Zeitschriftenartikel: „Wavelet Scattering Transform“

1

Yaou, M. H., und W. T. Chang. „Wavelet transform in scattering data interpolation“. Electronics Letters 29, Nr. 21 (1993): 1835. http://dx.doi.org/10.1049/el:19931221.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

2

Wang, Juan, Jiangshe Zhang und Jie Zhao. „Texture Classification Using Scattering Statistical and Cooccurrence Features“. Mathematical Problems in Engineering 2016 (2016): 1–6. http://dx.doi.org/10.1155/2016/3946312.

Der volle Inhalt der Quelle

Annotation:

Texture classification is an important research topic in image processing. In 2012, scattering transform computed by iterating over successive wavelet transforms and modulus operators was introduced. This paper presents new approaches for texture features extraction using scattering transform. Scattering statistical features and scattering cooccurrence features are derived from subbands of the scattering decomposition and original images. And these features are used for classification for the four datasets containing 20, 30, 112, and 129 texture images, respectively. Experimental results show that our approaches have the promising results in classification.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

3

Liu, Zhishuai, Guihua Yao, Qing Zhang, Junpu Zhang und Xueying Zeng. „Wavelet Scattering Transform for ECG Beat Classification“. Computational and Mathematical Methods in Medicine 2020 (09.10.2020): 1–11. http://dx.doi.org/10.1155/2020/3215681.

Der volle Inhalt der Quelle

Annotation:

An electrocardiogram (ECG) records the electrical activity of the heart; it contains rich pathological information on cardiovascular diseases, such as arrhythmia. However, it is difficult to visually analyze ECG signals due to their complexity and nonlinearity. The wavelet scattering transform can generate translation-invariant and deformation-stable representations of ECG signals through cascades of wavelet convolutions with nonlinear modulus and averaging operators. We proposed a novel approach using wavelet scattering transform to automatically classify four categories of arrhythmia ECG heartbeats, namely, nonectopic (N), supraventricular ectopic (S), ventricular ectopic (V), and fusion (F) beats. In this study, the wavelet scattering transform extracted 8 time windows from each ECG heartbeat. Two dimensionality reduction methods, principal component analysis (PCA) and time window selection, were applied on the 8 time windows. These processed features were fed to the neural network (NN), probabilistic neural network (PNN), and k-nearest neighbour (KNN) classifiers for classification. The 4th time window in combination with KNN (k=4) has achieved the optimal performance with an averaged accuracy, positive predictive value, sensitivity, and specificity of 99.3%, 99.6%, 99.5%, and 98.8%, respectively, using tenfold cross-validation. Thus, our proposed model is capable of highly accurate arrhythmia classification and will provide assistance to physicians in ECG interpretation.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

4

Marzog, Heyam A., und Haider J. Abd. „Machine Learning ECG Classification Using Wavelet Scattering of Feature Extraction“. Applied Computational Intelligence and Soft Computing 2022 (19.09.2022): 1–8. http://dx.doi.org/10.1155/2022/9884076.

Der volle Inhalt der Quelle

Annotation:

The heart’s electrical activity is registered by an electrocardiogram (ECG), which consists of a wealth of pathological data on heart diseases such as arrhythmia. However, with increasing complexity and nonlinearity, direct observation of ECG signals and analysis is very tough. The highest accuracy of classification performance for machine learning approaches are 99.7 for neural network with wavelet scattering features extraction and 99.92 for SVM also with wavelet scattering features extraction. Through wavelet cascades with a neural network, the wavelet scattering transform can yield a translation invariant and deflection depictions of ECG signals. We suggested a new wavelet scattering transform-based method for automatically classifying three types of ECG heart diseases as follows: arrhythmia (ARR), congestive heart failure (CHF), and normal sinus rhythm (NSR). The bandwidth of the scaling function is used to critically downsample the wavelet scattering transform in time. As a result, each of the scattering paths has 16-time windows. Beat classification performance is classified by utilizing the MIT-BIH arrhythmia dataset. The suggested method is able to conduct high accuracy arrhythmia classification, with a 99.7% and 99.92% accuracy rate of the neural network (NN) and support vector machine (SVM), respectively, and will aid physicians in ECG explanation.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

5

Shi, Jun, Yanan Zhao, Wei Xiang, Vishal Monga, Xiaoping Liu und Ran Tao. „Deep Scattering Network With Fractional Wavelet Transform“. IEEE Transactions on Signal Processing 69 (2021): 4740–57. http://dx.doi.org/10.1109/tsp.2021.3098936.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

6

Lone, Ab Waheed, und Nizamettin Aydin. „Wavelet Scattering Transform based Doppler signal classification“. Computers in Biology and Medicine 167 (Dezember 2023): 107611. http://dx.doi.org/10.1016/j.compbiomed.2023.107611.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

7

D. S. Aabdalla, Islam, und D. Vasumathi. „Wavelet Scattering Transform for ECG Cardiovascular Disease Classification“. International Journal of Artificial Intelligence & Applications 15, Nr. 1 (29.01.2024): 101–13. http://dx.doi.org/10.5121/ijaia.2024.15107.

Der volle Inhalt der Quelle

Annotation:

Classifying the ECG dataset is the main technique for diagnosing heart disease. However, the focus of this field is increasingly on prediction, with a growing dependence on machine learning techniques. This study aimed to enhance the accuracy of cardiovascular disease classification using data from the PhysioNet database by employing machine learning (ML). The study proposed several multi-class classification models that accurately identify patterns within three classes: heart failure rhythm (HFR), normal heart rhythm (NHR), and arrhythmia (ARR). This was accomplished by utilizing a database containing 162 ECG signals. The study employed a variety of techniques, including frequency-time domain analysis, spectral features, and wavelet scattering, to extract features and capture unique characteristics from the ECG dataset. The SVM model produced a training accuracy of 97.1% and a testing accuracy of 92%. This work provides a reliable, effective, and human error-free diagnostic tool for identifying heart disease. Furthermore, it could prove to be a valuable resource for future medical research projects aimed at improving the diagnosis and treatment of cardiovascular diseases.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

8

Khemani, Varun, Michael H. Azarian und Michael G. Pecht. „Learnable Wavelet Scattering Networks: Applications to Fault Diagnosis of Analog Circuits and Rotating Machinery“. Electronics 11, Nr. 3 (02.02.2022): 451. http://dx.doi.org/10.3390/electronics11030451.

