Multi-class fault diagnosis of induction motor using Hilbert and Wavelet Transform

The information extraction capability of two widely used signal processing tools, Hilbert Transform (HT) and Wavelet Transform (WT), is investigated to develop a multi-class fault diagnosis scheme for induction motor using radial vibration signals. The vibration signals are associated with unique predominant frequency components and instantaneous amplitudes depending on the motor condition. Using good systematic and analytical approach this fault frequencies can be identified. However, some faults either electrical or mechanical in nature are associated with same or similar vibration frequencies leading to erroneous conclusions. Genetic Algorithm (GA) is proposed and used successfully to find the most relevant fault frequencies in radial (vertical) frame vibration signal which can be used to diagnose the induction motor faults very effectively even in the presence of noise. The information obtained by Continuous Wavelet Transform (CWT) was found to be highly redundant compared to HT and thus by selecting the most relevant features using GA, the fault classification accuracy has considerably improved especially for CWT. Almost similar fault frequencies were found using CWT + GA and HT + GA for radial vibration signal.     

Unsupervised feature selection using swarm intelligence and consensus clustering for automatic fault detection and diagnosis in Heating Ventilation and Air Conditioning systems

Various sensory and control signals in a Heating Ventilation and Air Conditioning (HVAC) system are closely interrelated which give rise to severe redundancies between original signals. These redundancies may cripple the generalization capability of an automatic fault detection and diagnosis (AFDD) algorithm. This paper proposes an unsupervised feature selection approach and its application to AFDD in a HVAC system. Using Ensemble Rapid Centroid Estimation (ERCE), the important features are automatically selected from original measurements based on the relative entropy between the low- and high-frequency features. The materials used is the experimental HVAC fault data from the ASHRAE-1312-RP datasets containing a total of 49 days of various types of faults and corresponding severity. The features selected using ERCE (Median normalized mutual information (NMI) = 0.019) achieved the least redundancies compared to those selected using manual selection (Median NMI = 0.0199) Complete Linkage (Median NMI = 0.1305), Evidence Accumulation K-means (Median NMI = 0.04) and Weighted Evidence Accumulation K-means (Median NMI = 0.048). The effectiveness of the feature selection method is further investigated using two well-established time-sequence classification algorithms: (a) Nonlinear Auto-Regressive Neural Network with eXogenous inputs and distributed time delays (NARX-TDNN); and (b) Hidden Markov Models (HMM); where weighted average sensitivity and specificity of: (a) higher than 99% and 96% for NARX-TDNN; and (b) higher than 98% and 86% for HMM is observed. The proposed feature selection algorithm could potentially be applied to other model-based systems to improve the fault detection performance.     

Comparison of wavelet families for texture classification by using wavelet packet entropy adaptive network based fuzzy inference system

Recently, significant of the robust texture image classification has increased. The texture image classification is used for many areas such as medicine image processing, radar image processing, etc. In this study, a new method for invariant pixel regions texture image classification is presented. Wavelet packet entropy adaptive network based fuzzy inference system (WPEANFIS) was developed for classification of the twenty 512 × 512 texture images obtained from Brodatz image album. There, sixty 32 × 32 image regions were randomly selected (overlapping or non-overlapping) from each of these 20 images. Thirty of these image regions and other 30 of these image regions are used for training and testing processing of the WPEANFIS, respectively. In this application study, Daubechies, biorthogonal, coiflets, and symlets wavelet families were used for wavelet packet transform part of the WPEANFIS algorithm, respectively. In this way, effects to correct texture classification performance of these wavelet families were compared. Efficiency of WPEANFIS developed method was tested and a mean %93.12 recognition success was obtained.     

