Connected and Autonomous Vehicle (CAV)-related initiatives have become some of the fastest expanding in recent years, and have started to affect the daily lives of people. More and more companies and research organizations have announced their initiatives, and some have started CAV road trials. Governments around the world have also introduced policies to support and accelerate the deployments of CAVs. Along these, issues such as CAV cyber security have become predominant, forming an essential part of the complications of CAV deployment. There is, however, no universally agreed upon or recognized framework for CAV cyber security. In this paper, following the UK CAV cyber security principles, we propose a UML (Unified Modeling Language)-based CAV cyber security framework, and based on which we classify the potential vulnerabilities of CAV systems. With this framework, a new CAV communication cyber-attack data set (named CAV-KDD) is generated based on the widely tested benchmark data set KDD99. This data set focuses on the communication-based CAV cyber-attacks. Two classification models are developed, using two machine learning algorithms, namely Decision Tree and Naive Bayes, based on the CAV-KDD training data set. The accuracy, precision and runtime of these two models when identifying each type of communication-based attacks are compared and analysed. It is found that the Decision Tree model requires a shorter runtime, and is more appropriate for CAV communication attack detection.

Accurate and rapid response in complex driving scenarios is a challenging problem in autonomous driving. If a target is detected, the vehicle will not be able to react in time, resulting in fatal safety accidents. Therefore, the application of driver assistance systems requires a model that can accurately detect targets in complex scenes and respond quickly. In this paper, a lightweight feature extraction model, ShuffDet, is proposed to replace the CSPDark53 model used by YOLOX by improving the YOLOX algorithm. At the same time, an attention mechanism is introduced into the path aggregation feature pyramid network (PAFPN) to make the network focus more on important information in the network, thereby improving the accuracy of the model. This model, which combines two methods, is called ShuffYOLOX, and it can improve the accuracy of the model while keeping it lightweight. The performance of the ShuffYOLOX model on the KITTI dataset is tested in this paper, and the experimental results show that compared to the original network, the mean average precision (mAP) of the ShuffYOLOX model on the KITTI dataset reaches 92.20%. In addition, the number of parameters of the ShuffYOLOX model is reduced by 34.57%, the Gflops are reduced by 42.19%, and the FPS is increased by 65%. Therefore, the ShuffYOLOX model is very suitable for autonomous driving applications.

Tiny defect detection is a knotty task in industrial electronics production. Existing traditional and deep learning methods have achieved satisfactory performance, however, they still face challenges in accuracy, generalization ability, and computational complexity. Therefore, this study designs a tiny defect detection-based you only look once (TDD-YOLO) model and proposes an innovative compression training strategy to train on low-resolution images and test on original images. First, a four-ME layers structure is adopted to the backbone network, to integrate more underlying information and extract effective features. In addition, a miniature detection head is incorporated into the head network to improve the accuracy and generalization performance of you only look once (YOLO). Meanwhile, TDD-YOLO introduces wise intersection over union (W-IoU) to reevaluate the loss of bounding box regression (BBR) and reduce false negatives by fitting the model well to regular quality anchor boxes. Finally, an image compression method at different ratios is applied in the proposed compression training strategy, to reduce computational complexity and surprisingly further improve accuracy. Comprehensive experiments on several variable compressed datasets which are based on a public printed circuit board (PCB) defect dataset validate the effectiveness of our theoretical approach and illustrate that our proposed method outperforms state-of-the-art methods.

CAV (connected and autonomous vehicle) is a crucial part of intelligent transportation systems. CAVs utilize both sensors and communication components to make driving decisions. A large number of companies, research organizations, and governments have researched extensively on the development of CAVs. The increasing number of autonomous and connected functions however means that CAVs are exposed to more cyber security vulnerabilities. Unlike computer cyber security attacks, cyber attacks to CAVs could lead to not only information leakage but also physical damage. According to the UK CAV Cyber Security Principles, preventing CAVs from cyber security attacks need to be considered at the beginning of CAV development. In this paper, a large set of potential cyber attacks are collected and investigated from the aspects of target assets, risks, and consequences. Severity of each type of attacks is then analysed based on clearly defined new set of criteria. The levels of severity for the attacks can be categorized as critical, important, moderate, and minor. Mitigation methods including prevention, reduction, transference, acceptance, and contingency are then suggested. It is found that remote control, fake vision on cameras, hidden objects to LiDAR and Radar, spoofing attack to GNSS, and fake identity in cloud authority are the most dangerous and of the highest vulnerabilities in CAV cyber security.

Data are a strategic resource for industrial production, and an efficient data-mining process will increase productivity. However, there exist many missing values in data collected in real life due to various problems. Because the missing data may reduce productivity, missing value imputation is an important research topic in data mining. At present, most studies mainly focus on imputation methods for continuous missing data, while a few concentrate on discrete missing data. In this paper, a discrete missing value imputation method based on a multilayer perceptron (MLP) is proposed, which employs a momentum gradient descent algorithm, and some prefilling strategies are utilized to improve the convergence speed of the MLP. To verify the effectiveness of the method, experiments are conducted to compare the classification accuracy with eight common imputation methods, such as the mode, random, hot-deck, KNN, autoencoder, and MLP, under different missing mechanisms and missing proportions. Experimental results verify that the improved MLP model (IMLP) can effectively impute discrete missing values in most situations under three missing patterns.

With the rapid development of the Internet of Things (IoT), the curse of dimensionality becomes increasingly common. Feature selection (FS) is to eliminate irrelevant and redundant features in the datasets. Particle swarm optimization (PSO) is an efficient metaheuristic algorithm that has been successfully applied to obtain the optimal feature subset with essential information in an acceptable time. However, it is easy to fall into the local optima when dealing with high-dimensional datasets due to constant parameter values and insufficient population diversity. In the paper, an FS method is proposed by utilizing adaptive PSO with leadership learning (APSOLL). An adaptive updating strategy for parameters is used to replace the constant parameters, and the leadership learning strategy is utilized to provide valid population diversity. Experimental results on 10 UCI datasets show that APSOLL has better exploration and exploitation capabilities through comparison with PSO, grey wolf optimizer (GWO), Harris hawks optimization (HHO), flower pollination algorithm (FPA), salp swarm algorithm (SSA), linear PSO (LPSO), and hybrid PSO and differential evolution (HPSO-DE). Moreover, less than 8% of features in the original datasets are selected on average, and the feature subsets are more effective in most cases compared to those generated by 6 traditional FS methods (analysis of variance (ANOVA), Chi-Squared (CHI2), Pearson, Spearman, Kendall, and Mutual Information (MI)).