Time-based compression and classification of heartbeats

Heart function measured by electrocardiograms (ECG) is crucial for patient care. ECG generated waveforms are used to find patterns of irregularities in cardiac cycles in patients. In many cases, irregularities evolve over an extended period of time that requires continuous monitoring. However, this requires wireless ECG recording devices. These devices consist of an enclosed system that includes electrodes, processing circuitry, and a wireless communication block imposing constraints on area, power, bandwidth, and resolution. In order to provide continuous monitoring of cardiac functions for real-time diagnostics, we propose a methodology that combines compression and analysis of heartbeats. The signal encoding scheme is the time-based integrate and fire sampler. The diagnostics can be performed directly on the samples avoiding reconstruction required by the competing finite rate of innovation and compressed sensing. As an added benefit, our scheme provides an efficient hardware implementation and a compressed representation for the ECG recordings, while still preserving discriminative features. We demonstrate the performance of our approach through a heartbeat classification application consisting of normal and irregular heartbeats known as arrhythmia. Our approach that uses simple features extracted from ECG signals is comparable to results in the published literature.     

ECG beat classification using GreyART network

The grey relational grade is a similarity measure. On the basis of the grey relational grade, an adaptive resonant theory (ART) type network, GreyART, has been developed. When the GreyART is used to classify a dataset with varying amount of data, the measurement between two specific data in the dataset may vary since the measurement is affected by new added data. In this case, the grey relational grade is not a global measure. As the measurement varies, in the GreyART, it is hard to use a fixed vigilance threshold value for determining whether the current input data belong to one of the existing clusters or become the template of a new online-created cluster. A method to solve this problem has been proposed and then applied to develop an electrocardiogram (ECG) beat classifier. The proposed ECG beat classification involves two phases. One is the off-line learning phase. With the proposed performance index, the product of the classification accuracy and the partition quality, an optimal value for the vigilance threshold and the corresponding cluster centres from the learning results can be determined. The other is the online examining phase, which classifies the input ECG beats. In this phase, the vigilance threshold value and the initial cluster centres are the optimal ones obtained in the learning phase. Under these conditions, the GreyART network enables real-time classification of ECG beats. Simulation results show that the proposed network achieves a good accuracy with a good computational efficiency for ECG beat classification problems     

Scale space classification using area morphology

We explore the application of area morphology to image classification. From the input image, a scale space is created by successive application of an area morphology operator. The pixels within the scale space corresponding to the same image location form a scale space vector. A scale space vector therefore contains the intensity of a particular pixel for a given set of scales, determined in this approach by image granulometry. Using the standard k-means algorithm or the fuzzy c-means algorithm, the image pixels can be classified by clustering the associated scale space vectors. The scale space classifier presented here is rooted in the novel area open-close and area close-open scale spaces. Unlike other scale generating filters, the area operators affect the image by removing connected components within the image level sets that do not satisfy the minimum area criterion. To show that the area open-close and area close-open scale spaces provide an effective multiscale structure for image classification, we demonstrate the fidelity, causality, and edge localization properties for the scale spaces. The analysis also reveals that the area open-close and area close-open scale spaces improve classification by clustering members of similar objects more effectively than the fixed scale classifier. Experimental results are provided that demonstrate the reduction in intra-region classification error and in overall classification error given by the scale space classifier for classification applications where object scale is important. In both visual and objective comparisons, the scale space approach outperforms the traditional fixed scale clustering algorithms and the parametric Bayesian classifier for classification tasks that depend on object scale.     

Study of features based on nonlinear dynamical modeling in ECG arrhythmia detection and classification

We present a study of the nonlinear dynamics of electrocardiogram (ECG) signals for arrhythmia characterization. The correlation dimension and largest Lyapunov exponent are used to model the chaotic nature of five different classes of ECG signals. The model parameters are evaluated for a large number of real ECG signals within each class and the results are reported. The presented algorithms allow automatic calculation of the features. The statistical analysis of the calculated features indicates that they differ significantly between normal heart rhythm and the different arrhythmia types and, hence, can be rather useful in ECG arrhythmia detection. On the other hand, the results indicate that the discrimination between different arrhythmia types is difficult using such features. The results of this work are supported by statistical analysis that provides a clear outline for the potential uses and limitations of these features.     

