Search published articles


Showing 9 results for Data Mining

, , ,
Volume 20, Issue 1 (5-2009)
Abstract

Fuzzy Cognitive Maps (FCMs) have successfully been applied in numerous domains to show the relations between essential components in complex systems. In this paper, a novel learning method is proposed to construct FCMs based on historical data and by using meta-heuristic: Genetic Algorithm (GA), Simulated Annealing (SA), and Tabu Search (TS). Implementation of the proposed method has demonstrated via real data of a purchase system in order to simulate the system’s behavior.
Seyed Omid Hasanpour Jesri, Abbas Ahmadi, Behrooz Karimi, Mohsen Akbarpour ,
Volume 23, Issue 4 (11-2012)
Abstract

One of the most important issues in urban planning is developing sustainable public transportation. The basic condition for this purpose is analyzing current condition especially based on data. Data mining is a set of new techniques that are beyond statistical data analyzing. Clustering techniques is a subset of it that one of it’s techniques used for analyzing passengers’ trip. The result of this research shows relations and similarities in different segments that its usage is from strategic to tactical and operational areas. The approach in transportation is completely novel in the part of trip patterns and a novel process is proposed that can be implemented in highway analysis. Also this method can be applied in traffic and vehicle treats that need automatic number plate recognition (ANPR) for data gathering. A real case study has been studied here by developed process.
Mehdi Alinaghian,
Volume 25, Issue 2 (5-2014)
Abstract

periodic vehicle routing problem focuses on establishing a plan of visits to clients over a given time horizon so as to satisfy some service level while optimizing the routes used in each time period. This paper presents a new effective heuristic algorithm based on data mining tools for periodic vehicle routing problem (PVRP). The related results of proposed algorithm are compared with the results obtained by best Heuristics and meta-heuristics algorithms in the literature. Computational results indicate that the algorithm performs competitive in the accuracy and its small amount of solving time point of views.
Naghmeh Khosrowabadi, Rouzbeh Ghousi, Ahmad Makui,
Volume 30, Issue 2 (6-2019)
Abstract

With regard to the industry's development, occupational safety is a key factor in protecting the worker's health, achieving organizational goals and increasing productivity. Therefore, research is needed to investigate the factors affecting occupational safety. This research, based on the information gathered from the paint halts of one of the industrial units of Tehran, uses data mining technique to identify the important factors.Initially with Literature review to 2018, an insight into existing approaches and new ideas earned. Then, with a significant 5600 units of data, the results of the charts, association rules and K-means algorithm were used to extract the latent knowledge with the least error without human intervention from the six-step methodology of Crisp for data mining.The results of charts, association rules, and K-means algorithm for clustering are in a line and have been successful in determining effective factors such as important age groups and education, identifying important events, identifying the halls and finally, the root causes of major events that were the research questions.The results reveal the importance of very young and young age with often diploma education and low experience, in major accidents involving bruising, injury, and torsion, often due to self-unsafe act and unsafe conditions as slipping or collision with things. In addition, the important body members, hands and feet in the color retouching and surface color cabins are more at risk. These results help improve safety strategies. Finally, suggestions for future research were presented.
Mehrdad Kargari, Susan Sahranavard,
Volume 31, Issue 1 (3-2020)
Abstract

Background: The continuous growth of healthcare and medicine costs as a strategic commodity requires tools to identify high cost populations and cost control. After the implementation of the healthcare Reform plan in Iran, a huge share of hospital funding has been spent on undesirable costs due to changes in the use of medicines and instruments.
Objective: The aim of this study was to compare the cost of medicines in both the pre and post period of health plan implementation to detect abnormalities and low frequency patterns in the medical prescriptive that account more than 30% of hospital budget funds.
Method: Therefore a data mining model has been used. First, by forming incidence matrices on the cross-features; categorized prescriptions information. Then using normalized risk function to identify abnormal and high cost cases based on the distance between the input data and the mean of the data. The data used are 15078 records, including information from patients' prescriptions from Shari'ati HIS in Tehran-Iran from 2012 to 2016.
Results: According to the obtained results, the proposed model has a positive Likehood ratio (LR+) of 6.35.
 
