LAMOST的“Unknown”光谱分类研究:ODS-YOLOv7模型

天体识别是天文新发现和深入研究天体的基础。在LAMOST DR8 v1.0发布的低分辨率光谱数据中有约53万条因没有类别标签而被命名为“Unknown”的光谱,其中有88.56%的光谱信噪比在0~10之间,对这批光谱的研究分析将增加LAMOST的有效数据产出。该研究为“Unknown”光谱的分类设计了一种ODS-YOLOv7模型。它是一种端到端的类别预测模型,通过添加一维卷积注意力模块以提高光谱识别能力。在经过一批信噪比在0~10之间的已知类别光谱训练后,ODS-YOLOv7可以学习到低信噪比光谱的有效特征,进而实现对“Unknown”光谱的类别预测。实验表明,该模型在已知类别标记的低信噪比恒星、星系、类星体的光谱识别中,F1-score分别为0.98、0.95、0.95;同时在与传统算法KNN、RF、DT、SVM和深度学习算法1D CNN、1DSSCNN、ResNet、DenseNet、VIT对比实验中取得相对最好的效果。实验结果还给出了ODS-YOLOv7模型对DR8 v1.0中信噪比在0~10的“Unknown”光谱预测置信度分布,在预测类别为恒星、星系、类星体任务中,有92%的分类置信度在60%以上。为保证模型输出质量,本文只选取分类置信度大于99%的光谱类别作为输出结果。以此为依据,在DR8 v1.0和DR9 v0发布的全部“Unknown”光谱中分别有37.19%和47.03%被ODS-YOLOv7模型预测出类别。此外,还增加人工认证以检验该模型预测的正确性。为提升模型的可解释性,参照了二维图像特征可视化的Grad-CAM方法,将其改进为适合于可视化一维光谱数据特征的算法。其结果表明该模型可自动关注到不同的分类特征,使得该模型非常适用于低信噪比“Unknown”光谱的类别预测。

Data-Based Filters for Non-Gaussian Dynamic Systems With Unknown Output Noise Covariance

This paper proposes linear and nonlinear filters for a non-Gaussian dynamic system with an unknown nominal covariance of the output noise.The challenge of designing a suitable filter in the presence of an unknown covariance matrix is addressed by focusing on the output data set of the system.Considering that data generated from a Gaussian distribution exhibit ellipsoidal scattering,we first propose the weighted sum of norms(SON)clustering method that prioritizes nearby points,reduces distant point influence,and lowers computational cost.Then,by introducing the weighted maximum likelihood,we propose a semi-definite program(SDP)to detect outliers and reduce their impacts on each cluster.Detecting these weights paves the way to obtain an appropriate covariance of the output noise.Next,two filtering approaches are presented:a cluster-based robust linear filter using the maximum a posterior(MAP)estimation and a clusterbased robust nonlinear filter assuming that output noise distribution stems from some Gaussian noise resources according to the ellipsoidal clusters.At last,simulation results demonstrate the effectiveness of our proposed filtering approaches.

A Novel Intrusion Detection Model of Unknown Attacks Using Convolutional Neural Networks

With the increasing number of connected devices in the Internet of Things(IoT)era,the number of intrusions is also increasing.An intrusion detection system(IDS)is a secondary intelligent system for monitoring,detecting and alerting against malicious activity.IDS is important in developing advanced security models.This study reviews the importance of various techniques,tools,and methods used in IoT detection and/or prevention systems.Specifically,it focuses on machine learning(ML)and deep learning(DL)techniques for IDS.This paper proposes an accurate intrusion detection model to detect traditional and new attacks on the Internet of Vehicles.To speed up the detection of recent attacks,the proposed network architecture developed at the data processing layer is incorporated with a convolutional neural network(CNN),which performs better than a support vector machine(SVM).Processing data are enhanced using the synthetic minority oversampling technique to ensure learning accuracy.The nearest class mean classifier is applied during the testing phase to identify new attacks.Experimental results using the AWID dataset,which is one of the most common open intrusion detection datasets,revealed a higher detection accuracy(94%)compared to SVM and random forest methods.

