• The Korean Journal of Physiology
• /
• v.8 no.2
• /
• pp.1-17
• /
• 1974

This experiment was designed to explore the specific functional interrelations between the vestibular semicircular canals and the extraocular muscles which may disclose the neural organization, connecting the vestibular canals and each ocular motor nuclei in the brain system, for vestibuloocular reflex mechanism. In urethane anesthetized rabbits, a fine wire insulated except the cut cross section of its tip was inserted into the canals closely to the ampullary receptor organs through the minute holes provided on the osseous canal wall for monopolar stimulation of each canal nerve. All extraocular muscles of both eyes were ligated and cut at their insertio, and the isometric tension and EMG responses of the extraocular muscles to the vestibular canal nerve stimulation were recorded by means of a physiographic recorder. Upon stimulation of the semicircular canal nerve, direction if the eye movement was also observed. The experimental results were as follows. 1) Single canal nerve stimulation with high frequency square waves (240 cps, 0. 1 msec) caused excitation of three extraocular muscles and inhibition of remaining three muscles in the bilateral eyes; stimulation of any canal nerve of a unilateral labyrinth caused excitation (contraction) of the superior rectus, superior oblique and medial rectus muscles and inhibition (relaxation) of the inferior rectus, inferior oblique and lateral rectos muscles in the ipsilateral eye, and it caused the opposite events in the contralateral eye. 2) By the overlapped stimulation of triple canal nerves of a unilateral labyrinth, unidirectional (excitatory or inhibitory) summation of the individual canal effects on a given extraocular muscles was demonstrated, and this indicates that three different canals of a unilateral vestibular system exert similar effect on a given extraocular muscles. 3) Based on the above experimental evidences, a simple rule by which one can define the vestibular excitatory and inhibitory input sources to all the extraocular muscles is proposed; the superior rectus, superior oblique and medial rectus muscles receive excitatory impulses from the ipsilateral vestibular canals, and the inferior rectus, inferior oblique and lateral rectus muscles from the contralateral canals; the opposite relationship applies for vestibular inhibitory impulses to the extraocular muscles. 4) According to the specific direction of the eye movements induced by the individual canal nerve stimulation, an extraocutar muscle exerting major role (a muscle of primary contraction) and two muscles of synergistic contraction could be differentiated in both eyes. 5) When these experimental results were compared to the well known observations of Cohen et al. (1964) made in the cats, extraocular muscles of primary contraction were the same but those of synergistic contraction were partially different. Moreover, the oblique muscle responses to each canal nerve excitation appeared to be all identical. However, the responnes of horizontal (medial and lateral) and vertical (superior and inferior) rectus muscles showed considerable differences. By critical analysis of these data, the author was able to locate theoretical contradictions in the observations of Cohen et al. but not in the author's results. 6) An attempt was also made to compare the functional observation of this experiment to the morphological findings of Carpenter and his associates obtained by degeneration experiments in the monkeys, and it was able to find some significant coincidence between there two works of different approach. In summary, the author has demonstrated that the well known observations of Cohen et al. on the vestibulo-ocular interrelation contain important experimental errors which can he proved by theoretical evaluation and substantiated by a series of experiments. Based on such experimental evidences, a new rule is proposed to define the interrelation between the vestibular canals and the extraocular muscles.

• Journal of Intelligence and Information Systems
• /
• v.23 no.1
• /
• pp.47-67
• /
• 2017

