• Title/Summary/Keyword: DAR(1)

Search Result 385, Processing Time 0.027 seconds

Study of Deep Learning Based Specific Person Following Mobility Control for Logistics Transportation (물류 이송을 위한 딥러닝 기반 특정 사람 추종 모빌리티 제어 연구)

  • Yeong Jun Yu;SeongHoon Kang;JuHwan Kim;SeongIn No;GiHyeon Lee;Seung Yong Lee;Chul-hee Lee
    • Journal of Drive and Control
    • /
    • v.20 no.4
    • /
    • pp.1-8
    • /
    • 2023
  • In recent years, robots have been utilized in various industries to reduce workload and enhance work efficiency. The following mobility offers users convenience by autonomously tracking specific locations and targets without the need for additional equipment such as forklifts or carts. In this paper, deep learning techniques were employed to recognize individuals and assign each of them a unique identifier to enable the recognition of a specific person even among multiple individuals. To achieve this, the distance and angle between the robot and the targeted individual are transmitted to respective controllers. Furthermore, this study explored the control methodology for mobility that tracks a specific person, utilizing Simultaneous Localization and Mapping (SLAM) and Proportional-Integral-Derivative (PID) control techniques. In the PID control method, a genetic algorithm is employed to extract the optimal gain value, subsequently evaluating PID performance through simulation. The SLAM method involves generating a map by synchronizing data from a 2D LiDAR and a depth camera using Real-Time Appearance-Based Mapping (RTAB-MAP). Experiments are conducted to compare and analyze the performance of the two control methods, visualizing the paths of both the human and the following mobility.

Use of Magnetic Resonance Imaging for Evaluating Residual Breast Tissue After Robotic-Assisted Nipple-Sparing Mastectomy in Women With Early Breast Cancer

  • Wen-Pei Wu;Hung-Wen Lai;Chiung-Ying Liao;Joseph Lin;Hsin-I Huang;Shou-Tung Chen;Chen-Te Chou;Dar-Ren Chen
    • Korean Journal of Radiology
    • /
    • v.24 no.7
    • /
    • pp.640-646
    • /
    • 2023
  • Objective: Prospective studies on postoperative residual breast tissue (RBT) after robotic-assisted nipple-sparing mastectomy (R-NSM) for breast cancer are limited. RBT presents an unknown risk of local recurrence or the development of new cancer after curative or risk-reducing mastectomies. This study investigated the technical feasibility of using magnetic resonance imaging (MRI) to evaluate RBT after R-NSM in women with breast cancer. Materials and Methods: In this prospective pilot study, 105 patients, who underwent R-NSM for breast cancer at Changhua Christian Hospital between March 2017 and May 2022, were subjected to postoperative breast MRI to evaluate the presence and location of RBT. The postoperative MRI scans of 43 patients (age, 47.8 ± 8.5 years), with existing preoperative MRI scans, were evaluated for the presence and location of RBT. In total, 54 R-NSM procedures were performed. In parallel, we reviewed the literature on RBT after nipple-sparing mastectomy, considering its prevalence. Results: RBT was detected in 7 (13.0%) of the 54 mastectomies (6 of the 48 therapeutic mastectomies and 1 of the 6 prophylactic mastectomies). The most common location for RBT was behind the nipple-areolar complex (5 of 7 [71.4%]). Another RBT was found in the upper inner quadrant (2 of 7 [28.6%]). Among the six patients who underwent RBT after therapeutic mastectomies, one patient developed a local recurrence of the skin flap. The other five patients with RBT after therapeutic mastectomies remained disease-free. Conclusion: R-NSM, a surgical innovation, does not seem to increase the prevalence of RBT, and breast MRI showed feasibility as a noninvasive imaging tool for evaluating the presence and location of RBT.

