Introducing the nth-Order Features Adjoint Sensitivity Analysis Methodology for Nonlinear Systems (nth-FASAM-N): I. Mathematical Framework

This work presents the “nth-Order Feature Adjoint Sensitivity Analysis Methodology for Nonlinear Systems” (abbreviated as “nth-FASAM-N”), which will be shown to be the most efficient methodology for computing exact expressions of sensitivities, of any order, of model responses with respect to features of model parameters and, subsequently, with respect to the model’s uncertain parameters, boundaries, and internal interfaces. The unparalleled efficiency and accuracy of the nth-FASAM-N methodology stems from the maximal reduction of the number of adjoint computations (which are considered to be “large-scale” computations) for computing high-order sensitivities. When applying the nth-FASAM-N methodology to compute the second- and higher-order sensitivities, the number of large-scale computations is proportional to the number of “model features” as opposed to being proportional to the number of model parameters (which are considerably more than the number of features).When a model has no “feature” functions of parameters, but only comprises primary parameters, the nth-FASAM-N methodology becomes identical to the extant nth CASAM-N (“nth-Order Comprehensive Adjoint Sensitivity Analysis Methodology for Nonlinear Systems”) methodology. Both the nth-FASAM-N and the nth-CASAM-N methodologies are formulated in linearly increasing higher-dimensional Hilbert spaces as opposed to exponentially increasing parameter-dimensional spaces thus overcoming the curse of dimensionality in sensitivity analysis of nonlinear systems. Both the nth-FASAM-N and the nth-CASAM-N are incomparably more efficient and more accurate than any other methods (statistical, finite differences, etc.) for computing exact expressions of response sensitivities of any order with respect to the model’s features and/or primary uncertain parameters, boundaries, and internal interfaces.

Introducing the nth-Order Features Adjoint Sensitivity Analysis Methodology for Nonlinear Systems (nth-FASAM-N): II. Illustrative Example

This work highlights the unparalleled efficiency of the “nth-Order Function/ Feature Adjoint Sensitivity Analysis Methodology for Nonlinear Systems” (nth-FASAM-N) by considering the well-known Nordheim-Fuchs reactor dynamics/safety model. This model describes a short-time self-limiting power excursion in a nuclear reactor system having a negative temperature coefficient in which a large amount of reactivity is suddenly inserted, either intentionally or by accident. This nonlinear paradigm model is sufficiently complex to model realistically self-limiting power excursions for short times yet admits closed-form exact expressions for the time-dependent neutron flux, temperature distribution and energy released during the transient power burst. The nth-FASAM-N methodology is compared to the extant “nth-Order Comprehensive Adjoint Sensitivity Analysis Methodology for Nonlinear Systems” (nth-CASAM-N) showing that: (i) the 1st-FASAM-N and the 1st-CASAM-N methodologies are equally efficient for computing the first-order sensitivities;each methodology requires a single large-scale computation for solving the “First-Level Adjoint Sensitivity System” (1st-LASS);(ii) the 2nd-FASAM-N methodology is considerably more efficient than the 2nd-CASAM-N methodology for computing the second-order sensitivities since the number of feature-functions is much smaller than the number of primary parameters;specifically for the Nordheim-Fuchs model, the 2nd-FASAM-N methodology requires 2 large-scale computations to obtain all of the exact expressions of the 28 distinct second-order response sensitivities with respect to the model parameters while the 2nd-CASAM-N methodology requires 7 large-scale computations for obtaining these 28 second-order sensitivities;(iii) the 3rd-FASAM-N methodology is even more efficient than the 3rd-CASAM-N methodology: only 2 large-scale computations are needed to obtain the exact expressions of the 84 distinct third-order response sensitivities with respect to the Nordheim-Fuchs model’s parameters when applying the 3rd-FASAM-N methodology, while the application of the 3rd-CASAM-N methodology requires at least 22 large-scale computations for computing the same 84 distinct third-order sensitivities. Together, the nth-FASAM-N and the nth-CASAM-N methodologies are the most practical methodologies for computing response sensitivities of any order comprehensively and accurately, overcoming the curse of dimensionality in sensitivity analysis.

