Nader EBRAHIMPOUR, Tuğrul ÇAVDAR

Decision-making for small industrial Internet of Things using decision fusion

The industrial Internet of Things (IIoT) is a new field of Internet of Things (IoT) that has gained morepopularity recently in industrial units and makes it possible to access information anywhere and anytime. In otherwords, geographic coordinates cannot prevent obtaining equipment and its data. Today, it is possible to manage andcontrol equipment simply without spending time in an operational area and just by using the IIoT. This system collectsdata from manufacturing and production units by using wireless sensor networks or other networks for classification offault detection. These data are then used after analysis to allow operational decisions to be made in shorter amountsof time. In fact, the IIoT increases the efficiency and accuracy of the “connection, collection, analysis, and operation”cycle. The information collected through different sensors in the IIoT is unreliable and uncertain due to the sensitivity ofthe sensors to noise, failure, and loss of information during transmission. One of the most important techniques offeredto deal with this uncertainty in information is the decision fusion method. Among the decision fusion techniques, theDempster–Shafer and improved Dempster–Shafer theory, which is also known as Yager theory, are efficient and effectiveways to manage the uncertainty and have been used in many types of research. This paper offers an architecture fordecision fusion in a small IIoT using Dempster–Shafer and Yager theories. In this architecture, data collected fromthe desired environment are fed to classifiers for classification. In this architecture, artificial neural networks and adendrogram-based support vector machine are used as classifiers. To increase the accuracy of classifier results, theDempster–Shafer and Yager theories are used to combine these results. To prove the performance, the proposed methodwas applied for detection of faults in an induction motor and human activity detection in an environment. This proposedmethod improved the accuracy of the system and decreased its uncertainty significantly according to obtained resultsfrom these two example use cases.

