Plantar pressure image fusion for comfort fusion in diabetes mellitus using an improved fuzzy hidden Markov model

• Autorzy: Li Zairan , Wang Dan , Dey Nilanjan , Ashour Amira S. , Sherratt R. Simon , Shi Fuqian

Identyfikatory

DOI

10.1016/j.bbe.2019.06.007

• Języki publikacji: EN

Abstrakty

EN

Diabetes mellitus is a clinical syndrome caused by the interaction of genetic and environmental factors. The change of plantar pressure in diabetic patients is one of the important reasons for the occurrence of diabetic foot. The abnormal increase of plantar pressure is a predictor of the common occurrence of foot ulcers. The feature extraction of plantar pressure distribution will be beneficial to the design and manufacture of diabetic shoes that will be beneficial for early protection of diabetes mellitus patients. In this research, texture-based features of the angular second moment (ASM), moment of inertia (MI), inverse difference monument (IDM), and entropy (E) have been selected and fused by using the updown algorithm. The fused features are normalized to predict comfort plantar pressure imaging dataset using an improved fuzzy hidden Markov model (FHMM). In FHMM, type-I fuzzy set is proposed and fuzzy Baum–Welch algorithm is also applied to estimate the next features. The results are discussed, and by comparing with other back–forward algorithms and different fusion operations in FHMM. Improved HMMs with up–down fusion using type-I fuzzy definition performs high effectiveness in prediction comfort plantar pressure distribution in an image dataset with an accuracy of 82.2% and the research will be applied to the shoe-last personalized customization in the industry.

Słowa kluczowe

EN

plantar pressure; imaging dataset; image fusion; texture based feature extraction; fuzzy hidden Markov model; fuzzy Baum–Welch algorithm

PL

ciśnienie podeszwowe; dane obrazowe; fuzja obrazu; ekstrakcja cech; ukryty model Markowa

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2019
• Tom: Vol. 39, no. 3
• Strony: 742--752
• Opis fizyczny: Bibliogr. 61 poz., rys., tab., wykr.

Twórcy

autor

Li Zairan

• School of Electrical Engineering and Information Engineering, Tianjin University, Tianjin, PR China; Wenzhou Vocational & Technical College, Wenzhou, PR China

autor

Wang Dan

• School of Electrical Engineering and Information Engineering, Tianjin University, Tianjin, PR China

autor

Dey Nilanjan

• Department of Information Technology, Techno India College of Technology, West Bengal, India

autor

Ashour Amira S.

• Department of Electronics and Electrical Communications Engineering, Faculty of Engineering, Tanta University, Tanta, Egypt

