Bearing Fault Diagnosis Based on Deep Discriminative Adversarial Domain Adaptation Neural Networks

Intelligent diagnosis driven by big data for mechanical fault is an important means to ensure the safe operation ofequipment. In these methods, deep learning-based machinery fault diagnosis approaches have received increasingattention and achieved some results. It might lead to insufficient performance for using transfer learning alone andcause misclassification of target samples for domain bias when building deep models to learn domain-invariantfeatures. To address the above problems, a deep discriminative adversarial domain adaptation neural networkfor the bearing fault diagnosis model is proposed (DDADAN). In this method, the raw vibration data are firstlyconverted into frequency domain data by Fast Fourier Transform, and an improved deep convolutional neuralnetwork with wide first-layer kernels is used as a feature extractor to extract deep fault features. Then, domaininvariant features are learned from the fault data with correlation alignment-based domain adversarial training.Furthermore, to enhance the discriminative property of features, discriminative feature learning is embeddedinto this network to make the features compact, as well as separable between classes within the class. Finally, theperformance and anti-noise capability of the proposedmethod are evaluated using two sets of bearing fault datasets.The results demonstrate that the proposed method is capable of handling domain offset caused by differentworkingconditions and maintaining more than 97.53% accuracy on various transfer tasks. Furthermore, the proposedmethod can achieve high diagnostic accuracy under varying noise levels.

Artificial neural network-based method for discriminating Compton scattering events in high-purity germaniumγ-ray spectrometer

To detect radioactive substances with low activity levels,an anticoincidence detector and a high-purity germanium(HPGe)detector are typically used simultaneously to suppress Compton scattering background,thereby resulting in an extremely low detection limit and improving the measurement accuracy.However,the complex and expensive hardware required does not facilitate the application or promotion of this method.Thus,a method is proposed in this study to discriminate the digital waveform of pulse signals output using an HPGe detector,whereby Compton scattering background is suppressed and a low minimum detectable activity(MDA)is achieved without using an expensive and complex anticoincidence detector and device.The electric-field-strength and energy-deposition distributions of the detector are simulated to determine the relationship between pulse shape and energy-deposition location,as well as the characteristics of energy-deposition distributions for fulland partial-energy deposition events.This relationship is used to develop a pulse-shape-discrimination algorithm based on an artificial neural network for pulse-feature identification.To accurately determine the relationship between the deposited energy of gamma(γ)rays in the detector and the deposition location,we extract four shape parameters from the pulse signals output by the detector.Machine learning is used to input the four shape parameters into the detector.Subsequently,the pulse signals are identified and classified to discriminate between partial-and full-energy deposition events.Some partial-energy deposition events are removed to suppress Compton scattering.The proposed method effectively decreases the MDA of an HPGeγ-energy dispersive spectrometer.Test results show that the Compton suppression factors for energy spectra obtained from measurements on ^(152)Eu,^(137)Cs,and ^(60)Co radioactive sources are 1.13(344 keV),1.11(662 keV),and 1.08(1332 keV),respectively,and that the corresponding MDAs are 1.4%,5.3%,and 21.6%lower,respectively.

粮食气味物质的提取、关键组分判别及其在储藏中的应用研究进展

粮食气味物质受粮食种类、储藏条件、储藏时间及是否受有害生物污染等多种因素影响,气味物质种类及含量能够及时反映粮食是否变质或受有害生物危害。首先,本文概述目前常用的粮食气味物质的提取和鉴定技术,总结不同状态粮食气味物质组成,发现烷烃类、酸类、醛类和醇类等物质赋予粮食特有的气味,而不同的储藏环境和粮食状态下,其气味物质存在较大差异。其次,探讨粮食中特征气味物质的分析方法,梳理粮食关键气味物质可能的代谢途径,归纳水稻和小麦中特征气味物质,其中稻谷中特征气味物质2-乙酰基-1-吡咯啉的生成机制也已得到初步确认。最后,对气味物质在粮食安全储藏领域的应用进行概述,提出深入分析、挖掘粮食气味物质数据,构建新型预测模型以快速、精准检测粮食品质将成为未来粮食气味物质研究领域的重要方向;同时,部分气味物质也被证实对粮仓中有害生物具有防控作用,将成为未来研发新型绿色储粮药剂的重要来源。

