M.h. Fazel Zarandi, M. Zarinbal,
Volume 23, Issue 4 (11-2012)
Abstract
Image segmentation is an essential issue in image description and classification. Currently, in many real applications, segmentation is still mainly manual or strongly supervised by a human expert, which makes it irreproducible and deteriorating. Moreover, there are many uncertainties and vagueness in images, which crisp clustering and even Type-1 fuzzy clustering could not handle. Hence, Type-2 fuzzy clustering is the most preferred method. In recent years, neurology and neuroscience have been significantly advanced by imaging tools, which typically involve vast amount of data and many uncertainties. Therefore, Type-2 fuzzy clustering methods could process these images more efficient and could provide better performance. The focus of this paper is to segment the brain Magnetic Resonance Imaging (MRI) in to essential clusters based on Type-2 Possibilistic C-Mean (PCM) method. The results show that using Type-2 PCM method provides better results.
Yahia Zare Mehrjerdi,
Volume 25, Issue 2 (5-2014)
Abstract
Abstract
Purpose of this paper: The purpose of this article is to review some of the most prominent applications of RFID in industries and to provide a comprehensive review of the work done from 1985 through 2007 and the research trend on that. The effectiveness of RFID and the challenges that it is facing with are also discussed. Some applications of radio frequency identification in supply chain are briefly reviewed and three large cases of radio frequency identification implementation in supply chain are discussed.
Design/methodology/approach: Provides some background on radio frequency identification, and a deep look at the researches conducted from 1985 through 2007. Articles are classified by the year of publications and each case is discussed very briefly. To obtain a good understanding of the level of the researches completed up to the end of 2007 a table and graph are used to demonstrate the summary of results.
Findings: In this research, author came up with 401 articles on RFID as all are listed in a table. The findings point to this fact that research on RFID has started to pick up on year 2002 with 16 publications and then reached to its pick at year 2005 with 112 publications, and then trend went down to 42 and then up to 51 publications for years 2006 and 2007, respectively.
Practical implications (if applicable):
What is original/value of paper: Due to the fact that a better management of a system is related to the full understanding of the technologies implemented, sufficient background on the radio frequency identification technology is provided and the types of researches conducted so far on this matter are briefly discussed.
Sina Nayeri, Ebrahim Asadi-Gangraj, Saeed Emami,
Volume 29, Issue 1 (3-2018)
Abstract
Natural disasters, such as earthquakes, tsunamis, and hurricanes cause enormous harm during each year. To reduce casualties and economic losses in the response phase, rescue units must be allocated and scheduled efficiently, such that it is a key issues in emergency response. In this paper, a multi-objective mix integer nonlinear programming model (MOMINLP) is proposed to minimize sum of weighted completion times of relief operations as first objective function and makespan as second objective with considering time-window for incidents. The rescue units also have different capability and each incident just can be allocated to a rescue unit that has the ability to do it. By assuming the incidents and rescue units as jobs and machine, respectively, the research problem can be formulated as a parallel-machine scheduling problem with unrelated machines. Multi-Choice Goal programming (MCGP) is applied to solve research problem as single objective problem. The experimental results shows the superiority of the proposed approach to allocate and schedule the rescue units in the natural disasters.
Mohammad Mehdi Dehdar, Mustafa Jahangoshai Rezaee, Marzieh Zarinbal, Hamidreza Izadbakhsh,
Volume 29, Issue 4 (12-2018)
Abstract
Human-based quality control reduces the accuracy of this process. Also, the speed of decision making in some industries is very important. For removing these limitations in human-based quality control, in this paper, the design of an expert system for automatic and intelligent quality control is investigated. In fact, using an intelligent system, the accuracy in quality control is increased. It requires the knowledge of experts in quality control and design of expert systems based on the knowledge and information provided by human and equipment. For this purpose, Fuzzy Inference System (FIS) and Image Processing approach are integrated. In this expert system, the input information is the images of the products and the results of processing on images for quality control are as output. At first, they may be noisy images; the pre-processing is done and then a fuzzy system is used to be processed. In this fuzzy system, according to the images, the rules are designed to extract the specific features that are required. At second, after the required attributes are extracted, the control chart is used in terms of quality. Furthermore, the empirical case study of copper rods industry is presented to show the abilities of the proposed approach.
