An integrated DEMATEL and Fuzzy ANP techniques for evaluation and selection of outsourcing provider for a telecommunication company

In recent years, strategy aspects related to core competency, risk analysis and organizational flexibility especially have been growing. This trend has led researchers and industries to become more interested in the multi-criteria decision making (MCDM) models for selecting outsourcing providers. The efficiency of decision-making mostly depends on the ability of decision-makers analyzing the complex cause and effect relationship between criteria and taking effective actions based on the analysis. Using an analytical method to select the most eligible outsourcing provider is significant for a company which desires to improve its competitiveness. In this study, a fuzzy integrated multi-criteria decision making method for evaluation and determination of an outsourcing provider for a telecommunication company is analyzed by using DEMATEL and Fuzzy ANP multi-criteria decision making techniques. First, DEMATEL method is used in order to put forward the interrelationship among the main criteria which are determined in the study for outsourcing selection process. Then, local weights of the sub-criteria and sub-subcriteria are calculated by Fuzzy ANP approach on the basis of cause-effect relationships that are exposed through DEMATEL method. The local weights are put into ANP supermatrix, and calculations are implemented to select out the most eligible outsourcing provider.     

Smith模糊PID匀速升温控制策略研究

针对电加热炉匀速升温过程模型建立困难、调节过程滞后等问题,提出了一种基于炉体散热补偿的Smith模糊PID控制算法。通过炉体散热补偿建立针对被控量升温速率的一阶线性纯滞后模型;采用Smith预估器消除纯滞后特性带来的影响,提高系统的稳定性,加快调节过程;引入模糊PID控制,克服Smith预估补偿环节鲁棒性差的弱点,实现参数的自适应调整,并提高了稳态精度,实现了高精度的匀速升温控制。试验结果表明,该控制策略的控制偏差低于5%,明显优于常规PID控制。     

彩色图像分割的FCM初始化方法

针对传统模糊C-均值聚类方法所存在的过度依赖初始聚类中心、计算复杂度高等问题,提出一种新的FCM初始化方法.首先,使用维纳滤波分别对图像的R、G、B分量进行预处理,待转换为LAB色彩空间后,通过二次分水岭方法获取图像的封闭区域,并计算各区域的质心;其次,利用自适应无监督的方法对质心进行筛选和合并,将合并结果作为FCM的初始聚类中心;最后,使用FCM方法进行分割.实验结果表明,该方法不仅能够获得较准确的聚类中心,减少了迭代次数和运算时间,而且能够更好地实现图像的准确分割.     

Fuzzy decision fusion of complementary experts based on evolutionary cepstral coefficients for phoneme recognition

Optimal representation of acoustic features is an ongoing challenge in automatic speech recognition research. As an initial step toward this purpose, optimization of filterbanks for the cepstral coefficient using evolutionary optimization methods is proposed in some approaches. However, the large number of optimization parameters required by a filterbank makes it difficult to guarantee that an individual optimized filterbank can provide the best representation for phoneme classification. Moreover, in many cases, a number of potential solutions are obtained. Each solution presents discrimination between specific groups of phonemes. In other words, each filterbank has its own particular advantage. Therefore, the aggregation of the discriminative information provided by filterbanks is demanding challenging task. In this study, the optimization of a number of complementary filterbanks is considered to provide a different representation of speech signals for phoneme classification using the hidden Markov model (HMM). Fuzzy information fusion is used to aggregate the decisions provided by HMMs. Fuzzy theory can effectively handle the uncertainties of classifiers trained with different representations of speech data. In this study, the output of the HMM classifiers of each expert is fused using a fuzzy decision fusion scheme. The decision fusion employed a global and local confidence measurement to formulate the reliability of each classifier based on both the global and local context when making overall decisions. Experiments were conducted based on clean and noisy phonetic samples. The proposed method outperformed conventional Mel frequency cepstral coefficients under both conditions in terms of overall phoneme classification accuracy. The fuzzy fusion scheme was shown to be capable of the aggregation of complementary information provided by each filterbank.     

Mining fuzzy temporal association rules by item lifespans

Data mining is the process of extracting desirable knowledge or interesting patterns from existing databases for specific purposes. In real-world applications, transactions may contain quantitative values and each item may have a lifespan from a temporal database. In this paper, we thus propose a data mining algorithm for deriving fuzzy temporal association rules. It first transforms each quantitative value into a fuzzy set using the given membership functions. Meanwhile, item lifespans are collected and recorded in a temporal information table through a transformation process. The algorithm then calculates the scalar cardinality of each linguistic term of each item. A mining process based on fuzzy counts and item lifespans is then performed to find fuzzy temporal association rules. Experiments are finally performed on two simulation datasets and the foodmart dataset to show the effectiveness and the efficiency of the proposed approach.     