An optimum feature extraction method based on Wavelet–Radon Transform and Dynamic Neural Network for pavement distress classification

Quantification of pavement crack data is one of the most important criteria in determining optimum pavement maintenance strategies. Recently, multi-resolution analysis such as wavelet decompositions provides very good multi-resolution analytical tools for different scales of pavement analysis and distresses classification. This paper present an automatic diagnosis system for detecting and classification pavement crack distress based on Wavelet–Radon Transform (WR) and Dynamic Neural Network (DNN) threshold selection. The algorithm of the proposed system consists of a combination of feature extraction using WR and classification using the neural network technique. The proposed WR + DNN system performance is compared with static neural network (SNN). In test stage; proposed method was applied to the pavement images database to evaluate the system performance. The correct classification rate (CCR) of proposed system is over 99%. This research demonstrated that the WR + DNN method can be used efficiently for fast automatic pavement distress detection and classification. The details of the image processing technique and the characteristic of system are also described in this paper.     

High resolution ambulatory holter ECG events detection-delineation via modified multi-lead wavelet-based features analysis: Detection and quantification of heart rate turbulence

The presented study describes a false-alarm probability-FAP bounded solution for detecting and quantifying Heart Rate Turbulence (HRT) major parameters including heart rate (HR) acceleration/deceleration, turbulence jump, compensatory pause value and HR recovery rate. To this end, first, high resolution multi-lead holter electrocardiogram (ECG) signal is appropriately pre-processed via Discrete Wavelet Transform (DWT) and then, a fixed sample size sliding window is moved on the pre-processed trend. In each slid, the area under the excerpted segment is multiplied by its curve-length to generate the Area Curve Length (ACL) metric to be used as the ECG events detection-delineation decision statistic (DS). The ECG events detection-delineation algorithm was applied to various existing databases and as a result, the average values of sensitivity and positive predictivity Se = 99.95% and P+ = 99.92% were obtained for the detection of QRS complexes, with the average maximum delineation error of 7.4 msec, 4.2 msec and 8.3 msec for P-wave, QRS complex and T-wave, respectively. Because the heart-rate time series might include fast fluctuations which don’t follow a premature ventricular contraction (PVC) causing high-level false alarm probability (false positive detections) of HRT detection, based on the binary two-dimensional Neyman-Pearson radius test (which is a FAP-bounded classifier), a new method for discrimination of PVCs from other beats using the geometrical-based features is proposed. The statistical performance of the proposed HRT detection-quantification algorithm was obtained as Se = 99.94% and P+ = 99.85% showing marginal improvement for the detection-quantification of this phenomenon. In summary, marginal performance improvement of ECG events detection-delineation process, high performance PVC detection and isolation from noisy holter data and reliable robustness against holter strong noise and artifacts can be mentioned as important merits and capabilities of the proposed HRT detection algorithm.     

Computer-based analysis of explicit approximations to the implicit Colebrook–White equation in turbulent flow friction factor calculation

The implicit Colebrook–White equation has been widely used to estimate the friction factor for turbulent fluid-flow in rough-pipes. In this paper, the state-of-the-art review for the most currently available explicit alternatives to the Colebrook–White equation, is presented. An extensive comparison test was established on the 20 × 500 grid, for a wide range of relative roughness (ε/D) and Reynolds number (R) values (1 × 10^?6 ? ε/D ? 5 × 10^?2; 4 × 10³ ? R ? 10⁸), covering a large portion of turbulent flow zone in Moody’s diagram. Based on the comprehensive error analysis, the magnitude points in which the maximum absolute and the maximum relative error are occurred at the pair of ε/D and R values, are observed. A limiting case of the most of these approximations provided friction factor estimates that are characterized by a mean absolute error of 5 × 10^?4, a maximum absolute error of 4 × 10^?3 whereas, a mean relative error of 1.3% and a maximum relative error of 5.8%, over the entire range of ε/D and R values, respectively. For practical purposes, the complete results for the maximum and the mean relative errors versus the 20 sets of ε/D value, are also indicated in two comparative figures. The examination results for error properties of these approximations gives one an opportunity to practically evaluate the most accurate formula among of all the previous explicit models; and showing in this way its great flexibility for estimating turbulent flow friction factor. Comparative analysis for the mean relative error profile revealed, the classification for the best-fitted six equations examined was in a good agreement with those of the best model selection criterion claimed in the recent literature, for all performed simulations.     

