• International Journal of Internet, Broadcasting and Communication
• /
• 제14권3호
• /
• pp.193-204
• /
• 2022

The 2018 Seoul Zero Pay is a policy actively promoted by the government as an economic stimulus package for small business owners and the self-employed who are experiencing economic depression due to COVID-19. However, the controversy over the effectiveness of Zero Pay continues even after two years have passed since the implementation of the policy. Zero Pay is a joint QR code mobile payment service introduced by the government, Seoul city, financial companies, and private simple payment providers to reduce the burden of card merchant fees for small business owners and self-employed people who are experiencing economic difficulties due to the economic downturn., it was attempted in the direction of economic revitalization for the return of alleyways[1]. Therefore, this study intends to draw implications for improvement measures so that the ongoing zero-pay can be further activated and the economy can be settled normally. The analysis results of this study are as follows. First, it shows the effect of increasing the income of small business owners by inducing consumption in alleyways through the economic revitalization policy of Zero Pay. Second, the issuance and distribution of Zero Pay helps to revitalize the local economy and contribute to the establishment of a virtuous cycle system. Third, stable operation is being realized by the introduction of blockchain technology to the Zero Pay platform. In terms of academic significance, the direction of Zero Pay's policies and systems was able to identify changes in the use of Zero Pay through big data analysis. The implementation of the zero-pay policy is in its infancy, and there are limitations in factors for examining the consumer image perception of zero-pay as there are insufficient prior studies. Therefore, continuous follow-up research on Zero Pay should be conducted.

• Fisheries and Aquatic Sciences
• /
• 제25권3호
• /
• pp.151-157
• /
• 2022

Various approaches have been applied to transform aquaculture from a manual, labour-intensive industry to one dependent on automation technologies in the era of the fourth industrial revolution. Technologies associated with the monitoring of physical condition have successfully been applied in most aquafarm facilities; however, real-time biological monitoring systems that can observe fish condition and behaviour are still required. In this study, we used a video recorder placed on top of a fish tank to observe the swimming patterns of rock bream (Oplegnathus fasciatus), first one fish alone and then a group of five fish. Rock bream in the video samples were successfully identified using the you-only-look-once v3 algorithm, which is based on the Darknet-53 convolutional neural network. In addition to recordings of swimming behaviour under normal conditions, the swimming patterns of fish under abnormal conditions were recorded on adding an anaesthetic or lowering the salinity. The abnormal conditions led to changes in the velocity of movement (3.8 ± 0.6 cm/s) involving an initial rapid increase in speed (up to 16.5 ± 3.0 cm/s, upon 2-phenoxyethanol treatment) before the fish stopped moving, as well as changing from swimming upright to dying lying on their sides. Machine learning was applied to datasets consisting of normal or abnormal behaviour patterns, to evaluate the fish behaviour. The proposed algorithm showed a high accuracy (98.1%) in discriminating normal and abnormal rock bream behaviour. We conclude that artificial intelligence-based detection of abnormal behaviour can be applied to develop an automatic bio-management system for use in the aquaculture industry.

• 한국농공학회논문집
• /
• 제64권3호
• /
• pp.63-73
• /
• 2022

A more accurate understanding of the irrigation water supply is necessary for efficient agricultural water management. Although we measure water levels in an irrigation canal using ultrasonic water level gauges, some errors occur due to malfunctions or the surrounding environment. This study aims to apply CNN (Convolutional Neural Network) Deep-learning-based image classification and segmentation models to the irrigation canal's CCTV (Closed-Circuit Television) images. The CCTV images were acquired from the irrigation canal of the agricultural reservoir in Cheorwon-gun, Gangwon-do. We used the ResNet-50 model for the image classification model and the U-Net model for the image segmentation model. Using the Natural Breaks algorithm, we divided water level data into 2, 4, and 8 groups for image classification models. The classification models of 2, 4, and 8 groups showed the accuracy of 1.000, 0.987, and 0.634, respectively. The image segmentation model showed a Dice score of 0.998 and predicted water levels showed R² of 0.97 and MAE (Mean Absolute Error) of 0.02 m. The image classification models can be applied to the automatic gate-controller at four divisions of water levels. Also, the image segmentation model results can be applied to the alternative measurement for ultrasonic water gauges. We expect that the results of this study can provide a more scientific and efficient approach for agricultural water management.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.195-206
• /
• 2022