Urban Climate Impact Assessment Reflecting Urban Planning Scenarios - Connecting Green Network Across the North and South in Seoul - (서울 도시계획 정책을 적용한 기후영향평가 - 남북녹지축 조성사업을 대상으로 -)

  • Kwon, Hyuk-Gi;Yang, Ho-Jin;Yi, Chaeyeon;Kim, Yeon-Hee;Choi, Young-Jean
    • Journal of Environmental Impact Assessment
    • /
    • v.24 no.2
    • /
    • pp.134-153
    • /
    • 2015
  • When making urban planning, it is important to understand climate effect caused by urban structural changes. Seoul city applies UPIS(Urban Plan Information System) which provides information on urban planning scenario. Technology for analyzing climate effect resulted from urban planning needs to developed by linking urban planning scenario provided by UPIS and climate analysis model, CAS(Climate Analysis Seoul). CAS develops for analyzing urban climate conditions to provide realistic information considering local air temperature and wind flows. Quantitative analyses conducted by CAS for the production, transportation, and stagnation of cold air, wind flow and thermal conditions by incorporating GIS analysis on land cover and elevation and meteorological analysis from MetPhoMod(Meteorology and atmospheric Photochemistry Meso-scale model). In order to reflect land cover and elevation of the latest information, CAS used to highly accurate raster data (1m) sourced from LiDAR survey and KOMPSAT-2(KOrea Multi-Purpose SATellite) satellite image(4m). For more realistic representation of land surface characteristic, DSM(Digital Surface Model) and DTM(Digital Terrain Model) data used as an input data for CFD(Computational Fluid Dynamics) model. Eight inflow directions considered to investigate the change of flow pattern, wind speed according to reconstruction and change of thermal environment by connecting green area formation. Also, MetPhoMod in CAS data used to consider realistic weather condition. The result show that wind corridors change due to reconstruction. As a whole surface temperature around target area decreases due to connecting green area formation. CFD model coupled with CAS is possible to evaluate the wind corridor and heat environment before/after reconstruction and connecting green area formation. In This study, analysis of climate impact before and after created the green area, which is part of 'Connecting green network across the north and south in Seoul' plan, one of the '2020 Seoul master plan'.

The Relative Height Error Analysis of Digital Elevation Model on South Korea to Determine the TargetVertical Accuracy of CAS500-4 (농림위성의 목표 수직기하 정확도 결정을 위한 남한 지역 수치표고모델 상대 오차 분석)

  • Baek, Won-Kyung;Yu, Jin-Woo;Yoon, Young-Woong;Jung, Hyung-Sup;Lim, Joongbin
    • Korean Journal of Remote Sensing
    • /
    • v.37 no.5_1
    • /
    • pp.1043-1059
    • /
    • 2021
  • Forest and agricultural land are very important factors in the environmental ecosystem and securing food resources. Forest and agricultural land should be monitored regularly. CAS500-4 data are expected to be effectively used as a supplement of monitoring forest and agricultural land. Prior to the launch of the CAS500-4, the relative canopy height error analysis of the digital elevation model on South Korea was performed to determine the vertical target accuracy. Especially, by considering area of interest of the CAS500-4 (mountainous or agricultural area), it is conducted that vertical error analysis according to the slope and canopy. For Gongju, Jeju, and Samcheok, the average root mean squared differences were calculated compared to the drone LiDAR digitalsurface models, which were filmed in autumn and winter and the 5 m digital elevation model from the National Geographic Information Institute. As a result, the Shuttle radar topography mission digital elevation model showed a root mean squared differences of about 8.35, 8.19, and 7.49 m, respectively, while the Copernicus digital elevation model showed a root mean squared differences of about 5.65, 6.73, and 7.39 m, respectively. In addition, the root mean squared difference of shuttle radar topography mission digital elevation model and the Copernicus digital elevation model according to the slope angle were estimated on South Korea compared to the 5 m digital elevation model from the National Geographic Information Institute. At the slope angle of between 0° to 5°, root mean squared differences of the Shuttle radar topography mission digital elevation model and the Copernicus digital elevation model showed 3.62 and 2.52 m, respectively. On the other hands root mean squared differences of the Shuttle radar topography mission digital elevation model and the Copernicus digital elevation model respectively showed about 10.16 and 11.62 m at the slope angle of 35° or higher.

