Sensors最新文献

This paper proposes a novel decentralized federated reinforcement learning (DFRL) framework that integrates deep reinforcement learning (DRL) with decentralized federated learning (DFL). The DFRL framework boosts efficient virtual instance scaling in Mobile Edge Computing (MEC) environments for 5G core network automation. It enables multiple MECs to collaboratively optimize resource allocation without centralized data sharing. In this framework, DRL agents in each MEC make local scaling decisions and exchange model parameters with other MECs, rather than sharing raw data. To enhance robustness against malicious server attacks, we employ a committee mechanism that monitors the DFL process and ensures reliable aggregation of local gradients. Extensive simulations were conducted to evaluate the proposed framework, demonstrating its ability to maintain cost-effective resource usage while significantly reducing blocking rates across diverse traffic conditions. Furthermore, the framework demonstrated strong resilience against adversarial MEC nodes, ensuring reliable operation and efficient resource management. These results validate the framework's effectiveness in adaptive and efficient resource management, particularly in dynamic and varied network scenarios.

In-flight alignment is a critical milestone for inertial navigation system/global navigation satellite system (INS/GNSS) applications in unmanned aerial vehicles (UAVs). The traditional position integration formula for in-flight coarse alignment requires the GNSS velocity data to be valid throughout the alignment period, which greatly limits the engineering applicability of the method. In this paper, a new robust position integration optimization-based alignment (OBA) method for in-flight coarse alignment is presented to solve the problem of in-flight alignment under a prolonged ineffective GNSS. In this methodology, to achieve a higher alignment accuracy in case the GNSS is not effective throughout the alignment period, the integration of GNSS velocity into the local-level navigation frame is replaced by the GNSS position in the Earth-centered, Earth-fixed frame, which avoids the need for complete GNSS velocity data. The simulation and flight test results show that the new robust position integration method proposed in this paper achieves higher stability and robustness than the conventional position integration OBA method and can achieve an alignment accuracy of 0.2° even when the GNSS is partially time-invalidated. Thus, this greatly extends the application of the OBA method for in-flight alignment.

Germinal matrix hemorrhage (GMH) is a critical condition affecting premature infants, commonly diagnosed through cranial ultrasound imaging. This study presents an advanced deep learning approach for automated GMH grading using the YOLOv8 model. By analyzing a dataset of 586 infants, we classified ultrasound images into five distinct categories: Normal, Grade 1, Grade 2, Grade 3, and Grade 4. Utilizing transfer learning and data augmentation techniques, the YOLOv8 model achieved exceptional performance, with a mean average precision (mAP50) of 0.979 and a mAP50-95 of 0.724. These results indicate that the YOLOv8 model can significantly enhance the accuracy and efficiency of GMH diagnosis, providing a valuable tool to support radiologists in clinical settings.

Studies using source localization results have shown that cortical involvement increased in treadmill walking with brain-computer interface (BCI) control. However, the reorganization of cortical functional connectivity in treadmill walking with BCI control is largely unknown. To investigate this, a public dataset, a mobile brain-body imaging dataset recorded during treadmill walking with a brain-computer interface, was used. The electroencephalography (EEG)-coupling strength of the between-region and within-region during the continuous self-determinant movements of lower limbs were analyzed. The time-frequency cross-mutual information (TFCMI) method was used to calculate the coupling strength. The results showed the frontal-occipital connection increased in the gamma and delta bands (the threshold of the edge was >0.05) during walking with BCI, which may be related to the effective communication when subjects adjust their gaits to control the avatar. In walking with BCI control, the results showed theta oscillation within the left-frontal, which may be related to error processing and decision making. We also found that between-region connectivity was suppressed in walking with and without BCI control compared with in standing states. These findings suggest that walking with BCI may accelerate the rehabilitation process for lower limb stroke.

Current super-resolution algorithms exhibit limitations when processing noisy remote sensing images rich in surface information, as they tend to amplify noise during the recovery of high-frequency signals. To mitigate this issue, this paper presents a novel approach that incorporates the concept of compressed sensing and explores the super-resolution problem of remote sensing images for space cameras, particularly for high-speed imaging systems. The proposed algorithm employs K-singular value decomposition (K-SVD) to jointly train high- and low-resolution image blocks, updating them column by column to obtain overcomplete dictionary pairs. This approach compensates for the deficiency of fixed dictionaries in the original algorithm. In the process of dictionary updating, we innovatively integrate the circle chaotic mapping into the solution process of the dictionary sequence, replacing pseudorandom numbers. This integration facilitates balanced traversal and simplifies the search for global optimal solutions. For the optimization problem of sparse coefficients, we utilize the orthogonal matching pursuit method (OMP) instead of the L1 norm convex optimization method used in most reconstruction techniques, thereby complementing the K-SVD dictionary update algorithm. After upscaling and denoising the image using the dictionary pair mapping relationship, we further emphasize image edge details with local gradients as constraints. When compared with various representative super-resolution algorithms, our algorithm effectively filters out noise and stains in low-resolution images. It not only performs well visually but also stands out in objective evaluation indicators such as the peak signal-to-noise ratio and information entropy. The experimental results validate the effectiveness of the proposed method in super-resolution remote sensing images, yielding high-quality remote sensing image data.

