• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.1
• /
• pp.105-122
• /
• 2022

According to the statistics about the fatal crashes that have occurred on the expressways for the last 5 years, those who died on the shoulders of the road has been as 3 times high as the others who died on the expressways. It suggests that the crashes on the shoulders of the road should be fatal, and that it would be important to prevent the traffic crashes by cracking down on the vehicles intruding the shoulders of the road. Therefore, this study proposed a method to detect a vehicle that violates the shoulder lane by using the Faster R-CNN. The vehicle was detected based on the Faster R-CNN, and an additional reading module was configured to determine whether there was a shoulder violation. For experiments and evaluations, GTAV, a simulation game that can reproduce situations similar to the real world, was used. 1,800 images of training data and 800 evaluation data were processed and generated, and the performance according to the change of the threshold value was measured in ZFNet and VGG16. As a result, the detection rate of ZFNet was 99.2% based on Threshold 0.8 and VGG16 93.9% based on Threshold 0.7, and the average detection speed for each model was 0.0468 seconds for ZFNet and 0.16 seconds for VGG16, so the detection rate of ZFNet was about 7% higher. The speed was also confirmed to be about 3.4 times faster. These results show that even in a relatively uncomplicated network, it is possible to detect a vehicle that violates the shoulder lane at a high speed without pre-processing the input image. It suggests that this algorithm can be used to detect violations of designated lanes if sufficient training datasets based on actual video data are obtained.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.4A
• /
• pp.373-384
• /
• 2009

For the first step on the quantitative evaluation of shrinkage reduction and differential shrinkage analysis of lightweight aggregate concrete, this study sets the moisture transport model of concrete by pre-absorbed water of porous lightweight aggregates and measured effective moisture diffusion coefficient, moisture capacity, degree of humidity supply and degree of humidity consumption by water binder ratio and aggregate type. The effective moisture diffusion coefficient in steady state caused by humidity difference between inside and outside of concrete had low value as low water-binder ratio. And in case of same water-binder ratio, effective moisture diffusion of mixtures used normal aggregates were lower than those used lightweight aggregates. To determine moisture store capability of concrete - moisture capacity, moisture contents were measured in 9 humidity conditions. As a result moisture contents of mixtures used lightweight aggregates was higher than mixtures used normal aggregates in all humidity conditions. This study measured lightweight aggregates' degree of humidity supply that applicable to normal atmospheric environment (above RH 50%) and made it quantitatively. Also amount of moisture release was set as a exponential function that represents a clear trend proportion to time and inverse proportion to humidity of the surroundings. As the result of measurement about degree of moisture consumption inside concrete following the internal consumption caused by cement hydration self-drying, it was showed that rapid decrease of humidity, around 10%, at early ages (7~10 days) when water-binder ratio is 0.3 and slow decrease around 5% and 1% when water-binder ratio is 0.4 and 0.5.

• 한국노년학
• /
• v.39 no.2
• /
• pp.285-304
• /
• 2019

The purpose of this study was to investigate the effects of leisure-based occupational therapy on leisure satisfaction, activities of daily living, and rehabilitation motivation in elderly patients with chronic diseases. In the study, Subjects were assigned to either the control or experimental group. The experimental group consisted of 10 and the control group of 14 patients. The experimental group receive a Leisure-based occupational therapy intervention, and the control group receive a conventional occupational therapy intervention. Leisure satisfaction, activities of daily living, and rehabilitation motivation were measured to Canadian occupational performance measure(COPM), Korean Activities of Daily Living(K-ADL·K-IADL), and Patient Questionnaire of Rehabilitation Motivation(PAREMO). Evaluation scores were compared before and after intervention to determine whether or not there were differences over time. And we examined the correlation between the variables. The results of this study were as follows: 1) The leisure-based occupational therapy has a significant effect on leisure satisfaction and rehabilitation motivation(p<.01). 2) The conventional occupational therapy has a significant effect on activities of daily living(p<.01). 3) There was a significant correlation between ADL and IADL(p<.01). 4) There was a significant correlation between leisure satisfaction and Rehabilitation Motivation(p<.01). Implications for occupational therapy include that we must offer appropriate approach with considering the interests and value of patients to them. And proposing studies to demonstrate the efficacy of occupational therapy approaches.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.2
• /
• pp.15-21
• /
• 2024

The purpose of this study is to propose a framework for the introduction and evaluation of artificial intelligence (AI) services not only in general applications but also in public policies. To achieve this, the study explores AI service management and governance toolkits, providing insights into how to introduce AI services in public policies. Firstly, it offers guidelines on the direction of AI service development and what aspects to avoid. Secondly, in the development phase, it recommends using the AI governance toolkit to review content through checklists at each stage of design, development, and deployment. Thirdly, when operating AI services, it emphasizes the importance of adhering to principles related to 1) planning and design, 2) the lifecycle, 3) model construction and validation, 4) deployment and monitoring, and 5) accountability. The governance perspective of AI services is crucial for mitigating risks associated with service provision, and research in risk management aspects should be conducted. While embracing the advantages of AI, proactive measures should be taken to address limitations and risks. Efforts should be made to efficiently formulate policies using AI technology to create high value and provide meaningful societal impacts.

