Search

Advances in deep learning and computer vision have overcome many challenges inherent in the field of autonomous intelligent vehicles. To improve the detection accuracy and efficiency of EdgeBoard intelligent vehicles, we proposed an optimized design of EdgeBoard based on our PP-YOLOE+ model. This model innovatively introduces a composite backbone network, incorporating deep residual networks, feature pyramid networks, and RepResBlock structures to enrich environmental perception capabilities through the advanced analysis of sensor data. The incorporation of an efficient task-aligned head (ET-head) in the PP-YOLOE+ framework marks a pivotal innovation for precise interpretation of sensor information, addressing the interplay between classification and localization tasks with high effectiveness. Subsequent refinement of target regions by detection head units significantly sharpens the system's ability to navigate and adapt to diverse driving scenarios. Our innovative hardware design, featuring a custom-designed mainboard and drive board, is specifically tailored to enhance the computational speed and data processing capabilities of intelligent vehicles. Furthermore, the optimization of our Pos-PID control algorithm allows the system to dynamically adjust to complex driving scenarios, significantly enhancing vehicle safety and reliability. Besides, our methodology leverages the latest technologies in edge computing and dynamic label assignment, enhancing intelligent vehicles' operations through seamless sensor integration. Our custom dataset, specifically designed for this study, includes 4777 images captured by intelligent vehicles under a variety of environmental and lighting conditions. The dataset features diverse scenarios and objects pertinent to autonomous driving, such as pedestrian crossings and traffic signs, ensuring a comprehensive evaluation of the model's performance. We conducted extensive testing of our model on this dataset to thoroughly assess sensor performance. Evaluated against metrics including accuracy, error rate, precision, recall, mean average precision (mAP), and F1-score, our findings reveal that the model achieves a remarkable accuracy rate of 99.113%, an mAP of 54.9%, and a real-time detection frame rate of 192 FPS, all within a compact parameter footprint of just 81 MB. These results demonstrate the superior capability of our PP-YOLOE+ model to integrate sensor data, achieving an optimal balance between detection accuracy and computational speed compared with existing algorithms. [ABSTRACT FROM AUTHOR]

Recording the trajectory of table tennis balls in real-time enables the analysis of the opponent's attacking characteristics and weaknesses. The current analysis of the ball paths mainly relied on human viewing, which lacked certain theoretical data support. In order to solve the problem of the lack of objective data analysis in the research of table tennis competition, a target detection algorithm-based table tennis trajectory extraction network was proposed to record the trajectory of the table tennis movement in video. The network improved the feature reuse rate in order to achieve a lightweight network and enhance the detection accuracy. The core of the network was the "feature store & return" module, which could store the output of the current network layer and pass the features to the input of the network layer at the next moment to achieve efficient reuse of the features. In this module, the Transformer model was used to secondarily process the features, build the global association information, and enhance the feature richness of the feature map. According to the designed experiments, the detection accuracy of the network was 96.8% for table tennis and 89.1% for target localization. Moreover, the parameter size of the model was only 7.68 MB, and the detection frame rate could reach 634.19 FPS using the hardware for the tests. In summary, the network designed in this paper has the characteristics of both lightweight and high precision in table tennis detection, and the performance of the proposed model significantly outperforms that of the existing models. [ABSTRACT FROM AUTHOR]

In the fault diagnosis field, the fault feature signal is weak and contaminated by the noise. The lock-in amplifier is a useful tool for weak signal detection. Aiming to the amplitude error of the lock-in amplifier caused by frequency deviation between the measured signal and the reference signal, a DFT-based automatic signal frequency estimation method is studied to improve the frequency accuracy of the reference signal. Based on this frequency estimation method, a software digital lock-in amplifier method is proposed to detect the multiple frequencies signals. This proposed method can automatically measure the frequency value of the measured signal without prior frequency information. Then, the reference signals are generated through this frequency value to make the digital lock-in amplifier estimate the amplitude of the measured signal. Moreover, an iterative structure is used to implement the multiple frequencies signal measurement. The frequencies and amplitudes measurement accuracies are tested. Under different SNR conditions, the frequency relative error is less than 0.1 % . In addition, the amplitude relative error with different signal frequencies is less than 1.7 % when the SNR is −1 dB. This proposed software digital lock-in amplifier method has a higher signal frequency tracking ability and amplitude measurement accuracy. [ABSTRACT FROM AUTHOR]