Pegah Rahimian, Sahand Behnam,
Volume 31, Issue 3 (9-2020)
Abstract

In this paper, a novel data driven approach for improving the performance of wastewater management and pumping system is proposed, which is getting knowledge from data mining methods as the input parameters of optimization problem to be solved in nonlinear programming environment. As the first step, we used CART classifier decision tree to classify the operation mode -number of active pumps- based on the historical data of the Austin-Texas infrastructure. Then SOM is applied for clustering customers and selecting the most important features that might have effect on consumption pattern. Furthermore, the extracted features will be fed to Levenberg-Marquardt (LM) neural network which will predict the required outflow rate of the period for each operation mode, classified by CART. The result show that F-measure of the prediction is 90%, 88%, 84% for each operation mode 1,2,3, respectively. Finally, the nonlinear optimization problem is developed based on the data and features extracted from previous steps, and it is solved by artificial immune algorithm. We have compared the result of the optimization model with observed data, and it shows that our model can save up to 2%-8% of outflow rate and wastewater, which is significant improvement in the performance of pumping system.
Elaheh Bakhshizadeh, Hossein Aliasghari, Rassoul Noorossana, Rouzbeh Ghousi,
Volume 33, Issue 1 (3-2022)
Abstract

Organizations have used Customer Lifetime Value (CLV) as an appropriate pattern to classify their customers. Data mining techniques have enabled organizations to analyze their customers’ behaviors more quantitatively. This research has been carried out to cluster customers based on factors of CLV model including length, recency, frequency, and monetary (LRFM) through data mining. Based on LRFM, transaction data of 1865 customers in a software company has been analyzed through Crisp-DM method and the research roadmap. Four CLV factors have been developed based on feature selection algorithm. They also have been prepared for clustering using quintile method. To determine the optimum number of clusters, silhouette and SSE indexes have been evaluated. Additionally, k-means algorithm has been applied to cluster the customers. Then, CLV amounts have been evaluated and the clusters have been ranked. The results show that customers have been clustered in 4 groups namely high value loyal customers, uncertain lost customers, uncertain new customers, and high consumption cost customers. The first cluster customers with the highest number and the highest CLV are the most valuable customers and the fourth, third, and second cluster customers are in the second, third, and fourth positions respectively. The attributes of customers in each cluster have been analyzed and the marketing strategies have been proposed for each group.
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.
Ali Qorbani, Yousef Rabbani, Reza Kamranrad,
Volume 34, Issue 4 (12-2023)
Abstract

Prediction of unexpected incidents and energy consumption are some industry issues and problems. Single machine scheduling with preemption and considering failures has been pointed out in this study. Its aim is to minimize earliness and tardiness penalties by using job expansion or compression methods. The present study solves this problem in two parts. The first part predicts failures and obtains some rules to correct the process, and the second includes the sequence of single-machine scheduling operations. The failure time is predicted using some machine learning algorithms includes: Logistic Regression, Decision Tree, Random Forest, Support Vector Machine (SVM), Naïve Bayes, and k-nearest neighbors. Results of comparing the algorithms, indicate that the decision tree algorithm outperformed other algorithms with a probability of 70% in predicting failure. In the second part, the problem is scheduled considering these failures and machine idleness in a single-machine scheduling manner to achieve an optimal sequence, minimize energy consumption, and reduce failures. The mathematical model for this problem has been presented by considering processing time, machine idleness, release time, rotational speed and torque, failure time, and machine availability after repair and maintenance. The results of the model solving, concluded that the relevant mathematical model could schedule up to 8 jobs within a reasonable time and achieve an optimal sequence, which could reduce costs, energy consumption, and failures. Moreover, it is suggested that further studies use this approach for other types of scheduling, including parallel machine scheduling and flow job shop scheduling. Metaheuristic algorithms can be used for larger dimensions. 

Page 1 from 1