Zero-crossing Rate Research Articles

Cerebral Artery Vasospasm Detection Using Transcranial Doppler Signal Analysis.

Silent cerebral artery vasospasm in aneurysmal subarachnoid hemorrhage causes serious complications such as cerebral ischemia and death. A transcranial Doppler (TCD) ultrasound system is a noninvasive device that can effectively detect cerebral artery vasospasm as soon as it sets in, even before and in the absence of clinical deterioration. Continuous or even daily TCD monitoring is challenging because of the operator expertise and certification required in the form of a trained sonographer and interpretive experience required in the form of an additionally trained and certified physician to perform these studies. This barrier exists because of a lack of automation for detection (without human intervention) of cerebral artery vasospasm using TCD ultrasound. To overcome this barrier, we present an algorithm that automates detection of cerebral artery vasospasm. We extracted features such as the energy, energy entropy, zero-crossing rate, spectral centroid, spectral speed, spectral entropy, spectral flux, spectral roll-off, harmonic ratio, chroma, and Mel frequency cepstral coefficients for signal classification. Then we applied principal component analysis to reduce the data dimensionality. All of the chosen features were used for training a decision-tree classifier. The algorithm had high accuracy for cerebral artery vasospasm detection, with overall sensitivity of 87.5% and specificity of 89.74%. The algorithm has the potential for development into a continuous cerebral artery vasospasm monitor.

An endpoint-detection algorithm of surface electromyography insensitive to electrocardiogram interference

Surface electromyography (sEMG) has been widely used in the study of clinical medicine, rehabilitation medicine, sports, etc., and its endpoints should be detected accurately before analyzing. However, endpoint detection is vulnerable to electrocardiogram (ECG) interference when the sEMG recorders are placed near the heart. In this paper, an endpoint-detection algorithm which is insensitive to ECG interference is proposed. In the algorithm, endpoints of sEMG are detected based on the short-time energy and short-time zero-crossing rates of sEMG. The thresholds of short-time energy and short-time zero-crossing rate are set according to the statistical difference of short-time zero-crossing rate between sEMG and ECG, and the statistical difference of short-time energy between sEMG and the background noise. Experiment results on the sEMG of rectus abdominis muscle demonstrate that the algorithm detects the endpoints of the sEMG with a high accuracy rate of 95.6%.

Arrival time estimation methodology for partial discharge acoustic signals in power transformers based on a double-threshold technique

Much attention has been paid to different localisation algorithms to locate partial discharge (PD) sources in power transformers using the acoustic emission (AE) technique. Due to total reflection, AE sensors cannot always detect the signal of a direct wave. As a result, localisation algorithms based on an indirect wave can be more accurate. But little research has addressed arrival time (AT) methods of indirect PD signals. In this paper, a double-threshold (DT) method is introduced, and its improvement based on short-time energy and a zero-crossing rate is described. Because an indirect wave arrives earlier and has lower energy than a direct wave, current AT methods, such as the energy criterion, cross-correlation, and linear prediction residual methods, cannot determine its AT. However, the proposed DT method can determine the AT precisely. Moreover, a localisation experiment was conducted on a 35 kV transformer, and localisation results were calculated employing various AT methods and different localisation algorithms, such as the Chan, genetic, imperial competition, and improved-propagation-route-search algorithms. Characteristics of the proposed AT methods were compared and analysed to show their feasibility and accuracy.

Sounding out ecoacoustic metrics: Avian species richness is predicted by acoustic indices in temperate but not tropical habitats

Affordable, autonomous recording devices facilitate large scale acoustic monitoring and Rapid Acoustic Survey is emerging as a cost-effective approach to ecological monitoring; the success of the approach rests on the development of computational methods by which biodiversity metrics can be automatically derived from remotely collected audio data. Dozens of indices have been proposed to date, but systematic validation against classical, in situ diversity measures are lacking. This study conducted the most comprehensive comparative evaluation to date of the relationship between avian species diversity and a suite of acoustic indices. Acoustic surveys were carried out across habitat gradients in temperate and tropical biomes. Baseline avian species richness and subjective multi-taxa biophonic density estimates were established through aural counting by expert ornithologists. 26 acoustic indices were calculated and compared to observed variations in species diversity. Five acoustic diversity indices (Bioacoustic Index, Acoustic Diversity Index, Acoustic Evenness Index, Acoustic Entropy, and the Normalised Difference Sound Index) were assessed as well as three simple acoustic descriptors (Root-mean-square, Spectral centroid and Zero-crossing rate). Highly significant correlations, of up to 65%, between acoustic indices and avian species richness were observed across temperate habitats, supporting the use of automated acoustic indices in biodiversity monitoring where a single vocal taxon dominates. Significant, weaker correlations were observed in neotropical habitats which host multiple non-avian vocalizing species. Multivariate classification analyses demonstrated that each habitat has a very distinct soundscape and that AIs track observed differences in habitat-dependent community composition. Multivariate analyses of the relative predictive power of AIs show that compound indices are more powerful predictors of avian species richness than any single index and simple descriptors are significant contributors to avian diversity prediction in multi-taxa tropical environments. Our results support the use of community level acoustic indices as a proxy for species richness and point to the potential for tracking subtler habitat-dependent changes in community composition. Recommendations for the design of compound indices for multi-taxa community composition appraisal are put forward, with consideration for the requirements of next generation, low power remote monitoring networks.

