Fractal and multifractional-based predictive optimization model for stroke subtypes’ classification. (English) Zbl 1489.42022
Summary: Numerous natural phenomena display repeating self-similar patterns. Fractal is used when a pattern seems to repeat itself. Fractal and multifractal methods have extensive applications in neurosciences in which the prevalence of fractal properties like self-similarity in the brain, equipped with a complex structure, in medical data analysis at various levels of observation is admitted. The methods come to the fore since subtle details are not always detected by physicians, but these are critical particularly in neurological diseases like stroke which may be life-threatening. The aim of this paper is to identify the self-similar, significant and efficient attributes to achieve high classification accuracy rates for stroke subtypes. Accordingly, two approaches were implemented. The first approach is concerned with application of the fractal and multifractal methods on the stroke dataset in order to identify the regular, self-similar, efficient and significant attributes from the dataset, with these steps: a) application of Box-counting dimension generated BC\(_-\)stroke dataset b) application of Wavelet transform modulus maxima generated WTMM\(_-\)stroke dataset. The second approach involves the application of Feed Forward Back Propagation (FFBP) for stroke subtype classification with these steps: (i) FFBP algorithm was applied on the stroke dataset, BC\(_-\)stroke dataset and WTMM\(_-\)stroke dataset. (ii) Comparative analyses were performed based on accuracy, sensitivity and specificity for the three datasets. The main contribution is that the study has obtained the identification of self-similar, regular and significant attributes from the stroke subtypes datasets by following multifarious and integrated methodology. The study methodology is based on the singularity spectrum which provides a value concerning how fractal a set of points are in the datasets (BC\(_-\)stroke dataset and WTMM\(_-\)stroke dataset). The experimental results reveal the applicability, reliability and accuracy of our proposed integrated method. No earlier work exists in the literature with the relevant stroke datasets and the methods employed. Therefore, the study aims at pointing a new direction in the relevant fields concerning the complex dynamic systems and structures which display multifractional nature.
MSC:
| 42C40 | Nontrigonometric harmonic analysis involving wavelets and other special systems |
| 28A80 | Fractals |
| 94A12 | Signal theory (characterization, reconstruction, filtering, etc.) |
| 65T60 | Numerical methods for wavelets |
Keywords:
box-counting method; feedforward neural networks; fractal dimension; multifractals; stroke subtypes; wavelet transform modulus maximaReferences:
| [1] | Ieva, A. D.; Esteban, F. J.; Grizzi, F.; Klonowski, W.; Martin-Landrove, M., Fractals in the neurosciences, part II: clinical applications and future perspectives, Neuroscientist, 21, 1, 30-43 (2015) |
| [2] | Ai, T.; Zhang, R.; Zhou, H. W.; Pei, J. L., Box-counting methods to directly estimate the fractal dimension of a rock surface, Appl Surf Sci, 314, 610-621 (2014) |
| [3] | Ristanovic, D.; Stefanovic, B. D.; Puskas, N., Fractal analysis of dendrite morphology using modified box-counting method, Neurosci Res, 84, 64-67 (2014) |
| [4] | Karaca, Y.; Cattani, C.; Moonis, M.; Bayrak, S., Stroke subtype clustering by multifractal bayesian denoising with fuzzy c means and k-means algorithms, Complexity (2018) |
