Search results

1 – 8 of 8
To view the access options for this content please click here
Article
Publication date: 25 November 2013

Alireza Fathi and Ahmad Mozaffari

The purpose of the current investigation is to design a robust and reliable computational framework to effectively identify the nonlinear behavior of shape memory alloy…

Abstract

Purpose

The purpose of the current investigation is to design a robust and reliable computational framework to effectively identify the nonlinear behavior of shape memory alloy (SMA) actuators, as one of the most applicable types of actuators in engineering and industry. The motivation of proposing such an intelligent paradigm emanates in the pursuit of fulfilling the necessity of devising a simple yet effective identification system capable of modeling the hysteric dynamical respond of SMA actuators.

Design/methodology/approach

To address the requirements of designing a pragmatic identification system, the authors integrate a set of fast yet reliable intelligent methodologies and provide a predictive tool capable of realizing the nonlinear hysteric behavior of SMA actuators in a computationally efficient fashion. First, the authors utilize the governing equations to design a gray box Hammerstein-Wiener identifier model. At the next step, they adopt a computationally efficient metaheuristic algorithm to elicit the optimum operating parameters of the gray box identifier.

Findings

Applying the proposed hybrid identifier framework allows the authors to find out its advantages in modeling the behavior of SMA actuator. Through different experiments, the authors conclude that the proposed identifier can be used for identification of highly nonlinear dynamic behavior of SMA actuators. Furthermore, by extending the conclusions and expounding the obtained results, one can easily infer that such a hybrid method may be conveniently applied to model other engineering phenomena that possess dynamic nonlinear reactions. Based on the exerted experiments and implementing the method, the authors come to the conclusion that integrating the power of metaheuristic exploration/exploitation with gray box identifier results a predictive paradigm that much more computationally efficient as compared with black box identifiers such as neural networks. Additionally, the derived gray box method has a higher degree of preference over the black box identifiers, as it allows a manipulated expert to extract the knowledge of the system at hand.

Originality/value

The originality of the research paper is twofold. From the practical (engineering) point of view, the authors built a prototype biased-spring SMA actuator and carried out several experiments to ascertain and validate the parameters of the model. From the computational point of view, the authors seek for designing a novel identifier that overcomes the main flaws associated with the performance of black-box identifiers that are the lack of a mean for extracting the governing knowledge of the system at hand, and high computational expense pertinent to the structure of black-box identifiers.

Details

International Journal of Intelligent Computing and Cybernetics, vol. 6 no. 4
Type: Research Article
ISSN: 1756-378X

Keywords

To view the access options for this content please click here
Article
Publication date: 4 November 2014

Ahmad Mozaffari, Nasser Lashgarian Azad and Alireza Fathi

The purpose of this paper is to demonstrate the applicability of swarm and evolutionary techniques for regularized machine learning. Generally, by defining a proper…

Abstract

Purpose

The purpose of this paper is to demonstrate the applicability of swarm and evolutionary techniques for regularized machine learning. Generally, by defining a proper penalty function, regularization laws are embedded into the structure of common least square solutions to increase the numerical stability, sparsity, accuracy and robustness of regression weights. Several regularization techniques have been proposed so far which have their own advantages and disadvantages. Several efforts have been made to find fast and accurate deterministic solvers to handle those regularization techniques. However, the proposed numerical and deterministic approaches need certain knowledge of mathematical programming, and also do not guarantee the global optimality of the obtained solution. In this research, the authors propose the use of constraint swarm and evolutionary techniques to cope with demanding requirements of regularized extreme learning machine (ELM).

Design/methodology/approach

To implement the required tools for comparative numerical study, three steps are taken. The considered algorithms contain both classical and swarm and evolutionary approaches. For the classical regularization techniques, Lasso regularization, Tikhonov regularization, cascade Lasso-Tikhonov regularization, and elastic net are considered. For swarm and evolutionary-based regularization, an efficient constraint handling technique known as self-adaptive penalty function constraint handling is considered, and its algorithmic structure is modified so that it can efficiently perform the regularized learning. Several well-known metaheuristics are considered to check the generalization capability of the proposed scheme. To test the efficacy of the proposed constraint evolutionary-based regularization technique, a wide range of regression problems are used. Besides, the proposed framework is applied to a real-life identification problem, i.e. identifying the dominant factors affecting the hydrocarbon emissions of an automotive engine, for further assurance on the performance of the proposed scheme.

Findings

Through extensive numerical study, it is observed that the proposed scheme can be easily used for regularized machine learning. It is indicated that by defining a proper objective function and considering an appropriate penalty function, near global optimum values of regressors can be easily obtained. The results attest the high potentials of swarm and evolutionary techniques for fast, accurate and robust regularized machine learning.

