• Journal of the Korea Society of Computer and Information
• /
• v.23 no.4
• /
• pp.147-153
• /
• 2018

In this paper, we propose an efficient WBC 14-Diff classification which performs using the WBC-ResNet-152, a type of CNN model. The main point of view is to use Super-pixel for the segmentation of the image of WBC, and to use ResNet for the classification of WBC. A total of 136,164 blood image samples (224x224) were grouped for image segmentation, training, training verification, and final test performance analysis. Image segmentation using super-pixels have different number of images for each classes, so weighted average was applied and therefore image segmentation error was low at 7.23%. Using the training data-set for training 50 times, and using soft-max classifier, TPR average of 80.3% for the training set of 8,827 images was achieved. Based on this, using verification data-set of 21,437 images, 14-Diff classification TPR average of normal WBCs were at 93.4% and TPR average of abnormal WBCs were at 83.3%. The result and methodology of this research demonstrates the usefulness of artificial intelligence technology in the blood cell image classification field. WBC-ResNet-152 based morphology approach is shown to be meaningful and worthwhile method. And based on stored medical data, in-depth diagnosis and early detection of curable diseases is expected to improve the quality of treatment.

• Computers and Concrete
• /
• v.11 no.4
• /
• pp.337-350
• /
• 2013

The sensitivity of compressive strength of no-slump concrete to its ingredient materials and proportions, necessitate the use of robust models to guarantee both estimation and generalization features. It was known that the problem of compressive strength prediction owes high degree of complexity and uncertainty due to the variable nature of materials, workmanship quality, etc. Moreover, using the chemical and mineral additives, superimposes the problem's complexity. Traditionally this property of concrete is predicted by conventional linear or nonlinear regression models. In general, these models comprise lower accuracy and in most cases they fail to meet the extrapolation accuracy and generalization requirements. Recently, artificial intelligence-based robust systems have been successfully implemented in this area. In this regard, this paper aims to investigate the use of optimized support vector machine (SVM) to predict the compressive strength of no-slump concrete and compare with optimized neural network (ANN). The results showed that after optimization process, both models are applicable for prediction purposes with similar high-qualities of estimation and generalization norms; however, it was indicated that optimization and modeling with SVM is very rapid than ANN models.

• Journal of Information Processing Systems
• /
• v.16 no.1
• /
• pp.224-237
• /
• 2020

Recognition of banknote serial number is one of the important functions for intelligent banknote counter implementation and can be used for various purposes. However, the previous character recognition method is limited to use due to the font type of the banknote serial number, the variation problem by the solid status, and the recognition speed issue. In this paper, we propose an aspect ratio based character region segmentation and a convolutional neural network (CNN) based banknote serial number recognition method. In order to detect the character region, the character area is determined based on the aspect ratio of each character in the serial number candidate area after the banknote area detection and de-skewing process is performed. Then, we designed and compared four types of CNN models and determined the best model for serial number recognition. Experimental results showed that the recognition accuracy of each character was 99.85%. In addition, it was confirmed that the recognition performance is improved as a result of performing data augmentation. The banknote used in the experiment is Indian rupee, which is badly soiled and the font of characters is unusual, therefore it can be regarded to have good performance. Recognition speed was also enough to run in real time on a device that counts 800 banknotes per minute.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.756-759
• /
• 2017

The productivity of cultivated crops in Korea is low compared to the Netherlands, which is an advanced agricultural country. In addition, modernization of facility and complex environmental control technology are needed to overcome poor growth and productivity deterioration caused by shortage of sunshine, abnormal temperature and high temperature due to abnormal climate. On the other hand, domestic facility horticulture complex environmental control is a level of machine automation that can check the internal situation of a green house with a cell phone and remotely operate a sprinkler, heat cover, curtain, ventilator, Therefore, this paper suggests the development of optimum environment control technology for facility horticulture based on the growth model and the cultivation technology knowledge base in order to realize the automation of optimal complex environment control and contribute to improvement of quality and productivity of cultivated crops.

• Journal of Korea Multimedia Society
• /
• v.24 no.10
• /
• pp.1414-1424
• /
• 2021

In this paper, the importance of input factors of a DNN (Deep Neural Network) PM_2.5 forecasting model using LRP(Layer-wise Relevance Propagation) is analyzed, and forecasting performance is improved. Input factor importance analysis is performed by dividing the learning data into time and PM_2.5 concentration. As a result, in the low concentration patterns, the importance of weather factors such as temperature, atmospheric pressure, and solar radiation is high, and in the high concentration patterns, the importance of air quality factors such as PM_2.5, CO, and NO₂ is high. As a result of analysis by time, the importance of the measurement factors is high in the case of the forecast for the day, and the importance of the forecast factors increases in the forecast for tomorrow and the day after tomorrow. In addition, date, temperature, humidity, and atmospheric pressure all show high importance regardless of time and concentration. Based on the importance of these factors, the LRP_DNN prediction model is developed. As a result, the ACC(accuracy) and POD(probability of detection) are improved by up to 5%, and the FAR(false alarm rate) is improved by up to 9% compared to the previous DNN model.

