A hybrid classifier based on nonlinear-PCA and deep belief networks with applications in dysphagia diagnosis

References

• Logemann JA. Evaluation and treatment of swallowing disorders. 2nd ed. Austin: Pro-Ed:1998.
   Google Scholar
• Smithard DG, O’Neill PA, England RE, et al. The natural history of dysphagia following a stroke. Dysphagia. 1997;12:188–193.
   PubMed Web of Science ®Google Scholar
• Lawrence ES, Coshall C, Dundas R, et al. Estimates of the prevalence of acute stroke impairments and disability in a multiethnic population. Stroke. 2001;32:1279–1284.
   PubMed Web of Science ®Google Scholar
• Hassan HE, Aboloyoun AI. The value of bedside tests in dysphagia evaluation. Egypt J Ear Nose Throat Allied Sci. 2014; 15:197–203.
   Google Scholar
• Ellis AL, Hannibal RR. Nursing swallow screens: why is testing water only not enough? J Neurosci Nurs. 2013;45:244–253.
   PubMed Web of Science ®Google Scholar
• Smithard DG, O’Neill PA, Park C, et al. Complications and outcome after acute stroke does dysphagia matter? Stroke. 1996;27:1200–1204.
   PubMed Web of Science ®Google Scholar
• Smithard DG, O’Neill PA, Martin DF, et al. Aspiration following stroke: is it related to the side of the stroke? Clin Rehabil. 1997;11:73–76.
   PubMed Web of Science ®Google Scholar
• Ramsey DJ, Smithard DG. Assessment and management of dysphagia. Hosp Med. 2004;65:274–279.
   PubMed Web of Science ®Google Scholar
• Osawa A, Maeshima S, Tanahashi N. Water-swallowing test: screening for aspiration in stroke patients. Cerebrovasc Dis. 2013;35:276–281.
   PubMed Web of Science ®Google Scholar
• MartinoMaki R, Diamant EN. Identification of dysphagia using the Toronto Bedside Swallowing Screening Test (TOR-BSST©): are 10 teaspoons of water necessary? Int J Speech-Lang Pathol. 2014;6:193–198.
   Web of Science ®Google Scholar
• Suiter DM, Leder SB. Clinical utility of the 3-ounce water swallow test. Dysphagia. 2008;23:244–250.
   PubMed Web of Science ®Google Scholar
• Mallela UK, Upadhyay A. Buckling load prediction of laminated composite stiffened panels subjected to in-plane shear using artificial neural networks. Thin-Wall Struct. 2016;102:158–164.
   Web of Science ®Google Scholar
• Stojanovic B, Milivojevic M, Milivojevic N, et al. A self-tuning system for dam behavior modeling based on evolving artificial neural networks. Adv Eng Soft. 2016;97:85–95.
   Web of Science ®Google Scholar
• Wahab OA, Mourad A, Otrok H, et al. CEAP: SVM-based intelligent detection model for clustered vehicular ad hoc networks. Expert Syst Appl. 2016;15:40–54.
   Web of Science ®Google Scholar
• Yan Y, Zheng WK, Bao J, et al. An enhanced Mary SVM algorithm for multi-category classification and its application. Neurocomputing. 2016;187:119–125.
   Web of Science ®Google Scholar
• Fu JH, Lee SL. A multi-class SVM classification system based on learning methods from indistinguishable chinese official documents. Expert Syst Appl. 2012;39:3127–3134.
   Web of Science ®Google Scholar
• Yardimci A. Soft computing in medicine. Applied Soft Comput. 2009;9:1029–1043.
   Web of Science ®Google Scholar
• Teodorescua HL, Chelaru M, Kandela A, et al. Fuzzy methods in tremor assessment, prediction, and rehabilitation. Artif Intell Med. 2001;21:107–130.
   PubMed Web of Science ®Google Scholar
• Montani S. Exploring new roles for case-based reasoning in heterogeneous AI systems for medical decision support. Appl Intell. 2008; 28:275–285.
   Web of Science ®Google Scholar
• Palreddy S, Reddy NP, Green P, et al. Neural networks in computer-aided diagnosis classification of dysphagic patients. Paper presented at 14th Annual International Conference of the IEEE Engineering in Medicine and Biology Society; 1992(4). p. 1517–1518.
   Google Scholar
• Prabhu DNF, Reddy NP, Canilang EP. Neural networks for recognition of acceleration patterns during swallowing and coughing. Proceedings of the 16th Annual International Conference of the IEEE, 1994. p. 1105–1106.
   Google Scholar
• Reddy NP, Prabhu D, Palreddy, et al. Redundant neural networks for medical diagnosis: diagnosis of dysphagia. Intell Syst through Artif Neural Networks. 1995;5:699–704.
   Google Scholar
• Lee J, Blain S, Casas, et al. A radial basis classifier for the automatic detection of aspiration in children with dysphagia. J NeuroEng Rehabilit. 2006;3:1–3.