利用区域地震资料监测朝鲜地下核试验的研究进展

根据朝鲜6次地下核试验在中国东北及邻近地区产生的宽频带区域地震资料,中国科学院地质与地球物理研究所地震学学科组发展了一套用于监测地下核试验的地震学方法,主要包括震级测量和当量估计、高精度震中定位以及爆炸与天然地震事件识别等.在全球范围内,存在多个用于震级-当量转换的经验公式,确定何种公式适合于朝鲜半岛地区至关重要.通过搜集一组用于地震测深的化学爆炸的当量和埋深,并以这些已知爆炸源作为量规事件,能够标定朝鲜地下核试验场的震级-当量关系,从而实现对朝鲜地下核爆进行当量估计.在精确定位方面,发展了利用多事件之间波形互相关方法精确测定它们之间的走时差从而完成高精度相对震中定位.通过进一步利用Pn和Pg等多震相数据还实现了对核爆深度的相对定位.在爆炸震源识别方面,利用统计处理方法分析研究了不同类型事件所产生地震波的特征,包括6次地下核试验、4次天然地震和3次化学爆炸,以及一些矿区塌陷等.结果发现P和S类型波的振幅比,例如Pn/Lg、Pg/Lg和Pn/Sn等,在2 Hz以上能够较好区分各类震源.其中爆炸震源产生的振幅比显著高于天然地震的值.特别是,通过计算谱振幅比的台网平均值能够显著提高识别的可靠性.利用中国东北和附近地区地震台网所提供的数据可以准确地将朝鲜地下核试验从周边天然地震事件中识别出来.该方法同时得到化学爆炸的P/S谱振幅比值介于核爆炸和天然地震的群组之间.

量子核判别分析算法

核判别分析法通过核函数扩展了线性判别分析对非线性数据的处理能力,成为模式识别领域中一个重要的分支。然而,随着数据的指数增长,经典核判别分析算法在提取特征时会消耗大量计算资源。针对这一问题,利用量子叠加性和并行性提出了一种量子核判别分析算法。首先,借助量子随机存储器技术与控制旋转操作构造需要的类间矩阵和类内矩阵所对应的密度算子;然后,融入线性方程的求解思路并行获取特征态。理论分析表明,所提算法与经典算法相比具有指数级加速。

优化HS-SPME-GC-MS方法表征香菇不同成熟阶段的关键挥发性化合物

通过优化的顶空固相微萃取结合气相色谱-质谱联用技术鉴定香菇不同成熟阶段挥发性化合物,并采用气味活性值(odor activity value,OAV)和偏最小二乘判别分析(partial least squares discriminant analysis,PLS-DA)进行分析。结果表明:最佳提取条件为1.0 g香菇样品在50℃提取25 min,解吸3 min;在香菇不同成熟阶段共鉴定出71种挥发性化合物,不同成熟阶段挥发性化合物种类和含量存在显著差异(P<0.05);通过PLS-DA和变量投影重要性(variable importance in projection,VIP)筛选出18种挥发性化合物,可作为区分香菇不同成熟阶段的挥发性生物标志物;OAV结果表明,有16种挥发性化合物为香气活性化合物,其中,1-辛烯-3-醇、3-辛醇、1-辛烯-3-酮、3-辛酮、苯乙醛、二甲基二硫醚、二甲基三硫醚、2,3,5-三硫杂己烷和1,2,4-三硫杂环戊烷同时满足VIP>1和OAV≥1,是香菇不同成熟阶段最重要的差异挥发性化合物。本研究为探究香菇成熟过程中香气形成机制提供一定理论依据。

垄断势力视角下平台大数据杀熟的价格歧视机理

大数据杀熟问题近年来受到各界的广泛关注,政府出台了一系列有关大数据杀熟治理的政策文件。然而,诸多法规相互交叉、竞合,给监管执行造成了巨大的困难。大数据杀熟愈演愈烈,导致了消费者群体与涉事平台企业之间存在严重的信任危机。为了能更好地理解和治理大数据杀熟,本文深入分析了垄断势力视角下平台大数据杀熟的价格歧视机理。通过分析,揭示了大数据杀熟的经济逻辑为(:1)垄断势力是形成大数据杀熟的源泉(;2)大数据杀熟本质是不公平的高价价格歧视。在以上分析的基础上,本文对大数据杀熟的本质、认识误区和治理思路进行了分析,指出大数据杀熟治理的关键是反垄断和防欺诈。总之,本研究通过对大数据杀熟垄断势力下价格歧视机理的分析,厘清了大数据杀熟与价格歧视和精准营销的区别,从而为正确认识大数据杀熟和有效抑制大数据杀熟提供参考。

