基于改进判别字典学习的故障诊断方法

近年来,基于稀疏表示的分类技术在模式识别中取得一定的成功。该框架中,字典的学习和分类器的训练通常是两个独立的模块,降低了方法的识别精度。针对以上问题,提出了一种特征提取和模式识别相融合的改进判别字典学习模型,将重构误差项、稀疏编码判别项及分类误差项进行了整合,并用K奇异值分解算法对目标函数进行优化,实现了字典和分类器的同步学习。该方法先对原始信号进行经验模态分解,并从分解的本征模态函数中提取时、频特征,形成故障样本;然后将训练样本输入改进模型用K奇异值分解优化;最后用习得字典及分类器权重对测试样本进行识别。实验结果表明：该算法不但适用于小样本故障问题,而且鲁棒性和分类性能都明显高于其它算法。         

A physical approach to the automated ultrasonic characterization of buried weld defects in ferritic steel

This paper is concerned with the problem of automatically discriminating both smooth and rough cracks from more benign volumetric flaws such as porosity and slag, using pulse-echo ultrasound. Unlike many previous approaches, digital ultrasonic data were collected from transducers scanned over the whole of each reflector. Scans were also made using different angles of ultrasound.Qualitative physical models for the interaction of ultrasound with these defects are developed to identify three independent effects that, together, could be used to distinguish between these four classes of defect. Each effect is quantified by numerical features computed from the ultrasonic data and criteria are developed to select one feature for each effect. Automated defect classification is then achieved by a weighted minimum distance pattern recognition algorithm. The preliminary application of this approach to a database containing feature values from 40 buried defects in ferritic steel welds gave a classification success rate of 100%.     

基于AHP-熵权法的货舱码垛效果模糊综合评价

目的 解决快递包裹物流过程中暴力分拣问题的前提是对暴力分拣行为进行有效识别,为此提出一种基于加速度分布特征的快递包裹暴力分拣行为智能识别方法。方法 利用集成三轴加速度传感器的数据采集设备实时采集并截取潜在异常操作情况下快递包裹的加速度数据。然后将潜在异常数据上传服务器,在服务器端执行分布特征的提取。最后将特征矩阵送入神经元网络分类器,得到当前包裹所受操作类别的结果。结果 实验证明,文中提出的多阈值截取方法可以有效截取潜在异常数据,使用加速度分布作为特征可以有效对暴力分拣行为进行分类。其中,使用BP网络作为模式识别分类器时,分类正确率可以达到93.6%;使用CNN作为模式识别分类器时,分类正确率可以达到95.3%。结论 文中提出的暴力分拣识别方法准确、快速,具有良好的在线实时性。基于此方法可以构建暴力分拣行为识别数据库,为进一步完善快递企业服务水平定量化评价体系提供数据支撑。这些数据还可以用于对暴力分拣产生的原因进行深入分析,从而提出减少暴力分拣行为的针对性解决方案。     

基于加速度分布特征的快递暴力分拣识别方法

目的 针对我国烟草物流配送中心包装效率低、人工成本高、条烟差错率高等问题,设计一种异型烟全自动码垛的控制系统。方法 设计基于SIMATIC S7-1200 PLC、步科MT4523TE触摸屏、YAMAHA机器人控制器RCX240和工控机的控制系统,PLC作为主控制器,与触摸屏和工控机采用PROFINET通讯,与YAMAHA控制器采用PROFIBUS通讯,实现信息的交互。外接的控制按钮、传感器、伺服驱动器与PLC的SM1223和SM1231信号模块连接。PLC将传感器采集的信号和工控机发送的数据进行处理,然后与机器人控制器配合发出各种控制指令,通过各个机构相互协调动作实现对异型烟的快速、自动、精确码垛。结果 该套控制系统可对异型烟长、高进行自动识别,码垛差错率≤0.006%,对垛型进行自动整理功能,损烟率≤0.005%,设备故障率≤0.5%,码垛效率可达3861条/h,系统运行稳定。结论 该套控制系统大大提高了异型烟的码垛效率,降低了生产成本,具有良好的可靠性和稳定性,满足烟草物流配送中心高效稳定作业的要求。     

