• Journal of Intelligence and Information Systems
• /
• v.23 no.3
• /
• pp.119-138
• /
• 2017

Recently, SNS has become an important channel for marketing as well as personal communication. However, cybercrime has also evolved with the development of information and communication technology, and illegal advertising is distributed to SNS in large quantity. As a result, personal information is lost and even monetary damages occur more frequently. In this study, we propose a method to analyze which sentences and documents, which have been sent to the SNS, are related to financial fraud. First of all, as a conceptual framework, we developed a matrix of conceptual characteristics of cybercriminality on SNS and emergency management. We also suggested emergency management process which consists of Pre-Cybercriminality (e.g. risk identification) and Post-Cybercriminality steps. Among those we focused on risk identification in this paper. The main process consists of data collection, preprocessing and analysis. First, we selected two words 'daechul(loan)' and 'sachae(private loan)' as seed words and collected data with this word from SNS such as twitter. The collected data are given to the two researchers to decide whether they are related to the cybercriminality, particularly financial fraud, or not. Then we selected some of them as keywords if the vocabularies are related to the nominals and symbols. With the selected keywords, we searched and collected data from web materials such as twitter, news, blog, and more than 820,000 articles collected. The collected articles were refined through preprocessing and made into learning data. The preprocessing process is divided into performing morphological analysis step, removing stop words step, and selecting valid part-of-speech step. In the morphological analysis step, a complex sentence is transformed into some morpheme units to enable mechanical analysis. In the removing stop words step, non-lexical elements such as numbers, punctuation marks, and double spaces are removed from the text. In the step of selecting valid part-of-speech, only two kinds of nouns and symbols are considered. Since nouns could refer to things, the intent of message is expressed better than the other part-of-speech. Moreover, the more illegal the text is, the more frequently symbols are used. The selected data is given 'legal' or 'illegal'. To make the selected data as learning data through the preprocessing process, it is necessary to classify whether each data is legitimate or not. The processed data is then converted into Corpus type and Document-Term Matrix. Finally, the two types of 'legal' and 'illegal' files were mixed and randomly divided into learning data set and test data set. In this study, we set the learning data as 70% and the test data as 30%. SVM was used as the discrimination algorithm. Since SVM requires gamma and cost values as the main parameters, we set gamma as 0.5 and cost as 10, based on the optimal value function. The cost is set higher than general cases. To show the feasibility of the idea proposed in this paper, we compared the proposed method with MLE (Maximum Likelihood Estimation), Term Frequency, and Collective Intelligence method. Overall accuracy and was used as the metric. As a result, the overall accuracy of the proposed method was 92.41% of illegal loan advertisement and 77.75% of illegal visit sales, which is apparently superior to that of the Term Frequency, MLE, etc. Hence, the result suggests that the proposed method is valid and usable practically. In this paper, we propose a framework for crisis management caused by abnormalities of unstructured data sources such as SNS. We hope this study will contribute to the academia by identifying what to consider when applying the SVM-like discrimination algorithm to text analysis. Moreover, the study will also contribute to the practitioners in the field of brand management and opinion mining.

• Journal of Korean Elementary Science Education
• /
• v.41 no.4
• /
• pp.701-724
• /
• 2022

In this study, the Nature of Science (NOS) instrument for elementary school students in the form of open questionnaires was developed specifically to reveal elementary school students' perceptions of the NOS, and its validity and effectiveness were investigated. To develop a NOS instrument for elementary school students, problems that may occur when applying the existing NOS instruments to elementary school students were analyzed and based on this, the development direction of the NOS instrument was established. In addition, after selecting seven NOS types suitable for the level of elementary school students, the preliminary instrument was produced by modifying and supplementing the items in the existing instruments for each type or by developing new items. Finally, the NOS instrument consisting of eight questions was developed by adding one question asking for a comprehensive understanding of science to seven questions related to each type of NOS after a content validity test of the science education expert group. To verify the practical effect of the developed instrument, pre- and post-tests were conducted on 50 students in two classes of sixth grade at two elementary schools in Seoul: 'existing instrument → development instrument' in one class, and 'development instrument → existing instrument' in the other class. The collected data were then compared and evaluated through summary content analysis and analyzed by executing the Wilcoxon signed-rank test. As a result of comparing and analyzing students' responses to the existing NOS instrument and the developed NOS instrument, students' perspectives on the NOS were more diverse when using the developed instrument, and the level of error in the response caused by misinterpreting the intention of the question was reduced. In addition, when using the developed instrument, the responses of the majority of students at a statistically significant level changed more specifically. In this study, the implications for the development of NOS instruments suitable for elementary school students were discussed based on these results.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.79-104
• /
• 2020

