경계 스캔 기반 온-라인 회로 성능 모니터링 기법

In this paper, we study an approach to the processing of radar signals motivated by the neural processing of echolocation waveforms by certain species of bats. We propose a transmission strategy and a corresponding family of processing algorithms and study the resulting delay-Doppler resolution characteristics. We investigate both the improvement in delay-Doppler resolution and the generation of artifacts in the delay-Doppler maps generated by this approach. Because the resulting schemes are not optimal for detection, we investigate the degradation in detection performance when compared to the matched filter. The contribution of the proposed scheme is a significant improvement in delay-Doppler resolution without a significant increase in system or computational complexity or a significant degradation in detection performance.

It is required to detect distribution shift in order to prevent a machine learning model from performance degradation, and human-mediated data analysis from erroneous conclusions. For the purpose of comparing between unknown distributions of high-dimensional data, histograms are suitable density estimators due to its computational efficiency. It is important for histograms for distribution shift detection to have uniform density, which has been demonstrated in existing tree-based or cluster-based histograms. However, existing histograms do not consider generalization capability to out-of-sample data, resulting in degraded detection performance at test time. In this paper, we propose a neural-based histogram for distribution shift detection, which generalizes well to out-of-sample data. The bins of histogram are determined by a model trained to discriminate between a handful reference instances, which reflects their underlying distribution. Due to the batch-wise maximum entropy regularizer calculated from a bootstrap sample, the bins as a subset of the feature space partitioned by the decision boundaries of the model generalize, and thus the histogram keeps its density uniform for out-of-sample data. We evaluate our method on distribution shift detection task using multi-domain real-world datasets. The results show that our method outperforms state-of-the-art histogram-based methods.

A deep ensemble convolutional neural network (CNN) model to inspect printed circuit board (PCB) board dual in-line package (DIP) soldering defects with Hybrid-YOLOv2 (YOLOv2 as a foreground detector and ResNet-101 as a classifier) and Faster RCNN with ResNet-101 and Feature Pyramid Network (FPN) (FRRF) achieved a detection rate of 97.45% and a false alarm rate (FAR) of 20%–30% in the previous study [34] . However, applying the method to other production lines, environmental variations, such as lighting, orientations of the sample feeds, and mechanical deviations, led to the degradation in detection performance. This article proposes an effective self-adaption method that collects “exception data” like the samples with which the Artificial Intelligent (AI) model made mistakes from the automated optical inspection inference edge to the training server, retraining with exceptions on the server and deploying back to the edge. The proposed defect detection system has been verified with real tests that achieved a detection rate of 99.99% with an FAR 20%–30% and less than 15 s of inspection time on a resolution $7296 \times 6000$ PCB image. The proposed system has proven capable of shortening inspection and repair time for online operators, where a 33% efficiency boost from the three production lines of the collaborated factory has been reported [6] . The contribution of the proposed retraining mechanism is threefold: 1) because the retraining process directly learns from the exceptions, the model can quickly adapt to the characteristic of each production line, leading to a fast and reliable mass deployment; 2) the proposed retraining mechanism is a necessary self-service for conventional users as it incrementally improves the detection performance without professional guidance or fine-tuning; and 3) the semiautomatic exception data collection method helps to reduce the time-consuming manual labeling during the retraining process.

Out-of-Distribution (OoD) detectors based on AutoEncoder (AE) rely on an underlying assumption that an AE network cannot reconstruct OoD data as good as in-distribution (ID) data when it is constructed based on ID data only. However, this assumption may be violated in practice, resulting in a degradation in detection performance. Therefore, alleviating the factors violating this assumption can potentially improve the robustness of OoD performance. Our empirical studies also show that image complexity can be another factor hindering detection performance for AE-based detectors. To cater for these issues, we propose two OoD detectors LAMAE and LAMAE+. Both can be trained without the availability of any OoD-related data. The key idea is to regularize the AE network architecture with a classifier and a label-assisted memory to confine the reconstruction of OoD data while retaining the reconstruction ability for ID data. We also adjust the reconstruction error by taking image complexity into consideration. Experimental studies show that the proposed OoD detectors can perform well on a wider range of OoD scenarios.

