riverine ($R_z$, M1~M3), transition ($T_z$, M4~M6), and lacustrine zone ($L_z$, M7) in water quality, as shown in other foreign reservoirs. Chlorophyll-a (CHL) and BOD as an indicator of organic matter, were maximum in the $T_z$. Concentration of total phosphorus (TP) was the highest (8.52 $mg\;L^{-1}$) on March in the $R_z$, and was the highest (165 ${\mu}g\;L^{-1}$) in the $L_z$ on July. Values of TN was the maximum (377 ${\mu}g\;L^{-1}$) on August in the $R_z$, and was the highest (3.76 $mg\;L^{-1}$) in the $L_z$ on August. Ionic dilution was evident during September~October, after the monsoon rain. The mean ratios of TN : TP, as an indicator of limiting factor, were 88, which indicates that nitrogen is a surplus for phytoplankton growth in this system. Nutrient analysis of inflowing streams showed that major nutrient sources were headwater streams of T1~T2 and Ockcheon-Stream of T5, and the most influential inflowing stream to the reservoir was T5, which is located in the mid-reservoir, and is directly influenced by the waste-water treatment plants. The key parameters, influenced by the monsoon rain, were TP and suspended solids (SS). Empirical models of trophic variables indicated that variations of CHL in the $R_z$ ($R^2$=0.044, p=0.264) and $T_z$ ($R^2$=0.126, p=0.054) were not accounted by TN, but were significant (p=0.032) in the $L_z$. The variation of the log-transformed $I_r$-CHL was not accounted ($R^2$=0.258, p=0.110) by $I_w$-TN of inflowing streams, but was determined ($R^2$=0.567, p=0.005) by $I_w$-TP of inflowing streams. In other words, TP inputs from the inflowing streams were the major determinants on the in-reservoir phytoplankton growth. Regression analysis of TN : TP suggested that the ratio was determined by P, rather than N. Overall, our data suggest that TP and suspended solids, during the summer flood period, should be reduced from the eutrophication control and P-input from Ockcheon-Stream should be controlled for water quality improvement.

• Korean Journal of Environment and Ecology
• /
• v.18 no.1
• /
• pp.75-91
• /
• 2004

Biodiversity and seasonal community composition of benthic macroinvertebrates were studied from Upo wetlands in Gyeongsangnam-do, Korea, comprising Upo (4 sites), Mokpo (2 sites), Sajipo (1 site), Jjokjibeol (1 site), Yeobeol (1 site), and Topyeongcheon (2 sites) areas from October 2002 to August 2003. As a result, it was known that Upo wetlands retained relatively well-preserved littoral zones which may provide good habitats for benthic macroinvertebrates; however, frequent disturbances of littoral zones caused by flood were the major factor affecting on the survival and distribution of benthic macroinvertebrates in the areas. During the study period, a total of 135 species of benthic macroinvertebrates in 10 genera, 59 families, 16 orders, 7 classes, and 3 phyla were collected those of which are the highest degree of diversity of the taxa ever known in Korean wetlands: aquatic insects 103 spp. (Diptera 27 spp., Odonata 24 spp., Coleoptera 19 spp., Hemiptera 16 spp., Ephemeroptera 9 spp., Trichoptera 7 spp., and Collembola 1 sp.), Crustacea 2 spp., Mollusca 19 spp. (Gastropoda 12 spp. and Bivalvia 7 spp.), and Annelids 11 spp. (Oligocaeta 1 sp. and Hirudinea 10 spp.). Sajipo (St.G) and Jjokjibeol (St.H) areas yielded relatively larger numbers of species, 54 spp. and 53 spp., respectively, while more than 40 species occurred at most other sites. Based on quantitative sampling (0.5m${\times}$2m), aquatic insects (88.0％), particularly chironomids in Diptera (61.0％), occupied major proportion of the total individuals of benthic macroinvertebrates, while Mollusca (5.3％), Annelida (3.5％), and Crustacea (3.2％) occupied minor proportions. In standing water areas, diverse groups of benthic macroinvertebrates such as chironomids, demselflies, aquatic bugs, aquatic beetles, crustaceans, and gastropods were dominant in terms of individual number; in the running water areas, on the other hand, chironomids and baetid mayflies were dominant. However, gastropods, i.e. viviparids, were the dominant group of benthic macroinvertebrates in most study areas in terms of biomass. Dominance indices were 0.22-0.51 (mean$\pm$sd 0.42$\pm$0.09) in autumn, 0.31-0.96 (0.02$\pm$0.23) in winter, and 0.30-0.89 (0.57$\pm$0.18) in summer; diversity indices were 3.50-4.26 (3.80$\pm$0.24) in autumn,1.55-4.50 (3.10$\pm$1.01) in winter, and 1.35-3.77 (2.55$\pm$0.09) in summer. Highly movable or true aquatic benthic macroinvertebyates such as aquatic bugs, aquatic beetles, and gastropods recovered earlier after flood. In the study sites of Upo wetlands, Upo and Sajipo areas showed relatively higher values of average diversity index which may indicate a good habitat condition for benthic macroinvertebrates.

