• The Journal of the Convergence on Culture Technology
• /
• v.9 no.4
• /
• pp.331-335
• /
• 2023

As the viscosity of the blood increases, the blood becomes more sticky and difficult to flow, so the possibility of thrombosis increases and the probability of ischemic cerebral infarction increases. The importance of measuring blood viscosity has recently been emphasized for the prevention of circulatory system diseases, and the need for a viscometer capable of easily and accurately measuring blood viscosity has emerged. In this study, the measured values of a viscosity standard solution and an artificial blood by a parallel-plate viscometer ARS-Medi were compared with the those by Ares-G2 of TA instrument, which is internationally recognized for its accuracy and reliability. The viscosity of N44 standard solution, which is a Newtonian solution, was almost perfectly matched between the two instruments at all shear rates. In the case of an artificial blood, which is a non-Newtonian solution, the measured values between the two instruments showed a difference of about 10% at the lowest shear rate 1 rad/s; however, at a clinically significant shear rate of 10 rad/s or higher, the measured values between them were consistent within the error range. We expect that ARS-Medi, a newly developed parallel-plate viscometer for blood, using disposable plates, will be very useful in clinical practice as it improves the convenience and hygiene of blood viscosity measurement.

• The Journal of Bigdata
• /
• v.8 no.1
• /
• pp.157-165
• /
• 2023

Seafood is a major source of protein in many countries and its consumption is increasing. In Korea, consumption of seafood is increasing, but self-sufficiency rate is decreasing, and the importance of safety management is increasing as the amount of imported seafood increases. There are hundreds of species of aquatic products imported into Korea from over 110 countries, and there is a limit to relying only on the experience of inspectors for safety management of imported aquatic products. Based on the data, a model that can predict the customs inspection results of imported aquatic products is developed, and a machine learning classification model that determines the non-conformity of aquatic products when an import declaration is submitted is created. As a result of customs inspection of imported marine products, the nonconformity rate is less than 1%, which is very low imbalanced data. Therefore, a sampling method that can complement these characteristics was comparatively studied, and a preprocessing method that can interpret the classification result was applied. Among various machine learning-based classification models, Random Forest and XGBoost showed good performance. The model that predicts both compliance and non-conformance well as a result of the clearance inspection is the basic random forest model to which ADASYN and one-hot encoding are applied, and has an accuracy of 99.88%, precision of 99.87%, recall of 99.89%, and AUC of 99.88%. XGBoost is the most stable model with all indicators exceeding 90% regardless of oversampling and encoding type.

• Journal of Internet Computing and Services
• /
• v.24 no.5
• /
• pp.17-27
• /
• 2023

Today, as AI (Artificial Intelligence) technology develops and its practicality increases, it is widely used in various application fields in real life. At this time, the AI model is basically learned based on various statistical properties of the learning data and then distributed to the system, but unexpected changes in the data in a rapidly changing data situation cause a decrease in the model's performance. In particular, as it becomes important to find drift signals of deployed models in order to respond to new and unknown attacks that are constantly created in the security field, the need for lifecycle management of the entire model is gradually emerging. In general, it can be detected through performance changes in the model's accuracy and error rate (loss), but there are limitations in the usage environment in that an actual label for the model prediction result is required, and the detection of the point where the actual drift occurs is uncertain. there is. This is because the model's error rate is greatly influenced by various external environmental factors, model selection and parameter settings, and new input data, so it is necessary to precisely determine when actual drift in the data occurs based only on the corresponding value. There are limits to this. Therefore, this paper proposes a method to detect when actual drift occurs through an Anomaly analysis technique based on XAI (eXplainable Artificial Intelligence). As a result of testing a classification model that detects DGA (Domain Generation Algorithm), anomaly scores were extracted through the SHAP(Shapley Additive exPlanations) Value of the data after distribution, and as a result, it was confirmed that efficient drift point detection was possible.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.1
• /
• pp.82-96
• /
• 2024

While analyzing traffic flow, speed, traffic volume, and density are important macroscopic indicators, and acceleration and spacing are the important microscopic indicators. The speed and traffic volume can be collected with the currently installed traffic information collection devices. However, acceleration and spacing data are necessary for safety and autonomous driving but cannot be collected using the current traffic information collection devices. 'You Look Only Once'(YOLO), an object recognition technique, has excellent accuracy and real-time performance and is used in various fields, including the transportation field. In this study, to measure acceleration and spacing using YOLO, we developed a model that measures acceleration and spacing through changes in vehicle speed at each interval and the differences in the travel time between vehicles by setting the measurement intervals closely. It was confirmed that the range of acceleration and spacing is different depending on the traffic characteristics of each point, and a comparative analysis was performed according to the reference distance and screen angle to secure the measurement rate. The measurement interval was 20m, and the closer the angle was to a right angle, the higher the measurement rate. These results will contribute to the analysis of safety by intersection and the domestic vehicle behavior model.

