http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Development of Optimized Headland Turning Mechanism on an Agricultural Robot for Korean Garlic Farms
Ha, JongWoo,Lee, ChangJoo,Pal, Abhishesh,Park, GunWoo,Kim, HakJin Korean Society for Agricultural Machinery 2018 바이오시스템공학 Vol.43 No.4
Purpose: Conventional headland turning typically requires repeated forward and backward movements to move the farming equipment to the next row. This research focuses on developing an upland agricultural robot with an optimized headland turning mechanism that enables a $180^{\circ}$ turning positioning to the next row in one steering motion designed for a two-wheel steering, four-wheel drive agricultural robot named the HADA-bot. The proposed steering mechanism allows for faster turnings at each headland compared to those of the conventional steering system. Methods: The HADA-bot was designed with 1.7-m wide wheel tracks to travel along the furrows of a garlic bed, and a look-ahead path following algorithm was applied using a real-time kinematic global positioning system signal. Pivot turning tests focused primarily on accuracy regarding the turning radius for the next path matching, saving headland turning time, area, and effort. Results: Several test cases were performed by evaluating right and left turns on two different surfaces: concrete and soil, at three speeds: 1, 2, and 3 km/h. From the left and right side pivot turning results, the percentage of lateral deviation is within the acceptable range of 10% even on the soil surface. This U-turn scheme reduces 67% and 54% of the headland turning time, and 36% and 32% of the required headland area compared to a 50 hp tractor (ISEKI, TA5240, Ehime, Japan) and a riding-type cultivator (CFM-1200, Asia Technology, Deagu, Rep. Korea), respectively. Conclusion: The pivot turning trajectory on both soil and concrete surfaces achieved similar results within the typical operating speed range. Overall, these results prove that the pivot turning mechanism is suitable for improving conventional headland turning by reducing both turning radius and turning time.
( Jongwoo Ha ),( Changjoo Lee ),( Abhishesh Pal ),( Gunwoo Park ),( Hakjin Kim ) 한국농업기계학회 2018 바이오시스템공학 Vol.43 No.4
Purpose: Conventional headland turning typically requires repeated forward and backward movements to move the farming equipment to the next row. This research focuses on developing an upland agricultural robot with an optimized headland turning mechanism that enables a 180° turning positioning to the next row in one steering motion designed for a two-wheel steering, four-wheel drive agricultural robot named the HADA-bot. The proposed steering mechanism allows for faster turnings at each headland compared to those of the conventional steering system. Methods: The HADA-bot was designed with 1.7-m wide wheel tracks to travel along the furrows of a garlic bed, and a look-ahead path following algorithm was applied using a real-time kinematic global positioning system signal. Pivot turning tests focused primarily on accuracy regarding the turning radius for the next path matching, saving headland turning time, area, and effort. Results: Several test cases were performed by evaluating right and left turns on two different surfaces: concrete and soil, at three speeds: 1, 2, and 3 km/h. From the left and right side pivot turning results, the percentage of lateral deviation is within the acceptable range of 10% even on the soil surface. This U-turn scheme reduces 67% and 54% of the headland turning time, and 36% and 32% of the required headland area compared to a 50 hp tractor (ISEKI, TA5240, Ehime, Japan) and a riding-type cultivator (CFM-1200, Asia Technology, Deagu, Rep. Korea), respectively. Conclusion: The pivot turning trajectory on both soil and concrete surfaces achieved similar results within the typical operating speed range. Overall, these results prove that the pivot turning mechanism is suitable for improving conventional headland turning by reducing both turning radius and turning time.
EPE: An Embedded Personalization Engine for Mobile Users
JongWoo Ha,Jung-Hyun Lee,SangKeun Lee IEEE 2014 IEEE internet computing Vol.18 No.1
<P>The proposed embedded personalization engine (EPE) utilizes valuable in-device usage data for inferring mobile user interests in a privacy-preserving manner. To provide users with personalized services, the proposed approach analyzes both the usage data inside a mobile device and service items--such as news articles and mobile apps--using the Open Directory Project (ODP) as a knowledge base. Embedded classification and ranking methodologies effectively match such service items with inferred user interests. The scenario-based evaluation clearly shows that the proposed EPE gives users highly personalized services with both reasonable perceived latency and little energy consumption.</P>
하종우 ( Jongwoo Ha ),이정현 ( Jung-hyun Lee ),박상현 ( Sang-hyun Park ),이상근 ( Sangkeun Lee ) 한국정보처리학회 2009 한국정보처리학회 학술대회논문집 Vol.16 No.2
문맥 광고에서 계층적인 분류 트리를 활용하여 의미적으로 연관된 광고를 매칭하는 기법이 소개되었다. 하지만 기존 기법은 계층 구조의 특성에 기인하여 임의의 광고의 연관성을 측정할 때에는 적합하지 않다. 이러한 문제를 해결하기 위하여 본 논문에서는 분류 트리를 유사도 그래프로 변환한 후 개인화된 페이지 랭크를 응용한 링크 분석 기법을 적용하여 광고의 의미적 연관성을 측정하는 기법을 제안한다. 실험을 통하여 제안 기법이 문맥 광고에서 광고 매칭의 정확도 성능을 향상시킴을 확인하였다.
