He Ma

He Ma

Auto-generated profile, based on publicly available information

He Ma

Navigation College, Dalian Maritime University, Dalian 116026, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 January 2022 in Journal of Advanced Transportation
Verified
Journal Article
Open access
PDF file
HMHe Ma
He Ma
Yi ZuoYi Zuo
Yi Zuo
Tieshan LiTieshan Li
Tieshan Li
With the increasing application and utility of automatic identification systems (AISs), large volumes of AIS data are collected to record vessel navigation. In recent years, the prediction of vessel trajectories has become one of the hottest research issues. In contrast to existing studies, most researchers have focused on the single-trajectory prediction of vessels. This article proposes a multiple-trajectory prediction model and makes two main contributions. First, we propose a novel method of trajectory feature representation that uses a hierarchical clustering algorithm to analyze and extract the vessel navigation behavior for multiple trajectories. Compared with the classic methods, e.g., Douglas–Peucker (DP) and least-squares cubic spline curve approximation (LCSCA) algorithms, the mean loss of trajectory features extracted by our method is approximately 0.005, and it is reduced by 50% and 30% compared to the DP and LCSCA algorithms, respectively. Second, we design an integrated model for simultaneous prediction of multiple trajectories using the proposed features and employ the long short-term memory (LSTM)-based neural network and recurrent neural network (RNN) to pursue this time series task. Furthermore, the comparative experiments prove that the mean value and standard deviation of root mean squared error (RMSE) using the LSTM are 4% and 14% lower than those using the RNN, respectively.


1 December 2019
Verified
Conference Paper
Closed access
YSYing Su
Ying Su
WSWeizhong Sun
Weizhong Sun
YSYanchi Shi
Yanchi Shi
FHFangfang Han
Fangfang Han
HMHe Ma
He Ma
YKYing Kang
Ying Kang
During the diagnosis and treatment of cervical cancer, the relative position between cervical tumor boundary and cervical wall is an essential standard for cervical cancer staging. To obtain an accurate tumor boundary, it is of great clinical significance to design an algorithm which can accurately extract cervical tumor. Based on Magnetic Resonance Imaging (MRI), an algorithm combining the global information of images with Region Growing criteria is proposed in this paper, named Globally Adaptive Region Growing (GARG). First, preprocess the original images to reduce the interference of surrounding tissues and smooth the noise. Second, combining the global information into traditional Region Growing method, an automatic threshold initialization segmentation is realized. Third, apply the morphological operations to acquire more accurate target regions. The results obtained by the algorithm are contrasted with the tumor regions manually painted by doctors. The highest overlap rate reaches 93.8%, with 85.4% on average, which are superior to the results obtained by classic Region Growing, C-V Level Set and Threshold method. It has been proved that the algorithm can provide effective reference for the identification of tumor boundaries, which improves work efficiency of doctors to a large extent. It also reduces the influence of subjectivity and uncertainty on segmentation results at the same time. The proposed GARG method greatly shows the innovation on cervical tumor segmentation and its clinical significance.