autor

Sherratt R. Simon

• Department of Biomedical Engineering, The University of Reading, UK

autor

Shi Fuqian

• First Affiliated Hospital of Wenzhou Medical University, Wenzhou, PR China

Bibliografia

• [1] Cao L, Dey N, Ashour AS, Simon F, Sherratt RS, Wu L, et al. Diabetic plantar pressure analysis using image fusion. Multimed Tools Appl 2018. http://dx.doi.org/10.1007/s11042-018-6269-x.
• [2] Liu S, He C, Cai Y, Xing Q, Guo Y, Chen Z, et al. Evaluation of negative-pressure wound therapy for patients with diabetic foot ulcers: systematic review and meta-analysis. Ther Clin Risk Manag 2017;13:533–44.
• [3] Fernando ME, Crowther RG, Lazzarini PA, Sangla KS, Wearing S, Buttner P, et al. Plantar pressures are higher in cases with diabetic foot ulcers compared to controls despite a longer stance phase duration. BMC Endocr Disord 2016;16:51.
• [4] Falzon B, Formosa C, Camilleri L, Gatt A. Duration of Type 2 diabetes is a predictor of elevated plantar foot pressure. Rev Diabet Stud 2018;14(4):372–80.
• [5] Andrew KB, Jamie JA, Karl BL, Hylton BM. The relationship between foot posture and plantar pressure during walking in adults: a systematic review. Gait Posture 2018;62:56–67.
• [6] Chen H, Cao L, Li Z, Hemanth DJ, Wu L, Albuquerque DHC, et al. Evaluation on diabetic plantar pressure data-set employing auto-segmentation technologies. Neural Comput Appl 2018. http://dx.doi.org/10.1007/s00521-018-3838-x.
• [7] Arts ML, Bus SA. Twelve steps per foot are recommended for valid and reliable in-shoe plantar pressure data in neuropathic diabetic patients wearing custom made footwear. Clin Biomech (Bristol Avon) 2011;26(8):880–4.
• [8] Razak AH, Zayegh A, Begg RK, Wahab Y. Foot plantar pressure measurement system: a review. Sensors 2012;12 (7):9884–912.
• [9] Tong JW, Kong PW. Reliability of footprint geometric and plantar loading measurements in children using the Emed (R)M system. Gait Posture 2013;38(2):281–6.
• [10] Silva AH, Sampath WH, Sameera NH, Amarasinghe YW, Mitani A. Development of a novel telecare system, integrated with plantar pressure measurement system. Inform Med 2018;12:98–105.
• [11] Wang D, Li Z, Dey N, Ashour AS, Sherratt RS, Shi F. Case-based reasoning for product style construction and fuzzy analytic hierarchy process evaluation modeling using consumers linguistic variables. IEEE Access 2017;5:4900–12.
• [12] Kornfeind P, Eckl M, Baca A. A single step analysis of plantar pressure distribution in tennis specific movements. J Hum Sport Exerc 2018. http://dx.doi.org/10.14198/jhse.2019.142.14.
• [13] Naraghi R, Slack-Smith L, Bryant A. Plantar pressure measurements and geometric analysis of patients with and without Morton's neuroma. Foot Ankle Int )2018;(2). AID: 1071100718766553.
• [14] Lipsitz LA, Lough M, Niemi J, Travison T, Howlett H, Manor B. A shoe insole delivering sub-sensory vibratory noise improves balance and gait in healthy elderly people. Arch Phys Med Rehabil 2015;96(3):432–9.
• [15] Nishiwaki T, Nonogawa M. Application of topological optimization technique to running shoe designing. Procedia Engineering, in proc. The Impact of Technology on Sport VI 7th Asia-Pacific Congress on Sports Technology, APCST2015. 2015. pp. 314–9. 112.
• [16] Juanita W, Hank W, Sam A, Shapiro R, Walker J. Foot pressure analysis using the emed in typically developing children and adolescents: a summary of current techniques and typically developing cohort data for comparison with pathology. The Foot 2018;37:28–37.
• [17] Luximon A, Luximon Y. Shoe-last design innovation for better shoe fitting. Comput Ind 2009;60(8):621–8.
• [18] Rangra P, Santos D, Coda A, Jagadamma K. The influence of walking speed and heel height on peak plantar pressure in the forefoot of healthy adults: a pilot study. Clin Res Foot Ankle 2017;5(2):100239–46.
