• Journal of the Korea Convergence Society
• /
• v.12 no.10
• /
• pp.55-61
• /
• 2021

In this paper, we proposed a DeepLabv3+ based encoder-decoder model utilizing an attention mechanism for precise semantic segmentation. The DeepLabv3+ is a semantic segmentation method based on deep learning and is mainly used in applications such as autonomous vehicles, and infrared image analysis. In the conventional DeepLabv3+, there is little use of the encoder's intermediate feature map in the decoder part, resulting in loss in restoration process. Such restoration loss causes a problem of reducing segmentation accuracy. Therefore, the proposed method firstly minimized the restoration loss by additionally using one intermediate feature map. Furthermore, we fused hierarchically from small feature map in order to effectively utilize this. Finally, we applied an attention mechanism to the decoder to maximize the decoder's ability to converge intermediate feature maps. We evaluated the proposed method on the Cityscapes dataset, which is commonly used for street scene image segmentation research. Experiment results showed that our proposed method improved segmentation results compared to the conventional DeepLabv3+. The proposed method can be used in applications that require high accuracy.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.103-111
• /
• 2021

The purpose of this study is to study a method for preventing collisions of multiple drones in controlled airspace. As a result of the study, it was proved that it is appropriate as a method to control drone collisions after setting accurate information on the ROI (Region of Interest) area estimated based on the expected drone path and time in the control system as a method to avoid drone collision. As a result of the empirical analysis, the diameter of the flight path of the operating drone should be selected to reduce the risk of collision, and the change in the departure time and operating speed of the operating drone did not act as an influencing factor in the collision. In addition, it has been demonstrated that providing flight priority is one of the appropriate methods as a countermeasure to avoid collisions. For collision avoidance methods, not only drone sensor-based collision avoidance, but also collision avoidance can be doubled by monitoring and predicting collisions in the control system and performing real-time control. This study is meaningful in that it provided an idea for a method for preventing collisions of multiple drones in controlled airspace and conducted practical tests. This helps to solve the problem of collisions that occur when multiple drones of different types are operating based on the control system. This study will contribute to the development of related industries by preventing accidents caused by drone collisions and providing a safe drone operation environment.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.5
• /
• pp.100-112
• /
• 2021

With the advent of big data, traffic prediction has been developed based on historical data analysis methods, but this method deteriorates prediction performance when a traffic incident that has not been observed occurs. This study proposes a method that can compensate for the reduction in traffic prediction accuracy in traffic incidents situations by hybrid approach of machine learning and traffic simulation. The blind spots of the data-driven method are revealed when data patterns that have not been observed in the past are recognized. In this study, we tried to solve the problem by reinforcing historical data using traffic simulation. The proposed method performs machine learning-based traffic prediction and periodically compares the prediction result with real time traffic data to determine whether an incident occurs. When an incident is recognized, prediction is performed using the synthetic traffic data generated through simulation. The method proposed in this study was tested on an actual road section, and as a result of the experiment, it was confirmed that the error in predicting traffic state in incident situations was significantly reduced. The proposed traffic prediction method is expected to become a cornerstone for the advancement of traffic prediction.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.9 no.3
• /
• pp.268-275
• /
• 2021

The three factors that determine the strength of concrete are the strength of cement paste, aggregate and ITZ(Interfacial Transition Zone) between aggregate and cement paste. Out of these, the strength of ITZ is the most vulnerable. ITZ is formed in 10~50㎛, the ratio of calcium hydroxide is high, and CSH appears low ratio. A high calcium hydroxide ratio causes a decrease in the bond strength of ITZ. ITZ is due to further weak area. The problem of ITZ appears as a more disadvantageous factor when it used lightweight aggregate. The previous study of ITZ properties have measured interfacial toughness, identified influencing factors ITZ, and it progressed SEM and XRD analysis on cement matrix without using coarse aggregates. also it was identified microstructure using EMPA-BSE equipment. However, in previous studies, it is difficult to understand the microstructure and mechanical properties. Therefore, in this study, a method of measuring electrical resistance using EIS(Electrochemical Impedance Spectroscopy) measuring equipment was adopted to identify the ITZ between natural aggregate and lightweight aggregate, and it was tested the change of ITZ by surface coating of lightweight aggregate with ground granulated blast furnace slag. As a result, the compressive strength of natural aggregate and lightweight aggregate appear high strength of natural aggregate with high density, surface coating lightweight aggregate appear strength higher than natural aggregate. The electrical resistivity of ITZ according to the aggregate appeared difference.

• Journal of The Korean Association of Information Education
• /
• v.25 no.5
• /
• pp.691-704
• /
• 2021

The development of AI technology has brought about a big change in our lives. The importance of AI and data education is also growing as AI's influence from life to society to the economy grows. In response, the OECD Education Research Report and various domestic information and curriculum studies deal with data literacy and present it as an essential competency. However, the definition of data literacy and the content and scope of the components vary among researchers. Thus, we analyze the semantic similarity of words through Word2Vec deep learning natural language processing methods along with the definitions of key data literacy studies and analysis of word frequency utilized in components, to present objective and comprehensive definition and components. It was revised and supplemented by expert review, and we defined data literacy as the 'basic ability of knowledge construction and communication to collect, analyze, and use data and process it as information for problem solving'. Furthermore we propose the components of each category of knowledge, skills, values and attitudes. We hope that the definition and components of data literacy derived from this study will serve as a good foundation for the systematization and education research of AI education related to students' future competency.

