退化性神經疾病的盛行率日漸上升，常見的退化性神經疾病（如漸凍人症、杭亭頓症、帕金森氏症）皆會造成步態異常。本論文研究目標旨在結合多尺度樣本熵之特徵及機械學習演算法用於：1) 神經退化性疾病步態辨識、2) 帕金森氏症嚴重程度的步態識別，希望開發的演算未來可用於協助臨床醫師透過步態訊號快速篩檢神經退化性疾病、或患者帕金森氏症嚴重程度的變化。本研究採用麻省理工學院Physionet提供的1) 神經退化性疾病步態、2) 帕金森氏症嚴重程度步態的開源資料庫進行演算法開發及驗證。Physionet神經退化性疾病步態資料庫包含64位受測者資料（16位健康受測者、13位漸凍人症患者、20位杭亭頓症患者、15位帕金森氏症患者），每位受測者資料皆為5分鐘的左右腳足底壓力時序訊號。帕金森氏症嚴重程度資料庫包含166位受測者資料（73位健康受測者（Stage 0）、93位帕金森氏症患者（嚴重程度依臨床標準分為三類，分別為Stage 2（55位受測者）、Stage 2.5（28位受測者）、Stage 3（10位受測者））。本論文提出的演算法包括視窗化及前處理程序、特徵萃取程序、特徵選取程序、辨識程序。在視窗化及前處理程序中，足底壓力時序訊號依據分別切分成10秒、20秒、30秒、60秒等不同時間長度的視窗。在特徵萃取程序中，多尺度樣本熵的應用程序被應用於每一個視窗的原始訊號及其一次/二次微分萃取特徵值。虛擬少數類別過抽樣技術(synthetic minority oversampling technique, SMOTE)則被用於解決資料不平衡的問題。支持向量機以及K-近鄰演算法則作為辨識的演算法。在研究成果部分，在使用神經退化性疾病步態資料庫分類各種不同的神經退化性疾病與健康受測者的步態辨識皆可達到100%的辨識率，辨識（帕金森氏症及杭亭頓症步態）/（帕金森氏症及漸凍人症步態）/（杭亭頓症及漸凍人症步態）/（分辨健康受測者、帕金森氏症、杭亭頓症步態、漸凍人症步態的）的辨識率分別為100% / 99.81% / 99.72%、99.86%。在使用帕金森氏症嚴重程度步態資料庫的研究成果，辨識健康受測者及帕金森氏症步態的辨識率為99.24%，辨識不同帕金森氏症嚴重程度（Stage 0 vs. Stage 2 vs. Stage 2.5 vs. Stage 3）的辨識率可達到98.69%。本研究成功的結合開發了結合多尺度樣本熵及機器學習的神經退化性疾病步態分類/帕金森氏症嚴重程度識別之演算法。

Prevalence of neurodegenerative diseases (NDD) grows rapidly recent years and NDD screening get much attention. Neuro-degenerative diseases (NDDs), such as Amyotrophic Lateral Sclerosis (ALS), Huntington’s Disease (HD), and Parkinson’s Disease (PD), may cause serious gait abnormalities. Research aim of this study is to develop an NDD classification and PD severity detection algorithm via vertical ground reaction force (VGRF) signals using multiscale sample entropy (MSE) and machine learning models. The main purpose of this study is to help a physician with screening for NDDs for early diagnosis, efficient treatment planning, and monitoring of disease progression (such as PD severity detection). The Physionet NDD and PD gait databases were utilized to validate the proposed algorithm. The NDD database used in this study consisted 64 recordings (five-minutes in each recording) of VGRF signals acquired from 16 healthy controls, 13 ALS, 20 HD, and 15 PD subjects. The PD database consisted 93 PD patients and 73 HC subjects. The proposed detection algorithm consists of a windowing process, a feature extraction process, a feature selection process, and a classification process. In the preprocessing stage of the proposed algorithm, new signals were generated by taking one- and two-time of differential on VGRF and are divided into various time windows for NDD database (10/20/30/60-sec) and PD database (10/20/30-sec). In feature extraction, the VGRF signals were used to calculate multiscale sample entropy values. Owing to the imbalanced nature of the Physionet NDD and PD gait database, the synthetic minority oversampling technique (SMOTE) was used to rebalance data of each class. Support vector machine (SVM) and k-nearest neighbors (KNN) were used as the classifiers. In NDD database, the best classification accuracies the healthy controls (HC) vs. PD, (HC vs. HD), (HC vs. ALS), (PD vs. HD), (PD vs. ALS), (HD vs. ALS), and (HC vs. PD vs. HD vs. ALS) were 100%, 100%, 100%, 100%, 99.81%, 99.72%, and 99.86%. In PD database, the best classication accuracy for (HC vs. PD) was 99.24% and the best classification for PD severity (0 vs. 2 vs. 2.5 vs. 3) was 98.69%. We compared our highest performance accuracy in terms of these classification tasks with several studies using the same database, and found that the proposed method outperforms the performance results in the existing literature. In conclusion, this study successfully developed an NDD gait classification based on MSE and machine learning classifiers.

