http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Deep Learning-Based Approaches for Nucleus Segmentation
Duy Cuong Bui,유명식 한국통신학회 2024 韓國通信學會論文誌 Vol.49 No.4
The accurate identification of cell nuclei is a critical aspect of various analyses, given that human cells, numbering around 30 trillion, contain DNA as their genetic code. In this research paper, we provide a comprehensive overview of deep learning-based techniques for nucleus segmentation. We have replicated and assessed the state-of-the-art methods using datasets like FCN, SegNet, U-net, and DoubleU-net, with a focus on the Data Science Bowl 2018 dataset comprising 670 training data folders and 65 testing data folders. Our experimental findings reveal that DoubleU-Net surpasses U-Net and other baseline models, yielding more precise segmentation masks. This promising outcome suggests that DoubleU-Net could serve as a robust model for addressing various challenges in medical image segmentation.
Duy Nam Bui,Thi Thanh Van Nguyen,Manh Duong Phung 한국항공우주학회 2023 International Journal of Aeronautical and Space Sc Vol.24 No.2
This paper presents a new Lyapunov-based nonlinear model predictive controller (LNMPC) for the attitude control problem of unmanned aerial vehicles (UAVs), which is essential for their functioning operation. The controller is designed based on a quadratic cost function integrating UAV dynamics and system constraints. An additional contraction constraint is then introduced to ensure closed-loop system stability. That constraint is fulfilled via a Lyapunov function derived from a sliding mode controller (SMC). The feasibility and stability of the LNMPC are finally proved. Simulation and comparison results show that the proposed controller guarantees the system stability and outperforms other state-of-the-art nonlinear controllers, such as the backstepping controller and SMC. In addition, the proposed controller can be integrated into an existing UAV model in the Gazebo simulator to perform software-in-the-loop tests. The results show that the LNMPC is better than the built-in proportional–integral–derivative controller of the UAV, which confirms the validity and applicability of our proposed approach.
A software-controlled bandwidth allocation scheme for multiple router on-chip-networks
Bui, Phan-Duy,Lee, Chanho Institute of Korean Electrical and Electronics Eng 2019 전기전자학회논문지 Vol.23 No.4
As the number of IP cores has been increasing in a System-on-Chip (SoC), multiple routers are included in on-chip-networks. Each router has its own arbitration policy and it is difficult to obtain a desired arbitration result by combining multiple routers. Allocating desired bandwidths to the ports across the routers is more difficult. In this paper, a guaranteed bandwidth allocation scheme using an IP-level QoS control is proposed to overcome the limitations of existing local arbitration policies. Each IP can control the priority of a packet depending on the data communication requirement within the allocated bandwidth. The experimental results show that the proposed mechanism guarantees for IPs to utilize the allocated bandwidth in multiple router on-chip-networks. The maximum error rate of bandwidth allocation of the proposed scheme is only 1.9%.
Fiscal Decentralisation and Spatial Externalities in Vietnam Provincial Economic Growth
Bui Duy Tung,Canh Phuc Nguyen,DINH THANH SU 중앙대학교 경제연구소 2021 Journal of Economic Development Vol.46 No.4
This paper aims to investigate the impacts of fiscal decentralisation on the provincial economic development in 62 Vietnamese provinces from 2011-2018. We estimate a Spatial Durbin Model (SDM) based on a growth model with spatial externalities. The focus of the paper is on the spatial spillover effects of fiscal decentralisation on the provincial income levels. The results confirm the existence of spatial interdependency among Vietnamese provinces. The findings indicate that fiscal decentralisation and physical capital not only affects the income level within one province, but also contribute positively to the outputs of nearby provinces. The study does not find significant effects of human capital on provincial income. We also show that these effects vary across five main economic regions of Vietnam. There is also evidence that the total effects are stronger in high institutional quality levels, which points out to the “sand the wheels” effect. Policy implications are also discussed.
Bui-Duy Linh,Vu-Thi-Minh Ngoc 한국해운물류학회 2021 The Asian journal of shipping and Logistics Vol.37 No.1
Designating the ideal shipping route can spare expenses, enlarge profits and improve the competitiveness of shipping companies. Liner shipping route choice is mainly contingent on fuel cost, which always contributes the major proportion of the ship’s operating cost. Although many studies on this topic have been carried out, none are based on the fuel consumption forecast model designed by the advanced machine learning method. This paper provides a platform idea for selecting the optimal operating route for container ships to minimize fuel cost by using an asymmetric traveling salesman problem (ATSP) algorithm solution, in which the fuel consumption model for the route is estimated based on the deepmachine learning method. Five input variables are given in the model including average velocity, sailing time, ship’s capacity, wind speed, and wind direction. The mean absolute percentage error (MAPE) of the model is 5.89%, indicating that the predictive result obtains a very high accuracy, close to 95%. The optimal model is thus applied in combination with ATSP to address the optimal solution for a certain route.
Real-time Implementation of Passive Auto Focus on DM36x-based IP Network Camera
Bui Duy Cong,Tae in Seol,Sun-Tae Chung,HoSeok Kang,Seongwon Cho 한국통신학회 2013 한국통신학회 학술대회논문집 Vol.2013 No.1
Auto-focus (AF) is one of key features in a camera. The real-time performance of passive AF method is an important issue for successful commercial IP network cameras. This paper proposes a real-time implementation of a passive AF method using focus value for DM36x-based IPNC. The adopted AF searching algorithm is the so-called ‘Modified Rule? based Search’ (MRS) which decides adaptively the amount of the focus motor movement for the next iteration. MRS is well known for faster processing speed and comparable accuracy among AF searching methods. Experimental results indicate that our implementation of the adopted MRS-based AF method works successfully in real-time and outperforms than global searching algorithm with respect to processing speed and accuracy.
Real-time Zoom Tracking for DM36x-based IP Network Camera
Cong, Bui Duy,Seol, Tae In,Chung, Sun-Tae,Kang, HoSeok,Cho, Seongwon Korea Multimedia Society 2013 멀티미디어학회논문지 Vol.16 No.11
Zoom tracking involves the automatic adjustment of the focus motor in response to the zoom motor movements for the purpose of keeping an object of interest in focus, and is typically achieved by moving the zoom and focus motors in a zoom lens module so as to follow the so-called "trace curve", which shows the in-focus motor positions versus the zoom motor positions for a specific object distance. Thus, one can simply implement zoom tracking by following the most closest trace curve after all the trace curve data are stored in memory. However, this approach is often prohibitive in practical implementation because of its large memory requirement. Many other zoom tracking methods such as GZT, AZT and etc. have been proposed to avoid large memory requirement but with a deteriorated performance. In this paper, we propose a new zoom tracking method called 'Approximate Feedback Zoom Tracking method (AFZT)' on DM36x-based IP network camera, which does not need large memory by approximating nearby trace curves, but generates better zoom tracking accuracy than GZT or AZT by utilizing focus value as feedback information. Experiments through real implementation shows the proposed zoom tracking method improves the tracking performance and works in real-time.