• Journal of Cadastre & Land InformatiX
• /
• v.54 no.1
• /
• pp.19-32
• /
• 2024

This study examined the feasibility of image-based surveys by detecting objects in facilities and agricultural land using the YOLO algorithm based on drone images and comparing them with the land category by law. As a result of detecting objects through the YOLO algorithm, buildings showed a performance of detecting objects corresponding to 96.3% of the buildings provided in the existing digital map. In addition, the YOLO algorithm developed in this study detected 136 additional buildings that were not located in the digital map. Plastic greenhouses detected a total of 297 objects, but the detection rate was low for some plastic greenhouses for fruit trees. Also, agricultural land had the lowest detection rate. This result is because agricultural land has a larger area and irregular shape than buildings, so the accuracy is lower than buildings due to the inconsistency of training data. Therefore, segmentation detection, rather than box-shaped detection, is likely to be more effective for agricultural fields. Comparing the detected objects with the land category by law, it was analyzed that some buildings exist in agricultural and forest areas where it is difficult to locate buildings. It seems that it is necessary to link with administrative information to understand that these buildings are used illegally. Therefore, at the current level, it is possible to objectively determine the existence of buildings in fields where it is difficult to locate buildings.

• Science of Emotion and Sensibility
• /
• v.27 no.1
• /
• pp.3-12
• /
• 2024

This study examined affective representation by analyzing physiological responses measured using wearable devices and affective ratings in response to emotional videos. To achieve this aim, a published dataset was reanalyzed using multidimensional scaling to demonstrate affective representation in two dimensions. Cross-participant classification was also conducted to identify the consistency of emotional responses across participants. The accuracy and misclassification in each emotional condition were described by exploring the confusion matrix derived from the classification analysis. Multidimensional scaling revealed that the represented objects, namely, emotional videos, were positioned along the rated valence and arousal vectors, supporting the core affect theory (Russell, 1980). Vector fittings of physiological responses also showed the associations between heart rate acceleration and low arousal, increased heart rate variability and negative and high arousal, and increased electrodermal activity and negative and low arousal. Using the data of behavioral and physiological responses across participants, the classification results revealed that emotional videos were more accurately classified than the chance level of classification. The confusion matrix showed that awe, enthusiasm, and liking, which were categorized as positive, low arousal emotions in this study, were less accurately classified than the other emotions and were misclassified for each other. Through multivariate analyses, this study confirms the core affect theory using physiological responses measured through wearable devices and affective ratings in response to emotional videos.

• Journal of Intelligence and Information Systems
• /
• v.22 no.3
• /
• pp.71-89
• /
• 2016

Sentiment analysis is used for identifying emotions or sentiments embedded in the user generated data such as customer reviews from blogs, social network services, and so on. Various research fields such as computer science and business management can take advantage of this feature to analyze customer-generated opinions. In previous studies, the star rating of a review is regarded as the same as sentiment embedded in the text. However, it does not always correspond to the sentiment polarity. Due to this supposition, previous studies have some limitations in their accuracy. To solve this issue, the present study uses a supervised sentiment classification model to measure a more accurate sentiment polarity. This study aims to propose an advanced sentiment classifier and to discover the correlation between movie reviews and box-office success. The advanced sentiment classifier is based on two supervised machine learning techniques, the Support Vector Machines (SVM) and Feedforward Neural Network (FNN). The sentiment scores of the movie reviews are measured by the sentiment classifier and are analyzed by statistical correlations between movie reviews and box-office success. Movie reviews are collected along with a star-rate. The dataset used in this study consists of 1,258,538 reviews from 175 films gathered from Naver Movie website (movie.naver.com). The results show that the proposed sentiment classifier outperforms Naive Bayes (NB) classifier as its accuracy is about 6% higher than NB. Furthermore, the results indicate that there are positive correlations between the star-rate and the number of audiences, which can be regarded as the box-office success of a movie. The study also shows that there is the mild, positive correlation between the sentiment scores estimated by the classifier and the number of audiences. To verify the applicability of the sentiment scores, an independent sample t-test was conducted. For this, the movies were divided into two groups using the average of sentiment scores. The two groups are significantly different in terms of the star-rated scores.