Speech emotion recognition: Features and classification models

To solve the speaker independent emotion recognition problem, a three-level speech emotion recognition model is proposed to classify six speech emotions, including sadness, anger, surprise, fear, happiness and disgust from coarse to fine. For each level, appropriate features are selected from 288 candidates by using Fisher rate which is also regarded as input parameter for Support Vector Machine (SVM). In order to evaluate the proposed system, principal component analysis (PCA) for dimension reduction and artificial neural network (ANN) for classification are adopted to design four comparative experiments, including Fisher + SVM, PCA + SVM, Fisher + ANN, PCA + ANN. The experimental results proved that Fisher is better than PCA for dimension reduction, and SVM is more expansible than ANN for speaker independent speech emotion recognition. The average recognition rates for each level are 86.5%, 68.5% and 50.2% respectively.     

Exploitation of aeroelastic effects for drift reduction,in an all-polymer air flow sensor

This paper presents a vibration amplitude measurement method that greatly reduces the effects of baseline resistance drift in an all-polymer piezoresistive flow sensor or microtuft. The sensor fabrication is based on flexible printed circuit board (flex-PCB) technology to enable the potential for low-cost and scalable manufacture. Drift reduction is accomplished by discriminating the flow-induced vibration (‘flutter’) amplitude of the microtuft-based sensor as a function of flow velocity. Flutter peak-to-peak amplitude is measured using a microcontroller-based custom readout circuit. The fabricated sensor with the readout circuitry demonstrated a drift error of 2.8 mV/h, which corresponds to a flow-referenced drift error of 0.2 m/s of wind velocity per hour. The sensor has a sensitivity of 14.5 mV/(m/s) with less than 1% non-linearity over the velocity range of 5–16 m/s. The proposed vibration amplitude measurement method is also applied to a sensor array with a modified structure and a reduced dimension, which demonstrated a sensitivity of 13.2 mV/(m/s) with a flow-referenced drift error of 0.03 m/s of wind velocity per hour.     

Objective quality definition of scalable video coding and its application for optimal streaming of FGS-coded videos

With the proliferation of video contents widely distributed over the Internet and the progress of video coding (e.g., H.264/AVC) and transmission technologies, more challenges need to overcome in order to meet the requirements of all users with diverse terminals. Video streaming over IP and wireless becomes a popular issue since the new century.However, there is little work concerning the quantitative analysis on the objective quality of streaming videos. Thus a strict definition of the objective quality and quality variation of scalable video coding (SVC) is required, in order to efficiently transmit video contents over Internet and wireless and reach an attainable subjective quality perception for end-users. Since FGS (fine granularity scalability) video is coded in bit planes, its enhancing layer can be truncated arbitrarily, as a case study of scalable video coding, an objective quality definition for FGS-coded video is introduced in this paper, based on MSE (mean square error) and PSNR (peak signal-to-noise ratio). This definition can also be generalized to any layered scalable coding videos, such as the traditional layered videos in BL + ELs (base layer + enhancing layers) formats or H.264/AVC in BL + CGS (coarse granularity scalability) + FGS structures, and it can be applied to design optimal algorithms for video streaming. Furthermore, It can also be taken as a measure to assess the subjective quality of streaming videos, by incorporating user preferences and terminal capacities.According to this definition, a quality optimal problem of scene in video segments is formulated and solved using the state transfer graph and dynamic programming. The optimal transmission policy is also obtained and compared with a real-time transmission algorithm. Different aggregation levels (segmentation granularity) of video segments for optimal transmission are also examined by experimental data. Simulation results validate our observations.     

An optimisation approach to the recovery of reflection parameters from a single hyperspectral image

In this paper, we present a method to recover the parameters governing the reflection of light from a surface making use of a single hyperspectral image. To do this, we view the image radiance as a combination of specular and diffuse reflection components and present a cost functional which can be used for purposes of iterative least squares optimisation. This optimisation process is quite general in nature and can be applied to a number of reflectance models widely used in the computer vision and graphics communities. We elaborate on the use of these models in our optimisation process and provide a variant of the Beckmann–Kirchhoff model which incorporates the Fresnel reflection term. We show results on synthetic images and illustrate how the recovered photometric parameters can be employed for skin recognition in real world imagery, where our estimated albedo yields a classification rate of 95.09 ± 4.26% as compared to an alternative, whose classification rate is of 90.94 ± 6.12%. We also show quantitative results on the estimation of the index of refraction, where our method delivers an average per-pixel angular error of 0.15°. This is a considerable improvement with respect to an alternative, which yields an error of 9.9°.     

