AN UNSUPERVISED NEURAL NETWORK APPROACH TO TOOL WEAR IDENTIFICATION

An unsupervised neural network approach is proposed for tool wear identification. Conventional pattern recognition approaches to automating the wear monitoring task are non-adaptive and require expensive or inaccessible information. Rangwala's application of the supervised backpropagation neural network to tool wear identification in a turning operation represented a pioneering effort to integrate sensor signals (cutting force and acoustic emission) and to employ a neural network in the classification of those signals. However, backpropagation also requires expensive training information and cannot remain adaptive after training. The unsupervised adaptive resonance network exhibited the ability to classify sensor signals into fresh and worn classes, to remain adaptive, and to utilize considerably less training information.     

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.     

Modular artificial neural network for prediction of petrophysicalproperties from well log data

An application of Kohonen's self-organizing map (SOM), learning-vector quantization (LVQ) algorithms, and commonly used backpropagation neural network (BPNN) to predict petrophysical properties obtained from well-log data are presented. A modular, artificial neural network (ANN) comprising a complex network made up from a number of subnetworks is introduced. In this approach, the SOM algorithm is applied first to classify the well-log data into a predefined number of classes, This gives an indication of the lithology in the well. The classes obtained from SOM are then appended back to the training input logs for the training of supervised LVQ. After training, LVQ can be used to classify any unknown input logs. A set of BPNN that corresponds to different classes is then trained. Once the network is trained, it is then used as the classification and prediction model for subsequent input data. Results obtained from example studies using the proposed method have shown to be fast and accurate as compared to a single BPNN network     

Classification of primary radar tracks using gaussian mixture models

Classification of primary surveillance radar tracks as either aircraft or non-aircraft is critical to a number of emerging applications, including airspace situational awareness and collision avoidance. Substantial research has focused on target classification of pre-processed radar surveillance data. Unfortunately, many non-aircraft tracks still pass through the clutter-reduction processing built into the aviation surveillance radars used by the Federal Aviation Administration. This paper demonstrates an approach to radar track classification that uses only post-processed position reports and does not require features that are typically only available during the pre-processing stage. Gaussian mixture models learned from recorded data are shown to perform well without the use of features that have been traditionally used for target classification, such as radar crosssection measurements.     

不同车型的车辆声音与振动信号特征研究

首先对高速公路现场采集到的两种车型共计74辆车,单辆车行驶时产生的地面振动和车外噪声信号进行AR参数模型分析,然后利用假设检验进行显著性差异检验,并对两种信号发生机理进行了初步讨论,设计了BP神经网络进行分类识别。分析结果表明,不同车型的地面振动和车外噪声信号AR模型参数具有差异性,车辆车外噪声的AR模型参数差异性远大于地面振动的AR模型参数差异性,用来作为车型识别的特征参数是可行的,其单辆车分类的正确率达80%以上。     

Security monitoring using microphone arrays and audio classification

In the paper, the authors propose a security monitoring system that can detect and classify the location and nature of different sounds within a room. This system is reliable and robust even in the presence of reverberation and in low signal-to-noise (SNR) environments. We describe a novel algorithm for audio classification, which, first, classifies an audio segment as speech or nonspeech and, second, classifies nonspeech audio segments into a particular audio type. To classify an audio segment as speech or nonspeech, this algorithm divides the audio segment into frames, estimates the presence of pitch in each frame, and calculates a pitch ratio (PR) parameter; it is this PR parameter that is used to discriminate speech audio segments from nonspeech audio segments. The discerning threshold for the PR parameter is adaptive to accommodate different environments. A time-delayed neural network is employed to further classify nonspeech audio segments into an audio type. The performance of this novel audio classification algorithm is evaluated using a library of audio segments. This library includes both speech segments and nonspeech segments, such as windows breaking and footsteps. Evaluation is performed under different SNR environments, both with and without reverberation. Using 0.4-s audio segments, the proposed algorithm can achieve an average classification accuracy of 94.5% for the reverberant library and 95.1% for the nonreverberant library.     