• The Korean Journal of Nuclear Medicine
• /
• v.37 no.6
• /
• pp.355-363
• /
• 2003

Purpose: Regional contractility can be calculated using the regional volume change of left ventricle measured by gated myocardial SPECT image and curve of central artery pressure obtained from radial artery pressure data. In this study, a program to obtain the regional contractility was developed, and reproducibility of regional contractility measurement was assessed. Materials and Methods: Seven patients(male:female=5:2, $58{\pm}11.9$ years) with coronary artery diseases underwent gated Tc-99m MIBI myocardial SPECT twice without delay between two scans. Regional volume change of left ventricle was estimated using CSA (Cardiac SPECT Analyzer) software developed in this study. Regional contractility was iteratively estimated from the time-elastance curve obtained using the time-pressure curve and regional time-volume curve. Reproducibility of regional contractility measurement assessed by comparing the contractility values measured twice from the same SPECT data and by comparing those measured from the pair of SPECT data obtained from a same patient. Results: Measured regional contractility was $3.36{\pm}3.38{mm}Hg/mL$ using 15-segment model, $3.16{\pm}2.25{mm}Hg/mL$ using 7-segment model, and $3.11{\pm}2.57{mm}Hg/mL$ using 5-segment model. The harmonic average of regional contractility value was almost identical to the global contractility. Correlation coefficient of regional contractility values measured twice from the same data was greater than 0.97 for all models, and two standard deviations of contractility difference on Bland Altman plot were 1.5%, 1.0%, and 0.9% for 15-, 7-, and 5-segment models, respectively. Correlation coefficient of regional contractility values measured from the pair of SPECT data obtained from a same patient was greater than 0.95 for all models, and two standard deviations on Bland Altman plot were 2.2%, 1.0%, and 1.2%. Conclusion: Regional contractility of left ventricle measured using developed software in this study was reproducible. Regional contractility of left ventricle will be a new useful index for myocardial function after analysis of the clinical data.

• KDI Journal of Economic Policy
• /
• v.32 no.4
• /
• pp.115-151
• /
• 2010

Recently Korean universities show very rapid increases in both patents and R&D (research and development) expenditures. During the period from 1970 to 2008, university R&D spending has on the average increased 15.3% annually. Along with steady increases in R&D spending, university's research outputs have also continuously increased. In 1990 Korea as a total published 1,613 SCI-level scientific papers and Korean universities applied 27 patents to Korea patent office. In 2008, Korea published more that 35,000 SCI papers and Korean universities applied about 7,300 patents. The growth of scientific articles had begun from the early 1990s whereas the growth of patent has ignited entering the 2000s. The paper tried to investigate university research through the window of patent. Patents lie between invention and innovation and represent the potential value of invention which will be realized at the marketplace. Since Korean patents do not contain citation information, the paper used US patents-NBER patent database-as the main data. The key empirical question is whether Korean university patents granted from USPTO are characteristically different from other Korean patents granted from USPTO. Previous studies on US and Europe show that corporate patents are more stylized in appropriablity of invention, whereas university patents basicness. In case of Korea, the paper confirmed the appropriability characteristic of corporate patents; but the Korean unversity patents are not distinguishable in terms of basicness. The paper estimated the citation frequency function-an empirical model which was firstly developed by Caballero and Jaffe (1993) and later articulated by Jaffe and Trajtenberg (1996, 2002). The model is specified mainly composed of two interacting parts-diffusion effect and obsolescence effect of new ideas or innovations. Estimation results show that differences in forward citations between university and corporate patents are not statistically significant, after controlling self-citation. Since forward citations represent the quality of patents, this estimation result implies that there are no statistically significant quality differences between university and corporate patents. Prior research results, based on the same model of citation frequency function, about US and some European cases show that, in terms of forward citations, university patents are generally superior to corporate patents -for the case of US- or, the former not inferior to the latter-for the case of most of Europe. It is argued that some important and significant policy changes caused the rapid rise of university patents in Korea. Policy changes include the revision of technology transfer act allowing the ownership of publicly-funded research results to researchers and the changes in faculty/professor evaluation which gives more credit to the number of patents. These policy changes have triggered the rapid growth of the number of university patents. The results of the empirical analysis in this paper indicated that Korea now needs to make further efforts to enhance the quality of university patents, not just to produce more numbers of patents.

