Spatial Distribution Feature Extraction Network for Open Set Recognition of Electromagnetic Signal

This paper proposes a novel open set recognition method,the Spatial Distribution Feature Extraction Network(SDFEN),to address the problem of electromagnetic signal recognition in an open environment.The spatial distribution feature extraction layer in SDFEN replaces convolutional output neural networks with the spatial distribution features that focus more on inter-sample information by incorporating class center vectors.The designed hybrid loss function considers both intra-class distance and inter-class distance,thereby enhancing the similarity among samples of the same class and increasing the dissimilarity between samples of different classes during training.Consequently,this method allows unknown classes to occupy a larger space in the feature space.This reduces the possibility of overlap with known class samples and makes the boundaries between known and unknown samples more distinct.Additionally,the feature comparator threshold can be used to reject unknown samples.For signal open set recognition,seven methods,including the proposed method,are applied to two kinds of electromagnetic signal data:modulation signal and real-world emitter.The experimental results demonstrate that the proposed method outperforms the other six methods overall in a simulated open environment.Specifically,compared to the state-of-the-art Openmax method,the novel method achieves up to 8.87%and 5.25%higher micro-F-measures,respectively.

ON THE EXACT HAUSDORFF MEASURE OF A CLASS OF SELF-SIMILAR SETS SATISFYING OPEN SET CONDITION

In this paper, we provide a new effective method for computing the exact value of Hausdorff measures of a class of self-similar sets satisfying the open set condition （OSC）. As applications, we discuss a self-similar Cantor set satisfying OSC and give a simple method for computing its exact Hausdorff measure.

γ-（α,β）-Open Sets and γ-（α,β）-Ti Spaces

We introduce the concept of γ-(α, β)-open sets and the concepts of γ-(α, β)-T_i spaces(i = 0, 1, 2, 3, 4) based on the concept of(α, β)-open sets. We obtain some properties of γ-(α, β)-Tispaces. Furthermore, we study their essential characterization in topological space.

On <i>M</i>-Asymmetric Semi-Open Sets and Semicontinuous Multifunctions in Bitopological Spaces

The purpose of this paper is to introduce the notions of m-asymmetric semiopen sets and M-asymmetric semicontinuous multifunctions defined between asymmetric sets satisfying certain minimal conditions in the framework of bitopological spaces. Some new characterizations of m-asymmetric semiopen sets and M-asymmetric semicontinuous multifunctions will be investigated and several fundamental properties will be obtained.

Weak Form of Fuzzy Open Sets and Their Related Continuity

The aim of this paper is to give a new class of fuzzy open sets called fuzzy pre-γ-open sets in fuzzy topological spaces. Also,a new type of fuzzy continuous functions called,fuzzy pre-γ-continuous functions is introduced and studied.

Improving Open Set Domain Adaptation Using Image-to-Image Translation and Instance-Weighted Adversarial Learning

We propose to address the open set domain adaptation problem by aligning images at both the pixel space and the feature space.Our approach,called Open Set Translation and Adaptation Network(OSTAN),consists of two main components:translation and adaptation.The translation is a cycle-consistent generative adversarial network,which translates any source image to the“style”of a target domain to eliminate domain discrepancy in the pixel space.The adaptation is an instance-weighted adversarial network,which projects both(labeled)translated source images and(unlabeled)target images into a domain-invariant feature space to learn a prior probability for each target image.The learned probability is applied as a weight to the unknown classifier to facilitate the identification of the unknown class.The proposed OSTAN model significantly outperforms the state-of-the-art open set domain adaptation methods on multiple public datasets.Our experiments also demonstrate that both the image-to-image translation and the instance-weighting framework can further improve the decision boundaries for both known and unknown classes.

基于YOLO-OpenMax的水声通信信号开集识别方法

水声通信信号调制方式随着技术进步从典型的传统调制方式发展为水声通信机厂商私有开发的新型调制方式,这使得现有的水声通信信号闭集调制识别技术实用性受到制约,但现阶段鲜有研究基于深度学习的水声通信信号调制方式的开集识别方法。针对此现状,提出一种基于YOLO图像检测识别网络和OpenMax模型的开集识别方法。利用YOLOv5网络的输出特点,将传统OpenMax模型的处理方法进行改进,提出一种两步测试方法,实现了在多径信道下的水声通信信号的开集识别。仿真实验表明:在归一化系数为0.5,信噪比等于10 dB条件下的归一化开集识别准确率达到90%以上,实测数据同样验证了本文方法的有效性。

