• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.3
• /
• pp.237-246
• /
• 2019

In order to improve the accuracy of the rating prediction of the recommendation model, not only user-item rating data are used but also consider auxiliary information of item such as comments, tags, or descriptions. The traditional approaches use a word-level model of the bag-of-words for the auxiliary information. This model, however, cannot utilize the auxiliary information effectively, which leads to shallow understanding of auxiliary information. Convolution neural network (CNN) can capture and extract feature vector from auxiliary information effectively. Thus, this paper proposes character-level deep-Convolution Neural Network based matrix factorization (Char-DCNN-MF) that integrates deep CNN into matrix factorization for a novel recommendation model. Char-DCNN-MF can deeper understand auxiliary information and further enhance recommendation performance. Experiments are performed on three different real data sets, and the results show that Char-DCNN-MF performs significantly better than other comparative models.

• The Journal of the Convergence on Culture Technology
• /
• v.4 no.3
• /
• pp.241-246
• /
• 2018

Because of the mechanical problems of input camera equipment, image restoration process is performed in order to minimize recognition errors due to the noise problem generated in test data image. The image restoration method resolves the noise problem by examining the numbers and positions of the Direct neighbors and the Indirect neighbors for each pixel constituting the test data. As a result, satisfactory recognition result can be obtained by eliminating the noise problem generated in the test data through the image restoration process as much as possible and also by calculating the differences between the learning data and the test data in the area unit, thereby reducing the possibility of recognition error by the noise problem.

• The Journal of Bigdata
• /
• v.1 no.1
• /
• pp.33-39
• /
• 2016

Recently, predicting personality with the help of smartphone usage becomes very interesting and attention grabbing topic in the field of research. At present there are some approaches towards detecting a user's personality which uses the smartphones usage data, such as call detail records (CDRs), the usage of short message services (SMSs) and the usage of social networking services application. In this paper, we focus on the assessing the correlation between MBTI based user personality and the smartphone usage data. We used $Na{\ddot{i}}ve$ Bayes and SVM classifier for classifying user personalities by extracting some features from smartphone usage data. From analysis it is observed that, among all extracted features facebook usage log working as the best feature for classification of introverts and extraverts; and SVM classifier works well as compared to $Na{\ddot{i}}ve$ Bayes.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.621-623
• /
• 2022

최근 코로나19로 인해 비대면으로 소통할 수 있는 플랫폼에 대한 관심이 증가하고 있으며, 가상 세계의 개념을 도입한 메타버스 플랫폼이 MZ세대의 새로운 SNS로 떠오르고 있다. 아바타를 통해 상호 교류가 가능한 메타버스는 텍스트 기반의 소통뿐만 아니라 음성과 동작 시선 등을 활용하여 변화된 의사소통 방식을 사용한다. 음성을 활용한 소통이 증가함에 따라 다른 이용자에게 불쾌감을 주는 혐오 발언에 대한 신고가 증가하고 있다. 그러나 기존 혐오 발언 탐지 시스템은 텍스트를 기반으로 하여 사전에 정의된 혐오 키워드만 특수문자로 대체하는 방식을 사용하기 때문에 음성 혐오 발언에 대해서는 탐지하지 못한다. 이에 본 논문에서는 인공지능을 활용한 음성 혐오 표현 탐지 시스템을 제안한다. 제안하는 시스템은 음성 데이터의 파형을 통해 은유적 혐오 표현과 혐오 발언에 대한 감정적 특징을 추출하고 음성 데이터를 텍스트 데이터로 변환하여 혐오 문장을 탐지한 결과와 결합한다. 향후, 제안하는 시스템의 현실적인 검증을 위해 시스템 구축을 통한 성능평가가 필요하다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.8
• /
• pp.1947-1954
• /
• 2009

Camera-captured car plate images contain much variation and noise and the character images in a plate are typically very small. We attempted to improve the plate identification efficiency suitable for this undesirable condition. We experimented various image preprocessing and feature extracting methods and the very effective features that can compensate one feature's limitation is determined through extensive experiments. Finally two very effective features that can complement the limitations of each other feature(classifier) are determined and the efficiency is proved by recognition experiments. This approach is very necessary when handling plate character images which are typically small, various, and noisy. Individual classification result, confidence factor, region name relation and feedback verification are comprehensively considered to enhance the overall recognition efficiency. The efficiency of our method is verified by a recognition experiment using real car plate images taken from traffic roads.