• [19] Wang D, Li Z, Cao L, Balas VE, Dey N, Ashour AS, et al. Image fusion incorporating parameter estimation optimized Gaussian mixture model and fuzzy weighted evaluation system: a case study in time-series plantar pressure data set. IEEE Sens J 2017;17(5):1407–20.
• [20] Franciosa P, Gerbino S, Lanzotti A, Silvestri L. Improving comfort of shoe sole through experiments based on cad-fem modeling. Med Eng Phys 2013;35(1):36–46.
• [21] Horsak B, Heller M, Baca A. Muscle co-contraction around the knee when walking with unstable shoes. J Electromyogr Kinesiol 2015;25(1):175–81.
• [22] Souissi H, Zory R, Bredin J, Gerus P. Comparison of methodologies to assess muscle co-contraction during gait. J Biomech 2017;57:141–5.
• [23] Jacobs DA, Ferris DP. Estimation of ground reaction forces and ankle moment with multiple, low-cost sensors. J Neuroeng Rehabil 2015;12:90.
• [24] Xu W, Yu J. A novel approach to information fusion in multi-source datasets: a granular computing viewpoint. Inform Sci 2017;378:410–23.
• [25] Liu Z, Blasch E, John V. Statistical comparison of image fusion algorithms: recommendations. Inform Fusion 2017;36:251–60.
• [26] Lu Z, Xiang Q, Xu L. An application case study on multi-sensor data fusion system for intelligent process monitoring. Procedia CIRP, Variety Management in Manufacturing, Proceedings of the 47th CIRP Conference on Manufacturing Systems; 2014. p. 721–5. 17.
• [27] Dong L, Yang Q, Wu H, Xiao H, Xu M. High quality multi- spectral and panchromatic image fusion technologies based on curvelet transform. Neurocomputing 2015;159:268–74.
• [28] Wang D, Li Z, Dey N, Ashour AS, Moraru L, Biswas A, et al. Optical pressure sensors based plantar image segmenting using an improved fully convolutional network. Optik 2019;179:99–114.
• [29] Sung WT, Chang KY. Evidence-based multi-sensor information fusion for remote health care systems. Sens Actuators A: Phys 2013;204:1–19.
• [30] Tian T, Sun S, Li N. Multi-sensor information fusion estimators for stochastic uncertain systems with correlated noises. Inform Fusion 2016;27:126–37.
• [31] Liu J, Liu R, Wang Y, Chen J, Yang Y, Ma D. Image denoising searching similar blocks along edge directions. Signal Process: Image Commun 2017;57:33–45.
• [32] Hamid RS, Seyede MH. Image denoising in dual contourlet domain using hidden Markov tree models. Digital Signal Process 2017;67:17–29.
• [33] Liu X, Jing X, Tang G, Wu F, Ge Q. Image denoising using weighted nuclear norm minimization with multiple strategies. Signal Process 2017;135:239–52.
• [34] Choudhury D, Naug A, Ghosh S. Texture and color feature based WLS framework aided skin cancer classification using MSVM and ELM. Proc. IEEE INDICON. 2015. pp. 1–6.
• [35] Al-Angari HM, Khandoker AH, Lee S, Almahmeed W, Safar KSA, Jelinek HF, et al. Novel dynamic peak and distribution plantar pressure measures on diabetic patients during walking. Gait Posture 2017;51:261–7.
• [36] Wang M, Wang X, Fan Z, Chen F, Zhang S, Peng C. Research on feature extraction algorithm for plantar pressure image and gait analysis in stroke patients. J Vis Commun Image Represent 2019;58:525–31.
• [37] Senthilkumar S, Geetha PC. Hidden Markov model based channel selection framework for cognitive radio network. Author links open overlay panel. Comput Electr Eng 2018;65:516–26.
• [38] Huang S, Majid A, Sid-Ahmed MA. A hidden Markov model-based character extraction method. Pattern Recognit 2008;41:2890–900.
• [39] Thanh N, Abbas K, Douglas C, Nahavandi S. Hidden Markov models for cancer classification using gene expression profiles. Inform Sci 2015;316:293–307.
• [40] Zhang P, Li M, Wu Y, Gan L, Liu M, Wang F, et al. Unsupervised multi-class segmentation of SAR images using fuzzy triplet Markov fields model. Pattern Recognit 2012;45:4018–33.