Adaptive target and jamming recognition for the pulse doppler radar fuze based on a time-frequency joint feature and an online-updated naive bayesian classifier with minimal risk

This paper considers the problem of target and jamming recognition for the pulse Doppler radar fuze(PDRF).To solve the problem,the matched filter outputs of the PDRF under the action of target and jamming are analyzed.Then,the frequency entropy and peak-to-peak ratio are extracted from the matched filter output of the PDRF,and the time-frequency joint feature is constructed.Based on the time-frequency joint feature,the naive Bayesian classifier(NBC)with minimal risk is established for target and jamming recognition.To improve the adaptability of the proposed method in complex environments,an online update process that adaptively modifies the classifier in the duration of the work of the PDRF is proposed.The experiments show that the PDRF can maintain high recognition accuracy when the signal-to-noise ratio(SNR)decreases and the jamming-to-signal ratio(JSR)increases.Moreover,the applicable analysis shows that he ONBCMR method has low computational complexity and can fully meet the real-time requirements of PDRF.

A fault diagnosis method of reciprocating compressor based on sensitive feature evaluation and artificial neural network

A method combining information entropy and radial basis function network is proposed for fault automatic diagnosis of reciprocating compressors.Aiming at the current situation that the accuracy rate of reciprocating compressor fault diagnosis which depends on manual work in engineering is very low,we apply information entropy evaluation to select the sensitive features and make clear the corresponding relationship of characteristic parameters and failures.This method could reduce the feature dimension.Then,a complete fault diagnosis architecture has been built combining with radial basis function network which has the fast and efficient characteristics.According to the test results using experimental and engineering data,it is observed that the proposed fault diagnosis method improves the accuracy of fault automatic diagnosis effectively and it could improve the practicability of the monitoring system.

Digital modulation classification using multi-layer perceptron and time-frequency features

Considering that real communication signals corrupted by noise are generally nonstationary, and timefrequency distributions are especially suitable for the analysis of nonstationary signals, time-frequency distributions are introduced for the modulation classification of communication signals： The extracted time-frequency features have good classification information, and they are insensitive to signal to noise ratio （SNR） variation. According to good classification by the correct rate of a neural network classifier, a multilayer perceptron （MLP） classifier with better generalization, as well as, addition of time-frequency features set for classifying six different modulation types has been proposed. Computer simulations show that the MLP classifier outperforms the decision-theoretic classifier at low SNRs, and the classification experiments for real MPSK signals verify engineering significance of the MLP classifier.

A reliability-oriented genetic algorithm-levenberg marquardt model for leak risk assessment based on time-frequency features

Since leaks in high-pressure pipelines transporting crude oil can cause severe economic losses,a reliable leak risk assessment can assist in developing an effective pipeline maintenance plan and avoiding unexpected incidents.The fast and accurate leak detection methods are essential for maintaining pipeline safety in pipeline reliability engineering.Current oil pipeline leakage signals are insufficient for feature extraction,while the training time for traditional leakage prediction models is too long.A new leak detection method is proposed based on time-frequency features and the Genetic Algorithm-Levenberg Marquardt(GA-LM)classification model for predicting the leakage status of oil pipelines.The signal that has been processed is transformed to the time and frequency domain,allowing full expression of the original signal.The traditional Back Propagation(BP)neural network is optimized by the Genetic Algorithm(GA)and Levenberg Marquardt(LM)algorithms.The results show that the recognition effect of a combined feature parameter is superior to that of a single feature parameter.The Accuracy,Precision,Recall,and F1score of the GA-LM model is 95%,93.5%,96.7%,and 95.1%,respectively,which proves that the GA-LM model has a good predictive effect and excellent stability for positive and negative samples.The proposed GA-LM model can obviously reduce training time and improve recognition efficiency.In addition,considering that a large number of samples are required for model training,a wavelet threshold method is proposed to generate sample data with higher reliability.The research results can provide an effective theoretical and technical reference for the leakage risk assessment of the actual oil pipelines.

