基于离散小波变换提取脑机接口中脑电特征

在脑机接口中，针对脑电特征提取利用单一种类信息、使用数据量大、分类性能较差等缺点，提出一种新颖的基于离散小波变换的方法。分析了小波变换特征提取的特点和特征表示方式，用Daubechies类db4小波函数对脑电信号进行6层分解，抽取小波变换各子带关键的部分逼近系数、小波系数、小波子带系数均值组成特征向量。以分类正确率为指标检验了提取特征的性能。实验结果表明，这种方法能够利用少量数据提取脑电信号本质特征，具有较高的分类性能，为利用脑电识别人的不同意图提供了快速而有效的手段。     

基于小波变换的新疆地方性肝包虫CT 图像分类研究

采用基于 sym4和 db4小波基两种小波变换方法,探讨对新疆地方性肝包虫 CT 图像的分类价值。使用 sym4和 db4小波两种小波基,提取感兴趣病灶区的纹理特征,并通过统计学方法筛选出特征子集,采用C4．5决策树算法构建正常肝脏和多子囊型病变肝脏 CT 图像的计算机分类模型,并对模型进行准确性、灵敏度和特异性的验证评估。结果显示,对正常肝脏和多子囊型肝包虫进行分类,sym4小波的识别正确率为92．5％,db4小波的识别正确率为97．5％。实验结果表明,小波变换法所提取的纹理特征对识别正常肝脏和多子囊型肝包虫 CT 影像有较好的意义,也为后续的基于内容的新疆地方性肝包虫病的诊断系统奠定了基础。     

Evaluation of time domain features using best feature subsets based on mutual information for detecting epilepsy

Abstract

In this pattern recognition study of detecting epilepsy, the first time the authors have attempted to use time domain (TD) features such as waveform length (WL), number of zero-crossings (ZC) and number of slope sign changes (SSC) which are extracted from the discrete wavelet transform (DWT) for the detecting the epilepsy for University of Bonn datasets and real-time clinical data. The performance of these TD features is studied along with mean absolute value (MAV) which has been attempted by other researchers. The performance of the TD features derived from DWT is studied using naive Bayes (NB) and support vector machines (SVM) for five different datasets from University of Bonn with 14 different combinations datasets and 24 patients datasets from Christian Medical College and Hospital (CMCH), India database. Using feature selection and feature ranking based on the estimation of mutual information (MI), the significant features required for the classifier to get higher accuracy is obtained. Further, NB achieves 100% classification accuracy (CA) in distinguishing normal eyes open and epileptic dataset with top 4 ranked features and it gives 100% accuracy with top-ranked two features in using CMCH data.     

EEG epileptic seizure detection and classification based on dual-tree complex wavelet transform and machine learning algorithms

The visual analysis of common neurological disorders such as epileptic seizures in electroencephalography (EEG) is an oversensitive operation and prone to errors, which has motivated the researchers to develop effective automated seizure detection methods. This paper proposes a robust automatic seizure detection method that can establish a veritable diagnosis of these diseases. The proposed method consists of three steps: (i) remove artifact from EEG data using Savitzky-Golay filter and multi-scale principal component analysis (MSPCA), (ii) extract features from EEG signals using signal decomposition representations based on empirical mode decomposition (EMD), discrete wavelet transform (DWT), and dual-tree complex wavelet transform (DTCWT) allowing to overcome the non-linearity and non-stationary of EEG signals, and (iii) allocate the feature vector to the relevant class (i.e., seizure class "ictal" or free seizure class "interictal") using machine learning techniques such as support vector machine (SVM), k-nearest neighbor (k-NN), and linear discriminant analysis (LDA). The experimental results were based on two EEG datasets generated from the CHB-MIT database with and without overlapping process. The results obtained have shown the effectiveness of the proposed method that allows achieving a higher classification accuracy rate up to 100% and also outperforms similar state-of-the-art methods.     