• Korean Journal of Veterinary Service
• /
• v.25 no.1
• /
• pp.53-73
• /
• 2002

It has been reported that degranulation of mast cells in rats, rabbits and dog was observed after dosing xylazine hydrochloride(Xh) which has been widely used as sedative, analgesic and muscular relaxant. Therefore, this experiment was conducted to examine the relations between Xh and histamine release and to identify the action of ${\alpha}$-adrenoceptors which exists on the suface of mast cells. 1. The content of histamine within serum was measured with HPLC by performing the O-phthalaldehyde(OPA) fluorescent derivation. The pretreatment method had a little modification from the conventional method. The pretreament was carried out in the following method. 0.2$m\ell$ of serum and 1$m\ell$ of butanol were added to mixed together and then the liquid was centrifugally separated at 4$^{\circ}C$ and 2,000 rpm for 3 minutes. 0.4$m\ell$ of 0.1N HCl and 1.6$m\ell$ of heptane were added to 0.8$m\ell$ of supernatant taken from the liquid, and they were mixed together. This mixture was also centrifugally separated at 4$^{\circ}C$ and 2,000 rpm for 5 minutes. The supernatant was thrown away and the OPA fluorescent derivation was carried out with 0.2$m\ell$ of the lower liquid then, 5 minutes after mixing 400${\mu}\ell$ of 0.1N HCl, 120${\mu}\ell$ of 1N NaOH and 40${\mu}\ell$ of 0.1% OPA in the 0.2$m\ell$ of the lower liquid,120${\mu}\ell$ of 3.57N H$_3$PO$_4$ was added to the mixed liquid, and the liquid, was mixed again and syringe-filtered. Then, the measurement was done with HPLC in the 30 : 70(ν/ν) ratio of 0.004M KH$_2$PO$_4$: CH$_3$CN, flow rate of 1.0$m\ell$/min., and a wavelength of λex= 350nm and λem=444nm at the column temperature of 27$^{\circ}C$, using the fluorescence detector. 2. The content of histamine in each laboratory animal appeared to be higher in such an order as rabbit, rat, guinea pig, dog, Korean indigenous goat, swine, Korean indigenous cattle, Holstein, and mouse, of which the individual mean values${\pm}$standard deviation were 2.0668 ${\pm}$ 0.6049. 0.4999 ${\pm}$ 0.2278, 0.4241 ${\pm}$ 0.1974, 0.1054 ${\pm}$ 0.0556, 0.1028 ${\pm}$ 0.0276, 0.0972 ${\pm}$ 0.0513, 0.0872 ${\pm}$ 0.0373, 0.0717 ${\pm}$ 0.0379, and 0.0706 ${\pm}$ 0.0366, respectively. 3. The content of histamine was measured at the moments of 15-, 30-, 60-, 120-minutes after inoamuscular injection of 20mg/100kg Xh into two to 4 years old Holstein weighing 600∼700kg. The result showed that there was a significant increase at the times of 30- and 90-minutes after injection(p<0.05). 4. Intramuscular injection of 3mg/10kg Xh was given to crossbred pug dogs weighing 2.5∼4.3kg. The content of histamine was measured at the times of 30-, 60-, 90- and 120-minutes after injection. The result revealed that there was a significant increase at the times of 60-and 90-minutes after injection(p<0.05). 5. Intramuscular injection of 10mg/$m\ell$∼25mg/$m\ell$ Xh in concentration of 0.1$m\ell$ was applied to Korean indigenous goat over 5 months old. Then, the content of histamine was measured at the times of 15-, 30-, 60- and 90-minutes after injection. A significant increase was shown at the times of 30- and 60-minutes after injection(p<0.05). 6. The content of histamine was measured at the moments of 30- and 60-minutes after intramuscular injection of 0.1-0.2$m\ell$ Xh (20mg/$m\ell$) into male rabbits weighting 2.5-4kg. A significant increase was found at the moment of 60 minutes after injection(p<0.001). 7. After administering Xh to the mast cell taken from the abdominal cavity of mouse, the content of histamine was measured. The result showed that the higher the concentration, the more significantly the content of histamine was increased(p<0.05). 8. Compound 48/80 was administered in concentration of 5$\mu\textrm{g}$/$m\ell$ and 10$\mu\textrm{g}$/$m\ell$ to the mast cell picked from the abdominal cavity of mouse. The result showed that there was a significant increase in the content of histamine in case of the concentration of 10$\mu\textrm{g}$/$m\ell$(p<0.05). It was found to be about 10,000 to 500,000 times stronger than the Xh. 9. After premedication of 1mg/kg of yohimbine hydrochloride as ${\alpha}$$_2$-adrenergic antagonist to rabbits, the Xh was administered to them. The result was that the value of histamine within serum was decreased significantly(p<0.001). 10. After premeditation of 1mg/kg of prazosin hydrochloride as ${\alpha}$$_1$-adrenergic antagonist to rabbits, the Xh was administered to them. It was found that the value of histamine within serum was decreased significantly(p<0.005). 11, Prazosin hydrochloride and yohimbine hydrochloride as ${\alpha}$$_1$-adrenergic antagonist, respectively, and ${\alpha}$$_2$-adrenergic antagonist were administerd. In this case, the value of histamine within serum was decreased significantly(p<0.0001). As the results, when the Xh is administered to various kinds of animals, the amount of histamine release within serum is increased. In view of the results so far achieved, it is concluded that Xh acted on both a$_1$-adrenoreceptor and ${\alpha}$$_2$-adrenoreceptor induces the degranulation of mast cell.

