Deep learning technology provides novel solutions for increasingly complex target tracking requirements. For traditional target tracking models, the movement of the target need to be simulated by a predefined mathematical model. However, it is extremely difficult to obtain sufficient information in advance, which makes it challenging to track changeable and noisy trajectories in a timely and precise manner. A deep learning framework is constructed for automatic trajectory tracking based on learning the dynamic laws of motion, called DeepGTT. Specifically, a trajectory generator and a trajectory mapper were designed to standardise trajectory data and construct trajectory mapping, which enable the long short-term memory-based tracking network to learn general dynamic laws. Then, to discuss the interpretability of the model, the mechanism of the deep learning framework is considered and a memory factor matrix is defined. Finally, extensive experiments are conducted on various weak manoeuvring and manoeuvring scenarios to evaluate the algorithm. Experimental results demonstrate that the DeepGTT algorithm remarkably improves accuracy and efficiency compared with most conventional algorithms and state-of-the-art methods. In addition, interpretability experiments qualitatively prove that the tracking network can perceive dynamic laws when estimating the target state.This is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.

No abstract

Objective: The purpose of this study is to understand the incidence, related factors, and the prognosis factors in order to avoid risk, proper method of diagnosis and treatment and reduce complications and provide the basis. Methods: 85 Vulvar cancer (VC) patients treated in our hospital from 2002.10 to 2012.10 were collected and analyzed by retrospective comparative methods. SPSS19.0 application software was used for the statistical analysis. The clinical data are analyzed by chi-square and F test statistic methods. P < 0.05 was a significant difference between the judgment standard. Results: During 10 years, we treated 3391 cases of the primary malignant tumors including 85 VC cases; VC was 2.89% (85/3391). The age was between 24~88 years old, mean was 57.09±12.93 yrs. old, variable age (F=6. 013, P=0.016<0.05). VC had seen more in rural than urban patients. By statistical analysis, region distribution in these two groups was remarkably different=4.16, P=0.045<0.05, but the urban proportion of patients in different years has no difference (χ2=0.080, P=0.777). Conclusion:The number of cases increased progressively in young age. VC patients were more in rural area than urban. High-risk groups Suggested doing regular physical exam. For long-term genital itching, genital tumor, genital ulcers, and other symptoms, should be alert to the possibility of VC. Preoperative diagnosis should be Colposcopic, biopsy in order to improve the accuracy of earlier diagnosis. Postoperative common complications are wound infection. Follow-up rate is low; It is difficult to say statistically survival rate is 5 years.

No abstract