Journal of Advances in Industrial Engineering
Volume:56 Issue: 1, Winter and Spring 2022

Expansion of industrial activities and the unnecessary growth of cities has increased the concentration of greenhouse gases, including carbon dioxide in the atmosphere. Mostly, CO2 emissions are caused by the consumption of different forms of energy and the combustion of all types of fuels, especially fossil fuels. The development of data mining techniques that lead to accurate prediction of CO2 emissions is very useful in deciding the Preventive measures and appropriate policies in this area. Most studies in this field are limited to models that do not compare different techniques and Features and only examine the effect of economic factors and fossil fuel consumption on CO2 emissions. The aim of this study is to identify a combination of significant features as well as to select the best technique to predict CO2 emissions. For this purpose, a huge dataset containing various features was obtained from the IEA database. A new hybrid method for predicting CO2 emissions was developed, then results were compared with proposed data mining techniques including: ANN, KNN, GLE, Linear-AS, Regression. Also a combination of significant features, and the best techniques for predicting CO2 emissions were identified. The results show that the proposed hybrid technique, which is a combination of K-Means, Linear-AS and Discriminant Analysis, is most accurate in this case.

In recent years, supply chains have become an attractive topic for managers and industrialists, and the life and death of organizations and businesses somehow depend on the activity of intertwined chains. On the other hand, in today's highly competitive environment, the high speed of change and evolution has increased the uncertainty and ambiguity of decisions, which makes it difficult to predict future conditions in supply chains. Therefore, reliable planning should be done in uncertain and ambiguous conditions for better and more accurate planning. One of the new and reliable approaches is the robust programming approach. In this study, transferring petroleum products from supply points to consumption areas is examined through a supply chain. Due to the uncertainty in the product demand, a mathematical model is used with two objectives including the reduction of shipping costs and the reduction of the number of loads. Due to the high volume of calculations and the problem data as well as the lack of ability to use exact solution methods, especially on a large scale, PSO and MOGA-II meta-heuristic algorithms are used to solve the proposed model. The results show that the model has the required efficiency in large dimensions and the proposed solution methods provide appropriate answers.

Allocating a limited number of relief teams to casualties immediately after a disaster is a challenging task embedded in the casualty management process. This paper proposes several dynamic strategies for allocating teams to casualty groups right after a sudden-onset disaster in order to maximize the expected number of survivors. In the proposed strategies, serious triage groups and the deterioration of the physical condition of injured people are considered. The ratio of casualties in red and yellow triage groups, and the treatment rates and survival probabilities are the main parameters in the strategies. Then, a case study is employed to demonstrate the validity of the proposed model. The strategies are compared based on the summation of the ratio of survivors in two triage groups. This comparison shows that the saving rate can be an appropriate ratio for allocating medical teams to casualty groups. Sensitivity analysis evaluates the impact of key parameters on the model results. Accordingly, changes in the ratio of triaged people have less impact on the ratio of survivors than changes in the treatment rates. It demonstrates the importance of relief teams’ allocation for surviving the casualties.

In this paper, zero-inflated Poisson (ZIP) regression was assumed as an underlying model to generate network data. This model can be an appropriate model if the network data is sparse and produced with two processes, one generates only zeros and the other generates count data that follow the Poisson model, the two parameters of the model are functions of variables here referred to as similarity variables. The performance of the Likelihood Ratio Test (LRT), a Combined Residual-Square Residual (R-SR), and Hotelling's T^2 control charts was investigated in networks based on the ZIP regression model in Phase I. Traditionally, in Phase I the parameters of the model are unknown and need to be estimated. One needs to be sure the process is stable and the changes are detected and removed. The performance of our proposed methods is compared using simulation when parameters slope and intercept are under step changes. Signal probability was recorded as a comparison measure. The simulation results show that the LRT outperforms two other methods significantly in terms of signal probability. The efficiency of methods was also examined in real Enron data set

Many methods are applied to network surveillance for anomaly detection. Some quality control methods have been developed to monitor several quality characteristics simultaneously in different networks. In our study, we use three multivariate process monitoring techniques such as Hotelling’s T2, MEWMA, and MCUSUM to compare to the prior univariate control charts in the Degree-Corrected Stochastic Block Model (DCSBM), a random network model supporting the degree of each node based on Poisson distribution. By estimating parameters in Phase I from many charts, we apply ARL and SDRL metrics for the performance evaluation of multivariate control charts. The advantage of our method is detecting signals faster than previews ones by simulation and this is useful for defining the suitable method in different types of change. Furthermore, the quality of performance in different multivariate methods is displayed in detecting the shifts in the DCSBM. Finally, MCUSUM shows better performance for monitoring local and global changes than other methods.

In deregulated electricity markets, the electricity consumer should optimally divide the necessary electrical energy into different markets such as cash markets with spot prices and bilateral contract markets. This study aims to design a model to optimally select the electrical energy portfolio to minimize purchase costs by considering a risk level. For this purpose, an optimization model is proposed through the modern portfolio theory (MPT), mean-variance analysis, and conditional value-at-risk (CVaR) for cost minimization and risk reduction in the electricity supply problem. The mean-variance and CVaR were used as appropriate criteria for reducing unfavorable states in decision-making under uncertainty. Moreover, an artificial neural network was employed to predict the spot prices of the energy pool and the Iran Energy Exchange (IRENEX). The simulation was based on the actual data of Iran for 2018 and 2019. The entire statistical population was analyzed due to the small number of industrial subscribers, and the proposed model was implemented and executed in MATLAB software. Different sensitivity analyses proved the efficiency of the proposed models. According to the results, if an energy purchaser evades more risks, — i.e., the risk evasion coefficient increases a lower ratio of the electrical energy portfolio is allocated to cash markets, especially the IRENEX. In addition, the CVaR provided electricity markets with a more stable energy allocation than the mean-variance model