Discriminative tone model training and optimal integration for Mandarin speech recognition

Two discriminative methods for solving tone problems in Mandarin speech recognition are presented. First, discriminative training on the HMM （hidden Markov model） based tone models is proposed. Then an integration technique of tone models into a large vocabulary continuous speech recognition system is presented. Discriminative model weight training based on minimum phone error criteria is adopted aiming at optimal integration of the tone models. The extended Baum Welch algorithm is applied to find the model-dependent weights to scale the acoustic scores and tone scores. Experimental results show that tone recognition rates and continuous speech recognition accuracy can be improved by the discriminatively trained tone model. Performance of a large vocabulary continuous Mandarin speech recognition system can be further enhanced by the discriminatively trained weight combinations due to a better interpolation of the given models.

DISCRIMINATIVE REGULARIZATION:A NEW CLASSIFIER LEARNING METHOD

A novel regularization method -- discriminative regularization （DR）is presented. The method provides a general way to incorporate the prior knowledge for the classification. By introducing the prior information into the regularization term, DR is used to minimize the empirical loss between the desired and actual outputs, as well as maximize the inter-class separability and minimize the intra-class compactness in the output space simultane- ously. Furthermore, by embedding equality constraints in the formulation, the solution of DR can solve a set of linear equations. Classification experiments show the superiority of the proposed DR.

基于残差U型网络与双判别网络的图像分割方法

生成对抗网络在图像领域应用十分广泛,但在细胞核图像分割领域中的应用研究相对较少。由于细胞核的精准分割对于病理诊断工作有极大帮助,故提出了基于残差U型网络与生成对抗网络的图像分割方法。该方法以ResUNet网络作为生成网络,Image GAN为双判别网络,训练过程使用双损失函数和冻结策略进行优化。改进后网络在PanNuke数据集上评价指标MioU、Dice、Acc分别为80%、93%、80%,相比ResUNet网络的实验结果分别提升了2.3%、1.7%、2.1%。实验结果证明,改进后网络对细胞核分割具有较好准确率,可作为病理诊断工作的重要依据。

A new method of discriminating different types of post-Archean ophiolitic basalts and their tectonic significance using Th-Nb and Ce-Dy-Yb systematics

In this paper, a new discrimination diagram using absolute measures of Th and Nb is applied to postArchean ophiolites to best discriminate a large number of different ophiolitic basalts. This diagram was obtained using 〉2000 known ophiolitic basalts and was tested using -560 modern rocks from known tectonic settings. Ten different basaltic varieties from worldwide ophiolitic complexes have been examined. They include two basaltic types that have never been considered before, which are： （1） medium-Ti basalts （MTB） generated at nascent forearc settings; （2） a type of mid-ocean ridge basalts showing garnet signature （G-MORB） that characterizes Alpine-type （i,e., non volcanic） rifted margins and ocean-continent transition zones （OCTZ）. In the Th-Nb diagram, basalts generated in oceanic subductionunrelated settings, rifted margins, and OCTZ can be distinguished from subduction-related basalts with a misclassification rate 〈 1%. This diagram highlights the chemical variation of oceanic, rifted margin, and OCTZ basalts from depleted compositions to progressively more enriched compositions reflecting, in turn, the variance of source composition and degree of melting within the MORB-OIB array. It also highlights the chemical contributions of enriched （OIB-type） components to mantle sources. Enrichment of Th relative to Nb is particularly effective for highlighting crustal input via subduction or crustal contamination. Basalts formed at continental margin arcs and island arc with a complex polygenetic crust can be distinguished from those generated in intra-oceanic arcs in supra-subducrion zones （SSZ） with a misclassification rate 〈1%. Within the SSZ group, two sub-settings can be recognized with a misclassification rate 〈0.5%. They are： （1） SSZ influenced by chemical contribution from subduction- derived components （forearc and intra-arc sub-settings） characterized by island arc tholeiitic （IAT） and boninitic basalts; （2） SSZ with no contribution from subduction-derived components （nascent forearc sub-settings） characterized by MTBs and depleted-MORBs. Two additional discrimination diagrams are proposed： （1） a Dy-Yb diagram is used for discriminating boninite and IAT basalts; （2） a Ce/Yb-Dy/Yb diagram is used for discriminating G-MORBs and normal MORBs. The proposed method may effectively assist in recovering the tectonic affinity of ancient ophiolites, which is fundamental for establishing the geodvnamic evolution of ancient oceanic and continental domains, as well as orogenic belts.

