A multi-scale convolutional auto-encoder and its application in fault diagnosis of rolling bearings

Aiming at the difficulty of fault identification caused by manual extraction of fault features of rotating machinery,a one-dimensional multi-scale convolutional auto-encoder fault diagnosis model is proposed,based on the standard convolutional auto-encoder.In this model,the parallel convolutional and deconvolutional kernels of different scales are used to extract the features from the input signal and reconstruct the input signal;then the feature map extracted by multi-scale convolutional kernels is used as the input of the classifier;and finally the parameters of the whole model are fine-tuned using labeled data.Experiments on one set of simulation fault data and two sets of rolling bearing fault data are conducted to validate the proposed method.The results show that the model can achieve 99.75%,99.3%and 100%diagnostic accuracy,respectively.In addition,the diagnostic accuracy and reconstruction error of the one-dimensional multi-scale convolutional auto-encoder are compared with traditional machine learning,convolutional neural networks and a traditional convolutional auto-encoder.The final results show that the proposed model has a better recognition effect for rolling bearing fault data.

Adaptive Optimal Control of Space Tether System for Payload Capture via Policy Iteration

The libration control problem of space tether system(STS)for post-capture of payload is studied.The process of payload capture will cause tether swing and deviation from the nominal position,resulting in the failure of capture mission.Due to unknown inertial parameters after capturing the payload,an adaptive optimal control based on policy iteration is developed to stabilize the uncertain dynamic system in the post-capture phase.By introducing integral reinforcement learning(IRL)scheme,the algebraic Riccati equation(ARE)can be online solved without known dynamics.To avoid computational burden from iteration equations,the online implementation of policy iteration algorithm is provided by the least-squares solution method.Finally,the effectiveness of the algorithm is validated by numerical simulations.

Tongue image segmentation and tongue color classification based on deep learning

Objective To propose two novel methods based on deep learning for computer-aided tongue diagnosis,including tongue image segmentation and tongue color classification,improving their diagnostic accuracy.Methods LabelMe was used to label the tongue mask and Snake model to optimize the labeling results.A new dataset was constructed for tongue image segmentation.Tongue color was marked to build a classified dataset for network training.In this research,the Inception+Atrous Spatial Pyramid Pooling(ASPP)+UNet(IAUNet)method was proposed for tongue image segmentation,based on the existing UNet,Inception,and atrous convolution.Moreover,the Tongue Color Classification Net(TCCNet)was constructed with reference to ResNet,Inception,and Triple-Loss.Several important measurement indexes were selected to evaluate and compare the effects of the novel and existing methods for tongue segmentation and tongue color classification.IAUNet was compared with existing mainstream methods such as UNet and DeepLabV3+for tongue segmentation.TCCNet for tongue color classification was compared with VGG16 and GoogLeNet.Results IAUNet can accurately segment the tongue from original images.The results showed that the Mean Intersection over Union(MIoU)of IAUNet reached 96.30%,and its Mean Pixel Accuracy(MPA),mean Average Precision(mAP),F1-Score,G-Score,and Area Under Curve(AUC)reached 97.86%,99.18%,96.71%,96.82%,and 99.71%,respectively,suggesting IAUNet produced better segmentation than other methods,with fewer parameters.Triplet-Loss was applied in the proposed TCCNet to separate different embedded colors.The experiment yielded ideal results,with F1-Score and mAP of the TCCNet reached 88.86% and 93.49%,respectively.Conclusion IAUNet based on deep learning for tongue segmentation is better than traditional ones.IAUNet can not only produce ideal tongue segmentation,but have better effects than those of PSPNet,SegNet,UNet,and DeepLabV3+,the traditional networks.As for tongue color classification,the proposed network,TCCNet,had better F1-Score and mAP values as compared with other neural networks such as VGG16 and GoogLeNet.

Prediction of Departure Aircraft Taxi Time Based on Deep Learning

With the continuous increase in the number of flights,the use of airport collaborative decision-making(ACDM)systems has been more and more widely spread.The accuracy of the taxi time prediction has an important effect on the A-CDM calculation of the departure aircraft’s take-off queue and the accurate time for the aircraft blockout.The spatial-temporal-environment deep learning(STEDL)model is presented to improve the prediction accuracy of departure aircraft taxi-out time.The model is composed of time-flow sub-model(airport capacity,number of taxiing aircraft,and different time periods),spatial sub-model(taxiing distance)and environmental sub-model(weather,air traffic control,runway configuration,and aircraft category).The STEDL model is used to predict the taxi time of departure aircraft at Hong Kong Airport and the results show that the STEDL method has a prediction accuracy of 95.4%.The proposed model also greatly reduces the prediction error rate compared with the other machine learning methods.