Insulin Sensitivity and Gynaecological Features of Infertile Cameroonian Females with Polycystic Ovary Syndrome: A Cross-Sectional Study

Background: Polycystic ovary syndrome (PCOS), characterized by ovulatory dysfunction, polycystic ovary(PCO),hyperandrogenism and insulin resistance is the commonest endocrine disorder in women of reproductive age. It is an intriguing pathology that involves the perpetuation of a vicious circle with reproductive, endocrine and metabolic components. We aimed to assess the reproductive features and insulin sensitivity (IS) in infertile women with or without PCOS. Materials and Methods: We carried out a cross-sectional analytic study at the outpatient Obstetrics and Gynaecology Department of the Yaounde Gyneco-obstetric and Pediatrics Hospital, Cameroon from September 1st 2012 to March 31st 2013 giving total study duration of 07 months. Laboratory analyses were carried out at the National Obesity Centre(NOC)of the Yaounde Central Hospital, Cameroon. Results: Overall, 36 infertile females were enrolled, which included 15 diagnosed cases of PCOS according to Rotterdam consensus meeting of 2003 and 21 non PCOS subjects as control. PCOS women were younger than non PCOS women (28.8 ± 5.5 vs. 35.0 ± 4.2 years;p = 0.0004). The majority of the women in the PCOS group were spaniomenorrheic (11/15), and ultrasonographic findings were typical of PCOS. Hirsutism score was higher in the PCOS group with a median of 9 (7 - 13). Insulin sensitivity was impaired in two-thirds of the study population, with 12 women found to be insulin resistant(6 PCOS, 6 non PCOS), 12 patients had intermediate insulin sensitivity(2 PCOS, 10 non PCOS)and 12 insulin sensitive(7 PCOS, 5 non PCOS). Apart from blood glucose levels (p = 0.007), all other anthropometric and biological parameters were not significant. Spearman’s correlation identified fasting plasma glucose and total cholesterol as factors associated with insulin sensitivity in females with PCOS. Impaired fasting glucose was observed in 13 patients with 08 from the PCOS group. Conclusion: We conclude that young age, spaniomenorrhea and hirsutism are common findings in PCOS. Furthermore, our findings suggest that PCOS may be more of systemic metabolic disease than solely a purely gynecologic disorder as described hitherto. Despite normal fasting plasma glucose levels, a good proportion of these women has impaired insulin sensitivity and it is associated with a metabolic syndrome.

Identification of Question and Non-Question Segments in Arabic Monologues Using Prosodic Features: Novel Type-2 Fuzzy Logic and Sensitivity-Based Linear Learning Approaches

In this paper, we extend our previous study of addressing the important problem of automatically identifying question and non-question segments in Arabic monologues using prosodic features. We propose here two novel classification approaches to this problem: one based on the use of the powerful type-2 fuzzy logic systems (type-2 FLS) and the other on the use of the discriminative sensitivity-based linear learning method (SBLLM). The use of prosodic features has been used in a plethora of practical applications, including speech-related applications, such as speaker and word recognition, emotion and accent identification, topic and sentence segmentation, and text-to-speech applications. In this paper, we continue to specifically focus on the Arabic language, as other languages have received a lot of attention in this regard. Moreover, we aim to improve the performance of our previously-used techniques, of which the support vector machine (SVM) method was the best performing, by applying the two above-mentioned powerful classification approaches. The recorded continuous speech is first segmented into sentences using both energy and time duration parameters. The prosodic features are then extracted from each sentence and fed into each of the two proposed classifiers so as to classify each sentence as a Question or a Non-Question sentence. Our extensive simulation work, based on a moderately-sized database, showed the two proposed classifiers outperform SVM in all of the experiments carried out, with the type-2 FLS classifier consistently exhibiting the best performance, because of its ability to handle all forms of uncertainties.

