Efficient Mean-Shift Tracking Using an Improved Weighted Histogram Scheme

( Dejun Wang ),( Kai Chen ),( Weiping Sun ),( Shengsheng Yu ),( Hanbing Wang ) 한국인터넷정보학회 2014 KSII Transactions on Internet and Information Syst Vol.8 No.6

An improved Mean-Shift (MS) tracker called joint CB-LBWH, which uses a combined weighted-histogram scheme of CBWH (Corrected Background-Weighted Histogram) and LBWH (likelihood-based Background-Weighted Histogram), is presented. Joint CB-LBWH is based on the notion that target representation employs both feature saliency and confidence to form a compound weighted histogram criterion. As the more prominent and confident features mean more significant for tracking the target, the tuned histogram by joint CB-LBWH can reduce the interference of background in target localization effectively. Comparative experimental results show that the proposed joint CB-LBWH scheme can significantly improve the efficiency and robustness of MS tracker when heavy occlusions and complex scenes exist.

EVALUATION OF A VEHICLE DIRECTIONAL CONTROL WITH A FRACTIONAL ORDER PDμ CONTROLLER

Dejun Zhuang,F. Yu,Y. Lin 한국자동차공학회 2008 International journal of automotive technology Vol.9 No.6

In this paper, a novel controller, the fractional order PDμ controller, is designed to improve the performance of the driver-vehicle system. First, fractional calculus and fractional order PIλDμ controller are introduced. A control algorithm for vehicle directional control using the fractional order PDμ controller is then presented. Based on preview-follower theory, the on-line tuning method of the fractional order PDμ controller is designed. By comparing simulated and experimental results, the validity and robustness of the proposed fractional order PDμ controller in the closed loop system are verified. Finally, comprehensive evaluations are performed between the systems with the fractional order PDμ controller and with an integer PD controller. The results demonstrate that the use of the fractional order controller leads to an improvement of the performance of the driver-vehicle system. In this paper, a novel controller, the fractional order PDμ controller, is designed to improve the performance of the driver-vehicle system. First, fractional calculus and fractional order PIλDμ controller are introduced. A control algorithm for vehicle directional control using the fractional order PDμ controller is then presented. Based on preview-follower theory, the on-line tuning method of the fractional order PDμ controller is designed. By comparing simulated and experimental results, the validity and robustness of the proposed fractional order PDμ controller in the closed loop system are verified. Finally, comprehensive evaluations are performed between the systems with the fractional order PDμ controller and with an integer PD controller. The results demonstrate that the use of the fractional order controller leads to an improvement of the performance of the driver-vehicle system.

Development and Validation of a Prognostic Nomogram Based on Clinical and CT Features for Adverse Outcome Prediction in Patients with COVID-19

Zheng Yingyan,Xiao Anling,Yu Xiangrong,Zhao Yajing,Lu Yiping,Li Xuanxuan,Mei Nan,She Dejun,Wang Dongdong,Geng Daoying,Yin Bo 대한영상의학회 2020 Korean Journal of Radiology Vol.21 No.8

Objective: The purpose of our study was to investigate the predictive abilities of clinical and computed tomography (CT) features for outcome prediction in patients with coronavirus disease (COVID-19). Materials and Methods: The clinical and CT data of 238 patients with laboratory-confirmed COVID-19 in our two hospitals were retrospectively analyzed. One hundred sixty-six patients (103 males; age 43.8 ± 12.3 years) were allocated in the training cohort and 72 patients (38 males; age 45.1 ± 15.8 years) from another independent hospital were assigned in the validation cohort. The primary composite endpoint was admission to an intensive care unit, use of mechanical ventilation, or death. Univariate and multivariate Cox proportional hazard analyses were performed to identify independent predictors. A nomogram was constructed based on the combination of clinical and CT features, and its prognostic performance was externally tested in the validation group. The predictive value of the combined model was compared with models built on the clinical and radiological attributes alone. Results: Overall, 35 infected patients (21.1%) in the training cohort and 10 patients (13.9%) in the validation cohort experienced adverse outcomes. Underlying comorbidity (hazard ratio [HR], 3.35; 95% confidence interval [CI], 1.67–6.71; p < 0.001), lymphocyte count (HR, 0.12; 95% CI, 0.04–0.38; p < 0.001) and crazy-paving sign (HR, 2.15; 95% CI, 1.03–4.48; p = 0.042) were the independent factors. The nomogram displayed a concordance index (C-index) of 0.82 (95% CI, 0.76–0.88), and its prognostic value was confirmed in the validation cohort with a C-index of 0.89 (95% CI, 0.82–0.96). The combined model provided the best performance over the clinical or radiological model (p < 0.050). Conclusion: Underlying comorbidity, lymphocyte count and crazy-paving sign were independent predictors of adverse outcomes. The prognostic nomogram based on the combination of clinical and CT features could be a useful tool for predicting adverse outcomes of patients with COVID-19.