ECG beat classification using empirical mode decomposition and mixture of features

Computer-aided analysis is useful in predicting arrhythmia conditions of the heart by analysing the recorded ECG signals. In this work, we proposed a method to detect, extract informative features to classify six types of heartbeat of ECG signals obtained from the MIT-BIH Arrhythmia database. The powerful discrete wavelet transform (DWT) is used to eliminate different sources of noises. Empirical mode decomposition (EMD) with adaptive thresholding has been used to detect precise R-peaks and QRS complex. The significant features consists of temporal, morphological and statistical were extracted from the processed ECG signals and combined to form a set of features. This feature set is classified with probabilistic neural network (PNN) and radial basis function neural network (RBF-NN) to recognise the arrhythmia beats. The process achieved better result with sensitivity of 99.96%, and positive predictivity of 99.81 with error rate of 0.23% in detecting the QRS complex. In class-oriented scheme, the arrhythmia conditions are classified with accuracy of 99.54%, 99.89% using PNN and RBF-NN classifier respectively. The obtained result confirms the superiority of the proposed scheme compared to other published results cited in literature.     

Epileptic seizure detection using DWT-based approximate entropy,Shannon entropy and support vector machine: a case study

In this work, we have used a time–frequency domain analysis method called discrete wavelet transform (DWT) technique. This method stand out compared to other proposed methods because of its algorithmic elegance and accuracy. A wavelet is a mathematical function based on time-frequency analysis in signal processing. It is useful particularly because it allows a weak signal to be recovered from a noisy signal without much distortion. A wavelet analysis works by analysing the image and converting it to mathematical function which is decoded by the receiver. Furthermore, we have used Shannon entropy and approximate entropy (ApEn) for extracting the complexities associated with electroencephalographic (EEG) signals. The ApEn is a suitable feature to characterise the EEGs because its value drops suddenly due to excessive synchronous discharge of neurons in the brain during epileptic activity in this study. EEG signals are decomposed into six EEG sub-bands namely D1–D5 and A5 using DWT technique. Non-linear features such as ApEn and Shannon entropy are calculated from these sub-bands and support vector machine classifiers are used for classification purpose. This scheme is tested using EEG data recorded from five healthy subjects and five epileptic patients during the inter-ictal and ictal periods. The data are acquired from University of Bonn, Germany. The proposed method is evaluated through 15 classification problems, and obtained high classification accuracy of 100% for two cases and it indicates the good classifying performance of the proposed method.     

An expert system based on principal component analysis, artificial immune system and fuzzy k-NN for diagnosis of valvular heart diseases

In the last two decades, the use of artificial intelligence methods in medical analysis is increasing. This is mainly because the effectiveness of classification and detection systems have improved a great deal to help the medical experts in diagnosing. In this work, we investigate the use of principal component analysis (PCA), artificial immune system (AIS) and fuzzy k-NN to determine the normal and abnormal heart valves from the Doppler heart sounds. The proposed heart valve disorder detection system is composed of three stages. The first stage is the pre-processing stage. Filtering, normalization and white de-noising are the processes that were used in this stage. The feature extraction is the second stage. During feature extraction stage, wavelet packet decomposition was used. As a next step, wavelet entropy was considered as features. For reducing the complexity of the system, PCA was used for feature reduction. In the classification stage, AIS and fuzzy k-NN were used. To evaluate the performance of the proposed methodology, a comparative study is realized by using a data set containing 215 samples. The validation of the proposed method is measured by using the sensitivity and specificity parameters; 95.9% sensitivity and 96% specificity rate was obtained.     