Der volle Inhalt der Quelle

Annotation:

Analog circuits are a critical part of industrial electronics and systems. Estimates in the literature show that, even though analog circuits comprise less than 20% of all circuits, they are responsible for more than 80% of faults. Hence, analog circuit fault diagnosis and isolation can be a valuable means of ensuring the reliability of circuits. This paper introduces a novel technique of learning time–frequency representations, using learnable wavelet scattering networks, for the fault diagnosis of circuits and rotating machinery. Wavelet scattering networks, which are fixed time–frequency representations based on existing wavelets, are modified to be learnable so that they can learn features that are optimal for fault diagnosis. The learnable wavelet scattering networks are developed using the genetic algorithm-based optimization of second-generation wavelet transform operators. The simulation and experimental results for the diagnosis of analog circuit faults demonstrates that the developed diagnosis scheme achieves greater fault diagnosis accuracy than other methods in the literature, even while considering a larger number of fault classes. The performance of the diagnosis scheme on benchmark datasets of bearing faults and gear faults shows that the developed method generalizes well to fault diagnosis in multiple domains and has good transfer learning performance, too.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

9

Velicheti, Phani Datta, John F. Wu und Andreea Petric. „Quantifying Roman WFI Dark Images with the Wavelet Scattering Transform“. Publications of the Astronomical Society of the Pacific 135, Nr. 1050 (01.08.2023): 084502. http://dx.doi.org/10.1088/1538-3873/acf073.

Der volle Inhalt der Quelle

Annotation:

Abstract The Nancy Grace Roman Space Telescope will survey a large area of the sky at near-infrared wavelengths with its Wide Field Instrument (WFI). The performance of the 18 WFI H4RG-10 detectors will need to be well-characterized and regularly monitored in order for Roman to meet its science objectives. Weak lensing science goals are particularly sensitive to instrumental distortions and patterns that might masquerade as astronomical signals. We apply the wavelet scattering transform in order to analyze localized signals in Roman WFI images that have been taken as part of a dark image test suite. The scattering transform quantifies shapes and clustering information by reducing images into nonlinear combinations of wavelet modes on multiple size scales. We show that these interpretable scattering statistics can separate rare correlated patterns from typical noise signals, and we discuss the results in context of power spectrum analyses and other computer vision methods.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

10

Omer, Osama A., Mostafa Salah, Ammar M. Hassan, Mohamed Abdel-Nasser, Norihiro Sugita und Yoshifumi Saijo. „Blood Pressure Estimation from Photoplythmography Using Hybrid Scattering–LSTM Networks“. BioMedInformatics 4, Nr. 1 (09.01.2024): 139–57. http://dx.doi.org/10.3390/biomedinformatics4010010.

Der volle Inhalt der Quelle

Annotation:

One of the most significant indicators of heart and cardiovascular health is blood pressure (BP). Blood pressure (BP) has gained great attention in the last decade. Uncontrolled high blood pressure increases the risk of serious health problems, including heart attack and stroke. Recently, machine/deep learning has been leveraged for learning a BP from photoplethysmography (PPG) signals. Hence, continuous BP monitoring can be introduced, based on simple wearable contact sensors or even remotely sensed from a proper camera away from the clinical setup. However, the available training dataset imposes many limitations besides the other difficulties related to the PPG time series as high-dimensional data. This work presents beat-by-beat continuous PPG-based BP monitoring while accounting for the aforementioned limitations. For a better exploration of beats’ features, we propose to use wavelet scattering transform as a better descriptive domain to cope with the limitation of the training dataset and to help the deep learning network accurately learn the relationship between the morphological shapes of PPG beats and the BP. A long short-term memory (LSTM) network is utilized to demonstrate the superiority of the wavelet scattering transform over other domains. The learning scenarios are carried out on a beat basis where the input corresponding PPG beat is used for predicting BP in two scenarios; (1) Beat-by-beat arterial blood pressure (ABP) estimation, and (2) Beat-by-beat estimation of the systolic and diastolic blood pressure values. Different transformations are used to extract the features of the PPG beats in different domains including time, discrete cosine transform (DCT), discrete wavelet transform (DWT), and wavelet scattering transform (WST) domains. The simulation results show that using the WST domain outperforms the other domains in the sense of root mean square error (RMSE) and mean absolute error (MAE) for both of the suggested two scenarios.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

11

Yin, Tiantian, Zhun Wei und Xudong Chen. „Wavelet Transform Subspace-Based Optimization Method for Inverse Scattering“. IEEE Journal on Multiscale and Multiphysics Computational Techniques 3 (2018): 176–84. http://dx.doi.org/10.1109/jmmct.2018.2878483.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

12

Acuna-García, José Alfredo. „XRAY MEDICAL IMAGE CHARACTERIZATION WITH SPARSE RADIATION BASED ON WAVELETS“. International Journal of Advanced Research in Computer Science 11, Nr. 6 (20.12.2020): 10–14. http://dx.doi.org/10.26483/ijarcs.v11i6.6664.

Der volle Inhalt der Quelle

Annotation:

In medical radiology there are large amounts of digital images in hospitals and health centers. Equipment that enables the acquisition of medical radiographs uses X-radiation sensor plates for image acquisition in medical diagnosis. Medical radiology equipment uses anti-scatter grids, which are physical devices, to avoid unwanted effects on imaging. In the present work, we analyse from a qualitative point of view the radiation scattering effect that is caused in images without the presence of the anti-scattering grid. In this research, the acquisition of radiological images was made by means of X-ray equipment with an anti-scattering grid, capturing images without scattering and others that only present radiation scattering as a point of comparison. The methodology uses the Wavelet transformation to image characterization in segment process that define the regions that affect the different types of dispersion presented in X radiation. The tool used for the analysis of the images is the multi-resolution Wavelet transform, specifically the Discrete Wavelet Transform (DWT). The methodology was applied to different 2D radiological images in shades of gray. In the images used, it showed a robustness in the differentiation of X radiation incidence zones. This work is the beginning of a distortion analysis for the reconstruction of this type of images.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

13

Lee, Jin-A., und Keun-Chang Kwak. „Heart Sound Classification Using Wavelet Analysis Approaches and Ensemble of Deep Learning Models“. Applied Sciences 13, Nr. 21 (31.10.2023): 11942. http://dx.doi.org/10.3390/app132111942.