Bounded confidence opinion dynamics model the propagation of information in social networks. However, in the existing literature, opinions are only viewed as abstract quantities without semantics rather than as part of a decision-making system. In this work, opinion dynamics are examined when agents are Bayesian decision makers that perform hypothesis testing or signal detection, and the dynamics are applied to prior probabilities of hypotheses. Bounded confidence is defined on prior probabilities through Bayes risk error divergence, the appropriate measure between priors in hypothesis testing. This definition contrasts with the measure used between opinions in standard models: absolute error. It is shown that the rapid convergence of prior probabilities to a small number of limiting values is similar to that seen in the standard Krause-Hegselmann model. The most interesting finding in this work is that the number of these limiting values and the time to convergence changes with the signal-to-noise ratio in the detection task. The number of final values or clusters is maximal at intermediate signal-to-noise ratios, suggesting that the most contentious issues lead to the largest number of factions. It is at these same intermediate signal-to-noise ratios at which the degradation in detection performance of the aggregate vote of the decision makers is greatest in comparison to the Bayes optimal detection performance. Real-world data from the United States Senate is examined in connection with the proposed model.

Deep learning have been playing an increasing important role in ship detection in synthetic aperture radar (SAR) image because of its high accuracy, fast speed and no need of manual design features. It is difficult to set appropriate anchors when using anchor-based method because of multi-resolution SAR images and multi-scale ships, thus resulting in degradation of detection performance in operational applications. Recently, a lot of anchor-free architecture have been put forward, among which most of them apply horizontal bounding boxes (HBBs) to encode ship location, leading to inaccurate location description and decreased detection performance especially for arbitrary-oriented ships in complex scenes. Therefore, an anchor-free detector for arbitrary-oriented ship detection in SAR images, called R-FCOS is proposed in this paper. Specifically, based on the FCOS baseline method, ship aspect angle and rotate regression branch are introduced to regress oriented bounding boxes (OBBs) for arbitrary-oriented ships detection. Besides, to alleviate the effects of feature misalignment problem, ratio-ness branch is proposed to predict the aspect ratio of ship, which is used to filter and refine the OBBs in the post-processing step to improve detection accuracy. Finally, we carry out experiments on the SSDD+ data set to verify the effectiveness of our method. It turns out that our method obtains mAP 90.65% under an IoU threshold of 0.5.

Recent advancements in vehicle automation and driver-assistance systems that detect pavement markings has increased the importance of the detectability of pavement markings through various sensor modalities across weather and road conditions. Among the sensing techniques, light detection and ranging (LiDAR) sensors have become popular for vehicle-automation applications. This study used low-cost mobile multi-beam LiDAR to assess the performance of several types of pavement marking materials installed on a limited-access highway in various conditions, and quantified the degradation in detection performance over three years. Four marking materials, HPS-8, polyurea, cold plastic, and sprayable thermoplastic, were analyzed in the current study. LiDAR reflectivity data extracted from a total of 210 passes through the test sections were analyzed. A new detectability score based on LiDAR intensity data was proposed to quantify the marking detectability. The results showed that the pavement marking detectability varied across the material types over the years. The results provide guidance for selecting materials and developing maintenance schedules when marking detectability by LiDAR is a concern.

A fast reverberation suppression method is proposed for underwater target detection in ports and other locations. Given the strong correlation between multi-frame reverberations, the reverberation and target in multi-frame data are modeled into low-rank and sparse matrices, respectively. The low-rank sparse decomposition is achieved through robust orthogonal subspace learning; thus, the separation of reverberation and target is accomplished, and the signal-to-reverberation ratio (SRR) is enhanced. Furthermore, the proposed method lowers the dimensionality of matrix decomposition, thereby reducing computational complexity and accelerating processing speed. The Vladivostok reverberation experiment reveals that under SRR conditions from −15 dB to 0 dB, the proposed method attains a 91% computational speed enhancement compared to conventional methods, with no degradation in detection performance. Experimental results from the Songhua River target detection experiment further corroborate these findings.