Steel plate faults is one of important factors to affect the quality and price of the steel plates. So far many steelmakers generally have used visual inspection method that could be based on an inspector's intuition or experience. Specifically, the inspector checks the steel plate faults by looking the surface of the steel plates. However, the accuracy of this method is critically low that it can cause errors above 30% in judgment. Therefore, accurate steel plate faults diagnosis system has been continuously required in the industry. In order to meet the needs, this study proposed a new steel plate faults diagnosis system using Simultaneous MTS (S-MTS), which is an advanced Mahalanobis Taguchi System (MTS) algorithm, to classify various surface defects of the steel plates. MTS has generally been used to solve binary classification problems in various fields, but MTS was not used for multiclass classification due to its low accuracy. The reason is that only one mahalanobis space is established in the MTS. In contrast, S-MTS is suitable for multi-class classification. That is, S-MTS establishes individual mahalanobis space for each class. 'Simultaneous' implies comparing mahalanobis distances at the same time. The proposed steel plate faults diagnosis system was developed in four main stages. In the first stage, after various reference groups and related variables are defined, data of the steel plate faults is collected and used to establish the individual mahalanobis space per the reference groups and construct the full measurement scale. In the second stage, the mahalanobis distances of test groups is calculated based on the established mahalanobis spaces of the reference groups. Then, appropriateness of the spaces is verified by examining the separability of the mahalanobis diatances. In the third stage, orthogonal arrays and Signal-to-Noise (SN) ratio of dynamic type are applied for variable optimization. Also, Overall SN ratio gain is derived from the SN ratio and SN ratio gain. If the derived overall SN ratio gain is negative, it means that the variable should be removed. However, the variable with the positive gain may be considered as worth keeping. Finally, in the fourth stage, the measurement scale that is composed of selected useful variables is reconstructed. Next, an experimental test should be implemented to verify the ability of multi-class classification and thus the accuracy of the classification is acquired. If the accuracy is acceptable, this diagnosis system can be used for future applications. Also, this study compared the accuracy of the proposed steel plate faults diagnosis system with that of other popular classification algorithms including Decision Tree, Multi Perception Neural Network (MLPNN), Logistic Regression (LR), Support Vector Machine (SVM), Tree Bagger Random Forest, Grid Search (GS), Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). The steel plates faults dataset used in the study is taken from the University of California at Irvine (UCI) machine learning repository. As a result, the proposed steel plate faults diagnosis system based on S-MTS shows 90.79% of classification accuracy. The accuracy of the proposed diagnosis system is 6-27% higher than MLPNN, LR, GS, GA and PSO. Based on the fact that the accuracy of commercial systems is only about 75-80%, it means that the proposed system has enough classification performance to be applied in the industry. In addition, the proposed system can reduce the number of measurement sensors that are installed in the fields because of variable optimization process. These results show that the proposed system not only can have a good ability on the steel plate faults diagnosis but also reduce operation and maintenance cost. For our future work, it will be applied in the fields to validate actual effectiveness of the proposed system and plan to improve the accuracy based on the results.

• Radiation Oncology Journal
• /
• v.19 no.2
• /
• pp.87-94
• /
• 2001

Purpose : To evaluate the role of LINAC-based stereotactic radiosurgery (SRS) in the management of meningiomas, we reviewed clinical response, image response, neurological deficits for patients treated at our institution. Methods and materials : Between February 1995 and December 1999, twenty-six patients were treated with SRS. Seven patients had undergone prior resection. Nineteen patients received SRS as the initial treatment. There were 7 male and 19 female patients. The median age was 51 years (range, $14\~67\;years$). At least one clinical symptom presented at the time of SRS in 17 patients and cranial neuropathy was seen in 7 patients. The median tumor volume was $4.7\;cm^3\;(range,\;0.7\~16.5\;m^3)$. The mean marginal dose was 15 Gy (range, $10\~20\;Gy$), delivered to the $80\%$ isodose surface (range, $46\~90\%$). The median clinical and imaging follow-up periods were 27 months (range, 1-71 months) and 25 months (range, $1\~52\;months$), respectively. Results : Of 14 patients who had clinical follow-up of one year or longer, thirteen patients $(93\%)$ were improved clinically at follow-up examination. Clinical symptom worsened in one patient at 4 months after SRS as a result of intratumoral edema, who underwent surgical resection at 7 months. OF 14 patients who had radiologic follow-up of one year or longer, tumor volume decreased in 7 patients $(50\%)$ at a median of 11 months (range, $6\~25\;months$), remained stable in 6 patients $(43\%)$, and increased in one patient $(7\%)$, who underwent surgical resection at 44 months. New radiation-induced neurological deficits developed in six patients $(23\%)$. Five patients $(19\%)$ had transient neurological deficits, completely resolved by conservative treatment including steroid therapy. Radiation-induced brain necrosis developed in one patient $(3.8\%)$ at 9 months after SRS who followed by surgical resection of tumor and necrotic tissue. Conclusions : LINAC-based SRS proves to be an effective and safe management strategy for small to moderate sized meningiomas, inoperable, residual, and recurrent, but long-term follow-up will be necessary to fully evaluate its efficacy. To reduce the radiation-induced neurological deficit for large size meningioma and/or in the proximity of critical and neural structure, more delicate treatment planning and optimal decision of radiation dose will be necessary.

• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.93-112
• /
• 2015

Depending on the change in consumer's consumption pattern, existing retail shop has evolved in hypermarket or convenience store offering grocery and daily products mostly. Therefore, it is important to maintain the inventory levels and proper product configuration for effectively utilize the limited space in the retail store and increasing sales. Accordingly, this study proposed proper product configuration and inventory level strategy based on RFM(Recency, Frequency, Monetary) model and SOM(self-organizing map) for manage the retail shop effectively. RFM model is analytic model to analyze customer behaviors based on the past customer's buying activities. And it can differentiates important customers from large data by three variables. R represents recency, which refers to the last purchase of commodities. The latest consuming customer has bigger R. F represents frequency, which refers to the number of transactions in a particular period and M represents monetary, which refers to consumption money amount in a particular period. Thus, RFM method has been known to be a very effective model for customer segmentation. In this study, using a normalized value of the RFM variables, SOM cluster analysis was performed. SOM is regarded as one of the most distinguished artificial neural network models in the unsupervised learning tool space. It is a popular tool for clustering and visualization of high dimensional data in such a way that similar items are grouped spatially close to one another. In particular, it has been successfully applied in various technical fields for finding patterns. In our research, the procedure tries to find sales patterns by analyzing product sales records with Recency, Frequency and Monetary values. And to suggest a business strategy, we conduct the decision tree based on SOM results. To validate the proposed procedure in this study, we adopted the M-mart data collected between 2014.01.01~2014.12.31. Each product get the value of R, F, M, and they are clustered by 9 using SOM. And we also performed three tests using the weekday data, weekend data, whole data in order to analyze the sales pattern change. In order to propose the strategy of each cluster, we examine the criteria of product clustering. The clusters through the SOM can be explained by the characteristics of these clusters of decision trees. As a result, we can suggest the inventory management strategy of each 9 clusters through the suggested procedures of the study. The highest of all three value(R, F, M) cluster's products need to have high level of the inventory as well as to be disposed in a place where it can be increasing customer's path. In contrast, the lowest of all three value(R, F, M) cluster's products need to have low level of inventory as well as to be disposed in a place where visibility is low. The highest R value cluster's products is usually new releases products, and need to be placed on the front of the store. And, manager should decrease inventory levels gradually in the highest F value cluster's products purchased in the past. Because, we assume that cluster has lower R value and the M value than the average value of good. And it can be deduced that product are sold poorly in recent days and total sales also will be lower than the frequency. The procedure presented in this study is expected to contribute to raising the profitability of the retail store. The paper is organized as follows. The second chapter briefly reviews the literature related to this study. The third chapter suggests procedures for research proposals, and the fourth chapter applied suggested procedure using the actual product sales data. Finally, the fifth chapter described the conclusion of the study and further research.

• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.69-92
• /
• 2015

The explosion of social media data has led to apply text-mining techniques to analyze big social media data in a more rigorous manner. Even if social media text analysis algorithms were improved, previous approaches to social media text analysis have some limitations. In the field of sentiment analysis of social media written in Korean, there are two typical approaches. One is the linguistic approach using machine learning, which is the most common approach. Some studies have been conducted by adding grammatical factors to feature sets for training classification model. The other approach adopts the semantic analysis method to sentiment analysis, but this approach is mainly applied to English texts. To overcome these limitations, this study applies the Word2Vec algorithm which is an extension of the neural network algorithms to deal with more extensive semantic features that were underestimated in existing sentiment analysis. The result from adopting the Word2Vec algorithm is compared to the result from co-occurrence analysis to identify the difference between two approaches. The results show that the distribution related word extracted by Word2Vec algorithm in that the words represent some emotion about the keyword used are three times more than extracted by co-occurrence analysis. The reason of the difference between two results comes from Word2Vec's semantic features vectorization. Therefore, it is possible to say that Word2Vec algorithm is able to catch the hidden related words which have not been found in traditional analysis. In addition, Part Of Speech (POS) tagging for Korean is used to detect adjective as "emotional word" in Korean. In addition, the emotion words extracted from the text are converted into word vector by the Word2Vec algorithm to find related words. Among these related words, noun words are selected because each word of them would have causal relationship with "emotional word" in the sentence. The process of extracting these trigger factor of emotional word is named "Emotion Trigger" in this study. As a case study, the datasets used in the study are collected by searching using three keywords: professor, prosecutor, and doctor in that these keywords contain rich public emotion and opinion. Advanced data collecting was conducted to select secondary keywords for data gathering. The secondary keywords for each keyword used to gather the data to be used in actual analysis are followed: Professor (sexual assault, misappropriation of research money, recruitment irregularities, polifessor), Doctor (Shin hae-chul sky hospital, drinking and plastic surgery, rebate) Prosecutor (lewd behavior, sponsor). The size of the text data is about to 100,000(Professor: 25720, Doctor: 35110, Prosecutor: 43225) and the data are gathered from news, blog, and twitter to reflect various level of public emotion into text data analysis. As a visualization method, Gephi (http://gephi.github.io) was used and every program used in text processing and analysis are java coding. The contributions of this study are as follows: First, different approaches for sentiment analysis are integrated to overcome the limitations of existing approaches. Secondly, finding Emotion Trigger can detect the hidden connections to public emotion which existing method cannot detect. Finally, the approach used in this study could be generalized regardless of types of text data. The limitation of this study is that it is hard to say the word extracted by Emotion Trigger processing has significantly causal relationship with emotional word in a sentence. The future study will be conducted to clarify the causal relationship between emotional words and the words extracted by Emotion Trigger by comparing with the relationships manually tagged. Furthermore, the text data used in Emotion Trigger are twitter, so the data have a number of distinct features which we did not deal with in this study. These features will be considered in further study.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.1-21
• /
• 2020

With the rapid development of artificial intelligence technology, various techniques have been developed to extract meaningful information from unstructured text data which constitutes a large portion of big data. Over the past decades, text mining technologies have been utilized in various industries for practical applications. In the field of business intelligence, it has been employed to discover new market and/or technology opportunities and support rational decision making of business participants. The market information such as market size, market growth rate, and market share is essential for setting companies' business strategies. There has been a continuous demand in various fields for specific product level-market information. However, the information has been generally provided at industry level or broad categories based on classification standards, making it difficult to obtain specific and proper information. In this regard, we propose a new methodology that can estimate the market sizes of product groups at more detailed levels than that of previously offered. We applied Word2Vec algorithm, a neural network based semantic word embedding model, to enable automatic market size estimation from individual companies' product information in a bottom-up manner. The overall process is as follows: First, the data related to product information is collected, refined, and restructured into suitable form for applying Word2Vec model. Next, the preprocessed data is embedded into vector space by Word2Vec and then the product groups are derived by extracting similar products names based on cosine similarity calculation. Finally, the sales data on the extracted products is summated to estimate the market size of the product groups. As an experimental data, text data of product names from Statistics Korea's microdata (345,103 cases) were mapped in multidimensional vector space by Word2Vec training. We performed parameters optimization for training and then applied vector dimension of 300 and window size of 15 as optimized parameters for further experiments. We employed index words of Korean Standard Industry Classification (KSIC) as a product name dataset to more efficiently cluster product groups. The product names which are similar to KSIC indexes were extracted based on cosine similarity. The market size of extracted products as one product category was calculated from individual companies' sales data. The market sizes of 11,654 specific product lines were automatically estimated by the proposed model. For the performance verification, the results were compared with actual market size of some items. The Pearson's correlation coefficient was 0.513. Our approach has several advantages differing from the previous studies. First, text mining and machine learning techniques were applied for the first time on market size estimation, overcoming the limitations of traditional sampling based- or multiple assumption required-methods. In addition, the level of market category can be easily and efficiently adjusted according to the purpose of information use by changing cosine similarity threshold. Furthermore, it has a high potential of practical applications since it can resolve unmet needs for detailed market size information in public and private sectors. Specifically, it can be utilized in technology evaluation and technology commercialization support program conducted by governmental institutions, as well as business strategies consulting and market analysis report publishing by private firms. The limitation of our study is that the presented model needs to be improved in terms of accuracy and reliability. The semantic-based word embedding module can be advanced by giving a proper order in the preprocessed dataset or by combining another algorithm such as Jaccard similarity with Word2Vec. Also, the methods of product group clustering can be changed to other types of unsupervised machine learning algorithm. Our group is currently working on subsequent studies and we expect that it can further improve the performance of the conceptually proposed basic model in this study.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.33 no.1
• /
• pp.15-20
• /
• 2013