Group decision making based on incomplete multiplicative and fuzzy preference relations

The main aim of this paper is to investigate the group decision making on incomplete multiplicative and fuzzy preference relations without the requirement of satisfying reciprocity property. This paper introduces a new characterization of the multiplicative consistency condition, based on which a method to estimate unknown preference values in an incomplete multiplicative preference relation is proposed. Apart from the multiplicative consistency property among three known preference values, the method proposed also takes the multiplicative consistency property among more than three values into account. In addition, two models for group decision making with incomplete multiplicative preference relations and incomplete fuzzy preference relations are presented, respectively. Some properties of the collective preference relation are further discussed. Numerical examples are provided to make a discussion and comparison with other similar methods.     

A fuzzy framework to evaluate service quality in the healthcare industry: An empirical case of public hospital service evaluation in Sicily

A novel fuzzy evaluation framework is applied in this study to evaluate service quality in the public healthcare sector. In particular, the proposed framework is based on the ServQual disconfirmation paradigm and incorporates the Analytic Hierarchy Process (AHP) method to elicit reliable estimations of service quality expectations. Moreover, degrees of uncertainty, subjectivity and vagueness on the part of stakeholders are addressed via linguistic evaluation scales parameterized by triangular fuzzy numbers. With reference to nine relevant public hospitals in the Sicilian Region (Italy), a detailed case study evaluating four core service criteria and 15 fundamental service items is conducted so as to discern dissatisfying aspects regarding the public healthcare service in the Region. Dissatisfaction reasons with the provided service are identified in the analysis as well, further demonstrating the effectiveness of the proposed approach.     

On type-reduction of type-2 fuzzy sets: A review

As an undetachable module of type-2 (T2) fuzzy computations and reasoning, type-reduction methods play an important role in various fuzzy disciplines including fuzzy logic systems and fuzzy clustering. Importance of type-reduction techniques lies in the fact that they are the main tools for collecting the entire inherent vagueness of the data. Therefore, type-reduction methods form the output of type-2 fuzzy sets (T2 FSs) as the representative of the entire uncertainty in a given space. Hence, their accuracy, precision, and performance speed is of much interest. This paper, presents a comprehensive review on various type-reduction and defuzzification strategies for general and interval type-2 fuzzy sets and systems. It is tried to analyze the existing approaches from different point of views accompanied by extensive comparisons on different features of type-reduction methods to facilitate further research studies by the fuzzy community.     

A genetic fuzzy system based optimized zone based energy efficient routing protocol for mobile sensor networks (OZEEP)

Wireless sensor networks have become increasingly popular because of their ability to cater to multifaceted applications without much human intervention. However, because of their distributed deployment, these networks face certain challenges, namely, network coverage, continuous connectivity and bandwidth utilization. All of these correlated issues impact the network performance because they define the energy consumption model of the network and have therefore become a crucial subject of study. Well-managed energy usage of nodes can lead to an extended network lifetime. One way to achieve this is through clustering. Clustering of nodes minimizes the amount of data transmission, routing delay and redundant data in the network, thereby conserving network energy. In addition to these advantages, clustering also makes the network scalable for real world applications. However, clustering algorithms require careful planning and design so that balanced and uniformly distributed clusters are created in a way that the network lifetime is enhanced. In this work, we extend our previous algorithm, titled the zone-based energy efficient routing protocol for mobile sensor networks (ZEEP). The algorithm we propose optimizes the clustering and cluster head selection of ZEEP by using a genetic fuzzy system. The two-step clustering process of our algorithm uses a fuzzy inference system in the first step to select optimal nodes that can be a cluster head based on parameters such as energy, distance, density and mobility. In the second step, we use a genetic algorithm to make a final choice of cluster heads from the nominated candidates proposed by the fuzzy system so that the optimal solution generated is a uniformly distributed balanced set of clusters that aim at an enhanced network lifetime. We also study the impact and dominance of mobility with regard to the variables. However, before we arrived at a GFS-based solution, we also studied fuzzy-based clustering using different membership functions, and we present our understanding on the same. Simulations were carried out in MATLAB and ns2. The results obtained are compared with ZEEP.