IVDAS: an interactive visual design and analysis system for image data symmetry detection of CNN models

Journal of Visualization - Convolutional neural networks (CNNs) have achieved breakthrough performance in image recognition and classification. However, it is still a challenge for CNNs to classify...     

A Novel Conflict Management Method Based on Uncertainty of Evidence and Reinforcement Learning for Multi-Sensor Information Fusion

Dempster–Shafer theory (DST), which is widely used in information fusion, can process uncertain information without prior information; however, when the evidence to combine is highly conflicting, it may lead to counter-intuitive results. Moreover, the existing methods are not strong enough to process real-time and online conflicting evidence. In order to solve the above problems, a novel information fusion method is proposed in this paper. The proposed method combines the uncertainty of evidence and reinforcement learning (RL). Specifically, we consider two uncertainty degrees: the uncertainty of the original basic probability assignment (BPA) and the uncertainty of its negation. Then, Deng entropy is used to measure the uncertainty of BPAs. Two uncertainty degrees are considered as the condition of measuring information quality. Then, the adaptive conflict processing is performed by RL and the combination two uncertainty degrees. The next step is to compute Dempster’s combination rule (DCR) to achieve multi-sensor information fusion. Finally, a decision scheme based on correlation coefficient is used to make the decision. The proposed method not only realizes adaptive conflict evidence management, but also improves the accuracy of multi-sensor information fusion and reduces information loss. Numerical examples verify the effectiveness of the proposed method.     

Network-Based Driving Force of National Economic Development: A Social Capital Perspective

Network science has been widely applied in theoretical and empirical studies of global value chain (GVC), and many related articles have emerged, forming many more mature and complete analytical frameworks. Among them, the GVC accounting method based on complex network theory is different from the mainstream economics in both research angle and content. In this paper, we build up global industrial value chain network (GIVCN) models based on World Input–Output Database, introduce the theoretical framework of Social Capital, and define the network-based indicators with economic meanings. Second, we follow the econometric framework to analyze the hypothesis and test whether it is true. Finally, we study how the three types of capital constituted by these indicators interact with each other, and discuss their impact on the social capital (economic development level, i.e., GDP). The results prove that the structural capital (industrial status) has a positive impact on the social capital; the relational capital (industrial correlation) has a positive impact on both social capital and structural capital; the cognitive capital (industrial structure) has a small impact on the social capital, structural capital, and relational capital.     

A Novel Feature Extraction Method for Power Transformer Vibration Signal Based on CEEMDAN and Multi-Scale Dispersion Entropy

Effective diagnosis of vibration fault is of practical significance to ensure the safe and stable operation of power transformers. Aiming at the traditional problems of transformer vibration fault diagnosis, a novel feature extraction method based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and multi-scale dispersion entropy (MDE) was proposed. In this paper, CEEMDAN method is used to decompose the original transformer vibration signal. Additionally, then MDE is used to capture multi-scale fault features in the decomposed intrinsic mode functions (IMFs). Next, the principal component analysis (PCA) method is employed to reduce the feature dimension and extract the effective information in vibration signals. Finally, the simplified features are sent into density peak clustering (DPC) to get the fault diagnosis results. The experimental data analysis shows that CEEMDAN-MDE can effectively extract the information of the original vibration signals and DPC can accurately diagnose the types of transformer faults. By comparing different algorithms, the practicability and superiority of this proposed method are verified.     

Multifractality in Quasienergy Space of Coherent States as a Signature of Quantum Chaos

We present the multifractal analysis of coherent states in kicked top model by expanding them in the basis of Floquet operator eigenstates. We demonstrate the manifestation of phase space structures in the multifractal properties of coherent states. In the classical limit, the classical dynamical map can be constructed, allowing us to explore the corresponding phase space portraits and to calculate the Lyapunov exponent. By tuning the kicking strength, the system undergoes a transition from regularity to chaos. We show that the variation of multifractal dimensions of coherent states with kicking strength is able to capture the structural changes of the phase space. The onset of chaos is clearly identified by the phase-space-averaged multifractal dimensions, which are well described by random matrix theory in a strongly chaotic regime. We further investigate the probability distribution of expansion coefficients, and show that the deviation between the numerical results and the prediction of random matrix theory behaves as a reliable detector of quantum chaos.     

