• Journal of the Korean Society for information Management
• /
• v.30 no.1
• /
• pp.285-302
• /
• 2013

This study identified topic shifts and patterns over time by analyzing an enormous amount of Twitter data whose characteristics are high accessibility and briefness. First, we extracted keywords for a certain product and used them for representing the topic network allows for intuitive understanding of keywords associated with topics by nodes and edges by co-word analysis. We conducted temporal analysis of term co-occurrence as well as topic modeling to examine the results of network analysis. In addition, the results of comparing topic shifts on Twitter with the corresponding retrieval results from newspapers confirm that Twitter makes immediate responses to news media and spreads the negative issues out quickly. Our findings may suggest that companies utilize the proposed technique to identify public's negative opinions as quickly as possible and to apply for the timely decision making and effective responses to their customers.

• Journal of IKEEE
• /
• v.5 no.2 s.9
• /
• pp.190-200
• /
• 2001

This paper is addressed to welding defect feature vector selection and implementation method of welding defect classifier using fuzzy techniques. We compare IAV, zero-crossing number as time domain analysis, power spectrum coefficient as frequency domain, histogram as both domain for welding defect feature selection. We choose histogram as feature vector by graph analysis and find out that maximum frequent occurrence number and section of corresponding signal scale in relative histogram show obvious difference between normal welding and voiding with penetration depth defect. We implement a fuzzy welding defect classifier using these feature vector, test it to verify its effectiveness for 695 welding data frame which consist of 4000 sampled data. As result of test, correct classification rate is 92.96%. Lab experimental results show a effectiveness of fuzzy welding defect classifier using relative histogram for practical Laser welding monitoring system in industry.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.5
• /
• pp.203-208
• /
• 2018

In this paper, we selected power and power distribution facilities corresponding to urban infrastructure from the types of damage that could be caused by earthquakes and studied how they were calculated to damage. To calculate the damage, a graph of the magnitude of the damage was produced by applying the vulnerability curve calculation formula, which can be calculated for each type and type of facility. The scale of the earthquake and the probability of the occurrence of damage by the maximum earthquake acceleration were shown in the form of a vulnerability rate when the earthquake occurred in the urban infrastructure facility for utilizing the calculation result. It also applied a method of quantifying the fragility, which is a method of converting the calculated fragility into an integrated form, to represent a constant value for the magnitude of the damage. Continuing research, such as the method applied in this paper, could help identify in advance the types of structures affected by an earthquake and respond to reducing damage.

• International Journal of Highway Engineering
• /
• v.14 no.3
• /
• pp.41-48
• /
• 2012

In this study the negative skin friction test of foundation pile was performed in order to monitor the negative skin frictional force acting on the steel pipe pile installed in soft soil. The monitored frictional stresses obtained from the long-term loading test. Through the long-term frictional stress monitoring test, the economical period for the construction of the superstructure was determined. The following conclusion were derived from this study: (1) In soft soil, negative skin friction increases with the increase in the rate of settlement. (2) In the friction relationship graph, the period where there is no frictional strain increase is verified and the time for the construction of the superstructure is determined. (3) The pile loading test was performed and the negative skin friction was compared with the test results. It was determined that the negative skin friction after driving was larger than the negative skin friction obtained from the loading test. 15 days after the construction, the monitored value was similar with the theoretical data. (4) It was determined that even during the occurrence of negative skin friction an economical construction management can be performed using the long-term monitoring method of negative skin friction.

• Journal of The Korean Association of Information Education
• /
• v.19 no.4
• /
• pp.517-524
• /
• 2015

In this paper, to find out the direction of interest related to the SW education, SW education news data were gathered and its contents were analyzed. The topic analysis of SW education news was performed by collecting the data of July 23, 2013 to October 19, 2015. By analyzing the relationship among the most mentioned top 20 words with the web crawling using R, the result indicated that the 20 words are the closely relevant data as the thickness of the node size of the 20 words was balancing each other in the co-occurrence matrix graph focusing on the 'SW education' word. Moreover, our analysis revealed that the data were mainly composed of the topics about SW talent, SW support Program, SW educational mandate, SW camp, SW industry and the job creation. This could be used for big data analysis to find out the thoughts and interests of such people in the SW education.

• Proceedings of the Korea Contents Association Conference
• /
• 2008.05a
• /
• pp.84-86
• /
• 2008

The customer relation marketing in which companies can utilize to control and to get the filtered information efficiently has appeared. It is applying data mining to build the management that can even predict and recommend products to customers. In this paper, we proposed the adaptive customer relation management strategies using the association rules of data mining. The proposed method uses the association rules composes frequent customers with occurrence of candidate customer set creates the rules of associative customers. We analyzed the efficient feature of purchase customers using the hyper graph partition according to the lift of creative association rules. Therefore, we discovered strategies of the cross-selling and the up-selling about customers.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.3
• /
• pp.79-84
• /
• 2021