   PubMed Web of Science ®Google Scholar
• Cola PC, Gatto AR, da Silva RG, et al. Classification of normal swallowing and oropharyngeal dysphagia using wavelet. Appl Math Comput. 2009;207:75–82.
   Web of Science ®Google Scholar
• Saki F, Kehtarnavaz N. Online frame-based clustering with unknown number of clusters. Pattern Recogn. 2016;57:70–83.
   Web of Science ®Google Scholar
• Li H, Chung F-l, Wang S. A SVM based classification method for homogeneous data. Appl Soft Comput. 2015;36:228–235.
   Web of Science ®Google Scholar
• Embrechts MJ, Rossi F, Schleif F-M, et al. Advances in artificial neural networks, machine learning, and computational intelligence. Neurocomputing. 2014;141:1–2.
   Web of Science ®Google Scholar
• Zhang YP, Li X, Zhang ZF, et al. Deep learning driven blockwise moving object detection with binary scene modeling. Neurocomputing. 2015;168:454–463.
   Web of Science ®Google Scholar
• ZhouChen S, Wang QX. Active deep learning method for semi-supervised sentiment classification. Neurocomputing. 2013;120:536–546.
   Web of Science ®Google Scholar
• Shen FR, Chao J, Zhao JX. Forecasting exchange rate using deep belief networks and conjugate gradient method. Neurocomputing. 2015;167:243–253.
   Web of Science ®Google Scholar
• Li H, Li XY, Ramanathan M, et al. Identifying informative risk elements and predicting bone disease progression via deep belief networks. Methods. 2014;69:257–265.
   PubMed Web of Science ®Google Scholar
• Shang C, Yang F, Huang DX, et al. Data-driven soft sensor development based on deep learning technique. J Process Control. 2014;24:223–233.
   Web of Science ®Google Scholar
• M, Wöllmer F, Eyben Bö, Schuller, et al. Spoken term detection eith connectionist temporal classification:a novel hybrid CTC-DBN decoder. Poster presented at Acoustics, speech, and signal processing, ICASSP-88; 2010.
   Google Scholar
• Zhong Pin, Gong gZ. A hybrid DBN and CRF model for Spectral-Spatial classification of hyperspectral images. Stat Optim Inform Comput 2017;5:75–98.
   Google Scholar
• Verbanck M Josse, et al. Regularised PCA to denoise and visualise data. Stat Comput. 2015;25:471–486.
   Web of Science ®Google Scholar
• Zhu Ge J, Song ZZ. Dynamic mixture probabilistic PCA classifier modeling and application for fault classification. J Chemometrics. 2015;29:361–370.
   Web of Science ®Google Scholar
• Li EG, Yu JS. An input-training neural network based nonlinear principal component analysis approach for fault diagnosis. Control Decision. 2003;18:229–231.
   Google Scholar
• Niu Z, Liu ZJ, Niu yg. RBF networks-based nonlinear principal component analysis for process fault detection. Machine Learn Cybernet. 2005;8:4784–4788.
   Google Scholar
• Hessam M, Tarek E, Nejib S. A nonlinear principal component analysis approach for turbulent combustion composition space. Int J Hydrogen Energy. 2014;39:4622–4633.
   Web of Science ®Google Scholar
• Liu KL, Fei ZS, Yue BX, et al. Adaptive sparse principal component analysis for enhanced process monitoring and fault isolation. Chemometrics Intell Lab Sys. 2015;146:426–436.
   Web of Science ®Google Scholar
• Mansouri M, Nounou M, Nounou H, et al. Kernel PCA-based GLRT for nonlinear fault detection of chemical processes. J Loss Prevent Process Ind. 2016;40:334–347.
   Web of Science ®Google Scholar
• Tan S, Mavrovouniotis ML. Reducing data dimensionality through optimizing neural network inputs. Aiche J. 1995;41:1471–1480.
   Web of Science ®Google Scholar
• Liu J, Yu J, Yan B. A new method to fault nonlinear diagnosis for a class of systems. Chinese J Electron. 2011;2:217–222.
   Google Scholar
• Sanchez D, Melin P, Castillo O. Optimization of modular granular neural networks using a hierarchical genetic algorithm based on the database complexity applied to human recognition. Inform Sci. 2015;309:73–101.
   Web of Science ®Google Scholar
• Ni Y-y, Zhang J-x. Modeling and forecasting for multivariate time series using a vector autoregression model. Chinese J Health Stat. 2014;1:53–56.
   Google Scholar
• Liang X, Chen S-w, Zhou P, et al. Diagnosis and differential diagnosis of two dimensional and three dimensional transvaginal Ultrasound. Chinese Ultrasound Med. 2012;28:355–357.
   Google Scholar
• Deng F, Guan S, Yue X, et al. Energy-based sound source localization with low power consumption in wireless sensor networks. IEEE Trans Ind Electron. 2017;64:4894–4902.
   Web of Science ®Google Scholar
• Deng F, Guo S, Zhou R, et al Sensor multifault diagnosis with improved support vector machines. IEEE Trans Autom Sci Eng. 2017;14:1053–1063.
   Web of Science ®Google Scholar