| [5] | Zhang, Y. D.; Zhang, Y.; Phillips, P.; Dong, Z.; Wang, S., Synthetic minority oversampling technique and fractal dimension for identifying multiple sclerosis, Fractals, 25, 04, 1740010 (2017) |
| [6] | Karaca, Y.; Cattani, C., Computational methods for data analysis, 978-3110496352 (2018), Walter de Gruyter GmbH, Berlin/Boston + co-pub |
| [7] | Karaca, Y.; Cattani, C., Clustering multiple sclerosis subgroups with multifractal methods and self-organizing map algorithm, Fractals, 25, 4, 1740001 (2017) |
| [8] | Yin, J.; Li, Y.; Cui, H., Box-counting dimensions and upper semicontinuities of bi-spatial attractors for stochastic degenerate parabolic equations on an unbounded domain, J Math Anal Appl, 450, 2, 1180-1207 (2017) · Zbl 1375.35053 |
| [9] | Sudha, A.; Gayathri, P.; Jaisankar, N., Effective analysis and predictive model of stroke disease using classification methods, Int J Comput Appl, 43, 14, 26-31 (2012) |
| [10] | Moonis M., Husaini B.. The impact of co-morbid sleep apnea and stroke on the cost of health care. 2018. P1. 091. |
| [11] | Almadani, O.; Alshammari, R., Prediction of stroke using data mining classification techniques, Int J Adv Comput Sci Appl, 9, 1, 457-460 (2018) |
| [12] | Silver B., Hamid T., Napoli M.D., Behrouz R., Khan M., Saposnik G., Moonis M.. Twelve versus twenty four hour bed rest after acute ischemic stroke reperfusion therapy. 2018. P5, 204. |
| [13] | Barbui, T.; De Stefano, V.; Carobbio, A.; Lazzaro, V. D.; Guglielmelli, P.; Loscocco, G. G., Short and long-term risk of major cardiovascular events after ischemic stroke or transient ischemic attack in myeloproliferative neoplasms, Am Soc Hematol, 130, 202 (2017) |
| [14] | Uchino, K.; Hernandez, A. V., Dabigatran association with higher risk of acute coronary events: meta-analysis of noninferiority randomized controlled trials, Arch Intern Med, 172, 5, 397-402 (2017) |
| [15] | Novaes, M. M.; Palhano-Fontes, F.; Peres, A.; Mazzetto-Betti, K.; Pelicioni, M.; Andrade, K. C., Neurofunctional changes after a single mirror therapy intervention in chronic ischemic stroke, Int J Neurosci, 1-9 (2018) |
| [16] | Henninger, N.; Lin, E.; Haussen, D. C.; Lehman, L. L.; Takhtani, D.; Selim, M.; Moonis, M., Leukoaraiosis and sex predict the hyperacute ischemic core volume, Stroke, 44, 1, 61-67 (2013) |
| [17] | PMID: 16046924 |
| [18] | PMCID: PMC2861780 |
| [19] | Milicic, S., Box-counting dimensions of generalised fractal nests, Chaos Solitons Fractals, 113, 125-134 (2018) · Zbl 1404.28007 |
| [20] | Rajkovic, N.; Krstonosic, B.; Milosevic, N., Box-counting method of 2d neuronal image: method modification and quantitative analysis demonstrated on images from the monkey and human brain, Comput Math Methods Med (2017) |
| [21] | Lopes, R.; Betrouni, N., Fractal and multifractal analysis: a review, Med Image Anal, 13, 4, 634-649 (2009) |
| [22] | Karthik, C. K.R., Characterization of stroke lesion using fractal analysis, Asian J Pharm Clin Res, 10, 13, 53-56 (2017) |
| [23] | Zhou, R.; Luo, Y.; Fenster, A.; Spence, J. D.; Ding, M., Fractal dimension based carotid plaque characterization from three-dimensional ultrasound images, Med Biol Eng Comput, 57, 1, 135-146 (2019) |
| [24] | Das, N.; Chatterjee, S.; Kumar, S.; Pradhan, A.; Panigrahi, P.; Vitkin, I. A., Tissue multifractality and born approximation in analysis of light scattering: a novel approach for precancers detection, Sci Rep, 4, 1, 1-7 (2014) |
| [25] | Mukhopadhyay, S.; Das, N.; Kurmi, I.; Ghosh, N.; Pradhan, A.; Panigrahi, P. K., Tissue multifractality and hidden markov model based integrated framework for optimum precancer detection, J Biomed Opt, 22, 10, 105005 (2017) |