Feature Selection Method Based on Class Discriminative Degree for Intelligent Medical Diagnosis

By using efficient and timely medical diagnostic decision making,clinicians can positively impact the quality and cost of medical care.However,the high similarity of clinical manifestations between diseases and the limitation of clinicians’knowledge both bring much difficulty to decision making in diagnosis.Therefore,building a decision support system that can assist medical staff in diagnosing and treating diseases has lately received growing attentions in the medical domain.In this paper,we employ a multi-label classification framework to classify the Chinese electronic medical records to establish corresponding relation between the medical records and disease categories,and compare this method with the traditional medical expert system to verify the performance.To select the best subset of patient features,we propose a feature selection method based on the composition and distribution of symptoms in electronic medical records and compare it with the traditional feature selection methods such as chi-square test.We evaluate the feature selection methods and diagnostic models from two aspects,false negative rate(FNR)and accuracy.Extensive experiments have conducted on a real-world Chinese electronic medical record database.The evaluation results demonstrate that our proposed feature selection method can improve the accuracy and reduce the FNR compare to the traditional feature selection methods,and the multi-label classification framework have better accuracy and lower FNR than the traditional expert system.

DETERMINING THE DISCRIMINATING DOMAIN FOR HYBRID LINEAR DIFFERENTIAL GAME WITH TWO PLAYERS AND TWO TARGETS

This paper studies a bounded discriminating domain for hybrid linear differential game with two players and two targets using viability theory. First of all, we prove that the convex hull of a closed set is also a discriminating domain if the set is a discriminating domain. Secondly, in order to determine that a bounded polyhedron is a discriminating domain, we give a result that it only needs to verify that the extreme points of the polyhedron meet the viability conditions. The difference between our result and the existing ones is that our result just needs to verify the finite points （extreme points） and the existing ones need to verify all points in the bounded polyhedron.

A New Discriminating Experiment on the Invariance Hypothesis of Light Speed

This thesis puts forward a conjecture that, owing to some unknown special character of light, it is impossible to determine whether the speed of light is variable by the interference method. To verify the hypothesis of the invariance of light speed, a new method must be found to take accurate measurement of the infinitesimal change in the travelling time of light. The thesis suggests the adoption of high frequency laser pulse technology to carry out the measurement. On the basis of this idea a new discriminating experiment is proposed to test the hypothesis of the invariance of light speed. The thesis also makes some forecast of the future prospects of this experiment and of the future development of the theory of special relativity.

Predicting Lung Cancers Using Epidemiological Data:A Generative-Discriminative Framework

Predictive models for assessing the risk of developing lung cancers can help identify high-risk individuals with the aim of recommending further screening and early intervention.To facilitate pre-hospital self-assessments,some studies have exploited predictive models trained on non-clinical data(e.g.,smoking status and family history).The performance of these models is limited due to not considering clinical data(e.g.,blood test and medical imaging results).Deep learning has shown the potential in processing complex data that combine both clinical and non-clinical information.However,predicting lung cancers remains difficult due to the severe lack of positive samples among follow-ups.To tackle this problem,this paper presents a generative-discriminative framework for improving the ability of deep learning models to generalize.According to the proposed framework,two nonlinear generative models,one based on the generative adversarial network and another on the variational autoencoder,are used to synthesize auxiliary positive samples for the training set.Then,several discriminative models,including a deep neural network(DNN),are used to assess the lung cancer risk based on a comprehensive list of risk factors.The framework was evaluated on over 55000 subjects questioned between January 2014 and December 2017,with 699 subjects being clinically diagnosed with lung cancer between January 2014 and August 2019.According to the results,the best performing predictive model built using the proposed framework was based on DNN.It achieved an average sensitivity of 76.54%and an area under the curve of 69.24%in distinguishing between the cases of lung cancer and normal cases on test sets.

Learning a discriminative high-fidelity dictionary for single channel source separation

Sparse-representation-based single-channel source separation,which aims to recover each source’s signal using its corresponding sub-dictionary,has attracted many scholars’attention.The basic premise of this model is that each sub-dictionary possesses discriminative information about its corresponding source,and this information can be used to recover almost every sample from that source.However,in a more general sense,the samples from a source are composed not only of discriminative information but also common information shared with other sources.This paper proposes learning a discriminative high-fidelity dictionary to improve the separation performance.The innovations are threefold.Firstly,an extra sub-dictionary was combined into a conventional union dictionary to ensure that the source-specific sub-dictionaries can capture only the purely discriminative information for their corresponding sources because the common information is collected in the additional sub-dictionary.Secondly,a task-driven learning algorithm is designed to optimize the new union dictionary and a set of weights that indicate how much of the common information should be allocated to each source.Thirdly,a source separation scheme based on the learned dictionary is presented.Experimental results on a human speech dataset yield evidence that our algorithm can achieve better separation performance than either state-of-the-art or traditional algorithms.