Automatic classification of asymptomatic and osteoarthritis knee gait patterns using kinematic data features and the nearest neighbor classifier

The aim of this work is to develop an automatic computer method to distinguish between asymptomatic (AS) and osteoarthritis (OA) knee gait patterns using 3-D ground reaction force (GRF) measurements. GRF features are first extracted from the force vector variations as a function of time and then classified by the nearest neighbor rule. We investigated two different features: the coefficients of a polynomial expansion and the coefficients of a wavelet decomposition. We also analyzed the impact of each GRF component (vertical, anteroposterior, and medial lateral) on classification. The best discrimination rate (91%) was achieved with the wavelet decomposition using the anteroposterior and the medial lateral components. These results demonstrate the validity of the representation and the classifier for automatic classification of AS and OA knee gait patterns. They also highlight the relevance of the anteroposterior and medial lateral force components in gait pattern classification.     

Baseline normalisation of ECG signals using empirical mode decomposition and mathematical morphology

An approach to remove baseline wander from electrocardiogram (ECG) signals, based on empirical mode decomposition and mathematical morphology, is described.     

利用灰度和纹理特征的SAR图像分类研究

多类别多特征量情况下的合成孔径雷达(SAR)图像的目标分类是一个难以解决的问题.从灰度和纹理模型出发,提出了综合利用灰度和纹理特征的目标分类方法.均值和方差是灰度模型中重要的特征统计量,而能量、熵、对比度、局部相似性和相关性是纹理模型中重要的特征统计量.灰度和纹理特征能确切地描述SAR图像中的目标.通过构造特征向量,定义向量之间的距离,并按照最小距离方法进行目标分类.以一定大小的窗口读入样本,提高了算法的运行速度和抗噪能力.理论上,窗口越大,特征向量值越接近真实值.窗口越小,边缘的分类精度越高.实验表明该方法较好地处理了多类别多特征量情况下的SAR图像分类问题,分类结果是有效的,这为SAR图像目标分类提供了一条简单可行的途径.     

Mass classification of mammograms using fractal dimensions and statistical features

For classification of tumors in mammography, the major features are extracted from the segmented tumor. However, some details of the tumor margin, such as the spiculated parts, are eliminated in the segmentation step. The current study suggests a new approach for extracting the spiculated parts and tumor core. The proposed method segments the tumor by assessing the similarity of the pixels of the tumor core and dissimilarity of the spiculated parts. Then, the spiculated parts and the tumor core are combined to create the final segmentation. Next, the statistical features and fractal dimensions are extracted from the tumor. The fractal dimension is a measure of complexity of the tumor shape that is effective for discriminating between benign and malignant tumors. The simulation results show that the proposed method is more suitable than other methods. The area under the ROC curve and the accuracy of the proposed method on mini-MIAS were 0.9627 and 89.66% and for DDSM were 0.9777 and 93.50%, respectively. The results confirm the efficiency of the proposed method for extracting the mass core and spiculated parts. They also show that use of the fractal dimension increases the accuracy of classification and complements the other shape features.

     

小波变换与模式识别用于自动识别调制模式

本文提出小波变换与模式识别相结合的算法实现通信信号调制模式的自动识别。不同于其他调制模式识别算法，该算法能同时识别模拟调制信号和数字调制信号。采用小波变换估计信号的码速率以区分模拟信号和数字信号。对模拟信号或者数字信号，提取相应的特征参数，识别具体的调制模式。计算机仿真结果表明SNR≥15dB时，该算法艮有很好的性能。     

Automatic classification of brain resting states using fMRI temporal signals

A novel technique is presented for the automatic discrimination between networks of `resting states? of the human brain and physiological fluctuations in functional magnetic resonance imaging (fMRI). The method is based on features identified via a statistical approach to group independent component analysis time courses, which may be extracted from fMRI data. This technique is entirely automatic and, unlike other approaches, uses temporal rather than spatial information. The method achieves 83% accuracy in the identification of resting state networks.     