Dataset of Long-term Investigation on Change in Hydrology, Channel Morphology, Landscape and Vegetation Along the Naeseong Stream (II) (내성천의 수문, 하도 형태, 경관 및 식생 특성에 관한 장기모니터링 자료 (II))

  • Lee, Chanjoo;Kim, Dong Gu;Hwang, Seung-Yong;Kim, Yongjeon;Jeong, Sangjun;Kim, Sinae;Cho, Hyeongjin
    • Ecology and Resilient Infrastructure
    • /
    • v.6 no.1
    • /
    • pp.34-48
    • /
    • 2019
  • Naeseong Stream is a natural sand-bed river that flows through mountainous and cultivated area in northern part of Gyeongbuk province. It had maintained its inherent landscape characterized by white sandbars before 2010s. However, since then changes occurred, which include construction of Yeongju Dam and the extensive vegetation development around 2015. In this study, long-term monitoring was carried out on Naeseong Stream to analyze these changes objectively. This paper aims to provide a dataset of the investigation on channel morphology and vegetation for the period 2012-2018. Methods of investigation include drone/terrestrial photography, LiDAR aerial survey and on-site fieldwork. The main findings are as follows. Vegetation development in the channel of Naeseong Stream began around 1987. Before 2013 it occurred along the downstream reach and since then in the entire reach. Some of the sites where riverbed is covered with vegetation during 2014~2015 were rejuvenated to bare bars due to the floods afterwards, but woody vegetation was established in many sites. Bed changes occurred due to deposition of sediment on the vegetated surfaces. Though Naeseong Stream has maintained its substantial sand-bed characteristics, there has been a slight tendency in bed material coarsening. Riverbed degradation at the thalweg was observed in the surveyed cross sections. Considering all the results together with the hydrological characteristics mentioned in the precedent paper (I), it is thought that the change in vegetation and landscape along Naeseong Stream was mainly due to decrease of flow. The effect of Yeongju Dam on the change of the riverbed degradation was briefly discussed as well.

Characterization of Fault Kinematics based on Paleoseismic Data in the Malbang area in the Central Part of the Ulsan Fault Zone (고지진학적 자료를 이용한 울산단층대 중부 말방지역에서의 단층운동 특성 해석)

  • Park, Kiwoong;Prasanajit, Naik Sambit;Gwon, Ohsang;Shin, Hyeon-Cho;Kim, Young-Seog
    • Journal of the Korean earth science society
    • /
    • v.43 no.1
    • /
    • pp.151-164
    • /
    • 2022
  • According to the records of historical and instrumental earthquakes, the southeastern part of the Korean Peninsula is considered the highest seismic activity area. Owing to recent reports of numerous Quaternary faults along the Yangsan and Ulsan fault zones, paleoseismological studies are being actively conducted in these areas. The study area is located in the central part of the Ulsan fault zone, where the largest number of active faults have been reported. Based on lineament and geomorphic analysis using LiDAR images and aerial photographs, fault-related landforms showing topographic relief were observed and a trench survey was conducted. The trench length 20 m, width 5 m, depth 5 m is located approximately 300 m away to the northeast from the previously reported Malbang fault. From the trench section, we interpreted the geometric and kinematic characteristics of the fault based on the deformed features of the Quaternary sedimentary layers. The attitude of the reverse fault, N26°W/33°NE, is similar to those of the reported faults distributed along the Ulsan fault zone. Although a single apparent displacement of approximately 40 cm has been observed, the true displacement could not be calculated due to the absence of the slickenline on the fault plane. Based on the geochronological results of the cryogenic structure proposed in a previous study, the most recent faulting event has been estimated as being earlier than the late Wurm glaciation. We interpreted the thrust fault system of the study area as an imbrication structure based on the previous studies and the fault geometry obtained in this additional trench. Although several previous investigations including many trench surveys have been conducted, they found limited success in obtaining the information on fault parameters, which could be due to complex characteristics of the reverse fault system. Additional paleoseismic studies will contribute to solving the mentioned problems and the comprehensive fault evolution.

Mobile Camera-Based Positioning Method by Applying Landmark Corner Extraction (랜드마크 코너 추출을 적용한 모바일 카메라 기반 위치결정 기법)