This study was carried out to determine the optimum harvest stage of Italian ryegrass (Lolium multiflorum Lam., IRG) for maximum forage production during the spring season in Suwon, 2010. The variety of IRG was the early maturity type, 'Kowinearly', and six harvest stages (treatments) were first heading (T1), heading (T2), late heading to early bloom (T3), bloom to late bloom (T4), ripeness (T5), and late ripeness stage (T6). The dates of the first heading and heading of 'Kowinearly' were seen on 4 to 5 May, and 14 May, respectively. Plant length and dry matter (DM) percentage at first harvest were from 69 cm and 14.8% at T1 stage to 103 cm and 35.0% at T6 stage, respectively. The content of crude protein (CP) and in vitro DM digestibility (IVDMD) of T1, T2, T3, T4, T5 and T6 at first harvest were 15.6%, 10.6%, 10.1%, 8.1%, 7.3% and 5.4%, and 81.8%, 72.1%, 64.8%, 63.8%, 61.4% and 59.0%, respectively. The content of neural detergent fiber (NDF) and acid detergent fiber (ADF) were increased continuously with delayed harvest. A significantly higher yield of DM, CP and in vitro digestible DM (IVDDM) were observed for T3, and T4 (p<0.05). DM yield of 3,526 kg, 6,278 kg, 7,842 kg, 8,984 kg, 8,346 kg and 8,008 kg/ha, CP yield of 549 kg, 665 kg, 795 kg, 725 kg, 608 kg and 430 kg/ha, and IVDDM of 2,883 kg. 4,526 kg, 5,083 kg, 5,728 kg, 5,124 kg and 4,722 kg/ha at first harvest were recorded in T1, T2, T3, T4, T5 and T6, respectively. Regrowth yield of DM, CP and IVDDM were shown to be higher at T1 and T2 (p<0.05). However, no significant differences were observed between the two stages. Daily DM and DDM production of regrowth IRG were higher at T2, followed by T1. The total yield (at first and at regrowth) of DM, CP and IVDDM were significant higher for T2, followed by T3, T4 and T1 in order. At T2 stage, the yield was 11,089 kg, 1,254 kg, and 7,669 kg/ha in DM, CP, and IVDDM. In conclusion, the late heading to bloom stage was determined to be the optimum harvest stage for a single harvest, while the heading stage was a suitable stage of first harvest of 'Kowinearly' where two harvests were sought in a single year.

• Childhood Kidney Diseases
• /
• v.8 no.1
• /
• pp.18-25
• /
• 2004

Purpose : Alport syndrome is clinically characterized by hereditary progressive nephritis causing ESRD with irregular thickening of the GBM and sensory neural hearing loss. The mutations of type IV collagen gene(COL4A5) located on the long arm of X chromosome is considered responsible for most of the structural abnormalities in the GBM of Alport patients. Since no definite clinical prognostic predictor has been reported in the disease yet, we designed this study to evaluate the significance of genetic polymorphism of the angiotensin converting enzyme in children with Alport syndrome as a prognostic factor for disease progression. Methods : ACE I/D genotype were examined by PCR amplification of the genomic DNA in 12 patients with Alport syndrome and 12 of their family members. Alport patients were divided into two groups; the conservative group, those who had preserved renal function for more than 10 years of age, the early CRF group, those who had progressed to CRF within 10 years of age. Results : The mean age of onset was $3.45{\pm}2.4$ years in the conservative group, $4.4{\pm}1.2$ years in the early CRF group. Sex ratios were 5:3 and 2:1 in each group. Among 12 cases of patients, 4 cases were in early CRF group and their mean duration of onset to CRF was 4.5 yews(8.9 years of age). Eight patients(67%) were in the conservative group and they had normal renal function for more than 10 years of age(mean duration of renal preservation was 10.6 years). The incidence of II type ACE gene were in 25.0%(3 cases), ID type in 41.7%(5 cases), DD type in 33.3%(4 cases). There was no significant difference between Alport patient and normal control(II type 44.3%, ID type 40.9%, DD type 14.8%). The incidence of DD type of early CRF group were higher than that of the conservative group(75% vs 12.5%)(p<0.05). There was no difference in ACE gene polymorphism between normal Alport family members and control group. Conclusion : Even though there was no significant difference of ACE polymorphism between Alport patients and the normal control group, the incidence of DD type is significantly increased in early CRF group which means DD type of ACE polymorphism has a possibility of being a predictor for early progression to CRF in Alport patients.

