Evaluating Customer Satisfaction: Linguistic Reasoning by Fuzzy Artificial Neural Networks

被引：2

作者：

Mashinchi, Reza ^{[1
]}

Selamat, Ali ^{[1
,3
]}

Ibrahim, Suhaimi ^{[2
]}

Krejcar, Ondrej ^{[3
]}

Penhaker, Marek ^{[4
]}

机构：

[1] Univ Teknol Malaysia, Fac Comp, Johor Baharu 81310, Johor, Malaysia

[2] Univ Teknol Malaysia, Adv Informat Sch, Kuala Lumpur 54100, Malaysia

[3] Univ Hradec Kralove, Fac Informat & Management, Ctr Basic & Appl Res, Hradec Kralove 50003, Czech Republic

[4] VSB Tech Univ Ostrava, Fac Elect Engn & Comp Sci, Dept Cybernet & Biomed Engn, Ostrava 70833, Czech Republic

来源：

NEW TRENDS IN INTELLIGENT INFORMATION AND DATABASE SYSTEMS | 2015年 / 598卷

关键词：

Prediction; customer satisfactory index (CSI); rich data; computing with words; genetic algorithms; fuzzy artificial neural networks; GENETIC ALGORITHM; BACKPROPAGATION;

D O I：

10.1007/978-3-319-16211-9_10

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Customer satisfaction is a measure of how a company meets or surpasses customers' expectations. It is seen as a key element in business strategy; and therefore, enhancing the methods to evaluate the satisfactory level is worth studying. Collecting rich data to know the customers' opinion is often encapsulated in verbal forms, or linguistic terms, which requires proper approaches to process them. This paper proposes and investigates the application of fuzzy artificial neural networks (FANNs) to evaluate the level of customer satisfaction. Genetic algorithm (GA) and back-propagation algorithm (BP) adjust the fuzzy variables of FANN. To investigate the performances of GA- and BP-based FANNs, we compare the results of each algorithm in terms of obtained error on each alpha-cut of fuzzy values.

引用

页码：91 / 100

页数：10

共 50 条

[21] Evaluating artificial neural networks for medical applications
Burke, HB
[J]. 1997 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, 1997, : 2494 - 2496
[22] Evaluating customer satisfaction using fuzzy model based on flexible expert weight
Huang, T. T.
[J]. 2007 IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL ENGINEERING AND ENGINEERING MANAGEMENT, VOLS 1-4, 2007, : 1700 - 1703
[23] Artificial fuzzy neural networks in civil engineering
Rajasekaran, S
Febin, MF
Ramasamy, JV
[J]. COMPUTERS & STRUCTURES, 1996, 61 (02) : 291 - 302
[24] Modeling customer satisfaction in microfinance sector: A fuzzy Bayesian networks approach
Alaoui, Youssef Lamrani
Tkiouat, Mohamed
[J]. INTERNATIONAL JOURNAL OF ENGINEERING BUSINESS MANAGEMENT, 2019, 11
[25] Evaluating Students Satisfaction in Online Postgraduate Courses Through a Fuzzy Linguistic Approach
Zulueta-Veliz, Yeleny
Estrada-Velazco, Aylin
Tabares-Leon, Yoisbel
[J]. INTERNATIONAL JOURNAL OF E-COLLABORATION, 2022, 18 (01)
[26] Using artificial neural networks for constraint satisfaction problem
Popescu, I
[J]. NONLINEAR ANALYSIS-THEORY METHODS & APPLICATIONS, 1997, 30 (05) : 2937 - 2944
[27] Predicting surgical satisfaction using artificial neural networks
Rughani, Anand I.
Dumont, Travis M.
Tranmer, Bruce I.
[J]. JOURNAL OF NEUROSURGERY-SPINE, 2014, 20 (03) : 298 - 299
[28] Modeling the teacher job satisfaction by artificial neural networks
Seok, Bang Won
Wee, Kuk-hoan
Park, Ju-young
Anil Kumar, D.
Reddy, N. S.
[J]. SOFT COMPUTING, 2021, 25 (17) : 11803 - 11815
[29] Modeling the teacher job satisfaction by artificial neural networks
Bang Won Seok
Kuk-hoan Wee
Ju-young Park
D. Anil Kumar
N. S. Reddy
[J]. Soft Computing, 2021, 25 : 11803 - 11815
[30] Evaluating users' satisfaction in packet networks using random neural networks
Rubino, Gerardo
Tirilly, Pierre
Varela, Martin
[J]. ARTIFICIAL NEURAL NETWORKS - ICANN 2006, PT 1, 2006, 4131 : 303 - 312

← 1 2 3 4 5 →