ECG心搏分类的特征提取的研究

目的研究适于心搏分类的突出特征矢量。方法首先采用连续小波变换对QRS复合波进行定位,然后采用不同的特征提取技术,提取一组特征矢量,送入线性判别式分类器进行训练,并对基于MIT/BIH数据库中的4类心搏进行分类,评价其分类性能。结果用10维特征矢量对4类心搏进行分类,准确度可达97.83%。结论综合利用不同特征提取技术可以显著提高心搏分类的准确度。     

Complexity analysis and dynamic characteristics of EEG using MODWT based entropies for identification of seizure onset

In this paper, complexity analysis and dynamic characteristics of electroencephalogram (EEG) signal based on maximal overlap discrete wavelet transform (MODWT) has been exploited for the identification of seizure onset. Since wavelet-based studies were well suited for classification of normal and epileptic seizure EEG, we have applied MODWT which is an improved version of discrete wavelet transform (DWT). The selection of optimal wavelet sub-band and features plays a crucial role to understand the brain dynamics in epileptic patients. Therefore, we have investigated MODWT using four different wavelets, namely Haar, Coif4, Dmey, and Sym4 sub-bands until seven levels. Further, we have explored the potentials of six entropies, namely sigmoid, Shannon, wavelet, Renyi, Tsallis, and Steins unbiased risk estimator (SURE) entropies in each sub-band. The sigmoid entropy extracted from Haar wavelet in sub-band D4 showed the highest accuracy of 98.44% using support vector machine classifier for the EEG collected from Ramaiah Medical College and Hospitals (RMCH). Further, the highest accuracy of 100% and 94.51% was achieved for the University of Bonn (UBonn) and CHB-MIT databases respectively. The findings of the study showed that Haar and Dmey wavelets were found to be computationally economical and expensive respectively. Besides, in terms of dynamic characteristics, MODWT results revealed that the highest energy present in sub-bands D2, D3, and D4 and entropies in those respective sub-bands outperformed other entropies in terms of classification results for RMCH database. Similarly, using all the entropies, sub-bands D5 and D6 outperformed other sub-bands for UBonn and CHB-MIT databases respectively. In conclusion, the comparison results of MODWT outperformed DWT.     

Feature dimensionality reduction for myoelectric pattern recognition: A comparison study of feature selection and feature projection methods

This study investigates the effect of the feature dimensionality reduction strategies on the classification of surface electromyography (EMG) signals toward developing a practical myoelectric control system. Two dimensionality reduction strategies, feature selection and feature projection, were tested on both EMG feature sets, respectively. A feature selection based myoelectric pattern recognition system was introduced to select the features by eliminating the redundant features of EMG recordings instead of directly choosing a subset of EMG channels. The Markov random field (MRF) method and a forward orthogonal search algorithm were employed to evaluate the contribution of each individual feature to the classification, respectively. Our results from 15 healthy subjects indicate that, with a feature selection analysis, independent of the type of feature set, across all subjects high overall accuracies can be achieved in classification of seven different forearm motions with a small number of top ranked original EMG features obtained from the forearm muscles (average overall classification accuracy >95% with 12 selected EMG features). Compared to various feature dimensionality reduction techniques in myoelectric pattern recognition, the proposed filter-based feature selection approach is independent of the type of classification algorithms and features, which can effectively reduce the redundant information not only across different channels, but also cross different features in the same channel. This may enable robust EMG feature dimensionality reduction without needing to change ongoing, practical use of classification algorithms, an important step toward clinical utility.     

Decision support system for detection of hypertensive retinopathy using arteriovenous ratio

Hypertensive Retinopathy (HR) caused by hypertension is a retinal disease which may leads to vision loss and blindness. Computer aided diagnostic systems for various diseases are being used in clinics but there is a need to develop an automated system that detects and grades HR disease. In this paper, an automated system is presented that detects and grades HR disease using Arteriovenous Ratio (AVR).The presented system includes three modules i.e. main component extraction, artery/vein (A/V) classification and finally AVR calculation and grading of HR. Proposed system uses vascular map and a set of hybrid features for A/V classification. The evaluation of proposed system is carried out using three datasets. The proposed system shows average accuracies of 95.14% for images of INSPIRE-AVR database, 96.82% for images of VICAVR database and 98.76% for local dataset AVRDB. These results support that the proposed system is trustworthy for clinical use in detection and grading of HR disease. Main contribution of proposed system is that it utilizes complete blood vessel map for A/V classification. These arteries and veins are then used to calculate AVR and grade HR cases based on AVR values. Another contribution of this article is that it presents a new dataset AVRDB for A/V classification and HR detection.     