Feature Extraction and Recognition for Rolling Element Bearing Fault Utilizing Short-Time Fourier Transform and Non-negative Matrix Factorization

Due to the non-stationary characteristics of vibration signals acquired from rolling element bearing fault, thc time-frequency analysis is often applied to describe the local information of these unstable signals smartly. However, it is difficult to classitythe high dimensional feature matrix directly because of too large dimensions for many classifiers. This paper combines the concepts of time-frequency distribution（TFD） with non-negative matrix factorization（NMF）, and proposes a novel TFD matrix factorization method to enhance representation and identification of bearing fault. Throughout this method, the TFD of a vibration signal is firstly accomplished to describe the localized faults with short-time Fourier transform（STFT）. Then, the supervised NMF mapping is adopted to extract the fault features from TFD. Meanwhile, the fault samples can be clustered and recognized automatically by using the clustering property of NMF. The proposed method takes advantages of the NMF in the parts-based representation and the adaptive clustering. The localized fault features of interest can be extracted as well. To evaluate the performance of the proposed method, the 9 kinds of the bearing fault on a test bench is performed. The proposed method can effectively identify the fault severity and different fault types. Moreover, in comparison with the artificial neural network（ANN）, NMF yields 99.3% mean accuracy which is much superior to ANN. This research presents a simple and practical resolution for the fault diagnosis problem of rolling element bearing in high dimensional feature space.

Radar Signal Intra-Pulse Feature Extraction Based on Improved Wavelet Transform Algorithm

With the new system radar put into practical use, the characteristics of complex radar signals are changing and developing. The traditional analysis method of one-dimensional transformation domain is no longer applicable to the modern radar signal processing, and it is necessary to seek new methods in the two-dimensional transformation domain. The time-frequency analysis method is the most widely used method in the two-dimensional transformation domain. In this paper, two typical time-frequency analysis methods of short-time Fourier transform and Wigner-Ville distribution are studied by analyzing the time-frequency transform of typical radar reconnaissance linear frequency modulation signal, aiming at the problem of low accuracy and sen-sitivity to the signal noise of common methods, the improved wavelet transform algorithm was proposed.

Pathological Voice Classification Based on Features Dimension Opti mization

The classification of pathological voice from healthy voice was studied based upon 27 acoustic features derived from a single sound signal of vowel /a:/. First, the feature space was transferred to reduce the data dimension by principle component analysis (PCA). Then the voice samples were classified according to the reduced PCA parameters by support vector machine (SVM) using radial basis function (RBF) as a kernel function. Meanwhile, by changing the ratio of opposite class samples, the accuracy under different features combinations was tested. Experimental data were provided by the voice database of Massachusetts Eye and Ear Infirmary (MEEI) in which 216 vowel /a:/ samples were collected from subjects of healthy and pathological cases, and tested with 5 fold cross-validation method. The result shows the positive rate of pathological voices was improved from 92% to 98% through the PCA method. STD, Fatr, Tasm, NHR, SEG, and PER are pathology sensitive features in illness detection. Using these sensitive features the accuracy of detection of pathological voice from healthy voice can reach 97%.

Jamming Recognition Based on Feature Fusion and Convolutional Neural Network

The complicated electromagnetic environment of the BeiDou satellites introduces vari-ous types of external jamming to communication links,in which recognition of jamming signals with uncertainties is essential.In this work,the jamming recognition framework proposed consists of fea-ture fusion and a convolutional neural network(CNN).Firstly,the recognition inputs are obtained by prepossessing procedure,in which the 1-D power spectrum and 2-D time-frequency image are ac-cessed through the Welch algorithm and short-time Fourier transform(STFT),respectively.Then,the 1D-CNN and residual neural network(ResNet)are introduced to extract the deep features of the two prepossessing inputs,respectively.Finally,the two deep features are concatenated for the following three fully connected layers and output the jamming signal classification results through the softmax layer.Results show the proposed method could reduce the impacts of potential feature loss,therefore improving the generalization ability on dealing with uncertainties.