Der volle Inhalt der Quelle

Annotation:

Analyzing the condition and function of the heart is very important because cardiovascular diseases (CVDs) are responsible for high mortality rates worldwide and can lead to strokes and heart attacks; thus, early diagnosis and treatment are important. Phonocardiogram (PCG) signals can be used to analyze heart rate characteristics to detect heart health and detect heart-related diseases. In this paper, we propose a method for designing using wavelet analysis techniques and an ensemble of deep learning models from phonocardiogram (PCG) for heart sound classification. For this purpose, we use wavelet scattering transform (WST) and continuous wavelet transform (CWT) as the wavelet analysis approaches for 1D-convolutional neural network (CNN) and 2D-CNN modeling, respectively. These features are insensitive to translations of the input on an invariance scale and are continuous with respect to deformations. Furthermore, the ensemble model is combined with 1D-CNN and 2D-CNN. The proposed method consists of four stages: a preprocessing stage for dividing signals at regular intervals, a feature extraction stage through wavelet scattering transform (WST) and continuous wavelet transform (CWT), a design stage of individual 1D-CNN and 2D-CNN, and a classification stage of heart sound by the ensemble model. The datasets used for the experiment were the PhysioNet/CinC 2016 challenge dataset and the PASCAL classifying heart sounds challenge dataset. The performance evaluation is performed by precision, recall, F1-score, sensitivity, and specificity. The experimental results revealed that the proposed method showed good performance on two datasets in comparison to the previous methods. The ensemble method of the proposed deep learning model surpasses the performance of recent studies and is suitable for predicting and diagnosing heart-related diseases by classifying heart sounds through phonocardiogram (PCG) signals.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

14

Reine, Carl, Mirko van der Baan und Roger Clark. „The robustness of seismic attenuation measurements using fixed- and variable-window time-frequency transforms“. GEOPHYSICS 74, Nr. 2 (März 2009): WA123—WA135. http://dx.doi.org/10.1190/1.3043726.

Der volle Inhalt der Quelle

Annotation:

Frequency-based methods for measuring seismic attenuation are used commonly in exploration geophysics. To measure the spectrum of a nonstationary seismic signal, different methods are available, including transforms with time windows that are either fixed or systematically varying with the frequency being analyzed. We compare four time-frequency transforms and show that the choice of a fixed- or variable-window transform affects the robustness and accuracy of the resulting attenuation measurements. For fixed-window transforms, we use the short-time Fourier transform and Gabor transform. The S-transform and continuous wavelet transform are analyzed as the variable-length transforms. First we conduct a synthetic transmission experiment, and compare the frequency-dependent scattering attenuation to the theoretically predicted values. From this procedure, we find that variable-window transforms reduce the uncertainty and biasof the resulting attenuation estimate, specifically at the upper and lower ends of the signal bandwidth. Our second experiment measures attenuation from a zero-offset reflection synthetic using a linear regression of spectral ratios. Estimates for constant-[Formula: see text] attenuation obtained with the variable-window transforms depend less on the choice of regression bandwidth, resulting in a more precise attenuation estimate. These results are repeated in our analysis of surface seismic data, whereby we also find that the attenuation measurements made by variable-window transforms have a stronger match to their expected trend with offset. We conclude that time-frequency transforms with a systematically varying time window, such as the S-transform and continuous wavelet transform, allow for more robust estimates of seismic attenuation. Peaks and notches in the measured spectrum are reduced because the analyzed primary signal is better isolated from the coda, and because of high-frequency spectral smoothing implicit in the use of short-analysis windows.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

15

Tang, Yuan Yan, Yang Lu und Haoliang Yuan. „Hyperspectral Image Classification Based on Three-Dimensional Scattering Wavelet Transform“. IEEE Transactions on Geoscience and Remote Sensing 53, Nr. 5 (Mai 2015): 2467–80. http://dx.doi.org/10.1109/tgrs.2014.2360672.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

16

Nahak, Sudestna, Akanksha Pathak und Goutam Saha. „Fragment-level classification of ECG arrhythmia using wavelet scattering transform“. Expert Systems with Applications 224 (August 2023): 120019. http://dx.doi.org/10.1016/j.eswa.2023.120019.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

17

HAWKINS, STUART C., KE CHEN und PAUL J. HARRIS. „AN OPERATOR SPLITTING PRECONDITIONER FOR MATRICES ARISING FROM A WAVELET BOUNDARY ELEMENT METHOD FOR THE HELMHOLTZ EQUATION“. International Journal of Wavelets, Multiresolution and Information Processing 03, Nr. 04 (Dezember 2005): 601–20. http://dx.doi.org/10.1142/s0219691305001044.

Der volle Inhalt der Quelle

Annotation:

An operator splitting type preconditioner is presented for fast solution of linear systems obtained by Galerkin discretization of the Burton and Miller formulation for the Helmholtz equation. Our approach differs from usual boundary element treatments of the three-dimensional scattering problem because we use a basis of biorthogonal wavelets. Such wavelets result in a sparse linear system and that facilitates preconditioning and makes matrix vector products cheap to form. In this Part I of our work, we implement a biorthogonal wavelet transform on a closed surface in three dimensions. Numerical results demonstrate the gains in efficiency that are already achievable with this convenient but non-optimal implementation.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

18

Ashtari Jafari, Mohammad. „Comparative Application of Time-Frequency Methods on Strong Motion Signals“. Advances in Civil Engineering 2021 (31.07.2021): 1–14. http://dx.doi.org/10.1155/2021/9933078.

Der volle Inhalt der Quelle

Annotation:

Real-world physical signals are commonly nonstationary, and their frequency details change with time and do not remain constant. Fourier transform that uses infinite sine/cosine waves as basis functions represents frequency constituents of signals but does not show the variations of the signal frequency contents over time. Multiresolution demonstration of the time-frequency domain may be achieved by the techniques that can support adjustable resolution in time and frequency. Earthquake strong motion signals are nonstationary and indicate time-varying frequency content due to the scattering from the source to the site. In this paper, we applied short-time Fourier transform, S-transform, continuous wavelet transform, fast discrete wavelet transform, synchrosqueezing transform, synchroextracting transform, continuous wavelet synchrosqueezing, filter bank synchrosqueezing, empirical mode decomposition, and Fourier decomposition methods on the near-source strong motion signals from the 7 May 2020 Mosha-Iran earthquake to study and compare the frequency content of this event estimated by these methods. According to the results that are examined by Renyi entropy and relative error, synchroextracting performed better in terms of energy concentration, and the Fourier decomposition method revealed the lowest difference between the original and reconstructed records.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

19

Zhang, Lu, Zhenchao Ma, Kuiwen Xu und Yu Zhong. „Wavelet-Based Subspace Regularization for Solving Highly Nonlinear Inverse Scattering Problems with Contraction Integral Equation“. Electronics 9, Nr. 11 (23.10.2020): 1760. http://dx.doi.org/10.3390/electronics9111760.