Arrival Pattern Recognition and Prediction Based on Machine Learning

A data-driven method for arrival pattern recognition and prediction is proposed to provide air traffic controllers(ATCOs)with decision support. For arrival pattern recognition,a clustering-based method is proposed to cluster arrival patterns by control intentions. For arrival pattern prediction,two predictors are trained to estimate the most possible command issued by the ATCOs in a particular traffic situation. Training the arrival pattern predictor could be regarded as building an ATCOs simulator. The simulator can assign an appropriate arrival pattern for each arrival aircraft,just like real ATCOs do. Therefore,the simulator is considered to be able to provide effective advice for part of the work of ATCOs. Finally,a case study is carried out and demonstrates that the convolutional neural network(CNN)-based predictor performs better than the radom forest(RF)-based one.

Iterative sliding mode control strategy of robotic arm based on fractional calculus

In order to improve the control performance of industrial robotic arms,an efficient fractional-order iterative sliding mode control method is proposed by combining fractional calculus theory with iterative learning control and sliding mode control.In the design process of the controller,fractional approaching law and fractional sliding mode control theories are used to introduce fractional calculus into iterative sliding mode control,and Lyapunov theory is used to analyze the system stability.Then taking a two-joint robotic arm as an example,the proposed control strategy is verified by MATLAB simulation.The simulation experiments show that the fractional-order iterative sliding mode control strategy can effectively improve the tracking speed and tracking accuracy of the joint,reduce the tracking error,have strong robustness and effectively suppress the chattering phenomenon of sliding mode control.

A Cumulative Proportional Odds Model to Analyze the Influence of Mass Media on Teenagers in Messina

The media are constantly evolving at a breakneck pace and mainly young people, with their flexibility of mind and their continuous curiosity, can better understand the characteristics and potential of such advances. The aim of this paper is to analyze the relationship between teenagers and media, in order to try to better understand the habits and to conduct analysis on social interactions with young people. In order to evaluate the influence of mass media in the life of the young people, the Statisticians of Messina University decided to perform a statistical survey to evaluate the influence of the media in the life of Messina＇s teenagers. A questionnaire entitled ＂Perceptions of the influence exerted by mass media＂ was administered in some schools. From the methodological point of view, three statistical models were estimated in order to formalize the dependence of the mass media influence by the kind of TV programs, the time spent on TV viewing and computer use and the kind of most used social networks. Since the mass media influence is an ordinal variable expressed by four ordered categories （1 = nothing; 2 = low; 3 = average; 4 = high） we used the Cumulative Proportional Odds Model to formalize the dependence by the potential predictors.

Study of the Practice Teaching Reform of Floriculture

This paper analyzes the current situation and problems of the of gardening flowers professional practice teaching, including： rigid and obsolete teaching mode, student learning enthusiasm deficiencies; practice over a single, and the lack of opportunity to practice and platform; lack of software and hardware construction, internship bases imperfect; lack of teachers＇ quality, teaching lack the times. The paper proposes a gardening the flowers professional practice teaching improvement strategies, including： innovative teaching ideas, improvement of education quality; comprehensive local conditions perfect practice, promote the construction and improvement of the practice platform; increase funding, improve the practice teachin~ base; to enhance the training and continuing education to improve practice, the overall quality of the course insla＇uctor.

Object detection of artifact threaded hole based on Faster R-CNN

In order to improve the accuracy of threaded hole object detection,combining a dual camera vision system with the Hough transform circle detection,we propose an object detection method of artifact threaded hole based on Faster region-ased convolutional neural network(Faster R-CNN).First,a dual camera image acquisition system is established.One industrial camera placed at a high position is responsible for collecting the whole image of the workpiece,and the suspected screw hole position on the workpiece can be preliminarily selected by Hough transform detection algorithm.Then,the other industrial camera is responsible for collecting the local images of the suspected screw holes that have been detected by Hough transform one by one.After that,ResNet50-based Faster R-CNN object detection model is trained on the self-built screw hole data set.Finally,the local image of the threaded hole is input into the trained Faster R-CNN object detection model for further identification and location.The experimental results show that the proposed method can effectively avoid small object detection of threaded holes,and compared with the method that only uses Hough transform or Faster RCNN object detection alone,it has high recognition and positioning accuracy.