Unknown DDoS Attack Detection with Fuzzy C-Means Clustering and Spatial Location Constraint Prototype Loss

Since its inception,the Internet has been rapidly evolving.With the advancement of science and technology and the explosive growth of the population,the demand for the Internet has been on the rise.Many applications in education,healthcare,entertainment,science,and more are being increasingly deployed based on the internet.Concurrently,malicious threats on the internet are on the rise as well.Distributed Denial of Service(DDoS)attacks are among the most common and dangerous threats on the internet today.The scale and complexity of DDoS attacks are constantly growing.Intrusion Detection Systems(IDS)have been deployed and have demonstrated their effectiveness in defense against those threats.In addition,the research of Machine Learning(ML)and Deep Learning(DL)in IDS has gained effective results and significant attention.However,one of the challenges when applying ML and DL techniques in intrusion detection is the identification of unknown attacks.These attacks,which are not encountered during the system’s training,can lead to misclassification with significant errors.In this research,we focused on addressing the issue of Unknown Attack Detection,combining two methods:Spatial Location Constraint Prototype Loss(SLCPL)and Fuzzy C-Means(FCM).With the proposed method,we achieved promising results compared to traditional methods.The proposed method demonstrates a very high accuracy of up to 99.8%with a low false positive rate for known attacks on the Intrusion Detection Evaluation Dataset(CICIDS2017)dataset.Particularly,the accuracy is also very high,reaching 99.7%,and the precision goes up to 99.9%for unknown DDoS attacks on the DDoS Evaluation Dataset(CICDDoS2019)dataset.The success of the proposed method is due to the combination of SLCPL,an advanced Open-Set Recognition(OSR)technique,and FCM,a traditional yet highly applicable clustering technique.This has yielded a novel method in the field of unknown attack detection.This further expands the trend of applying DL and ML techniques in the development of intrusion detection systems and cybersecurity.Finally,implementing the proposed method in real-world systems can enhance the security capabilities against increasingly complex threats on computer networks.

Practical prescribed-time tracking control for uncertain strict-feedback systems with guaranteed performance under unknown control directions

In this paper,we consider the practical prescribed-time performance guaranteed tracking control problem for a class of uncertain strict-feedback systems subject to unknown control direction.Due to the existence of unknown nonlinearities and uncertainties,it is challenging to design a controller that can ensure the stability of closed-loop system within a predetermined finite time while maintaining the specified transient performance.The underlying problem becomes further complex as the control directions are unknown.To deal with the above problems,a special translation function as well as Nussbaum type function are introduced in the prescribed performance control(PPC)framework.Finally,a PPC as well as preset finite time tracking control scheme is designed,and its effectiveness is confirmed by both theoretical analysis and numerical simulation.

Subspace Identification for Closed-Loop Systems With Unknown Deterministic Disturbances

This paper presents a subspace identification method for closed-loop systems with unknown deterministic disturbances.To deal with the unknown deterministic disturbances,two strategies are implemented to construct the row space that can be used to approximately represent the unknown deterministic disturbances using the trigonometric functions or Bernstein polynomials depending on whether the disturbance frequencies are known.For closed-loop identification,CCF-N4SID is extended to the case with unknown deterministic disturbances using the oblique projection.In addition,a proper Bernstein polynomial order can be determined using the Akaike information criterion(AIC)or the Bayesian information criterion(BIC).Numerical simulation results demonstrate the effectiveness of the proposed identification method for both periodic and aperiodic deterministic disturbances.

Acute hepatitis of unknown etiology in an adult female:A case report

BACKGROUND Acute liver injury(ALI)refers to inflammation of the hepatic parenchyma without hepatic encephalopathy that lasts less than 6 mo.When the etiology is unknown,Acute Hepatitis of Unknown Origin(AHUO)can present as a diagnostic and treatment challenge.AHUO in the adult population is unusual and poorly documented.It has an incidence between 11%and 75%.Currently,no treatment guidelines exist.With no identified cause,treatment is often blind,and the wrong treatment plan may have unintended consequences.CASE SUMMARY We present the case of a 58-year-old woman who presented to the emergency room for elevated liver function tests(LFTs).Her symptoms started 10 d prior to admission and included nausea,vomiting,jaundice,decreased appetite,weight loss of 10 lbs,and dark urine.She denied drinking alcohol or taking any hepatotoxic agents,including acetaminophen,statins,vitamins,or supplements.She was admitted to the hospital,and an etiologic work-up was carried out.Her initial bloodwork revealed elevated liver enzymes(alanine aminotransferase 2500 U/L,aspartate aminotransferase 3159 U/L,and alkaline phosphatase 714 U/L)and elevated total bilirubin of 6.4 mg/dL.She tested negative for common infectious etiologies such as hepatotropic viruses A,B,C,and E.Further infective work-up revealed negative serology for cytomegalovirus,Epstein-Barr virus,herpes simplex virus 1&2,and human immunodeficiency virus.Her autoanti-body test results were negative,including anti-smooth muscle antibody,anti-mitochondrial antibody,and anti-liver kidney microsome 1 antibody.Magnetic resonance cholangiopancreatography ruled out biliary causes of elevated LFTs,and her core liver biopsy proved inconclusive.Over the course of her hospital stay,the patient's LFTs improved with supportive care and without steroids.CONCLUSION Idiopathic hepatitis makes treatment challenging.It can leave patients feeling confused and unfulfilled.Thus,educating the patient thoroughly for shared decision-making and management becomes essential.