• Journal of Intelligence and Information Systems
• /
• v.20 no.1
• /
• pp.133-148
• /
• 2014

Recently, with the advent of various information channels, the number of has continued to grow. The main cause of this phenomenon can be found in the significant increase of unstructured data, as the use of smart devices enables users to create data in the form of text, audio, images, and video. In various types of unstructured data, the user's opinion and a variety of information is clearly expressed in text data such as news, reports, papers, and various articles. Thus, active attempts have been made to create new value by analyzing these texts. The representative techniques used in text analysis are text mining and opinion mining. These share certain important characteristics; for example, they not only use text documents as input data, but also use many natural language processing techniques such as filtering and parsing. Therefore, opinion mining is usually recognized as a sub-concept of text mining, or, in many cases, the two terms are used interchangeably in the literature. Suppose that the purpose of a certain classification analysis is to predict a positive or negative opinion contained in some documents. If we focus on the classification process, the analysis can be regarded as a traditional text mining case. However, if we observe that the target of the analysis is a positive or negative opinion, the analysis can be regarded as a typical example of opinion mining. In other words, two methods (i.e., text mining and opinion mining) are available for opinion classification. Thus, in order to distinguish between the two, a precise definition of each method is needed. In this paper, we found that it is very difficult to distinguish between the two methods clearly with respect to the purpose of analysis and the type of results. We conclude that the most definitive criterion to distinguish text mining from opinion mining is whether an analysis utilizes any kind of sentiment lexicon. We first established two prediction models, one based on opinion mining and the other on text mining. Next, we compared the main processes used by the two prediction models. Finally, we compared their prediction accuracy. We then analyzed 2,000 movie reviews. The results revealed that the prediction model based on opinion mining showed higher average prediction accuracy compared to the text mining model. Moreover, in the lift chart generated by the opinion mining based model, the prediction accuracy for the documents with strong certainty was higher than that for the documents with weak certainty. Most of all, opinion mining has a meaningful advantage in that it can reduce learning time dramatically, because a sentiment lexicon generated once can be reused in a similar application domain. Additionally, the classification results can be clearly explained by using a sentiment lexicon. This study has two limitations. First, the results of the experiments cannot be generalized, mainly because the experiment is limited to a small number of movie reviews. Additionally, various parameters in the parsing and filtering steps of the text mining may have affected the accuracy of the prediction models. However, this research contributes a performance and comparison of text mining analysis and opinion mining analysis for opinion classification. In future research, a more precise evaluation of the two methods should be made through intensive experiments.

• Nuclear Medicine and Molecular Imaging
• /
• v.42 no.4
• /
• pp.275-284
• /
• 2008

Purpose: We intended to evaluate myocardial oxygen consumption ($MVO_2)$ by applying recirculation correction and modified one-compartment model to have a reference range of $MVO_2$ in normal young population and to reveal the effect of recirculation on time-activity curve (TAC). Materials and Methods: In nine normal male volunteers with mean age of $26.3{\pm}4.0$, $MVO_2$ was estimated with 925 MBq (25mCi) of $^{11}C$-Acetate (Neuroscience Research Institute, Gachon University of Medicine and Science, Incheon, Korea) and PET/CT (Biograph 6, Siemens Medical Solution, Germany). Analysis software such as $MATLAB^{(R)}$ v7.1 (Mathworks, Inc., United States), $Excel^{(R)}$ 2007 (Microsoft, United States), and $SPSS^{(R)}$ v12.0 (Apache Software Foundation, United States) were used. Twenty three frames were of $12{\times}10$, $5{\times}60$, $3{\times}120$, $2{\times}300's$ duration, respectively. The modified one-compartmental model and the recirculation correction method were applied. Statistical analysis was performed by using Test of Normality, ANOVA and Post-Hoc (Scheffe's) analysis, and p-value less than 0.05 was considered as significant. Results: The normal reference ranges of $MVO_2$ were presented as $3.18-4.64\;{\times}\;10^{-4}\;ml/g/sec$, $1.91-3.94\;{\times}\;10^{-4}\;ml/g/sec$, $4.31-6.40\;{\times}\;10^{-4}\;ml/g/sec$, $2.84-4.53\;{\times}\;10^{-4}\;ml/g/sec$ and $3.42-5.00\;{\times}\;10^{-4}\;ml/g/sec$ in the septum, the inferior wall, the lateral wall, the anterior wall and the entire wall, respectively. In addition, it was noted that the dual exponentiality of the clearance curve is due to the recirculation effect and that the characteristic of the curve is essentially mono-exponential. Conclusion: $^{11}C$-Acetate is a radiotracer worthwhile to assess $MVO_2$. Re-circulated $^{11}C$ can influence TAC of $^{11}C$ in myocadia and so the recirculation correction must be considered when measuring $MVO_2$.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.18 no.2
• /
• pp.33-38
• /
• 2014