Automatic modulation classification for cognitive radios using cyclic feature detection

Cognitive radios have become a key research area in communications over the past few years. Automatic modulation classification (AMC) is an important component that improves the overall performance of the cognitive radio. Most modulated signals exhibit the property of cyclostationarity that can be exploited for the purpose of classification. In this paper, AMCs that are based on exploiting the cyclostationarity property of the modulated signals are discussed. Inherent advantages of using cyclostationarity based AMC are also addressed. When the cognitive radio is in a network, distributed sensing methods have the potential to increase the spectral sensing reliability, and decrease the probability of interference to existing radio systems. The use of cyclostationarity based methods for distributed signal detection and classification are presented. Examples are given to illustrate the concepts. The Matlab codes for some of the algorithms described in the paper are available for free download at http://filebox.vt.edu/user/bramkum.     

Automatic modulation classification of noise-like radar intrapulse signals using cascade classifier

Automatic modulation classification is essential in radar emitter identification. We propose a cascade classifier by combining a support vector machine (SVM) and convolutional neural network (CNN), considering that noise might be taken as radar signals. First, the SVM distinguishes noise signals by the main ridge slice feature of signals. Second, the complex envelope features of the predicted radar signals are extracted and placed into a designed CNN, where a modulation classification task is performed. Simulation results show that the SVM-CNN can effectively distinguish radar signals from noise. The overall probability of successful recognition (PSR) of modulation is 98.52% at 20 dB and 82.27% at −2 dB with low computation costs. Furthermore, we found that the accuracy of intermediate frequency estimation significantly affects the PSR. This study shows the possibility of training a classifier using complex envelope features. What the proposed CNN has learned can be interpreted as an equivalent matched filter consisting of a series of small filters that can provide different responses determined by envelope features.     

Automatic registration of CT and MR brain images using correlation of geometrical features

Describes an automated approach to register CT and MR brain images. Differential operators in scale space are applied to each type of image data, so as to produce feature images depicting "ridgeness". The resulting CT and MR feature images show similarities which can be used for matching. No segmentation is needed and the method is devoid of human interaction. The matching is accomplished by hierarchical correlation techniques. Results of 2-D and 3-D matching experiments are presented. The correlation function ensures an accurate match even if the scanned volumes to be matched do not completely overlap, or if some of the features in the images are not similar.     

Automatic motion and noise artifact detection in Holter ECG data using empirical mode decomposition and statistical approaches

We present a real-time method for the detection of motion and noise (MN) artifacts, which frequently interferes with accurate rhythm assessment when ECG signals are collected from Holter monitors. Our MN artifact detection approach involves two stages. The first stage involves the use of the first-order intrinsic mode function (F-IMF) from the empirical mode decomposition to isolate the artifacts' dynamics as they are largely concentrated in the higher frequencies. The second stage of our approach uses three statistical measures on the F-IMF time series to look for characteristics of randomness and variability, which are hallmark signatures of MN artifacts: the Shannon entropy, mean, and variance. We then use the receiver-operator characteristics curve on Holter data from 15 healthy subjects to derive threshold values associated with these statistical measures to separate between the clean and MN artifacts' data segments. With threshold values derived from 15 training data sets, we tested our algorithms on 30 additional healthy subjects. Our results show that our algorithms are able to detect the presence of MN artifacts with sensitivity and specificity of 96.63% and 94.73%, respectively. In addition, when we applied our previously developed algorithm for atrial fibrillation (AF) detection on those segments that have been labeled to be free from MN artifacts, the specificity increased from 73.66% to 85.04% without loss of sensitivity (74.48%-74.62%) on six subjects diagnosed with AF. Finally, the computation time was less than 0.2?s using a MATLAB code, indicating that real-time application of the algorithms is possible for Holter monitoring.     

Automatic fake document identification and localization using DE-Net and color-based features of foreign inks

Document examination is a vital mission for revealing illegal modifications that assist in the detection and resolution of criminal acts. Addition and alteration are more frequently used in handwritten documents. However, most of the documents have been modified with similar inks, and it is tough to detect or observe them with human eyes. As a result, there is a need for methods to automatically detect handwriting forgery to reach an accurate detection efficiently. In this paper, a novel and efficient method is proposed for automatically detecting altered handwritten documents and locating the fake part. Therefore, DE-Net is proposed to identify the forged document using a digitally scanned version of the document. Unlike the existing methods, a further localization schema is applied to locate the forged parts in the candidate forged document accurately. Where each forged document is segmented into objects. Color histograms of R, G, and B channels are used to generate a fused feature vector for each object. Then a structural similarity index (SSIM) is applied to detect the lower similarity parts as forged. The experimental results demonstrate that the proposed method can identify and localize foreign ink in handwritten documents with high performance.     