低空智联网中基于多质心OpenMax的无人机开集识别方法

随着网络化、智能化的发展,无人机(Unmanned aerial vehicles, UAVs)逐渐成为低空智联网(Low-altitude intelligent network, LAIN)的重要组成部分,但如何对低空智联网中的无人机平台进行有效的管理仍面临严峻挑战。基于无人机信号中的细微特征可对无人机进行个体识别,并检测是否为非法无人机,从而实现低空智联网中无人机的身份识别和管理。针对低空领域信道环境复杂且无法提前获取非法无人机信号样本的问题,本文提出了基于差值时频和多质心OpenMax的无人机开集识别方法。首先,提出了与信道无关的差值时频特征来降低多径信道环境对射频指纹(Radio frequency fingerprinting, RFF)特征的影响,并利用数据增强提高了识别模型的准确率和鲁棒性。其次,利用多质心OpenMax替代神经网络Softmax层,以实现无人机个体的开集识别。最后,对神经网络的损失函数进行了改进,提高了开集识别准确率。本文利用真实环境采集的数据对所提算法进行了验证,在多径信道环境中开放度为0.087时,开集识别准确率达到了93.23%,与基准算法相比,准确率分别提高了7.61%和13.4%。本文提出的算法可在复杂信道环境中有效识别无人机个体并检测出首次出现的非法无人机。

Exclusive Fibula Osteosynthesis for Treating Open Fractures Gustillo I-III B of the Distal Half of the Leg Bones in a Resources-Limited Setting

Introduction: Management of open leg bones fractures is a challenging health issue for the surgeon, particularly true in resource-limited settings. In this study, we evaluate exclusive fibular osteosynthesis in the treatment of open fractures of the distal half of the leg bones as a therapeutic option in our context. Methods: This is a prospective, experimental, multicenter study of 30 open fractures of the distal half of the leg bones treated with exclusive fibula osteosynthesis, conducted in 3 hospitals in the DRC from January 1, 2013 to September 30, 2016. Results: The age range of 20 to 40 years grouped 22 (73.4%) patients, the sex ratio was 1:1 and the unemployed were the most involved with 16 (53.3%) cases. The Gustilo II, I, III B and III A types represented 40%, 33.3%, 20% and 6.7%, respectively. The fractures were located in the distal third in 12 (40%) cases, in the middle third in 11 (36.7%) cases, and in both malleoli in 7 cases (23.3%). Osteosynthesis of the fibula by screw plate was applied in 22 (73.3%) patients and pinning in 8 (26.7%). Satisfactory reduction of the tibial fracture site was achieved in 29 (96.7%) cases and 100% bone healing was achieved within an average of 10 weeks. Four (13.3%) loss of alignment, 1 (3.3%) infection, 1 (3.3%) skin necrosis and 2 (6.7%) ankle stiffness complicated our fractures. Conclusion: Exclusive osteosynthesis of the fibula as a common technique for fractures of the distal half of the leg bones allowed us to reduce, immobilize and consolidate the tibial fracture in the required time and to preserve the mobility of the ankle.

THE EXPLICIT SOLUTIONS OF C_(p,q)^(k+α)-FORM FOR THE -EQUATIONS ON PSEUDOCONVEX OPEN SETS

In this paper, we study the integral solution operators for the -equations on pseudoconvex domains. As a generalization of [1] for the -dequations on pseudoconvex domains with boundary of class C∞, we obtain the explicit integral operator solutions of C -form for the -equations on pseudoconvex open sets with boundary of Ck (k≥0) and the sup-norm estimates of which solutions have similar as that [1] in form.

Pointwise dimensions of general Moran measures with open set condition

Recently Lou and Wu obtained the formulas of pointwise dimensions of some Moran measures on Moran sets in Rd under the strong separation condition.In this paper,we prove that the result is still true under the open set condition.Due to the lack of the strong separation condition,our approach is essentially different from that used by Lou and Wu.We also obtain the formulas of the Hausdorff and packing dimensions of the Moran measures and discuss some interesting examples.

Robust Set Stabilization and Its Instances for Open Quantum Systems

We propose and discuss a novel concept of robust set stabilization by permissible controls; this concept is helpful when dealing with both a priori information of model parameters and different permissible controls including quantum measurements. Both controllability and stabilization can be regarded as the special case of the novel concept. An instance is presented for a kind of uncertain open quantum systems to further justify this gen- eralized concept. It is underlined that a new type of hybrid control based on periodically perturbed projective measurements can be the permissible control of uncertain open quantum systems when perturbed projective measurements are available. The sufficient conditions are given for the robust set stabilization of uncertain quantum open systems by the hybrid control, and the design of the hybrid control is reduced to selecting the period of measurements.

