• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.11
• /
• pp.151-157
• /
• 2017

Recently, the retail industry has created efficient store operations, and has differentiated customer service through the future store. The intelligence of these stores is being applied by using technologies such as the Internet of Things (IoT), and the business process is being improved through this. The process also focuses on efficient store operations and service developments to provide customers with shopping convenience. The change in trends in the industry means that domestic distribution has already reached maturity. Even in countries where retail industries are mature, such as the U.S. and Europe, recent trends are moving toward maximizing operational efficiency and customer service. The reason is that many retailers have already reached saturation and survived the competition. This paper is a study of a drive-through service for automation and efficiency in receiving service after ordering by a customer of the distribution store. When ordering a product being purchased by a customer, the product picking process is done in a timely fashion through a picking scheduling agent. When the customer enters the store parking lot, a service supports the entry of information and finding a parking place so the customer can quickly pick up the goods. The proposed service can be applied to a retail store drive-through system, the distribution store's delivery system, the digital picking system, and indoor/outdoor large parking management systems, and it is possible to provide one-dimensional customer service through the application of IoT technology.

• Journal of Environmental Health Sciences
• /
• v.47 no.5
• /
• pp.410-424
• /
• 2021

Background: Subway stations have the characteristics of being located underground and are a representative public-use facility used by an unspecified number of people. As concerns about indoor air quality (IAQ) increase, various management measures are being implemented. However, there are few systematic studies and cases of long-term continuous measurement of underground station air quality. Objectives: The purpose of this study is to analyze changes and factors influencing IAQ in subway stations through real-time continuous long-term measurement using IoT-based IAQ sensing equipment, and to evaluate the IAQ improvement effect of a bio-filter system. Methods: The IAQ of a subway station in Seoul was measured using IoT-based sensing equipment. A bio-filter system was installed after collecting the background concentrations for about five months. Based on the data collected over about 21 months, changes in indoor air quality and influencing factors were analyzed and the reduction effect of the bio-filter system was evaluated. Results: As a result of the analysis, PM₁₀, PM_2.5, and CO₂ increased during rush hour according to the change in the number of passengers, and PM₁₀ and PM_2.5 concentrations were high when a PM warning/watch was issued. There was an effect of improving IAQ with the installation of the bio-filter system. The reduction rate of a new-bio-filter system with improved efficiency was higher than that of the existing bio-filter system. Factors affecting PM_2.5 in the subway station were the outdoor PM_2.5, platform PM_2.5, and the number of passengers. Conclusions: The IAQ in a subway station is affected by passengers, ventilation through the air supply and exhaust, and the spread of particulate matter generated by train operation. Based on these results, it is expected that IAQ can be efficiently improved if a bio-filter system with improved efficiency is developed in consideration of the factors affecting IAQ and proper placement.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1273-1283
• /
• 2022

Recently, forest fires have frequently occurred due to climate change, leading to human and property damage every year. The forest fire monitoring technique using remote sensing can obtain quick and large-scale information of fire-damaged areas. In this study, the Gangneung and Donghae forest fires that occurred in March 2022 were analyzed using the spectral band of Sentinel-2, the normalized difference vegetation index (NDVI), and the normalized difference water index (NDWI) to classify the affected areas of forest fires. The U-net based convolutional neural networks (CNNs) model was simulated for the fire-damaged areas. The accuracy of forest fire classification in Donghae and Gangneung classification was high at 97.3% (f₁=0.486, IoU=0.946). The same model used in Donghae and Gangneung was applied to Uljin and Samcheok areas to get rid of the possibility of overfitting often happen in machine learning. As a result, the portion of overlap with the forest fire damage area reported by the National Institute of Forest Science (NIFoS) was 74.4%, confirming a high level of accuracy even considering the uncertainty of the model. This study suggests that it is possible to quantitatively evaluate the classification of forest fire-damaged area using a spectral band and indices similar to that of the Compact Advanced Satellite 500 (CAS500-4) in the Sentinel-2.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.377-380
• /
• 2023

