Set Of Statistical Features Research Articles

Medical Decision Support System for Diagnosis of Heart Arrhythmia using DWT and Random Forests Classifier

In this study, Random Forests (RF) classifier is proposed for ECG heartbeat signal classification in diagnosis of heart arrhythmia. Discrete wavelet transform (DWT) is used to decompose ECG signals into different successive frequency bands. A set of different statistical features were extracted from the obtained frequency bands to denote the distribution of wavelet coefficients. This study shows that RF classifier achieves superior performances compared to other decision tree methods using 10-fold cross-validation for the ECG datasets and the obtained results suggest that further significant improvements in terms of classification accuracy can be accomplished by the proposed classification system. Accurate ECG signal classification is the major requirement for detection of all arrhythmia types. Performances of the proposed system have been evaluated on two different databases, namely MIT-BIH database and St. -Petersburg Institute of Cardiological Technics 12-lead Arrhythmia Database. For MIT-BIH database, RF classifier yielded an overall accuracy 99.33 % against 98.44 and 98.67 % for the C4.5 and CART classifiers, respectively. For St. -Petersburg Institute of Cardiological Technics 12-lead Arrhythmia Database, RF classifier yielded an overall accuracy 99.95 % against 99.80 % for both C4.5 and CART classifiers, respectively. The combined model with multiscale principal component analysis (MSPCA) de-noising, discrete wavelet transform (DWT) and RF classifier also achieves better performance with the area under the receiver operating characteristic (ROC) curve (AUC) and F-measure equal to 0.999 and 0.993 for MIT-BIH database and 1 and 0.999 for and St. -Petersburg Institute of Cardiological Technics 12-lead Arrhythmia Database, respectively. Obtained results demonstrate that the proposed system has capacity for reliable classification of ECG signals, and to assist the clinicians for making an accurate diagnosis of cardiovascular disorders (CVDs).

Enhanced Industrial Machinery Condition Monitoring Methodology Based on Novelty Detection and Multi-Modal Analysis

This paper presents a condition-based monitoring methodology based on novelty detection applied to industrial machinery. The proposed approach includes both the classical classification of multiple a priori known scenarios, and the innovative detection capability of new operating modes not previously available. The development of condition-based monitoring methodologies considering the isolation capabilities of unexpected scenarios represents, nowadays, a trending topic able to answer the demanding requirements of the future industrial processes monitoring systems. First, the method is based on the temporal segmentation of the available physical magnitudes, and the estimation of a set of time-based statistical features. Then, a double feature reduction stage based on principal component analysis and linear discriminant analysis is applied in order to optimize the classification and novelty detection performances. The posterior combination of a feed-forward neural network and one-class support vector machine allows the proper interpretation of known and unknown operating conditions. The effectiveness of this novel condition monitoring scheme has been verified by experimental results obtained from an automotive industry machine.

Offline cursive Urdu-Nastaliq script recognition using multidimensional recurrent neural networks

Optical Character Recognition of cursive scripts remains a challenging task due to a large number of character shapes, inter- and intra-word overlaps, context sensitivity and diagonality of text. This paper presents an implicit segmentation based recognition system for Urdu text lines in Nastaliq script. The proposed technique relies on sliding overlapped windows on lines of text and extracting a set of statistical features. The extracted features are fed to a multi-dimensional long short term memory recurrent neural network (MDLSTM RNN) with a connectionist temporal classification (CTC) output layer that labels the character sequences. Experimental study of the proposed technique is carried out on the standard Urdu Printed Text-line Images (UPTI) database which comprises 10,000 text lines in Nastaliq font. Evaluations under different experimental settings realize promising recognition rates with a highest character recognition rate of 96.40%.

Stress Estimation of ECG Signal by using DWT

Identification and prediction of stress using existing data processing methodologies are incompetent to predict the stress either in real time or laboratory based experiments. The main aim of this work is to classify the stress. The appropriate signal processing methodology, (i) to analyze the Electrocardiogram (ECG) signal for normal and stress condition and (ii) to derive the optimum features from a set of statistical features over frequency band. This paper represent method to find out stress condition. Electrocardiogram, were recorded continuously while drivers followed a set route through open roads in the greater Boston area. Stress levels are created by driving into different condition. By driving in city, highway and rest condition. We used physionet data base ‘Stress Recognition in Automobile Drivers’ for ECG signal.ECG signal is used to analysis the stress. Parameters( RMS, Max ,Std ,kurtosis , min ,mean ,variance)are used for analysis by using discrete wavelet transform by using ‘db6’ mother wavelet function . Entropy Correlation, Skew ness, median, crest factor are not giving the appropriate changes from normal condition to stressed condition so these parameters are not considered. Artificial neural network was used for decision making you are in stress or not.

