基于时频域融合和ECA-1DCNN的航空串联故障电弧检测

为了快速准确地检测航空交流线路中出现的串联故障电弧,提出了一种基于时频域融合和加入高效注意力机制(efficient channel attention, ECA)的一维卷积神经网络(one-dimensional convolutional neural network, 1DCNN)的故障检测算法。首先,搭建航空交流电弧故障实验平台,负载选择多类型、多参数值进行电流信号的采集;其次,为了保留更多的故障信息,分析其特征频段,经过大量数据验证,航空串联电弧在发生时,1 000～4 000 Hz分量具有一定的占比,因此将原始信号与特征频段进行融合,融合后的一维数据作为模型输入;最后,搭建ECA-1DCNN检测模型,进行训练,并通过K折交叉验证模型的有效性,得到测试集平均准确率为97.96%。该方法网络层数较少,计算快速,避免了复杂时频域计算过程,较为智能,对航空串联电弧检测装置的研究提供了理论参考。     

Closed queueing networks with batch services

In this paper we study queueing networks which allow multiple changes at a given time. The model has a natural application to discrete-time queueing networks but describes also queueing networks in continuous time. It is shown that product-form results which are known to hold when there are single changes at a given instant remain valid when multiple changes are allowed.     

基于人工神经网络的商业银行信用风险模型

在对人工神经网络的基本原理进行简要介绍的基础上 ,着重对构建商业银行信用风险的人工神经网络模型进行了研究 ,实证结果表明 ,人工神经网模型具有很高的预测精度     

A highly clustered scale-free network evolved by random walking

In present paper, we propose a highly clustered weighted network model that incorporates the addition of a new node with some links, new links between existing nodes and the edge's weight dynamical evolution based on weight-dependent walks at each time step. The analytical approach and numerical simulation show that the system grows into a weighted network with the power-law distributions of strength, weight and degree. The weight-dependent walk length l will not influence the strength distribution, but the clustering coefficient of the network is sensitive to l. Particularly, the clustering coefficient is especially high and almost independent of the network size when l=2.     

Investigation of lengthscales, scalar dissipation, and flame orientation in a piloted diffusion flame by LES

This work investigates the structure of a diffusion flame in terms of lengthscales, scalar dissipation, and flame orientation by using large eddy simulation. This has been performed for a turbulent, non-premixed, piloted methane/air jet flame (Flame D) at a Reynolds-number of 22,400. A steady flamelet model, which was represented by artificial neural networks, yields species mass fractions, density, and viscosity as a function of the mixture fraction. This will be shown to suffice to simulate such flames. To allow to examine scalar dissipation, a grid of 1.97 × 10⁶ nodes was applied that resolves more than 75% of the turbulent kinetic energy. The accuracy of the results is assessed by varying the grid-resolution and by comparison to experimental data by Barlow, Frank, Karpetis, Schneider (Sandia, Darmstadt), and others. The numerical procedure solves the filtered, incompressible transport equations for mass, momentum, and mixture fraction. For subgrid closure, an eddy viscosity/diffusivity approach is applied, relying on the dynamic Germano model. Artificial turbulent inflow velocities were generated to feature proper one- and two-point statistics. The results obtained for both the one- and two-point statistics were found in good agreement to the experimental data. The PDF of the flame orientation shows the tilting of the flame fronts towards the centerline. Finally, the steady flamelet approach was found to be sufficient for this type of flame unless slowly reacting species are of interest.     

少节点基因调控网络的控制

近年来,自组织振荡网络受到越来越多科学家的关注,对生物体的生长、发育起调控作用的基因调控网络即是其中的一种.本文研究了少节点基因调控网络的控制问题.运用多相位超前驱动方法对该种网络进行调控,可以有效地提高对网络的控制效率.通过数值模拟,发现对于少节点基因调控网络,当系统参数确定时,网络的有效控制率可以达到95％以上(10节点网络);当系统参数不确定时,控制的效率也非常高.     

季节因素对气候网络影响研究

气候网络在地球科学领域研究中是一个新的热点,对于分析和揭示气候场的特征及关联结构具有较强优势.已有气候网络的构建一般选取冬季月份的样本数据,而且在研究中忽略了其他季节月份对气候网络的影响.本文研究了季节因素对气候网络的影响,研究发现:气候网络在不同季节的整体特征参数基本保持稳定,但是网络社团结构以及局部节点拓扑连接随季节变化显著.可以利用这一结论来研究不同季节全球遥相关模态变化情况以及局部地区气候特征随季节变化情况.     

具有随机节点结构的复杂网络同步研究

针对具有随机节点结构的复杂网络, 研究其同步问题. 基于Lyapunov稳定性理论和线性矩阵不等式技术给出了复杂网络同步稳定的充分性条件, 该充分性条件不仅与复杂网络的状态时延有关, 还与节点结构的概率分布有关. 数值仿真表明本文方法的有效性. 关键词： 复杂网络 随机节点 同步稳定 时滞     

A Probabilistic Re-Intepretation of Confidence Scores in Multi-Exit Models

In this paper, we propose a new approach to train a deep neural network with multiple intermediate auxiliary classifiers, branching from it. These ‘multi-exits’ models can be used to reduce the inference time by performing early exit on the intermediate branches, if the confidence of the prediction is higher than a threshold. They rely on the assumption that not all the samples require the same amount of processing to yield a good prediction. In this paper, we propose a way to train jointly all the branches of a multi-exit model without hyper-parameters, by weighting the predictions from each branch with a trained confidence score. Each confidence score is an approximation of the real one produced by the branch, and it is calculated and regularized while training the rest of the model. We evaluate our proposal on a set of image classification benchmarks, using different neural models and early-exit stopping criteria.     

Permutation Entropy-Based Interpretability of Convolutional Neural Network Models for Interictal EEG Discrimination of Subjects with Epileptic Seizures vs. Psychogenic Non-Epileptic Seizures

The differential diagnosis of epileptic seizures (ES) and psychogenic non-epileptic seizures (PNES) may be difficult, due to the lack of distinctive clinical features. The interictal electroencephalographic (EEG) signal may also be normal in patients with ES. Innovative diagnostic tools that exploit non-linear EEG analysis and deep learning (DL) could provide important support to physicians for clinical diagnosis. In this work, 18 patients with new-onset ES (12 males, 6 females) and 18 patients with video-recorded PNES (2 males, 16 females) with normal interictal EEG at visual inspection were enrolled. None of them was taking psychotropic drugs. A convolutional neural network (CNN) scheme using DL classification was designed to classify the two categories of subjects (ES vs. PNES). The proposed architecture performs an EEG time-frequency transformation and a classification step with a CNN. The CNN was able to classify the EEG recordings of subjects with ES vs. subjects with PNES with 94.4% accuracy. CNN provided high performance in the assigned binary classification when compared to standard learning algorithms (multi-layer perceptron, support vector machine, linear discriminant analysis and quadratic discriminant analysis). In order to interpret how the CNN achieved this performance, information theoretical analysis was carried out. Specifically, the permutation entropy (PE) of the feature maps was evaluated and compared in the two classes. The achieved results, although preliminary, encourage the use of these innovative techniques to support neurologists in early diagnoses.