For urban traffic, traffic accidents are the most direct and serious risk to people’s lives, and rapid recognition and warning of traffic accidents is an important remedy to reduce their harmful ...effects. However, research scholars are often confronted with the problem of scarce and difficult-to-collect accident data resources for traffic accident scenarios. Therefore, in this paper, a traffic data generation model based on Generative Adversarial Networks (GAN) is developed. To make GAN applicable to non-graphical data, we improve the generator network structure of the model and used the generated model to resample the original data to obtain new traffic accident data. By constructing an adversarial neural network model, we generate a large number of data samples that are similar to the original traffic accident data. Results of the statistical test indicate that the generated samples are not significantly different from the original data. Furthermore, the experiments of traffic accident recognition with several representative classifiers demonstrate that the augmented data can effectively enhance the performance of accident recognition, with a maximum increase in accuracy of 3.05% and a maximum decrease in the false positive rate of 2.95%. Experimental results verify that the proposed method can provide reliable mass data support for the recognition of traffic accidents and road traffic safety.
Revealing the general status quo of teacher curriculum leadership has great theoretical, policy, and practical significance. However, large-scale empirical investigations in this area are rare, and ...there is even less attention to the current situation of rural teacher curriculum leadership. Based on the survey of 2,966 rural teachers in 20 provinces of China, this paper presented the status quo of rural teacher curriculum leadership and examined influencing factors through multiple linear regression analysis. It was found that curriculum leadership of rural teachers was at a low level with backward leadership views, lack of practical ability, and low sense of identity. Regression analysis demonstrated that individual field factors had a significant impact on teachers' curriculum leadership. Specifically, the higher the teachers' leadership willingness, trust in others, and self-efficacy, the higher the curriculum leadership. The school field was also an important influential aspect. In particular, the formation of a common vision and teacher community by the school and the appropriate empowerment of the principal had a significant positive impact on the curriculum leadership of rural teachers. Based on these key findings, several improvement suggestions are put forward at the end, which can be used as references for other countries to develop improvement plans on rural teacher curriculum leadership.
Malignant mesothelioma that originates from mediastinal (MMM) is a rare form of malignant pleural mesothelioma (MPM). The prognosis of advanced stage MPM was poor, and the traditional treatment was ...chemotherapy. Here, we present a patient with MMM that was treated with anlotinib, a multitargeted tyrosine kinase inhibitor (TKI) who had a 24-month progression-free survival (PFS). Further review of the literature showed that, despite some explorations of applying small-molecule multitargeted TKIs in the treatment of MPM, until today, no large series had a positive result. Anlotinib had been approved by the China Food and Drug Administration on treating non-small cell lung cancer, soft tissue sarcoma, renal cell carcinoma, and medullary thyroid cancer. We assumed that the ability of anlotinib to target more tyrosine kinase receptors than most of other TKIs could contribute to the long duration of PFS in this case, but further study is needed to further validate the efficacy of anlotinib in treatment of MPM.
Feature selection is one of the core issues in designing pattern recognition systems and has attracted considerable attention in the literature. Most of the feature selection methods in the ...literature only handle relevance and redundancy analysis from the point of view of the whole class, which neglects the relation of features and the separate classes. In this paper, we propose a novel feature selection framework to explicitly handle the relevance and redundancy analysis for each class label. Then we propose two simple and effective feature selection algorithms based on this framework and Kullback–Leibler divergence. An empirical study is conducted to evaluate the efficiency and effectiveness of our algorithms comparing with five representative feature selection algorithms. Empirical results show that our proposed algorithms are efficient and outperform the selected algorithms in most cases, and show the superiority of our proposed feature selection framework.
To address the performance deterioration of ZIF-8 for the adsorption of copper ions caused by powder volume pressure and particle aggregation, we employed multilayer graphene oxide (MGO) as a support ...to prepare composite adsorbents (MGO@ZIF-8) by using the in situ growth of ZIF-8 on MGO. Due to a good interfacial compatibility and affinity between ZIF-8 and graphene nanosheets, the MGO@ZIF-8 was successfully prepared. The optimal Cu2+ adsorption conditions of MGO@ZIF-8 were obtained through single factor experiments and orthogonal experiments. Surprisingly, the Cu2+ adsorption capacity was significantly improved by the integration of MGO and ZIF-8, and the maximum Cu2+ adsorption capacity of MGO@ZIF-8 reached 431.63 mg/g under the optimal adsorption conditions. Furthermore, the kinetic fitting and isotherm curve fitting confirmed that the adsorption law of Cu2+ by MGO@ZIF-8 was the pseudo-second-order kinetic model and the Langmuir isotherm model, which indicated that the process of Cu2+ adsorption was monolayer chemisorption. This work provides a new approach for designing and constructing ZIF-8 composites, and also offers an efficient means for the removal of heavy metals.