PDF

___

[1] Ashton K. That ‘internet of things’ thing. RFiD Journal 2011; 22 (7): 97-114.
[2] Fox GC, Kamburugamuve S, Hartman RD. Architecture and measured characteristics of a cloud based internet of things. In: 2012 International Conference on Collaboration Technologies and Systems; Denver, CO, USA; 2012. pp. 6-12.
[3] Uckelmann D, Harrison M, Michahelles F, Architecting the Internet of Things. Berlin, Germany: Springer, 2011.
[4] Miorandi D, Sicari S, De Pellegrini F. Internet of things: Vision, applications and research challenges. Ad Hoc Networks 2012; 10 (7): 1497-1516. doi: 10.1016/j.adhoc.2012.02.016
[5] Islam SR, Kwak D, Kabir MH, Hossain M, Kwak KS. The internet of things for health care: a comprehensive survey. IEEE Access 2015; 3: 678-708. doi: 10.1109/ACCESS.2015.2437951
[6] Beyerer J, Usländer T. Industrial internet of things supporting factory automation. at-Automatisierungstechnik 2016; 64 (9): 697-698. doi: 10.1515/auto-2016-0104
[7] Gilchrist A. Industry 4.0: The Industrial Internet of Things. Bangken, Thailand: Apress, 2016.
[8] Ob WL, DeLand SM, Rutherford BM, Diegert KV, Alvin KF. Estimation of Total Uncertainty in Modeling and Simulation. Sandia Report SAND2000-0824. Albuquerque, NM, USA: Sandia, 2000.
[9] Raol JR. Multi-Sensor Data Fusion with MATLAB. Boca Raton, FL, USA: CRC Press, 2009.
[10] Palumbo F, Gallicchio C, Pucci R, Micheli A. Human activity recognition using multisensor data fusion based on reservoir computing. Journal of Ambient Intelligence and Smart Environments 2016; 8 (2): 87-107. doi: 10.3233/AIS-160372
[11] Liggins M 2nd, Hall D, Llinas J. Handbook of Multisensor Data Fusion: Theory and Practice. Boca Raton, FL, USA: CRC Press, 2017.
[12] Inspection N. Reducing uncertainty in wireless sensor networks. PhD, University of Karlsruhe, Karlsruhe, Germany, 2009.
[13] Jeschke S, Brecher C, Meisen T, Özdemir D, Eschert T. Industrial Internet of Things and cyber manufacturing systems. In: Jeschke S, Brecher C, Song H, Rawat D (editors). Industrial Internet of Things. Cham, Switzerland: Springer, 2017, pp. 3-19.
[14] Dubois D, Prade H. Possibility theory is not fully compositional! A comment on a short note by H.J. Greenberg. Fuzzy Sets and Systems 1998; 95 (1): 131-134. doi: 10.1016/S0165-0114(97)00204-2
[15] Krishnasamy L, Khan F, Haddara M. Development of a risk-based maintenance (RBM) strategy for a power-generating plant. Journal of Loss Prevention in the Process Industries 2005; 18 (2): 69-81. doi: 10.1016/j.jlp.2005.01.002
[16] Joslyn CA. Possibilistic processes for complex systems modeling. PhD, State University of New York at Binghamton, Binghamton, NY, USA, 1994.
[17] Shafer G. A Mathematical Theory of Evidence. Princeton, NJ, USA: Princeton University Press, 1976.
[18] Dempster AP. Upper and lower probabilities induced by a multivalued mapping. In: Yager R, Liu L (editors). Classic Works of the Dempster-Shafer Theory of Belief Functions. Berlin, Germany: Springer, 2008, pp. 57-72.
[19] Smets P, Kennes R. The transferable belief model. Artificial Intelligence 1994; 66 (2): 191-234. doi: 0004- 3702(94)90026-4
[20] Berger JO. Statistical Decision Theory and Bayesian Analysis. Durham, NC, USA: Springer Science and Business Media, 2013.
[21] Sentz K, Ferson S. Combination of Evidence in Dempster-Shafer Theory. Albuquerque, New Mexico, USA: Sandia National Laboratories, 2002.
[22] Lu T, Neng W. Future Internet: The Internet of Things. In: 2010 3rd International Conference on Advanced Computer Theory and Engineering; Chengdu, China; 2010. p. V5-376.
[23] Kaliczynska M, Dabek P. Value of the internet of things for the industry – an overview. In: Awrejcewicz J, Szewczyk R, Trojnacki M, Kaliczynska M (editors). Mechatronics - Ideas for Industrial Application. Cham, Switzerland: Springer, 2015, pp. 51-63.
[24] Verdouw CN, Beulens AJ, Reijers HA, van der Vorst JG. A control model for object virtualization in supply chain management. Computers in Industry 2015; 68: 116-131. doi: 10.1016/j.compind.2014.12.011
[25] Kubler S, Främling K, Derigent W. P2P data synchronization for product lifecycle management. Computers in Industry 2015; 66: 82-98. doi: 10.1016/j.compind.2014.10.009