Der volle Inhalt der Quelle

Annotation:

A wavelet transform twofold subspace-based optimization method (WT-TSOM) is proposed to solve the highly nonlinear inverse scattering problems with contraction integral equation for inversion (CIE-I). While the CIE-I is able to suppress the multiple scattering effects within inversion (without compromising the accuracy of the physics), proper regularization is needed. In this paper, we investigate a new type subspace regularization technique based on wavelet expansions for the induced currents. We found that the bior3.5 wavelet is a good choice to stabilize the inversions with the CIE-I model and in the meanwhile it also can rectify the contrast profile. Numerical tests against both synthetic and experimental data show that WT-TSOM is a promising regularization technique for inversion with CIE-I.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

20

Bruni, Vittoria, Maria Lucia Cardinali und Domenico Vitulano. „An MDL-Based Wavelet Scattering Features Selection for Signal Classification“. Axioms 11, Nr. 8 (30.07.2022): 376. http://dx.doi.org/10.3390/axioms11080376.

Der volle Inhalt der Quelle

Annotation:

Wavelet scattering is a redundant time-frequency transform that was shown to be a powerful tool in signal classification. It shares the convolutional architecture with convolutional neural networks, but it offers some advantages, including faster training and small training sets. However, it introduces some redundancy along the frequency axis, especially for filters that have a high degree of overlap. This naturally leads to a need for dimensionality reduction to further increase its efficiency as a machine learning tool. In this paper, the Minimum Description Length is used to define an automatic procedure for optimizing the selection of the scattering features, even in the frequency domain. The proposed study is limited to the class of uniform sampling models. Experimental results show that the proposed method is able to automatically select the optimal sampling step that guarantees the highest classification accuracy for fixed transform parameters, when applied to audio/sound signals.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

21

SIBUL, L. H., L. G. WEISS und T. L. DIXON. „CHARACTERIZATION OF STOCHASTIC PROPAGATION AND SCATTERING VIA GABOR AND WAVELET TRANSFORMS“. Journal of Computational Acoustics 02, Nr. 03 (September 1994): 345–69. http://dx.doi.org/10.1142/s0218396x94000221.

Der volle Inhalt der Quelle

Annotation:

An application to remote acoustic sensing that remains unexploited is measuring acoustic scattering and spreading effects with wideband, coherent signal processing techniques. Such techniques allow distributed objects, such as a layer of scatterers due to bubbles or biological particles, and first order time variations in an ocean channel to be estimated. This paper presents narrowband and wideband methods for characterizing stochastic propagation and acoustic scattering in a time-varying ocean in terms of spreading functions. It is shown that the Gabor transform is the natural transform for estimating the narrowband spreading function, and the wavelet transform is the natural transform for estimating the wideband spreading function. Both techniques of characterization use a correlator processing structure in a monostatic transmitter/receiver configuration to estimate the spreading function. The narrowband and wideband spreading functions characterize the distribution of scatterers in range and velocity (time and frequency) in a propagation channel. It is shown that the wideband formulation follows directly from a physical derivation. Moreover, wideband processing removes many of the narrowband restrictions and allows first order time variations, caused by inhomogeneities and relative motion in the ocean channel, to be processed. In addition, wideband techniques allow for increased time intervals and, therefore, increased energy transmission when the transmitter is peak-power-limited. Thus, weak scatterers that may have been unidentified with narrowband techniques may be identified with the wideband methods. Numerical examples for wideband characterization of a distributed scatterer are presented.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

22

Singh, Prabhishek, und Raj Shree. „Statistical Quality Analysis of Wavelet Based SAR Images in Despeckling Process“. Asian Journal of Electrical Sciences 6, Nr. 2 (05.11.2017): 1–18. http://dx.doi.org/10.51983/ajes-2017.6.2.2001.

Der volle Inhalt der Quelle

Annotation:

Synthetic aperture radar (SAR) images are mainly denoised by multiplicative speckle noise, which is due to the consistent behavior of scattering phenomenon known as speckle noise. This paper presents the basic concept, role and importance of Discrete Wavelet Transform (DWT) in the field of despeckling SAR images and also offers a study of SAR image quality on applying DWT on the speckled image and log transformed speckled image. Log transform operation plays a decisive and comfortable role in despeckling SAR images as this operation changes the multiplicative behavior of the speckle noise to an additive which enables to use the additive noise restoration model efficiently. Wavelet transform has now become important in the field of image restoration although being in practice for a decade. Wavelet transform allows both time and frequency analysis simultaneously around a particular time. This transform is most appropriate for the non-stationary signals, so it deals with satellite imagery in a more efficient manner. The major part of this paper is revolving around DWT image decomposition with its role and practical implementation on the speckled image and log transformed speckled image. All the experimental results are performed on the SAR images.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

23

Kigoshi, Katsunori, Ning Guan, Ken-ichiro Yashiro und Sumio Ohkawa. „Wavelet Matrix Transform Approach for Electromagnetic Scattering by a Dielectric Cylinder“. IEEJ Transactions on Fundamentals and Materials 120, Nr. 10 (2000): 878–84. http://dx.doi.org/10.1541/ieejfms1990.120.10_878.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

24

Buriro, Abdul Baseer, Bilal Ahmed, Gulsher Baloch, Junaid Ahmed, Reza Shoorangiz, Stephen J. Weddell und Richard D. Jones. „Classification of alcoholic EEG signals using wavelet scattering transform-based features“. Computers in Biology and Medicine 139 (Dezember 2021): 104969. http://dx.doi.org/10.1016/j.compbiomed.2021.104969.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

25

Drumheller, D. M., D. H. Hughes, B. T. O’Connor und C. F. Gaumond. „Identification and synthesis of acoustic scattering components via the wavelet transform“. Journal of the Acoustical Society of America 97, Nr. 6 (Juni 1995): 3649–56. http://dx.doi.org/10.1121/1.412412.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

26

Kigoshi, Katsunori, Ning Guan, Ichiro Yashiro und Sumio Ohkawa. „Wavelet matrix transform approach for electromagnetic scattering by a dielectric cylinder“. Electrical Engineering in Japan 137, Nr. 3 (30.11.2001): 1–9. http://dx.doi.org/10.1002/eej.1089.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

27

Parab, Rajan Vishnu, Meenal Suryakant Vatsaraj und D. S. Bade. „AGE ESTIMATION USING NEURAL NETWORKS BASED ON FACE IMAGES WITH STUDY OF DIFFERENT FEATURE EXTRACTION METHODS“. International Journal of Students' Research in Technology & Management 5, Nr. 2 (20.07.2017): 56–61. http://dx.doi.org/10.18510/ijsrtm.2017.526.