Louiza Dehyadegari, Somayeh Khajehasani,
Volume 32, Issue 1 (1-2021)
Abstract
In this paper, a multivariable control of a two-link robot is performed by fuzzy-sliding mode control. Robots on the one hand have complex dynamics due to nonlinearity, uncertainty and indeterminacy resulting from friction and other factors. The uncertainty and nonlinearity of the governing equations more and more necessitates the use of these two types of controllers in spite of a two-link and multivariable dynamic system. In this paper simulation, a fuzzy system is used in two parts. In the first part, a fuzzy system is used to approximate the uncertainty of the robot arm dynamic model in the control law and in the second part the nonlinear term of the signal function is replaced by an adaptive neuro-fuzzy controller to produce appropriate
s and to track the output properly. The comparison of simulation results suggests that the intelligent method based on the proposed adaptive neuro-fuzzy control has better performance in tracking reference signal with slight tracking error and higher accuracy compared to sliding mode method.
Amir Akbarzadeh Janatabad, Ahmad Sadegheih, Mohammad Mehdi Lotfi, Ali Mostafaeipour,
Volume 33, Issue 1 (3-2022)
Abstract
The health insurance system can play an effective role to control health expenditures. The purpose of this study is to provide a model for estimating the physician visit tariffs. To achieve this goal, a hybrid model was used. fuzzy logic is the most appropriate tool for controlling systems and deriving rules for the relationship between inputs and outputs. So, the output of the data mining techniques enter the fuzzy logic as an input variable. The data were collected from the Health Insurance Organization of Iran in two sections including the physicians' costs and physicians' deductions. Owing to the techniques used in this model, NN had the least error, as compared to other data mining techniques (0.0034 and 0.0013, respectively). After defining the variables, membership functions and fuzzy logic rules, the accuracy of the whole control model was confirmed by random data. This research has dealt with the domains of health insurance , their connections and defining effective variables better and more extensively than the other studies in the field.
Mahdi Rezaei, Ali Salmasnia, Mohammad Reza Maleki,
Volume 34, Issue 3 (9-2023)
Abstract
This article develops an integrated model of transmitting strategies and operational activities to enhance the efficiency of supply chain management. As the second objective, this paper aims to improve supply chain performance management (SCPM) by employing proper decision-making approaches. The proposed model optimizes the performance indicator based on SCOR metrics. A process-based method is utilized for high-level decisions, while a mathematical programming method is proposed for low-level decisions. The suggested operational model takes some major supply chain properties such as multiple suppliers, multiple plants, multiple materials, and multiple produced items over several time periods into account. To solve the operational multi-objective optimization model, a goal programming approach is applied. The computational results are explained in terms of a numerical example, and a sensitivity analysis is performed to investigate how the performance of the supply chain is influenced by strategic scenario planning.
Faikul Umam, Hanifudin Sukri, Ach Dafid, Firman Maolana, Mycel Natalis Stopper Ndruru,
Volume 35, Issue 4 (12-2024)
Abstract
Robots are one of the testbeds that can be used as objects for the application of intelligent systems in the current era of Industry 4.0. With such systems, robots can interact with humans through perception (sensors) like cameras. Through this interaction, it is expected that robots can assist humans in providing reliable and efficient service improvements. In this research, the robot collects data from the camera, which is then processed using a Convolutional Neural Network (CNN). This approach is based on the adaptive nature of CNN in recognizing visuals captured by the camera. In its application, the robot used in this research is a humanoid model named Robolater, commonly known as the Integrated Service Robot. The fundamental reason for using a humanoid robot model is to enhance human-robot interaction, aiming to achieve better efficiency, reliability, and quality. The research begins with the implementation of hardware and software so that the robot can recognize human movements through the camera sensor. The robot is trained to recognize hand gestures using the Convolutional Neural Network method, where the deep learning algorithm, as a supervised type, can recognize movements through visual inputs. At this stage, the robot is trained with various weights, backbones, and detectors. The results of this study show that the F-T Last Half technique exhibits more stable performance compared to other techniques, especially with larger input scales (640×644). The model using this technique achieved a mAP of 91.6%, with a precision of 84.6%, and a recall of 80.6%.