Recently, as deep learning has attracted attention, the use of deep learning is being considered as a method for solving problems in various fields. In particular, deep learning is known to have excellent performance when applied to applying unstructured data such as text, sound and images, and many studies have proven its effectiveness. Owing to the remarkable development of text and image deep learning technology, interests in image captioning technology and its application is rapidly increasing. Image captioning is a technique that automatically generates relevant captions for a given image by handling both image comprehension and text generation simultaneously. In spite of the high entry barrier of image captioning that analysts should be able to process both image and text data, image captioning has established itself as one of the key fields in the A.I. research owing to its various applicability. In addition, many researches have been conducted to improve the performance of image captioning in various aspects. Recent researches attempt to create advanced captions that can not only describe an image accurately, but also convey the information contained in the image more sophisticatedly. Despite many recent efforts to improve the performance of image captioning, it is difficult to find any researches to interpret images from the perspective of domain experts in each field not from the perspective of the general public. Even for the same image, the part of interests may differ according to the professional field of the person who has encountered the image. Moreover, the way of interpreting and expressing the image also differs according to the level of expertise. The public tends to recognize the image from a holistic and general perspective, that is, from the perspective of identifying the image's constituent objects and their relationships. On the contrary, the domain experts tend to recognize the image by focusing on some specific elements necessary to interpret the given image based on their expertise. It implies that meaningful parts of an image are mutually different depending on viewers' perspective even for the same image. So, image captioning needs to implement this phenomenon. Therefore, in this study, we propose a method to generate captions specialized in each domain for the image by utilizing the expertise of experts in the corresponding domain. Specifically, after performing pre-training on a large amount of general data, the expertise in the field is transplanted through transfer-learning with a small amount of expertise data. However, simple adaption of transfer learning using expertise data may invoke another type of problems. Simultaneous learning with captions of various characteristics may invoke so-called 'inter-observation interference' problem, which make it difficult to perform pure learning of each characteristic point of view. For learning with vast amount of data, most of this interference is self-purified and has little impact on learning results. On the contrary, in the case of fine-tuning where learning is performed on a small amount of data, the impact of such interference on learning can be relatively large. To solve this problem, therefore, we propose a novel 'Character-Independent Transfer-learning' that performs transfer learning independently for each character. In order to confirm the feasibility of the proposed methodology, we performed experiments utilizing the results of pre-training on MSCOCO dataset which is comprised of 120,000 images and about 600,000 general captions. Additionally, according to the advice of an art therapist, about 300 pairs of 'image / expertise captions' were created, and the data was used for the experiments of expertise transplantation. As a result of the experiment, it was confirmed that the caption generated according to the proposed methodology generates captions from the perspective of implanted expertise whereas the caption generated through learning on general data contains a number of contents irrelevant to expertise interpretation. In this paper, we propose a novel approach of specialized image interpretation. To achieve this goal, we present a method to use transfer learning and generate captions specialized in the specific domain. In the future, by applying the proposed methodology to expertise transplant in various fields, we expected that many researches will be actively conducted to solve the problem of lack of expertise data and to improve performance of image captioning.