• Tuberculosis and Respiratory Diseases
• /
• v.48 no.6
• /
• pp.922-931
• /
• 2000

Background : It has been well known that bronchia1 asthma is a chronic airway inflammatory disorder. Recently, sputum induced with hypertonic saline was introduced as a simple and useful nonivasive medium to investigate airway inflammation and symptom severity in patients with asthma. We examined the eosinophil, eosinophil cationic protein (ECP), interleukin(IL)-3, IL-5, granulocyte-macrophage colony-stimulating facta (GM-CSF), and nitric oxide (NO) derivatives in induced sputum from patients with bronchia1 asthma in order to determine the role of NO and various inflammatory cytokines as a useful markers of airway inflammation or changes in pulmonary function tests and symptoms. Methods : A total 30 patients with bronchia1 asthma received oral prednisolone 30 mg daily for 2 weeks. Forced expiratory volume in one second ($FEV_1$), total blood eosinophil count and induced sputum eosinophil count, ECP, IL-3, IL-5, GM-CSF, and NO derivatives were determined before and after the administration of prednisolone. Results : Of the 30 patients, 13 (43.3%) were male and 17 (56.7%) were female. The mean age of patients was 41.8 years (range 19-64 years). Two patients could not produce sputum at the second study and 3 could not be followed up after their first visit. Two weeks after the prednisolone administration, there was a significant increase in $FEV_1$ (% of predicted value) from 78.1$\pm$20.6 % to 90.3$\pm$ 18.3 % (P<0.001). The eosinophil percentages in induced sputum were significantly decreased after treatment with prednisolone, with values of 56.1$\pm$27.2 % versus 29.6$\pm$21.3 % (P<0.001), and ECP were $134.5\pm68.1\;{\mu}g/L$ versus $41.5\pm42.4\;{\mu}g/L$ (P<0.001) respectively. After the prednisolone treatments, the eotaxin concentration also showed a decreasing tendency from 26.7$\pm$12.8 pg/ml to 21.7$\pm$8.7 pg/ml. There was a decreasing tendency but no significant differences in total blood eosinophil count (425.7$\pm$265.9 vs 287.7$\pm$294.7) and in the concentration of NO derivatives ($70.4\pm44.6{\mu}mol/L$ vs $91.5\pm48.3\;{\mu}mol/L$) after the prednisolone treatments. IL-3, IL-5, GM-CSF were undetectable in the sputum of most subjects either before the prednisolone treatments or after the treatments. Before the prednisolone treatments, a significant inverse correlation was observed between FEV1 and sputum ECP (r=-D.364, P<0.05) and there was a significant correlation between sputum eosinophils and eotaxin (r=0.369, P<0.05) Conclusion : The eotaxin and ECP concentration in induced sputum may be used as markers of airway inflammation after treatments in bronchia1 asthma. In addition, the measurement of sputum eosinophil percent ages is believed to be a simple method displaying the degree of airway inflammation and airway obstruction before and after the prednisolone treatment in bronchia1 asthma. However, unlike exhaled NO, the examination of NO derivatives with Griess reaction in induced sputum is considered an ineffective marker of changing airway inflammation and obstructing symptoms.