Segmentation of continuous audio recordings of Carnatic music concerts into items for archival

Concert recordings of Carnatic music are often continuous and unsegmented. At present, these recordings are manually segmented into items for making CDs. The objective of this paper is to develop algorithms that segment continuous concert recordings into items using applause as a cue. Owing to the ‘here and now’ nature of applauses, the number of applauses exceeds the number of items in the concert. This results in a concert being fragmented into different segments. In the first part of the paper, applause locations are identified using time, and spectral domain features, namely, short-time energy, zero-crossing rate, spectral flux and spectral entropy. In the second part, inter-applause segments are merged if they belong to the same item. The main component of every item in a concert is a composition. A composition is characterised by an ensemble of vocal (or main instrument), violin (optional) and percussion. Inter-applause segments are classified into three segments, namely, vocal solo, violin solo, composition and thaniavarthanam using tonic normalised cent filter-bank cepstral coefficients. Adjacent composition segments are merged into a single item, if they belong to the same melody. Meta-data corresponding to the concert in terms of items, available from listeners, are matched to the segmented audio. The applauses are further classified based on strength using Cumulative Sum. The location of the top three highlights of every concert is documented. The performance of the proposed approaches to applause identification, inter-applause classification and mapping of items is evaluated on 50 live recordings of Carnatic music concerts. The applause identification accuracy is 99%, and the inter- and intra-item classification is 93%, while the mapping accuracy is 95%.

Land Cover Change Detection Using Multiple Shape Parameters of Spectral and NDVI Curves

Spectral and NDVI values have been used to calculate the change magnitudes of land cover, but may result in many pseudo-changes because of inter-class variance. Recently, the shape information of spectral or NDVI curves such as direction, angle, gradient, or other mathematical indicators have been used to improve the accuracy of land cover change detection. However, these measurements, in terms of the single shape features, can hardly capture the complete trends of curves affected by the unsynchronized phenology. Therefore, the calculated change magnitudes are indistinct such that changes and no-changes have a low contrast. This problem has prevented traditional change detection methods from achieving a higher accuracy using bi-temporal images or NDVI time series. In this paper, a multiple shape parameters-based change detection method is proposed by combining the spectral correlation operator and the shape features of NDVI temporal curves (phase angle cumulant, baseline cumulant, relative cumulation rate, and zero-crossing rate). The change magnitude is derived by integrating all the inter-annual differences of these shape parameters. The change regions are discriminated by an automated threshold selection method known as histogram concavity analysis. The results showed that the mean differences in the change magnitudes of the proposed method between 2100 changed and 2523 unchanged pixels was 32%, the overall accuracy was approximately 88%, and the kappa coefficient was 0.76. A comparative analysis was conducted with bi-temporal image-based methods and NDVI time series-based methods, and we demonstrate that the proposed method is more effective and robust than traditional methods in achieving high-contrast change magnitudes and accuracy.

Electromyography-signal-based muscle fatigue assessment for knee rehabilitation monitoring systems.

This study suggested a new EMG-signal-based evaluation method for knee rehabilitation that provides not only fragmentary information like muscle power but also in-depth information like muscle fatigue in the field of rehabilitation which it has not been applied to. In our experiment, nine healthy subjects performed straight leg raise exercises which are widely performed for knee rehabilitation. During the exercises, we recorded the joint angle of the leg and EMG signals from four prime movers of the leg: rectus femoris (RFM), vastus lateralis, vastus medialis, and biceps femoris (BFLH). We extracted two parameters to estimate muscle fatigue from the EMG signals, the zero-crossing rate (ZCR) and amplitude of muscle tension (AMT) that can quantitatively assess muscle fatigue from EMG signals. We found a decrease in the ZCR for the RFM and the BFLH in the muscle fatigue condition for most of the subjects. Also, we found increases in the AMT for the RFM and the BFLH. Based on the results, we quantitatively confirmed that in the state of muscle fatigue, the ZCR shows a decreasing trend whereas the AMT shows an increasing trend. Our results show that both the ZCR and AMT are useful parameters for characterizing the EMG signals in the muscle fatigue condition. In addition, our proposed methods are expected to be useful for developing a navigation system for knee rehabilitation exercises by evaluating the two parameters in two-dimensional parameter space.