Sample partition and grouped sparse representation

Recently, conventional representation-based classification (RBC) methods demonstrate promising performance in image recognition. However, conventional RBCs only use a kind of deviations between the test sample and the linear combination of training samples of each class to perform classification. In many cases, a single kind of deviations corresponding to each class cannot effectively reflect the difference between the test sample and reconstructed sample of each class. Moreover, in practical applications, limited training samples are not able to reflect the possible changes of the image sufficiently. In this paper, we propose a novel scheme to tackle the above-mentioned problems. Specifically, we first use the original training samples to generate corresponding mirror samples. Thus, the original sample set and its mirror counterpart are treated as two separate training groups. Secondly, we perform collaborative representation classification on these two groups from which each class leads to two kinds of deviations, respectively. Finally, we fuse two kinds of deviations of each class and their correlation coefficient to classify the test sample. The correlation coefficient is defined for two kinds of deviations of each class. Experimental results on four databases show the proposed scheme can improve the recognition rate in image-based recognition.     

Finding a cluster of points and the grey pattern quadratic assignment problem

In this paper we propose a model which aims at selecting a tight cluster from a set of points. The same formulation applies also to the grey pattern problem where the objective is to find a set of black dots in a rectangular grid with a given density so that the dots are spread as evenly as possible. A branch and bound algorithm and five heuristic approaches are proposed. Computational results demonstrate the efficiency of these approaches. Seven grey pattern problems are solved to optimality and for eight additional grey pattern problems the best known solution is improved. The cluster problem on a network is solved for 40 problems with the number of points ranging between 100 and 900 and the size of the cluster ranging between 5 and 200. Twenty one problems were solved optimally and the remaining 19 problems were heuristically solved in a very short computer time with excellent results.     

Automatic identification of bird targets with radar via patterns produced by wing flapping.

Bird identification with radar is important for bird migration research, environmental impact assessments (e.g. wind farms), aircraft security and radar meteorology. In a study on bird migration, radar signals from birds, insects and ground clutter were recorded. Signals from birds show a typical pattern due to wing flapping. The data were labelled by experts into the four classes BIRD, INSECT, CLUTTER and UFO (unidentifiable signals). We present a classification algorithm aimed at automatic recognition of bird targets. Variables related to signal intensity and wing flapping pattern were extracted (via continuous wavelet transform). We used support vector classifiers to build predictive models. We estimated classification performance via cross validation on four datasets. When data from the same dataset were used for training and testing the classifier, the classification performance was extremely to moderately high. When data from one dataset were used for training and the three remaining datasets were used as test sets, the performance was lower but still extremely to moderately high. This shows that the method generalizes well across different locations or times. Our method provides a substantial gain of time when birds must be identified in large collections of radar signals and it represents the first substantial step in developing a real time bird identification radar system. We provide some guidelines and ideas for future research.     

Automated screening of glaucoma stages from retinal fundus images using BPS and LBP based GLCM features

Glaucoma is an eye disease in which the retinal nerve fibers are irreversibly damaged. Early identification of glaucoma is essential because it may slow the progression of the illness. The clinical treatments and medical imaging methods that are currently available are all manual and require expert supervision. An automated glaucoma diagnosis system that is fast, accurate, and helps to reduce the load on professionals is necessary for mass screening. In our proposed work, a novel approach based on bit-plane slicing (BPS), local binary pattern (LBP), and gray-level co-occurrence matrix (GLCM) is used. First, fundus images are separated into channels like red, green, and blue, and these separated channels are split into plans using BPS. Then, LBP images are obtained from selected green channel images. Second, we extract features based on GLCM from LBP images. Finally, using a least-squares support vector machine classifier, the higher ranked features are employed to classify glaucoma stages. According to the findings of the experiments, our model outperformed state-of-the-art approaches for glaucoma classification. Using 10-fold cross-validation, this model achieved an improved classification accuracy of 95.04%, specificity of 96.37%, and sensitivity of 93.77%. We conducted many relative experiments with deep learning and traditional machine learning-based models to test our proposed methodology. Compared to existing glaucoma classification approaches, the new method has been shown to be more efficient.     