Purpose Auto exposure control (AEC) in SPECT/CT automatically controls the exposure dose (mA) according to patient's shape and size. The aim of this study was to evaluate the effect of AEC in SPECT/CT on exposure dose reduction and image quality. Materials and Methods The model of SPECT/CT used in this study was Discovery 670 (GE, USA), Smart mA for AEC; and $^{99m}Tc$ as a radioisotope. To compare SPECT and CT images by CT exposure dose variation, we used a standard technique set at 80, 100, 120, 140 kVp, 10, 30, 50, 100, 150, 200, 250 mA, and AEC at 80, 100, 120, 140 kVp, 10-250 mA. To evaluate resolution and contrast of SPECT images, triple line phantom and flangeless Esser PET phantom were used. For CT images, noise and uniformity were checked by anthropomrphic chest phantom. For dose evaluation to find DLP value, anthropomorphic chest phantom was used and the CT protocol of torso was applied by standard technique (120 kVp, 100 mA) and AEC (120 kVp, 10-250 mA). Results When standard and AEC were applied, the resolutions at SPECT images with attenuation correction (AC) were the same as FWHM by center 3.65 mm, left 3.48 mm, right 3.61 mm. Contrasts of standard and AEC showed no significant difference: standard 53.5, 29.8, 22.5, 15.8, 6.0, AEC 53.5, 29.6, 22.4, 15.7, 6.1 In CT images, noise values at standard and AEC were 15.4 and 18.5 respectively. The application of AEC increases noise but the value of coefficient variation were 33.8, 24.9 respectively, obtaining uniform noise image. The values of DLP at standard and AEC were 426.78 and 352.09 each, which shows that the application of AEC decreases exposure dose more than standard by approximately 18%. Conclusion The results of our study show that there was no difference of AC in SPECT images based on the CT exposure dose variation at SPECT/CT images. It was found that the increased CT exposure dose leads to the improvement of CT image quality but also increases the exposure dose. Thus, the use of AEC in SPECT/CT contributes to obtaining equal AC SPECT images, and uniform noise in CT images while reducing exposure dose.

• Journal of Korean Society of Forest Science
• /
• v.102 no.3
• /
• pp.390-397
• /
• 2013

The study, utilizing a data envelopment analysis (DEA) which is one of the nonparametric estimation methods, aims to evaluate the management efficiency of chestnut tree cultivators in such provinces in Chungchungnam-do as Cheong-yang, Gong-ju, Bu-yeo and so on. The analysis data of this study is based on inputs and outputs of 20 forestry households surveyed in the 2012 survey titled 'A Study on Current Level and Condition of Chestnut Cultivation and Management', which was conducted from March 2012 to October 2012. The elements of inputs are composed of management cost, harvesting cost, material cost, non-operation expenses and cultivation area, while the element of output is a gross margin only. Then the study analyzes a technical efficiency, a puretechnical efficiency and a scale efficiency using CCR and BCC model among DEA methods. Based on that, it also provides improvement methods for forestry households that turned out to be inefficient. In order to verify the result of DEA analysis, the study additionally compares a result of this efficiency study with that of chestnuts management standard diagnostic table. According to the result, the average value of technical efficiency analyzed was 0.667, proving to be inefficient in general. Given that the average value of pure-technical efficiency was 0.944 and that of scale efficiency was 0.703, it can be inferred that inefficiency exists in the field of scale, not in the field of cultivation techniques. As for forestry households with the efficiency score of 1, it is shown that there were 6 households that recorded 1 in the technical efficiency field and 13 households that recorded 1 in the pure technical efficiency. Meanwhile, there were 6 households that recorded 1 in all of the three aspects. In the comparison with the scores from chestnuts management standard diagnostic table, there were 5 households made a high score of over 80, among which are 3 households with score 1 in the technical efficiency. Also, the results of this study and the chestnuts management standard diagnostic table are proved to have the same result, both of them showing the same households that recorded the highest score and the lowest score. This means the management efficiency evaluation using DEA can be applied to the fieldwork along with the chestnuts management standard diagnostic table.