Radar signal sorting is a critical step in electronic reconnaissance. To address the lack of correlation between temporal and spatial information in radar signal sorting, we propose the spatial and temporal hypergraph contrastive learning architecture (STH-CL). This architecture utilizes a Gaussian mixture model (GMM) to construct a spatial hypergraph based solely on pulse positions in feature space. It integrates the GMM prior into the attention mechanism of a lightweight Transformer to extract temporal features, thereby establishing a temporal hypergraph using K-Nearest Neighbors (KNN). The complementary contrastive learning improves hyperedge quality and enables accurate sorting. Experiments on simulated radar parameter data demonstrate that STH-CL achieves over 90% sorting accuracy.

Compact models of transistors are essential for simulating and optimizing circuits with the use of SPICE simulation tool. Parameter extraction, which is calibrating these models, is essential to ensure their alignment with measured or simulated data. However, conventional parameter extraction methods are generally iterative and experience-dependent, requiring significant time and effort from modeling engineers. Moreover, as semiconductor devices and compact models become increasingly advanced, the need for a tailored extraction process for each model has become increasingly inefficient. To address the above challenges, this work proposes an agile transistor compact modeling framework, ATMAD. The proposed framework takes a compact model file and a set of electrical characteristic data as inputs, producing a calibrated model with minimal human intervention. ATMAD automatically retrieves the equations in the compact model and converts them into computational flow graphs, thus supporting different compact models with a generalized process. A graph unlooping technique is proposed to support automatic differentiation for compact models with implicit functions (e.g., series resistance and surface potential solving). Based on the computational flow graph, ATMAD adopts automatic differentiation technique to achieve automatic and parallel optimization of model parameters. The proposed ATMAD framework is validated on commonly-used compact models in academia and industry, showing its effectiveness for compact modeling for both I-V and C-V characteristics.

In the complex marine environment, traditional detectors based on the classifiers cannot guarantee the global false alarm control. In this paper, we propose a detector based on dual channel convolutional neural network (DC-CNN) and global false alarm controllable adaptive boosting tree (GFAC-A), which is shortened as DC-CNN-GFAC-A. DC-CNN focuses on the correlation features of radar echoes in time domain and frequency domain, better use multi-dimensional features and show a better feature extraction ability. Through the application of GFAC-A, the false alarm rate is introduced into the algorithm combining decision tree and AdaBoost to achieve the high-performance detection of global false alarm controllable for high-dimensional features. It is heuristics. The combination of DC-CNN and GFAC-A solves the disadvantage that current classifiers cannot meet the conditions of good performance and low false alarm. First, the connectivity information is obtained by using the frequency domain amplitude characteristics of radar echo data, and the recursive information is obtained by using the nonlinear recursive time series characteristics. And the dual-channel datasets of targets and clutter are built. Then, DC-CNN is built to extract and fuse high-dimensional features to obtain feature vectors of targets and clutter. Besides, the performance comparison of different neural network model combinations is carried out. Finally, compared with the traditional threshold-controllable classifiers, the proposed GFAC-A classifier achieves the high detection performance under the global controlled false alarm. The results show that DC-CNN-GFAC-A can achieve 96.491% detection accuracy when the false alarm rate is 10-3, which is superior to other detections.

Abstract In this article, a constant false alarm rate (CFAR) detection algorithm based on the fractional Fourier transform (FRFT) and orthogonal projection (OP) is proposed. With a low signal‐to‐clutter ratio (SCR), the radar returns of sea‐surface small targets are often submerged by sea clutter. The FRFT can accumulate target energy in the optimal order. Meanwhile, the OP suppresses the sea clutter in a projection space in the FRFT domain, thus enhancing the output SCR. The FRFT and the OP are in conjunction with the CFAR to realise target detection, which is referred to as the FRFT‐OP‐CFAR. For the FRFT‐OP‐CFAR detector, the most important is the selection of the optimal order and the calculation of the OP operator . The experimental results show that the proposed FRFT‐OP‐CFAR has a better clutter suppression and detection performance than some detectors in the authors’ comparison.