具有未知时变参数城轨列车的精准停车鲁棒控制

列车运行情况复杂多变,使得列车质量、基本运行阻力及线路状况等参数难以精确获得且随着列车运行存在明显的时变特性。列车模型参数的不确定性和时变特性会对列车的精准停车性能产生重要的影响。在动车组多质点动力学模型的基础上,根据Lyapunov再设计方法设计了一种非线性列车鲁棒控制器。该控制器将系统中的不确定性因素视为等价干扰,并设计相应的鲁棒补偿项。根据参数的先验区间,设计的鲁棒补偿项能够抑制模型估计误差,使得列车的位置和速度跟踪误差快速收敛,最终实现精准停车的控制目标;同时,也证明了系统的最终一致有界稳定性。最后,选取城市轨道交通场景进行仿真验证,仿真结果表明:本文提出的控制方法在列车模型参数未知且时变情景下也能实现对期望停车曲线的快速、精确追踪,表现出较强的鲁棒特性。

基于超声子宫内膜容受性参数和淋巴细胞免疫表型对复发性流产再孕早期流产的影响因素分析

目的基于超声子宫内膜容受性参数和淋巴细胞免疫表型探究不明原因复发性流产患者再妊娠后妊娠结局的影响因素。方法选择2022年4-8月南通市妇幼保健院收治的不明原因复发性自然流产再次妊娠患者166例。根据妊娠结局分为成功分娩组和再次流产组,检测子宫内膜容受性参数及外周血T淋巴细胞,筛查不明原因复发性流产患者再次妊娠流产的影响因素。结果166例患者中成功分娩102例(61.45%),再次流产64例(38.55%)。成功分娩组患者的子宫内膜厚度、内膜容积、血管化血流指数(VFI)均高于再次流产组(P<0.05)。成功分娩组患者的CD4^(+)、CD4^(+)/CD8^(+)低于再次流产组(P<0.05)。CD4^(+)、CD4^(+)/CD8^(+)是妊娠失败的危险因素(P<0.05),子宫内膜厚度、内膜容积、VFI是妊娠失败的保护因素(P<0.05)。结论不明原因复发性流产患者再妊娠的妊娠结局与子宫内膜厚度、内膜容积、VFI、CD4^(+)、CD4^(+)/CD8^(+)有关。

真空泵用屏蔽电机无传感器残压重投控制策略

针对真空干泵机组故障、生产工艺需要等原因影响真空设备产线在线运行时间的问题,研究真空干泵用屏蔽式感应电机带速重投策略,寻求重投的有利时刻以保证带速重投的成功,对电机断电后的转速和定子失电残压特性展开研究。为此,根据屏蔽感应电机空间向量模型,建立基于电压电流混合磁链观测的无速度传感器估算模型、推导电机断电期间的转速估算方法以及定子失电残压解析式。通过重点研究定子残压和虚拟重投电压间幅值特性和相角特性,确定控制系统的首次重投点和其次重投点。以4 kW真空干泵用屏蔽感应电机机组为例,通过模型仿真和失电残压实验验证了该控制方法在泵类工程中有较好的适用性和准确性,重投阶段的转速稳定时间为0.5 s以内,重投阶段的冲击电流平均减小59.18%。

基于未知风荷载作用下拉索振动位移的拉索MR阻尼器失效破坏的原位识别方法

MR阻尼器在长期服役过程中可能由于各种因素导致阻尼器失效破坏。现有的对MR阻尼器的性能识别多为离线方法,需将阻尼器从斜拉索上拆卸下来后进行人工检测。该文提出一种基于斜拉索在未知风荷载作用下振动位移,对在役失效无模型的MR阻尼器作用力进行原位在线识别的方法。首先,建立模态坐标下斜拉索-阻尼器系统运动方程及观测方程,并进行模态截断以减少未知变量的数量。然后,将模态风荷载建模为随机游走过程并加入系统的增广状态中,并视MR阻尼器的作用力视为作用在斜拉索上的‘附加未知输入’,采用最近提出的无直接反馈的平滑最小方差无偏Bayesian滤波,对结构增广状态和MR阻尼器作用力进行识别。通过识别数值模拟的MR阻尼器三种典型的失效破坏模式,验证所提方法的有效性。