• Radiation Oncology Journal
• /
• v.21 no.3
• /
• pp.238-244
• /
• 2003

Purpose: The Planning of High-Dose-Rate (HDR) brachytherapy treatments are becoming individualized and more dependent on the treatment planning system. Therefore, computer software has been developed to perform independent point dose calculations with the integration of an isodose distribution curve display into the patient anatomy images. Meterials and Methods: As primary input data, the program takes patients'planning data including the source dwell positions, dwell times and the doses at reference points, computed by an HDR treatment planning system (TPS). Dosimetric calculations were peformed in a $10\times12\times10\;Cm^3$ grid space using the Interstitial Collaborative Working Group (ICWG) formalism and an anisotropy table for the HDR Iridium-192 source. The computed doses at the reference points were automatically compared with the relevant results of the TPS. The MR and simulation film images were then imported and the isodose distributions on the axial, sagittal and coronal planes intersecting the point selected by a user were superimposed on the imported images and then displayed. The accuracy of the software was tested in three benchmark plans peformed by Gamma-Med 12i TPS (MDS Nordion, Germany). Nine patients'plans generated by Plato (Nucletron Corporation, The Netherlands) were verified by the developed software. Results: The absolute doses computed by the developed software agreed with the commercial TPS results within an accuracy of $2.8\%$ in the benchmark plans. The isodose distribution plots showed excellent agreements with the exception of the tip legion of the source's longitudinal axis where a slight deviation was observed. In clinical plans, the secondary dose calculations had, on average, about a $3.4\%$ deviation from the TPS plans. Conclusion: The accurate validation of complicate treatment plans is possible with the developed software and the qualify of the HDR treatment plan can be improved with the isodose display integrated into the patient anatomy information.

• Applied Chemistry for Engineering
• /
• v.29 no.3
• /
• pp.283-288
• /
• 2018

As the use of environmentally friendly and non-disease natural pigments grows, various methods for extracting natural pigments have been studied. The natural color was extracted from parsley, a vegetable ingredient containing natural dyes. Target color codes of green series of natural dyes extracted as variables #50932C (L = 55.0, a = -40.0, b = 46.0) were set with the pH and temperature of extracted natural color coordinates (of the extracted), and the quantitative intensities of natural dyes were analyzed. During the colorimetric analysis predicted by the reaction surface analysis method, a color coordinate analysis was conducted under the optimal conditions of pH 8.0 and extraction temperature of $60.9^{\circ}C$. Under these conditions, predicted figures of L, a, and b were 55.0, -36.3, and 36.8, respectively, while actual experimental ones confirmed were 69.0, -35.9, and 31.4, respectively. In these results, the theory accuracy and actual error rate were confirmed to be 73.0 and 13.8%, respectively. The theoretical optimization condition of the color difference (${\Delta}E$) was at the pH of 9.2 and extraction temperature of $55.2^{\circ}C$. Under these conditions the predicted ${\Delta}E$ figure was 12.4 while the experimental one was 13.0. The difference in color analysis showed 97.5% of the theoretical accuracy and 4.5% of the actual error rate. However, the combination of color coordinates did not represent a desired target color, but rather close to the targeted color by means of an arithmetic mean. Therefore, it can be said that when the reaction surface analysis method was applied to the natural dye extraction process, the use of color coordinates as a response value can be a better method for optimizing the dye extraction process.

• Journal of Korean Society for Geospatial Information Science
• /
• v.21 no.2
• /
• pp.53-62
• /
• 2013

Land-use/cover changes not only amplify or alleviate influence of climate changes but also they are representative factors to affect environmental change along with climate changes. Thus, the use of land-use/cover changes scenario, consistent climate change scenario is very important to evaluate reliable influences by climate change. The purpose for this study is to predict and analyze the future urban growth considering social and economic scenario from RCP scenario suggested by the 5th evaluation report of IPCC. This study sets land-use/cover changes scenario based on storyline from RCP 4.5 and 8.5 scenario. Urban growth rate for each scenario is calculated by urban area per person and GDP for the last 25 years and regression formula based on double logarithmic model. In addition, the urban demand is predicted by the future population and GDP suggested by the government. This predicted demand is spatially distributed by the urban growth probability map made by logistic regression. As a result, the accuracy of urban growth probability map is appeared to be 89.3~90.3% high and the prediction accuracy for RCP 4.5 showed higher value than that of RCP 8.5. Urban areas from 2020 to 2050 showed consistent growth while the rate of increasing urban areas for RCP 8.5 scenario showed higher value than that of RCP 4.5 scenario. Increase of urban areas is predicted by the fact that famlands are damaged. Especially RCP 8.5 scenario indicated more increase not only farmland but also forest than RCP 4.5 scenario. In addition, the decrease of farmland and forest showed higher level from metropolitan cities than province cities. The results of this study is believed to be used for basic data to clarify complex two-way effects quantitatively for future climate change, land-use/cover changes.