• [41] Rozita R, Hossein P. Breast cancer detection using MRF-based probable texture feature and decision-level fusion-based classification using HMM on thermography images. Pattern Recognit 2016;51:176–86.
• [42] Du J, Li W, Lu K, Xiao B. An overview of multi-modal medical image fusion. Neurocomputing 2016;215:3–20.
• [43] Niranjan PB, Chetty M, Kamruzzaman J. Hidden Markov models incorporating fuzzy measures and integrals for protein sequence identification and alignment. Genomics Proteomics Bioinformatics 2008;6(2):98–110.
• [44] Xie F, Wu B, Hu Y, Wang Y, Jia G, Cheng Y. A generalized interval probability-based optimization method for training generalized hidden Markov model. Signal Process 2014;94:319–29.
• [45] Zhao Q, Li X, Li Y, Zhao X. A fuzzy clustering image segmentation algorithm based on hidden Markov random field models and Voronoi tessellation. Pattern Recognit Lett 2017;85:49–55.
• [46] Rafiul H. A combination of hidden Markov model and fuzzy model for stock market forecasting. Neurocomputing 2009;72:3439–46.
• [47] Tran TD, Michael W. Generalised fuzzy hidden markov models for speech recognition. In: Pal NR, Sugeno M, editors. Proc. AFSS 2002, LNAI 2275. Berlin, Heidelberg: Springer; 2002.
• [48] Harun U, Halife K. Classification of internal carotid artery Doppler signals using fuzzy discrete hidden Markov model. Expert Syst Appl 2011;38:7407–14.
• [49] Ferhat A, Yacine A, Abdelghani C, Mohammed S. Automatic recognition of gait phases using a multiple-regression hidden Markov model. IEEE/ASME Trans Mech 2018;23 (4):1597–607.
• [50] Juri T, Stefano R, Eduardo P, Patanè P, Cappa P. A novel HMM distributed classifier for the detection of gait phases by means of a wearable inertial sensor network. Sensors 2014;14(9):16212–34.
• [51] Pataky TC, Mu T, Bosch K, Rosenbaum D, Goulermas JY. Gait recognition: highly unique dynamic plantar pressure patterns among 104 individuals. J Royal Soc Interface 2012;9 (69):790–800.
• [52] MathWorks Documentation Center. https://ww2.mathworks.cn/help/wavelet/ref/wfusimg. Html.
• [53] Krista A, Yun Z, Peter D. Wavelet based image fusion techniques – an introduction, review and comparison. ISPRS J Photogram Rem Sens 2007;62(4):249–63.
• [54] Gleb Z, Alexey SM. Min–max optimal data encoding and fusion in sensor networks. Automatica 2010;46(9):1546–52.
• [55] Li Z, He T, Cao L, Wu T, McCauley P, Balas VE, et al. Multi- source information fusion model in rule-based Gaussian- shaped fuzzy control inference system incorporating Gaussian density function. J Intell Fuzzy Syst 2015;29:2335–44.
• [56] Harun U, Emre EG, Uçman E, Saraçoglu R. Biomedical system based on the discrete hidden Markov model using the Rocchio – genetic approach for the classification of internal carotid artery Doppler signals. Comput Methods Programs Biomed 2011;103(1):51–60.
• [57] Liu J, Wang Z, Xiao X. A hybrid SVM/DDBHMM decision fusion modeling for robust continuous digital speech recognition. Pattern Recognit Lett 2007;28(8):912–20.
• [58] Ioannis S, Steve P. An introduction to infinite HMMs for single-molecule data analysis. Biophys J 2017;112(10):2021–9.
• [59] Selma B, Clément C, Thierry P. Gesture sequence recognition with one shot learned CRF/HMM hybrid model. Image Vis Comput 2017;61:12–21.
• [60] Zhao X, Zhang J, Chen Y, Li Q, Yang T, Pian C, et al. Promoter recognition based on the maximum entropy hidden Markov model. Comput Biol Med 2014;51:73–81.
• [61] Duan Y, Liu F, Jiao L, Zhao P, Zhang L. SAR Image segmentation based on convolutional-wavelet neural network and markov random field. Pattern Recognit 2017;64:255–67.

Uwagi

PL

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).