• Journal of the Society of Disaster Information
• /
• v.17 no.2
• /
• pp.391-402
• /
• 2021

Purpose: By categorizing opinions by subject in the safety certification ecosystem, we want to identify weaknesses in system operation and suggest improvement plans so that the safety certification system can have quick resilience against future variability. Method: Through literature research and data analysis, similar domestic and foreign safety certifications and related cases, as well as the current status of international standards and national standards, etc. were confirmed, and a fact-finding survey was conducted for each stakeholder in the safety certification ecosystem, and problem types and improvement measures were established. Result: We conduct a fact-finding survey of the overall system, such as quality satisfaction with safety certification target products, obstacles in the development, manufacturing and use process, and safety certification-related improvements, targeting workplaces that manufacture, import or use safety certification target machines By discovering and categorizing problems and weaknesses in system operation, detailed implementation tasks were derived to establish improvement directions and improve operability. Conclusion: For the advancement and internationalization of the safety certification system, it is necessary to efficiently carry out the detailed promotion tasks derived from this study. In addition, in order to strengthen the resilience to the variability of the safety certification ecosystem, the operating system of a virtuous cycle structure by improving the mutual relationship between each subject construction is considered important.

• Journal of the Korea Convergence Society
• /
• v.12 no.5
• /
• pp.337-344
• /
• 2021

To determine the impact of long-term social distancing and isolation from COVID-19 on the area of adult occupational performance, targeting adults in their 20s to 60s distributed nationwide for 2 months from November 2020 to December 2020. A questionnaire based on the occupational therapy execution system was constructed and investigated. A total of 270 people responded to the questionnaire, and the survey method was an online questionnaire. As a result of the analysis, there were significant differences in both occupational performance and satisfaction before and after COVID-19 in 33 (75%) of 45 items in 9 areas of the occupational performance area. There were significant changes in performance and satisfaction by age group in all age groups in health management, social participation, leisure, and work. In particular, those in their twenties showed the greatest change in performance and satisfaction in the leisure domain, while those in their 30s and 60s showed the greatest change in both the performance and satisfaction in the leisure domain. Along with these changes, the survey subjects recognized that their occupational performance and satisfaction were lower than before COVID-19 was a problem and confirmed that they are willing to improve. As COVID-19 is still a pandemic, it is necessary to involve experts in each area and follow-up studies to improve the differences by occupational performance area and age, which have changed due to long-term social distancing and isolation.

• Journal of the Korea Convergence Society
• /
• v.12 no.5
• /
• pp.373-383
• /
• 2021

Our society is aging rapidly. In this super-aged society, the increase in healthcare costs are considered a national problem that undermines the sustainability of social security. Various services for healthcare for the elderly have been promoted to address this. However, most of them have focused on healthcare after the outbreak of chronic diseases and lack preventive healthcare. Most of the preventive healthcare projects are only pilots. In this paper, the current status of health care services for senior citizens at home and abroad was analyzed and based on this, the limitations and improvements were analyzed to propose the establishment of IoT-based Total Silver Care Center. IoT-based Total Silver Care Center may be conveniently monitored the health status of the elderly through various sensors, medical devices, and smart bands. And based on this, it can improve the quality of nursing services through time-saving and work efficiency of nursing providers. In addition, health care interventions may be provided in a timely manner if there is a change in the health status of users. And real-time imaging systems can help overcome mental difficulties.

• Korean Journal of Psychosomatic Medicine
• /
• v.29 no.2
• /
• pp.121-127
• /
• 2021

Objectives : The characteristics of depressive symptoms in patients with cancer is different from those in control group. However, few research has focused on the association between depressive symptoms in cancer patients. The aim of this study was to compare the network structure of depressive symptoms between patients with cancer and normal control. Methods : This study was based on cohort data from Korea National Health and Nutrition Examination Survey in 2016-2018. The Patient health Quetionnaire-9 (PHQ-9) was used to assess depressive symptoms in 599 patients with cancer and 599 age-sex matched controls. We estimated network structure of depressive symptom using Isingfit model. Results : There was no significant difference of each PHQ-9 item score. There were strong associations between symptoms were concentration problem-psychomotor activity, anhedonia-depressed mood, and depressed mood-suicidal ideation in both groups. Strength centrality of worthlessness was significantly higher in patients with cancer. Conclusions : These results suggest that worthless is associated with other depressive symptoms more tightly in patients with cancer. Worthless can serve as important treatment targets for intervention of depression in patients with cancer.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.11
• /
• pp.1-9
• /
• 2021

3D-NAND flash memory provides high capacity per unit area by stacking 2D-NAND cells having a planar structure. However, due to the nature of the lamination process, there is a problem that the frequency of error occurrence may vary depending on each layer or physical cell location. This phenomenon becomes more pronounced as the number of write/erase(P/E) operations of the flash memory increases. Most flash-based storage devices such as SSDs use ECC for error correction. Since this method provides a fixed strength of data protection for all flash memory pages, it has limitations in 3D NAND flash memory, where the error rate varies depending on the physical location. Therefore, in this paper, pages and layers with different error rates are classified into clusters through the K-means machine learning algorithm, and differentiated data protection strength is applied to each cluster. We classify pages and layers based on the number of errors measured after endurance test, where the error rate varies significantly for each page and layer, and add parity data to stripes for areas vulnerable to errors to provides differentiate data protection strength. We show the possibility that this differentiated data protection policy can contribute to the improvement of reliability and lifespan of 3D NAND flash memory compared to the protection techniques using RAID-like or ECC alone.