References
[1] T. D. Pham, “Texture Classification and Visualization of Time Series of Gait Dynamics in Patients with Neuro-Degenerative Diseases,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 26, no. 1, pp. 188–196, 2018, doi: 10.1109/TNSRE.2017.2732448.
[2] M. Agrawal and A. Biswas, “Molecular diagnostics of neurodegenerative disorders,” Front. Mol. Biosci., vol. 2, no. SEP, pp. 1–10, 2015, doi: 10.3389/fmolb.2015.00054.
[3] T. Vos et al., “Global, regional, and national incidence, prevalence, and years lived with disability for 310 diseases and injuries, 1990–2015: a systematic analysis for the Global Burden of Disease Study 2015,” Lancet, vol. 388, no. 10053, pp. 1545–1602, 2016, doi: 10.1016/S0140-6736(16)31678-6.
[4] J. M. Hausdorff, M. E. Cudkowicz, R. Firtion, J. Y. Wei, and A. L. Goldberger, “Gait variability and basal ganglia disorders: Stride-to-stride variations of gait cycle timing in Parkinson’s disease and Huntington’s disease,” Mov. Disord., vol. 13, no. 3, pp. 428–437, 1998, doi: 10.1002/mds.870130310.
[5] O. B. Tysnes and A. Storstein, “Epidemiology of Parkinson’s disease,” J. Neural Transm., vol. 124, no. 8, pp. 901–905, 2017, doi: 10.1007/s00702-017-1686-y.
[6] S. Sveinbjornsdottir, “The clinical symptoms of Parkinson’s disease,” J. Neurochem., vol. 139, pp. 318–324, 2016, doi: 10.1111/jnc.13691.
[7] P. Dayalu and R. L. Albin, “Huntington Disease: Pathogenesis and Treatment,” Neurol. Clin., vol. 33, no. 1, pp. 101–114, 2015, doi: 10.1016/j.ncl.2014.09.003.
[8] E. Van Duijn, E. M. Kingma, and R. C. Van Der Mast, “Psychopathology in verified Huntington’s disease gene carriers,” J. Neuropsychiatry Clin. Neurosci., vol. 19, no. 4, pp. 441–448, 2007, doi: 10.1176/jnp.2007.19.4.441.
[9] S. Frank, “Treatment of Huntington’s Disease,” Neurotherapeutics, vol. 11, no. 1, pp. 153–160, 2014, doi: 10.1007/s13311-013-0244-z.
[10] A. Chio, B. Traynor, J. Collins, J. Simeone, L. Goldstein, and L. White, “Global Epidemiology of Amyotrophic Lateral Sclerosis: a Systematic Review of the Published Literature,” Neuroepidemiology, vol. 41, no. 2, pp. 118–130, 2013, doi: 10.1159/000351153.Global.
[11] A. E. Renton, A. Chiò, and B. J. Traynor, “State of play in amyotrophic lateral sclerosis genetics HHS Public Access Author manuscript,” Nat Neurosci, vol. 17, no. 1, pp. 17–23, 2014, doi: 10.1038/nn.3584.State.
[12] J. M. Hausdorff, A. Lertratanakul, M. E. Cudkowicz, A. L. Peterson, D. Kaliton, and A. L. Goldberger, “Dynamic markers of altered gait rhythm in amyotrophic lateral sclerosis,” J. Appl. Physiol., vol. 88, no. 6, pp. 2045–2053, 2000, doi: 10.1152/jappl.2000.88.6.2045.