ZNF772甲基化及HR-HPV检测在意义不明的非典型鳞状细胞病人分流中的意义

目的:探讨锌指蛋白(ZNF)772甲基化及高危型人乳头瘤病毒(HR-HPV)检测在意义不明的非典型鳞状细胞(ASCUS)病人分流中的意义。方法:选取初筛ASCUS病人195例,均接受HC2-HPV-DNA检测及ZNF772基因DNA甲基化检测;比较宫颈上皮内瘤样变(CIN)Ⅱ及以上与CINⅡ以下、CINⅢ及以上及CINⅢ以下病人ZNF772基因位点甲基化水平的差异,并评估ZNF772甲基化水平及HR-HPV对ASCUS病人CINⅡ及以上、CINⅢ及以上的分流价值。结果:病理学检查显示,195例ASCUS病人中炎症80例(41.03%)、CINⅠ64例(32.82%)、CINⅡ29例(14.87%)、CINⅢ/CIS/AIS 18例(9.23%)、SCC/AC 4例(2.05%)。HR-HPV(HC2)阳性141例(72.31%)、HR-HPV(HC2)阴性54例(27.69%);CINⅡ及以上病人HR-HPV(HC2)阳性检出率高于CINⅡ以下(P<0.05);CINⅢ及以上病人HR-HPV(HC2)阳性检出率高于CINⅢ以下(P<0.05)。CINⅡ及以上、CINⅢ及以上病人ZNF772基因-420、-422位点甲基化水平分别高于CINⅡ以下、CINⅢ以下病人(P<0.05)。ZNF772基因-420、-422位点甲基化水平及HR-HPV诊断CINⅡ及以上的AUC(95%CI)分别为0.867(0.811~0.911)、0.806(0.743~0.859)、0.777(0.712~0.834),诊断CINⅢ及以上的AUC(95%CI)分别为0.891(0.838~0.931)、0.868(0.813~0.912)、0.780(0.716~0.836)。ZNF772基因-420位点甲基化水平诊断CINⅡ及以上、CINⅢ及以上的AUC面积最大。结论:相较于HC2-HPV-DNA检测,ZNF772甲基化检测更能准确地识别ASCUS中CINⅡ及以上、CINⅢ及以上病变病人,有望成为分流ASCUS的有效替代手段。

多域特征提取结合AdaBoost的含未知故障提速道岔故障诊断方法

针对提速道岔未知新故障误判影响列车安全运行及道岔检修效率的问题,提出一种基于多域特征提取和自适应提升算法(Adaptive boosting, adaboost)的信号分析及故障诊断模型。首先,为了深入挖掘道岔的故障特征,分别从时域、频域及时频域提取故障特征,构造原始特征集;然后根据AdaBoost模型获得的特征重要度排序构造不同特征数量的分类模型,并利用模型分类精度进一步获得最佳特征子集;最后将最佳特征子集输入含判定机制的AdaBoost故障诊断模型,完成对提速道岔含未知故障类型的诊断,同时,通过对模型的再训练,实现了对现有故障诊断模型的自适应更新。结果表明:本文方法在有效提取故障特征,提高道岔已知类故障诊断精度的同时,可以有效地识别出道岔之前未出现的新故障。

基于未知输入观测器的电液执行器容错控制研究

电液执行器(EHA)中的传感器或执行器故障,会导致系统不稳定,存在安全隐患。为了解决这些问题,提出并研发了一种用于EHA的容错控制补偿技术。建立其数学模型,利用PID控制器进行位置跟踪控制,通过重构的未知输入观测器实现对干扰和传感器故障的诊断和误差补偿;利用容错控制补偿技术,可以提高EHA运行的可靠性和稳定性,确保控制器的稳定性及其跟踪性能。通过数值模拟和实验,证明了所研发的容错控制补偿技术的有效性。

