• Journal of Intelligence and Information Systems
• /
• v.27 no.4
• /
• pp.73-95
• /
• 2021

This study uses Node2vec graph embedding method and Light GBM link prediction to explore undeveloped export candidate countries in Korea's food and beverage industry. Node2vec is the method that improves the limit of the structural equivalence representation of the network, which is known to be relatively weak compared to the existing link prediction method based on the number of common neighbors of the network. Therefore, the method is known to show excellent performance in both community detection and structural equivalence of the network. The vector value obtained by embedding the network in this way operates under the condition of a constant length from an arbitrarily designated starting point node. Therefore, it has the advantage that it is easy to apply the sequence of nodes as an input value to the model for downstream tasks such as Logistic Regression, Support Vector Machine, and Random Forest. Based on these features of the Node2vec graph embedding method, this study applied the above method to the international trade information of the Korean food and beverage industry. Through this, we intend to contribute to creating the effect of extensive margin diversification in Korea in the global value chain relationship of the industry. The optimal predictive model derived from the results of this study recorded a precision of 0.95 and a recall of 0.79, and an F1 score of 0.86, showing excellent performance. This performance was shown to be superior to that of the binary classifier based on Logistic Regression set as the baseline model. In the baseline model, a precision of 0.95 and a recall of 0.73 were recorded, and an F1 score of 0.83 was recorded. In addition, the light GBM-based optimal prediction model derived from this study showed superior performance than the link prediction model of previous studies, which is set as a benchmarking model in this study. The predictive model of the previous study recorded only a recall rate of 0.75, but the proposed model of this study showed better performance which recall rate is 0.79. The difference in the performance of the prediction results between benchmarking model and this study model is due to the model learning strategy. In this study, groups were classified by the trade value scale, and prediction models were trained differently for these groups. Specific methods are (1) a method of randomly masking and learning a model for all trades without setting specific conditions for trade value, (2) arbitrarily masking a part of the trades with an average trade value or higher and using the model method, and (3) a method of arbitrarily masking some of the trades with the top 25% or higher trade value and learning the model. As a result of the experiment, it was confirmed that the performance of the model trained by randomly masking some of the trades with the above-average trade value in this method was the best and appeared stably. It was found that most of the results of potential export candidates for Korea derived through the above model appeared appropriate through additional investigation. Combining the above, this study could suggest the practical utility of the link prediction method applying Node2vec and Light GBM. In addition, useful implications could be derived for weight update strategies that can perform better link prediction while training the model. On the other hand, this study also has policy utility because it is applied to trade transactions that have not been performed much in the research related to link prediction based on graph embedding. The results of this study support a rapid response to changes in the global value chain such as the recent US-China trade conflict or Japan's export regulations, and I think that it has sufficient usefulness as a tool for policy decision-making.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.9
• /
• pp.403-408
• /
• 2015

Kinect sensors have the ability to recognize the behavior and voice of the user. Due to its low-cost and high accessibility, Kinect sensors have been used in various fields, including healthcare, education and so on. In this paper, we propose to use Kinect in piano education. Specifically, the proposed method first recognizes the coordinate values of user's posture, compares them with coordinate values of teacher's posture and provide real-time feedbacks to the user. This enables user to keep the correct posture even when he is learning piano without a teacher. However, since the piano education is a long process, it is difficult to achieve the correct posture as a teacher immediately. Thus, we propose a user-oriented method to measure the error tolerance rate. The proposed method is the first feedback based piano education system that uses Kinect sensors.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.1
• /
• pp.53-59
• /
• 2008

Recently, vision-based hand gesture recognition techniques have been developed for assisting elderly and disabled people to control home appliances. Frequently occurred problems which lower the hand gesture recognition rate are due to the inter-person variation and intra-person variation. The recognition difficulty caused by inter-person variation can be handled by using user dependent model and model selection technique. And the recognition difficulty caused by intra-person variation can be handled by using fuzzy logic. In this paper, we propose multivariate fuzzy decision tree learning and classification method for a hand motion recognition system for multiple users. When a user starts to use the system, the most appropriate recognition model is selected and used for the user.