| [26] | Foroutan-pour, K.; Dutilleul, P.; Smith, D. L., Advances in the implementation of the box-counting method of fractal dimension estimation, Appl Math Comput, 105, 2-3, 195-210 (1999) · Zbl 1025.28004 |
| [27] | PMID: 19690763 |
| [28] | ISSN 2229-5518 |
| [29] | Chirag, J., Multifractal analysis of heart rate variability using wavelet-transform modulus-maxima method,M. S. Thesis (2005), Biomedical Engineering Depart., New Jersey Institute of Technology: Biomedical Engineering Depart., New Jersey Institute of Technology Newark, New Jersey |
| [30] | Doi: 10.1049/cp.2013.0039 |
| [31] | Muzy, J. F.; Bacry, E.; Arneodo, Multifractal formalism for fractal signals - the structure function approach versus the wavelet-transform modulus-maxima method, Phys Rev E, 47, 2, 875-884 (1993) |
| [32] | Arneodo, A.; Bacry, E.; Muzy, J. F., The multifractal formalism revisited with wavelets, Int J Bifurcation Chaos, 4, 2, 245-302 (1994) · Zbl 0807.58032 |
| [33] | Ivanov, P. C.; Rosenblum, M. G.; Amaral, L. A.N.; Struzik, Z. R.; Havlin, S.; Goldberger, A. L.; Stanley, H. E., Multifractality in human heartbeat dynamics, Nature, 399, 461-465 (1999) |
| [34] | Venkatakrishnan, P.; Sangeetha, S.; Gnanasekaran, J. S.; Vishnukumar, M. G.; Padmanaban, A. S., Analysis of vibration in gearbox sensor data using lipschitz exponent (LE) function: a wavelet approach, IFAC Proc Vol, 47, 1, 1067-1071 (2014) |
| [35] | Pavlov, A. N.; Abdurashitov, A. S.; Sindeeva, O. A.; Sindeev, S. S.; Pavlova, O. N.; Shihalov, G. M., Characterizing cerebrovascular dynamics with the wavelet-based multifractal formalism, Physica A, 442, 149-155 (2016) · Zbl 1400.92158 |
| [36] | Jian-xun, L. I.; Xi-zheng, K. E., An accumulative method of pulsar standard profile based on wavelet-modulus-maxima correlation information, Chin Astron Astrophy, 33, 2, 158-167 (2009) |
| [37] | Doi: 10.1007/978-981-10-8863-6_5 |
| [38] | Sahoo, S.; Kanungo, B.; Behera, S.; Sabut, S., Multiresolution wavelet transform based feature extraction and ECG classification to detect cardiac abnormalities, Measurement, 108, 55-66 (2017) |
| [39] | Shanthi, D.; Sahoo, G.; Saravanan, N., Designing an artificial neural network model for the prediction of thrombo-embolic stroke, Int J BiometrBioinform (IJBB), 3, 1, 10-18 (2009) |
| [40] | Colak, C.; Karaman, E.; Turtay, M. G., Application of knowledge discovery process on the prediction of stroke, Comput Methods Programs Biomed, 119, 3, 181-185 (2015) |
| [41] | Karaca, Y.; Moonis, M.; Zhang, Y. D.; Gezgez, C., Mobile cloud computing based stroke healthcare system, Int J Inf Manage, 45, 250-261 (2019) |
| [42] | Doi: 10.1109/UKSim.2015.33 |
| [43] | Bong, S. Z.; Wan, K.; Murugappan, M.; Ibrahim, N. M.; Rajamanickam, Y.; Mohamad, K., Implementation of wavelet packet transform and non linear analysis for emotion classification in stroke patient using brain datas, Biomed Data Process Control, 36, 102-112 (2017) |
| [44] | Pavlov, A. N.; Abdurashitov, A. S.; Sindeeva, O. A.; Sindeev, S. S.; Pavlova, O. N.; Shihalov, G. M., Characterizing cerebrovascular dynamics with the wavelet-based multifractal formalism, Physica A, 442, 149-155 (2016) · Zbl 1400.92158 |
| [45] | The mathworks, MATLAB (r2018b). 2018. The mathWorks, inc., natick, MA |
| [46] | Vehel J.L.. 2018. FracLab, [Online]. Available: project.inria.fr/fraclab/. |
| [47] | Foroutan-pour, K.; Dutilleul, P.; Smith, D. L., Advances in the implementation of the box-counting method of fractal dimension estimation, Appl Math Comput, 105, 2-3, 195-210 (1999) · Zbl 1025.28004 |