• Journal of Ginseng Research
• /
• v.32 no.4
• /
• pp.382-389
• /
• 2008

To achieve a better understanding of protective effects of water extracts of Panax ginseng against TCDD-induced toxicities, we monitored physiological and clinical changes in rat for 4 weeks after administrations of each Panax Ginseng extract or TCDD, and co-administration of the two materials. For this study, 120 male Sprague-Dawley (SD) rats weighing 190-210 g each (8 weeks old) were divided into four groups: TCDD-administered, co-administered group with TCDD and ginseng extract, ginseng extract-administered, and control group. The TCDD-administered group received single dose of TCDD in a corn oil vehicle ($25\;{\mu}g/kg$ body weight) by intraperitoneal administration on Day 1. The Panax ginseng extracts-administered group received intraperitoneally 100 mg/kg body weight every other day for one month. For the co-administered group with TCDD and ginseng extracts, Panax ginseng extracts were intraperitoneally administered to rats at 100 mg/kg body weight every other day for one month after a single intraperitoneal dose of $25\;{\mu}g$ of TCDD/kg body weight on Day 1. Panax ginseng extracts attenuated the mortality induced by TCDD administration. The extracts also slightly attenuated the TCDD-induced body weight loss. Administration of TCDD alone increased liver weight at 2, 5, and 16 days after administration of TCDD. Administration of Panax ginseng extracts rather decreased liver weight through whole the experimental period, but which was statistically insignificant. Administration of TCDD alone at $25\;{\mu}g/kg$ body weight increased both serum enzyme activities of alanine aminotransferase (ALT) and aspartate aminotransferase (AST) at 32 days, indicating that liver damage occurred maximally at that time. Ginseng extract administration caused insignificant changes in serum ALT, but gradually decreased in AST as the exposure time increased. Coadministration of TCDD and ginseng extracts caused serum AST activity to significant recovery to normal value at 16 days and 32 days after exposure to TCDD. The extracts also significantly decreased the TCDD-induced ALT activity after 16 days of TCDD administration. These results suggest that Panax ginseng extracts may possess a protective effect against TCDD-induced toxicities including hepatotoxicity in rats.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.3
• /
• pp.721-726
• /
• 2004

The image binarization is applied frequently as one part of the preprocessing phase for a variety of image processing techniques such as character recognition and image analysis, etc. The performance of binarization algorithms is determined by the selection of threshold value for binarization, and most of the previous binarization algorithms analyze the intensity distribution of the original images by using the histogram and determine the threshold value using the mean value of Intensity or the intensity value corresponding to the valley of the histogram. The previous algorithms could not get the proper threshold value in the case that doesn't show the bimodal characteristic in the intensity histogram or for the case that tries to separate the feature area from the original image. So, this paper proposed the novel algorithm for image binarization, which, first, segments the intensity range of grayscale images to several intervals and calculates mean value of intensity for each interval, and next, repeats the interval integration until getting the final threshold value. The interval integration of two neighborhood intervals calculates the ratio of the distances between mean value and adjacent boundary value of two intervals and determine as the threshold value of the new integrated interval the intensity value that divides the distance between mean values of two intervals according to the ratio. The experiment for performance evaluation of the proposed binarization algorithm showed that the proposed algorithm generates the more effective threshold value than the previous algorithms.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.109-125
• /
• 2019

