Journal of Industrial and Systems Engineering
Volume:13 Issue: 3, Summer 2021

Owing to climate change, global warming, and contemporary droughts, temperature forecasting, as one of the most influential climatic parameters, produces a well-suited opportunity for executives to plan and provide the necessary preparations. The matter of time series forecasting of air temperature is one of the most intriguing issues in climate investigations. In this article, an intelligent hybrid model is presented to predict the time series of air temperature. This paper uses the idea of practicing the feature selection model based on the genetic algorithm (GA) to determine the input variables of the model and the high forecasting power of the neural network. The recommended model used the structure of the Autoregressive time series model. But, the problem of selecting the delay of the time series when they should be used in the model was done using genetic algorithm. Finally, the selected delays were used as input of the neural network model. The average monthly air temperature of Tabriz and Kermanshah stations throughout the statistical period 1980-2010 was used to assess the proposed model. The performance of the suggested model was compared with neural network models that do not use the feature selection method. The results corroborated the high accuracy of the developed model compared to the other models, indicating the significance of the problem of feature selection in predicting time series.

Many real-world networks, including biological networks, internet, information and social networks can be modeled by a complex network consisting of a large number of elements connected to each other. One of the important issues in complex networks is the evaluation of node importance because of its wide usage and great theoretical significance, such as in information diffusion, control of disease spreading, viral marketing and rumor dynamics. A fundamental issue is to identify a set of most influential individuals who would maximize the influence spread of the network. In this paper, we propose a novel algorithm for identifying influential nodes in complex networks with community structure without having to determine the number of seed nodes based on genetic algorithm. The proposed algorithm can identify influential nodes with three methods at each stage (degree centrality, random and structural hole) in each community and measure the spread of influence again at each stage. This process continues until the end of the genetic algorithm, and at the last stage, the most influential nodes are identified with maximum diffusion in each community. Our community-based influencers detection approach enables us to find more influential nodes than those suggested by page-rank and other centrality measures. Furthermore, the proposed algorithm does not require determining the number of k initial active nodes.

So far, various decompositions of the Malmquist productivity growth index have been presented. Although factors such as efficiency, scale, and technology have already been examined, there is no factor measures productivity growth from a financial perspective by covering costs. The purpose of this article is to show the impact of cost-efficiency changes as an important component on the productivity growth indices. This article evaluates the rate of productivity growth in the cost space and decomposes the Malmquist productivity growth index into components of cost-efficiency and Allocative efficiency. Then a similar Decomposition for the cost Malmquist index and the allocation Malmquist index based on changes in cost-efficiency and price effect obtained. In the following, we get the relation between the Malmquist index, the Cost Malmquist index, and the allocation Malmquist index with changes in technology and cost-efficiency. Then we model, and calculate the parsing factors of Malmquist indices related to decision-making units using data envelopment analysis and input distance functions. Finally, the data obtained from a real case study modeled and compared the results of previous Malmquist indices with the new Malmquist indices, and the preference of new decompositions have been analyzed.

Contrary to most countries, coronavirus has peaked three times during the last eight months in Iran. Unfortunately, increasing the number of positive COVID-19 cases is not the only crucial problem we faced. Indeed, it seems that lung coronavirus infections have also become more severe during these three peaks. Therefore, this study proposes a quantitative scoring system based on medical imaging to score the degree of lung coronavirus infection during each peak. Regarding the degree of lung coronavirus infection for all patients during the last three peaks, we test the mentioned hypothesis by employing statistical methods. Comparing the characteristics of the disease during three different peaks is another goal of the research. To this end, 5265 lung CT scan images from 270 patients with a definite diagnosis of COVID-19 infection were annotated under radiology expert supervision. Then, was used deep learning methods for image segmentation. In the next step, each patient’s lung was divided into six sections, and the percentage of infection was calculated in each section. Finally, the Friedman and Games-Howell tests showed that the average degree of COVID-19 infection has increased during the considered period, and the average of infection in men was about twenty percent higher than in women.

Perishing of the items in an inventory model has always been a crucial issue for beverage companies. Besides, some items not only perish but also have specific expiration dates. To manage the inventory-in-hand, proposing a delay in payment is usually an appropriate solution. Also, beverage companies encounter sustainable policies that are regulated to dispose of waste without damaging the environment. These regulations lead companies to establish waste treatment units in their companies to purify the obsolete items before disposing of them. Despite the importance of this challenge in practice, no research has been made to contribute to these issues. To fill the mentioned gap in the literature, this paper proposes an inventory model for perishable items which: (a) items perish continuously and have specific expiration dates, (b) a single-level trade credit is offered to the customer to stimulate the demand, and (c) waste treatment policy is considered for the beverage company to purify the returning items before disposing of them. To develop our work in practice, the case study of Behnoush Beverage Company is considered and a real domain dataset is utilized. To validate the proposed mathematical model, a sensitivity analysis is developed. Eventually, managerial implications are outlined and the findings are concluded.