• Tuberculosis and Respiratory Diseases
• /
• v.47 no.3
• /
• pp.321-330
• /
• 1999

Background : Early diagnosis and proper antibiotic treatment are very important in the management of ventilator-associated pneumonia (VAP) because of its high mortality. Bronchoscopy with a protected specimen brush (PSB) has been considered the standard method to isolate the causative organisms of VAP. However, this method burdens consumer economically to purchase a PSB. Another useful method for the diagnosis of VAP is quantitative cultures of aspirated specimens through bronchoscopic bronchoalveolar lavage (BAL), for which the infusion of more than 120 m1 of saline has been recommended for adequate sampling of a pulmonary segment. However, occasionally it leads to deterioration of the patient's condition. We studied the diagnostic efficacy of minibronchoalveolar lavage (miniBAL), which retrieves only 25 ml of BAL fluid, in the isolation of causative organisms of VAP. Methods: We included 38 consecutive patients (41 cases) suspected of having VAP on the basis of clinical evidence, who had received antibiotics before the bronchoscopy. The two diagnostic techniques of PSB and miniBAL, which were performed one after another at the same pulmonary segment, 'were compared prospectively. The cut-off values for quantitative cultures to define causative bacteria of VAP were more than $10^3$ colony-forming units (cfu)/ml for PSB and more than $10^4$ cfu/ml for BAL. Results: The amount of instilled normal saline required to retrieve 25 ml of BAL fluid was $93{\pm}32 ml$ (mean${\pm}$SD). The detection rate of causative agents was 46.3% (19/41) with PSB and 43.9% (18/41) with miniBAL. The concordance rate of PSB and miniBAL in the bacterial culture was 85.4% (35/41). Although arterial blood oxygen saturation dropped significantly (p<0.05) during ($92{\pm}10%$) and 10 min after ($95{\pm}3%$) miniBAL compared with the baseline ($97{\pm}3%$), all except 3 cases were within normal ranges. The significantly elevated heart rate during ($l25{\pm}24$/min, p<0.05) miniBAL compared with the baseline ($1l1{\pm}22$/min) recovered again in 10 min after ($111{\pm}26$/min) miniBAL. Transient hypotension was developed during the procedure in two cases. The procedure was stopped in one case due to atrial flutter. Conclusion: MiniBAL is a safe and effective technique to detect the causative organisms of VAP.

• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.185-202
• /
• 2012

.Since the value of information has been realized in the information society, the usage and collection of information has become important. A facial expression that contains thousands of information as an artistic painting can be described in thousands of words. Followed by the idea, there has recently been a number of attempts to provide customers and companies with an intelligent service, which enables the perception of human emotions through one's facial expressions. For example, MIT Media Lab, the leading organization in this research area, has developed the human emotion prediction model, and has applied their studies to the commercial business. In the academic area, a number of the conventional methods such as Multiple Regression Analysis (MRA) or Artificial Neural Networks (ANN) have been applied to predict human emotion in prior studies. However, MRA is generally criticized because of its low prediction accuracy. This is inevitable since MRA can only explain the linear relationship between the dependent variables and the independent variable. To mitigate the limitations of MRA, some studies like Jung and Kim (2012) have used ANN as the alternative, and they reported that ANN generated more accurate prediction than the statistical methods like MRA. However, it has also been criticized due to over fitting and the difficulty of the network design (e.g. setting the number of the layers and the number of the nodes in the hidden layers). Under this background, we propose a novel model using Support Vector Regression (SVR) in order to increase the prediction accuracy. SVR is an extensive version of Support Vector Machine (SVM) designated to solve the regression problems. The model produced by SVR only depends on a subset of the training data, because the cost function for building the model ignores any training data that is close (within a threshold ${\varepsilon}$) to the model prediction. Using SVR, we tried to build a model that can measure the level of arousal and valence from the facial features. To validate the usefulness of the proposed model, we collected the data of facial reactions when providing appropriate visual stimulating contents, and extracted the features from the data. Next, the steps of the preprocessing were taken to choose statistically significant variables. In total, 297 cases were used for the experiment. As the comparative models, we also applied MRA and ANN to the same data set. For SVR, we adopted '${\varepsilon}$-insensitive loss function', and 'grid search' technique to find the optimal values of the parameters like C, d, ${\sigma}^2$, and ${\varepsilon}$. In the case of ANN, we adopted a standard three-layer backpropagation network, which has a single hidden layer. The learning rate and momentum rate of ANN were set to 10%, and we used sigmoid function as the transfer function of hidden and output nodes. We performed the experiments repeatedly by varying the number of nodes in the hidden layer to n/2, n, 3n/2, and 2n, where n is the number of the input variables. The stopping condition for ANN was set to 50,000 learning events. And, we used MAE (Mean Absolute Error) as the measure for performance comparison. From the experiment, we found that SVR achieved the highest prediction accuracy for the hold-out data set compared to MRA and ANN. Regardless of the target variables (the level of arousal, or the level of positive / negative valence), SVR showed the best performance for the hold-out data set. ANN also outperformed MRA, however, it showed the considerably lower prediction accuracy than SVR for both target variables. The findings of our research are expected to be useful to the researchers or practitioners who are willing to build the models for recognizing human emotions.