As interest on intelligent search engines increases, various studies have been conducted to extract and utilize the features related to products intelligencely. In particular, when users search for goods in e-commerce search engines, the 'color' of a product is an important feature that describes the product. Therefore, it is necessary to deal with the synonyms of color terms in order to produce accurate results to user's color-related queries. Previous studies have suggested dictionary-based approach to process synonyms for color features. However, the dictionary-based approach has a limitation that it cannot handle unregistered color-related terms in user queries. In order to overcome the limitation of the conventional methods, this research proposes a model which extracts RGB values from an internet search engine in real time, and outputs similar color names based on designated color information. At first, a color term dictionary was constructed which includes color names and R, G, B values of each color from Korean color standard digital palette program and the Wikipedia color list for the basic color search. The dictionary has been made more robust by adding 138 color names converted from English color names to foreign words in Korean, and with corresponding RGB values. Therefore, the fininal color dictionary includes a total of 671 color names and corresponding RGB values. The method proposed in this research starts by searching for a specific color which a user searched for. Then, the presence of the searched color in the built-in color dictionary is checked. If there exists the color in the dictionary, the RGB values of the color in the dictioanry are used as reference values of the retrieved color. If the searched color does not exist in the dictionary, the top-5 Google image search results of the searched color are crawled and average RGB values are extracted in certain middle area of each image. To extract the RGB values in images, a variety of different ways was attempted since there are limits to simply obtain the average of the RGB values of the center area of images. As a result, clustering RGB values in image's certain area and making average value of the cluster with the highest density as the reference values showed the best performance. Based on the reference RGB values of the searched color, the RGB values of all the colors in the color dictionary constructed aforetime are compared. Then a color list is created with colors within the range of ${\pm}50$ for each R value, G value, and B value. Finally, using the Euclidean distance between the above results and the reference RGB values of the searched color, the color with the highest similarity from up to five colors becomes the final outcome. In order to evaluate the usefulness of the proposed method, we performed an experiment. In the experiment, 300 color names and corresponding color RGB values by the questionnaires were obtained. They are used to compare the RGB values obtained from four different methods including the proposed method. The average euclidean distance of CIE-Lab using our method was about 13.85, which showed a relatively low distance compared to 3088 for the case using synonym dictionary only and 30.38 for the case using the dictionary with Korean synonym website WordNet. The case which didn't use clustering method of the proposed method showed 13.88 of average euclidean distance, which implies the DBSCAN clustering of the proposed method can reduce the Euclidean distance. This research suggests a new color synonym processing method based on RGB values that combines the dictionary method with the real time synonym processing method for new color names. This method enables to get rid of the limit of the dictionary-based approach which is a conventional synonym processing method. This research can contribute to improve the intelligence of e-commerce search systems especially on the color searching feature.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.1
• /
• pp.163-172
• /
• 2007

The web as global network includes text document, video, sound, etc and connects each distributed information using link Through development of web, it accumulates abundant information and the main is text based documents. Most of user use the web to retrieve information what they want. So, numerous researches have progressed to retrieve the text documents using the many methods, such as probability, statistics, vector similarity, Bayesian, and so on. These researches however, could not consider both the subject and the semantics of documents. As a result user have to find by their hand again. Especially, it is more hard to find the korean document because the researches of korean document classification is insufficient. So, to overcome the previous problems, we propose the korean document classification method for semantic retrieval. This method firstly, extracts TF value and RV value of concepts that is included in document, and maps into U-WIN that is korean vocabulary dictionary to select the topic of document. This method is possible to classify the document semantically and showed the efficiency through experiment.

• Journal of the Korean School Mathematics Society
• /
• v.17 no.4
• /
• pp.507-539
• /
• 2014

The algebra is an important tool influencing on a mathematics in general. To make good use of the algebra, it is necessary to transfer from a given situation to a proper algebraic representation. But some research in related to algebraic word problems have reported the difficulty changing to a proper algebraic representation. Our study have focused on transformation and elaboration of algebraic representation. We investigated in detail the responses and perceptions of 29 Grade 7 students while transforming to algebraic representation, only concentrating on the literature expression form the problematic situations given. Most of students showed difficulties in transforming both descriptive and geometric problems to algebraic representation. 10% of them responded wrong answers except only a problem. Four of them were interviewed individually to show their thinking and find the factor influencing on a positive elaboration. As results, we could find some characteristics of their thinking including the misconception that regard the problem finding a functional formula because there are the variables x and y in the problematic situation. In addition, we could find the their fixation which student have to set up the equation. Furthermore we could check that making student explain own algebraic representation was able to become the factor influencing on a positive elaboration. From these, we also discussed about several didactical implications.