• 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.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.10
• /
• pp.239-246
• /
• 2020

In the medical field where artificial intelligence technology is introduced, research related to clinical decision support system(CDSS) in relation to diagnosis and prediction is actively being conducted. In particular, medical imaging-based disease diagnosis area applied AI technologies at various products. However, medical imaging data consists of inconsistent data, and it is a reality that it takes considerable time to prepare and use it for research. This paper describes a one-stop AI learning platform for converting to medical image standard R_CDM(Radiology Common Data Model) and supporting AI algorithm development research based on the dataset. To this, the focus is on linking with the existing CDM(common data model) and model the system, including the schema of the medical imaging standard model and report information for multi-center research based on DICOM(Digital Imaging and Communications in Medicine) tag information. And also, we show the execution results based on generated datasets through the AI learning platform. As a proposed platform, it is expected to be used for various image-based artificial intelligence researches.

• Journal of The Korean Association For Science Education
• /
• v.40 no.1
• /
• pp.1-12
• /
• 2020

In scientific argumentation, students can use rebuttals to escape uncertainty, which, in this case, can be defined as a vague and fuzzy feeling about other students' explanations. As rebuttals can play a critical role in the sophistication of arguments and the alleviation of uncertainty, this study aims to understand the dynamics of uncertainty and rebuttals by exploring the context of the uncertainty experienced by elementary school students in the argumentation of "Why did the kidney beans not germinate?" and to get insights based on the research results. Twenty fourth-grade students and their homeroom teacher in Kyong-Ki province, South Korea, took part in the research. Students engaged in argumentation in five small groups of four students. The researcher collected qualitative data through video transcriptions, student interviews, and field notes. In the data analysis, the researcher employed the constant comparative method to explore in what context students experienced uncertainty and how they used rebuttals. The results of this study were as follows: First, students tried to reduce their uncertainty through argumentation on why the kidney beans did not germinate. Second, students used elaboration-oriented rebuttals, personal opinion-oriented rebuttals, and blame-oriented rebuttals to reduce this uncertainty. However, when they used blame-oriented rebuttals, their uncertainty and negative emotions increased. Third, intervention by the teacher led students to stop using blame-oriented rebuttals. Instead, they employed elaboration-oriented rebuttals to explore why the kidney beans would not sprout, and finally, they escaped uncertainty by discovering an appropriate explanation. Based on the findings of this study, the researcher discussed how the interaction between uncertainty and elaboration-oriented rebuttals could shape and facilitate argument development in elementary school students.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.9 s.351
• /
• pp.149-157
• /
• 2006

Turbo code, a kind of error correction coding technique, has been used in the field of digital mobile communication system. As the number of iterations increases, it can achieves remarkable BER performance over AWGN channel environment. However, if the number of iterations is increased in the several channel environments, any further iteration results in very little improvement, and requires much delay and computation in proportion to the number of iterations. To solve this problems, it is necessary to device an efficient criterion to stop the iteration process and prevent unnecessary delay and computation. In this paper, it proposes an efficient and simple criterion for stopping the iteration process in turbo decoding. By using variance values of LLR in turbo decoder, the proposed algerian can largely reduce the average number of iterations without BER performance degradation in all SNR regions. As a result of simulation, the average number of iterations in the upper SNR region is reduced by about $34.66%{\sim}41.33%$ compared to method using variance values of extrinsic information. the average number of iterations in the lower SNR region is reduced by about $13.93%{\sim}14.45%$ compared to CE algorithm and about $13.23%{\sim}14.26%$ compared to SDR algorithm.

• Journal of Korean Society of Environmental Engineers
• /
• v.37 no.10
• /
• pp.563-572
• /
• 2015

The purpose of this study was to model the effect of flushing discharge on algae removal by multi-purpose weir operation in Yeongsan River (Seungchon Weir) using a 3-dimensional (3D) model. The chlorophyceae Eudorina sp. formed bloom in May 2013. Flushing discharge was conducted in two different ways for algal bloom reduction. To elucidate the spatial variability, a high-resolution 3D model, ELCOM-CAEDYM, was used to simulate the spatial variations of water quality and chl-a over a month. The results showed that ELCOM-CAEDYM could reproduce highly spatially resolved field data at low cost, and showed very good performance in simulating the pattern of algal bloom occurrence. The effect of each flushing discharge operation was analyzed with the results of modeling. The results of case 1, flushing discharge using an open movable weir, showed that the algal bloom between the Seochang Bridge and the Hwangryong River junction is rapidly flushed after operating the movable weir, but the residual algae remained in the weir pool as the discharge decreased. However, the results of case 2, fixed weir overflow with a small hydropower stop, showed that most of the algae was removed after flushing discharge and the effect of algae removal was much bigger than that in case 1, as per modeling results and observed data.

• Journal of Bio-Environment Control
• /
• v.27 no.3
• /
• pp.206-212
• /
• 2018

As many consumers prefer good quality food, farms have used various facilities to cultivate products for satisfying their desires. Among them, the most representative facilities are plastic and glass multi-span greenhouse. The height of both plastic greenhouse and glass greenhouse is around three meters high in Korea. As a result, the crop productivity is limited. The solution is to increase the height of the greenhouses to improve the greenhouses' environment. The device for raising columns consists of a stop device, a pneumatic cylinder, and a vertical member. Pneumatic cylinders were designed with a diameter of 160 mm and a stroke length of 50 mm, taking into consideration the safety factor of 1.5. In addition, the air flow was controlled by nozzle to achieve a time of less than 30 seconds per stroke. It was calculated that $21.5L{\cdot}min^{-1}$ of air was needed to complete in less than 30 seconds. Accordingly, the diameter of the nozzle is designed to be 0.5 mm. When the pressure was 0.9 MPa, the average raising force was 13,805N, which was close to the calculated value of 15,612N. The field test results show that any inconsistency in the row columns was not generated. and that it is considered applicable to the actual glass and plastic greenhouses.