Highly AC Voltage Fluctuation-Resistant LED Driver with Sinusoid-Like Reference

Ning Ning,Zhenxiao Tong,Dejun Yu,Shuangyi Wu,Wenbin Chen,Chunyi Feng 전력전자학회 2014 JOURNAL OF POWER ELECTRONICS Vol.14 No.2

A novel converter-free AC LED driver that is highly resistant to the fluctuation of AC voltage is proposed in this study. By removing large passive components, such as the bulky capacitor and the large-value inductor, the integration of the driver circuit is enhanced while the driving current remains stable. The proposed circuit provides LED lamps with a driving current that can follow the sinusoid waveform to obtain a very high power factor (PF) and low total harmonic distortion (THD). The LED input current produced by this driving current is insensitive to fluctuations in the AC voltage. Users will thus not feel that LED lamps are flashing during the fluctuation. Experiment results indicate that the proposed system can obtain PF of 0.999 and THD as low as 3.3% for a five-string 6 W LED load under 220 V at 50 Hz.

Mixture copulas with discrete margins and their application to imbalanced data

Liu Yujian,Xie Dejun,Edwards David A.,Yu Siyi 한국통계학회 2023 Journal of the Korean Statistical Society Vol.52 No.4

This article introduces the approach of using Bayesian sampling to estimate the mixture copula with discrete margins, we further apply our models to solve the class imbalanced problems in data science by oversampling. The methodology makes it possible to learn and sample from the data set with the discrete and continuous features exists simultaneously. On the other hand, the discreetness of factors in a data set are not naturally considered for the classic SMOTE algorithm and classic random oversampling is simply performed by generating the already existing points, which do not give any new information to the classifiers and is easy to overfit. Copula methods enable us to generate new points with the correlation structure memorized by learning from the training set. Hence, the overfitting problems are reduced. Experiments with synthetic and real data are done in the article following the introduction of the methodology. The outcomes shows the validity of the approach when compared with the benchmark methods.

The enhancement of oxygen sensitivity of ZnO macropore film by functionalizing with azo pigment

Peng, Liang,Zhai, Jiali,Wang, Dejun,Zhang, Yu,Zhao, Qidong,Wang, Ping,Pang, Shan,Fan, Zhiyong,Xie, Tengfeng Korean Society of Photoscience 2009 Photochemical & photobiological sciences Vol.8 No.6

Azo-ZnO hybrid films were prepared by functionalizing the ZnO macropore films with azo pigment (1,1'-(biphenyl-4,4'-diylbis(diazene-2,1-diyl))dinaphthalen-2-ol). Scanning electronic microscopy, current-voltage, UV-Vis absorption spectroscopy and Kelvin probe were used to characterize these films. The oxygen sensing characteristics of hybrid films and pure ZnO film were measured under the irradiation of UV light. The results show that the sensitivity of hybrid film is about 500 times higher than that of pure ZnO film. The high sensitivity to oxygen of hybrid films is mainly attributed to the increasing of the photo-generated electron concentration. Enhanced photo-induced charge separation after functionalization is confirmed by the pattern of transient photovoltage. Our results demonstrate that the functionalization with azo pigment is a promising approach to enhance the oxygen sensitivity of ZnO under the irradiation of UV light.