본 논문에서는 합성곱 신경망(Convolutional Neural Networks, CNN)과 탄성왜곡(Elastic Distortion) 기법을 통한 데이터 증강 기법을 활용하여 학습 데이터를 구축하는 프레임워크를 제안한다. 실제 균열 이미지는 정형화된 형태가 없고 복잡한 패턴을 지니고 있어 구하기 어려울 뿐만 아니라, 데이터를 확보할 때 위험한 상황에 노출될 우려가 있다. 이러한 데이터베이스 구축 문제점을 본 논문에서 제안하는 데이터 증강 기법을 통해 비용적, 시간적 측면에서 효율적으로 해결한다. 세부적으로는 DeepCrack의 데이터를 10배 이상 증가하여 실제 균열의 특징을 반영한 메타 데이터를 생성하여 U-net을 학습하였다. 성능을 검증하기 위해 균열 탐지 연구를 진행한 결과, IoU 정확도가 향상되었음을 확인하였다. 데이터를 증강하지 않았을 경우 잘못 예측(FP)된 경우의 비율이 약 25%였으나, 데이터 증강을 통해 3%까지 감소하였음을 확인하였다.

• Koreanishche Zeitschrift fur Deutsche Sprachwissenschaft
• /
• v.5
• /
• pp.67-89
• /
• 2002

Die meisten $W\"{o}rter$ im Deutschen, die zur lexikalichen Hauptkategorie $geh\"{o}ren,\;erf\"{u}llen$ die prosodischen Bedingungen, class sie ein phonologisches Wort bilden und class ein phonologisches Wort zumindest aus zwei Moren besteht. In dieser Arbeit wird gezeigt, welche Konsequenzen diese Constraints $f\"{u}r$ die prosodische Gestalt der deutschen $W\"{o}rter$ haben. Eine davon bezieht sich auf das $Ph\"{a}nomen$, das in der Literatur als 'minimales Wort' bekannt ist. Die distributionellen $Beschr\"{a}nkungen$ eines ungespannten kurzen Vokals im Deutschen sind darauf $Zur\"{u}ckzuf\"{u}hren$, class ein prosodisches Wort mindestens zwei Moren enthalten muss. Die Forderung nach einem minimalen Wort wirft aber die Frage, warum ein Stamm wie feige eine zweisilbige Struktur CVCV mit einer finalen Schwasilbe aufweisen, ein Stamm wie reif dagegen eine einsilbige Struktur eve. Allein die Forderung nach einem zweimorigen prosodischen Wort wurde auch eine ungrammatische Form wie feig $erf\"{u}llen$. Bei Formen wie feige ist festzustellen, dass das Constraint IDENT-IO [voiced] wichtiger als das Constraint ist, das einen einsilbigen Stamm verlangt. Eine Analyse, in der die finale Schwa-Silbe in einem CVCV-Stamm als ein stammbildendes Element oder Pseudosuffix aufgefasst wird, kann diese Interaktion zwischen Constraint nicht erfassen. Im Vergleich dazu zeigen die zweisilben Flexionsformen, bei denen Schwa-Silben als ein echtes Suffix fungieren, dass das Constraint 'Realisiere Morphem' nur dann verletzt werden kann, wenn es zur $Erf\"{u}llung\;des\;h\"{o}her$ rangierten Constraints OCP(nucleus) dient. Dieses Constraint ist seinerseits nur dann verletzbar, wenn damit das $h\"{o}here$ Constraint Coda-Cond erfullt werden kann.

• Journal of IKEEE
• /
• v.22 no.1
• /
• pp.174-179
• /
• 2018

In this paper, design of high-efficiency DC-DC converter is presented for low-power PMIC (power management integrated circuit). As PMIC technologies for IoT and wearable devices have been continuously improved, high-efficiency energy harvesting schemes should be essential. Since the supply voltage resulting from energy harvesting is low and widely variable, design techniques to achieve high efficiency over a wide input voltage range are required. To obtain a constant switching frequency for wide input voltage range, frequency compensation circuit using supply-voltage variation sensing circuit is included. In order to obtain high efficiency performance at very low-power condition, accurate burst-mode control circuit was adopted to control switching operations. In the proposed DC-DC buck converter, output voltage is set to be 0.9V at the input voltage of 0.95~3.3V and maximum measured efficiency is up to 78% for the load current of 180uA.

