In this study, a millimeter-wave (MMW) radar and an onboard camera are used to develop a sensor fusion algorithm for a forward collision warning system. This study proposed integrating an MMW radar and camera to compensate for the deficiencies caused by relying on a single sensor and to improve frontal object detection rates. Density-based spatial clustering of applications with noise and particle filter algorithms are used in the radar-based object detection system to remove non-object noise and track the target object. Meanwhile, the two-stage vision recognition system can detect and recognize the objects in front of a vehicle. The detected objects include pedestrians, motorcycles, and cars. The spatial alignment uses a radial basis function neural network to learn the conversion relationship between the distance information of the MMW radar and the coordinate information in the image. Then a neural network is utilized for object matching. The sensor with a higher confidence index is selected as the system output. Finally, three kinds of scenario conditions (daytime, nighttime, and rainy-day) were designed to test the performance of the proposed method. The detection rates and the false alarm rates of proposed system were approximately 90.5% and 0.6%, respectively.

This study discusses the quality analysis of a new tapping machine. By measuring the torque and speed of the tapping machine, the correlation between the quality of the nut and the tapping process is analyzed. Using various regression trees and learning methods, the results show that the magnitude of the tapping torque is an essential indicator of the quality of the thread. In addition, through such methods, the appropriate operation boundary of the tapper torque and tapper speed can be determined. Thread, processed in the two boundaries, can have a high probability of being a Class 1 thread. Furthermore, the tapping torque is also used for quality classification by a one-dimensional convolutional neural network (1-D CNN). The 1-D CNN model performs high classification accuracy and has the ability to localize the important area of the signal. The experimental results show that the regression tree can effectively find the operation boundary, providing information for users to adjust their machine settings, and improve the thread quality. In addition, the off-line classification of thread done by humans can be replaced by the high-accuracy 1-D CNN model predicting the thread quality in real-time. The detection speed can be accelerated, and labor costs can be reduced.