Construction of a Model for the Cross-Domain Opinion Word Extraction

In this paper we consider a new approach for domain-specific opinion word extraction in the Russian language. We propose a set of statistical features and an algorithm combination that can extract opinion words in a particular domain. The extraction model was trained in the movie domain and then applied to four other domains. The quality of the obtained sentiment lexicons was evaluated intrinsically on the base of an expert markup and remained on the high level during the model transfer to various domains. Finally, our method is adapted to the movie domain in English and it demonstrated good results.

Classification of Ultrasound Kidney Images using PCA and Neural Networks

In this paper, a computer-aided system is proposed for automatic classification of Ultrasound Kidney diseases. Images of five classes: Normal, Cyst, Stone, Tumor and Failure were considered. A set of statistical features and another set of multi-scale wavelet-based features were extracted from the region of interest (ROI) of each image and the principal component analysis was performed to reduce the number of features. The selected features were utilized in the design and training of a neural network classifier. A correct classification rate of 97% has been obtained using the multi-scale wavelet-based features.

Power Consumption Profiling Using Energy Time-Frequency Distributions in Smart Grids

Smart grids are power distribution networks that include a significant communication infrastructure, which is used to collect usage data and monitor the operational status of the grid. As a consequence of this additional infrastructure, power networks are at an increased risk of cyber-attacks. In this letter, we address the problem of detecting and attributing anomalies that occur in the sub-meter power consumption measurements of a smart grid, which could be indicative of malicious behavior. We achieve this by clustering a set of statistical features of power measurements that are determined using the Smoothed Pseudo Wigner Ville (SPWV) energy Time-Frequency (TF) distribution. We show how this approach is able to more accurately distinguish clusters of energy consumption than simply using raw power measurements. Our ultimate goal is to apply the principles of profiling power consumption measurements as part of an enhanced anomaly detection system for smart grids.

Human activity data discovery from triaxial accelerometer sensor: Non-supervised learning sensitivity to feature extraction parametrization

Background: Our methodology describes a human activity recognition framework based on feature extraction and feature selection techniques where a set of time, statistical and frequency domain features taken from 3-dimensional accelerometer sensors are extracted. This framework specifically focuses on activity recognition using on-body accelerometer sensors. We present a novel interactive knowledge discovery tool for accelerometry in human activity recognition and study the sensitivity to the feature extraction parametrization. Results: The implemented framework achieved encouraging results in human activity recognition. We have implemented a new set of features extracted from wearable sensors that are ambitious from a computational point of view and able to ensure high classification results comparable with the state of the art wearable systems (Mannini et al. 2013). A feature selection framework is developed in order to improve the clustering accuracy and reduce computational complexity.1The software OpenSignals (Gomes, Nunes, Sousa, & Gamboa, 2012) was used for signal acquisition and signal processing algorithms were developed in Python Programming Language (Rossum & de Boer, 1991) and Orange Software (Curk et al., 2005).1 Several clustering methods such as K-Means, Affinity Propagation, Mean Shift and Spectral Clustering were applied. The K-means methodology presented promising accuracy results for person-dependent and independent cases, with 99.29% and 88.57%, respectively. Conclusions: The presented study performs two different tests in intra and inter subject context and a set of 180 features is implemented which are easily selected to classify different activities. The implemented algorithm does not stipulate, a priori, any value for time window or its overlap percentage of the signal but performs a search to find the best parameters that define the specific data. A clustering metric based on the construction of the data confusion matrix is also proposed. The main contribution of this work is the design of a novel gesture recognition system based solely on data from a single 3-dimensional accelerometer.