• Journal of Intelligence and Information Systems
• /
• v.20 no.2
• /
• pp.73-92
• /
• 2014

An Adaptive Clustering-based Collaborative Filtering Technique was proposed to solve the fundamental problems of collaborative filtering, such as cold-start problems, scalability problems and data sparsity problems. Previous collaborative filtering techniques were carried out according to the recommendations based on the predicted preference of the user to a particular item using a similar item subset and a similar user subset composed based on the preference of users to items. For this reason, if the density of the user preference matrix is low, the reliability of the recommendation system will decrease rapidly. Therefore, the difficulty of creating a similar item subset and similar user subset will be increased. In addition, as the scale of service increases, the time needed to create a similar item subset and similar user subset increases geometrically, and the response time of the recommendation system is then increased. To solve these problems, this paper suggests a collaborative filtering technique that adapts a condition actively to the model and adopts the concepts of a context-based filtering technique. This technique consists of four major methodologies. First, items are made, the users are clustered according their feature vectors, and an inter-cluster preference between each item cluster and user cluster is then assumed. According to this method, the run-time for creating a similar item subset or user subset can be economized, the reliability of a recommendation system can be made higher than that using only the user preference information for creating a similar item subset or similar user subset, and the cold start problem can be partially solved. Second, recommendations are made using the prior composed item and user clusters and inter-cluster preference between each item cluster and user cluster. In this phase, a list of items is made for users by examining the item clusters in the order of the size of the inter-cluster preference of the user cluster, in which the user belongs, and selecting and ranking the items according to the predicted or recorded user preference information. Using this method, the creation of a recommendation model phase bears the highest load of the recommendation system, and it minimizes the load of the recommendation system in run-time. Therefore, the scalability problem and large scale recommendation system can be performed with collaborative filtering, which is highly reliable. Third, the missing user preference information is predicted using the item and user clusters. Using this method, the problem caused by the low density of the user preference matrix can be mitigated. Existing studies on this used an item-based prediction or user-based prediction. In this paper, Hao Ji's idea, which uses both an item-based prediction and user-based prediction, was improved. The reliability of the recommendation service can be improved by combining the predictive values of both techniques by applying the condition of the recommendation model. By predicting the user preference based on the item or user clusters, the time required to predict the user preference can be reduced, and missing user preference in run-time can be predicted. Fourth, the item and user feature vector can be made to learn the following input of the user feedback. This phase applied normalized user feedback to the item and user feature vector. This method can mitigate the problems caused by the use of the concepts of context-based filtering, such as the item and user feature vector based on the user profile and item properties. The problems with using the item and user feature vector are due to the limitation of quantifying the qualitative features of the items and users. Therefore, the elements of the user and item feature vectors are made to match one to one, and if user feedback to a particular item is obtained, it will be applied to the feature vector using the opposite one. Verification of this method was accomplished by comparing the performance with existing hybrid filtering techniques. Two methods were used for verification: MAE(Mean Absolute Error) and response time. Using MAE, this technique was confirmed to improve the reliability of the recommendation system. Using the response time, this technique was found to be suitable for a large scaled recommendation system. This paper suggested an Adaptive Clustering-based Collaborative Filtering Technique with high reliability and low time complexity, but it had some limitations. This technique focused on reducing the time complexity. Hence, an improvement in reliability was not expected. The next topic will be to improve this technique by rule-based filtering.