基于可穿戴设备的开放集动作识别技术研究

随着智能手表、手环等可穿戴设备的普及,将其用于人体行为识别领域并从中解码出人类行为活动,对于健康监测、日常行为分析、智能家居等应用具有重要意义。然而,传统的动作识别算法存在特征提取困难、识别准确率较低等问题,并且均基于封闭集假设,即所有的训练数据和测试数据均来自同一个标签空间,而现实世界中大多都是开放集(Open-Set)场景,在测试阶段可能会将未知标签样本送入模型,从而导致分类错误。文中针对人体动作识别问题,提出了多通道自适应卷积网络(Multi-channel Adaptive Convolutional Network,MCACN),针对传统CNN网络特征提取仅局限于一个小范围内的问题,自适应卷积模块能够使用不同大小的卷积核提取不同时间跨度的特征,并自动计算权重求和。此外MCACN的多通道结构使各传感器数据得以分头进行处理,获得能够区分相近动作的特征细节。最后,设计了基于标签的多元变分自编码器,提出了用于开放集识别的模型MCACN-VAE。该模型能够通过计算重建误差来识别未知类,聚焦于已知类别动作,提高了模型的健壮性。实验结果表明,在封闭集实验中,MCACN模型能够有效地对动作进行识别,对7种日常动作的识别准确率均达到了91%以上,总体准确率达到了95%。在开放集实验中,MCACN-VAE在不同开放度下对于已知类别的总体识别准确率均达到了89%以上,对于未知动作片段的识别准确率也保持在75%以上,证明了所提模型能够有效拒绝未知类,识别已知类。

基于原型对比学习的开放集识别方法

开放集识别的目标是识别出未知类样本,同时保持对已知类样本的分类能力.现有的判别式开放集识别方法忽视了已知类过度占用特征空间和模型训练过程缺乏未知类信息的问题,导致未知类样本容易被误分类为已知类.为此,提出一种结合原型对比学习的开放集识别方法.引入对比学习和类原型理论,使用编码器和投影网络对开放集识别问题进行建模,设计原型对比损失函数,使用梯度下降法学习模型参数,最小化样本与其对应的类原型之间的距离和最大化样本与其他类原型间的距离,促使样本在特征空间中向类原型靠近,从而缓解已知类过度占用特征空间的问题.此外,设计混合样本对比损失函数,提出样本生成方法OSR-Mix以生成未知类样本,从而在模型训练过程有效地补充未知类信息.在4个公开数据集上的实验结果表明,与主流的开放集识别方法相比,本文提出的方法在AUROC和F1分数上均有明显的优势.

公共数据开放如何促进数字化发展——基于模糊集定性比较分析的研究

随着新一代信息通信技术和计算技术的迅速发展,公共数据在经济、社会、行政、科学研究等领域发挥着越来越重要的作用。为帮助人们理解公共数据开放如何促进数字化发展,文章借助中国内地31个省份的国家统计数据和部分研究者开发的评估数据,利用模糊集定性比较分析方法,研究公共数据开放与其他因素共同推动数字化发展的途径。结果表明:公共数据开放可以与其他因素相结合,共同推动数字化发展。公共数据开放主要通过3条途径促进数字化发展,即研发经费投入型路径、市场规模拉动型路径、数字技术应用型路径。

基于Gem5的CM3仿真器的研究与实现

在嵌入式领域,业界主要使用ARM公司Keil系列仿真工具进行ARM嵌入式系统开发,芯片仿真是其重要功能之一。然而ARM Keil是国外商业软件,购买License价格不菲,且仿真器也是影响芯片验证和软件开发的关键技术之一。针对上述情况,以Cortex-M3芯片为例设计了一种基于开源模拟器Gem5的系统调用仿真方法。首先,分析Gem5模拟器的源码结构、运行过程以及指令集仿真流程,描述Gem5仿真原理。然后,通过为Gem5添加Cortex-M3寄存器和指令集支持实现Cortex-M3在Atomic SimpleCPU的SE(System Emulation)模式下的仿真。最后,设计了灵活可扩展的指令集自动化测试工具,以验证指令功能是否正确仿真。实验结果表明,经过充分测试实现的仿真器能够正确仿真,且仿真效率较高,提供了一种开源、技术可控的Cortex-M3的软仿真方案。