Originality/value

The originality of the research paper lies behind the use of a novel constraint metaheuristic computing scheme which can be used for effective regularized optimally pruned extreme learning machine (OP-ELM). The self-adaption of the proposed method alleviates the user from the knowledge of the underlying system, and also increases the degree of the automation of OP-ELM. Besides, by using different types of metaheuristics, it is demonstrated that the proposed methodology is a general flexible scheme, and can be combined with different types of swarm and evolutionary-based optimization techniques to form a regularized machine learning approach.

Details

International Journal of Intelligent Computing and Cybernetics, vol. 7 no. 4
Type: Research Article
ISSN: 1756-378X

Keywords

To view the access options for this content please click here
Article
Publication date: 4 March 2014

Ahmad Mozaffari, Alireza Fathi and Saeed Behzadipour

The purpose of this paper is to apply a hybrid neuro-fuzzy paradigm called self-organizing neuro-fuzzy multilayered classifier (SONeFMUC) to classify the operating faults…

Abstract

Purpose

The purpose of this paper is to apply a hybrid neuro-fuzzy paradigm called self-organizing neuro-fuzzy multilayered classifier (SONeFMUC) to classify the operating faults of a hydraulic system. The main motivation behind the use of SONeFMUC is to attest the capabilities of neuro-fuzzy classifier for handling the difficulties associated with fault diagnosis of hydraulic circuits.

Design/methodology/approach

In the proposed methodology, first, the neuro-fuzzy nodes at each layer of the SONeFMUC are trained separately using two well-known bio-inspired algorithms, i.e. a semi deterministic method with random walks called co-variance matrix adaptation evolutionary strategy (CMA-ES) and a swarm-based explorer with adaptive fuzzified parameters (SBEAFP). Thereafter, a revised version of the group method data handling (GMDH) policy that uses the Darwinian concepts such as truncation selection and elitism is engaged to connect the nodes of different layers in an effective manner.

Findings

Based on comparative numerical experiments, the authors conclude that integration of neuro-fuzzy method and bio-inspired supervisor results in a really powerful classification tool beneficial for uncertain environments. It is proved that the method outperforms some well-known classifiers such as support vector machine (SVM) and particle swarm optimization-based SVM (PSO-SVM). Besides, it is indicated that an efficient bio-inspired method can effectively adjust the constructive parameters of the multi-layered neuro-fuzzy classifier. For the case, it is observed that designing a fuzzy controller for PSO predisposes it to effectively balance the exploration/exploitation capabilities, and consequently optimize the structure of SONeFMUC.

Originality/value

The originality of the paper can be considered from both numerical and practical points of view. The signals obtained through the data acquisition possess six different features in order for the hydraulic system to undergo four types of faults, i.e. cylinder fault, pump fault, valve leakage fault and rupture of the piping system. Besides, to elaborate on the authenticity and efficacy of the proposed method, its performance is compared with well-known rival techniques.

Details

International Journal of Intelligent Computing and Cybernetics, vol. 7 no. 1
Type: Research Article
ISSN: 1756-378X

Keywords

To view the access options for this content please click here
Article
Publication date: 9 March 2015

Ahmad Mozaffari, Nasser L. Azad and Alireza Fathi

The purpose of this paper is to probe the potentials of computational intelligence (CI) and bio-inspired computational tools for designing a hybrid framework which can…

Abstract

Purpose

The purpose of this paper is to probe the potentials of computational intelligence (CI) and bio-inspired computational tools for designing a hybrid framework which can simultaneously design an identifier to capture the underlying knowledge regarding a given plug-in hybrid electric vehicle’s (PHEVs) fuel cost and optimize its fuel consumption rate. Besides, the current investigation aims at elaborating the effectiveness of Pareto-based multiobjective programming for coping with the difficulties associated with such a tedious automotive engineering problem.

Design/methodology/approach

The hybrid intelligent tool is implemented in two different levels. The hyper-level algorithm is a Pareto-based memetic algorithm, known as the chaos-enhanced Lamarckian immune algorithm (CLIA), with three different objective functions. As a hyper-level supervisor, CLIA tries to design a fast and accurate identifier which, at the same time, can handle the effects of uncertainty as well as use this identifier to find the optimum design parameters of PHEV for improving the fuel economy.

Findings

Based on the conducted numerical simulations, a set of interesting points are inferred. First, it is observed that CI techniques provide us with a comprehensive tool capable of simultaneous identification/optimization of the PHEV operating features. It is concluded that considering fuzzy polynomial programming enables us to not only design a proper identifier but also helps us capturing the undesired effects of uncertainty and measurement noises associated with the collected database.

Originality/value

To the best knowledge of the authors, this is the first attempt at implementing a comprehensive hybrid intelligent tool which can use a set of experimental data representing the behavior of PHEVs as the input and yields the optimized values of PHEV design parameters as the output.