• The Journal of Bigdata
• /
• v.1 no.1
• /
• pp.61-66
• /
• 2016

With big data analysis, companies use the customized marketing strategy based on customer's information. However, because of the concerns about privacy issue and identity theft, people start erasing their personal information or changing the privacy settings on social network site. Facebook, the most used social networking site, has the feature called 'Likes' which can be used as a tool to predict user's demographic profiles, such as sex and age range. To make accurate analysis model for the study, 'Likes' data has been processed by using Gaussian RBF and nFactors for dimensionality reduction. With random Forest and 5-fold cross-validation, the result shows that sex has 75% and age has 97.85% accuracy rate. From this study, we expect to provide an useful guideline for companies and marketers who are suffering to collect customers' data.

• Journal of Gastric Cancer
• /
• v.8 no.1
• /
• pp.27-34
• /
• 2008

Purpose: Many recent studies have reported on the feasibility and usefulness of laparoscopy assisted distal gastrectomy (LADG) for treating early gastric cancer. On the other hand, there has been few reports about laparoscopy assisted total gastrectomy (LATG) because upper located gastric cancer is relatively rare and the surgical technique is more difficult than that for LADG, We now present our procedure and results of performing LATG for the gastric cancer located in the upper or middle portion of the stomach. Materials and Methods: From Jan 2005 to Sep 2007, 96 patients underwent LATG by four surgeons at the Asan Medical Center, Seoul, Korea. Among them, 48 consecutive patients who were operated on by asingle surgeon were analyzed with respect to the clinicopathological features, the surgical results and the postoperative courses with using the prospectively collected laparoscopy surgery data. Results: There was no conversion to open surgery during LATG. For all the reconstructions, Roux-en Y esophago-jejunostomy and D1+beta lymphadenectomy were the standard procedures. The mean operation time was $212{\pm}67$ minutes. The mean total number of retrieved lymph nodes was $28.9{\pm}10.54$ (range: $12{\sim}64$) and all the patients had a clear proximal resection margin in their final pathologic reports. The mean time to passing gas, first oral feeding and discharge from the hospital was 2.98, 3.67 and 7.08 days, respectively. There were 5 surgical complications and 2 non-surgical complications for 5 (10.4%) patients, and there was no mortality. None of the patients needed operation because of complications and they recovered with conservative treatments. The mean operation time remained constant after 20 cases and so a learning curve was present. The morbidity rate was not different between the two periods, but the postoperative course was significantly better after the learning curve. Analysis of the factors contributing to the postoperative morbidity, with using logistic regression analysis, showed that the 8MI is the only contributing factor forpostoperative complications (P=0.029, HR=2.513, 95% CI=1.097-5.755). Conclusions: LATG with regional lymph node dissection for upper and middle early gastric cancer is considered to be a safe, feasible method that showed an excellent postoperative course and acceptable morbidity. BMI should be considered in the patient selection at the beginning period because of the impact of the BMI on the postoperative morbidity.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.453-462
• /
• 2021

A lot of license plate data is required for car number recognition. License plate data needs to be balanced from past license plates to the latest license plates. However, it is difficult to obtain data from the actual past license plate to the latest ones. In order to solve this problem, a license plate recognition study through deep learning is being conducted by creating a synthetic license plates. Since the synthetic data have differences from real data, and various data augmentation techniques are used to solve these problems. Existing data augmentation simply used methods such as brightness, rotation, affine transformation, blur, and noise. In this paper, we apply a style transformation method that transforms synthetic data into real-world data styles with data augmentation methods. In addition, real license plate data are noisy when it is captured from a distance and under the dark environment. If we simply recognize characters with input data, chances of misrecognition are high. To improve character recognition, in this paper, we applied the DeblurGANv2 method as a quality improvement method for character recognition, increasing the accuracy of license plate recognition. The method of deep learning for license plate detection and license plate number recognition used YOLO-V5. To determine the performance of the synthetic license plate data, we construct a test set by collecting our own secured license plates. License plate detection without style conversion recorded 0.614 mAP. As a result of applying the style transformation, we confirm that the license plate detection performance was improved by recording 0.679mAP. In addition, the successul detection rate without image enhancement was 0.872, and the detection rate was 0.915 after image enhancement, confirming that the performance improved.

