Search

Micro-electro-mechanical system (MEMS) sensors have been widely used in the automotive field owing to their small size, low cost, and high reliability. Various defects are caused by complicated environments and multistep processes in the manufacturing process of automotive MEMS pressure sensors. These defects are often small in size but can significantly impact the performance of products. The traditional detection method is inefficient and inaccurate. In this study, an improved you only look once v8 (YOLOv8) C2f-RFCBAMConv (CR) network is proposed to detect the defects of the automotive MEMS pressure sensors. The network is an improved version of YOLOv8. The faster version of the CSP bottleneck with two convolutions (C2f) and receptive-field convolutional block attention (RFCBAMConv) modules are applied. The ablation experiments confirm the impact of C2f and RFCBAMConv modules on network performance. The improved YOLOv8-CR network can effectively enhance the accuracy and speed of defect detection of the automotive MEMS pressure sensor. Furthermore, comparisons are made between the improved YOLOv8-CR network and other networks such as YOLOv8-large, YOLOv5, and faster region-based convolutional neural network (Fast-RCNN), demonstrating its effectiveness in identifying five types of defects in the automotive MEMS pressure sensors. The improved YOLOv8-CR exhibits considerably superior defect detection capabilities with a mean average precision (mAP) of 94.98% and a single picture detection time of 42.68 ms on the test set. The improved YOLOv8-CR network is helpful in realizing real-time and accurate online monitoring of product quality in the key process of the automotive MEMS pressure sensors.

Proper signal measurement and processing are crucial in electroencephalography (EEG)-based brain-computer interfaces (BCIs), as they form the basis of brain insight and precise BCI control. Currently, extensive papers have reported their progress and successful applications in this field. Nevertheless, a systematic review of progress and challenges in this field is still lacking, and the research challenges have not been thoroughly discussed. Herein, a systematic review of instrumentation, measurement, and signal processing in EEG-based BCIs is proposed. First, EEG signals and the application of EEG-based BCIs are introduced. Then, the components and products related to the measurement, processing, and control of EEG signals are analyzed. Specifically, detailed discussions are provided on the measurement methods and results. Moreover, typical EEG paradigms and the processing methods of EEG signals are analyzed. Finally, four major challenges in this field are proposed and discussed: BCIs for acquiring high-quality EEG signals, EEG-based BCIs for long-term tasks, EEG-based BCIs for mobile or dynamic scenarios, and EEG-based BCIs with user-centered designs. This study offers practitioners a comprehensive guide for the measurement and processing of EEG signals, encompassing instrument selection, methodology implementation, current challenges, and future considerations.

Corrections are presented for the above named paper.