Loop-Mediated Isothermal Loop-Mediated Isothermal Amplification (LAMP) is a widely used technique for nucleic acid amplification due to its high specificity, sensitivity, and rapid results. Advances in microfluidic lab-on-chip (LOC) technology have enabled the integration of LAMP into miniaturized devices, known as μ-LAMP, which require precise thermal control for optimal DNA amplification. This paper introduces a novel thermal bed design using PCB copper traces and FR-4 dielectric materials, providing a reliable, modular, and repairable heating platform. The system achieves accurate and stable temperature control, which is critical for μ-LAMP applications, with temperature deviations within ±1.0 °C. The thermal bed's performance is validated through finite element method (FEM) simulations, showing uniform temperature distribution and a rapid thermal response of 2.5 s to reach the target temperature. These results highlight the system's potential for applications such as disease diagnostics, biological safety, and forensic analysis, where precision and reliability are paramount.

Pipe-type cable systems, including high-pressure fluid-filled (HPFF) and high-pressure gas-filled cables, are widely used for underground high-voltage transmission. These systems consist of insulated conductor cables within steel pipes, filled with pressurized fluids or gases for insulation and cooling. Despite their reliability, faults can occur due to insulation degradation, thermal expansion, and environmental factors. As many circuits exceed their 40-year design life, efficient fault localization becomes crucial. Fault location involves prelocation and pinpointing. Therefore, a novel pinpointing approach for pipe-type cable systems is proposed, utilizing accelerometers mounted on a steel pipe to capture fault-induced acoustic signals and employing the time difference of arrival method to accurately pinpoint the location of the fault. The experimental investigations utilized a scaled-down HPFF pipe-type cable system setup, featuring a carbon steel pipe, high-frequency accelerometers, and both mechanical and capacitive discharge methods for generating acoustic pulses. The tests evaluated the propagation velocity, attenuation, and pinpointing accuracy with the pipe in various embedment conditions. The experimental results demonstrated accurate fault pinpointing in the centimeter range, even when the pipe was fully embedded, with the acoustic pulse velocities aligning closely with the theoretical values. These experimental investigation findings highlight the potential of this novel acoustic pinpointing technique to improve fault localization in underground systems, enhance grid reliability, and reduce outage duration. Further research is recommended to validate this approach in full-scale systems.

Impact loads affect the operational performance and safety life of rolling equipment's connecting-shaft rotor system, even causing faults and accidents. Therefore, recognizing and investigating impact loads is of great significance. Hence, a load recognition method based on motor current information is proposed in this paper to recognize impact loads on the connecting-shaft rotor system. First, the fast Fourier transform is used to obtain the frequency domain information for the motor's current response signal from the rotor system load recognition test. Consequently, the required load response information can be presented more clearly using the singular value decomposition method to remove the power frequency components in the current signal. Then, wavelet packet decomposition is performed on the signal to generate energy analysis feature vectors. A qualitative recognition of the impact load on the system is achieved by learning vector quantization neural networks; the resulting load recognition results are good. These findings indicate that using the motor current as the analysis signal can solve the problem of the difficult layout for traditional vibration sensors in rolling sites. The preprocessing and recognition method of the current response signal can recognize the impact load, confirming the applicability and feasibility of the proposed method.

This paper presents a comprehensive review of cardiorespiratory auscultation sensing devices (i.e., stethoscopes), which is useful for understanding the theoretical aspects and practical design notes. In this paper, we first introduce the acoustic properties of the heart and lungs, as well as a brief history of stethoscope evolution. Then, we discuss the basic concept of electret condenser microphones (ECMs) and a stethoscope based on them. Then, we discuss the microelectromechanical systems (MEMSs) technology, particularly focusing on piezoelectric transducer sensors. This paper comprehensively reviews sensing technologies for cardiorespiratory auscultation, emphasizing MEMS-based wearable designs in the past decade. To our knowledge, this is the first paper to summarize ECM and MEMS applications for heart and lung sound analysis.

An accurate panorama depth estimation result is crucial to risk perception in autonomous driving practice. In this paper, an innovative framework is presented to address the challenges of imperfect observation and projection fusion in panorama depth estimation, enabling the accurate capture of distances from surrounding images in driving scenarios. First, the Patch Filling method is proposed to alleviate the imperfect observation of panoramic depth in autonomous driving scenarios, which constructs a panoramic depth map based on the sparse distance data provided by the 3D point cloud. Then, in order to tackle the distortion challenge faced by outdoor panoramic images, a method for image context learning, ViT-Fuse, is proposed and specifically designed for equirectangular panoramic views. The experimental results show that the proposed ViT-Fuse reduces the estimation error by 9.15% on average in driving scenarios compared with the basic method and exhibits more robust and smoother results on the edge details of the depth estimation maps.