In the field of non-Euclidean statistical analysis, a trend has emerged in recent times, of attempts to recover a low dimensional structure, namely a manifold, underlying the high dimensional data. Recovering the manifold requires the noise to be of a certain concentration and prevailing methods address this requirement by constructing an approximated manifold that is based on the tangent space estimation at each sample point. Although theoretical convergence for these methods is guaranteed, the samples are either noiseless or the noise is bounded. However, if the noise is unbounded, as is commonplace, the tangent space estimation at the noisy samples will be blurred – an undesirable outcome since fitting a manifold from the blurred tangent space might be more greatly compromised in terms of its accuracy. In this paper, we introduce a new manifold-fitting method, whereby the output manifold is constructed by directly estimating the tangent spaces at the projected points on the latent manifold, rather than at the sample points, thus reducing the error caused by the noise. Assuming the noise is unbounded, our new method has a high probability of achieving theoretical convergence, in terms of the upper bound of the distance between the estimated and latent manifold. The smoothness of the estimated manifold is also evaluated by bounding the supremum of twice difference above. Numerical simulations are conducted as part of this new method to help validate our theoretical findings and demonstrate the advantages of our method over other relevant manifold fitting methods. Finally, our method is applied to real data examples.

Cloud detection is an essential step in remote sensing (RS) image processing, contributing to various applications. However, existing fully supervised cloud detection methods rely on massive pixel-wise annotations, which are expensive and time-consuming. To alleviate the annotation burden, weakly supervised cloud detection (WSCD) has received extensive attention recently. One standard approach performs cloud detection within a classification paradigm, which inevitably faces category ambiguity when detecting semitransparent clouds. To tackle this problem, we propose a novel WSCD framework based on the diffusion model, termed CLDiff. Specifically, a multiscale feature rectification (MFR) module is introduced to extract multiscale semantic features in the encoder, enabling a definite identification of clouds and mitigating interference from bright objects in the background. Considering that clouds exhibit varying optical thicknesses, a diffusion decoder is developed to model the intraclass variations of clouds in a generative strategy, improving thin cloud detection. Initially, it devises a Gaussian modulation function to recalibrate ambiguous cloud activations and emphasize semitransparent clouds. Subsequently, these modulated activations serve as semantic guidance to optimize the diffusion process. This approach enables CLDiff to activate cloud contours under definite semantic conditions and avoids the additional branches for semantic learning as found in previous methods. Experimental results demonstrate that CLDiff achieves state-of-the-art performance in WSCD. A public reference implementation of this work in PyTorch is available athttps://github.com/YLiu-creator/CLDiff.

The CLLC resonant converters are widely used in data center, battery chargers, electrical vehicles due to its high efficiency and high power density. The voltage gain characteristic of CLLC resonant converters plays an important role in both operation analysis and design optimization. This paper presents a precise and fast backpropagation neural network (BPNN)-based voltage gain model of CLLC that considers two degrees of freedom (2DOFs), the switching frequency$\boldsymbol{f}_{\mathbf{s}}$and duty ratio$\boldsymbol{d}$, in all operation conditions. The effectiveness of the model is verified by a 3-kW 480-V CLLC prototype. The voltage gain error is reduced by 95% compared to the conventional fundamental harmonic approximation (FHA) method, and the calculation burden is reduced by 99% compared to the time-domain method.

Cloud detection plays a significant role in remote sensing image applications. Existing deep learning-based cloud detection methods rely on massive precise pixel-wise annotations, which are time-consuming and expensive. To alleviate this problem, we propose a weakly supervised cloud detection framework that leverages physical rules to generate weak supervision for cloud detection in remote sensing images. Specifically, a rule-based adaptive pseudo labeling (RAPL) algorithm is devised to adaptively annotate potential cloud pixels based on cloud spectral properties without manual intervention. Unlike existing physical annotations using fixed thresholds, RAPL employs the bidirectional threshold segmentation and adaptive gating mechanism to annotate cloud and boundary masks with more explicit semantic categories and spatial structures separately. Subsequently, these pseudo masks are treated as weak supervision to optimize the heuristic cloud detection network for pixel-wise segmentation. Considering that clouds appear as complex geometric structures and nonuniform spectral reflectance, a deformable boundary refining module is designed to enhance the modeling ability of spatial transformation and activate sharp boundaries from translucent cloud regions. Moreover, a harmonic loss is employed to recognize clouds with nonuniform spectral reflectance and suppress the interference of bright backgrounds. Extensive experiments on the GF-1, L8 Biome, and WDCD datasets demonstrate that the proposed method achieves state-of-the-art results. A public reference implementation of this work in PyTorch is available at https://github.com/NiAn-creator/HeuristicCloudDetection.

Recently, deep convolutional neural networks (CNNs) have made important progress in cloud detection with powerful representation learning capability and yield significant performance. However, most existing CNN-based cloud detection methods still face serious challenges because of the variable geometry of clouds and the complexity of underlying surfaces. It is attributed that they only use the fixed grid to extract contextual information, which lacks internal mechanisms to handle the geometric transformations of clouds. To tackle this problem, we propose a deformable convolutional cloud detection network with an encoder-decoder architecture, named DCNet, which can enhance the adaptability of a model to cloud variations. Specifically, we introduce deformable convolution blocks at the encoder to capture saliency spatial contexts adaptively based on the morphological characteristics of clouds and generate high-level semantic representations. After this, we incorporate skip-connection mechanisms into the decoder that integrate low-level spatial contexts as guidance to recover high-level semantic pixel localization and export precise cloud-detection results. Extensive experiments on the GF-1 wide field-of-view (WFV) Satellite Imagery demonstrate that DCNet outperforms several state-of-the-art methods. A public reference implementation of our proposed model in PyTorch is available athttps://github.com/NiAn-creator/deformableCloudDetection.git.