• The Journal of the Korea Contents Association
• /
• v.10 no.1
• /
• pp.19-26
• /
• 2010

This paper proposes a classifier based on rectangular feature to detect face in real time. The goal is to realize a strong detection algorithm which satisfies both efficiency in calculation and detection performance. The proposed algorithm consists of the following three stages: Feature creation, classifier study and real time facial domain detection. Feature creation organizes a feature set with the proposed five rectangular features and calculates the feature values efficiently by using SAT (Summed-Area Tables). Classifier learning creates classifiers hierarchically by using the AdaBoost algorithm. In addition, it gets excellent detection performance by applying important face patterns repeatedly at the next level. Real time facial domain detection finds facial domains rapidly and efficiently through the classifier based on the rectangular feature that was created. Also, the recognition rate was improved by using the domain which detected a face domain as the input image and by using PCA and KNN algorithms and a Class to Class rather than the existing Point to Point technique.

• Convergence Security Journal
• /
• v.8 no.2
• /
• pp.63-70
• /
• 2008

In order not to make the malwares be easily analyzed, the hackers apply various anti-reversing and obfuscation techniques to the malwares. However, as the more anti-revering techniques are applied to the malwares the more abnormal characteristics in the PE file's header which are not shown in the normal PE file, could be observed. In this letter, a new malware detection technique is proposed based on this observation. For the malware detection, we define the Characteristics Vector(CV) which can represent the characteristics of a PE file's header. In the learning phase, we calculate the average CV(ACV) of malwares(ACVM) and normal files(ACVN). To detect the malwares we calculate the 2 Weighted Euclidean Distances(WEDs) from a file's CV to ACVs and they are used to decide whether the file is a malware or not. The proposed technique is very fast and detection rate is fairly high, so it could be applied to the network based attack detection and prevention devices. Moreover, this technique is could be used to detect the unknown malwares because it does not utilize a signature but the malware's characteristics.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.31 no.6
• /
• pp.1084-1091
• /
• 2002

Mortierella alpina, a common soil fungus, is the most efficient organism for production of production acid presently known. Since arachidonic acid are important in human brain and retina development, it was undertaken the growing effect containing diet as a food ingredient. Arachidonic acid rich oil derived from Mortierella alpina, was subjected to a program of studies to establish for use in diet supplement. This study was compared the growth and learning effect of fungal oil rich in arachidonic acid by incorporated into diets ad libitum. Sprague-Dawley rats received experimental diets 5 groups (standard AIN 93 based control with beef tallow, extract oil 8%, and 4%, and Mortierella alpina in diet 10% and 20%) over all experiment duration (pre-mating, mating, gestation, lactation, and after weaning 4 weeks). Pups born during this period consumed same diets after wean for 4 weeks. There was no statistical significance of diet effects in reproductive performance and fertility from birth to weaning. But the groups of Mortierella alpine diet were lower of weight gain and diet intake after weaning. The serum lipids were significantly different with diet groups, higher TG in LO (oil 4%) group of dams, and higher total cholesterol in LF (M. alpina 10%) of pups, although serum albumin content was not significantly different in diet group. The spent-time and memory effect within 4 weeks of T-Morris water maze pass test in dam and 7-week- age pups did not differ in diet groups. On the count of backing error in weaning period of pups was lower in HO(extracted oil 8%) group. In the group of 10% and 20% Mortierella alpina diet, DNA content was lower in brain with lower body weight, but liver DNA relative to body weight was higher than control. Further correlation analyses would be needed DNA and arachidonic acid intakes, with Mortierella alpina diet digestion rate.

• KIISE Transactions on Computing Practices
• /
• v.21 no.11
• /
• pp.681-688
• /
• 2015

The k nearest neighbor (k-NN) graph construction is an important operation with many web-related applications, including collaborative filtering, similarity search, and many others in data mining and machine learning. Despite its many elegant properties, the brute force k-NN graph construction method has a computational complexity of $O(n^2)$, which is prohibitive for large scale data sets. Thus, (Key, Value)-based distributed framework, MapReduce, is gaining increasingly widespread use in Locality Sensitive Hashing which is efficient for high-dimension and sparse data. Based on the two-stage strategy, we engage the locality sensitive hashing technique to divide users into small subsets, and then calculate similarity between pairs in the small subsets using a brute force method on MapReduce. Specifically, generating a candidate group stage is important since brute-force calculation is performed in the following step. However, existing methods do not prevent large candidate groups. In this paper, we proposed an efficient algorithm for approximate k-NN graph construction by regrouping candidate groups. Experimental results show that our approach is more effective than existing methods in terms of graph accuracy and scan rate.