Crack detection is essential for inspection of existing structures and crack segmentation based on deep learning is a significant solution. However, datasets are usually one of the key issues. When building a new dataset for deep learning, laborious and time-consuming annotation of a large number of crack images is an obstacle. The aim of this study is to develop an approach that can automatically select a small portion of the most informative crack images from a large pool in order to annotate them, not to label all crack images. An active learning method with difficulty learning mechanism for crack segmentation tasks is proposed. Experiments are carried out on a crack image dataset of a steel box girder, which contains 500 images of 320×320 size for training, 100 for validation, and 190 for testing. In active learning experiments, the 500 images for training are acted as unlabeled image. The acquisition function in our method is compared with traditional acquisition functions, i.e., Query-By-Committee (QBC), Entropy, and Core-set. Further, comparisons are made on four common segmentation networks: U-Net, DeepLabV3, Feature Pyramid Network (FPN), and PSPNet. The results show that when training occurs with 200 (40%) of the most informative crack images that are selected by our method, the four segmentation networks can achieve 92%-95% of the obtained performance when training takes place with 500 (100%) crack images. The acquisition function in our method shows more accurate measurements of informativeness for unlabeled crack images compared to the four traditional acquisition functions at most active learning stages. Our method can select the most informative images for annotation from many unlabeled crack images automatically and accurately. Additionally, the dataset built after selecting 40% of all crack images can support crack segmentation networks that perform more than 92% when all the images are used.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.17-28
• /
• 2022

The cable component of cable-stayed bridges is gradually impacted by weather conditions, vehicle loads, and material corrosion. The stayed cable is a critical load-carrying part that closely affects the operational stability of a cable-stayed bridge. Damaged cables might lead to the bridge collapse due to their tension capacity reduction. Thus, it is necessary to develop structural health monitoring (SHM) techniques that accurately identify damaged cables. In this work, a combinational identification method of three efficient techniques, including statistical analysis, clustering, and neural network models, is proposed to detect the damaged cable in a cable-stayed bridge. The measured dataset from the bridge was initially preprocessed to remove the outlier channels. Then, the theory and application of each technique for damage detection were introduced. In general, the statistical approach extracts the parameters representing the damage within time series, and the clustering approach identifies the outliers from the data signals as damaged members, while the deep learning approach uses the nonlinear data dependencies in SHM for the training model. The performance of these approaches in classifying the damaged cable was assessed, and the combinational identification method was obtained using the voting ensemble. Finally, the combination method was compared with an existing outlier detection algorithm, support vector machines (SVM). The results demonstrate that the proposed method is robust and provides higher accuracy for the damaged cable detection in the cable-stayed bridge.

• 한국소프트웨어감정평가학회 논문지
• /
• 제16권2호
• /
• pp.127-133
• /
• 2020

인공지능의 활용성이 다양해지면서 소형 휴대용기기에 알고리즘을 탑재하려는 요구가 증가하고 있다. 또한 임베디드 시스템이 고성능화하면서 운영체제는 물론 고속연산 및 머신러닝의 알고리즘 구현이 가능해 지고 있다. 그러나 반복연산과 방대한 학습데이터를 처리하는 머신러닝알고리즘의 특성으로 네트워크 연결에 의한 클라우드 환경에 의존하고 있다. 임베디드 시스템에서의 독자적인 운영을 위해서는 저 전력화 및 최적화 알고리즘에 의한 빠른 실행이 요구된다. 본 연구에서는 스마트 제어를 목적으로 임베디드 시스템에 에너지 측정용 센서를 연결하고, 실시간 측정 및 모니터링 시스템으로 측정정보를 데이터베이스로 저장하는 장치를 구현하였다. 연속적으로 측정되어 저장된 데이터는 학습 알고리즘에 적용하여, 최적화 전력제어에 활용가능하며, 에너지 측정에 요구되는 다양한 센서의 인터페이스가 가능한 시스템을 구성하였다.