A novel RBF neural network for radar emitter recognition based on Rough Sets

With the spreading of radar emitter technology, it is more difficult for traditional methods to recognize radar emitter signals. In this article, a new method is proposed to establish a novel radial basis function (RBF) neural network for radar emitter recognition based on Rough Sets theory. First of all, radar emitter signals describing words are processed by Rough Sets, and the importance weight of each attribute is obtained and the classification rules are extracted. The classification rules are the basis of initial centers of Rough k-means. These initial centers can reduce the computational complexity of Rough k-means efficiently because of a priori knowledge from Rough Sets. In addition, basis functions of neural units of an RBF neural network are improved with attribute importance weights based on Rough Sets theory. The novel network structure makes the RBF neural network more effective. The simulation results show that novel RBF neural network radar emitter recognition can recognize radar emitter signals more effectively than a traditional RBF neural network, because of the improved Rough k-means and the network structure with attribute importance weights.     

超近程拦截系统中信号处理单元的研究

为了提高超近程系统拦截空中目标的有效性,采用线性切割器作为毁伤元,根据线性切割器的原理及特点,针对雷达系统后端数据处理的计算时间要求,在地面坐标系中建立雷达参数模型,研究一种雷达信号处理单元,该单元具有能够对超长信号做出高速实时处理的能力,且精度高,对提高超近程反导命中概率具有一定的实用价值.     

An Optimized Approach to Vehicle-Type Classification Using a Convolutional Neural Network

Vehicle type classification is considered a central part of an intelligent traffic system. In recent years, deep learning had a vital role in object detection in many computer vision tasks. To learn high-level deep features and semantics, deep learning offers powerful tools to address problems in traditional architectures of handcrafted feature-extraction techniques. Unlike other algorithms using handcrated visual features, convolutional neural network is able to automatically learn good features of vehicle type classification. This study develops an optimized automatic surveillance and auditing system to detect and classify vehicles of different categories. Transfer learning is used to quickly learn the features by recording a small number of training images from vehicle frontal view images. The proposed system employs extensive data-augmentation techniques for effective training while avoiding the problem of data shortage. In order to capture rich and discriminative information of vehicles, the convolutional neural network is fine-tuned for the classification of vehicle types using the augmented data. The network extracts the feature maps from the entire dataset and generates a label for each object (vehicle) in an image, which can help in vehicle-type detection and classification. Experimental results on a public dataset and our own dataset demonstrated that the proposed method is quite effective in detection and classification of different types of vehicles. The experimental results show that the proposed model achieves 96.04% accuracy on vehicle type classification.     

Application of an artificial neural network in chromatography—retention behavior prediction and pattern recognition

Layered feed-forward neural networks are powerful tools particularly suitable for the analysis of nonlinear multivariate data. In this paper, an artificial neural network using improved error back-propagation algorithm has been applied to solve problems in the field of chromatography. In this paper, an artificial neural network has been used in the following two applications: (1) To model retention behavior of 32 solutes in a methanol–tetrahydrofuran–water system and 49 solutes in methanol–acetonitrile–water system as a function of mobile phase compositions in high performance liquid chromatography. The correlation coefficients between the calculated and the experimental capacity factors were all larger than 0.98 for each solute in both the training set and the predicting set. The average deviation for all data points was 8.74% for the tetrahydrofuran-containing system and 7.33% for the acetonitrile-containing system. 2). To classify and predict two groups of different liver and bile diseases using bile acid data analyzed by reversed-phase high performance liquid chromatography (RP-HPLC). The first group includes three classes: healthy persons, choledocholithiasis patients and cholecystolithiasis patients; the total consistent rate of classification was 87%. The second group includes six classes: healthy persons, pancreas cancer patients, hepatoportal high pressure patients, cholelithiasis patients, cholangietic jaundice patients and hepatonecrosis patients; the total consistent rate of classification was 83%. It was shown that artificial neural network possesses considerable potential for retention prediction and pattern recognition based on chromatographic data.     