An Adaptive Deblurring Vehicle Detection Method for High-Speed Moving Drones: Resistance to Shake

Vehicle detection is an essential part of an intelligent traffic system, which is an important research field in drone application. Because unmanned aerial vehicles (UAVs) are rarely configured with stable camera platforms, aerial images are easily blurred. There is a challenge for detectors to accurately locate vehicles in blurred images in the target detection process. To improve the detection performance of blurred images, an end-to-end adaptive vehicle detection algorithm (DCNet) for drones is proposed in this article. First, the clarity evaluation module is used to determine adaptively whether the input image is a blurred image using improved information entropy. An improved GAN called Drone-GAN is proposed to enhance the vehicle features of blurred images. Extensive experiments were performed, the results of which show that the proposed method can detect both blurred and clear images well in poor environments (complex illumination and occlusion). The detector proposed achieves larger gains compared with SOTA detectors. The proposed method can enhance the vehicle feature details in blurred images effectively and improve the detection accuracy of blurred aerial images, which shows good performance with regard to resistance to shake.     

Personal Interest Attention Graph Neural Networks for Session-Based Recommendation

Session-based recommendations aim to predict a user’s next click based on the user’s current and historical sessions, which can be applied to shopping websites and APPs. Existing session-based recommendation methods cannot accurately capture the complex transitions between items. In addition, some approaches compress sessions into a fixed representation vector without taking into account the user’s interest preferences at the current moment, thus limiting the accuracy of recommendations. Considering the diversity of items and users’ interests, a personalized interest attention graph neural network (PIA-GNN) is proposed for session-based recommendation. This approach utilizes personalized graph convolutional networks (PGNN) to capture complex transitions between items, invoking an interest-aware mechanism to activate users’ interest in different items adaptively. In addition, a self-attention layer is used to capture long-term dependencies between items when capturing users’ long-term preferences. In this paper, the cross-entropy loss is used as the objective function to train our model. We conduct rich experiments on two real datasets, and the results show that PIA-GNN outperforms existing personalized session-aware recommendation methods.     

Femtosecond laser micromachined optical waveguides in LiTaO3 crystal

By using femtosecond laser micromachining, optical wave guides in both depressed cladding and dual‐line configurations have been produced in LiTaO₃ crystal. The guiding properties and the thermal stability have been investigated for both geometries, which exhibit different performance. Depressed cladding waveguides support guidance along both extraordinary and ordinary index polarizations, while dual‐line waveguides support only extraordinary index polarization. Thermal annealing has been proved to be an effective method to reduce the propagation losses. For the cladding waveguide, the lowest propagation loss was as low as 0.38 dB/cm after the annealing treatment at 400 °C. (© 2013 WILEY‐VCH Verlag GmbH & Co. KGaA, Weinheim)     

CaCu3Ti4O12 陶瓷介电模量响应特性的研究

由于CaCu₃Ti₄O₁₂巨介电常数陶瓷的低频区直流电导较大, 本文采用模量 M"-f频谱表征与分析了低频和高频的两个松弛极化过程. 研究认为, 这两个特征峰属于晶界区Schottky 势垒耗尽层边缘深陷阱的电子松弛过程, 其中高频松弛峰起源于晶粒本征缺陷的电子松弛过程, 而低频松弛峰则为与氧空位有关的松弛极化过程. 对于CaCu₃Ti₄O₁₂这类低频下具有高直流电导的陶瓷材料, 采用模量频谱能更有效地分析研究其损耗极化机理. 关键词： 3Ti₄O₁₂陶瓷')" href="#">CaCu₃Ti₄O₁₂陶瓷 模量 松弛过程 电导     

新型单模大模场红外硫系玻璃光子晶体光纤设计研究

大模场光子晶体光纤在高功率激光传输、光纤放大器、光纤激光器中的广泛应用, 使其受到研究者的广泛关注.硫系玻璃在红外波段(1–20μm)具有优良透过性能, 且具有折射率高(2.0–3.5)、声子能量低(小于350 cm^-1)、 组分可调等特性, 成为制备红外光纤的理想材料. 本文设计一种基于Ge₂₀Sb₁₅Se₆₅硫系玻璃基质的新型单模传输、低损耗、超大模场面积光子晶体光纤结构, 经理论验证其在λ =10.6 μm处基模限制损耗远低于0.1 dB/m, 高阶限制模损耗大于2 dB/m, 模场面积约为13333 μm². 关键词： 硫系玻璃 大模场面积 红外光子晶体光纤 结构设计