[26] Ondemir O, Gupta SM. Quality management in product recovery using the Internet of Things: an optimization approach. Computers in Industry 2014; 65 (3): 491-504. doi: 10.1016/j.compind.2013.11.006
[27] Jamison J, Snow C. An architecture for customer experience management based on the Internet of Things. IBM Journal of Research and Development 2014; 58 (5/6): 1-15. doi: 10.1147/JRD.2014.2346593
[28] Tsai CW, Lai CF, Chiang MC, Yang LT. Data mining for internet of things: a survey. IEEE Communications Surveys and Tutorials 2013; 16 (1): 77-97. doi: 10.1109/SURV.2013.103013.00206
[29] Wu Q, Ding G, Xu Y, Feng S, Du Z et al. Cognitive internet of things: a new paradigm beyond connection. IEEE Internet of Things Journal 2014; 1 (2): 129-143. doi: 10.1109/JIOT.2014.2311513
[30] Li S, Oikonomou G, Tryfonas T, Chen TM, Da Xu L. A distributed consensus algorithm for decision making in service-oriented internet of things. IEEE Transactions on Industrial Informatics 2014; 10 (2): 1461-1468. doi: 10.1109/TII.2014.2306331
[31] Schlesinger M, Parisi D. The agent-based approach: a new direction for computational models of development. Developmental Review 2001; 21 (1): 121-146. doi: 10.1006/drev.2000.0520
[32] Schlesinger M, McMurray B. The past, present, and future of computational models of cognitive development. Cognitive Development 2012; 27 (4): 326-348. doi: 10.1016/j.cogdev.2012.07.002
[33] Shultz TR. A constructive neural-network approach to modeling psychological development. Cognitive Development 2012; 27 (4): 383-400. doi: 10.1016/j.cogdev.2012.08.002
[34] Easley D, Kleinberg J. Networks, Crowds, And Markets: Reasoning About a Highly Connected World. New York, NY, USA: Cambridge University Press, 2010.
[35] Kaur N, Sood SK. Cognitive decision making in smart industry. Computers in Industry 2015; 74: 151-161. doi: 10.1016/j.compind.2015.06.006
[36] Alam F, Mehmood R, Katib I, Albogami NN, Albeshri A. Data fusion and iot for smart ubiquitous environments: a survey. IEEE Access 2017; 5: 9533-9554. doi: 10.1109/ACCESS.2017.2697839
[37] Recommendation ITU-T Y.2060. Overview of the Internet of Things. ITU-T Study Group 13, 2012.
[38] Colina AL, Vives A, Bagula A, Zennaro M, Pietrosemoli E. Internet of Things (IoT) in 5 Days. Autoedición, 2016 (http://www.iet.unipi.it/c.vallati/files/IoTinfivedays-v1.1.pdf).
[39] Guyon I, Elisseeff A. An introduction to feature extraction. In: Guyon I, Nikravesh M, Gunn S, Zadeh LA (editors). Feature Extraction: Foundations and Applications. Berlin, Germany: Springer, 2006, pp. 1-25.
[40] Ripley BD. Pattern Recognition and Neural Networks. Cambridge, UK: Cambridge University Press, 2007.
[41] Wang JS, Lee CG. Self-adaptive neuro-fuzzy inference systems for classification applications. IEEE Transactions on Fuzzy Systems 2002; 10 (6): 790-802. doi: 10.1109/TFUZZ.2002.805880
[42] Bennani Y, Benabdeslem K. Dendrogram-based SVM for multi-class classification. CIT Journal of Computing and Information Technology 2006; 14 (4): 283-289. doi: 10.1109/ITI.2006.1708473
[43] Gustafson DE, Kessel WC. Fuzzy clustering with a fuzzy covariance matrix. In: 1978 IEEE Conference on Decision and Control including the 17th Symposium on Adaptive Processes; San Diego, CA, USA; 1979. pp. 761-766.
[44] Steinwart I, Christmann A. Support Vector Machines. Durham, NC, USA: Springer Science and Business Media, 2008.
[45] Duda RO, Hart PE, Stork DG. Pattern Classification and Scene Analysis. 2nd ed. Hoboken, NJ, USA: Wiley Interscience, 1995.
[46] Rosenblatt F. Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms. Ithaca, NY, USA: Cornell Aeronautical Lab, 1961.
[47] Yegnanarayana B. Artificial Neural Networks. New Delhi, India: PHI Learning Pvt. Ltd., 2009.
[48] Castanedo F. A review of data fusion techniques. Scientific World Journal 2013; 2013: 704504. doi: 10.1155/2013/704504
[49] Huynh VN. Discounting and combination scheme in evidence theory for dealing with conflict in information fusion. In: Springer 2009 International Conference on Modeling Decisions for Artificial Intelligence; Berlin, Germany; 2009. pp. 217-230.
[50] Karmakar S, Chattopadhyay S, Mitra M, Sengupta S. Induction motor and faults. In: Karmakar S, Chattopadhyay S, Mitra M, Sengupta S (editors). Induction Motor Fault Diagnosis: Approach through Current Signature Analysis. Singapore: Springer, 2016, pp. 7-28.