A lazy data mining approach for protein classification

In this work, we propose a new computational technique to solve the protein classification problem. The goal is to predict the functional family of novel protein sequences based on their motif composition. In order to improve the results obtained with other known approaches, we propose a new data mining technique for protein classification based on Bayes' theorem, called highest subset probability (HiSP). To evaluate our proposal, datasets extracted from Prosite, a curated protein family database, are used as experimental datasets. The computational results have shown that the proposed method outperforms other known methods for all tested datasets and looks very promising for problems with characteristics similar to the problem addressed here. In addition, our experiments suggest that HiSP performs well on highly imbalanced datasets     

面向语义的精简化多关系频繁模式发现方法

多关系频繁模式发现能够直接从复杂结构化数据中发现涉及多个关系的复杂频繁模式,避免了传统方法的局限。有别于主流基于归纳逻辑程序设计技术的方法,提出了基于合取查询包含关系的面向语义的精简化多关系频繁模式发现方法,具有理论与技术基础的新颖性,解决了两种语义冗余问题。实验表明,该方法在可理解性、功能、效率以及可扩展性方面具有优势。     

Deep Learning-Based Approach for Arabic Visual Speech Recognition

Lip-reading technologies are rapidly progressing following the breakthrough of deep learning. It plays a vital role in its many applications, such as: human-machine communication practices or security applications. In this paper, we propose to develop an effective lip-reading recognition model for Arabic visual speech recognition by implementing deep learning algorithms. The Arabic visual datasets that have been collected contains 2400 records of Arabic digits and 960 records of Arabic phrases from 24 native speakers. The primary purpose is to provide a high-performance model in terms of enhancing the preprocessing phase. Firstly, we extract keyframes from our dataset. Secondly, we produce a Concatenated Frame Images (CFIs) that represent the utterance sequence in one single image. Finally, the VGG-19 is employed for visual features extraction in our proposed model. We have examined different keyframes: 10, 15, and 20 for comparing two types of approaches in the proposed model: (1) the VGG-19 base model and (2) VGG-19 base model with batch normalization. The results show that the second approach achieves greater accuracy: 94% for digit recognition, 97% for phrase recognition, and 93% for digits and phrases recognition in the test dataset. Therefore, our proposed model is superior to models based on CFIs input.     

A chemometric approach for brain tumor classification using magnetic resonance imaging and spectroscopy

A new classification approach was developed to improve the noninvasive diagnosis of brain tumors. Within this approach, information is extracted from magnetic resonance imaging and spectroscopy data, from which the relative location and distribution of selected tumor classes in feature space can be calculated. This relative location and distribution is used to select the best information extraction procedure, to identify overlapping tumor classes, and to calculate probabilities of class membership. These probabilities are very important, since they provide information about the reliability of classification and might provide information about the heterogeneity of the tissue. Classification boundaries were calculated by setting thresholds for each investigated tumor class, which enabled the classification of new objects. Results on histopathologically determined tumors are excellent, demonstrated by spatial maps showing a high probability for the correctly identified tumor class and, moreover, low probabilities for other tumor classes.     

Continuous-time algorithms for scheduling a single machine with sequence-dependent setup times and time window constraints in coordinated chains

In this paper we address the problem of selecting and scheduling several jobs on a single machine with sequence-dependent setup times and strictly enforced time window constraints on the start time of each job. We use short-term production targets to coordinate decentralised local schedulers and to make the objectives of specific areas in line with the chain objectives by maintaining a desired work in process profile in manufacturing environments. The existing literature in this domain is based on discrete-time approaches. We depart from prior approaches by considering continuous time. We introduce a two-step mathematical programming model based on disjunctive constraints to solve small problems to optimality, and propose an insertion-based heuristic to solve large-scale instances. We provide several variations of the insertion heuristic based on different score functions. The primary objective of these approaches is to maximise the total defined score for jobs while satisfying production targets for families of jobs in each shift. Further, our models minimise the maximum completion time of all selected jobs. The effectiveness, efficiency, and robustness of the proposed algorithms are analysed and compared with the existing literature.     