Analysis of low-order autoregressive models for ultrasonic grain signal characterization

When testing materials nondestructively with ultrasound, the grain scattering signal provides information that may be correlated to regional microstructure variation. Second and third-order autoregressive (AR) models are used to evaluate the spectral shift in grain signals by utilizing features such as resonating frequency, maximum energy frequency, or AR coefficients. Then, Euclidean distance, based on these features, is applied to classify grain scattering characteristics. Using both computer simulated data and experimental results, the probability of correct classification is found to be about 75% for the second-order AR model and 88% for the third-order AR model, when the conditions are such that the expected shift between the center frequency of echoes is less than 4%. This implies that, by increasing the order of the AR model, the frequency information extracted from the random signal is increased, which can result in obtaining a better classification.     

基于共空间模式和均匀流形投影的运动想象脑电信号识别方法

运动想象脑电信号的识别与分类问题一直是脑机领域研究的热点问题。针对此问题,使用区别传统线性降维方法的流形学习方法,将共空间模式算法与均匀流形投影算法相结合,充分利用了脑电信号中的非线性特征,对运动想象脑电信号进行了特征提取和数据降维,并使用KNN分类器进行了分类,对分类效果做出了评价;将降维前后的数据分类结果进行对比,说明了数据降维的优点和必要性;进一步讨论了降维结果在数据可视化方面的表现。发现经过数据降维的特征数据的可视化效果明显优于未经过降维的数据,进一步提出了一种基于共空间模式和均匀流形投影的新型脑电信号识别方法,对进行脑电信号深度剖析。挖掘脑电信号非线性特征提供了参考价值,同时也在数据流形分布以及数据可视化的角度为运动想象脑电信号识别提供了新思路。     

Advanced Agent Identification With Fluctuation-Enhanced Sensing

Conventional agent sensing methods normally use the steady state sensor values for agent classification. Many sensing elements (Hines , 1999; Ryan, 2004; Young, 2003;Qian, 2004; Qian, 2006; Carmel, 2003) are needed in order to correctly classify multiple agents in mixtures. Fluctuation-enhanced sensing (FES) looks beyond the steady-state values and extracts agent information from spectra and bispectra. As a result, it is possible to use a single sensor to perform multiple agent classification. This paper summarizes the application of some advanced algorithms that can classify and estimate concentrations of different chemical agents. Our tool involves two steps. First, spectral and bispectral features will be extracted from the sensor signals. The features contain unique agent characteristics. Second, the features are fed into a hyperspectral signal processing algorithm for agent classification and concentration estimation. The basic idea here is to use the spectral/bispectral shape information to perform agent classification. Extensive simulations have been performed by using simulated nanosensor data, as well as actual experimental data using commercial sensor (Taguchi). It was observed that our algorithms are able to accurately classify different agents, and also can estimate the concentration of the agents. Bispectra contain more information than spectra at the expense of high-computational costs. Specific nanostructured sensor model data yielded excellent performance because the agent responses are additive with this type of sensor. Moreover, for measured conventional sensor outputs, our algorithms also showed reasonable performance in terms of agent classification.     

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.     

Genetic algorithms for the optimization of piecewise linear discriminants

The application of genetic algorithms (GAs) to the optimization of piecewise linear discriminants is described. Piecewise linear discriminant analysis (PLDA) is a supervised pattern recognition technique employed in this work for the automated classification of Fourier transform infrared (FTIR) remote sensing data. PLDA employs multiple linear discriminants to approximate a nonlinear separating surface between data categories defined in a vector space. The key to the successful implementation of PLDA is the positioning of the individual discriminants that comprise the piecewise linear discriminant. For the remote sensing application, the discriminant optimization is challenging due to the large number of input variables required and the corresponding tendency for local optima to occur on the response surface of the optimization. In this work, three implementations of GAs are configured and evaluated: a binary-coded GA (GAB), a real-coded GA (GAR), and a Simplex-GA hybrid (SGA). GA configurations are developed by use of experimental design studies, and piecewise linear discriminants for acetone, methanol, and sulfur hexafluoride are optimized (trained). The training and prediction classification results indicate that GAs area viable approach for discriminant optimization. On average, the best piecewise linear discriminant optimized by a GA is observed to classify 11% more analyte-active patterns correctly in prediction than an unoptimized piecewise linear discriminant. Discriminant optimization problems not used in the experimental design study are employed to test the stability of the GA configurations. For these cases, the best piecewise linear discriminant optimized by SGA is shown to classify 19% more analyte-active patterns correctly in prediction than an unoptimized discriminant. These results also demonstrate that the two real number coded GAs (GAR and SGA) perform better than the GAB. Real number coded GAs are also observed to execute faster and are simpler to implement.     