Feature Preserving Mesh Simplification Using Feature Sensitive Metric

We present a new method for feature preserving mesh simplification based on feature sensitive （FS） metric. Previous quadric error based approach is extended to a high-dimensional FS space so as to measure the geometric distance together with normal deviation. As the normal direction of a surface point is uniquely determined by the position in Euclidian space, we employ a two-step linear optimization scheme to efficiently derive the constrained optimal target point. We demonstrate that our algorithm can preserve features more precisely under the global geometric properties, and can naturally retain more triangular patches on the feature regions without special feature detection procedure during the simplification process. Taking the advantage of the blow-up phenomenon in FS space, we design an error weight that can produce more suitable results. We also show that Hausdorff distance is markedly reduced during FS simplification.

Underground Pipeline Surveillance with an Algorithm Based on Statistical Time-Frequency Acoustic Features

Underground pipeline networks suffer from severe damage by earth-moving devices due to rapid urbanization.Thus,designing a round-the-clock intelligent surveillance system has become crucial and urgent.In this study,we develop an acoustic signal-based excavation device recognition system for underground pipeline protection.The front-end hardware system is equipped with an acoustic sensor array,an Analog-to-Digital Converter(ADC)module(ADS1274),and an industrial processor Advanced RISC Machine(ARM)cortex-A8 for signal collection and algorithm implementation.Then,a novel Statistical Time-Frequency acoustic Feature(STFF)is proposed,and a fast Extreme Learning Machine(ELM)is adopted as the classifier.Experiments on real recorded data show that the proposed STFF achieves better discriminative capability than the conventional acoustic cepstrum features.In addition,the surveillance platform is applicable for encountering big data owing to the fast learning speed of ELM.

Spatiotemporal emotion recognition based on 3D time-frequency domain feature matrix

The research of emotion recognition based on electroencephalogram(EEG)signals often ignores the related information between the brain electrode channels and the contextual emotional information existing in EEG signals,which may contain important characteristics related to emotional states.Aiming at the above defects,a spatiotemporal emotion recognition method based on a 3-dimensional(3 D)time-frequency domain feature matrix was proposed.Specifically,the extracted time-frequency domain EEG features are first expressed as a 3 D matrix format according to the actual position of the cerebral cortex.Then,the input 3 D matrix is processed successively by multivariate convolutional neural network(MVCNN)and long short-term memory(LSTM)to classify the emotional state.Spatiotemporal emotion recognition method is evaluated on the DEAP data set,and achieved accuracy of 87.58%and 88.50%on arousal and valence dimensions respectively in binary classification tasks,as well as obtained accuracy of 84.58%in four class classification tasks.The experimental results show that 3 D matrix representation can represent emotional information more reasonably than two-dimensional(2 D).In addition,MVCNN and LSTM can utilize the spatial information of the electrode channels and the temporal context information of the EEG signal respectively.

复杂动态负荷幅度域波形模态聚类与电能表误差敏感特征

针对复杂动态负荷游程波形模态及引起电能表误差的典型特征认识不足的问题,首先提出动态电流信号幅度域游程波形模态提取算法,提取了多种幅度域毫秒级小颗粒度游程波形模态;其次,提出LK-Shape游程波形模态聚类算法,提取了动态电流信号幅度域的6类典型游程波形模态及其快速变化特征;最后,提出导致电能表超差的两种敏感游程波形模态,并通过实验验证了该游程波形模态适于测试电能表误差,表明了所提方法的有效性和实用性。