[13] M. C. Kiernan, Matthew C Vucic, Steve Cheah, Benjamin C Turner, Martin R Eisen, Andrew Hardiman, Orla Burrell, James R Zoing, “Amyotrophic lateral sclerosis,” Lancet, vol. 377, no. 9769, pp. 942–955, Mar. 2011, doi: 10.1016/S0140-6736(10)61156-7.
[14] N. Joint, S. Motion, D. The, and G. Cycle, “Clinical Application of Neuromuscular Techniques, Volume 2,” no. Perry, pp. 61–84, 2011, doi: 10.1016/B978-0-443-06815-7.00003-6.
[15] E. Abdulhay, N. Arunkumar, K. Narasimhan, E. Vellaiappan, and V. Venkatraman, “Gait and tremor investigation using machine learning techniques for the diagnosis of Parkinson disease,” Futur. Gener. Comput. Syst., vol. 83, pp. 366–373, 2018, doi: 10.1016/j.future.2018.02.009.
[16] F. Arafsha, C. Hanna, A. Aboualmagd, S. Fraser, and A. El Saddik, “Instrumented wireless smartinsole system for mobile gait analysis: A validation pilot study with Tekscan Strideway,” J. Sens. Actuator Networks, vol. 7, no. 3, 2018, doi: 10.3390/jsan7030036.
[17] M. Gómez-Río, M. M. Caballero, J. M. Górriz Sáez, and A. Mínguez-Castellanos, “Diagnosis of Neurodegenerative Diseases: The Clinical Approach.,” Curr. Alzheimer Res., vol. 13, no. 5, pp. 469–474, 2016, doi: 10.2174/1567205013666151116141603.
[18] M. Borowska, “Entropy-based algorithms in the analysis of biomedical signals,” Stud. Logic, Gramm. Rhetor., vol. 43, no. 56, pp. 21–32, 2015, doi: 10.1515/slgr-2015-0039.
[19] R. Zhao, J. Rong, and X. Li, “Entropy and its application in turbulence modeling,” Chinese Sci. Bull., vol. 59, no. 31, pp. 4137–4141, 2014, doi: 10.1007/s11434-014-0569-y.
[20] A. Martínez-Rodrigo, B. García-Martínez, R. Alcaraz, P. González, and A. Fernández-Caballero, “Multiscale Entropy Analysis for Recognition of Visually Elicited Negative Stress from EEG Recordings,” Int. J. Neural Syst., vol. 29, no. 2, 2019, doi: 10.1142/S0129065718500387.
[21] M. Liu, C. Song, Y. Liang, T. Knöpfel, and C. Zhou, “Assessing spatiotemporal variability of brain spontaneous activity by multiscale entropy and functional connectivity,” Neuroimage, vol. 198, no. May, pp. 198–220, 2019, doi: 10.1016/j.neuroimage.2019.05.022.
[22] Y. Wu, P. Shang, and Y. Li, “Multiscale sample entropy and cross-sample entropy based on symbolic representation and similarity of stock markets,” Commun. Nonlinear Sci. Numer. Simul., vol. 56, pp. 49–61, 2018, doi: 10.1016/j.cnsns.2017.07.021.
[23] M. M. Platiša, N. N. Radovanović, A. Kalauzi, G. Milašinović, and S. U. Pavlović, “Multiscale Entropy Analysis: Application to Cardio-Respiratory Coupling,” Entropy, vol. 22, no. 9, p. 1042, 2020, doi: 10.3390/e22091042.
[24] G. Ouyang, J. Li, X. Liu, and X. Li, “Dynamic characteristics of absence EEG recordings with multiscale permutation entropy analysis,” Epilepsy Res., vol. 104, no. 3, pp. 246–252, 2013, doi: 10.1016/j.eplepsyres.2012.11.003.
[25] K. Zeng, G. Ouyang, H. Chen, Y. Gu, X. Liu, and X. Li, “Characterizing dynamics of absence seizure EEG with spatial-temporal permutation entropy,” Neurocomputing, vol. 275, pp. 577–585, 2018, doi: 10.1016/j.neucom.2017.09.007.