RETRACTED: Automatic Arrhythmia Detection Based on Convolutional Neural Networks

ECG signal is of great importance in the clinical diagnosis of various heart diseases. The abnormal origin or conduction of excitation is the electrophysiological mechanism leading to arrhythmia, but the type and frequency of arrhythmia is an important indicator reflecting the stability of cardiac electrical activity. In clinical practice, arrhythmic signals can be classified according to the origin of excitation, the frequency of excitation, or the transmission of excitation. Traditional heart disease diagnosis depends on doctors, and it is influenced by doctors' professional skills and the department's specialty. ECG signal has the characteristics of weak signal, low frequency, large variation, and easy to be interfered. In this investigation, an ECG anomaly automatic classification system based on the convolutional neural network is proposed. The training sets of the convolutional neural network are ECG beats extracted from the MIT-BIH database as training sets. A 36-layer convolutional neural network (CNN) is trained based on Caffe framework to classify ECG signals automatically. The experimental results show that it can reach or even exceed the level of a senior cardiologist in judging three diseases: FIB, AFL and IVR.     

Analog fault diagnosis of actual circuits using neural networks

We have developed a neural-network based analog fault diagnostic system for actual circuits. Our system uses a data acquisition board to excite a circuit with an impulse and sample its output to collect training data for the neural network. The collected data is preprocessed by wavelet decomposition, normalization, and principal component analysis (PCA) to generate optimal features for training the neural network. This ensures a simple architecture for the neural network and minimizes the size of the training set required for its proper training. Our studies indicate that features extracted from actual circuits lie closer to each other and exhibit more overlap across fault classes compared to SPICE simulations. This implies that the neural network architecture which can most reliably perform fault diagnosis of actual circuits is one whose outputs estimate the probabilities that input features belong to different fault classes. Our work also shows that SPICE simulations can be used to select appropriate features for training the neural network. Reliable diagnosis of faults in an actual circuit, however, requires training data from the circuit itself. Our fault diagnostic system, trained and tested using data obtained from real sample circuits, achieves 95% accuracy in classifying faulty components     

基于卷积神经网络的光学遥感图像船只检测

目的研究无需进行复杂的图像预处理和人工特征提取,就能提高光学遥感图像的船只检测准确率和实现船只类型精细分类。方法对输入的检测图像,采用选择性搜索的方法产生船只候选区域,用已经标记好的训练样本对卷积神经网络进行监督训练,得到网络参数,然后使用经过监督训练的卷积神经网络提取抽象特征,并对候选区域进行分类,根据船只候选区域的分类概率同时确定船只的位置以及类型。结果与现有的2种检测方法进行对比,实验结果表明卷积神经网络能有效提高船只检测准确率,平均检测准确率达到了93.3%。结论该检测方法无需进行复杂的预处理,能同时对船只进行检测和分类,并能有效提高船只检测准确率。     

An automated methodology for the classification of focal and nonfocal EEG signals using a hybrid classification approach

The uncertainty in human brain leads to the formation of epilepsy disease in human. The automatic detection and severity analysis of epilepsy disease is proposed in this article using a hybrid classification algorithm. The proposed method consists of decomposition stage, feature extraction, and classification stages. The electroencephalogram (EEG) signals are decomposed using dual-tree complex wavelet transform and then features are extracted from these coefficients. These features are then classified using the neural network classification approach in order to classify the EEG signals into either focal or nonfocal EEG signals. Furthermore, severity of the focal EEG signal is analyzed using an adaptive neuro-fuzzy inference system classification approach. The proposed hybrid classification method for the classification of focal signals and nonfocal signals achieved 98.6% of sensitivity, 99.1% of specificity, and 99.4% of accuracy. The average detection rate for both focal and nonfocal dataset is about 98.5%.