  • Yoo Jin Lee;Wansang Yoon;Sooahm Rhee
    • Korean Journal of Remote Sensing
    • /
    • v.39 no.6_1
    • /
    • pp.1309-1320
    • /
    • 2023
  • The technological development and popularization of mobile devices have developed so that users can check their location anywhere and use the Internet. However, in the case of indoors, the Internet can be used smoothly, but the global positioning system (GPS) function is difficult to use. There is an increasing need to provide real-time location information in shaded areas where GPS is not received, such as department stores, museums, conference halls, schools, and tunnels, which are indoor public places. Accordingly, research on the recent indoor positioning technology based on light detection and ranging (LiDAR) equipment is increasing to build a landmark database. Focusing on the accessibility of building a landmark database, this study attempted to develop a technique for estimating the user's location by using a single image taken of a landmark based on a mobile device and the landmark database information constructed in advance. First, a landmark database was constructed. In order to estimate the user's location only with the mobile image photographing the landmark, it is essential to detect the landmark from the mobile image, and to acquire the ground coordinates of the points with fixed characteristics from the detected landmark. In the second step, by applying the bag of words (BoW) image search technology, the landmark photographed by the mobile image among the landmark database was searched up to a similar 4th place. In the third step, one of the four candidate landmarks searched through the scale invariant feature transform (SIFT) feature point extraction technique and Homography random sample consensus(RANSAC) was selected, and at this time, filtering was performed once more based on the number of matching points through threshold setting. In the fourth step, the landmark image was projected onto the mobile image through the Homography matrix between the corresponding landmark and the mobile image to detect the area of the landmark and the corner. Finally, the user's location was estimated through the location estimation technique. As a result of analyzing the performance of the technology, the landmark search performance was measured to be about 86%. As a result of comparing the location estimation result with the user's actual ground coordinate, it was confirmed that it had a horizontal location accuracy of about 0.56 m, and it was confirmed that the user's location could be estimated with a mobile image by constructing a landmark database without separate expensive equipment.

Estimation of Fractional Urban Tree Canopy Cover through Machine Learning Using Optical Satellite Images (기계학습을 이용한 광학 위성 영상 기반의 도시 내 수목 피복률 추정)

  • Sejeong Bae ;Bokyung Son ;Taejun Sung ;Yeonsu Lee ;Jungho Im ;Yoojin Kang
    • Korean Journal of Remote Sensing
    • /
    • v.39 no.5_3
    • /
    • pp.1009-1029
    • /
    • 2023
  • Urban trees play a vital role in urban ecosystems,significantly reducing impervious surfaces and impacting carbon cycling within the city. Although previous research has demonstrated the efficacy of employing artificial intelligence in conjunction with airborne light detection and ranging (LiDAR) data to generate urban tree information, the availability and cost constraints associated with LiDAR data pose limitations. Consequently, this study employed freely accessible, high-resolution multispectral satellite imagery (i.e., Sentinel-2 data) to estimate fractional tree canopy cover (FTC) within the urban confines of Suwon, South Korea, employing machine learning techniques. This study leveraged a median composite image derived from a time series of Sentinel-2 images. In order to account for the diverse land cover found in urban areas, the model incorporated three types of input variables: average (mean) and standard deviation (std) values within a 30-meter grid from 10 m resolution of optical indices from Sentinel-2, and fractional coverage for distinct land cover classes within 30 m grids from the existing level 3 land cover map. Four schemes with different combinations of input variables were compared. Notably, when all three factors (i.e., mean, std, and fractional cover) were used to consider the variation of landcover in urban areas(Scheme 4, S4), the machine learning model exhibited improved performance compared to using only the mean of optical indices (Scheme 1). Of the various models proposed, the random forest (RF) model with S4 demonstrated the most remarkable performance, achieving R2 of 0.8196, and mean absolute error (MAE) of 0.0749, and a root mean squared error (RMSE) of 0.1022. The std variable exhibited the highest impact on model outputs within the heterogeneous land covers based on the variable importance analysis. This trained RF model with S4 was then applied to the entire Suwon region, consistently delivering robust results with an R2 of 0.8702, MAE of 0.0873, and RMSE of 0.1335. The FTC estimation method developed in this study is expected to offer advantages for application in various regions, providing fundamental data for a better understanding of carbon dynamics in urban ecosystems in the future.