• Electronics and Telecommunications Trends
• /
• v.36 no.5
• /
• pp.74-81
• /
• 2021

Based on data provided by the science and technology knowledge infrastructure (ScienceON, 2017-2021), this paper reviews the research trends of domestic police services and related technologies, and describes the research and development direction of policing technology. For this purpose, the research was searched using the keywords science policing, smart policing, predictive policing, and policing. Policing technology is used for crime investigation (prevention), such as crime analysis and crime prediction. The collection of related data use urban infrastructure, the processing of data collected using technologies, such as artificial intelligence, and the utilization of data in police services (system) were summarized. In future, on-site support technology and crime investigation (prevention) technology for a preemptive correspondence to social threats and effective police activities must be developed. In addition, the quality of police services should be improved, a system to use police-related data should be developed, and the capabilities of police experts need to be strengthened.

• Nuclear Engineering and Technology
• /
• v.53 no.3
• /
• pp.776-792
• /
• 2021

Conventional integral effect test facilities were constructed to enable the precise observation of thermal-hydraulic phenomena and reactor behaviors under postulated accident conditions to prove reactor safety. Although these facilities improved the understanding of thermal-hydraulic phenomena and reactor safety, applications of new technologies and their performance tests have been limited owing to the cost and large scale of the facilities. Various nuclear technologies converging 4th industrial revolution technologies such as artificial intelligence, drone, and 3D printing, are being developed to improve plant management strategies. Additionally, new conceptual passive safety systems are being developed to enhance reactor safety. A new integral effect test facility having a noticeable scaling ratio, i.e., the (UNIST reactor innovation loop (URI-LO), is designed and constructed to improve the technical quality of these technologies by performance and feasibility tests. In particular, the URI-LO, which is constructed using a transparent material, enables better visualization and provides physical insights on multidimensional phenomena inside the reactor system. The facility design based on three-level approach is qualitatively validated with preliminary analyses, and its functionality as a test facility is confirmed through a series of experiments. The design feature, design validation, functionality test, and future utilization of the URI-LO are introduced.

• Journal of National Security and Military Science
• /
• s.15
• /
• pp.31-55
• /
• 2018

It has been fifteen years since military science was introduced into private and public universities since 2004. The department focuses on the improvements of the South Korean Army quality based on the Korean Army's traits including: an increase of power in the armed force and operations through research, development, and the expansion of a cooperation between the public (civilians) and military. Approximately, four hundred students from various universities in the military science department graduate in order to become an officer. The fourth industrial revolution causes structural transformation to our lives. Through the use of Artificial Intelligence (AI,) war and the military as a whole will be altered significantly particularly with regard to efficiency. Nevertheless, it is important for us to train officers in creative ways so that they can deal with situations where machines will be unable to handle situations. Considering this change in our lives, it is necessary for the military science departments to change the way to teach and train their students. In order to accomplish this goal, we need to introduce a method called "Flipped Learning" and during the process all the members need to participate and communicate in an interactive way. By doing this, the military science departments will play an important role by improving human resource in terms of military and national security.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.4
• /
• pp.208-216
• /
• 2020

With the spread of smart manufacturing, one of the key topics of the 4th industrial revolution, manufacturing systems are moving beyond automation to smartization using artificial intelligence. In particular, in the existing automatic machining, a number of machining defects and non-processing occur due to tool damage or severe wear, resulting in a decrease in productivity and an increase in quality defect rates. Therefore, it is important to measure and predict tool life. In this paper, ν-ASVR (ν-Asymmetric Support Vector Regression), which considers the asymmetry of ⲉ-tube and the asymmetry of penalties for data out of ⲉ-tube, was proposed and applied to the tool wear prediction problem. In the case of tool wear, if the predicted value of the tool wear amount is smaller than the actual value (under-estimation), product failure may occur due to tool damage or wear. Therefore, it can be said that ν-ASVR is suitable because it is necessary to overestimate. It is shown that even when adjusting the asymmetry of ⲉ-tube and the asymmetry of penalties for data out of ⲉ-tube, the ratio of the number of data belonging to ⲉ-tube can be adjusted with ν. Experiments are performed to compare the accuracy of various kernel functions such as linear, polynomial. RBF (radialbasis function), sigmoid, The best result isthe use of the RBF kernel in all cases

• Journal of Korean society of Dental Hygiene
• /
• v.21 no.1
• /
• pp.5-16
• /
• 2021

Objectives: To evaluate the impact of an oral exercise program including whole-body exercises on oral function in older people. Methods: The participants (aged ≥65 years) were divided into three groups: intervention group I (only oral exercise), intervention group II (oral exercise with whole-body exercises), and control group (no intervention). The oral health status, saliva flow rate, and oral muscle strength were evaluated. Analyses were performed to compare the three groups and identify the changes in the aforementioned parameters before and after the program. Results: The saliva flow rate significantly increased in intervention groups I and II after the program. Oral muscle strength evaluation using the Iow a oral performance instrument showed that the anterior tongue strength increased significantly in intervention group I; the posterior tongue strength and cheek strength also increased but not significantly. The anterior tongue, posterior tongue, and cheek strengths significantly increased in intervention group II. Conclusions: The oral exercise program including whole-body exercises showed positive effects on the saliva flow rate and oral strength. No significant differences were observed in the quality of life related to oral health.