Project procurement is one of the essential parts of the project covering a large portion of project costs. Supplier selection is one of the significant issues in project procurement. The appropriate supplier must be selected before ordering the materials needed for the project. Hence, a new combination of COPRAS and GRA methods is presented for choosing the best project’s supplier under uncertain conditions in this paper. Moreover, the weight of criteria is specified utilizing the multi-objective optimization model (MOOM). Furthermore, in group decision-making, decision-makers' importance is different because of varying education, views,  and experience. Hence, determining the weights of decision-makers is inevitable. Nevertheless, decision-makers' importance is specified by a new version of a combination of COPRAS and GRA methods. To evaluate the proposed model's performance, a numerical example is solved, and the results are investigated.

In the light of the impact of transportation management and logistics on the economy and extending the efficiency in the systems of production, the well-timed supply of materials and products is a momentous prerequisite for economic and environmental extension.  In addition, since the optimality usage of communication networks and detecting optimal routes to decrease traffic volume and travel time in the logistics network by discovering optimal routes for vehicles to attain the destination, is an fundamental challenge and a goal in the smart transportation system,  hence, in this paper, we accomplish a new model targeted to minimize the costs of customer service for a dynamic transport network in a safe solution in regard to monitor the dynamic production process and achieve the instantaneous information dependent upon the traffic situation of an advanced evolutionary genetic algorithm.  Besides, the Logit function is used to obtain probability and assign routes in the model.  Eventually, So that to evaluate the proficiency and feasibility of the suggested model, a number of numerical examples accompanied with sensitivity analysis are demonstrated.

The proper location of facilities /service providers is of paramount importance in the business success of several economy sectors for the sake of its effects on the service demand and hence on the market share. A vital problem resulted from modernization, urbanization, and globalization is the reconfiguration of branch locations and service capabilities to match the fast-changing and competitive market, regional economy, and customer distribution. This work introduces a new spatial decision support methodology to restructure branches' network with proposing a mathematical model taken from a real national project in the financial market. It considers establishing the new branches, relocating the current branches, merging the redundant branches, or ones with poor performance into the other branches. Moreover, a credibility-based fuzzy chance-constrained programming model is proposed to consider uncertainty in travel distances and market attractiveness of each node. The data and results are processed using the geographical information system (GIS) for Bank Melli in an urban district of Tehran.

Electricity demand is continuously increasing in developed and developing countries. The accurate estimation of power consumption in the long-term horizon is of great importance for planning in the field of power generation and the management of the demand section. The use of a single model to forecast the consumption of all economic sectors leads to many errors, due to the different sectors consuming electricity in each country, as well as the difference in indicators and their changes in each sector. Hence, new research has highly considered the use of the decomposition approach of different consumer sectors. In this regard, identifying the fundamental factors of each sector and implementing the relationships between factors in an integrated platform for estimation are the two main issues in this area. The present study proposed a combination of interpretive-structural modeling and system dynamics (ISMSD). This method can evaluate scenarios and design policies to help decision makers. According to this methodology, Iran's electricity demand has been estimated as a developing country. The results of the evaluation highlighted the high accuracy of this method in prediction. Finally, the impact of energy subsidy targeting on Iran’s electricity demand was investigated in three scenarios.

The present scenario of supply chain management is full of uncertainty due to the intrinsic complexity of operating environments. A perishable products supply chain is not an exception and is often vulnerable to disruptive incidents throughout all stages from upstream to downstream. To deal with such a challenge, a resilient structure of the supply chain with the capability to recover from or react to disruptions is approached in this study. To secure the supply chain operations, we investigate a set of proactive strategies, including signing contracts with backup suppliers, reserving extra capacity in production facilities, lateral transshipment, and keeping inventory. Using a two-stage stochastic programming model, this study examines the extent to which supply chain responsiveness and resilience are supportive. The proposed model is validated through a numerical example, and managerial insights are derived. The computational results are based on three analyses: (1) extracting the relationship between the cost function and the acceptable service levels, (2) examining the effectiveness of different strategies in managing disruptions, (3) and evaluating the accuracy of the two-stage stochastic programming approach in comparison with other approaches.

