Autonomous vehicles (AVs) represent an exciting frontier in transportation, promising increased safety and efficiency on the roads. However, like any technological advancement, they are not immune to accidents. Understanding the severity of accidents involving AVs is crucial for enhancing their reliability and ensuring public trust in this transformative technology. To address this challenge, our study has employed cutting-edge natural language processing techniques combined with machine learning to predict the severity of accidents involving AVs. Our study has contributed significantly by creating a novel dataset derived from post-disengagement accident reports, covering the years 2019-2022. This dataset comprises detailed descriptions of accidents, sensor information, and other critical parameters. Moreover, we have introduced a novel approach called Multi-Distance Synthetic Technique (MDST) to balance the imbalanced nature of our dataset, which included only 334 samples due to the rarity of such accident data. Utilizing MDST for data balancing, we aimed to enhance the robustness of our analysis. Additionally, we employed Recursive Feature Selection (RFS) to extract a valuable feature set that was crucial in predicting accident severity. Leveraging this selected feature set, we trained an ensemble model, which remarkably outperformed expectations, achieving an impressive accuracy score of 0.92.

Ancient stelae are considered important historical sources. However, it is a challenge to recognize the inscriptions carved on stelae that have rough surfaces due to prolonged weathering. In this paper, we propose a deep learning-based method to extract engraved regions from the 3D scanned mesh of a stela. First, the uneven distribution of vertices in the mesh is transformed using a mesh subdivision method such that the vertices in the mesh are uniformly distributed. Then, surface features (depth, concave features, and local surface features) are extracted from the subdivided mesh. The depth represents the basic shape of the mesh and is obtained from the aligned mesh. The concave features effectively represent concave regions by using a Frangi filter, and the local surface features have the spin image technique applied to describe the fine shapes of neighboring vertices relative to a vertex. The mesh and the surface features are rasterized into feature images, and engraved regions are segmented from the feature images by using a FC-DenseNet. Our experiments confirm that the proposed method effectively extracts engraved regions of the inscriptions from the rough surface of a stela and it shows robustness to noisy and extremely abraded characters. The proposed method outperformed the second-best method, obtaining an F1 score, IoU, and SIRI of approximately 2.95%, 3.65%, and 7.53%, respectively.

Archaeological steles having a rough surface due to long periods of weathering make recognizing the inscription difficult. In this paper, we propose a machine learning-based method to extract reliefs for the inscription from a rough stele surface. Relief candidate segments are initially obtained by using a curvature-based method, which include not only actual reliefs but also noises such as dents and scratches. Then, relief segments are selected using a support vector machine classifier that is trained with various features extracted from relief candidate segments. While conventional methods using a single geometric feature easily fail to detect reliefs from the rough surface, the proposed method utilizes 79-dimensional features consisting of appearance-based, cross section-based, and local extrema-based characteristics of each candidate segment to determine whether the segment is relief or not. Using the proposed method, the inscription of the stele Musul-ojakbi made during the Silla Dynasty AD578 were completely recognized. The experimental results demonstrate that the proposed method accurately extracts reliefs and achieves the highest performance on the rough stele data. The performance of the proposed method is about 8.95% and 10.4% higher than the best of the conventional methods in terms of the F1-score and the SIRI, respectively.

The integration of reliable and accurate sensors is critical to the performance and safety of autonomous vehicles in the automotive industry. Sensors like LiDAR, cameras, and radar are essential to ensure proper vehicle functioning and perception capabilities. Failure or misalignment of any of these sensors degrades system performance and poses significant safety risks. In particular, radar is suitable for applications such as adaptive cruise control, collision avoidance, and lane change assistance systems and plays a crucial role in autonomous vehicle systems. Misalignments in radar, vertical or horizontal, can lead to severe performance degradation in these applications. This survey paper comprehensively analyzes radar misalignment issues, reviewing detection techniques that address various types of offset. Through a comparative evaluation of existing methods, this work aims to identify current gaps and provide valuable information to researchers to improve the reliability and accuracy of radar systems in autonomous vehicles.

In this paper, we propose a new multiple-input multiple-output (MIMO) transmission scheme, called parallel complex quadrature spatial modulation (PCQSM). The proposed technique is based on the complex quadrature spatial modulation (CQSM) to further increase the spectral efficiency of the communication system. CQSM transmits two different complex symbols at each channel use. In contrast with CQSM, the new transmission scheme splits the transmit antennas into groups, and modulates the two signal symbols using the conventional CQSM before transmission. Based on the selected modulation order and the number of possible groups that can be realized, the incoming bits modulate the two signal symbols and the indices of the transmit antennas in each group. We demonstrated that while the complexity and performance of the proposed scheme is the same as that of CQSM, the number of required transmit antennas is significantly reduced. The proposed PCQSM achieves such a benefit without requiring any additional radio frequency (RF) chains. The results obtained from Monte Carlo simulation showed that at a Bit Error Rate (BER) of ${10}^{-4}$, the performance of the PCQSM with two antenna groups closely matches that of CQSM, and outperformed quadrature spatial modulation (QSM) and parallel quadrature spatial modulation (PQSM) by over $0.7$ dB. As the number of antenna groups increased to 4, the BER performance of PCQSM with reduced number of transmit antenna and modulation order matches that of QSM. The BER of the proposed scheme using maximum likelihood (ML) receiver is also analyzed theoretically and compared with the BER obtained via simulations.

In spatial modulation (SM), a single signal symbol is transmitted from a given physical antenna, where both the signal symbol and the antenna index carry information. SM with multiple active antennas (MA-SM) transmits several signal symbols from a combination of antennas at each channel use, thereby increasing the spectral efficiency. MA-SM is proposed in combination with a new 3-dimensional constellation, where signal symbols transmitted from a given antenna combination are rotated before transmission. In this paper, we derived an upper-bound on the error probability of the MA-SM as a function of the rotation angles. The search for the optimal rotation angles is modeled as a multi-objective optimization problem. We concluded based on both analytical and simulation results that the 3-dimensional constellation with the optimal angles achieved negligible improvement. Therefore, we do not recommend using the 3-dimensional constellation with the MA-SM system.