• 한국정보통신학회논문지
• /
• 제26권7호
• /
• pp.981-988
• /
• 2022

정보통신기술(ICT)를 적용한 스마트팩토리로 불리는 지능형 생산 공장은 각종 센서를 통해 공정 데이터를 실시간으로 수집하고 있다. 이렇게 수집된 데이터를 효과적으로 활용하는 연구가 많이 진행되고 있는데, 본 논문에서는 생산 공정에서 발생되는 음향 신호를 기반으로 공구 상태를 진단하는 기법을 제안한다. 첫 번째로 결함이 있는 공구를 감지할 뿐만 아니라 공회전 및 공정 운용에 따른 다양한 공구 상태를 제시한다. 두 번째로 푸리에 분석을 이용하여 사운드의 전력스펙트럼을 영상으로 표현하고, 데이터에 숨겨진 건강한 패턴을 드러내고, 강조하기 위해 일부 변형을 적용한다. 마지막으로 이렇게 획득한 대비 강화된 PSD 영상은 CNN을 이용해 상태별로 진단한다. 그 결과 제안한 음향 PSD 영상 + CNN 방법은 데이터의 차별화된 특징이 잘 반영되어 공구 상태에 따른 높은 진단 결과를 보여준다.

• 한국전자통신학회논문지
• /
• 제17권4호
• /
• pp.617-624
• /
• 2022

V2X를 탑재한 소형 전기운송차는 기존 자동차의 운전시스템에 더 많은 정보와 기능을 제공할 수 있다. V2X 기술의 주요 요소는 V2V(자동차 대 자동차), V2N(자동차 대 네트워크), V2I(자동차 대 인프라) 등이 있다. 본 연구는 외부장비와 연계되는 VI형 E-PTO를 설계하고 구현하는 것으로 E-PTO는 DC/DC 변환기, DC/AC 변환기, 배터리 양방향 충전시스템 등으로 구성된다. 또한 구동을 위한 기기와 제어시스템을 구현하였다. 기동/정지 및 정상상태 운전 통한 VI형 E-PTO 구성부품에 대한 시험결과는 100ms 이내 회복시간과 순간 전압변동율 10%의 허용 가능한 요건을 충족하였다.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제11권2호
• /
• pp.51-58
• /
• 2022

블록체인 기술은 블록체인 네트워크에 참여하는 사용자의 데이터가 분산 처리되어 저장되는 시스템이다. 비트코인과 이더리움을 필두로 세계적으로 관심을 받고 있으며, 블록체인의 활용성은 무궁무진한 것으로 예측되고 있다. 하지만 블록체인의 모든 데이터를 네트워크 참여자에게 공개하는 투명성으로 인해 블록체인 데이터 프라이버시 보호에 대한 필요성이 개인정보를 처리하는 각종 금융, 의료, 부동산 분야에서 떠오르고 있다. 기존 블록체인 데이터 프라이버시 보호를 위해서 스마트 컨트랙트, 동형암호화, 암호학 키 방식을 사용하는 연구들이 주를 이루었으나, 본 논문에서는 기존의 논문들과 차별화된 매트릭스 문자 재배치 기법을 사용한 데이터 프라이버시 보호를 제안한다. 본 논문에서 제안하는 접근방안은 원본 데이터를 매트릭스 문자 재배치 하는 방법, 배치된 데이터를 다시 원본으로 되돌리는 방법, 크게 두 가지로 구성이 되어있다. 정성적인 실험을 통해 본 논문에서 제안하는 접근방안의 안전성을 평가하였으며, 매트릭스 문자 재배치가 적용된 데이터를 원본 데이터로 되돌릴 때 걸리는 시간을 측정하여 프라이빗 블록체인 환경에서도 충분히 적용이 가능할 것이라는 것을 증명하였다.

• Proceedings of the National Institute of Ecology of the Republic of Korea
• /
• 제3권1호
• /
• pp.54-65
• /
• 2022

Species distribution models are a useful tool for predicting future distribution and establishing a preemptive response of invasive species. However, few studies considered the possibility of habitat for the aquatic organism and the number of target sites was relatively small compared to the area. Environmental DNA (eDNA) is the emerging tool as the methodology obtaining the bulk of species presence data with high detectability. Thus, this study applied eDNA survey results of Micropterus salmoides and Lepomis macrochirus to species distribution modeling by seasons in the Anyang stream network. Maximum Entropy (MaxEnt) model evaluated that both species extended potential distribution area in October compared to July from 89.1% (12,110,675 m²) to 99.3% (13,625,525 m²) for M. salmoides and 76.6% (10,407,350 m²) to 100% (13,724,225 m²) for L. macrochirus. The prediction value by streams was varied according to species and seasons. Also, models elucidate the significant environmental variables which affect the distribution by seasons and species. Our results identified the potential of eDNA methodology as a way to retrieve species data effectively and use data for building a model.