Der volle Inhalt der Quelle

Annotation:

Facial age estimation recently becomes active research topic in pattern recognition. As there are vast potential application in age specific human computer interaction security control and surveillance monitoring. Insufficient and incomplete training data, uncontrollable environment, facial expression are the most prominent challenges in facial age estimation. Degree of accuracy for age estimation is obtained by forming appropriate feature vector of a facial image. Feature vectors are constructed from facial features. Therefore comparative study of feature extraction from facial image by bio inspired feature (BIF), histogram of gradient (HOG), Gabor filter, wavelet transform and scattering transform is done. The propose approach exploits scattering transform gives more information about features of the facial images. Well organized system consist scattering transform that disperse gabber coefficients pulling with smooth gaussian process in number of layers which isused to calculate for facial feature representation. These extracted features are classified using support vector machine and artificial neural network.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

28

Brandner, Paul A., James A. Venning und Bryce W. Pearce. „Wavelet analysis techniques in cavitating flows“. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences 376, Nr. 2126 (09.07.2018): 20170242. http://dx.doi.org/10.1098/rsta.2017.0242.

Der volle Inhalt der Quelle

Annotation:

Cavitating and bubbly flows involve a host of physical phenomena and processes ranging from nucleation, surface and interfacial effects, mass transfer via diffusion and phase change to macroscopic flow physics involving bubble dynamics, turbulent flow interactions and two-phase compressible effects. The complex physics that result from these phenomena and their interactions make for flows that are difficult to investigate and analyse. From an experimental perspective, evolving sensing technology and data processing provide opportunities for gaining new insight and understanding of these complex flows, and the continuous wavelet transform (CWT) is a powerful tool to aid in their elucidation. Five case studies are presented involving many of these phenomena in which the CWT was key to data analysis and interpretation. A diverse set of experiments are presented involving a range of physical and temporal scales and experimental techniques. Bubble turbulent break-up is investigated using hydroacoustics, bubble dynamics and high-speed imaging; microbubbles are sized using light scattering and ultrasonic sensing, and large-scale coherent shedding driven by various mechanisms are analysed using simultaneous high-speed imaging and physical measurement techniques. The experimental set-up, aspect of cavitation being addressed, how the wavelets were applied, their advantages over other techniques and key findings are presented for each case study. This paper is part of the theme issue ‘Redundancy rules: the continuous wavelet transform comes of age’.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

29

Lu, Guizhen, Zhonghang Duan, Hongcheng Yin, Zhihe Xiao und Jing Zhang. „Determining the Effective Electromagnetic Parameters of Photonic Crystal by Phase Unwrapping and Denoising Method“. International Journal of Antennas and Propagation 2019 (03.07.2019): 1–10. http://dx.doi.org/10.1155/2019/8513150.

Der volle Inhalt der Quelle

Annotation:

The electromagnetic parameters of the dispersion material and metamaterial are vital in the engineering. The phase unwrapping method is proposed to deal with the phase ambiguity of the transmission and reflection method in electromagnetic (EM) parameters extraction. The computed results demonstrate that the proposed method can give the correct effective parameters. In dealing with scattering parameters with noise, the wavelet transform method is utilized to remove the noise added to the scattering parameters. The simulated results show that the correct material parameters can be obtained by wavelet denoising method. Finally, the proposed method is used to extract the parameters of the photonic crystal. The effective parameter gives a different aspect in explanation to the function for the photonic crystal.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

30

Li, Xuelei, Yanjie Wei und Wei Ouyang. „Angle-domain generalized Radon transform for elastic multiparameter inverse scattering inversion“. GEOPHYSICS 87, Nr. 1 (23.12.2021): R147—R164. http://dx.doi.org/10.1190/geo2021-0098.1.

Der volle Inhalt der Quelle

Annotation:

Linearized algorithms based on the Born approximation are well-known and popular techniques for quantitative seismic imaging and inversion. However, linearization methods usually suffer from some significant problems, such as the computational cost for the required number of iterations, requirement for background models, and uncertain and unstable multiparameter extraction, which make the methods difficult to implement in practical applications. To avoid these problems, we have developed an angle-domain generalized Radon transform (AD-GRT) inversion in 2D elastic isotropic media. This AD-GRT is an approximate transform between the seismic data and an angle-domain model, which acts as a scattering function, and the seismic data can be reconstructed accurately, even when the background models are incorrect. The density and Lamé moduli perturbation parameters can be extracted stably from the inverted angle-domain scattering function. Deconvolution of the source wavelet is taken into account to remove the effect of the wavelet and improve the resolution and accuracy of the inversion results. The derived AD-GRT inversion is noniterative and is as efficient as the traditional elastic GRT method. The additional dimension of the angle domain has little effect on the computational cost of the AD-GRT, as opposed to other extended-domain inversion/migration methods. Our method also can be used to solve nonlinear Born inversion problems using iteration, which can significantly improve their convergence rate. Three numerical examples illustrate that the angle-domain scattering function inversion, data reconstruction, and multiparameter extraction using the presented AD-GRT inversion are effective.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

31

Rasti, Pejman, Ali Ahmad, Salma Samiei, Etienne Belin und David Rousseau. „Supervised Image Classification by Scattering Transform with Application to Weed Detection in Culture Crops of High Density“. Remote Sensing 11, Nr. 3 (26.01.2019): 249. http://dx.doi.org/10.3390/rs11030249.

Der volle Inhalt der Quelle

Annotation:

In this article, we assess the interest of the recently introduced multiscale scattering transform for texture classification applied for the first time in plant science. Scattering transform is shown to outperform monoscale approaches (gray-level co-occurrence matrix, local binary patterns) but also multiscale approaches (wavelet decomposition) which do not include combinatory steps. The regime in which scatter transform also outperforms a standard CNN architecture in terms of data-set size is evaluated ( 10 4 instances). An approach on how to optimally design the scatter transform based on energy contrast is provided. This is illustrated on the hard and open problem of weed detection in culture crops of high density from the top view in intensity images. An annotated synthetic data-set available under the form of a data challenge and a simulator are proposed for reproducible science (https://uabox.univ-angers.fr/index.php/s/iuj0knyzOUgsUV9). Scatter transform only trained on synthetic data shows an accuracy of 85 % when tested on real data.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

32

Alaraji, Yousif, und Sina Alp. „investigation into vibration analysis for detecting faults in vehicle steering outer tie-rod“. Acta IMEKO 13, Nr. 1 (18.03.2024): 1–9. http://dx.doi.org/10.21014/actaimeko.v13i1.1742.