In recent years, the automated driving system has been known to be one of the most popular research topics of artificial intelligence (AI) and intelligent transportation system (ITS). The journey ...experience on automated vehicles and the intelligent automated driving system could be improved by individualization driving understanding. Although previous studies have proposed methods for driving styles understanding, the individualization driving classification has not been addressed thoroughly. Therefore, in this study, a supervised method is proposed to understand driving behavioral structure and the latent driving styles by incorporating the prior knowledge. Firstly, a novel method is established for driving behavioral encoding and raw driving data mining. Then, the Labeled Latent Dirichlet Allocation (LLDA) is proposed to understand the latent driving styles from individual driving with driving behaviors. Finally, the Safety Pilot Model Deployment (SPMD) data are used to validate the performance of the proposed model. Experimental results show that the proposed model uncovers latent driving styles effectively and shows good agreement to real situations, which provides theoretical guidance on driving behavior recognition for better individual experience on automated driving vehicles.
The ability to identify driving risk status plays an important role for reducing the number of traffic accidents. Bayesian networks (BNs) was applied to extract the main factors that significantly ...influence driving risk status. Five factors (driver state, sex, experience, vehicle state, and environment) were selected and considered to significantly influence driving risk status based on driving simulation experiments. Next, a logistic regression algorithm was employed to establish the driving risk status prediction model, and the receiver operating characteristic curve was adopted to evaluate the performance of the prediction model. The area under the curve was 0.903, indicating that the prediction model was both adaptable and practical. In addition, this study also compared three different models, namely modelling directly, modelling based on expert experience, and modelling based on BN. The results indicated that modelling based on BN outperformed all other methods. The conclusions could provide reference evidence for driver training and the development of danger warning products to significantly contribute to traffic safety.
The ability to identify hazardous traffic events is already considered as one of the most effective solutions for reducing the occurrence of crashes. Only certain particular hazardous traffic events ...have been studied in previous studies, which were mainly based on dedicated video stream data and GPS data. The objective of this study is twofold: (1) the Markov blanket (MB) algorithm is employed to extract the main factors associated with hazardous traffic events; (2) a model is developed to identify hazardous traffic event using driving characteristics, vehicle trajectory, and vehicle position data. Twenty-two licensed drivers were recruited to carry out a natural driving experiment in Wuhan, China, and multi-sensor information data were collected for different types of traffic events. The results indicated that a vehicle's speed, the standard deviation of speed, the standard deviation of skin conductance, the standard deviation of brake pressure, turn signal, the acceleration of steering, the standard deviation of acceleration, and the acceleration in Z (G) have significant influences on hazardous traffic events. The sequential minimal optimization (SMO) algorithm was adopted to build the identification model, and the accuracy of prediction was higher than 86%. Moreover, compared with other detection algorithms, the MB-SMO algorithm was ranked best in terms of the prediction accuracy. The conclusions can provide reference evidence for the development of dangerous situation warning products and the design of intelligent vehicles.
Abstract OBJECTIVE: It is important to analyze and track Epidermal Growth Factor Receptor ( EGFR ) mutation status for predicting efficacy and monitoring resistance throughout EGFR-tyrosine kinase ...inhibitors (TKIs) treatment in non-small cell lung cancer (NSCLC) patients. The objective of this study was to determine the feasibility and predictive utility of EGFR mutation detection in peripheral blood. METHODS: Plasma, serum and tumor tissue samples from 164 NSCLC patients were assessed for EGFR mutations using Amplification Refractory Mutation System (ARMS). RESULTS: Compared with matched tumor tissue, the concordance rate of EGFR mutation status in plasma and serum was 73.6% and 66.3%, respectively. ARMS for EGFR mutation detection in blood showed low sensitivity (plasma, 48.2%; serum, 39.6%) but high specificity (plasma, 95.4%; serum, 95.5%). Treated with EGFR-TKIs, patients with EGFR mutations in blood had significantly higher objective response rate (ORR) and insignificantly longer progression-free survival (PFS) than those without mutations (ORR: plasma, 68.4% versus 38.9%, P = 0.037; serum, 75.0% versus 39.5%, P = 0.017; PFS: plasma, 7.9 months versus 6.1 months, P = 0.953; serum, 7.9 months versus 5.7 months, P = 0.889). In patients with mutant tumors, those without EGFR mutations in blood tended to have prolonged PFS than patients with mutations (19.7 months versus 11.0 months, P = 0.102). CONCLUSIONS: EGFR mutations detected in blood may be highly predictive of identical mutations in corresponding tumor, as well as showing correlations with tumor response and survival benefit from EGFR-TKIs. Therefore, blood for EGFR mutation detection may allow NSCLC patients with unavailable or insufficient tumor tissue the opportunity to benefit from personalized treatment. However, due to the high false negative rate in blood samples, analysis for EGFR mutations in tumor tissue remains the gold standard.