In this work, a MEMS piezoresistive micro pressure sensor (1.5 × 1.5 × 0.82 mm) is designed and fabricated with SOI-based micromachining technology and assembled using anodic bonding technology. In order to optimize the linearity and sensitivity over a wide effective pressure range (0–5 MPa) and temperature range (25–125 °C), the diaphragm thickness and the insulation of piezoresistors are precisely controlled by an optimized micromachining process. The consistency of the four piezoresistors is greatly improved by optimizing the structure of the ohmic contact pads. Furthermore, the probability of piezoresistive breakdown during anodic bonding is greatly reduced by conducting the top and bottom silicon of the SOI. At room temperature, the pressure sensor with 40 µm diaphragm demonstrates reliable linearity (0.48% F.S.) and sensitivity (33.04 mV/MPa) over a wide pressure range of 0–5.0 MPa. In addition, a polyimide protection layer is fabricated on the top surface of the sensor to prevent it from corrosion by a moist marine environment. To overcome the linearity drift due to temperature variation in practice, a digital temperature compensation system is developed for the pressure sensor, which shows a maximum error of 0.43% F.S. in a temperature range of 25–125 °C. [ABSTRACT FROM AUTHOR]

The advent of optogenetics provides a well-targeted tool to manipulate neurons because of its high time resolution and cell-type specificity. Recently, closed-loop neural manipulation techniques consisting of optical stimulation and electrical recording have been widely used. However, metal microelectrodes exposed to light radiation could generate photoelectric noise, thus causing loss or distortion of neural signal in recording channels. Meanwhile, the biocompatibility of neural probes remains to be improved. Here, five kinds of neural interface materials are deposited on flexible polyimide-based neural probes and illuminated with a series of blue laser pulses to study their electrochemical performance and photoelectric noises for single-unit recording. The results show that the modifications can not only improve the electrochemical performance, but can also reduce the photoelectric artifacts. In particular, the double-layer composite consisting of platinum-black and conductive polymer has the best comprehensive performance. Thus, a layer of polypeptide is deposited on the entire surface of the double-layer modified neural probes to further improve their biocompatibility. The results show that the biocompatible polypeptide coating has little effect on the electrochemical performance of the neural probe, and it may serve as a drug carrier due to its special micromorphology. [ABSTRACT FROM AUTHOR]

With the rapid increase in the use of optogenetics to investigate nervous systems, there is high demand for neural interfaces that can simultaneously perform optical stimulation and electrophysiological recording. However, high-magnitude stimulation artifacts have prevented experiments from being conducted at a desirably high temporal resolution. Here, a flexible polyimide-based neural probe with polyethylene glycol (PEG) packaged optical fiber and Pt-Black/PEDOT-GO (graphene oxide doped poly(3,4-ethylene-dioxythiophene)) modified microelectrodes was developed to reduce the stimulation artifacts that are induced by photoelectrochemical (PEC) and photovoltaic (PV) effects. The advantages of this design include quick and accurate implantation and high-resolution recording capacities. Firstly, electrochemical performance of the modified microelectrodes is significantly improved due to the large specific surface area of the GO layer. Secondly, good mechanical and electrochemical stability of the modified microelectrodes is obtained by using Pt-Black as bonding layer. Lastly, bench noise recordings revealed that PEC noise amplitude of the modified neural probes could be reduced to less than 50 µV and no PV noise was detected when compared to silicon-based neural probes. The results indicate that this device is a promising optogenetic tool for studying local neural circuits. [ABSTRACT FROM AUTHOR]

In this article, the state-of-the-art multi-wave and hybrid imaging techniques in the field of nondestructive evaluation and structural health monitoring were comprehensively reviewed. A new direction for assessment and health monitoring of various structures by capitalizing the advantages of those imaging methods was discussed. Although sharing similar system configurations, the imaging physics and principles of multi-wave phenomena and hybrid imaging methods are inherently different. After a brief introduction of nondestructive evaluation (NDE) , structure health monitoring (SHM) and their related challenges, several recent advances that have significantly extended imaging methods from laboratory development into practical applications were summarized, followed by conclusions and discussion on future directions.