Der volle Inhalt der Quelle

Annotation:

This study presents a novel fault detection method in car gear steering systems, employing MSC Adams and MATLAB simulations to analyze angular acceleration from the outer tie rod. The approach closely mimics real accelerometer data to differentiate between normal and faulty conditions, including wear and obstacle navigation. Emphasis is on noise robustness, utilizing advanced noise injection and denoising techniques. The efficacy of wavelet scattering, discrete wavelet transform (DWT) methods, and classifiers like Support Vector Machines (SVM) and Neural Networks (NN) is extensively evaluated. Among fifteen fault detection methods, the combination of wavelet scattering with Long Short-Term Memory (LSTM) Neural Networks, optimized with Adam tuning, is notably stable across four scenarios. The research highlights the importance of precise feature selection, employing techniques like Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), and Recursive Feature Elimination (RFE). This research significantly advances the reliability of autonomous driving systems and provides essential insights into fault detection in gear steering systems.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

33

Fan, Xin, Jianyuan Cheng, Yunhong Wang, Sheng Li, Bin Yan und Qingqing Zhang. „Automatic Events Recognition in Low SNR Microseismic Signals of Coal Mine Based on Wavelet Scattering Transform and SVM“. Energies 15, Nr. 7 (23.03.2022): 2326. http://dx.doi.org/10.3390/en15072326.

Der volle Inhalt der Quelle

Annotation:

The technology of microseismic monitoring, the first step of which is event recognition, provides an effective method for giving early warning of dynamic disasters in coal mines, especially mining water hazards, while signals with a low signal-to-noise ratio (SNR) usually cannot be recognized effectively by systematic methods. This paper proposes a wavelet scattering decomposition (WSD) transform and support vector machine (SVM) algorithm for discriminating events of microseismic signals with a low SNR. Firstly, a method of signal feature extraction based on WSD transform is presented by studying the matrix constructed by the scattering decomposition coefficients. Secondly, the microseismic events intelligent recognition model built by operating a WSD coefficients calculation for the acquired raw vibration signals, shaping a feature vector matrix of them, is outlined. Finally, a comparative analysis of the microseismic events and noise signals in the experiment verifies that the discriminative features of the two can accurately be expressed by using wavelet scattering coefficients. The artificial intelligence recognition model developed based on both SVM and WSD not only provides a fast method with a high classification accuracy rate, but it also fits the online feature extraction of microseismic monitoring signals. We establish that the proposed method improves the efficiency and the accuracy of microseismic signals processing for monitoring rock instability and seismicity.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

34

Badura, Aleksandra, Aleksandra Masłowska, Andrzej Myśliwiec und Ewa Piętka. „Multimodal Signal Analysis for Pain Recognition in Physiotherapy Using Wavelet Scattering Transform“. Sensors 21, Nr. 4 (12.02.2021): 1311. http://dx.doi.org/10.3390/s21041311.

Der volle Inhalt der Quelle

Annotation:

Fascial therapy is an effective, yet painful, procedure. Information about pain level is essential for the physiotherapist to adjust the therapy course and avoid potential tissue damage. We have developed a method for automatic pain-related reaction assessment in physiotherapy due to the subjectivity of a self-report. Based on a multimodal data set, we determine the feature vector, including wavelet scattering transforms coefficients. The AdaBoost classification model distinguishes three levels of reaction (no-pain, moderate pain, and severe pain). Because patients vary in pain reactions and pain resistance, our survey assumes a subject-dependent protocol. The results reflect an individual perception of pain in patients. They also show that multiclass evaluation outperforms the binary recognition.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

35

Kikuchi, Tsuneo, und Sojun Sato. „Experimental Studies on Ultrasonic Measurements of Scattering Media by Using Wavelet Transform“. Japanese Journal of Applied Physics 31, S1 (01.01.1992): 115. http://dx.doi.org/10.7567/jjaps.31s1.115.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

36

Mei, Na, Hongxia Wang, Yatao Zhang, Feifei Liu, Xinge Jiang und Shoushui Wei. „Classification of heart sounds based on quality assessment and wavelet scattering transform“. Computers in Biology and Medicine 137 (Oktober 2021): 104814. http://dx.doi.org/10.1016/j.compbiomed.2021.104814.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

37

Omer, Osama A., Mostafa Salah, Ammar M. Hassan und Ahmed S. Mubarak. „Beat-by-Beat ECG Monitoring from Photoplythmography Based on Scattering Wavelet Transform“. Traitement du Signal 39, Nr. 5 (30.11.2022): 1483–88. http://dx.doi.org/10.18280/ts.390504.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

38

Yang, Mei, Xiukun Li, Yang Yang und Xiangxia Meng. „Characteristic analysis of underwater acoustic scattering echoes in the wavelet transform domain“. Journal of Marine Science and Application 16, Nr. 1 (26.01.2017): 93–101. http://dx.doi.org/10.1007/s11804-017-1398-6.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

39

omer, osama, Sabreen Hussein und El-Attar Mohamed. „Solar Cell Anomaly Detection Based on Wavelet Scattering Transform and Artificial Intelligence“. Aswan University Journal of Sciences and Technology 3, Nr. 1 (01.06.2023): 1–10. http://dx.doi.org/10.21608/aujst.2023.312683.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

40

Barglazan, Adrian-Alin, und Remus Brad. „Enhanced Wavelet Scattering Network for Image Inpainting Detection“. Computation 12, Nr. 11 (13.11.2024): 228. http://dx.doi.org/10.3390/computation12110228.

Der volle Inhalt der Quelle

Annotation:

The rapid advancement of image inpainting tools, especially those aimed at removing artifacts, has made digital image manipulation alarmingly accessible. This paper proposes several innovative ideas for detecting inpainting forgeries based on a low-level noise analysis by combining Dual-Tree Complex Wavelet Transform (DT-CWT) for feature extraction with convolutional neural networks (CNN) for forged area detection and localization, and lastly by employing an innovative combination of texture segmentation with noise variance estimations. The DT-CWT offers significant advantages due to its shift-invariance, enhancing its robustness against subtle manipulations during the inpainting process. Furthermore, its directional selectivity allows for the detection of subtle artifacts introduced by inpainting within specific frequency bands and orientations. Various neural network architectures were evaluated and proposed. Lastly, we propose a fusion detection module that combines texture analysis with noise variance estimation to give the forged area. Also, to address the limitations of existing inpainting datasets, particularly their lack of clear separation between inpainted regions and removed objects—which can inadvertently favor detection—we introduced a new dataset named the Real Inpainting Detection Dataset. Our approach was benchmarked against state-of-the-art methods and demonstrated superior performance over all cited alternatives.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

41

Liu, Yi, Qi Qi, Xinyuan Cao, Mingsheng Chen, Guoqing Deng, Zhixiang Huang und Xianliang Wu. „Application of Two-Dimensional Compressive Sensing to Wavelet Method of Moments for Fast Analysis of Wide-Angle Electromagnetic Scattering Problems“. International Journal of Antennas and Propagation 2021 (20.08.2021): 1–9. http://dx.doi.org/10.1155/2021/9912502.