[26] Y. Lu, M. Wang, W. Wu, Y. Han, Q. Zhang, and S. Chen, “Dynamic entropy-based pattern learning to identify emotions from EEG signals across individuals,” Meas. J. Int. Meas. Confed., vol. 150, p. 107003, 2020, doi: 10.1016/j.measurement.2019.107003.
[27] C. Chen, J. Li, and X. Lu, “Multiscale entropy-based analysis and processing of EEG signal during watching 3DTV,” Meas. J. Int. Meas. Confed., vol. 125, no. 169, pp. 432–437, 2018, doi: 10.1016/j.measurement.2018.05.017.
[28] D. Labate, F. La Foresta, G. Morabito, I. Palamara, and F. C. Morabito, “Entropic measures of EEG complexity in alzheimer’s disease through a multivariate multiscale approach,” IEEE Sens. J., vol. 13, no. 9, pp. 3284–3292, 2013, doi: 10.1109/JSEN.2013.2271735.
[29] L. Zhao, J. Li, J. Xiong, X. Liang, and C. Liu, “Suppressing the influence of ectopic beats by applying a physical threshold-based sample entropy,” Entropy, vol. 22, no. 4, pp. 1–16, 2020, doi: 10.3390/E22040411.
[30] E. M. C. Roldan, S. Calero, V. M. Hidalgo, J. Enero, J. J. Rieta, and R. Alcaraz, “Multi-scale entropy evaluates the proarrhythmic condition of persistent atrial fibrillation patients predicting early failure of electrical cardioversion,” Entropy, vol. 22, no. 7, pp. 1–17, 2020, doi: 10.3390/e22070748.
[31] P. Trybek, M. Nowakowski, J. Salowka, J. Spiechowicz, and L. Machura, “Sample entropy of sEMG signals at different stages of rectal cancer treatment,” Entropy, vol. 20, no. 11, pp. 1–14, 2018, doi: 10.3390/e20110863.
[32] P. Qin and X. Shi, “Evaluation of feature extraction and classification for lower limb motion based on sEMG signal,” Entropy, vol. 22, no. 8, 2020, doi: 10.3390/E22080852.
[33] T. Mizuno et al., “Assessment of EEG dynamical complexity in Alzheimer’s disease using multiscale entropy,” Clin. Neurophysiol., vol. 121, no. 9, pp. 1438–1446, 2010, doi: 10.1016/j.clinph.2010.03.025.
[34] R. Mahajan and B. I. Morshed, “Unsupervised eye blink artifact denoising of EEG data with modified multiscale sample entropy, kurtosis, and wavelet-ICA,” IEEE J. Biomed. Heal. Informatics, vol. 19, no. 1, pp. 158–165, 2015, doi: 10.1109/JBHI.2014.2333010.
[35] S. M. G. Beyrami and P. Ghaderyan, “A robust, cost-effective and non-invasive computer-aided method for diagnosis three types of neurodegenerative diseases with gait signal analysis,” Meas. J. Int. Meas. Confed., vol. 156, p. 107579, 2020, doi: 10.1016/j.measurement.2020.107579.
[36] Y. Wu et al., “Measuring signal fluctuations in gait rhythm time series of patients with Parkinson’s disease using entropy parameters,” Biomed. Signal Process. Control, vol. 31, pp. 265–271, 2017, doi: 10.1016/j.bspc.2016.08.022.
[37] P. Ren, W. Zhao, Z. Zhao, M. L. Bringas-Vega, P. A. Valdes-Sosa, and K. M. Kendrick, “Analysis of Gait Rhythm Fluctuations for Neurodegenerative Diseases by Phase Synchronization and Conditional Entropy,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 24, no. 2, pp. 291–299, 2016, doi: 10.1109/TNSRE.2015.2477325.
[38] A. B. Liu and C. W. Lin, “Multiscale approximate entropy for gait analysis in patients with neurodegenerative diseases,” Entropy, vol. 21, no. 10, pp. 1–11, 2019, doi: 10.3390/e21100934.
[39] J. Yu, J. Cao, W. H. Liao, Y. Chen, J. Lin, and R. Liu, “Multivariate multiscale symbolic entropy analysis of human gait signals,” Entropy, vol. 19, no. 10, pp. 1–10, 2017, doi: 10.3390/e19100557.