Analysis of spike-wave discharges in rats using discrete wavelet transform

A feature is a distinctive or characteristic measurement, transform, structural component extracted from a segment of a pattern. Features are used to represent patterns with the goal of minimizing the loss of important information. The discrete wavelet transform (DWT) as a feature extraction method was used in representing the spike-wave discharges (SWDs) records of Wistar Albino Glaxo/Rijswijk (WAG/Rij) rats. The SWD records of WAG/Rij rats were decomposed into time-frequency representations using the DWT and the statistical features were calculated to depict their distribution. The obtained wavelet coefficients were used to identify characteristics of the signal that were not apparent from the original time domain signal. The present study demonstrates that the wavelet coefficients are useful in determining the dynamics in the time-frequency domain of SWD records.     

A multi-stage automatic arrhythmia recognition and classification system

This paper describes an automatic classification system based on combination of diverse features for the purpose of automatic heartbeat recognition. The method consists of three stages. At the first stage, heartbeats are classified into 5 main groups defined by AAMI using optimal feature sets for each main group. At the second stage, main groups are classified into subgroups using optimal features for each subgroup. Then the third stage is added to the system for classifying beats that are labeled as unclassified beats in the first two classification stages. A diverse set of features including higher order statistics, morphological features, Fourier transform coefficients, and higher order statistics of the wavelet package coefficients are extracted for each different type of ECG beat. At the first stage, optimal features for main groups are determined by using a wrapper type feature selection algorithm. At the second stage, optimal features are similarly selected for discriminating each subgroup of the main groups. Then at the third stage, only raw data is used for classifying beats. In all stages, the classifiers are based on the k-nearest neighbor algorithm. ECG records used in this study are obtained from the MIT-BIH arrhythmia database. The classification accuracy of the proposed system is measured by sensitivity, selectivity, and specificity measures. The system is classified 16 heartbeat types. The measures of proposed system are 85.59%, 95.46%, and 99.56%, for average sensitivity, average selectivity, and average specificity, respectively.     

A New Blood Vessel Extraction Technique Using Edge Enhancement and Object Classification

Diabetic retinopathy (DR) is increasing progressively pushing the demand of automatic extraction and classification of severity of diseases. Blood vessel extraction from the fundus image is a vital and challenging task. Therefore, this paper presents a new, computationally simple, and automatic method to extract the retinal blood vessel. The proposed method comprises several basic image processing techniques, namely edge enhancement by standard template, noise removal, thresholding, morphological operation, and object classification. The proposed method has been tested on a set of retinal images. The retinal images were collected from the DRIVE database and we have employed robust performance analysis to evaluate the accuracy. The results obtained from this study reveal that the proposed method offers an average accuracy of about 97 %, sensitivity of 99 %, specificity of 86 %, and predictive value of 98 %, which is superior to various well-known techniques.     

Matrix decomposition based feature extraction for murmur classification

Heart murmurs often indicate heart valvular disorders. However, not all heart murmurs are organic. For example, musical murmurs detected in children are mostly innocent. Because of the challenges of mastering auscultation skills and reducing healthcare expenses, this study aims to discover new features for distinguishing innocent murmurs from organic murmurs, with the ultimate objective of designing an intelligent diagnostic system that could be used at home. Phonocardiographic signals that were recorded in an auscultation training CD were used for analysis. Instead of the discrete wavelet transform that has been used often in previous work, a continuous wavelet transform was applied on the heart sound data. The matrix that was derived from the continuous wavelet transform was then processed via singular value decomposition and QR decomposition, for feature extraction. Shannon entropy and the Gini index were adopted to generate features. To reduce the number of features that were extracted, the feature selection algorithm of sequential forward floating selection (SFFS) was utilized to select the most significant features, with the selection criterion being the maximization of the average accuracy from a 10-fold cross-validation of a classification algorithm called classification and regression trees (CART). An average sensitivity of 94%, a specificity of 83%, and a classification accuracy of 90% were achieved. These favorable results substantiate the effectiveness of the feature extraction methods based on the proposed matrix decomposition method.     