• Journal of Gastric Cancer
• /
• v.5 no.1
• /
• pp.10-15
• /
• 2005

Purpose: Recently the role of vitamins, folate in particular, has been emphasized in the maintenance of health. Folate deficiency is known to give rise to developmental delay, immature vascular disease, neural tube defect, acute leukemia, atherosclerotic vascular disease, delivery defects, breast cancer, and particularly gastrointestinal neoplasia. Methylenetetrahydrofolate reductase (MTHFR) is an essential enzyme in folate metaboism, and influences DNA synthesis and DNA methylation. Generally, folate deficiency is associated with gastrointestinal neoplasms. The amino-acid- changing and enzyme-activity-reducing nucleotide polymorphism (766C$\rightarrow$T/ Ala222Val) has been described in the MTHFR polymorphism and leads to low enzyme activity that may reduce the capacity of DNA methylation and possibly uracil mis-incorporation into DNA. These processes may be critical in the oncogenic transformation of human cells, especially in colorectal carcinomas. We investigated the relationship between the MTHFR polymorphism in gastric cancer and the tumor site, the smoking history, and the alcoholic history. Materials and Methods: Ninety-six (96) individuals with gastric cancer and 287 healthy persons were analyzed. Blood sampling was performed, PCR-RFLP was analyzed, and MTHFR polymorphism genotypes of C/C, C/T, and T/T were obtained and analyzed statistically for their correlation. Results: In the gastric cancer group there were 69 ($72\%$) males and 27 ($28\%$) females. There were also 58 cases ($60\%$) involving the gastric lower body, 20 cases ($21\%$) the gastric mid-body, and 18 cases ($19\%$) the gastric upper body. In the control group there were 169 ($59\%$) males and 118 ($41\%$) females. Among the gastric cancer, 56 ($61\%$) smoking patients, 40 ($39\%$) non-smoking patients, 45($47\%$) alcoholic patients, 51 ($53\%$) non-alcoholic patients. In the gastric cancer group, MTHER polymorphisms were C/C in 18 ($19\%$) cases, C/T in 59 ($61\%$) cases, T/T in 19 ($20\%$) cases. In the control group polymorphisms were C/C 116 ($40\%$) cases, C/T 103 ($36\%$) cases, and T/T 68 ($24\%$) cases (P=0.045). In cases of lower gastric body cancer, polymorphisms were C/C in 16 ($24\%$) C/C in 16 ($24\%$) cases and C/T or T/T in 42 ($72\%$) cases. In cases of upper and mid-body cancer, polymorphisms were C/C in 2 ($5\%$) cases and C/T or T/T 36 ($95\%$) cases (P=0.006). In the non-smoking patient group, polymorphisms were C/C in 5 (12%) cases and C/T or T/T in 35 ($88\%$) cases. In the smoking patient group, C/C in 13 ($23\%$) cases and C/T or T/T in 43 ($77\%$) cases (P=0.189). In the non-alcoholic patient group, polymorphisms were C/C in 6 ($12\%$) cases and C/T or T/T in 45 ($88\%$) cases. In the alcoholic patient group, polymorphisms were C/C in 12 ($26\%$) cases and C/T or T/T in 33 ($74\%$) cases (P=0.063) Conclusion: MTHFR polymorphisms are associated with gastric cancer and tumor site, but not with smoking and alcohol drinking.

• 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.