A feature extraction method capable of reflecting features well while mainaining the properties of data is required in order to process high-dimensional data. The principal component analysis method that converts high-level data into low-dimensional data and express high-dimensional data with fewer variables than the original data is a representative method for feature extraction of data. In this study, we propose a principal component analysis method based on adaptive correlation when selecting principal component variables in principal component analysis for data feature extraction when the data is high-dimensional. The proposed method analyzes the principal components of the data by adaptively reflecting the correlation based on the correlation between the input data. I want to exclude them from the candidate list. It is intended to analyze the principal component hierarchy by the eigen-vector coefficient value, to prevent the selection of the principal component with a low hierarchy, and to minimize the occurrence of data duplication inducing data bias through correlation analysis. Through this, we propose a method of selecting a well-presented principal component variable that represents the characteristics of actual data by reducing the influence of data bias when selecting the principal component variable.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.1
• /
• pp.117-124
• /
• 2021

Among growth disorders, 'Short Stature' can be improved through rapid diagnosis and treatment, and for that, it is important to detect early'Short Stature'. It is recommended to measure the height steadily for early detection of 'Short Stature' and checking the kid's growth process, but existing height measurement methods have problems such as time and space limitations, cost occurrence, and difficulty in keeping records. So in this paper, we proposed an 'Development of Kid Height Measurement Application based on Image using computer vision' method using smart phones, a medium that is highly accessible to people. In images taken through a smartphone camera, the kid's height is measured using algorithms from OpenCV, a computer vision library, and the measured heights were printed on the screen through 'a comparison graph with the standard height by gender and age' and 'list by date', made possible to check the kid's growth process. It is expected to measure height anytime, anywhere without time and space limitations and costs through this proposed method, and it is expected to help early detection of 'Short Stature' and other disorder through steady height measurement and confirmation of growth process.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.32 no.2
• /
• pp.137-145
• /
• 2022

Objectives: This study aimed to identify PM₁₀ mass concentration levels and conduct peak identification during five tasks in agricultural works. Methods: We investigated five agricultural tasks in 12 farms, which were harvesting, plowing, sowing, planting, and decapitation. All samples were measured by using the portable aerosol spectrometer(PAS 1.108) and the aerosol monitor(SidePak AM520). The collected data were compared with the national PM₁₀ concentrations. They were calculated to descriptive statistics, independent t-test, or ANOVA, and the peak identification on time series graph. Results: The ten investigated farms showed no significant difference with the national PM₁₀ concentrations, but the two greenhouses(AM, 143.31, 85.16 ㎍/m³) showed significant difference(p<0.05). As a result of the peak identification, the harvesting tasks showed repeated peak occurrence with the background concentration level of about 50 ㎍/m³. For plowing and sowing tasks, the peak occurred intermittently when the working was conducted near the sampling sites. Among the five tasks, the arithmetic mean of the harvesting task was 138.84±294.71 ㎍/m³, which was significantly higher than the other tasks(p<0.05). In addition, the case of using a tractor was higher than the case of not using the tractor(p<0.05), and the driver's seat showed the highest concentration(AM, 95.81 ㎍/m³). Conclusions: Works in greenhouses might have exposure to PM₁₀, while outdoor works is similar to general atmospheric PM₁₀ concentration levels. However, there is a possibility of intermittent exposure to high concentrations of PM₁₀ depending on the characteristics of agricultural tasks.

• Journal of Sericultural and Entomological Science
• /
• v.17 no.1
• /
• pp.1-26
• /
• 1975

These studies were attempted to find out the optimum silk reeling system by use of automatic silk reeling machine to increase raw silk yield and reeling efficiency with various silk reelable cocoons. The obtained results are as follows; 1. The mean silk reelability ratio(X)of the Korean cocoons during the last ten years was 61 per cent, beside 64.7 per cent in autumn cocoon and 57.3 per cent in spring cocoon. However, the ratio variation of autumn cocoons was larger than that of spring cocoons. 2. A positive correlation between cocoon filament breaks during its process and silk reelability levels was shown to be significant. The cocoons of both poor and good reelability evidenced "J" shape distribution on the filament break graph by the order of reeling cocoon end. Many bave breaks were found at the inner shell of the cocoons, or in case of poor reelability cocoons. 3. The morphology of broken cocoon ends during the process was classified into A, B, C, D, E and F types, The occurrence of B type was majority, but that of F type was minority among them. 4. In case of the cocoon cooking, H-type ion-exchanged soft water was better for good reelability cocoons, Na and H-type ion exchanged neutral soft water for those of fair reelability, and alkaline (Na-type) soft water for those of poor reelability, respectively. 5. The modification of cooking water by mixing the above different types of water (50％ Na-type and 50％ H-type passed by standard natural water; 75％ Na-type and 25％ H-type passed by hard natural water; 25％ Na-type and 75％ H-type passed by soluble natural water) made higher yield of raw silk with tess breaks of thread. 6, In case cocoon ends groping water included sodium hexametaphosphate as much as 800 ppm. the groping efficiency and raw silk yield of cocoon was improved. The effect was pronounced in case of poor reelability cordons. 7. The most reasonable cocoon cooking and silk reeling condition for automatic silk reeling process were observed to be rather incomplete cook with good reelability cocoons and optimum cook with poor reelability cocoons succeeded by the reeling bath temperature of 45$^{\circ}C$, 8. The reasonable silk reeling velocities were observed to be about 150m per min. for good reelability cocoons, 120m per min. for fair reelability ones and 90 to 120m per min. for poor reelability ones. 9. In order to improve the raw silk yield of cocoons and reeling efficiency, the cocoon stand-by-ratio for reeling should be kept at the level of 40 per cent for good reelability cocoons or at 60 per cent for poor reelability ones beside necessary end found cocoon condition.