Feature selection plays a very significant role for the success of pattern recognition and data mining. Based on maximal relevance minimal redundancy (mRMR) method, combined with feature subset, this paper proposes an improved (ImRMR) method based subset. In ImRMR, Pearson correlation coefficient mutual information are first used to measure single sample category, factor is introduced adjust weights two measurement criteria. And equal grouping exploited generate candidate subsets according...

This study explores the mediating effects of repetitive negative thinking in relationship between perfectionism and adolescent sleep quality. A sample 1664 Chinese adolescents with a mean age 15.0 years was recruited, they completed four measures relating to perfectionism, quality, worry, rumination. The results showed that maladaptive positively correlated poor quality adolescents, which mediated by both worry However, adaptive not significantly associated this suppressed rumination (but...

With the advent of big data era and rapid improvement raw scale, feature selection is basic critical technologies for mining. However, in most studies on methods before, mainly directed to treat single or overall subset, while influence correlation redundancy features subset classification results ignored. In this paper, combination grouping factor analysis (FA), a hybrid method based subsets generation through (FAFS_HFS) proposed. Firstly, generate maximum load (maximum explanatory power)...

An energy management strategy based on dynamic programming for a plug-in serial-parallel hybrid electric bus is proposed. The sets of comprehensive cost function, five control variables and mesh accuracies are illustrated. Then the fuel economy discussed, followed by sensitivity analysis this different lengths driving cycle input dissimilar variable settings. It can be concluded that scaling length battery capacity have little effect laws output while optimum settings should combine exact...

Humanlike automated driving (AD) strategies which are inspired by drivers' cognition ways may show advantages in dealing with complicated scenarios. However, many humanlike AD just mimic behaviors or some specific characteristic. Learning algorithms powerful technics to realize these strategies, but the architectures learning-based too simple no detailed foundations. Therefore, we mean summarize characteristics and design a comprehensive well-founded architecture for solutions. We review...

Abstract Trajectory prediction of the ego vehicle is necessary for cooperation driving intelligent vehicles and drivers. Methods based on deep learning can fit complex functions, but they usually focus vehicles' behavioral characteristics. However, trajectories are closely related to cognition results Therefore, drivers' cognitive characteristics, a network model designed predict trajectories. Specifically, in perception stage, featured grids used that driver's view encode perceptual...

The estimation of state charge (SOC) for power battery packs is significant a hybrid electric vehicle with providing data supports the efficient and fine energy managements. In this brief, extended Kalman filter (EKF), multi-model (MMEKF) adaptive fading (AFEKF) are used to estimate SOC respectively, then they combined switching strategy match their own features that in different working areas. error below 2.5 percent. And verified have good initialization stabilities convergence behaviors.

Energy management strategy is vital for a plug-in hybrid electric vehicle and in this paper, based on stochastic model predictive control proposed. Firstly, Markov Chain Monte Carlo Simulation used to predict velocity sequences the 10-second horizon followed by post-processing like average filtering, quadratic fitting, etc. which meant moderate fluctuations of results. The RMSE controlled around 2.4357 Km/h. Moreover, dynamic programming adopted construct benchmark also act as rolling...

We explored the factor structure and psychometric properties of Insomnia Severity Index (ISI) using 3 samples totaling 2,066 Mainland Chinese undergraduates. All participants completed ISI Sample 2 other related measures. Their responses were processed exploratory analysis (EFA), confirmatory (CFA), multiple group analyses. The EFA results revealed a 2-factor structure, whereas CFA supported 3-factor solution, latter which was further confirmed by version had satisfactory Cronbach's alpha...

Automated driving (AD) aims at human-level intelligence and good cooperation with humans. Therefore, it is necessary to consider the characteristics of human behavior intelligence. Indeed, researchers have attempted develop human-like AD strategies. However, there no quantitative definition Meanwhile, existing strategies cannot yet be applied in extensive scenarios well. In this paper, we look for inspiration from propose a general solution. Specifically, first summarize classify driver...

The abbreviated version of Penn State Worry Questionnaire (PSWQ-A) has been widely used to assess worry. However, its measurement invariance not yet warranted. With a cross-sectional and longitudinal sample Chinese adolescents (N1 = 1,329, N2 408), this study examined age, gender, PSWQ-A. Results supported strict invariance, including configural, metric, scalar, error level, across gender age in the sample; was also sample. This suggests application PSWQ-A measuring adolescent worry basis...

The interactions between driver, vehicle and environment generate vehicle's behaviors, the of groups shape traffic modes. Therefore, conditionally or fully automated driving technologies should be developed tested in driver-vehicle-environment (DVE) system rather than being individually. To build DVE dynamics, firstly, we propose an architecture to cope with complicated vehicles (AVs) mixed situations. Then summarize driver behavior models compare differences intelligence human vehicle....

As software running on computer, mental activities of human brain may entry a dead loop too. Computer-brain interfaces give computers special channels to detect and interfere interrupt unwanted thoughts which induce unpleasant intrusive uncontrollable worry. In the present study, we intend develop noninterference non-wake-up solution those extend transition from waking sleeping. When an appropriate stimulus serial is given by this embedded computer according subject state, it possible that...

The mixed-logit model is a flexible tool in transportation choice analysis, which provides valuable insights into inter and intra-individual behavioural heterogeneity. However, applications of models are limited by the high computational data requirements for estimation. When estimating on small samples, Bayesian estimation approach becomes vulnerable to over under-fitting. This problematic investigating behaviour specific population sub-groups or market segments with low availability....

In recent years, with the characteristics of nonforgery, nontampering and traceability, blockchain has changed way human social value transmission a new trust system, been deeply integrated industry applications. Due to imbalance security privacy protection between nodes, however, stability system are damaged in process integration. The have attracted much more attention. From perspective security, this paper summarizes problems from platform architecture, analyses issues such as data...

Tractor-trailer systems (TTSs) have been adopted in the logistics and transportation domain owing to their vast cargo capacity. Trajectory planning plays an important role autonomous TTS driving, where existing predominant planners are usually based on graph search sampling. However, such prevailing face difficulties of poor real-time performance, due unique underactuated characteristic complex kinematic constraints TTS. Based motion characteristics its application environment, this paper...