• Journal of the Korean Applied Science and Technology
• /
• v.36 no.1
• /
• pp.324-332
• /
• 2019

Most countries including Korea and Indonesia have strong policy for implementing biofuels like biodiesel. Shortage of the oil feedstock is the main barrier for increasing the supply of biodiesel fuel. In this study, in order to improve the stability of feedstock supply and lower the biodiesel production cost, the feasibility of biodiesel production using two types of Indonesian tropical crop oils, pressed at different harvesting times, were investigated. R. Trisperma oils, a high productive non-edible feedstocks, were investigated to produce biodiesel by esterification and transesterification because of it's high impurity and free fatty acid contents. the kindly provided oils from Indonesia were required to perform the filtering and water removal process to increase the efficiency of the esterificaton and transesterification reactions. The esterification used heterogeneous acid catalyst, Amberlyst-15. Before the reaction, the acid value of two types oil were 41, 17 mg KOH/g respectively. After the pre-esterification reaction, the acid value of oils were 3.7, 1.8 mg KOH/g respectively, the conversions were about 90%. Free fatty acid content was reduced to below 2%. Afterwards, the transesterification was performed using KOH as the base catalyst for transesterification. The prepared biodiesel showed about 93% of FAME content, and the total glycerol content was 0.43%. It did not meet the quality specification(FAME 96.5% and Total glycerol 0.24%) since the tested oils were identified to have a uncommon fatty acid, generally not found in vegetable oils, ${\alpha}$-eleostearic acid with much contents of 10.7~33.4%. So, it is required to perform the further research on reaction optimization and product purification to meet the fuel quality standards. So if the biodiesel production technology using un-utilized non-edible feedstock oils is successfully developed, stable supply of the feedstock for biodiesel production may be possible in the future.

• Journal of Chest Surgery
• /
• v.36 no.9
• /
• pp.651-658
• /
• 2003

Since the first implanted in September 1997, the use of On-X prosthetic heart valve has been increasing around in the world. This study was designed to assess the feasibility, safety, and the postoperative hemodynamics with this new valve in clinical setting. Material and Method: The current study was carried out on 52 patients undergoing aortic valve replacement with this prosthesis between April 1999 to August 2002 at Chonnam National University Hospital to evaluate the surgical results. 52％ of the patients were male and the average age at implant was 50$\pm$13 years. The study followed the guidelines of the AATS/STS. Preoperatively, 32(61.5％) patients were in NYHA functional class III or IV and 2 patients had previous aortic valve surgery. Concomitant cardiac surgery was performed in 71.1％. The implanted valve sizes were 19 mm in 13 patients, 21 mm in 26, 23 mm in 10 and 25 mm in 3, respectively. Mean follow-up was 16.6$\pm$10.5 months (1∼39 months). Echocardiographic assessment was performed pre- and immediate postoperatively, as well as 3, 6, 12 months after surgery, evaluating pressure loss and regression of left ventricular hypertrophy. Result: Mean cardiopulmonary bypass time was 191$\pm$94.7 minutes with an aortic cross-clamp time of 142$\pm$51.7 minutes. There was no early and late mortality, Freedom from adverse events at 1 year in the study were as follows: thromboembolism, 95.6$\pm$6％; bleeding events, 90.2$\pm$4％; paravalvular leakage 92.3$\pm$4％; and overall valve-related morbidity at 1 year was 76.6$\pm$3％. There were no cases of valve thrombosis, prosthetic valve endocarditis and structural or non-structural failure. Left ventricular function at 12 months after surgery (EF=62.7$\pm$9.8％) revealed a statistically significant improvement compared to preoperative investigation (EF=55.8$\pm$15.9％, p=0.006). Left ventricular mass index was 247.3$\pm$122.3 g/$m^2$ on preoperative echocardiographic study, but regressed to 155.5$\pm$58.2 g/$m^2$ at postoperative 1 year (p=0.002). Over the follow-up period a further decrease of peak transvalvular gradients was observed in all patients: 62.5$\pm$38.0 mmHg on preoperative assessment, 18.2$\pm$6.8 mmHg at immediate postoperative period (p < 0.0001), 7.6$\pm$5.09 mmHg (p<0.0001) at 6 month, 18.0$\pm$10.8 mmHg (p<0.0001) at 1 year. Conclusion: The On-X prosthetic heart valve performs satisfactorily in the first 1 year period. Clinical outcome by examining NYHA functional classification revealed especially good results. Effective regression of left ventricular hypertrophy and statistically significant decrease of transvalvular gradient were observed over the first year, but longer-term follow-up of this patient group is needed to establish the expected rates for late valve-related events as well as the long-term clinical efficacy of this valve.