[40] F. Liao, J. Wang, and P. He, “Multi-resolution entropy analysis of gait symmetry in neurological degenerative diseases and amyotrophic lateral sclerosis,” Med. Eng. Phys., vol. 30, no. 3, pp. 299–310, 2008, doi: 10.1016/j.medengphy.2007.04.014.
[41] G. Yogev, N. Giladi, C. Peretz, S. Springer, E. S. Simon, and J. M. Hausdorff, “Dual tasking, gait rhythmicity, and Parkinson’s disease: Which aspects of gait are attention demanding?,” Eur. J. Neurosci., vol. 22, no. 5, pp. 1248–1256, 2005, doi: 10.1111/j.1460-9568.2005.04298.x.
[42] J. M. Hausdorff, J. Lowenthal, T. Herman, L. Gruendlinger, C. Peretz, and N. Giladi, “Rhythmic auditory stimulation modulates gait variability in Parkinson’s disease,” Eur. J. Neurosci., vol. 26, no. 8, pp. 2369–2375, 2007, doi: 10.1111/j.1460-9568.2007.05810.x.
[43] J. M. Hausdorff, “Gait variability : methods , modeling and meaning Example of Increased Stride Time Variability in Elderly Fallers Quantification of Stride-to-Stride Fluctuations,” vol. 9, pp. 1–9, 2005, doi: 10.1186/1743-Received.
[44] S. Frenkel-Toledo, N. Giladi, C. Peretz, T. Herman, L. Gruendlinger, and J. M. Hausdorff, “Treadmill walking as an external pacemaker to improve gait rhythm and stability in Parkinson’s disease,” Mov. Disord., vol. 20, no. 9, pp. 1109–1114, 2005, doi: 10.1002/mds.20507.
[45] W. Zeng and C. Wang, “Classification of neurodegenerative diseases using gait dynamics via deterministic learning,” Inf. Sci. (Ny)., vol. 317, pp. 246–258, 2015, doi: 10.1016/j.ins.2015.04.047.
[46] M. N. Alam, A. Garg, T. T. K. Munia, R. Fazel-Rezai, and K. Tavakolian, “Vertical ground reaction force marker for Parkinson’s disease,” PLoS One, vol. 12, no. 5, pp. 1–13, 2017, doi: 10.1371/journal.pone.0175951.
[47] W. Zeng, F. Liu, Q. Wang, Y. Wang, L. Ma, and Y. Zhang, “Parkinson’s disease classification using gait analysis via deterministic learning,” Neurosci. Lett., vol. 633, pp. 268–278, 2016, doi: 10.1016/j.neulet.2016.09.043.
[48] Z. Li, W. Chen, J. Wang, and J. Liu, “An automatic recognition system for patients with movement disorders based on wearable sensors,” Proc. 2014 9th IEEE Conf. Ind. Electron. Appl. ICIEA 2014, pp. 1948–1953, 2014, doi: 10.1109/ICIEA.2014.6931487.
[49] M. Yang, H. Zheng, H. Wang, and S. McClean, “Feature selection and construction for the discrimination of neurodegenerative diseases based on gait analysis,” 2009 3rd Int. Conf. Pervasive Comput. Technol. Healthc. - Pervasive Heal. 2009, PCTHealth 2009, 2009, doi: 10.4108/ICST.PERVASIVEHEALTH2009.6053.
[50] Y. Xia, Q. Gao, and Q. Ye, “Classification of gait rhythm signals between patients with neuro-degenerative diseases and normal subjects: Experiments with statistical features and different classification models,” Biomed. Signal Process. Control, vol. 18, pp. 254–262, Apr. 2015, doi: 10.1016/J.BSPC.2015.02.002.
[51] Ö. F. Ertuǧrul, Yi. Kaya, R. Tekin, and M. N. Almali, “Detection of Parkinson’s disease by Shifted One Dimensional Local Binary Patterns from gait,” Expert Syst. Appl., vol. 56, pp. 156–163, 2016, doi: 10.1016/j.eswa.2016.03.018.