面向开集识别的稳健测试时适应方法

开集识别旨在研究测试阶段突现未见类别对于机器学习模型的挑战,以期学习模型既能分类已见类别又可识别/拒绝未见类别,是确保机器学习模型能够在开放世界中高效稳健部署的重要技术.既有开集识别技术通常假设已见类别的协变量分布在训练与测试阶段维持不变.然而在实际场景中,类别的协变量分布常不断变化.直接利用既有技术不再奏效,其性能甚至劣于基线方案.因此,亟需研究新型开集识别方法,使其能不断适应协变量分布偏移,以期模型在测试阶段既能稳健分类已见类别又可识别未见类别.将此新问题设置命名为开放世界适应问题(AOW),并提出了一种开放测试时适应方法(OTA).该方法基于无标注测试数据优化自适应熵损失与开集熵损失更新模型,维持对已见类的既有判别能力,同时增强了识别未见类的能力.大量实验分析表明,该方法在多组基准数据集、多组不同协变量偏移程度下均稳健地优于现有先进的开集识别方法.

开放式创新社区治理机制对用户知识共享行为的影响——基于fsQCA的双平台对比分析

基于平台治理视角,选择以小米为代表的互联网企业和以华为为代表的科技型企业创立的开放式创新社区为研究对象,运用模糊集定性比较分析法(fsQCA),对两类社区治理机制影响用户知识共享行为的多重路径进行对比分析。研究发现,社区监管是两类社区实现高知识共享行为的共同必要条件;二者存在一个由引导机制和约束机制构成的一致组态;用户嵌入、知识保护在促进二者知识共享行为中的作用存在差异。

局部一致性主动学习的源域无关开集域自适应

无监督域自适应在解决训练集(源域)和测试集(目标域)分布不一致的问题上已经取得了一定的成功.在面向低能耗场景和开放动态任务环境时,在资源约束和开放类别出现的情况下,现有的无监督域自适应方法面临着严峻的挑战.源域无关开集域自适应(SF-ODA)旨在将源域模型中的知识迁移到开放类出现的无标签目标域,从而在无源域数据资源的限制下辨别公共类和检测开放类.现有的源域无关开集域自适应的方法聚焦于设计准确检测开放类别的源域模型或增改模型的结构.但是,这些方法不仅需要额外的存储空间和训练开销,而且在严格的隐私保护场景下难以实现.提出了一个更加实际的场景:主动学习的源域无关开集域自适应(ASF-ODA),目标是基于一个普通训练的源域模型和少量专家标注的有价值的目标域样本来实现鲁棒的迁移.为了达成此目标,提出了局部一致性主动学习(LCAL)算法.首先,利用目标域中局部特征标签一致的特点,LCAL设计了一种新的主动选择方法:局部多样性选择,来挑选更有价值的阈值模糊样本来促进开放类和公共类分离.接着,LCAL基于信息熵初步筛选出潜在的公共类集合和开放类集合,并利用第一步得到的主动标注样本对这两个集合进行匹配纠正,得到两个对应的可信集合.最后,LCAL引入开集损失和信息最大化损失来进一步促使公共类和开放类分离,引入交叉熵损失来实现公共类的辨别.在Office-31、Office-Home和VisDA-C这3个公开的基准数据集上的大量实验表明:在少量有价值的目标域样本的帮助下,LCAL不仅显著优于现有的源域无关开集域自适应方法,还大幅度超过了现有的主动学习方法的表现,在某些迁移任务上可以提升20%.

基于迁移学习的齿轮箱开放集跨工况故障诊断

随着工业与航空航天技术的不断发展,齿轮箱等旋转机械的工况与故障模式逐渐趋于多样化、复杂化,可靠性与安全性问题日益突出,大量工况数据缺乏故障标签,且不同工况间故障模式不对称,迫切需要研究有效的故障诊断方法。以齿轮箱为案例验证对象,设置跨工况和开放集故障诊断场景,针对目标工况故障标签匮乏的问题,提出利用迁移学习将源工况的知识迁移到目标工况,利用交叉熵分类损失函数对已知故障类型进行识别的方法;针对跨工况条件下故障模式不对称的开放集问题,提出利用卷积神经网络提取工况间的相似数据特征,利用二分类损失函数对目标工况的已知类与未知类进行分类的方法。提出联合损失函数,训练诊断模型,实现故障特征从源域到目标域的联合迁移。案例分析结果表明:所提方法能够实现开放集情况下的跨工况故障诊断,且平均诊断准确度在90%以上。