A Feasibility Study for Mapping Using The KOMPSAT-2 Stereo Imagery (아리랑위성 2호 입체영상을 이용한 지도제작 가능성 연구)

  • Lee, Kwang-Jae;Kim, Youn-Soo;Seo, Hyun-Duck
    • Journal of the Korean Association of Geographic Information Studies
    • /
    • v.15 no.1
    • /
    • pp.197-210
    • /
    • 2012
  • The KOrea Multi-Purpose SATellite(KOMPSAT)-2 has a capability to provide a cross-track stereo imagery using two different orbits for generating various spatial information. However, in order to fully realize the potential of the KOMPSAT-2 stereo imagery in terms of mapping, various tests are necessary. The purpose of this study is to evaluate the possibility of mapping using the KOMPSAT-2 stereo imagery. For this, digital plotting was conducted based on the stereoscopic images. Also the Digital Elevation Model(DEM) and an ortho-image were generated using digital plotting results. An accuracy of digital plotting, DEM, and ortho-image were evaluated by comparing with the existing data. Consequently, we found that horizontal and vertical error of the modeling results based on the Rational Polynomial Coefficient(RPC) was less than 1.5 meters compared with the Global Positioning System(GPS) survey results. The maximum difference of vertical direction between the plotted results in this study and the existing digital map on the scale of 1/5,000 was more than 5 meters according as the topographical characteristics. Although there were some irregular parallax on the images, we realized that it was possible to interpret and plot at least seventy percent of the layer which was required the digital map on the scale of 1/5,000. Also an accuracy of DEM, which was generated based on the digital plotting, was compared with the existing LiDAR DEM. We found that the ortho-images, which were generated using the extracted DEM in this study, sufficiently satisfied with the requirement of the geometric accuracy for an ortho-image map on the scale of 1/5,000.

Nutrition Survey in Younghung Island (영흥도 주민의 영양실태조사)

  • Kim, Joung-Kyun;Min, Kyung-Chan;Yi, Taek-Ku
    • Journal of Nutrition and Health
    • /
    • v.11 no.4
    • /
    • pp.31-38
    • /
    • 1978
  • Younghung-myun is located on a small island under the jurisdiction of Gyunggi province. The island occupying a total of approximately 40sq km is populated by 5,850 people. Two areas within the island were selected for this survey; 1) Nae 4-ri in Younghung-myun (mainly engaged in farming) 2) Nae 5-ri in Younghung-myun (mainly engaged in fishery) The survey was conducted for the period of 5-12 august 1978. Intake of foods and nutrients of all members in the households surveyed by means of questionnaire was computed based on number of meals a day. On the other hand, daily intake of nutrients by an individual was calculated by sex, age and type of work based on the conversion rate of RDA (Korean Recommended Dietary Allowances for Adult). The results obtained are summarized; 1. Status of food intake Average daily food intake of an individual in the surveyed areas was 1,018gm. Out of 1,018gm above, 490gm which represent 48% of the total intake were from cereals, grains or other vegetative products. Ratio of animal-origin foods was determined as only 16% of the total intake. These findings led us to the conclusion that people in the surveyed areas live heavily on vegetative foods. 2. Status of nutrients intake 1) Overall average intake of calorie by an individual in the surveyed areas was 2026.3Kcal per day. On the other hand, average calorie intake by adult persons was 2,491.3 Kcal per day, which is lower than 2,700 Kcal recommended by RDA by approximately 7.7%. Furthermore, it was observed that most of 2,491.3 Kcal obtained by adult persons was from such vegetative foods as cereals, grains, ect. 2) Overall average intake of protein by an individual in the areas surveyed was 52.2gm per dar. On the other hand, average protein intake among adult persons was 67.7gm a day, which indicates lower intake of protein than 80gm of RDA. It was also found that 84.3% of the protein intake by an adult person was of plant origin. 3) Overall average of fat intake by an individual in the areas surveyed was 18.9gm per day, whereas average fat intake among adult persons was 23. 2gm a day. It was brought to our attention that the average fat intake by adult persons is much lower than 36gm recom mended by RDA. 4) Average calcium intake among adult persons in the areas surveyed was 457.1mg per day, that is somewhat lower than 500mg in RDA. However, average iron intake among adult persons in the areas was slightly higher with 10.5mg a day than 10mg of RDA. 5) With exception with vitamin C, intake of all other vitamin groups, such as vit. A, vit. $B_1$, vit. $B_2$ and niacin, were lower among the inhabitants than recommended by RDA. 3. Economic status Average schooling years of food handlers was 6.5 years with average monthly income of \89,000 in the areas surveyed. Petroleum was used by majority of the households for fuel.

  • PDF