Automatic segmentation and classification of ionic-channel signals

Identification of ionic-channel types and their selectivity depends critically on the open channel current that can be resolved. In this paper, an automatic channel detection algorithm is proposed that is based on sequential minimization of an index which is usually used in cluster analysis. The algorithm consists of two stages, namely segmentation and classification. In the first stage, the signal samples are segmented based on the assumption that the samples in each segment should be sequentially connected. In the second stage, the resultant segments are classified with no regard to their connectivities. Results on synthetic and real channel currents are very encouraging and they suggest that this algorithm will substantially increase the productivity of many laboratories involved in ionic-channel research.     

Non-contact heartbeat and respiration detector using capacitive sensor with Colpitts oscillator

A capacitive sensor for detecting the heartbeat rate of a human without direct contact with the skin is investigated. Precordial movement changes the capacitance between patch electrodes and modulates the frequency of a Colpitts oscillator. Heartbeat and respiration information can be obtained by demodulating the oscillating signal. Heartbeat signal obtained by bandpass filtering the harmonics of heartbeat frequency is separated from the demodulated signal.     

Automatic identification of retinal arteries and veins from dual-wavelength images using structural and functional features

This paper presents an automated method to identify arteries and veins in dual-wavelength retinal fundus images recorded at 570 and 600 nm. Dual-wavelength imaging provides both structural and functional features that can be exploited for identification. The processing begins with automated tracing of the vessels from the 570-nm image. The 600-nm image is registered to this image, and structural and functional features are computed for each vessel segment. We use the relative strength of the vessel central reflex as the structural feature. The central reflex phenomenon, caused by light reflection from vessel surfaces that are parallel to the incident light, is especially pronounced at longer wavelengths for arteries compared to veins. We use a dual-Gaussian to model the cross-sectional intensity profile of vessels. The model parameters are estimated using a robust -estimator, and the relative strength of the central reflex is computed from these parameters. The functional feature exploits the fact that arterial blood is more oxygenated relative to that in veins. This motivates use of the ratio of the vessel optical densities (ODs) from images at oxygen-sensitive and oxygen-insensitive wavelengths () as a functional indicator. Finally, the structural and functional features are combined in a classifier to identify the type of the vessel. We experimented with four different classifiers and the best result was given by a support vector machine (SVM) classifier. With the SVM classifier, the proposed algorithm achieved true positive rates of 97% for the arteries and 90% for the veins, when applied to a set of 251 vessel segments obtained from 25 dual wavelength images. The ability to identify the vessel type is useful in applications such as automated retinal vessel oximetry and automated analysis of vascular changes without manual intervention.     

Automatic Detection of Respiration Rate From Ambulatory Single-Lead ECG

Ambulatory electrocardiography is increasingly being used in clinical practice to detect abnormal electrical behavior of the heart during ordinary daily activities. The utility of this monitoring can be improved by deriving respiration, which previously has been based on overnight apnea studies where patients are stationary, or the use of multilead ECG systems for stress testing. We compared six respiratory measures derived from a single-lead portable ECG monitor with simultaneously measured respiration air flow obtained from an ambulatory nasal cannula respiratory monitor. Ten controlled 1-h recordings were performed covering activities of daily living (lying, sitting, standing, walking, jogging, running, and stair climbing) and six overnight studies. The best method was an average of a 0.2–0.8 Hz bandpass filter and RR technique based on lengthening and shortening of the RR interval. Mean error rates with the reference gold standard were $pm$4 breaths per minute (bpm) (all activities), $pm$2 bpm (lying and sitting), and $pm$1 breath per minute (overnight studies). Statistically similar results were obtained using heart rate information alone (RR technique) compared to the best technique derived from the full ECG waveform that simplifies data collection procedures. The study shows that respiration can be derived under dynamic activities from a single-lead ECG without significant differences from traditional methods.