In this paper, we studied a joint sustainable lot-sizing/ pricing problem in a two echelon supply chain consists of a retailer and a supplier. For each member of the supply chain, Mathematical profit function containing revenue function and different cost functions based on different factors of sustainability such as economic, environmental and social parameters is formulated and for each member of the chain, optimal lot-sizing (Sustainable EOQ or Sustainable EPQ) and pricing decisions are made. Also, a new procedure for problem solving is presented. The contribution of this paper is integrating sustainable pricing and lot-sizing decisions of a supply chain in one model considering all main pillars of sustainability. We conducted a numerical example based on the real data of an Iranian petrochemical two-echelon supply chain and for better analyzing of numerical example results we performed a sensitivity analysis on production capacity of the supplier and profit margin of the retailer. The results show that in this case the decision variables values are not sensitive to production capacity, but they are so sensitive to profit margin of the retailer.

Independency of observations is one of the fundamental assumptions in control charts. However, in some processes this assumption is violated and data are auto-correlated. Also, it is assumed that the measurement errors are absent in measurement system while, this assumption is usually violated. The existence of the auto-correlation and measurement errors causes the poor performance of the control charts. In other words, the average run length in the case of out-of-control(OC) situations increases in the presence of auto-correlation and measurement errors. In this paper, the effect of auto-correlation and measurement errors on the performance of Hotelling’s T2 control charts in Phase II in multivariate normal processes is investigated in terms of average run length(ARL) criterion. The first order auto-regressive model as auto-correlation structure between observations within each sample is discussed in this paper. To decrease the effect of auto-correlation and measurement errors on the performance of the Hotelling’s T2 control chart, jump strategy and multiple measurements methods are applied, respectively. The effect of auto-correlation and measurement errors, individually and simultaneously, as well as the performance of the suggested methods to address these effects is appraised through simulation studies and a numerical example. The effect of number of measurements and jumps on the ARL values of the proposed control chart is also evaluated. Results show the acceptable performance of the multiple measurements and jumps methods in diminishing the effect of measurement errors and auto-correlation, respectively. At last, a real case is presented to show the application of the proposed scheme.

Nowadays, air pollution is one of the pressing environmental issues, and it causes different diseases especially cardiac and respiratory ones. The relation between air pollutants (including PM10, PM2.5, CO, SO2, NO2, and O3) and heart-pulmonary diseases (ischemic, angina, pneumonia, and chronic obstructive pulmonary disease (COPD)) is studied in Tehran, the most polluted city of Iran. Air quality data related to all pollutants PM10, PM2.5, CO, SO2, NO2, and O3 have been gathered. The relation between the pollutants and the number of admitted heart-pulmonary diseases patients is modeled by using radial basis function (RBF), multilayer perceptron (MLP) networks, and ANFIS in terms of MSE and correlation coefficient. In each network, pollutants are assumed as inputs, and heart-pulmonary diseases are considered as an output of the network. The experiments show that the ANFIS network has more accuracy than MLP and RBF. Moreover, the obtained results in the ANFIS network show that the correlation coefficient between ischemic and NO2, angina and CO, pneumonia and PM10 and COPD and (PM10 & PM2.5) respectively are 0.7229, 0.7006, 0.81 and (0.7280 & 0.7249).

Recently, renewable energy resources such as solar energy have been significantly utilized in various sectors, regarding world population growth and the increasing use of fossil fuel and non-renewable resources, and consequently, the increased rate of environmental pollution. Implementing photovoltaic systems is regarded as one of the methods of using solar energy, which countries have highly considered in recent years. With the limited lifetime of photovoltaic systems, addressing the forward and reverse supply chain of these systems plays a significant role in increasing their efficiency. To this end, the present study seeks to develop a two-objective mixed-integer non-linear model, including minimizing total costs and minimizing the negative environmental impacts, aiming to design a closed-loop supply chain network for photovoltaic systems. In this study, the augmented ε-constraint method was employed to convert the current two-objective programming model into a single-objective one. Finally, the proposed model was implemented in a case study in Iran to evaluate the model's efficiency. The results indicated that solar power plants should be built in areas with higher solar energy and lower cost. Also, the model dynamics could increase the number of constructed solar power plants and their electricity generation capacity over the time horizon, followed by increased demand for annual electricity generated by solar energy.

This paper studies a location-inventory problem with uncertain demands and lead times in a three-level supply chain including a producer, multiple distribution centres (DCs) and multiple retailers. A number of perishable products such as food and medicine goods are considered with a specific shelf life; unlike the previous studies in the literature, the restrictions of storing different perishable products in identical DC is considered. The objective is to determine the number and location of DCs, the allocation of retailers to DCs, the reorder point and demand rate at each DC. Due to the uncertainty on demands and lead times, a queuing approach is utilized to model the problem. The problem is formulated as an integer nonlinear programming and solved using the Genetic and the Imperialist Competitive algorithms.