Synthetic Aperture Radar (SAR) incremental target detection faces challenges from the limits of incremental learning frameworks and distinctive properties of SAR imagery. The limited spatial representation of targets, combined with strong background interference and fluctuating scattering characteristics, leads to unstable feature learning when new classes are introduced. These factors exacerbate representation mismatches between existing and incremental tasks, resulting in significant degradation in detection performance. To address these challenges, we propose a novel incremental learning framework featuring Hierarchical Frequency-Knowledge Reconstruction (HFKR). HFKR leverages wavelet-based frequency decomposition and cross-domain feature reconstruction to enhance consistency between global and detailed features throughout the incremental learning process. Specifically, we analyze the manifestation of representation mismatch in feature space and its impact on detection accuracy, while investigating the correlation between hierarchical semantic features and frequency-domain components. Based on these insights, HFKR is embedded within the feature transfer phase, where frequency-guided decomposition and reconstruction facilitate seamless integration of new and old task features, thereby maintaining model stability across updates. Extensive experiments on two benchmark SAR datasets, MSAR and SARAIRcraft, demonstrate that our method delivers superior performance compared to existing incremental detection approaches. Furthermore, its robustness in multi-step incremental scenarios highlights the potential of HFKR for broader applications in SAR image analysis.

In this study, for channels containing primary user traffic, we investigate how non-Gaussian noise model affects detection performance in cognitive radio. As decision statistic, energy detector has been preferred by considering its simple structure and the fact that it does not need a priori knowledge about primary user signal. Gaussian mixture model, Laplacian distribution, and symmetric α-stable distribution have been used as non-Gaussian noise models. The status changes of the primary user have been modeled via Poisson process. The simulations have been carried out separately for both under status changes and no status changes in the channel. According to our simulation results, primary user traffic degrades detection performance as does existence of non-Gaussian noise. In addition, it has been observed that the maximum degradation in detection performance of energy detector occurs for symmetric α-stable distributions among the considered noise models in this study.

This project focused on developing advanced methods for thermal performance monitoring of a coal-fueled power plant. The specific goal was to develop and demonstrate a new thermal performance monitoring approach using a hybrid model that integrates a physics-based heat balance model with a machine learning-based pattern recognition model. The hybrid model enables increased accuracy and scope of the thermal analysis and an improved ability to monitor and detect changes in plant operation. This new approach takes full advantage of the individual model capabilities and creates an important new set of capabilities not previously possible using the two types of models separately. Using the heat balance model, a rich set of derived parameters (virtual sensors) are calculated from the measured plant operating data at each time point. The combined measured and derived data values are used by machine learning algorithms to create pattern recognition models over the range of normal unit operation. To create the monitoring models, historical data from normal operation of the plant is first processed by the heat balance model to compute the derived parameter data. The result is a greatly expanded set of normal operating data that can be used as input to create the pattern recognition model. Once the models are calibrated for normal operation, the hybrid model is suitable for use in continuous online monitoring. During online monitoring, new plant operating data is processed first by the heat balance model and then by the pattern recognition model. Results from the pattern recognition model quantify the deviation of each measured or derived parameter from its expected value in normal operation. The hybrid models can detect abnormal changes in plant operating data with very high accuracy and sensitivity. When abnormal behavior is detected, alerts are generated automatically for evaluation by the plant monitoring staff. The new hybrid solution product was developed and verified in the performance of the project. The hybrid solution was tested first in a simulation environment that mimicked the plant data systems and infrastructure used by U.S. power generating plants and utilities. The hybrid solution was then deployed for real-time, online monitoring of an operating coal-fueled power plant at a field test site. Field testing demonstrated that all hybrid solution development objectives were accomplished. The project work was based on combining the capabilities of two existing software products to create the new hybrid solution product. One of these was the existing MapEx® heat balance product and the other was the existing SureSense® advanced pattern recognition product. Each of these separate products was assessed to be at a Technology Readiness Level (TRL) of 9 at the start of the effort. The hybrid solution product was assessed to be at a TRL of 2 at the start of the project based on early feasibility work by the project team. At completion of the field testing performed in the project, the hybrid solution product was assessed to be at a TRL of 7. The project team expects that the hybrid solution product will be deployed commercially and will achieve a TRL of 9 within one year after completion of the project.