Arabic Handwriting Text Offline Recognition Using the HMM Toolkit (HTK)

This Recognition of Arabic text handwritten awaits precise recognition solutions. There are a lot of difficulties facing a good handwritten Arabic recognition system such as unlimited variant in human handwriting, similarities of different character shapes, and their location in the word. This paper presents a handwriting Arabic text recognition system. It decomposes the text image into text line images and extracts a set of simple statistical features from a narrow window which is sliding a long that text line, then it injects the resulting feature vectors to the Hidden Markov Model Toolkit (HTK). HTK is a portable toolkit for speech recognition system. In recognized state, the concatenation of characters to form words is modelled by simple lexical models, each word is modelled by a stochastic finite-state automaton (SFSA), and the concatenation of words into sentences is modelled by an n-gram language model. The proposed system is applied to a data corpus constructed by Text lines examples from the “Arabic-Numbers”, which contains 1905 sentences and 47 words. This phrase is written by 5 different peoples.

Support vector machine based optimization of multi-fault classification of gears with evolutionary algorithms from time–frequency vibration data

A multi-fault classification of gears has been attempted by support vector machine (SVM) learning techniques with the help of time–frequency (wavelet) vibration data. A suitable exploitation of SVM is based on the selection of SVM parameters. The main focus of the present paper is to study the performance of the multiclass capability of SVM techniques. Different optimization methods (i.e., the grid-search method (GSM), the genetic algorithm (GA) and the artificial bee colony algorithm (ABCA)) have been performed for optimizing SVM parameters. Four fault conditions of gears have been considered. The continuous wavelet transform (CWT) and wavelet packet transform (WPT) are estimated from time domain signals, and a set of statistical features are extracted from the wavelet transform. The prediction of fault classification has been attempted at the same angular speed as the measured data as well as innovatively at the intermediate and extrapolated angular speed conditions, since it is not feasible to have measurement of vibration data at continuous speeds of interest. The classification ability is noted and compared with predictions when purely time domain data is used, and it shows an excellent prediction performance.

No-reference image quality assessment in curvelet domain

We study the efficacy of utilizing a powerful image descriptor, the curvelet transform, to learn a no-reference (NR) image quality assessment (IQA) model. A set of statistical features are extracted from a computed image curvelet representation, including the coordinates of the maxima of the log-histograms of the curvelet coefficients values, and the energy distributions of both orientation and scale in the curvelet domain. Our results indicate that these features are sensitive to the presence and severity of image distortion. Operating within a 2-stage framework of distortion classification followed by quality assessment, we train an image distortion and quality prediction engine using a support vector machine (SVM). The resulting algorithm, dubbed CurveletQA for short, was tested on the LIVE IQA database and compared to state-of-the-art NR/FR IQA algorithms. We found that CurveletQA correlates well with human subjective opinions of image quality, delivering performance that is competitive with popular full-reference (FR) IQA algorithms such as SSIM, and with top-performing NR IQA models. At the same time, CurveletQA has a relatively low complexity.

Applying ICA monitoring and profile monitoring to statistical process control of manufacturing variability at multiple locations within the same unit

The assessment of in-process observations can provide useful information on potential sources of process variability. In this research, each source of variation was assumed to generate specific patterns in the spatial and temporal variations observed in data related to the measurement of quality characteristics. The spatial variation pattern and temporal pattern caused by a variation source may turn into the observed within-part and between-part variations in the monitoring of product measurements from multi-location. The traditional chart is a useful tool to deal with this type of process monitoring. To further improve the monitoring performance, this paper proposes two new process control methods based on independent component analysis (ICA) monitoring and profile monitoring. The ICA monitoring uses various monitoring statistics obtained from ICA to construct a control procedure. In the profile monitoring approach, a set of distance-based and statistical features is used as the input of a support vector regression (SVR)-based decision function to create a process monitoring method. Average run length (ARL) is used as a performance criterion to evaluate the capability of various control methods in detecting abnormalities. Simulation results show that profile monitoring approach has the best overall performance in terms of ARL, followed by ICA monitoring, and chart. This paper makes an important contribution to the monitoring of within-part and between-part variations.