Details

International Journal of Intelligent Computing and Cybernetics, vol. 8 no. 1
Type: Research Article
ISSN: 1756-378X

Keywords

To view the access options for this content please click here
Article
Publication date: 8 June 2015

Ahmad Mozaffari, Nasser L. Azad and Alireza Fathi

The purpose of this paper is to examine the structural and computational potentials of a powerful class of neural networks (NNs), called multiple-valued logic neural…

Abstract

Purpose

The purpose of this paper is to examine the structural and computational potentials of a powerful class of neural networks (NNs), called multiple-valued logic neural networks (MVLNN), for predicting the behavior of phenomenological systems with highly nonlinear dynamics. MVLNNs are constructed based on the integration of a number of neurons working based on the principle of multiple-valued logics. MVLNNs possess some particular features, namely complex-valued weights, input, and outputs coded by kth roots of unity, and a continuous activation as a mean for transferring numbers from complex spaces to trigonometric spaces, which distinguish them from most of the existing NNs.

Design/methodology/approach

The presented study can be categorized into three sections. At the first part, the authors attempt at providing the mathematical formulations required for the implementation of ARX-based MVLNN (AMVLNN). In this context, it is indicated that how the concept of ARX can be used to revise the structure of MVLNN for online applications. Besides, the stepwise formulation for the simulation of Chua’s oscillatory map and multiple-valued logic-based BP are given. Through an analysis, some interesting characteristics of the Chua’s map, including a number of possible attractors of the state and sequences generated as a function of time, are given.

Findings

Based on a throughout simulation as well as a comprehensive numerical comparative study, some important features of AMVLNN are demonstrated. The simulation results indicate that AMVLNN can be employed as a tool for the online identification of highly nonlinear dynamic systems. Furthermore, the results show the compatibility of the Chua’s oscillatory system with BP for an effective tuning of the synaptic weights. The results also unveil the potentials of AMVLNN as a fast, robust, and efficient control-oriented model at the heart of NMPC control schemes.

Originality/value

This study presents two innovative propositions. First, the structure of MVLNN is modified based on the concept of ARX system identification programming to suit the base structure for coping with chaotic and highly nonlinear systems. Second, the authors share the findings about the learning characteristics of MVLNNs. Through an exhaustive comparative study and considering different rival methodologies, a novel and efficient double-stage learning strategy is proposed which remarkably improves the performance of MVLNNs. Finally, the authors describe the outline of a novel formulation which prepares the proposed AMVLNN for applications in NMPC controllers for dynamic systems.

Details

International Journal of Intelligent Computing and Cybernetics, vol. 8 no. 2
Type: Research Article
ISSN: 1756-378X

Keywords

To view the access options for this content please click here
Article
Publication date: 11 February 2019

Shahrooz Fathi Ajirlo, Alireza Amirteimoori and Sohrab Kordrostami

The purpose of this paper is to propose a modified model in multi-stage processes when there are intermediate measures between the stages and in this sense, the new…

Abstract

Purpose

The purpose of this paper is to propose a modified model in multi-stage processes when there are intermediate measures between the stages and in this sense, the new efficiency scores are more accurate. Conventional data envelopment analysis (DEA) models disregard the internal structures of peer decision-making units (DMUs) in evaluating their relative efficiency. Such an approach would cause managers to lose important DMU information. Therefore, in multistage processes, traditional DEA models encounter problems when intermediate measures are used for efficiency evaluation.

Design/methodology/approach

In this study, two-stage additive integer-valued DEA models were proposed. Three models were proposed for measuring inefficiency slacks in each stage and in the system as a whole.

Findings

Three models were proposed for measuring inefficiency slacks in each stage and in the system as a whole.

Originality/value

The advantage of the proposed models for multi-stage systems is that they can accurately determine the stages with the greatest weaknesses/strengths. By introducing an applied case in the Iranian power industry, the paper demonstrated the applications and advantages of the proposed models.

Details

Journal of Modelling in Management, vol. 14 no. 1
Type: Research Article
ISSN: 1746-5664

Keywords

To view the access options for this content please click here
Article
Publication date: 28 January 2020

Nan Jiang, Erlin Tian, Fattaneh Daneshmand Malayeri and Alireza Balali

A fundamental concept of the smart city is to get the right information at the right place to make city-related decisions easier and quicker. The main goal of supply chain…

Abstract

Purpose

A fundamental concept of the smart city is to get the right information at the right place to make city-related decisions easier and quicker. The main goal of supply chain management (SCM) systems is to enhance the supply chain process for delivering the identified products to customers correctly in distributed organizations. In addition, new IT infrastructure such as cloud-based systems and internet of things (IoT) have changed many organizations and firms. Hence, this study aims to assess the factors that contribute to the success of SCM systems.