A group of white OLEDs (organic light-emitting devices), were fabricated using the blue yellow complementary principle. Among them, MCP(1,3-Bis(carbazol-9-yl)benzene) was used as the main material for the blue light layer, FIrPic(Bis(3,5-difluoro)-2-(2-pyridyl)phenyl-(2-carboxypyridyl)iridium(III)) as the phosphorescent object material, and Rubrene(5,6,11,12-Tetraphenylnaphthacene) as the fluorescent material for the yellow light layer. The device structure is NPB(N,N′-Bis(naphthalen-1-yl)-N,N′-bis(phenyl)-benzidine) (20 nm)/Rubrene (0.5 nm)/MCP (3 nm)/MCP: FIrPic (30 nm, 10%)/Rubrene (z nm)/TPBi(1,3,5-Tris(1-phenyl-1Hbenzimidazol-2-yl) benzene)(10 nm)/Alq3(20 nm/LiF (0.6 nm)/Al (100 nm). By adjusting the thickness of Rubrene, the structure of the device was optimized and the performance of the device was improved. When the thickness of Rubrene was 0.5 nm, the performance of the device was the best, the maximum efficiency was 6.41 cd/A, the maximum luminance was 8344 cd/m2. When the driving voltage changed from 5 V to 14 V, the device changed from warm white light to cold white light.

Optimal design of distributed detection systems is studied. The two cases of noise-free and noisy communication links that connect the detector cluster with the central processor are considered. The presence of noisy links does not pose any significantly new theoretical problem and the general result is that link SNRs greater than 10 dB are sufficient to ensure negligible degradation of system detection performance. A fast and easy graphical solution method involving the new concept of sensor fusion characteristics is proposed and appears to be a promising technique for distributed system design.

To monitor objects of interest, such as wildlife and people, image-capturing devices are used to collect a large number of images with and without objects of interest. As we are recording valuable information about the behavior and activity of objects, the quality of images containing objects of interest should be better than that of images without objects of interest, even if the former exhibits more severe distortion than the latter. However, according to current methods, quality assessments produce the opposite results. In this study, we propose an end-to-end model, named DETR-IQA (detection transformer image quality assessment), which extends the capability to perform object detection and blind image quality assessment (IQA) simultaneously by adding IQA heads comprising simple multi-layer perceptrons at the top of the DETRs (detection transformers) decoder. Using IQA heads, DETR-IQA carried out blind IQAs based on the weighted fusion of the distortion degree of the region of objects of interest and the other regions of the image; the predicted quality score of images containing objects of interest was generally greater than that of images without objects of interest. Currently, the subjective quality score of all public datasets is in accordance with the distortion of images and does not consider objects of interest. We manually extracted the images in which the five predefined classes of objects were the main contents of the largest authentic distortion dataset, KonIQ-10k, which was used as the experimental dataset. The experimental results show that with slight degradation in object detection performance and simple IQA heads, the values of PLCC and SRCC were 0.785 and 0.727, respectively, and exceeded those of some deep learning-based IQA models that are specially designed for only performing IQA. With the negligible increase in the computation and complexity of object detection and without a decrease in inference speeds, DETR-IQA can perform object detection and IQA via multi-tasking and substantially reduce the workload.

Fractal theory has improved the target detection performance under sea clutter background. However, the traditional fractal methods in time domain or Fourier domain cannot accurately characterize the complex sea clutter properties, which leads to the degradation of the target detection performance under low signal-clutter-ratio (SCR) conditions. This article investigates the multifractal correlation property of sea clutter in the autoregressive (AR) spectrum domain for detection performance improvement. In this work, the traditional target detection problem is converted to a binary classification problem of sea clutter and targets. The refined fractal characteristics in various singularity scale interval and range bins are analyzed, and the AR singularity intensity correlation function width together with the accumulation area of AR multifractal correlation spectrum is extracted as intrinsic features. Then, a simple and efficient fully connected network is developed to realize the classification. Experimental results on real measured marine radar datasets demonstrate that the proposed method can increase the detection probability by about 15% than the state-of-art fractal-based methods under a low SCR condition.