In this paper, we propose the False-Alarm-Rate-Controllable (FAC) classification of sea clutter Recurrence Plots (RPs) based on Convolutional Neural Networks (CNN), which is shortened as RPs-CNN. Sea clutter data is a non-linear and recursive time series, and RPs provide qualitative analysis of non-linear and recursive dynamic systems. Thus, we construct the RPs datasets to extract the recursive feature of sea clutter. In the RPs datasets, RPs parameters, embedding delay τ and embedding dimension m, are obtained by the average mutual information (AMI) and false nearest neighbor (FNN) algorithms, respectively. In addition, in order to extract the local features of RPs, CNN is applied. CNN makes full use of local features of the datasets, has the advantages of translation invariance and strong generalization ability, and shares the available weights to simplify network structure. We implement a proper LeNet-5 CNN training on the constructed RPs datasets, and verity it by IPIX measured datasets. The experimental results demonstrate that the CNN successfully classifies the RPs of targets and clutter. Moreover, the feasibility of RPs-CNN is verified by seven aspects, i.e., Accuracy, Precision, False Alarm, Miss Rate, Recall, F1-measure and Kappa. In addition, six parameters that may affect the classification performance are also analyzed, including time-series length, embedding delay, embedding dimension, convolutional kernel size, kernel depth, and optimization function. The results indicate that the proposed RPs-CNN method can reach a 92.05% F1-measure and 87.19% Kappa which performs better than other classification methods. Meanwhile, the false alarm rate (FAR) of the RPs-CNN is testified by the FAC classification. Experimental results demonstrate that the proposed RPs-CNN significantly improves the detection probability over other classification detectors in low FAR cases.

For those who love painting but unfortunately have visual impairments, holding a paintbrush to create a work is really a difficult task. For the purpose of solving this problem, a painting navigation system for visually impaired painters is introduced through the live demonstration. When painting, the developed system can endow visually impaired persons with the ability to perceive the surrounding environment, thus helping them realize their dream of painting. To achieve this goal, we designed four main modules viz., QR code based drawing board positioning module, brush real-time positioning module, color recognition module and human-computer interaction module, and integrated them into the system. In the validation experiments, the blindfolded users can successfully create a painting with the help of the developed navigation system. Moreover, the users told us that this system provided them with good experience. In a way, this painting navigation system can be seen as "angel's eyes" of visually impaired painters. The demo video of the proposed painting navigation system is available at: https://doi.org/10.6084/m9.figshare.9760004.v1.

According to recent results on Middlebury, MPI Sintel, and KITTI benchmarks, the accuracy of optical flow estimation algorithms has been significantly improved. The speed of them, however, has been too slow to meet the requirement of real-time applications. As a result, some parallel architectures (such as FPGA or GPU) have to be used for accelerating. Therefore, reducing the computational cost of optical flow estimation makes a lot of sense. To overcome the above issues, this paper proposes a fast local method based on 3D-gradients and approximate nearest-neighbor field (NNF), which is different from the widely used global model. In our method, NNF is used to provide initial optical flow field, and the proposed fast 3D-gradients-based local operator is used to propagate flow from coarse level to finer level in the coarse-to-fine refinement. We implement two versions of our method (with/without NNF initialization). Experimental results show that our method has a significant advantage for speed over other methods, where the fast version is capable of processing$Urban$sequence ($640\times 480$) at$\approx 10$frames/s without parallel architectures. Meanwhile, our accuracy is also within acceptable levels on both small and large motion for some real-time applications.

We investigate the detection of range distributed floating target in sea clutter that consists of stationary speckle modulated by nonstationary texture. With the elimination of the nonstationary part of sea clutter, here a feature-based detector using the consistency factor of speckle is proposed. Experimental results of IPIX radar data sets show that the proposed feature-based detector achieves the better detection performance in comparison with other methods. The nonstationary property of sea clutter has a negative effect on the probability of detection, thus warrant consideration in designing the detector.