An Embedded Classifier of Lung Sounds based on the Wavelet Packet Transform and ANN

Electronic auscultation is an efficient technique for capturing lung sounds and analysis of these sounds permits to evaluate the health condition of the respiratory system. Since the lung sound signals are non-stationary, the conventional method of frequency analysis is not highly successful in diagnostic classification. This paper presents a method of analysis of lung sound signals using the Wavelet Packet Transform (WPT), and classification using artificial neural network (ANN). Lung sound signals were decomposed into the frequency sub-bands using the WPT and a set of statistical features was extracted from the sub-bands to represent the distribution of wavelet coefficients. An ANN is trained and then applied to classify the lung sounds into one of three categories: normal, wheeze or crackle. This classifier was embedded in a microcontroller to provide an automated and portable device that will provide support for research and diagnosis in the evaluation of the respiratory function.

A New Feature Extraction Method Using Genetic Optimization for Texture Recognition of Satellite Images

In this paper, a new approach is proposed for texture feature extraction of satellite images using genetic algorithms. In this approach, the texture feature does not change by changing the angle of the texture. First, image texture is convolved with a trained mask, and then its energy is calculated. A regulatory mask has also been trained by a genetic algorithm using many examples of textured images. Feature extraction experiments are performed on a series of aerial images. Experimental results on both agricultural and urban images show the effectiveness of this feature for texture discrimination process of satellite images. Feature extraction for texture analysis is the key method that is used for texture recognition of satellite images. It is divided into four main categories: 1- structural methods; 2- model-based methods, 3- conversion methods, and 4- statistical methods (1-2). Texture of structural method is defined as micro-texture and macro-texture. The advantage of structural method describes a good symbolic from images and more for composition analysis is presented. This method is not suitable for normal textures, since great variability exists in micro-texture and macro-texture and cannot be identified to distinguish them. Texture analysis based on such models, fractal and Markov models are based on building an image, so that it can be used to describe the composition and texture. In this method, the image, as a possible model or as a combination of basic functions is described by a set of lines. Fractal model for modeling natural textures and sizes and analyzed texture and texture differentiation is useful, but this method is weak to choose the angle and describing the structure of the local image context is useful. Methods such as Fourier transform, Gabor and violet by using frequencies within the image, do texture analysis work, and each has its own weaknesses. Statistical methods indirectly describe the texture distribution and the relationship between the gray levels of the image handles. For images with natural texture, most statistical methods are used for feature extraction. In statistical methods, texture is specified as a probability distribution on the image space to form a random model or a set of statistical features. The most common features that are actually used for texture analysis, are based on harmony search and search pattern in the fabric. In the weakness in features from most of the above methods, there is a change in the angle of the texture that will change, and therefore the feature for classification in the texture of a different type than the angle changes does not stay constant, and it cannot be so strong in appearance (3). In continued histological classification of other methods (4-5), a method for extracting a feature here is useful to apply the texture, which is a measure of energy. Of previous methods for texture classification, the feature space is necessarily random search. In this method, a random search of the parameter space for masks (6) takes place before applying the texture of the image and calculating the energy, initially trained by type of texture, which results in a simple and effective classifier. We apply a convolution mask on the texture image and obtain the energy of each pixel at position (I, J) from image. In the proposed method, we set the parameters for the mask instead of the conventional randomized algorithms, and then the genetic algorithm is used. By using the genetic algorithm makes, this method is insensitive to the angle of the texture and the significance of the classifier of random algorithms will increase. The reminder paper is organized as follows: Section 2 introduces desirable texture features. In Section 3, genetic algorithm is used to optimize a mask to extract the optimal texture features, and experimental results are presented in Section 4.

Tool condition monitoring using K-star algorithm

Cutting tools are required for day to day activities in manufacturing. Continuous machining operations lead tool to undergo wear. Worn out tools effect surface finish during machining. The dimensional accuracy of components is also compromised. Robust tool health is vital for better productivity. Hence, an online system condition monitoring of tools is the need of hour, promising reduction in maintenance cost with a greater productivity saving both time and money. This paper presents the classification performance of K-star algorithm. A set of statistical features extracted from vibration signals (good and faulty conditions) form the input to algorithm. In the present study, the K-star algorithm is able to achieve 78% classification accuracy.