Bar in SILL Questionnaire for Multiple Results Processing： Users＇ Frequency and Confidence

One hundred and fifteen first-year students of Greek took the SILL （Strategy Inventory for Language Learning） questionnaire in an attempt to reveal and activate potential a successful and widely used questionnaire like SILL might have but not identified and investigated so far. The first original point to be investigated, tackled in a previous experiment （Kambakis-Vougiouklis, 2012）, concerns users＇ confidence whether their choice of a specific strategy is effective while the second point concerns the use of the bar as an alternative statistical tool. More specifically, in this particular experiment the bar is not divided only into five equal length spaces as in the first experiment but also into five equal area spaces according to Gauss distribution, giving the researcher the chance to investigate possible differences between two ways of data processing--an advantage only the use of the bar could provide in the analysis stage. Additionally, there are advantages concerning results collection, as subjects and researcher will have a completely free choice among infinite points on a line rather than a limited 3, 4, 5, and 6 of a Likert scale, avoiding at the same time fine verbal differences between different subdivisions. Although the two different methods of processing performed homogeneous behaviour with not statistically considerable differences, it needs further applications in order to reach safe conclusions

ITERATIVE MULTICHANNEL BLIND DECONVOLUTION METHOD FOR TEMPORALLY COLORED SOURCES

An iterative separation approach, i.e. source signals are extracted and removed one by one, is proposed for multichannel blind deconvolution of colored signals. Each source signal is extracted in two stages: a filtered version of the source signal is first obtained by solving the generalized eigenvalue problem, which is then followed by a single channel blind deconvolution based on ensemble learning. Simulation demonstrates the capability of the approach to perform efficient mutichannel blind deconvolution.

Cultivated land information extraction in UAV imagery based on deep convolutional neural network and transfer learning

The development of precision agriculture demands high accuracy and efficiency of cultivated land information extraction. As a new means of monitoring the ground in recent years, unmanned aerial vehicle （UAV） low-height remote sensing technique, which is flexible, efficient with low cost and with high resolution, is widely applied to investing various resources. Based on this, a novel extraction method for cultivated land information based on Deep Convolutional Neural Network and Transfer Learning （DTCLE） was proposed. First, linear features （roads and ridges etc.） were excluded based on Deep Convolutional Neural Network （DCNN）. Next, feature extraction method learned from DCNN was used to cultivated land information extraction by introducing transfer learning mechanism. Last, cultivated land information extraction results were completed by the DTCLE and eCognifion for cultivated land information extraction （ECLE）. The location of the Pengzhou County and Guanghan County, Sichuan Province were selected for the experimental purpose. The experimental results showed that the overall precision for the experimental image 1, 2 and 3 （of extracting cultivated land） with the DTCLE method was 91.7%, 88.1% and 88.2% respectively, and the overall precision of ECLE is 9o.7%, 90.5% and 87.0%, respectively. Accuracy of DTCLE was equivalent to that of ECLE, and also outperformed ECLE in terms of integrity and continuity.

External and Internal Validation of a Computer Assisted Diagnostic Model for Detecting Multi-Organ Mass Lesions in CT images

Objective We developed a universal lesion detector(ULDor)which showed good performance in in-lab experiments.The study aims to evaluate the performance and its ability to generalize in clinical setting via both external and internal validation.Methods The ULDor system consists of a convolutional neural network(CNN)trained on around 80 K lesion annotations from about 12 K CT studies in the DeepLesion dataset and 5 other public organ-specific datasets.During the validation process,the test sets include two parts:the external validation dataset which was comprised of 164 sets of non-contrasted chest and upper abdomen CT scans from a comprehensive hospital,and the internal validation dataset which was comprised of 187 sets of low-dose helical CT scans from the National Lung Screening Trial(NLST).We ran the model on the two test sets to output lesion detection.Three board-certified radiologists read the CT scans and verified the detection results of ULDor.We used positive predictive value(PPV)and sensitivity to evaluate the performance of the model in detecting space-occupying lesions at all extra-pulmonary organs visualized on CT images,including liver,kidney,pancreas,adrenal,spleen,esophagus,thyroid,lymph nodes,body wall,thoracic spine,etc.Results In the external validation,the lesion-level PPV and sensitivity of the model were 57.9%and 67.0%,respectively.On average,the model detected 2.1 findings per set,and among them,0.9 were false positives.ULDor worked well for detecting liver lesions,with a PPV of 78.9%and a sensitivity of 92.7%,followed by kidney,with a PPV of 70.0%and a sensitivity of 58.3%.In internal validation with NLST test set,ULDor obtained a PPV of 75.3%and a sensitivity of 52.0%despite the relatively high noise level of soft tissue on images.Conclusions The performance tests of ULDor with the external real-world data have shown its high effectiveness in multiple-purposed detection for lesions in certain organs.With further optimisation and iterative upgrades,ULDor may be well suited for extensive application to external data.

Knowledge Barriers Based on Standards in Global Value Chain

The knowledge accumulation through knowledge acquisition and technological learning is a necessary condition for enterprise upgrading in global chains.The knowledge flow obstacle caused by the knowledge barriers is the major reason for low-locked in the global value chain based on the analysis of knowledge flow,where standard is one of the most cmmonly used knowledge barriers.In this regard,a standard strategy based on similar technology development can be adopted to step over knowledge barriers and achieve upgrading.