Detection of gastric dysrhythmia using WT and ANN in diabetic gastroparesis patients

Gastric myoelectrical activity can be measured by a noninvasive technique called electrogastrography where surface electrodes are placed on the epigastric area of the abdomen. The electrogastrogram (EGG) signal is by nature a nonstationary signal in terms of its frequency, amplitude and wave shape. Unlike the other methods discrete wavelet analysis (DWT) was designed for nonstationary signals. For automatic assessment of EGG, we used artificial neural networks (ANNs) that have been widely employed in pattern recognition due to their great potential of high performance, flexibility, robust fault tolerance, cost-effective functionality and capability for real-time applications. So we developed a new method for classification of EGG based on DWT and ANN.     

Single-channel EEG sleep stage classification based on a streamlined set of statistical features in wavelet domain

The main objective of this study was to enhance the performance of sleep stage classification using single-channel electroencephalograms (EEGs), which are highly desirable for many emerging technologies, such as telemedicine and home care. The proposed method consists of decomposing EEGs by a discrete wavelet transform and computing the kurtosis, skewness and variance of its coefficients at selected levels. A random forest predictor is trained to classify each epoch into one of the Rechtschaffen and Kales’ stages. By performing a comprehensive set of tests on 106,376 epochs available from the Physionet public database, it is demonstrated that the use of these three statistical moments has enhanced performance when compared to their application in the time domain. Furthermore, the chosen set of features has the advantage of exhibiting a stable classification performance for all scoring systems, i.e., from 2- to 6-state sleep stages. The stability of the feature set is confirmed with ReliefF tests which show a performance reduction when any individual feature is removed, suggesting that this group of feature cannot be further reduced. The accuracies and kappa coefficients yield higher than 90 % and 0.8, respectively, for all of the 2- to 6-state sleep stage classification cases.     

Decision support system for age-related macular degeneration using discrete wavelet transform

Age-related macular degeneration (AMD) affects the central vision and subsequently may lead to visual loss in people over 60 years of age. There is no permanent cure for AMD, but early detection and successive treatment may improve the visual acuity. AMD is mainly classified into dry and wet type; however, dry AMD is more common in aging population. AMD is characterized by drusen, yellow pigmentation, and neovascularization. These lesions are examined through visual inspection of retinal fundus images by ophthalmologists. It is laborious, time-consuming, and resource-intensive. Hence, in this study, we have proposed an automated AMD detection system using discrete wavelet transform (DWT) and feature ranking strategies. The first four-order statistical moments (mean, variance, skewness, and kurtosis), energy, entropy, and Gini index-based features are extracted from DWT coefficients. We have used five (t test, Kullback–Lieber Divergence (KLD), Chernoff Bound and Bhattacharyya Distance, receiver operating characteristics curve-based, and Wilcoxon) feature ranking strategies to identify optimal feature set. A set of supervised classifiers namely support vector machine (SVM), decision tree, \(k\) -nearest neighbor ( \(k\) -NN), Naive Bayes, and probabilistic neural network were used to evaluate the highest performance measure using minimum number of features in classifying normal and dry AMD classes. The proposed framework obtained an average accuracy of 93.70 %, sensitivity of 91.11 %, and specificity of 96.30 % using KLD ranking and SVM classifier. We have also formulated an AMD Risk Index using selected features to classify the normal and dry AMD classes using one number. The proposed system can be used to assist the clinicians and also for mass AMD screening programs.