Design/methodology/approach

In this paper, the usage of urban knowledge, urban intelligent transportation systems and IT infrastructure was considered as a key factor for the success of SCM systems. For assessing the features of the model, a comprehensive questionnaire was designed. The survey questionnaires were sent to critical informers who are practical heads associated with SCM and urbanism. Of these, 315 usable responses were received, resulting in a response rate of 82.03%. The data were examined using Smart-PLS version 3.2 and IBM SPSS version 25.

Findings

The obtained results showed the high strength of the proposed model. This study found that the impact of urban ITS (safety, accessibility, information management and flexibility) is important to the success of supply chain management systems. Another important finding is that the cloud-based system (cloud security, resource virtualization, on-demand self-service and scalability) has a very important role in the success of supply chain management systems. The finding showed that the effect of IoT service variable (commercialization, mobility features, infrastructure capabilities and security and privacy) on the success of supply chain management systems is significant and positive. The findings also showed that urban knowledge (usage skills, awareness, experience and knowledge sharing) is viewed as a significant factor in the success of supply chain management systems.

Research limitations/implications

The inductive nature of research methodology has introduced limitations on the generalizability of results. Therefore, it is recommended to examine the validity of this research model in other supply chains.

Practical implications

The statistical results support the crucial role of urban knowledge, urban intelligent transportation systems, IoT services and cloud-based systems. Therefore, aspects relating to these factors must be the focus of attention of any distributed organization in their endeavor to develop supply chain management systems. Implementing cloud based IoT through accurate and timely availability of information, can predict forecasting and planning processes, resources, logistics and support, service management and spare parts and many sub-processes in the supply chain. These technologies allow organizations to invest in manufacturing and operating processes rather than paying for the software section, which will generate more cash flow.

Originality/value

One of the most crucial and fundamental parts of an organization’s management is the supply chain management. The department is responsible for coordinating all units from the initial stages, such as supplying materials to the final stages, such as delivery and after-sales service. Comprehensive and credible information platforms are essential for managing a supply chain. Therefore, it is important to use integrated information systems such as IoT, cloud computing, intelligent transportation systems and more in this part of the organization management. Covering this information in a timely and accurate manner will facilitate the process and make the process more transparent. For this purpose, a model is needed to determine the relationship between technologies and supply chain management, which this study has provided a comprehensive model.

Details

Kybernetes, vol. 49 no. 11
Type: Research Article
ISSN: 0368-492X

Keywords

To view the access options for this content please click here
Article
Publication date: 13 July 2018

Amin Vahidi, Alireza Aliahmadi and Ebrahim Teimoury

This paper reviews the underpinning principles and scientific trends of cybernetics and the viable system model (VSM). Therefore, this paper aims to guide authors and…

Abstract

Purpose

This paper reviews the underpinning principles and scientific trends of cybernetics and the viable system model (VSM). Therefore, this paper aims to guide authors and managers active in management cybernetics and to inform them about the past, current and future trends in this discipline.

Design/methodology/approach

This paper adopts both qualitative and quantitative methods. First, a descriptive and qualitative approach is used to review and analyze management cybernetics historical trends. Then, a frequency analysis (quantitative) is conducted on the 1,000 first publications in the field.

Findings

The cybernetics was emerged in the Josiah Macy conference in 1946. Then, Wiener introduced the field of cybernetics and Ashby, Von Foerster and McCulloch developed this concept as a discipline. The Management cybernetics field that was introduced by Beer is a combination of system, control and management sciences. Beer presented VSM as an operational model in this area. Analyzing the 1,000 top-ranked publications shows that the introduction of this field reached maturity and further development became relatively mature. Moreover, based on the analyzed trends, VSM model application can now be strongly attractive. In this paper, the main journals, authors and research trends are analyzed. The main application area of this model is in the IT field and large-scale organizations.

Practical implications

The present paper’s implication for practitioners and researchers is guiding authors and managers to most appropriate studies in the field, so that they can produce and use the most efficient studies in this field.

Social implications

The fields of IT, Policy-Making, Production, Social Issues, Service industry, Software developers, etc., are some of this paper’s implications for industry and society.

Originality/value

In this paper, the steps of VSM development are investigated. Then, recent trends (classifications, authors, journals and topics analysis) are surveyed by analyzing the top 1,000 publications in this field. This paper would help researchers find more appropriate research fields. In addition, it helps practitioners find the optimum solutions based on management cybernetics for their problems among vast numbers of publications.

Details

Kybernetes, vol. 48 no. 5
Type: Research Article
ISSN: 0368-492X

Keywords

1 – 8 of 8