Regional Assessment of Cardiac Left Ventricular Myocardial Function via MRI Statistical Features

Automating the detection and localization of segmental (regional) left ventricle (LV) abnormalities in magnetic resonance imaging (MRI) has recently sparked an impressive research effort, with promising performances and a breadth of techniques. However, despite such an effort, the problem is still acknowledged to be challenging, with much room for improvements in regard to accuracy. Furthermore, most of the existing techniques are labor intensive, requiring delineations of the endo- and/or epi-cardial boundaries in all frames of a cardiac sequence. The purpose of this study is to investigate a real-time machine-learning approach which uses some image features that can be easily computed, but that nevertheless correlate well with the segmental cardiac function. Starting from a minimum user input in only one frame in a subject dataset, we build for all the regional segments and all subsequent frames a set of statistical MRI features based on a measure of similarity between distributions. We demonstrate that, over a cardiac cycle, the statistical features are related to the proportion of blood within each segment. Therefore, they can characterize segmental contraction without the need for delineating the LV boundaries in all the frames. We first seek the optimal direction along which the proposed image features are most descriptive via a linear discriminant analysis. Then, using the results as inputs to a linear support vector machine classifier, we obtain an abnormality assessment of each of the standard cardiac segments in real-time. We report a comprehensive experimental evaluation of the proposed algorithm over 928 cardiac segments obtained from 58 subjects. Compared against ground-truth evaluations by experienced radiologists, the proposed algorithm performed competitively, with an overall classification accuracy of 86.09% and a kappa measure of 0.73.

A MULTI-STREAM HMM APPROACH TO OFFLINE HANDWRITTEN ARABIC WORD RECOGNITION

In This paper we presented new approach for cursive Arabic text recognition system. The objective is to propose methodology analytical offline recognition of handwritten Arabic for rapid implementation. The first part in the writing recognition system is the preprocessing phase is the preprocessing phase to prepare the data was introduces and extracts a set of simple statistical features by two methods : from a window which is sliding long that text line the right to left and the approach VH2D (consists in projecting every character on the abscissa, on the ordinate and the diagonals 45° and 135°) . It then injects the resulting feature vectors to Hidden Markov Model (HMM) and combined the two HMM by multi-stream approach.

A Multi-Stream Hmm Approach to Offline Handwritten Arabic Word Recognition

In This paper we presented new approach for cursive Arabic text recogniti on system. The objective is to propose methodology analytical offline recognition of handwritten Arabic for rapid implementation. The first part in the writing recognition system is the preprocessing phaseis the preprocessing phase to prepare the data was introduces and extracts a set of simple statistical features by twomethods : from a window which is sliding long that text line the right to left and the approach VH2D (consists in projecting every character on the abscissa, on the ordinate and the diag onals 45° and 135°) . It then injects the resulting feature vectors to Hidden Markov Model (HMM) and combined the two HMM by multi -stream approach.

Sound Source Distance Estimation in Rooms based on Statistical Properties of Binaural Signals

A novel method for the estimation of the distance of a sound source from binaural speech signals is proposed. The method relies on several statistical features extracted from such signals and their binaural cues. Firstly, the standard deviation of the difference of the magnitude spectra of the left and right binaural signals is used as a feature for this method. In addition, an extended set of additional statistical features that can improve distance detection is extracted from an auditory front-end which models the peripheral processing of the human auditory system. The method incorporates the above features into two classification frameworks based on Gaussian mixture models and Support Vector Machines and the relative merits of those frameworks are evaluated. The proposed method achieves distance detection when tested in various acoustical environments and performs well in unknown environments. Its performance is also compared to an existing binaural distance detection method.

Emotion recognition from facial EMG signals using higher order statistics and principal component analysis

Higher order statistics (HOS) is an efficient feature extraction method used in diverse applications such as bio signal processing, seismic data processing, image processing, sonar, and radar. In this work, we have investigated the application of HOS to derive a set of features from facial electromyography (fEMG) signals for classifying six emotional states (happy, sad, afraid, surprised, disgusted, and neutral). fEMG signals were collected from different types of subjects in a controlled environment using audio-visual (film clips/ video clips) stimuli. Acquired fEMG signals were preprocessed using moving average filter and a set of statistical features were extracted from fEMG signals. Extracted features were mapped into corresponding emotions using k-nearest neighbor classifier. Principal component analysis was utilized to analyze the efficacy of HOS features over conventional statistical features on retaining the emotional information retrieval from fEMG signals. The results of this work indicate an improved mean emotion recognition rate of 69.5% from this proposed methodology to recognize six emotional states.