Search

The mobility status of self and surrounding vehicles provides important information to various tasks in autonomous driving (AD) and intelligent transportation system (ITS). Accordingly, a precise, stable, and robust mobility tracking framework is essential. Compared with self-tracking that relies only on mobility observations from onboard sensors [e.g., global positioning system (GPS), inertial measurement unit (IMU), and camera], cooperative tracking markedly increases the precision and reliability of the mobility information by integrating observations from roadside units (RSUs) and nearby vehicles through vehicle-to-everything (V2X) communications in the Internet of Vehicles (IoV). Nevertheless, cooperative tracking can be quite vulnerable if there are malicious users sending bogus observations in the cooperative network. In this article, we present a malicious user detection framework, which includes two sequential detection algorithms and a secure mobility data exchange and fusion model to detect and remove bogus mobility information and integrate proposed detection algorithms with previous data fusion algorithms, which secures the cooperative mobility tracking in AD, ITS. Simulations validate the effectiveness and robustness of the proposed framework under different types of attacks.

The mobility status of vehicles play a crucial role in most tasks of Autonomous Vehicles (AVs) and Intelligent Transportation System (ITS). To operate securely, a precise, stable and robust mobility tracking system is essential. Compared with self-tracking that relies only on mobility observations from on-board sensors (e.g. Global Positioning System (GPS), Inertial Measurement Unit (IMU) and camera), cooperative tracking increases the precision and reliability of mobility data greatly by integrating observations from road side units and nearby vehicles through V2X communications. Nevertheless, cooperative tracking can be quite vulnerable if there are malicious collaborators sending bogus observations in the network. In this paper, we present a dynamic sequential detection algorithm, dynamic model based mean state detection (DMMSD), to exclude bogus mobility data. Simulations validate the effectiveness and robustness of the proposed algorithm as compared with existing approaches.

Brain-inspired Hyperdimensional (HD) computing is a computing paradigm emulating a neuron’s activity in high-dimensional space. In practice, HD first encodes all data points to high-dimensional vectors, called hypervectors, and then performs the classification task in an efficient way using a well-defined set of operations. In order to provide acceptable classification accuracy, the current HD computing algorithms need to map data points to hypervectors with non-binary elements. However, working with non-binary vectors significantly increases the HD computation cost and the amount of memory requirement for both training and inference. In this paper, we propose BinHD, a novel learning framework which enables HD computing to be trained and tested using binary hypervectors. BinHD encodes data points to binary hypervectors and provides a framework which enables HD to perform the training task with significantly low resources and memory footprint. In inference, BinHD binarizes the model and simplifies the costly Cosine similarity used in existing HD computing algorithms to a hardware-friendly Hamming distance metric. In addition, for the first time, BinHD introduces the concept of learning rate in HD computing which gives an extra knob to the HD in order to control the training efficiency and accuracy. We accordingly design a digital hardware to accelerate BinHD computation. Our evaluations on four practical classification applications show that BinHD in training (inference) can achieve 12.4× and 6.3× (13.8× and 9.9×) energy efficiency and speedup as compared to the state-of-the-art HD computing algorithm while providing the similar classification accuracy.

A new multi-layer self-organizing map (MLSOM) is proposed for unsupervised processing tree-structured data. The MLSOM is an improved self-organizing map for handling structured data. By introducing multiple SOM layers, the MLSOM can overcome the computational speed and visualization problems of SOM for structured data (SOM-SD). Node data in different levels of a tree are processed in different layers of the MLSOM. Root nodes are dedicatedly processed on the top SOM layer enabling the MLSOM a better utilization of SOM map compared with the SOM-SD. Thus, the MLSOM exhibits better data organization, clustering, visualization, and classification results of tree-structured data. Experimental results on three different data sets demonstrate that the proposed MLSOM approach can be more efficient and effective than the SOM-SD.