Der volle Inhalt der Quelle

Annotation:

To efficiently solve the electromagnetic scattering problems over a wide incident angle, a novel scheme by introducing the two-dimensional compressive sensing theory into the wavelet method of moments is proposed. In this scheme, a linear system of equations with multiple right-hand sides in wavelet domain is formed firstly, and one side of the bilateral sparse transform to the induced current matrix is simultaneously accomplished and then the bilateral measurement of the induced current matrix is operated by the linear superposition of the right-hand side vectors a few times and the extraction of rows from the impedance matrix. Finally, after completing the other side of the bilateral sparse transform, the wide-angle problems can be solved rapidly by two times of recovery algorithm with prior knowledge. The basic principle is elaborated in detail, and the effectiveness is demonstrated by numerical experiments.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

42

Mansour, Naema M., Ibrahim A. Awaad und Abdelazeem A. Abdelsalam. „Performance analysis of wavelet scattering transform-based feature matrix for power system disturbances classification“. International Journal of Electrical and Computer Engineering (IJECE) 14, Nr. 6 (01.12.2024): 6094. http://dx.doi.org/10.11591/ijece.v14i6.pp6094-6110.

Der volle Inhalt der Quelle

Annotation:

Recently, the wavelet scattering transform (WST) was introduced as a powerful feature extraction tool for classification processes. It provides good performance in applications involving audio signals, images, medical data, and quadcopters for structural health diagnosis. It is also employed in several electrical engineering applications, such as the classification of induction motor bearing failures, electrical loads, and industrial robot faults. Despite its development, the performance of the wavelet scattering (WS) network constructed in the MATLAB environment to compute WST coefficients has not been highlighted in the literature so far. In this paper, the properties of the WST feature matrix are examined, and the parameters that have a significant impact on coefficient magnitudes and matrix dimensions are defined. With minimal configuration, a WS network could extract low-variance features from real-valued time series for use in machine learning and deep learning applications. The feature matrix, which contains zero, first, and second-level WST coefficients derived from various power system signal configurations, is constructed to be trained using long short-term memory (LSTM) networks. The simulation results demonstrate the efficacy of the proposed classifier with an accuracy approach of 100%. The MATLAB toolbox has been used to create different signals for the WS and LSTM networks. WST has proven to be a powerful tool for power system disturbance classification.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

43

Toma, Rafia Nishat, Yangde Gao, Farzin Piltan, Kichang Im, Dongkoo Shon, Tae Hyun Yoon, Dae-Seung Yoo und Jong-Myon Kim. „Classification Framework of the Bearing Faults of an Induction Motor Using Wavelet Scattering Transform-Based Features“. Sensors 22, Nr. 22 (19.11.2022): 8958. http://dx.doi.org/10.3390/s22228958.

Der volle Inhalt der Quelle

Annotation:

In the machine learning and data science pipelines, feature extraction is considered the most crucial component according to researchers, where generating a discriminative feature matrix is the utmost challenging task to achieve high classification accuracy. Generally, the classical feature extraction techniques are sensitive to the noisy component of the signal and need more time for training. To deal with these issues, a comparatively new feature extraction technique, referred to as a wavelet scattering transform (WST) is utilized, and incorporated with ML classifiers to design a framework for bearing fault classification in this paper. The WST is a knowledge-based technique, and the structure is similar to the convolution neural network. This technique provides low-variance features of real-valued signals, which are usually necessary for classification tasks. These signals are resistant to signal deformation and preserve information at high frequencies. The current signal data from a publicly available dataset for three different bearing conditions are considered. By combining the scattering path coefficients, the decomposition coefficients from the 0th and 1st layers are considered as features. The experimental results demonstrate that WST-based features, when used with ensemble ML algorithms, could achieve more than 99% classification accuracy. The performance of ANN models with these features is similar. This work exhibits that utilizing WST coefficients for the motor current signal as features can improve the bearing fault classification accuracy when compared to other feature extraction approaches such as empirical wavelet transform (EWT), information fusion (IF), and wavelet packet decomposition (WPD). Thus, our proposed approach can be considered as an effective classification method for the fault diagnosis of rotating machinery.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

44

Christensen, Andrew, Ananya Sen Gupta und Ivars Kirsteins. „Underwater Small Target Classification Using Sparse Multi-View Discriminant Analysis and the Invariant Scattering Transform“. Journal of Marine Science and Engineering 12, Nr. 10 (21.10.2024): 1886. http://dx.doi.org/10.3390/jmse12101886.

Der volle Inhalt der Quelle

Annotation:

Sonar automatic target recognition (ATR) systems suffer from complex acoustic scattering, background clutter, and waveguide effects that are ever-present in the ocean. Traditional signal processing techniques often struggle to distinguish targets when noise and complicated target geometries are introduced. Recent advancements in machine learning and wavelet theory offer promising directions for extracting informative features from sonar return data. This work introduces a feature extraction and dimensionality reduction technique using the invariant scattering transform and Sparse Multi-view Discriminant Analysis for identifying highly informative features in the PONDEX09/PONDEX10 datasets. The extracted features are used to train a support vector machine classifier that achieves an average classification accuracy of 97.3% using six unique targets.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

45

Wang, Xiaoya, Songlin Sun, Haiying Zhang und Qiang Liu. „RF Signal Feature Extraction in Integrated Sensing and Communication“. IET Signal Processing 2023 (28.10.2023): 1–16. http://dx.doi.org/10.1049/2023/4251265.