Precise detection of speech endpoints dynamically: A wavelet convolution based approach

Precise detection of speech endpoints is an important factor which affects the performance of the systems where speech utterances need to be extracted from the speech signal such as Automatic Speech Recognition (ASR) system. Existing endpoint detection (EPD) methods mostly uses Short-Term Energy (STE), Zero-Crossing Rate (ZCR) based approaches and their variants. But STE and ZCR based EPD algorithms often fail in the presence of Non-speech Sound Artifacts (NSAs) produced by the speakers. Pattern recognition and classification techniques are also applied but those methods require labeled data for training. In this article, a novel approach is proposed to extract speech endpoints and the algorithm is termed as Wavelet Convolution based Speech Endpoint Detection (WCSED). WCSED decomposes the speech signal into high-frequency and low-frequency components using wavelet convolution and then computes information-entropy based thresholds for the two frequency components. The low-frequency thresholds are used to extract voiced speech segments, whereas the high-frequency thresholds are used to extract the unvoiced speech segments by filtering out the NSAs. WCSED does not require any labeled data for training and can automatically extract speech segments. Experiments are carried out on two speech databases and the results are promising even in the presence of NSAs.

Evaluation of Acoustic Parameters for Angulimala Sutta using Voiced to Unvoiced Ration and Vowel Distribution

Pirith is believed as a protective doctrine preached by the Load Buddha in Pali language. The aim of this study is to analyze acoustic properties of Pirith using computer-aided methods and identify special characteristics and patterns. In this study, two methods were used to identify special characteristics of Angulimala Sutta. First method calculates voiced to unvoiced ratio using zero crossing rate and energy content associated with the acoustic signal while second method recognizes vowel distribution using first and second formant frequencies. Results of the first method indicates approximately 96% of frames are voiced while the second method suggests approximately 72% of vowels concentrate in the square region of F1,0~1500 Hz and demonstrating when chanting the Angulimala sutta most of the time the tongue height is low positioned in back levels while lips shaped unrounded. KEYWORDS: Formant frequencies, Voiced to unvoiced ratio, Zero-Crossing rate, Vowel distribution

A novel hand gesture recognition method based on 2-channel sEMG.

Hand gesture recognition is getting more and more important in the area of rehabilitation and human machine interface (HMI). However, most current approaches are difficult to achieve practical application because of an excess of sensors. In this work, we proposed a method to recognize six common hand gestures and establish the optimal relationship between hand gesture and muscle by utilizing only two channels of surface electromyography (sEMG). We proposed an integrated approach to process the sEMG data including filtering, endpoint detection, feature extraction, and classifier. In this study, we used one-order digital lowpass infinite impulse response (IIR) filter with the cutoff frequency of 500 Hz to extract the envelope of the sEMG signals. The energy was utilized as a feature to detect the endpoint of motion. The short-time energy, zero-crossing rate and linear predictive coefficient (LPC) with 12 levels were chosen as the features and back propagation (BP) neural network was utilized to classify. In order to test the method, five subjects were involved in the experiment to test the hypothesis. With the proposed method, 96.41% to 99.70% recognition rate was obtained. The experimental results revealed that the proposed method is highly efficient both in sEMG data acquisition and hand motions recognition, and played a role in promoting hand rehabilitation and HMI.

Electroencephalography Based Fusion Two-Dimensional (2D)-Convolution Neural Networks (CNN) Model for Emotion Recognition System.

The purpose of this study is to improve human emotional classification accuracy using a convolution neural networks (CNN) model and to suggest an overall method to classify emotion based on multimodal data. We improved classification performance by combining electroencephalogram (EEG) and galvanic skin response (GSR) signals. GSR signals are preprocessed using by the zero-crossing rate. Sufficient EEG feature extraction can be obtained through CNN. Therefore, we propose a suitable CNN model for feature extraction by tuning hyper parameters in convolution filters. The EEG signal is preprocessed prior to convolution by a wavelet transform while considering time and frequency simultaneously. We use a database for emotion analysis using the physiological signals open dataset to verify the proposed process, achieving 73.4% accuracy, showing significant performance improvement over the current best practice models.