神经网络阻尼比模型及工业机器人导纳控制

在工业机器人打磨过程中,环境刚度随未知环境的变化,将对力控制精度产生不利的影响,针对环境刚度变化的问题,该文提出一种基于神经网络阻尼比模型的自适应导纳控制方法。在导纳控制设计中,根据力误差与系统阻尼比之间的机理关系,设计激励函数,构造神经网络阻尼比模型;通过该模型使阻尼比在线调整,适应末端环境的刚度变化,实现力到位置自适应转换的导纳控制。与常规导纳控制进行仿真比较,结果表明所提出的力控制策略力误差更小,响应速度更快,能适应变刚度的未知打磨环境。

基于神经网络参数自学习的阻抗控制

针对机器人在打磨过程中环境刚度和位置未知,传统的阻抗控制难以有效保持打磨质量的问题,提出了一种基于调节参数神经网络自学习的阻抗控制。由于基于李雅普诺夫稳定性理论设计的阻尼参数补偿方法中调节参数的选取直接影响系统的控制性能,根据阻尼补偿的数学描述,构建神经网络,用于其参数自适应调节,设计不同的激励函数用于反映阻尼在多种因素影响下变化的特征。通过所搭建的神经网络在线学习,实现参数的优化,以适应打磨过程环境变化。在斜面、平面及曲面等不同环境下,考虑其刚度突变、刚度动态变化、期望力动态变化等因素的仿真实验,结果表明所提出的控制方法与传统控制方法相比,具有更小的超调和稳态误差,并能够适应环境参数未知的情况,明显提高打磨质量和效率。

物联网双层耦合动力学信息传播模型研究

信息传播模型的研究是物联网领域的重要组成部分,它有助于提高物联网系统的性能和效率,促进物联网技术的进一步发展,针对物联网通信中影响信息传播的因素复杂且不稳定的问题,该文提出一种双层耦合信息传播模型SIVR-UAD,通过分析物联网中不同状态的设备和用户对信息传播的影响,建立了6种耦合状态,并利用马尔科夫方法分析耦合节点的状态变化过程,找到信息传播平衡点,最后通过理论分析证明了模型的平衡点的唯一性以及稳定性。仿真结果表明,在3组不同的初始耦合节点数下,SIVR-UAD模型中的6种耦合节点数量变化始终趋向同一稳定水平,证明了该模型的平衡点和稳定性。

智慧网络大规模未知访问源的安全性预警研究

由于智慧网络环境具有复杂性和动态性,且存在大量的未知访问请求,没有预先定义的信誉信息,增加了安全性预警的难度。为此,提出智慧网络大规模未知访问源安全性预警方法。利用提升小波变换方法对未知访问源的数据包展开降噪处理,建立自动免疫抗体,提取未知访问源数据包特征,识别未知访问源异常,采用模糊综合评价方法对异常访问源的安全性展开评价,根据评价结果确定访问源的风险等级,实现安全性预警。仿真结果表明,所提方法的降噪效果好,可以准确获取未知访问源的风险值变化情况,且预警精度高。

DCVAE与DPC融合的网络入侵检测模型研究

入侵检测是主动防御网络中攻击行为的技术,以往入侵检测模型因正常网络流量与未知攻击内在特征区分度不足,导致对未知攻击识别率不够高,本文设计基于判别条件变分自编码器与密度峰值聚类算法的入侵检测模型(DCVAE-DPC).利用判别条件变分自编码器能够生成指定类别样本的能力,学习正常网络流量特征的隐空间表示并计算其重建误差,增加其与未知攻击间的特征区分度,并使用密度峰值聚类算法求出正常网络流量重建误差的分布,提高未知攻击识别率.实验结果表明,在NSL-KDD数据集中与当前流行的入侵检测模型相比,模型的分类准确率可以达到97.08%,具有更高的未知攻击检测能力,面对当前复杂网络环境,有更强的入侵检测性能.

面向未知环境探索的分层架构路径规划算法

为实现无人平台在未知环境下的高效路径探索,该文提出了一种以“感知-规划-控制”分层架构为基础的路径规划算法。在感知层通过Cartographer建图算法实时构建未知环境的二维栅格地图。在规划层,通过Canny边缘检测、基于密度的聚类算法、效能函数评估选择最佳探索目标点,并在规划的效能函数中引入探索方向延续性概念,克服了传统路径规划反复探索已知环境的难题。在控制层,通过概率路线图算法规划从当前位姿到目标点的最短路径,并通过纯跟踪算法和向量直方图算法实现了路径无碰撞跟踪。3种典型环境下的仿真实验表明,所提出的算法在不同环境下均具有较高的探索效率和完成度。