http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Trinh Tuan Hung,Tran Quang Duy,Sang-Hoon Bae(배상훈) 대한교통학회 2021 대한교통학회 학술대회지 Vol.85 No.-
Safe driving is one of important factors for evaluating the traffic service quality. Almost traffic accident were caused by human errors, which was about 94% according to the National Highway Traffic Safety Administration (Singh, 2015). In order to solve the safe driving problem, autonomous vehicles (AVs) were getting a promising way to reduce accidents, human stress, and emissions (Crayton and Meier, 2017). Moreover, the development of cooperative intelligent transport systems (C_ITS) and advanced driver assistance systems (ADAS) can help to push the AVs in the real environment. Various studies mainly focused on an operation of AVs under mixed traffic environment in which the AVs will share the road with human-driven vehicles. Recently, reinforcement learning (RL) is a branch of machine learning, which optimized the reward to generate an appropriate policy for autonomous agents. The Markov decision process (MDP) is an original RL for full observations. In order to address the uncertain environment, the partially observable Markov decision process (POMDP) was applied for the partial observation MDP, such as traffic signal control (Manniona et al., 2015) and roundabout(Garc Cuenca et al., 2019).
박다윤,배상훈,TRINH TUAN HUNG,박부기,정보경 한국ITS학회 2023 한국ITS학회논문지 Vol.22 No.1
Several efforts in Korea are currently underway with the goal of commercializing autonomous vehicles. Hence, various studies are emerging on autonomous vehicles that drive safely and quickly according to operating guidelines. The current study examines the path search of an autonomous vehicle from a microscopic viewpoint and tries to prove the efficiency required by learning the lane change of an autonomous vehicle through Deep Q-Learning. A SUMO was used to achieve this purpose. The scenario was set to start with a random lane at the starting point and make a right turn through a lane change to the third lane at the destination. As a result of the study, the analysis was divided into simulation-based lane change and simulation-based lane change applied with Deep Q-Learning. The average traffic speed was improved by about 40% in the case of simulation with Deep Q-Learning applied, compared to the case without application, and the average waiting time was reduced by about 2 seconds and the average queue length by about 2.3 vehicles. 현재 국내에서는 자율주행차량의 상용화를 목표로 다양한 노력을 기울이고 있으며 자율주행차량이 운영 가이드라인에 따라 안전하고 신속하게 주행할 수 있는 연구들이 대두되고 있다. 본 연구는 자율주행차량의 경로탐색을 미시적인 관점으로 바라보며 Deep Q-Learning을 통해 자율주행차량의 차로변경을 학습시켜 효율성을 입증하고자 한다. 이를 위해 SUMO를 사용하였으며, 시나리오는 출발지에서 랜덤 차로로 출발하여 목적지의 3차로까지 차로변경을 통해우회전하는 것으로 설정하였다. 연구 결과 시뮬레이션 기반의 차로변경과 Deep Q-Learning을적용한 시뮬레이션 기반의 차로변경으로 구분하여 분석하였다. 평균 통행 속도는 Deep Q-Learning을 적용한 시뮬레이션의 경우가 적용하지 않은 경우에 비해 약 40% 향상되었으며평균 대기 시간은 약 2초, 평균 대기 행렬 길이는 약 2.3대 감소하였다.
Nguyen Van Quy,Tran Minh Hung,Trinh Quang Thong,Le Anh Tuan,Tran Quang Huy,Nguyen Duc Hoa 한국물리학회 2013 Current Applied Physics Vol.13 No.8
The controlled synthesis of mesoporous silica and metal oxide nanocomposites with a highly ordered porous structure and large specific surface area for specific applications has been an attractive topic in the field of porous materials. Herein, we introduce a novel method for the fabrication of highly ordered mesoporous structured and large specific surface area Fe2O3/SiO2 nanocomposites, and consider their application in room temperature gas sensors. The mesoporous Fe2O3/SiO2 nanocomposites were synthesised by a two-step method, which combines the hydrothermal growth of Fe2O3 nanoparticles and the microemulsion phase of Brij 56 (C16EO10) surfactant as templates in instantly direct-templating synthesis. This synthesis method enables the fabrication of mesoporous Fe2O3/SiO2 nanocomposites without distortion of the ordered porous structure after calcination at high temperature. The synthesised materials were found to be efficient in a room temperature VOC sensor application, with good recovery.
Investigation of flexural behavior of a prestressed girder for bridges using nonproprietary UHPC
Pham, Hoa D.,Khuc, Tung,Nguyen, Tuan V.,Cu, Hung V.,Le, Danh B.,Trinh, Thanh P. Techno-Press 2020 Advances in concrete construction Vol.10 No.1
Ultra-high-performance concrete (UHPC) is recognized as a promising material in future civil engineering projects due to its outstanding mechanical and durability properties. However, the lack of local UHPC materials and official standards, especially for prestressed UHPC structures, has limited the application of UHPC. In this research, a large-scale prestressed bridge girder composed of nonproprietary UHPC is produced and investigated. This work has two objectives to develop the mixing procedure required to create UHPC in large batches and to study the flexural behavior of the prestressed girder. The results demonstrate that a sizeable batch of UHPC can be produced by using a conventional concrete mixing system at any precast factory. In addition, incorporating local aggregates and using conventional mixing systems enables regional widespread use. The flexural behavior of a girder made by this UHPC is investigated including flexural strength, cracking pattern and development, load-deflection curve, and strain and neutral axis behaviors through a comprehensive bending test. The experimental data is similar to the theoretical results from analytical methods based on several standards and recommendations of UHPC design.
Truong Giang Nguyen,Thanh Khiem Nguyen,Ham Hoi Nguyen,Hong Son Trinh,Tuan Hiep Luong,Minh Trong Nguyen,Van Duy Le,Hai Dang Do,Kieu Hung Nguyen,Van Minh Do,Quang Huy Tran,Cuong Thinh Nguyen 한국간담췌외과학회 2024 Annals of hepato-biliary-pancreatic surgery Vol.28 No.1
Backgrounds/Aims: Parenchymal-sparing anatomical hepatectomy (Ps–AH) based on portal ramification of the right anterior section (RAS) is a new technique to avoid unnecessarily transecting too much liver parenchyma, especially in cases of major anatomical hepatectomy. Methods: We prospectively assessed 26 patients with primary hepatic malignancies having undergone major Ps–AH based on portal ramification of the RAS from August 2018 to August 2022 (48 months). The perioperative indications, clinical data, intra-operative index, pathological postoperative specimens, postoperative complications, and follow-up results were retrospectively evaluated. Results: Among the 26 patients analyzed, there was just one case that had intrahepatic cholangiocarcinoma The preoperative level of α– Fetoprotein was 25.2 ng/mL. All cases (100%) had Child–Pugh A liver function preoperatively. The ventral/dorsal RAS was preserved in 19 and 7 patients, respectively. The mean surgical margin was 6.2 mm. The mean surgical time was 228.5 minutes, while the mean blood loss was 255 mL. In pathology, 5 cases (19.2%) had microvascular invasion, and in the group of HCC patients, 92% of all cases had moderate or poor tumor differentiation. Six cases (23.1%) of postoperative complications were graded over III according to the Clavien–Dindo system, including in three patients resistant ascites or intra-abdominal abscess that required intervention. Conclusions: Parenchymal-sparing anatomical hepatectomy based on portal ramification of the RAS to achieve R0-resection was safe and effective, with favorable short-term outcomes. This technique can be used widely in clinical practice.