Driver Behaviour State Recognition based on Speech

Researches have linked the cause of traffic accident to driver behavior and some studies provided practical preventive measures based on different input sources. Due to its simplicity to collect, speech can be used as one of the input. The emotion information gathered from speech can be used to measure driver behavior state based on the hypothesis that emotion influences driver behavior. However, the massive amount of driving speech data may hinder optimal performance of processing and analyzing the data due to the computational complexity and time constraint. This paper presents a silence removal approach using Short Term Energy (STE) and Zero Crossing Rate (ZCR) in the pre-processing phase to reduce the unnecessary processing. Mel Frequency Cepstral Coefficient (MFCC) feature extraction method coupled with Multi-Layer Perceptron (MLP) classifier are employed to get the driver behavior state recognition performance. Experimental results demonstrated that the proposed approach can obtain comparable performance with accuracy ranging between 58.7% and 76.6% to differentiate four driver behavior states, namely; talking through mobile phone, laughing, sleepy and normal driving. It is envisaged that such approach can be extended for a more comprehensive driver behavior identification system that may acts as an embedded warning system for sleepy driver.

An Energy-Minimizing Level Set Method for Defect Detection

This paper proposes an energy-minimizing level set method for defect detection in product surface, which consists of image segmentation module, image feature extraction module and product defect detection module. This new method, embedding energy function into the classic level set algorithm, segments internal and external areas of product image with minimized energy consumption, ensuring that the gradient of the level set function is in the direction of the minimum point so that the evolution process is closer to the zero level set. 15-dimentional features including zero-crossing rate and image entropy are used in the process of contour detection. Results show that the method is highly accurate and effective.

Probabilistic Event Discrimination Algorithm for Fiber Optic Perimeter Security Systems

This paper proposes an event discrimination algorithm with probabilistic output for fiber optic perimeter security systems. Multiscale permutation entropy and the zero-crossing rate are employed to increase the efficiency of the algorithm and extract intrusion features. A probabilistic support vector machine is used to calculate multiple event probabilities by solving a convex quadratic programming problem. The experimental results demonstrate that the proposed algorithm can distinguish six intrusion events at an average recognition rate of 92.68% and in a processing time of 0.32 s. Compared with traditional discrimination methods, the proposed algorithm obtains more detailed information (probabilities) of intrusion events. The recognition results are obtained after analyzing the probabilities, which not only reduces the decision-making costs but also reduces the losses from erroneous decisions. Therefore, the proposed high-efficiency feature extraction method and reliable discrimination algorithm can be used to improve the monitoring efficiency of fiber optic perimeter security systems.

Use of Acoustic Emission and Pattern Recognition for Crack Detection of a Large Carbide Anvil.

Large-volume cubic high-pressure apparatus is commonly used to produce synthetic diamond. Due to the high pressure, high temperature and alternative stresses in practical production, cracks often occur in the carbide anvil, thereby resulting in significant economic losses or even casualties. Conventional methods are unsuitable for crack detection of the carbide anvil. This paper is concerned with acoustic emission-based crack detection of carbide anvils, regarded as a pattern recognition problem; this is achieved using a microphone, with methods including sound pulse detection, feature extraction, feature optimization and classifier design. Through analyzing the characteristics of background noise, the cracked sound pulses are separated accurately from the originally continuous signal. Subsequently, three different kinds of features including a zero-crossing rate, sound pressure levels, and linear prediction cepstrum coefficients are presented for characterizing the cracked sound pulses. The original high-dimensional features are adaptively optimized using principal component analysis. A hybrid framework of a support vector machine with k nearest neighbors is designed to recognize the cracked sound pulses. Finally, experiments are conducted in a practical diamond workshop to validate the feasibility and efficiency of the proposed method.

Auditory Suspicious Event Databases: DASE and Bi-DASE

The lack of open-access databases for auditory suspicious events’ detection and classification algorithms is a hurdle for researchers while evaluating and comparing the performance of suspicious sound event detection and recognition systems. This paper introduces two databases called DASE and bi-DASE. DASE contains nine of the most common acoustic suspicious events with a total of 3105 sound event recordings of glass breaking, dog barking, scream, gunshot, explosion, alarm, sirens, door slams, and footsteps. Bi-DASE database is prepared by mixing two auditory suspicious events from DASE to generate 25 possible real-life scenarios. Both databases are divided into two sets as a training set and testing set. ANOVA and regression analysis are performed in regard to commonly used features, energy, 12 MFCCs, pitch range, spectral centroid frequency, spectral spread, spectral flatness, tonality, harmonics, zero-crossing rate, and fundamental frequency. All features are found to be significantly important based on their $p$ -values for both databases, which are evaluated by designing two baseline systems using support vector machines and $k$ -nearest neighbors algorithm. Experimental results are presented. The databases are available for free to the research community upon request.