Experimental blood glucose interval identification of patients with type 1 diabetes

Many problems are confronted when characterizing a type 1 diabetic patient such as model mismatches, noisy inputs, measurement errors and huge variability in the glucose profiles. In this work we introduce a new identification method based on interval analysis where variability and model imprecisions are represented by an interval model as parametric uncertainty.The minimization of a composite cost index comprising: (1) the glucose envelope width predicted by the interval model, and (2) a Hausdorff-distance-based prediction error with respect to the envelope, is proposed. The method is evaluated with clinical data consisting in insulin and blood glucose reference measurements from 12 patients for four different lunchtime postprandial periods each.Following a “leave-one-day-out” cross-validation study, model prediction capabilities for validation days were encouraging (medians of: relative error = 5.45%, samples predicted = 57%, prediction width = 79.1 mg/dL). The consideration of the days with maximum patient variability represented as identification days, resulted in improved prediction capabilities for the identified model (medians of: relative error = 0.03%, samples predicted = 96.8%, prediction width = 101.3 mg/dL). Feasibility of interval models identification in the context of type 1 diabetes was demonstrated.     

Calculation of sound generation and radiation from instationary flows

The Lattice–Boltzmann method (LBM) for simulation of low Mach number flows is evaluated for the application in flow acoustics. By linearization and von-Neumann analysis quantitative measures for the accuracy of phase speed and attenuation of low amplitude sound waves in presence of a mean flow are derived. It is shown that only phase errors are relevant when simulating sound waves in the audible frequency range in air. For the two dimensional 9 bit model and the three dimensional 19 bit model the phase speed error is below 0.1% (1%) as long as the wave is resolved with at least 34 (12) points per wavelength. The LBM is applied to the problem of a Helmholtz resonator under a grazing flow and to the trailing edge noise generation problem. The results clearly demonstrate the ability to reproduce relevant flow acoustic effects.     

On the mechanism of substrate/non-substrate recognition by P-glycoprotein

P-Glycoprotein (P-gp, multi-drug resistance protein, MDR1) plays a gatekeeper role, interfering delivery of multiple pharmaceuticals to the target tissues and cells. We performed Molecular Dynamics (MD) simulations to generate fifty side-chain variants for P-gp (PDB ID: 4Q9H-L) followed by docking of 31 drugs (0.6 ≤ ER ≤ 22.7) to the whole surface except the ATPase domains and the extracellular part. A selection of the most negative energy complex for each ligand followed. All compounds docked to the two areas – the main binding cavity at the top of P-gp (12.5% of compounds with ER < 1; 44.4% of 1 ≤ ER ≤ 2; and 100% of ER > 2), and the binding sites in the middle of P-gp (87.5% of ER < 1; 55.6% of 1 ≤ ER ≤ 2; and 0% of ER > 2). Our results show that anti-substrates (ER < 1), intermediate compounds (1 ≤ ER ≤ 2) and strong substrates (ER > 2) might behave differently in relation to the P-gp. According to our calculations, the anti-substrates almost do not bind the main binding cavity (MBC) of P-gp and rather approach the other binding sites on the protein; the substrates preferably bind the MBC; the intermediate compounds with 1 ≤ ER ≤ 2 bind both MBC and other binding sites almost equally. The modelling results are in line with the known hypothesis that binding the MBC is prerequisite for the pumping the compound off the P-gp.     