Coupling Discriminating Statistical Analysis and Artificial Intelligence for Geotechnical Characterization of the Kampemba’s Municipality Soils (Lubumbashi, DR Congo)

This study focuses on the determination of physical and mechanical characteristics based on in vitro tests, by using field samples for the Kampemba urban area in the city of Lubumbashi. At the end of this study, we identified the soils according to their parameters, and established the geotechnical classification by determining their bearing capacity by the group index method using from the identification tests carried out. By using the AASHTO classification method (American Association for State Highway Transportation Official), the results obtained after our studies revealed five classes of soil: A-2, A-4, A-5, A-6, A-7 in a general way, and particularly eight subgroups of soil: A-2-4, A-2-6, A-2-7, A-4, A-5, A-6, A-7-5 and A-7-6 for the concerned area. The latter has given statistical analysis and deep learning based on multi-layer perceptron, the global values of the physical parameters. It’s about: 31.77% ± 1.05% for the limit of liquidity;18.71% ± 0.76% for the plastic limit;13.06% ± 0.79% for the plasticity index;83.00% ± 3.33% for passing of 2 mm sieve;76.22% ± 3.2% for passing of 400 μm sieve;89.07% ± 2.99% for passing of 4.75 mm sieve;70.62% ± 2.39% passing of 80 μm sieve;1.66 ± 0.61 for the consistency index;−0.67 ± 0.62 for the liquidity index and 8 ± 1 for the group index.

Unsupervised Domain Adaptation Based on Discriminative Subspace Learning for Cross-Project Defect Prediction

:Cross-project defect prediction(CPDP)aims to predict the defects on target project by using a prediction model built on source projects.The main problem in CPDP is the huge distribution gap between the source project and the target project,which prevents the prediction model from performing well.Most existing methods overlook the class discrimination of the learned features.Seeking an effective transferable model from the source project to the target project for CPDP is challenging.In this paper,we propose an unsupervised domain adaptation based on the discriminative subspace learning(DSL)approach for CPDP.DSL treats the data from two projects as being from two domains and maps the data into a common feature space.It employs crossdomain alignment with discriminative information from different projects to reduce the distribution difference of the data between different projects and incorporates the class discriminative information.Specifically,DSL first utilizes subspace learning based domain adaptation to reduce the distribution gap of data between different projects.Then,it makes full use of the class label information of the source project and transfers the discrimination ability of the source project to the target project in the common space.Comprehensive experiments on five projects verify that DSL can build an effective prediction model and improve the performance over the related competing methods by at least 7.10%and 11.08%in terms of G-measure and AUC.

Entity Burst Discriminative Model for Cumulative Citation Recommendation

Knowledge base acceleration-cumulative citation recommendation(KBA-CCR)aims to detect citation-worthiness documents from a chronological stream corpus for a set of target entities in a knowledge base.Most previous works only consider a number of semantic features between documents and target entities in the knowledge base,and then use powerful machine learning approaches such as logistic regression to classify relevant documents and non-relevant documents.However,the burst activities of an entity have been proved to be a significant signal to predict potential citations.In this paper,an entity burst discriminative model(EBDM)is presented to substantially exploit such burst features.The EBDM presents a new temporal representation based on the burst features,which can capture both temporal and semantic correlations between entities and documents.Meanwhile,in contrast to the bag-of-words model,the EBDM can significantly decrease the number of non-zero entries of feature vectors.An extensive set of experiments were conducted on the TREC-KBA-2012 dataset.The results show that the EBDM outperforms the performance of the state-of-the-art models.

Application of Fisher method to discriminating earthquakes and explosions using criterion m_b/M_S

We try to give a quantitative and global discrimination function by studying mb/MS data using Fisher method that is a kind of pattern recognition methods. The reliability of the function is also analyzed. The results show that this criterion works well and has a global feature, which can be used as first-level filtering criterions in event identification. The quantitative and linear discrimination function makes it possible to identify events automatically and achieve the goal to react the events quickly and effectively.