Driving intelligence tests are critical to the development and deployment of autonomous vehicles. The prevailing approach tests autonomous vehicles in life-like simulations of the naturalistic ...driving environment. However, due to the high dimensionality of the environment and the rareness of safety-critical events, hundreds of millions of miles would be required to demonstrate the safety performance of autonomous vehicles, which is severely inefficient. We discover that sparse but adversarial adjustments to the naturalistic driving environment, resulting in the naturalistic and adversarial driving environment, can significantly reduce the required test miles without loss of evaluation unbiasedness. By training the background vehicles to learn when to execute what adversarial maneuver, the proposed environment becomes an intelligent environment for driving intelligence testing. We demonstrate the effectiveness of the proposed environment in a highway-driving simulation. Comparing with the naturalistic driving environment, the proposed environment can accelerate the evaluation process by multiple orders of magnitude.
The Interface Hypothesis proposes that second language (L2) learners, even at highly proficient levels, often fail to integrate information at the external interfaces where grammar interacts with ...other cognitive systems. While much early L2 work has focused on the syntax–discourse interface or scalar implicatures at the semantics–pragmatics interface, the present article adds to this line of research by exploring another understudied phenomenon at the semantics–pragmatics interface, namely, presuppositions. Furthermore, this study explores both inference computation and suspension via a covered-box picture-selection task. Specifically, this study investigates the interpretation of the presupposition trigger stop and stop under negation. The results from 38 native English speakers and 41 first language (L1) Mandarin Chinese learners of English indicated similar response patterns between native and L2 groups in computing presuppositions but not in suspending presuppositions. That is, L2 learners were less likely to suspend presuppositions than native speakers. This study contributes to a more precise understanding of L2 acquisition at the external interface level, as well as computation and suspension of pragmatic inferences.
Deep neural network (DNN) exhibits state-of-the-art performance in many fields including microstructure recognition where big dataset is used in training. However, DNN trained by conventional methods ...with small datasets commonly shows worse performance than traditional machine learning methods, e.g. shallow neural network and support vector machine. This inherent limitation prevented the wide adoption of DNN in material study because collecting and assembling big dataset in material science is a challenge. In this study, we attempted to predict solidification defects by DNN regression with a small dataset that contains 487 data points. It is found that a pre-trained and fine-tuned DNN shows better generalization performance over shallow neural network, support vector machine, and DNN trained by conventional methods. The trained DNN transforms scattered experimental data points into a map of high accuracy in high-dimensional chemistry and processing parameters space. Though DNN with big datasets is the optimal solution, DNN with small datasets and pre-training can be a reasonable choice when big datasets are unavailable in material study.
Display omitted
•The deep neural network model for predicting solidification cracking susceptibility of stainless steels are developed.•Stacked auto-encoder is used to pre-train deep neural network with a small dataset for optimization of initial weights.•Deep neural network model shows better generalization performance than shallow neural network and support vector machine.
In response to the escalating demands of wireless local area network (WLAN) users for enhanced network transmission quality, this study explores the optimization of a multi-domain communication ...system within WLANs. By applying cross-layer technology, we optimize WLAN routing protocols and address end security issues through re-routing and handshake protocol-based solutions. Empirical analysis reveals that our multi-domain communication system outperforms traditional systems, with a 0.28s reduction in delay, a 3.6% to 4.5% decrease in transmit channel utilization, a 2.7% to 3.3% reduction in receive channel utilization, and a queue response time improvement of 0.05 to 0.072s. This research not only demonstrates the superiority of the WLAN multi-domain communication system and End Secure Interaction Protocol over conventional WLAN systems but also provides a viable approach to significantly enhancing WLAN quality.
There is no doubt that big data are now rapidly expanding in all science and engineering domains. While the potential of these massive data is undoubtedly significant, fully making sense of them ...requires new ways of thinking and novel learning techniques to address the various challenges. In this paper, we present a literature survey of the latest advances in researches on machine learning for big data processing. First, we review the machine learning techniques and highlight some promising learning methods in recent studies, such as representation learning, deep learning, distributed and parallel learning, transfer learning, active learning, and kernel-based learning. Next, we focus on the analysis and discussions about the challenges and possible solutions of machine learning for big data. Following that, we investigate the close connections of machine learning with signal processing techniques for big data processing. Finally, we outline several open issues and research trends.