데이터 방송 환경에서 Sweep SFC를 활용한 효율적인 스카이라인 질의 처리 기법
하종우(JongWoo Ha),최재호(Jae-Ho Choi),이정현(Jung-Hyun Lee),이상근(SangKeun Lee) 한국정보과학회 2011 정보과학회논문지 : 데이타베이스 Vol.38 No.1
본 논문에서는 T-DMB와 같은 데이터 방송 환경에서 모바일 사용자가 스카이라인 질의를 점진적으로 처리하는 문제h를 다룬다. Sweep SFC는 데이터의 속성 값에 따라 인코딩이 이루어지기 때문에, 스카이라인을 점진적으로 처리하는데 유리한 특성이 있다. 이러한 발견에 따라, 기존의 분산 공간 인덱스기법에 Sweep SFC를 적용한 인덱스 제작 기법 및 그에 상응하는 질의 처리 알고리즘을 제안한다. 일련의 실험을 통하여 제안 기법이 질의 처리의 튜닝 시간 및 접근 시간을 비약적으로 개선함을 확인하였다. This paper deals with the problem of progressive processing of skyline queries in data broadcast environments such as T-DMB. Since Sweep SFC is calculated according to the data attributes, it has unique characteristics that enable progressive processing of skyline queries. Based on this observation, we propose an index structure by applying Sweep SFC based on the distributed spatial index and the corresponding processing algorithm. By series of experiments, we confirm that the proposed method significantly improves the performance in terms of the tuning time and the access time.
딥러닝 기반의 분할과 객체탐지를 활용한 도로균열 탐지시스템 개발
하종우(Jongwoo Ha),박경원(Kyongwon Park),김민수(Minsoo Kim) 한국전자거래학회 2021 한국전자거래학회지 Vol.26 No.1
최근 도로균열 탐지에 대한 많은 연구에서 딥러닝 기반의 접근법을 활용하면서 과거 알고리즘 기반의 접근법을 활용한 연구들보다 높은 성능과 성과를 보이고 있다. 그러나 딥러닝 기반의 많은 연구가 여전히 균열의 유형을 분류하는 것에 집중되어 있다. 균열 유형의 분류는 현재 수작업에 의존하고 있는 균열탐지 프로세스를 획기적으로 개선해 줄 수 있다는 점에서 상당한 기대를 받고 있다. 그러나 실제 도로의 유지보수 작업에 있어서는 균열의 유형뿐만 아니라 균열의 심각도에 관한 판단이 필수적이지만, 아직까지 도로균열 탐지와 관련된 연구들이 균열의 심각도에 대한 자동화된 산출까지 진전되지 못하고 있다. 균열의 심각도를 산출하기 위해서는 균열의 유형과 이미지 속 균열의 부위가 함께 파악되어야 한다. 본 연구에서는 균열 유형과 균열 부위의 동시적 탐지를 효과적으로 자동화하기 위해 딥러닝 기반의 객체탐지 모델인 Mobilenet-SSD를 활용하는 방법을 다루고 있다. 균열탐지의 정확도를 개선하기 위해 U-Net을 활용해 입력 이미지를 자동 분할하고, 이를 객체탐지 기법과 결합하기 위한 여러 실험을 진행하여 그 결과를 정리하였다. 결과적으로 U-Net을 활용한 이미지 의 자동 마스킹을 통해 객체탐지의 성능을 mAP 값이 0.9315가 되도록 향상시킬 수 있었다. 본 연구의 결과를 참고하여 도로포장 관리시스템의 구현에 균열탐지 기능의 자동화가 더욱 진전될 수 있다고 기대된다. Many recent studies on deep learning-based road crack detection have shown significantly more improved performances than previous works using algorithm-based conventional approaches. However, many deep learning-based studies are still focused on classifying the types of cracks. The classification of crack types is highly anticipated in that it can improve the crack detection process, which is currently relying on manual intervention. However, it is essential to calculate the severity of the cracks as well as identifying the type of cracks in actual pavement maintenance planning, but studies related to road crack detection have not progressed enough to automated calculation of the severity of cracks. In order to calculate the severity of the crack, the type of crack and the area of the crack in the image must be identified together. This study deals with a method of using Mobilenet-SSD that is deep learning-based object detection techniques to effectively automate the simultaneous detection of crack types and crack areas. To improve the accuracy of object-detection for road cracks, several experiments were conducted to combine the U-Net for automatic segmentation of input image and object-detection model, and the results were summarized. As a result, image masking with U-Net is able to maximize object-detection performance with 0.9315 mAP value. While referring the results of this study, it is expected that the automation of the crack detection functionality on pave management system can be further enhanced.