基于敏感特征深度域关联的Android恶意应用检测方法

利用机器学习或深度学习算法进行Android恶意应用的检测是当前主流方法,取得了一定的效果。然而,多数方法仅关注应用的权限和敏感行为等信息,缺乏对敏感行为协同的深度分析,导致恶意应用检测准确率低。对敏感行为协同深度分析的挑战主要有两个:表征敏感特征域关联和基于敏感特征域关联的深层分析与检测。本文提出了一种新的Android恶意应用检测模型GCNDroid,基于敏感特征域关联关系图描述的应用程序主要敏感行为以及敏感行为之间的域关联关系来有效地检测Android恶意应用。首先,为了筛选出对分类更加敏感的特征,同时减少图节点的数量,加速分析,本文构建了敏感特征字典。接着,定义类或者包为域,在同一个域中的敏感特征具有域关联关系。通过敏感特征所在域的相对范围,构造敏感特征之间不同的域关联权重,生成敏感特征域关联关系图,敏感特征域关联关系图可以准确表征特定功能模块中的敏感行为,以及敏感行为之间的完整关系。然后,基于敏感特征域关联关系图,设计基于图卷积神经网络的深度表征,构建Android恶意应用检测模型GCNDroid。在实践中,GCNDroid还可以利用新的敏感特征不断更新,以适应移动应用程序新的敏感行为。最后,本文对GCDNroid进行了系统评估,召回率、调和平均数、AUC等重要指标均超过96%。与传统的机器学习算法(支持向量机和决策树)和深度学习算法(深度神经网络和卷积神经网络)相比,GCNDroid取得了预期的效果。

基于差异化能源大数据与敏感特征的轻量级共享数据加密方法

差异化大数据属性的路径密钥生成较为复杂,存在额外记录加密数据的行为,难以针对特定的敏感数据进行加密,导致整体开销较大。对此,基于差异化能源大数据与敏感特征,设计了一种轻量级共享数据加密方法。分析了能源大数据的差异化特征,建立同参数的无向图,通过顶点搜索法分类顶点权重值下的差异化特性,将其分离成为轻量级的数据形态,解析相应能源大数据的Raft共识机制。基于Raft共识机制,结合敏感特征测试代价矩阵,修正不同状态的能源大数据信息,针对性地定义共享能源大数据的加密密文格式,结合RSA(Rivest-Shamir-Adleman)算法,完成轻量级共享数据加密。实验结果表明,主动攻击数据、被动攻击数据、高级持续性威胁攻击数据、差分攻击数据、连接攻击数据的总体防御成功率较高,带宽开销与验证开销较小,满足了能源大数据安全保障需求。

基于ECSDNN的航空安全事件风险等级预测

航空安全事件风险等级预测是主动风险管理的重要手段。考虑海量航空安全事件数据呈现的高维复杂、类不平衡等特性,提出一种基于集成代价敏感深度神经网络(ECSDNN)的航空安全事件风险等级预测方法。采用分类型属性嵌入特征编码和数值型属性拼接的方法实现航空安全事件数据的特征表示;综合考虑错分比例和固定代价设计代价敏感矩阵和代价敏感损失函数,构建基于代价敏感深度神经网络(CSDNN)的基分类器模型;采用硬投票方法,集成多个参数不同、性能各异的基分类器,构建航空安全事件风险等级预测模型。在航空安全事件报告系统(ASRS)数据集上的实验结果表明:相比基准算法,所提ECSDNN模型的预测准确率提升了4.51%;相比单个CSDNN基分类器,所提ECSDNN模型的预测准确率提升了3.17%。验证了基于ECSDNN的航空安全事件风险等级预测方法的有效性。

基于特征相似的作业执行时间和内存预测算法

准确预估作业所需的执行时间和内存量是提高作业调度系统性能的关键,然而,大多数用户提供的预估值准确性较差。提出一种基于作业特征相似性的预测算法——LSH-Sim,该算法将相似搜索和机器学习相结合,根据文本特征和数值特征搜索历史作业集中的相似作业,在相似作业集中使用机器学习或者均值法进行预测。借助局部敏感哈希算法搜索相似作业,在提高预测准确率的同时缩短预测时间。使用来自国家超级计算昆山中心、合肥先进计算中心和“乌镇之光”超级计算中心的历史作业集进行实验,实验结果表明,相较于朴素预测和改进模板预测算法,LSH-Sim算法的平均绝对误差更低,预测时间更短。