Synaptic Device Network Architecture with Feature Extraction for Unsupervised Image Classification

For the efficient recognition and classification of numerous images, neuroinspired deep learning algorithms have demonstrated their substantial performance. Nevertheless, current deep learning algorithms that are performed on von Neumann machines face significant limitations due to their inherent inefficient energy consumption. Thus, alternative approaches (i.e., neuromorphic systems) are expected to provide more energy‐efficient computing units. However, the implementation of the neuromorphic system is still challenging due to the uncertain impacts of synaptic device specifications on system performance. Moreover, only few studies are reported how to implement feature extraction algorithms on the neuromorphic system. Here, a synaptic device network architecture with a feature extraction algorithm inspired by the convolutional neural network is demonstrated. Its pattern recognition efficacy is validated using a device‐to‐system level simulation. The network can classify handwritten digits at up to a 90% recognition rate despite using fewer synaptic devices than the architecture without feature extraction.     

Principle of pattern-signature synthesis and analysis based on double optical correlations

Pattern-recognition problems for which patterns cannot be recognized directly but by their attitudes and/or behaviors is addressed. To analyze these attitudes, pattern signatures are generated from picture sequences. Two complementary signature synthesis algorithms are presented. The architecture is made up of two cascaded correlators. The first is used to create the signatures and the second to classify them. We focus our analysis on the case of optical implementations. Illustrations are given in the case of face recognition by attitudes (multisensor in the optronic imaging range) and moving-target recognition by behavior (in the radar imaging range).     

一种快速的基于稀疏表示的人脸识别算法

基于稀疏表示的人脸识别算法（SRC）识别率相当高,但是当使用l1范数求最优的稀疏表示时,大大增加了算法的计算复杂度,矩阵随着维度的增加,计算时间呈几何级别上升,该文提出利用拉格朗日算法求解矩阵的逆的推导思路,用一种简化的伪逆求解方法来代替l1范数的计算,可将运算量较高的矩阵求逆运算转变为轻量级向量矩阵运算,基于AR人脸库的实验证明,维度高的时候识别率高达97%,同时,计算复杂度和开销比SRC算法大幅度降低95%。     

A nonlinear programming technique to compute a tight lower bound for the real structured singular value

The real structured singular value (RSSV, or real μ) is a useful measure to analyze the robustness of linear systems subject to structured real parametric uncertainty, and surely a valuable design tool for the control systems engineers. We formulate the RSSV problem as a nonlinear programming problem and use a new computation technique, F-modified subgradient (F-MSG) algorithm, for its lower bound computation. The F-MSG algorithm can handle a large class of nonconvex optimization problems and requires no differentiability. The RSSV computation is a well known NP hard problem. There are several approaches that propose lower and upper bounds for the RSSV. However, with the existing approaches, the gap between the lower and upper bounds is large for many problems so that the benefit arising from usage of RSSV is reduced significantly. Although the F-MSG algorithm aims to solve the nonconvex programming problems exactly, its performance depends on the quality of the standard solvers used for solving subproblems arising at each iteration of the algorithm. In the case it does not find the optimal solution of the problem, due to its high performance, it practically produces a very tight lower bound. Considering that the RSSV problem can be discontinuous, it is found to provide a good fit to the problem. We also provide examples for demonstrating the validity of our approach.     

Improved Logistic Regression Algorithm Based on Kernel Density Estimation for Multi-Classification with Non-Equilibrium Samples

Logistic regression is often used to solve linear binary classification problems such as machine vision, speech recognition, and handwriting recognition. However, it usually fails to solve certain nonlinear multi-classification problem, such as problem with non-equilibrium samples. Many scholars have proposed some methods, such as neural network, least square support vector machine, AdaBoost meta-algorithm, etc. These methods essentially belong to machine learning categories. In this work, based on the probability theory and statistical principle, we propose an improved logistic regression algorithm based on kernel density estimation for solving nonlinear multi-classification. We have compared our approach with other methods using non-equilibrium samples, the results show that our approach guarantees sample integrity and achieves superior classification.