ORIGINAL ARTICLE An integrated fuzzy DEA algorithm for efficiency assessment and optimization of wireless communication sectors with ambiguous data Ali Azadeh & Seyed Mohammad Asadzadeh & Ali Bukhari & Hamid Reza Izadbakhsh Received: 25 November 2009 / Accepted: 17 May 2010 / Published online: 6 June 2010 # Springer-Verlag London Limited 2010 Abstract This paper presents an integrated algorithm for efficiency assessment of wireless communication sectors with imprecise data. It is based on standard indicators as defined by the International Telecommunication Union (ITU). It uses data envelopment analysis (DEA) and fuzzy data envelopment analysis (FDEA) for efficiency assess- ment and optimization. The DEA models are verified and validated by principal component analysis and Spearman correlation technique. Eight standard indicators pertaining to wireless communication sector were identified from the ITU database. To present the usability of the algorithm, data for 42 countries with respect to three inputs and five outputs were collected through ITU. The results show weak and strong points of each country identifying inputs or outputs having a major impact on performance. Finally, FDEA is used for the performance assessment of wireless communication industry in seven different regions, namely, Central and South Africa, Central America, Central Asia, East Asia, European Union, Middle East, and North Africa. This is the first study that uses DEA and FDEA for the performance assessment and optimization of the wireless communication sector. Keywords Fuzzy data envelopment analysis . DEA . Wireless communication . Efficiency . Principal component analysis . Assessment . Optimization . Ambiguous data 1 Introduction Major factors influencing the overall productivity of an organization are identified as technology, machinery, management, personnel, and rules and procedures [4, 5, 36]. Managerial and economic factors play an important role in the overall performance of a particular industrial sector. The need for an integrated approach for the continuous assessment and improvement of communication sectors based on managerial performance has become essential. Continuous assessment requires classifications and taxonomy to be introduced to enhance knowledge and understanding about the behavior of communication systems. Consequently, it will enable predictions to be made about organizational system behavior. References in this regard are Azadeh and Ebrahimipour [7], Bolden et al. [9], Hulten [17], McCarthy [27], and Schmitt et al. [33]. In a real-world situation, there exist peer groups of decision-making units (DMUs) such as communication systems which use various resources (inputs) to generate various results (outputs). We want to know the overall performance of communication systems by their inputs A. Azadeh (*) : S. M. Asadzadeh Department of Industrial Engineering, Department of Engineering Optimization Research and Center of Excellence for Intelligent-Based Experimental Mechanics, College of Engineering, University of Tehran, Tehran P.O. Box 11365-4563, Iran e-mail: aazadeh@ut.ac.ir S. M. Asadzadeh e-mail: smasadzadeh@ut.ac.ir A. Bukhari Department of Telecommunication, A. James Clark School of Engineering, University of Maryland, College Park, MD, USA e-mail: abukhari@umd.edu H. R. Izadbakhsh Department of Industrial Engineering, Iran University of Science and Technology, Young Researchers Club of Azad University and Payame Noor University, Tehran, Iran e-mail: hizadbakhsh@iust.ac.ir Int J Adv Manuf Technol (2011) 52:805–819 DOI 10.1007/s00170-010-2741-0