Recognizing and classifying traffic signs is a challenging task that can significantly improve road safety. Deep neural networks have achieved impressive results in various applications, including object identification and automatic recognition of traffic signs. These deep neural network-based traffic sign recognition systems may have limitations in practical applications due to their computational requirements and resource consumption. To address this issue, this paper presents a lightweight neural network for traffic sign recognition that achieves high accuracy and precision with fewer trainable parameters. The proposed model is trained on the German Traffic Sign Recognition Benchmark (GTSRB) and Belgium Traffic Sign (BelgiumTS) datasets. Experimental results demonstrate that the proposed model has achieved 98.41% and 92.06% accuracy on GTSRB and BelgiumTS datasets, respectively, outperforming several state-of-the-art models such as GoogleNet, AlexNet, VGG16, VGG19, MobileNetv2, and ResNetv2. Furthermore, the proposed model outperformed these methods by margins ranging from 0.1 to 4.20 percentage point on the GTSRB dataset and by margins ranging from 9.33 to 33.18 percentage point on the BelgiumTS dataset.

As wireless and mobile devices are prevalent and resource-rich, users can frequently query point-of-interests and enjoy diverse location-based services (LBSs) in infrastructure-based wireless networks. However, users often trade their location privacy with services by sharing their location information with an LBS server, without knowing that the server can fully be trusted. In this article, we propose a sky caching-aided spatial querying scheme with the support of a flying drone. The basic idea is that both the user and its drone collaboratively generate a set of dummy locations to hide the current location of the user from the server. We also propose cache admission control techniques to efficiently cache the queried results to minimize the number of duplicated cached copies. The location privacy is analyzed and measured in terms of the location obfuscation and the size of the convex hull area that consists of dummy locations resided within the cloaking areas of user and drone. We conduct extensive simulation experiments using the OMNeT++ for performance evaluation and comparison. The simulation results show that the proposed approach can reduce the number of queries sent to the server, extend the cloaking area, and improve the location privacy of users significantly.

Reconstruction of neuron anatomy structure is a challenging and important task in neuroscience. However, few algorithms can automatically reconstruct the full structure well without manual assistance, making it essential to develop new methods for this task.