| [48] | Stephen, W., Diagnosing ASD with fractal analysis, Adv Autism, 3, 1, 47-56 (2017) |
| [49] | Mallat, S., A wavelet tour of data processing (1999), Academic press · Zbl 0998.94510 |
| [50] | Doi.org/10.1007/978-3-030-29022-1_4 |
| [51] | Peng, Z. K.; Chu, F. L.; Peter, W. T., Singularity analysis of the vibration signals by means of wavelet modulus maximal method, Mech Syst Signal Process, 21, 2, 780-794 (2007) |
| [52] | So, G. B.; So, H. R.; Jin, G. G., Enhancement of the box-counting algorithm for fractal dimension estimation, Pattern Recognit Lett, 98, 53-58 (2017) |
| [53] | Xu, J.; Jian, Z.; Lian, X., An application of box counting method for measuring phase fraction, Measurement, 100, 297-300 (2017) |
| [54] | Mandelbrot, B. B., Self-affine fractals and fractal dimension, Phys Scr, 32, 4, 257 (2006) · Zbl 1063.28500 |
| [55] | Sanderson, B. G.; Booth, D. A., The fractal dimension of drifter trajectories and estimates of horizontal eddy-diffusivity, Tellus A, 43, 5, 334-349 (1991) |
| [56] | Liebovitch, L. S.; Toth, T., A fast algorithm to determine fractal dimensions by box counting, Phys Lett A, 141, 8-9, 386-390 (1989) |
| [57] | Doi:10.1007/978-3-7643-7778-6_17 · Zbl 1114.65164 |
| [58] | Mallat, S.; Hwang, W. L., Singularity detection and processing with wavelets, IEEE Trans Inf Theory, 38, 2, 617-643 (1992) · Zbl 0745.93073 |
| [59] | Bujanovic, T.; Abdel-Qader, I., On wavelet transform general modulus maxima metric for singularity classification in mammograms, Open J Med Imaging, 3, 1, 17 (2013) |
| [60] | Pavlova, O. N.; Abdurashitov, A. S.; Ulanova, M. V.; Shushunova, N. A.; Pavlov, A. N., Effects of missing data on characterization of complex dynamics from time series, Commun Nonlinear Sci Numer Simul, 66, 31-40 (2019) · Zbl 1508.62266 |
| [61] | Jaffard, S., Pointwise smoothness, two-microlocalization and wavelet coefficients, Publicacions Matematiques, 35, 1, 155-168 (1991) · Zbl 0760.42016 |
| [62] | Jaffard, S., Exponant de hölder et coefficients d’ ondelettes, (hölder exponents and wavelet coefficients”), vol. 308, 79-81 (1989), C. R. Academie des Sciences · Zbl 0665.42012 |
| [63] | ISBN-13: 978-0198536475 |
| [64] | Yuan, Y. T.; Li, B. F.; Ma, H.; Lin, J., Ring-projection-wavelet-fractal signatures: a novel approach to feature extraction, IEEE TransCircuits Syst II, 45, 8, 1130-1134 (1998) |
| [65] | Jaffard, S.; Melot, C., Wavelet analysis of fractal boundaries. part 1: local exponents, Commun Math Phys, 258, 3, 513-539 (2005) · Zbl 1080.28005 |
| [66] | Qijun, X.; Wei, H.; Zhonghui, L.; Yanghua, L.; Canyi, D., Wavelet transform singularity detection technology applied in the seabed sediment sound velocity measurement, 12^th IEEE Conf on In Industrial Electronics and Applications (ICIEA), 2017, 1050-1054 (2017), Siem Reap: Siem Reap Cambodia |
| [67] | Vrscay, E. R., A generalized class of fractal-wavelet transforms for image representation and compression, Can J Electr Comput Eng, 23, 1-2, 69-83 (1998) |
| [68] | Ramirez-Pacheco, J. C.; Trejo-Sanchez, J. A.; Cortez-Gonzalez, J.; Palacio, R. R., Classification of fractal signals using two-parameter non-extensive wavelet entropy, Entropy, 19, 5, 224 (2017) |
| [69] | Doi: 10.1109/APBME.2003.1302650 |
| [70] | Hagan, M. T.; Menhaj, M. B., Training feedforward networks with the marquardt algorithm, IEEE Trans Neural Networks, 5, 6, 989-993 (1994) |
| [71] | Doi.org/10.1007/978-3-030-24296-1_23 |
| [72] | Saeedi, E.; Hossain, M. S.; Kong, Y., Feed-forward back-propagation neural networks in side-channel information characterisation, J Circuits Syst Comput, 28, 1 (2019) |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