• Analytical Science and Technology
• /
• v.16 no.2
• /
• pp.110-116
• /
• 2003

A study has been done on the separation of iodide from spent pressurized water reactor (PWR) fuels and its quantitative determination using ion chromatography. Spent PWR fuels were dissolved with mixed acid of nitric and hydrochloric acids (80 : 20 molL%) which can oxidize iodide to iodate to prevent it from be vaporized. After reducing ${IO_3}^-$ ­to $I_2$ in 2.5 M $HNO_3$ with $NH_2OH{\cdot}HCl$, Iodine was selectively separated from actinides and all other fission products with carbontetrachloride and back-extracted with 0.1 M $NaHSO_3$. Recovered iodide was determined using the ion chromatograph of which the column was installed in a glove box for the analysis of radioactive materials. In practice, spent PWR fuel with 42,000~44,000 MWd/MtU was analyzed and its quantity was compared to that calculated by burnup code, ORIGEN2. The agreement was achieved with a deviation of -8.3~-0.5% from the ORIGEN 2 data, $324.5{\sim}343.6{\mu}g/g$.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.4
• /
• pp.373-379
• /
• 2019

In this study, image-based flock monitoring and density evaluation were conducted for broiler chicks welfare. Image data were captured by using a mono camera and region of broiler chicks in the image was detected using converting to HSV color model, thresholding, and clustering with filtering. The results show that region detection was performed with 5% relative error and 0.81 IoU on average. The detected region was corrected to the actual region by projection into ground using coordinate transformation between camera and real-world. The flock density of broiler chicks was estimated using the corrected actual region, and it was observed with an average of 80%. The developed algorithm can be applied to the broiler chicks house through enhancing accuracy of region detection and low-cost system configuration.

• The Journal of the Korea Contents Association
• /
• v.21 no.3
• /
• pp.23-32
• /
• 2021

Semantic image segmentation technology in the field of computer vision is a technology that classifies an image by dividing it into pixels. This technique is also rapidly improving performance using a machine learning method, and a high possibility of utilizing information in units of pixels is drawing attention. However, this technology has been raised from the early days until recently for 'lack of detailed segmentation' problem. Since this problem was caused by increasing the size of the label map, it was expected that the label map could be improved by using the edge map of the original image with detailed edge information. Therefore, in this paper, we propose a post-processing algorithm that maintains semantic image segmentation based on learning, but modifies the resulting label map based on the edge map of the original image. After applying the algorithm to the existing method, when comparing similar applications before and after, approximately 1.74% pixels and 1.35% IoU (Intersection of Union) were applied, and when analyzing the results, the precise targeting fine segmentation function was improved.

• Journal of Animal Science and Technology
• /
• v.63 no.6
• /
• pp.1453-1463
• /
• 2021

Feeding is the most important behavior that represents the health and welfare of weanling pigs. The early detection of feed refusal is crucial for the control of disease in the initial stages and the detection of empty feeders for adding feed in a timely manner. This paper proposes a real-time technique for the detection and recognition of small pigs using a deep-leaning-based method. The proposed model focuses on detecting pigs on a feeder in a feeding position. Conventional methods detect pigs and then classify them into different behavior gestures. In contrast, in the proposed method, these two tasks are combined into a single process to detect only feeding behavior to increase the speed of detection. Considering the significant differences between pig behaviors at different sizes, adaptive adjustments are introduced into a you-only-look-once (YOLO) model, including an angle optimization strategy between the head and body for detecting a head in a feeder. According to experimental results, this method can detect the feeding behavior of pigs and screen non-feeding positions with 95.66%, 94.22%, and 96.56% average precision (AP) at an intersection over union (IoU) threshold of 0.5 for YOLOv3, YOLOv4, and an additional layer and with the proposed activation function, respectively. Drinking behavior was detected with 86.86%, 89.16%, and 86.41% AP at a 0.5 IoU threshold for YOLOv3, YOLOv4, and the proposed activation function, respectively. In terms of detection and classification, the results of our study demonstrate that the proposed method yields higher precision and recall compared to conventional methods.