• Food Science and Preservation
• /
• v.5 no.4
• /
• pp.326-330
• /
• 1998

Freeze storage technique is widely used for food processing to keep freshness and quality of the product. This technique was applied to fresh, unshelled groundnut to develop a new type of product which could maintain fresh taste and nutritive values even after several months of storage. The groundnut varieties, Daepungtangkong, Daekwangtangkong and Sindaekwangtangkong were grown at the experimental field of NCES in 1996. Immatured pods or groundnut were harvested around 20 to 3o days before full maturity, washed, and steamed at 100$^{\circ}C$ for 5 min. to stop enzyme activity. After vacuum packing (at -760mmHg for 10 min.) with 0.08mm polyvinyldichloride film, the pods were immediately frozen at -70$^{\circ}C$ for 24h and transfered at -20$^{\circ}C$ for long-term storage. Physico-chemical properties of frozen vegetable groundnut were investigated at 2 months after storage and compared to those of conventionally dried groundnut. After 2 months storage, the thawed kernels were very palatable with softness and fresh taste. Acid value and hardness (measured as the compression force on the probe of a texture analyzer) were much lower in frozen vegetable groundnut than those in the air-dried ones. Presence of free sugars is one of the important factors affecting groundnut taste, and the free sugar contents were considerably decreased in the frozen vegetable groundnut compared to freshly harvested groundnut. But in dried groundnut no free sugar was detected.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.7 s.349
• /
• pp.143-149
• /
• 2006

Turbo code, a kind of error correction coding technique, has been used in the field of digital mobile communication system. As the number of iterations increases, it can achieves remarkable BER performance over AWGN channel environment. However, if the number of iterations is increased in the several channel environments, any further iteration results in very little improvement, and requires much delay and computation in proportion to the number of iterations. To solve this problems, it is necessary to device an efficient criterion to stop the iteration process and prevent unnecessary delay and computation. In this paper, it proposes an efficient and simple criterion for stopping the iteration process in turbo decoding. By using sign changed ratio of extrinsic information values in turbo decoder, the proposed algorithm can largely reduce the average number of iterations without BER performance degradation. As a result of simulations, the average number of iterations is reduced by about $12.48%{\sim}22.22%$ compared to CE algorithm and about $20.43%{\sim}54.02%$ compared to SDR algorithm.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.6
• /
• pp.679-685
• /
• 2011

This paper presents an algorithm identifying devices that generate observed mixed signals that are collected at main power-supply line. The proposed algorithm, which is necessary for low cost electric power monitoring system at appliance-level, that is non-intrusive load monitoring system, divides incoming mixed signal into multiple time intervals, calculating difference-signals between consecutive time interval, and identifies which device is operating at the time interval by analysing the difference-signals. Since the features of one device can remain when the time interval is short enough and the features are independent and additive, well-known classification algorithms can be used to classify the difference-signals with features of N individual devices, otherwise $2^N$ features might be necessary. The proposed algorithm was verified using data mixed in a laboratory with individual devices's data collected from field. When maximum 4 devices operate or stop sequentially and when features satisfy the requirements of proposed algorithm, the proposed algorithm resulted nearly 100% success rate under the constrained test condition. In order to apply the proposed algorithm in real world, the number devices shall increase, the time interval shall be smaller and the pattern of mixture shall be more diverse. However we can expect, if features used follow guidelines of proposed algorithm, future system could have certain level of performance without the guideline.

• International Journal of Highway Engineering
• /
• v.9 no.3
• /
• pp.83-89
• /
• 2007

When allocating traffic signal at the signalized intersection, minimum green time and clearance time for bicyclists should be significantly considered in order to enhance safety aspects to bicyclists when crossing intersections, especially where intersections with exclusive bicycle paths that are physically separated from pedestrians. In this study, field measurements related to bicycle crossing time, including minimum peen time and clearance time, were collected and analyzed according to bicycles crossing types at the signalized intersections where high rate of bicyclists exists. Three types of bicycle crossing are defined as follows 1) stopping: completely stop before crossing (at least one foot on found) 2) riding: crossing with riding bicycle 3) pulling: crossing without riding bicycles. Minimum green time based on pedestrian speeds should be used as crossing time in this case. For bicyclists, speed of bicycle that is applicable to estimate the minimum green time is in the 1.36m/sec($15^{th}$ percentile) to 1.60m/sec($25^{th}$ percentile) range in case of its stopping. Also it is in the 0.75($15^{th}$ percentile) to 0.87($25^{th}$ percentile) range for pulling at crosswalk. In addition, speed of bicycle to consider for calculating the clearance time is in the 2.51m/sec($15^{th}$ percentile) to 2.79m/sec($25^{th}$ percentile). These values also resulted from $15^{th}$ percentile or $25^{th}$ percentile speeds of riding. The results of this study are expected to be supported in traffic signal allocation process, reflecting bicyclists' characteristics.