Der volle Inhalt der Quelle

Annotation:

Because of the open property of information sharing in integrated sensing and communication, it is inevitable to face security problems such as user information being tampered, eavesdropped, and copied. Radio frequency (RF) individual identification technology is an important means to solve its security problems at present. Whether using machine learning methods or current deep learning-based target fingerprint identification, its performance is based on how well the radio frequency features (RFF) are extracted. Since the received signal is affected by various factors, we believe that we should first find the intrinsic features that can describe the properties of the target, which is the key to enhance the RF fingerprint recognition. In this paper, we try to analyze the intrinsic characteristics of the components that influenced the signal by the transmitting source and derive a mathematical formula to describe the RF characteristics. We propose a method using dynamic wavelet transform and wavelet spectrum (DWTWS) to enhance RFF features. The performance of the proposed method was evaluated by experimental data. Using a support vector machine classifier, the recognition accuracy is 99.6% for 10 individuals at a signal-to-noise ratio (SNR) of 10 dB. In comparison with the dual-tree complex wavelet transform (DT-CWT) feature extraction method and the wavelet scattering transform method, the DWTWS method has increased the interclass distance of different individuals and enhanced the recognition accuracy. The DWTWS method is superior at low SNR, with performance improvements of 53.1% and 10.7% at 0 dB.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

46

de Aguiar, Everton Luiz, André Eugenio Lazzaretti, Bruna Machado Mulinari und Daniel Rodrigues Pipa. „Scattering Transform for Classification in Non-Intrusive Load Monitoring“. Energies 14, Nr. 20 (18.10.2021): 6796. http://dx.doi.org/10.3390/en14206796.

Der volle Inhalt der Quelle

Annotation:

Nonintrusive Load Monitoring (NILM) uses computational methods to disaggregate and classify electrical appliances signals. The classification is usually based on the power signatures of the appliances obtained by a feature extractor. State-of-the-art results were obtained extracting NILM features with convolutional neural networks (CNN). However, it depends on the training process with large datasets or data augmentation strategies. In this paper, we propose a feature extraction strategy for NILM using the Scattering Transform (ST). The ST is a convolutional network analogous to CNN. Nevertheless, it does not need a training process in the feature extraction stage, and the filter coefficients are analytically determined (not empirically, like CNN). We perform tests with the proposed method on different publicly available datasets and compare the results with state-of-the-art deep learning-based and traditional approaches (including wavelet transform and V-I representations). The results show that ST classification accuracy is more robust in terms of waveform parameters, such as signal length, sampling frequency, and event location. Besides, ST overcame the state-of-the-art techniques for single and aggregated loads (accuracies above 99% for all evaluated datasets), in different training scenarios with single and aggregated loads, indicating its feasibility in practical NILM scenarios.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

47

Tan, Jun, Jiamin Yuan, Xiaoyong Fu und Yilin Bai. „Colonoscopy polyp classification via enhanced scattering wavelet Convolutional Neural Network“. PLOS ONE 19, Nr. 10 (11.10.2024): e0302800. http://dx.doi.org/10.1371/journal.pone.0302800.

Der volle Inhalt der Quelle

Annotation:

Among the most common cancers, colorectal cancer (CRC) has a high death rate. The best way to screen for colorectal cancer (CRC) is with a colonoscopy, which has been shown to lower the risk of the disease. As a result, Computer-aided polyp classification technique is applied to identify colorectal cancer. But visually categorizing polyps is difficult since different polyps have different lighting conditions. Different from previous works, this article presents Enhanced Scattering Wavelet Convolutional Neural Network (ESWCNN), a polyp classification technique that combines Convolutional Neural Network (CNN) and Scattering Wavelet Transform (SWT) to improve polyp classification performance. This method concatenates simultaneously learnable image filters and wavelet filters on each input channel. The scattering wavelet filters can extract common spectral features with various scales and orientations, while the learnable filters can capture image spatial features that wavelet filters may miss. A network architecture for ESWCNN is designed based on these principles and trained and tested using colonoscopy datasets (two public datasets and one private dataset). An n-fold cross-validation experiment was conducted for three classes (adenoma, hyperplastic, serrated) achieving a classification accuracy of 96.4%, and 94.8% accuracy in two-class polyp classification (positive and negative). In the three-class classification, correct classification rates of 96.2% for adenomas, 98.71% for hyperplastic polyps, and 97.9% for serrated polyps were achieved. The proposed method in the two-class experiment reached an average sensitivity of 96.7% with 93.1% specificity. Furthermore, we compare the performance of our model with the state-of-the-art general classification models and commonly used CNNs. Six end-to-end models based on CNNs were trained using 2 dataset of video sequences. The experimental results demonstrate that the proposed ESWCNN method can effectively classify polyps with higher accuracy and efficacy compared to the state-of-the-art CNN models. These findings can provide guidance for future research in polyp classification.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

48

Ho, Derek, Sanghoon Kim, Tyler K. Drake, Will J. Eldridge und Adam Wax. „Wavelet transform fast inverse light scattering analysis for size determination of spherical scatterers“. Biomedical Optics Express 5, Nr. 10 (29.08.2014): 3292. http://dx.doi.org/10.1364/boe.5.003292.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

49

Kleć, Mariusz, und Danijel Koržinek. „Unsupervised Feature Pre-training of the Scattering Wavelet Transform for Musical Genre Recognition“. Procedia Technology 18 (2014): 133–39. http://dx.doi.org/10.1016/j.protcy.2014.11.025.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

50

Valogiannis, Georgios, Francisco Villaescusa-Navarro und Marco Baldi. „Towards unveiling the large-scale nature of gravity with the wavelet scattering transform“. Journal of Cosmology and Astroparticle Physics 2024, Nr. 11 (01.11.2024): 061. http://dx.doi.org/10.1088/1475-7516/2024/11/061.

Der volle Inhalt der Quelle

Annotation:

Abstract We present the first application of the Wavelet Scattering Transform (WST) in order to constrain the nature of gravity using the three-dimensional (3D) large-scale structure of the universe. Utilizing the Quijote-MG N-body simulations, we can reliably model the 3D matter overdensity field for the f(R) Hu-Sawicki modified gravity (MG) model down to k max = 0.5 h/Mpc. Combining these simulations with the Quijote νCDM collection, we then conduct a Fisher forecast of the marginalized constraints obtained on gravity using the WST coefficients and the matter power spectrum at redshift z=0. Our results demonstrate that the WST substantially improves upon the 1σ error obtained on the parameter that captures deviations from standard General Relativity (GR), yielding a tenfold improvement compared to the corresponding matter power spectrum result. At the same time, the WST also enhances the precision on the ΛCDM parameters and the sum of neutrino masses, by factors of 1.2-3.4 compared to the matter power spectrum, respectively. Despite the overall reduction in the WST performance when we focus on larger scales, it still provides a relatively 4.5× tighter 1σ error for the MG parameter at k max =0.2 h/Mpc, highlighting its great sensitivity to the underlying gravity theory. This first proof-of-concept study reaffirms the constraining properties of the WST technique and paves the way for exciting future applications in order to perform precise large-scale tests of gravity with the new generation of cutting-edge cosmological data.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Zeitschriftenartikel zum Thema „Wavelet Scattering Transform“

Geben Sie eine Quelle nach APA, MLA, Chicago, Harvard und anderen Zitierweisen an