ECG Signal De-noising and Baseline Wander Correction Based on CEEMDAN and Wavelet Threshold.

A novel electrocardiogram (ECG) signal de-noising and baseline wander correction method based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and wavelet threshold is proposed. Although CEEMDAN is based on empirical mode decomposition (EMD), it represents a significant improvement of the original EMD by overcoming the mode-mixing problem. However, there has been no previous study on using CEEMDAN to de-noise ECG signals, to the authors’ best knowledge. In the proposed method, the original noisy ECG signal is decomposed into a series of intrinsic mode functions (IMFs) sorted from high to low frequency by CEEMDAN. Each IMF is then analyzed by the autocorrelation method to find out the first few high frequency IMFs containing random noise, and these IMFs should be de-noised by the wavelet threshold. The zero-crossing rate (ZCR) of all IMFs, including final residue, are computed, and the IMFs with ZCR less than a certain value are removed. Finally, the remaining IMFs are reconstructed to obtain the clean ECG signal. The proposed algorithm is validated through experiments using the MIT–BIH ECG databases, and the results show that the random noise in the ECG signal can be effectively suppressed, and at the same time the baseline wander can be corrected efficiently.

Development of Acoustical Feature Based Classifier Using Decision Fusion Technique for Malay Language Disfluencies Classification

<p>Speech disfluency such as filled pause (FP) is a hindrance in Automated Speech Recognition as it degrades the accuracy performance. Previous work of FP detection and classification have fused a number of acoustical features as fusion classification is known to improve classification results. This paper presents new decision fusion of two well-established acoustical features that are zero crossing rates (ZCR) and speech envelope (ENV) with eight popular acoustical features for classification of Malay language filled pause (FP) and elongation (ELO). Five hundred ELO and 500 FP are selected from a spontaneous speeches of a parliamentary session and Naïve Bayes classifier is used for the decision fusion classification. The proposed feature fusion produced better classification performance compared to single feature classification with the highest F-measure of 82% for both classes.</p>

Frog sound identification using extended k-nearest neighbor classifier

Frog sound identification based on the vocalization becomes important for biological research and environmental monitoring. As a result, different types of feature extractions and classifiers have been employed to evaluate the accuracy of frog sound identification. This paper presents a frog sound identification with Extended k-Nearest Neighbor (EKNN) classifier. The EKNN classifier integrates the nearest neighbors and mutual sharing of neighborhood concepts, with the aims of improving the classification performance. It makes a prediction based on who are the nearest neighbors of the testing sample and who consider the testing sample as their nearest neighbors. In order to evaluate the classification performance in frog sound identification, the EKNN classifier is compared with competing classifier, k -Nearest Neighbor (KNN), Fuzzy k -Nearest Neighbor (FKNN) k - General Nearest Neighbor (KGNN)and Mutual k -Nearest Neighbor (MKNN) on the recorded sounds of 15 frog species obtained in Malaysia forest. The recorded sounds have been segmented using Short Time Energy and Short Time Average Zero Crossing Rate (STE+STAZCR), sinusoidal modeling (SM), manual and the combination of Energy (E) and Zero Crossing Rate (ZCR) (E+ZCR) while the features are extracted by Mel Frequency Cepstrum Coefficient (MFCC). The experimental results have shown that the EKNCN classifier exhibits the best performance in terms of accuracy compared to the competing classifiers, KNN, FKNN, GKNN and MKNN for all cases.

On the Evolutionary Characteristics of the Acceleration Records Generated From Linear Time-Variant Systems

This paper discusses the time-varying characteristics of the output signals resulted from linear time variant (LTV) systems using level crossing properties. These systems which are used for generating synthetic records based on a target record contain two identification processes: 1) amplitude modulating function, 2) time-varying impulse response function (IRF) parameters. For efficient tracking of the IRF parameters, the zero-crossing and positive minima/negative maxima cumulative curves are usually utilized as the measures of the instantaneous spectral power. Using spectral moments, analytic relations for zero-crossing and positive minima/negative maxima cumulative count are developed with respect to the IRF’s evolutionary power spectrum. In order to efficiently investigate the low-frequency components of the output records, the zero-crossing rate of the velocity and the displacement records are tracked and rigorous analytic equations for their descriptions are developed. Some of the issues concerning application of the developed equations are explored using two LVT models, and the limitations of the proposed procedures are explained. Through introduction of new compatibility measures, the necessity of implementing Monte Carlo simulations would no longer be needed and it would be possible to generate the synthetic acceleration records with desirable evolutionary characteristics with much less computation time.