[52] P. Prabhu, A. K. Karunakar, H. Anitha, and N. Pradhan, “Classification of gait signals into different neurodegenerative diseases using statistical analysis and recurrence quantification analysis,” Pattern Recognit. Lett., vol. 0, pp. 1–7, 2018, doi: 10.1016/j.patrec.2018.05.006.
[53] I. El Maachi, G. A. Bilodeau, and W. Bouachir, “Deep 1D-Convnet for accurate Parkinson disease detection and severity prediction from gait,” Expert Syst. Appl., vol. 143, p. 113075, 2020, doi: 10.1016/j.eswa.2019.113075.
[54] A. Zhao, L. Qi, J. Li, J. Dong, and H. Yu, “A hybrid spatio-temporal model for detection and severity rating of Parkinson’s disease from gait data,” Neurocomputing, vol. 315, pp. 1–8, 2018, doi: 10.1016/j.neucom.2018.03.032.
[55] C. W. Lin, T. C. Wen, and F. Setiawan, “Evaluation of vertical ground reaction forces pattern visualization in neurodegenerative diseases identification using deep learning and recurrence plot image feature extraction,” Sensors (Switzerland), vol. 20, no. 14, pp. 1–22, 2020, doi: 10.3390/s20143857.
[56] B. E., B. D., and B. R., “Supervised machine learning based gait classification system for early detection and stage classification of Parkinson’s disease,” Appl. Soft Comput. J., vol. 94, p. 106494, 2020, doi: 10.1016/j.asoc.2020.106494.
[57] M. Costa, A. L. Goldberger, and C. K. Peng, “Multiscale Entropy Analysis of Complex Physiologic Time Series,” Phys. Rev. Lett., vol. 89, no. 6, pp. 6–9, 2002, doi: 10.1103/PhysRevLett.89.068102.
[58] M. Costa, A. L. Goldberger, and C. K. Peng, “Multiscale entropy to distinguish physiologic and synthetic RR time series,” Comput. Cardiol., vol. 29, no. 1, pp. 137–140, 2002, doi: 10.1109/cic.2002.1166726.
[59] M. M. Hoehn and M. D. Yahr, “Parkinsonism: onset, progression, and mortality. 1967.,” Neurology, vol. 50, no. 2, p. 318 and 16 pages following, Feb. 1998, doi: 10.1212/wnl.50.2.318.
[60] D. Elreedy and A. F. Atiya, “A Comprehensive Analysis of Synthetic Minority Oversampling Technique (SMOTE) for handling class imbalance,” Inf. Sci. (Ny)., vol. 505, pp. 32–64, 2019, doi: 10.1016/j.ins.2019.07.070.
[61] T. Pan, J. Zhao, W. Wu, and J. Yang, “Learning imbalanced datasets based on SMOTE and Gaussian distribution,” Inf. Sci. (Ny)., vol. 512, pp. 1214–1233, 2020, doi: 10.1016/j.ins.2019.10.048.
[62] A. Marcano-Cedeño, J. Quintanilla-Domínguez, M. G. Cortina-Januchs, and D. Andina, “Feature selection using Sequential Forward Selection and classification applying Artificial Metaplasticity Neural Network,” IECON Proc. (Industrial Electron. Conf., pp. 2845–2850, 2010, doi: 10.1109/IECON.2010.5675075.
 
[63] J. Fairley, G. Georgoulas, and G. Vachtsevanos, “Sequential feature selection methods for Parkinsonian human sleep analysis,” pp. 1468–1473, 2009, doi: 10.1109/med.2009.5164754.
[64] L. S. Burrell, O. L. Smart, G. Georgoulas, E. Marsh, and G. J. Vachtsevanos, “Evaluation of feature selection techniques for analysis of functional MRI and EEG,” Int. Conf. Data Min., pp. 256–262, 2007.
[65] J. S. Richman and J. R. Moorman, “Physiological time-series analysis using approximate entropy and sample entropy maturity in premature infants Physiological time-series analysis using approximate entropy and sample entropy,” Am. J. Physiol. Hear. Circ. Physiol., vol. 278, pp. H2039–H2049, 2000.
[66] E. M. Cirugeda-Roldán, A. Molina Picó, D. Novák, D. Cuesta-Frau, and V. Kremen, “Sample Entropy Analysis of Noisy Atrial Electrograms during Atrial Fibrillation,” Comput. Math. Methods Med., vol. 2018, 2018, doi: 10.1155/2018/1874651.