AN EMPIRICAL STUDY ON THE DEVELOPMENT OF L2 VOCABULARY ACQUISITION BY NON-ENGLISH MAJORS

词汇是语言学习者的主要障碍之一,也是二语习得研究领域中的一个重大课题。作者通过对沈阳师范大学的60名非英语专业学生的消极词汇、半积极词汇和积极词汇进行两次不同时间的测试,随后用SPSS软件对所采集的数据进行分析,得出结论:通过一年的英语学习,受试者的消极词汇量和半积极词汇量均有显著提高,而积极词汇量却无显著变化,说明学习者的积极词汇在二语词汇习得过程中出现了停滞和僵化现象,很难继续发展。作者由此对二语词汇教学与学习提出了一些建议。

Classification of hyperspectral images based on a convolutional neural network and spectral sensitivity

In recent years,deep learning methods have gradually come to be used in hyperspectral imaging domains.Because of the peculiarity of hyperspectral imaging,a mass of information is contained in the spectral dimensions of hyperspectral images.Also,different ob jects on a land surface are sensitive to different ranges of wavelength.To achieve higher accuracy in classification,we propose a structure that combines spectral sensitivity with a convolutional neural network by adding spectral weights derived from predicted outcomes before the final classification layer.First,samples are divided into visible light and infrared,with a portion of the samples fed into networks during training.Then,two key parameters,unrecognized rate(δ)and wrongly recognized rate(γ),are calculated from the predicted outcome of the whole scene.Next,the spectral weight,derived from these two parameters,is calculated.Finally,the spectral weight is added and an improved structure is constructed.The improved structure not only combines the features in spatial and spectral dimensions,but also gives spectral sensitivity a primary status.Compared with inputs from the whole spectrum,the improved structure attains a nearly 2%higher prediction accuracy.When applied to public data sets,compared with the whole spectrum,on the average we achieve approximately 1%higher accuracy.

EncyCatalogRec: catalog recommendation for encyclopedia article completion

Online encyclopedias such as Wikipedia provide a large and growing number of articles on many topics.However,the content of many articles is still far from complete.In this paper,we propose Ency Catalog Rec,a system to help generate a more comprehensive article by recommending catalogs.First,we represent articles and catalog items as embedding vectors,and obtain similar articles via the locality sensitive hashing technology,where the items of these articles are considered as the candidate items.Then a relation graph is built from the articles and the candidate items.This is further transformed into a product graph.So,the recommendation problem is changed to a transductive learning problem in the product graph.Finally,the recommended items are sorted by the learning-to-rank technology.Experimental results demonstrate that our approach achieves state-of-the-art performance on catalog recommendation in both warm-and cold-start scenarios.We have validated our approach by a case study.

CONVERGENCE ANALYSIS IN SENSE OF LEBESGUE-p NORM OF DECENTRALIZED NON-REPETITIVE ITERATIVE LEARNING CONTROL FOR LINEAR LARGE-SCALE SYSTEMS

In this paper,a decentralized iterative learning control strategy is embedded into theprocedure of hierarchical steady-state optimization for a class of linear large-scale industrial processeswhich consists of a number of subsystems.The task of the learning controller for each subsystem is toiteratively generate a sequence of upgraded control inputs to take responsibilities of a sequential stepfunctional control signals with distinct scales which are determined by the local decision-making units inthe two-layer hierarchical steady-state optimization processing.The objective of the designated strategyis to consecutively improve the transient performance of the system.By means of the generalized Younginequality of convolution integral,the convergence of the learning algorithm is analyzed in the sense ofLebesgue-p norm.It is shown that the inherent feature of system such as the multi-dimensionality andthe interaction may influence the convergence of the non-repetitive learning rule.Numerical simulationsillustrate the effectiveness of the proposed control scheme and the validity of the conclusion.

Two-level hierarchical feature learning for image classification

In some image classification tasks, similarities among different categories are different and the samples are usually misclassified as highly similar categories. To distinguish highly similar categories, more specific features are required so that the classifier can improve the classification performance. In this paper, we propose a novel two-level hierarchical feature learning framework based on the deep convolutional neural network(CNN), which is simple and effective. First, the deep feature extractors of different levels are trained using the transfer learning method that fine-tunes the pre-trained deep CNN model toward the new target dataset. Second, the general feature extracted from all the categories and the specific feature extracted from highly similar categories are fused into a feature vector. Then the final feature representation is fed into a linear classifier. Finally, experiments using the Caltech-256, Oxford Flower-102, and Tasmania Coral Point Count(CPC) datasets demonstrate that the expression ability of the deep features resulting from two-level hierarchical feature learning is powerful. Our proposed method effectively increases the classification accuracy in comparison with flat multiple classification methods.