Two-terminal ultrahigh frequency carrier type thin-film magnetic sensor using impedance matching lines

This article reports on output and band characteristics of the two-terminal ultrahigh frequency (UHF) carrier type magnetic field sensor, which is based on impedance change due to magnetic field dependent permeability, and a magnetic field is detected as an amplitude modulation of a UHF carrier voltage. Two types of transmission line configurations (type-A and type-B) are proposed to make a two-terminal sensor rather than the four terminals of the conventional sensor operating on this principle, because the two-terminal sensor is more advantageous in terms of designing and fabricating of the sensor element and the transmission lines than the four-terminal sensor. In the type-A, a half-wave impedance matching line is added between the element and the carrier power supplying points. Also, in the type-B, a carrier power is supplied on the quarter-wave matching line located between the element and the load. The type-A sensor exhibits a lower output and a much narrower 3 dB-bandwidth of a few tens of MHz than the four-terminal sensor. In contrast, a higher output than that in the four-terminal sensor and a 3 dB-bandwidth of ～100 MHz are confirmed in the type-B sensor by experiments and calculations.     

Automated delineation of thyroid nodules in ultrasound images using spatial neutrosophic clustering and level set

An accurate contour estimation plays a significant role in classification and estimation of shape, size, and position of thyroid nodule. This helps to reduce the number of false positives, improves the accurate detection and efficient diagnosis of thyroid nodules. This paper introduces an automated delineation method that integrates spatial information with neutrosophic clustering and level-sets for accurate and effective segmentation of thyroid nodules in ultrasound images. The proposed delineation method named as Spatial Neutrosophic Distance Regularized Level Set (SNDRLS) is based on Neutrosophic L-Means (NLM) clustering which incorporates spatial information for Level Set evolution. The SNDRLS takes rough estimation of region of interest (ROI) as input provided by Spatial NLM (SNLM) clustering for precise delineation of one or more nodules. The performance of the proposed method is compared with level set, NLM clustering, Active Contour Without Edges (ACWE), Fuzzy C-Means (FCM) clustering and Neutrosophic based Watershed segmentation methods using the same image dataset. To validate the SNDRLS method, the manual demarcations from three expert radiologists are employed as ground truth. The SNDRLS yields the closest boundaries to the ground truth compared to other methods as revealed by six assessment measures (true positive rate is 95.45 ± 3.5%, false positive rate is 7.32 ± 5.3% and overlap is 93.15 ± 5. 2%, mean absolute distance is 1.8 ± 1.4 pixels, Hausdorff distance is 0.7 ± 0.4 pixels and Dice metric is 94.25 ± 4.6%). The experimental results show that the SNDRLS is able to delineate multiple nodules in thyroid ultrasound images accurately and effectively. The proposed method achieves the automated nodule boundary even for low-contrast, blurred, and noisy thyroid ultrasound images without any human intervention. Additionally, the SNDRLS has the ability to determine the controlling parameters adaptively from SNLM clustering.     

Comparison of multilabel classification models to forecast project dispute resolutions

Early forecasting of project dispute resolutions (PDRs) provides decision-support information for resolving potential procurement problems before a dispute occurs. This study compares the performances of classification and ensemble models for predicting dispute handling methods in public–private partnership (PPP) projects. Model analyses use machine learners (i.e., Support Vector Machines (SVMs), Artificial Neural Networks (ANNs), and Tree-augmented Naïve (TAN) Bayesian), classification and regression-based techniques (i.e., Classification and Regression Tree (CART), Quick, Unbiased and Efficient Statistical Tree (QUEST), Exhaustive Chi-squared Automatic Interaction Detection (Exhaustive CHAID), and C5.0), and combinations of these techniques that performed best for a set of PPP data. Analytical results exhibit that the combined technique of QUEST + CHAID + C5.0 has the best classification accuracy at 84.65% in predicting dispute resolution outcomes (i.e., mediation, arbitration, litigation, negotiation, administrative appeals or no dispute occurred). Moreover, as the dispute category and phase in which the dispute occurs are known during project execution, the best classification model is the CART model, with an accuracy of 69.05%. This study demonstrates effective classification application for early PDR prediction related to public infrastructure projects.     