[67] E. Guerreschi, A. Humeau-Heurtier, G. Mahe, M. Collette, and G. Leftheriotis, “Complexity quantification of signals from the heart, the macrocirculation and the microcirculation through a multiscale entropy analysis,” Biomed. Signal Process. Control, vol. 8, no. 4, pp. 341–345, Jul. 2013, doi: 10.1016/J.BSPC.2013.04.001.
[68] M. Costa, A. L. Goldberger, and C. K. Peng, “Multiscale entropy analysis of biological signals,” Phys. Rev. E - Stat. Nonlinear, Soft Matter Phys., vol. 71, no. 2, pp. 1–18, 2005, doi: 10.1103/PhysRevE.71.021906.
[69] A. Dal Pozzolo, O. Caelen, and G. Bontempi, “Comparison of Balancing Techniques for Unbalanced Datasets,” Mach. Learn. Gr. Univ. Libr. Bruxelles Belgium, vol. 16, no. 1, pp. 732–735, 2010, doi: 10.1613/jair.953.
[70] W. Yang, K. Wang, and W. Zuo, “Neighborhood component feature selection for high-dimensional data,” J. Comput., vol. 7, no. 1, pp. 162–168, 2012, doi: 10.4304/jcp.7.1.161-168.
[71] J. Fairley, G. Georgoulas, and G. Vachtsevanos, “Sequential feature selection methods for Parkinsonian human sleep analysis,” 2009 17th Mediterr. Conf. Control Autom., pp. 1468–1473, 2009, doi: 10.1109/med.2009.5164754.
[72] O. Yaman, “An automated faults classification method based on binary pattern and neighborhood component analysis using induction motor,” Meas. J. Int. Meas. Confed., vol. 168, no. July 2020, p. 108323, 2021, doi: 10.1016/j.measurement.2020.108323.
[73] R. K. Begg, M. Palaniswami, and B. Owen, “Support vector machines for automated gait classification,” IEEE Trans. Biomed. Eng., vol. 52, no. 5, pp. 828–838, 2005, doi: 10.1109/TBME.2005.845241.
[74] T. Nakano et al., “Gaits classification of normal vs. patients by wireless gait sensor and Support Vector Machine (SVM) classifier,” 2016 IEEE/ACIS 15th Int. Conf. Comput. Inf. Sci. ICIS 2016 - Proc., pp. 1–6, 2016, doi: 10.1109/ICIS.2016.7550922.
[75] B. Quost and S. Destercke, “Classification by pairwise coupling of imprecise probabilities,” Pattern Recognit., vol. 77, pp. 412–425, 2018, doi: 10.1016/j.patcog.2017.10.019.
[76] Q. Nie, L. Jin, and S. Fei, “Probability estimation for multi-class classification using AdaBoost,” Pattern Recognit., vol. 47, no. 12, pp. 3931–3940, 2014, doi: 10.1016/j.patcog.2014.06.008.
[77] K. Lee, H. O. Choi, S. D. Min, J. Lee, B. B. Gupta, and Y. Nam, “A Comparative Evaluation of Atrial Fibrillation Detection Methods in Koreans Based on Optical Recordings Using a Smartphone,” IEEE Access, vol. 5, pp. 11437–11443, 2017, doi: 10.1109/ACCESS.2017.2700488.
[78] N. S. Altman, “An introduction to kernel and nearest-neighbor nonparametric regression,” Am. Stat., vol. 46, no. 3, pp. 175–185, 1992, doi: 10.1080/00031305.1992.10475879.
[79] H. Lodhi, S. Muggleton, and M. J. E. Sternberg, “Multi-class protein fold recognition using large margin logic based divide and conquer learning,” Proc. KDD-09 Work. Stat. Relational Learn. Bioinformatics, StReBio ’09, vol. 17, no. 4, pp. 22–26, 2009, doi: 10.1145/1562090.1562095.
[80] H. Ling, C. Qian, W. Kang, C. Liang, and H. Chen, “Combination of Support Vector Machine and K-Fold cross validation to predict compressive strength of concrete in marine environment,” Constr. Build. Mater., vol. 206, pp. 355–363, 2019.