Mind mapping has always played a role in graphic design as a logical analysis and integration of ideas. By using the method of mind mapping it is possible to develop thinking and reasoning from a ...wider range or different perspectives, thus reorganising relevant factors to break through the original deconstruction to achieve innovative research in graphic design. At the same time, the structural order and visualisation of the mind map is very conducive to logical reasoning and building systems for graphic design. Therefore, in this paper, the application of the mind mapping method in graphic design is investigated with the example of the traditional Chinese local opera, the Qin Qiang. Using the logical tool of mind mapping, a set of graphic design works on the theme of Qin Qiang was completed by clarifying the theme, divergent thinking and determining the direction and method of research to integrate and unify the various forms of Qin Qiang. This paper uses mind mapping to provide a wealth of information and inspirational derivation for the graphic design about the Qin Qiang, allowing the design to visualise effective information in a more comprehensive and concrete way. At the same time, this allows the central idea of the Qin Qiang to be communicated more effectively and accurately in the graphic design than in previous graphic design works.
In general, there are two kinds of cooperative driving strategies, planning-based strategy, and ad hoc negotiation-based strategy, for connected and automated vehicles merging problems. The ...planning-based strategy aims to find the globally optimal passing order, but it is time-consuming when the number of considered vehicles is large. In contrast, the ad hoc negotiation-based strategy runs fast, but it always finds a locally optimal solution. In this paper, we propose a grouping-based cooperative driving strategy to make a good tradeoff between computation time and coordination performance. The key idea is to fix the passing orders for some vehicles whose inter-vehicle headways are small enough (e.g., smaller than the pre-selected grouping threshold). From the viewpoint of optimization, this method reduces the size of the solution space. Then, two analyses are given to explain why this kind of strategy is good and how to determine suitable values for the strategy parameters. A series of simulation experiments are carried out to validate that the proposed strategy can yield a satisfied coordination performance with less computation time and is promising to be used in practice.
The development of bifunctional electrocatalysts with high performance for both hydrogen evolution reaction (HER) and oxygen evolution reaction (OER) with earth-abundant elements is still a challenge ...in electrochemical water splitting technology. Herein, we fabricated a free-standing electrocatalyst in the form of vertically oriented Fe-doped Ni3S2 nanosheet array grown on three-dimensional (3D) Ni foam (Fe-Ni3S2/NF), which presented a high activity and durability for both HER and OER in alkaline media. On the basis of systematic experiments and calculation, the Fe-doping was evidenced to increase the electrochemical surface area, improve the water adsorption ability, and optimize the hydrogen adsorption energy of Ni3S2, which resulted in the enhancement of HER activity on Fe-Ni3S2/NF. Moreover, metal sites of Fe-Ni3S2/NF were proved to play a significant role in the HER process. During the catalysis of OER, the formation of Ni–Fe (oxy)hydroxide was observed on the near-surface section of Fe-Ni3S2/NF, and the introduction of the Fe element dramatically enhanced the OER activity of Ni3S2. The overall water splitting electrolyzer assembled by Fe-Ni3S2/NF exhibited a low cell voltage (1.54 V @ 10 mA cm–2) and a high durability in 1 M KOH. This work demonstrated a promising bifunctional electrocatalyst for water electrolysis in alkaline media with potential application in the future.
Testing and evaluation is a critical step in the development and deployment of connected and automated vehicles (CAVs), and yet there is no systematic framework to generate testing scenario library. ...This study aims to provide a general framework for the testing scenario library generation (TSLG) problem with different operational design domains (ODDs), CAV models, and performance metrics. Given an ODD, the testing scenario library is defined as a critical set of scenarios that can be used for CAV test. Each testing scenario is evaluated by a newly proposed measure, scenario criticality, which can be computed as a combination of maneuver challenge and exposure frequency. To search for critical scenarios, an auxiliary objective function is designed, and a multi-start optimization method along with seed-filling is applied. Theoretical analysis suggests that the proposed framework can obtain accurate evaluation results with much fewer number of tests, if compared with the on-road test method. In part II of the study, three case studies are investigated to demonstrate the proposed method. Reinforcement learning based technique is applied to enhance the searching method under high-dimensional scenarios.
PDF
