Dangerous driving, e.g., using mobile phone while driving, can result in serious traffic problem and threaten to safety. To efficiently alleviate such problem, in this paper, we design an intelligent monitoring system to detect the dangerous behavior while driving. The monitoring system is combined by a designed target detection algorithm, camera, terminal server and voice reminder. An efficiently deep learning model, namely Mobilenet combined with single shot multi-box detector (Mobilenet-SSD), was applied to identify the behavior of driver. To evaluate the performance of proposed system, a dangerous driving dataset,consisting of 6796 images, was constructed. The experimental results show that the proposed system can achieve the accuracy of 99%, and could be used for real-time monitoring of the drivers’ status.

The transferability of adversarial examples has been proven to be a potent tool for successful attacks on target models, even in challenging black-box environments. However, the majority of current research focuses on non-targeted attacks, making it arduous to enhance the transferability of targeted attacks using traditional methods. This paper identifies a crucial issue in existing gradient iteration algorithms that generate adversarial perturbations in a fixed manner. These perturbations have a detrimental impact on subsequent gradient computations, resulting in instability of the update direction after momentum accumulation. Consequently, the transferability of adversarial examples is negatively affected. To overcome this issue, we propose an approach called Adversarial Perturbation Transform (APT) that introduces a transformation to the perturbations at each iteration. APT randomly samples clean patches from the original image and replaces the corresponding patches in the iterative output image. This transformed image is then used to compute the next momentum. In addition, APT could seamlessly integrate with other iterative gradient-based algorithms, incurring minimal additional computational overhead. Experimental results demonstrate that APT significantly enhances the transferability of targeted attacks when combined with traditional methods. Our approach achieves this improvement while maintaining computational efficiency.

A series of porous carbon nanofibres, with network-like structures and high surface area, were prepared using low-cost renewable bacterial cellulose, fabricated from the raw materials of coconut. The performances of these coconut-based bacterial cellulose carbon nanofibres (BCCNFs) strongly rely on their porous network-like graphitised structure. The carbonisation temperatures affect both the graphitic degree of BCCNFs and the uniformity of their porous structure. The specific capacitance of BCCNFs at 900 °C drops off due to the decrease in the uniformity of their porous structure. The prepared BCCNFs materials exhibited high electrochemical energy storage performance (with its specific capacitance in 6 M KOH solution being 289 F g⁻¹) and cycling excellent stability (after 5000 charge–discharge cycles, the material still maintained more than 80% of its initial capacitance), making them potential for the practical application of supercapacitors.

The characteristic changes and the complete relaxation process of V₂O₅–P₂O₅ oxide glass are studied by dynamic thermal-mechanical analysis and differential scanning calorimetry.