Many soft-switching techniques have been introduced for non-isolated DC-DC converters in the literature. However, most of them show the results at the low power level. In this paper, an experimental comparison of soft-switching interleaved boost DC-DC converters with auxiliary switches for high-power applications is presented. Two zero voltage transition (ZVT) boost converter prototypes with and without the third diode in the active snubber circuit are built and evaluated. Analysis, operating principles, and parameter design for the ZVT boost converter without using the third diode in the snubber circuit are provided. The experimental verifications from laboratory tests of equivalent 10-kW/50-kHz interleaved boost converters based on discrete SiC MOSFETs and diodes are given. The results are obtained for the input voltage of 200 V and the output voltage range from 320 V to 530 V. The efficiency and power loss distribution of the converters are compared.

Network function virtualization (NFV) technology continues to gain more attention as a paradigm shift, and telecommunication services can be flexibly deployed and managed. Any service can be represented by a service function chain (SFC) that is a set of virtual network functions (VNFs) to be executed based on the strict order. The NFV-enabled SFCs applied in the future Internet-of-Things (IoT) networks emerge a challenging problem, particularly more and more IoT devices are trying to access their telecommunication services whenever and wherever, SFCs are needed to be dynamically and adaptively reconfigured, thus adapting to the service requests' dynamics for lower resource consumption and higher revenue for Internet service providers (ISPs). In this article, we study the SFC dynamic reconfiguration problem (SFC-DRP) in the IoT networks, a discrete-time Markov decision process (DTMDP)-based IoT SFC-DRP is formulated by guaranteeing the QoS and resource constraints. We subsequently propose a novel deep Dyna-Q (DDQ) approach to solve this model. Our proposal has been evaluated with the obtained results demonstrating an average CPU root-mean-square error (RMSE) of 0.17, compared to 0.75 obtained while using the original approach. Moreover, our proposed SFC reconfiguration technique can approximate the performance of the integer linear programming (ILP) model within a polynomial time, and outperform the existing benchmarks in terms of the reconfiguration overhead and the resource utilization ratio from service provisioning, respectively.

Spaceborne millimeter-wave radars can acquire sea surface backscatter information under clear sky conditions. The analysis based on the classical sea surface scattering model and a matching data set of global CloudSat Cloud Profiling Radar (CPR) observations and AMSR-E sea surface parameters shows that the sea surface scattering cross section is significantly dependent on the sea surface wind speed (SSW) in the range of less than 13 m/s. Then, with CPR observations and the sea surface temperature as the input information, an SSW retrieval model under clear sky conditions is established using neural networks. Retrieval results show that the correlation coefficient and the RMS error, between the millimeter-wave cloud radar SSW and the AMSR-E SSW, are approximately 0.95 and 0.97 m/s, respectively.

Image quality is an important factor for automated fingerprint identification systems (AFIS) because the matching performance could be significantly affected by poor quality samples. Most of the existing studies mainly focus on calculating a quality index via either a single feature or a combination of multiple features, and some others achieve this purpose with learning approaches which may depend on a prior-knowledge of matching performance. In this paper, a general framework for estimating fingerprint image quality is proposed by fusing features in segmentation phase. The quality index is indicated by a ratio of the pixel number of the integrated foreground area to the size (pixel number) of the fingerprint image. The potential advantage of this framework is that it could be improved by integrating other segmentation approaches or quality features rather than fusing them in a more complicated manner. The experiment is performed with several fingerprint datasets created via different sensors. Experimental results obtained from a dual evaluation approach demonstrate the validity of the proposed method in improving the overall performance.

Nowadays, when someone wants to make a payment with a smartcard, the user has to enter a pin code to be identified. Only biometrics is able to authenticate a user; yet biometric information is sensitive. To ensure the security and privacy of biometric data, OCC (On-Card-Comparison) has been proposed. This approach consists in storing biometric data in a secure zone on a smartcard and computing the verification decision in a Secure Element (SE). The purpose of this paper is to propose an evaluation platform for testing biometric systems such as the analysis of performance and security on biometric OCC. Based on two examples, we illustrate its different uses in an operationnal context. The first example focus on the ”Quality module” which allows to choose the enrollment by considering the fingerprint quality with one proposed metric. The second one addresses the minutiae reduction of the fingerprint template when the number of minutiae is higher than expected by the OCC.

This article proposes a new quality assessment method of fingerprint, represented by only a set of minutiae points. The proposed quality metric is modeled with the convex-hull and Delaunay triangulation of the minutiae points. The validity of this quality metric is verified on several Fingerprint Verification Competition (FVC) databases by referring to an image-based metric from the state of the art (considered as the reference). The experiments of the utility-based evaluation approach demonstrate that the proposed quality metric is able to generate a desired result. We reveal the possibility of assessing fingerprint quality when only the minutiae template is available.

Biometric sample quality assessment approaches are generally designed in terms of utility property due to the potential difference between human perception of quality and the biometric quality requirements for a recognition system. This study proposes a utility based quality assessment method of fingerprints by considering several complementary aspects: 1) Image quality assessment without any reference which is consistent with human conception of inspecting quality, 2) Textural features related to the fingerprint image and 3) minutiae features which correspond to the most used information for matching. The proposed quality metric is obtained by a linear combination of these features and is validated with a reference metric using different approaches. Experiments performed on several trial databases show the benefit of the proposed fingerprint quality metric.