Two novel proposed discrete wavelet transform and filter based approaches for short-circuit faults detection in power transmission lines

In this study, two approaches are presented to detect short-circuit faults in power transmission lines. The two proposed methods are completely novel from both theoretical and technical aspects. The first approach is a soft computing method that uses discrete wavelet transform with Daubechies mother wavelets db1, db2, db3, and db4. The second approach is a hardware based method that utilizes a novel proposed two-stage finite impulse response filter with a sampling frequency of 32 kHz, and a very short process time about three samples time. The two approaches are analyzed by presenting theoretical results. Simulated results obtained by simulating a three-phase 230 kV, 50 Hz power transmission line are given that validate the theoretical results, and explicitly verify that the filter based approach has an accuracy of 100% in presence of 10% disturbance while the accuracy of the wavelet transform based approach is maximally 97%, but it has less complication and implementation cost. Another comparative study between this work and other works shows that the two proposed methods have higher accuracy and very shorter process time compared to the other methods, especially in presence of 10% disturbance that actually occurs in power transmission lines.     

Fabrication of a thin plasmonic color sheet embedded with Al subwavelength gratings in parylene

In this study, we developed a thin plasmonic color sheet (TPCS) embedded with Al subwavelength gratings for use in flexible optical transmission filters, and experimentally demonstrated its transmission characteristics. Al subwavelength gratings were formed in a freestanding thin poly-para-xylylene (parylene-N) film less than 1-μm thick by using electron beam (EB) direct writing and sacrificial etching. The fabricated TPCS contained Al subwavelength gratings with periods ranging from 400 nm to 600 nm, and succeeded in shifting the transmission peak wavelength from 510 nm to 650 nm in the visible range. The freestanding thin parylene-N film deposited by room-temperature chemical vapor deposition provided enough flatness to the TPCS with a height difference of 900 nm in a whole filter area, resulting in uniform transmission spectra. The experimentally obtained peak shift dependent on the grating period agreed well with theoretical calculation results.     

Performance comparison of artificial neural network and logistic regression model for differentiating lung nodules on CT scans

PurposeTo compare the diagnostic performances of artificial neural networks (ANNs) and multivariable logistic regression (LR) analyses for differentiating between malignant and benign lung nodules on computed tomography (CT) scans.MethodsThis study evaluated 135 malignant nodules and 65 benign nodules. For each nodule, morphologic features (size, margins, contour, internal characteristics) on CT images and the patient’s age, sex and history of bloody sputum were recorded. Based on 200 bootstrap samples generated from the initial dataset, 200 pairs of ANN and LR models were built and tested. The area under the receiver operating characteristic (ROC) curve, Hosmer–Lemeshow statistic and overall accuracy rate were used for the performance comparison.ResultsANNs had a higher discriminative performance than LR models (area under the ROC curve: 0.955 ± 0.015 (mean ± standard error) and 0.929 ± 0.017, respectively, p < 0.05). The overall accuracy rate for ANNs (90.0 ± 2.0%) was greater than that for LR models (86.9 ± 1.6%, p < 0.05). The Hosmer–Lemeshow statistic for the ANNs was 8.76 ± 6.59 vs. 6.62 ± 4.03 (p > 0.05) for the LR models.ConclusionsWhen used to differentiate between malignant and benign lung nodules on CT scans based on both objective and subjective features, ANNs outperformed LR models in both discrimination and clinical usefulness, but did not outperform for the calibration.     

GNSS accuracy enhancement based on pseudo range error estimation in an urban propagation environment

For new ITS applications, positioning solutions will require to be more accurate and available. The most common technique used today is composed of a GPS receiver, sometimes aided by other sensors. GPS, and GNSS in general, suffer from masking effects and propagation disturbances in urban areas that cause biases on pseudo range measurements. Mitigation solutions sometimes propose to detect and exclude outliers but in land transportation applications, such a decision reduces dramatically the service availability and thus, the interest of satellite-based solutions. In order to optimize the use the satellites received, we propose a new positioning algorithm based on signals only with pseudo range error modeling in association with an adapted filtering process. The model and the filter have been validated with simulation data performed along an urban bus line and have shown that both positioning error and availability can be improved. Along the trajectory tested, the mean accuracy has been reduced from 5.3 m with a classical filter to 2.6 m with our algorithm with 89% of the points more accurate than 5 m instead of 64% before.