Advances in Industrial Engineering

Both man-made and natural disasters can cause significant damage to property and human lives. Giving emergency medical services to the casualties as fast as possible after a disaster is critical. However, the destruction of some infrastructure such as roads, in the aftermath of a disaster, makes this process complicated. Artificial intelligence is now more frequently used to solve a wide range of difficult problems. In this paper, a combination of a deep learning model and particle swarm optimization algorithm is proposed to extract roads from satellite images, which can be useful for emergency vehicle drivers to recognize the best available path to reach casualties in disaster zones and give medical services to them faster. The model is evaluated by the evaluation metrics. Moreover, it is compared with other common models. The proposed model shows remarkable performance and 92% accuracy. Also, some predictions based on the model will be presented.

This paper highlights the shift in the industrial sector towards a decentralized structure, focusing the importance of energy efficiency for manufacturers and the need for quick job completion to satisfy customers. The study proposes a matching game approach using the Job Scheduling Problem (JSP) to address both manufacturer and customer concerns. It introduces the Deferred Acceptance (DA) algorithm, as a notable matching algorithm, to create stable and optimal matches between machines and operations, incorporating the W-value concept to represent willingness values between partners. The Enhanced Iterative DA (EIDA) algorithm, enhanced with the W-value, shows improved job completion time, reduced energy consumption, and faster runtime compared to the Genetic Algorithm (GA). Through experiments, our enhanced iterative DA (EIDA) algorithm results in an average 6.40% increase in job completion time and a 16.60% reduction in manufacturers' energy consumption compared to the Genetic Algorithm (GA). Moreover, utilizing the W-value leads to a 19.03% average runtime improvement.

Marine transportation has become a vital element of global trade, connecting commercial hubs around the world via low-cost sea routes. Its impact is increased by the environmental concerns raised by the associated maritime traffic, which necessitates a comprehensive and efficient method to resolving these worries. A vessel follows a predefined course and departs from the home port on a scheduled basis in order to reach its destination. It carries out loading and unloading operations at the allocated berth and crane during the tour. In order to conserve schedule, the vessel needs to navigate the route at the optimal speed, which is influenced by a number of factors including fuel consumption and vessel weight. This study used a novel model to generate a vessel schedule and route map for Iran's Shahid Rajaei Port in the Persian Gulf. The data suggest that the port can manage ten vessels at a time and has two cranes for loading and unloading each vessel. In addition, we carried out a sensitivity analysis on key components of our proposed model, including fuel costs, vessel weight, load-carrying capacity, and arrival/departure delays. The keys findings are as: higher arrival/departure costs result in shorter delays; higher fuel costs have a negative impact on the objective function; lower vessel weight results in better fuel efficiency; and higher vessel load-carrying capacity is coupled with higher fuel costs.

Coronavirus is a respiratory disease caused by coronavirus 2 acute respiratory syndrome. Forecasting the number of new cases and deaths can be an efficient step towards predicting costs and providing timely and sufficient facilities needed in the future. The goal of the current study is to accurately formulate and predict new cases and mortality in the future. Nine prediction models are tested on the Coronavirus data of Yazd province as a case study. Due to the evaluation criteria of root mean square error (RMSE), mean square error (MSE), mean absolute percentage error (MAPE), and mean absolute value of error (MAE), the models are compared. The analysis results emphasize that, according to the mentioned evaluation criteria, the KNN regression model and the BATS model are the best models for predicting the cumulative cases of hospitalization of Coronavirus and the cumulative cases of death, respectively. Moreover, the autoregressive neural network model has the worst performance for both hospitalization and death cases among other formulations.

One of the main aspects of the production industry is the optimization of acceptance sampling plans. Sampling plan performance depends on many uncertain factors that are difficult to model, especially in a multi-stage process. Therefore, it requires an innovative procedure to optimize it. This study presents an innovative double sampling plan for a multi-stage process based on discrete event simulation (DES) toward proposing an applicable plan to the inspection of the product whose accepting probability follows the hypergeometric distribution for a finite lot without replacement. This paper focuses on the five economic parameters of a double sampling plan that are determined by minimizing the average sample number (ASN) with the help of DES results and optimization methods. Several experiments based on DES were tested to determine the regression function of the ASN simulation study was carried out using Enterprise Dynamic software (ED). Our economic statistical lot acceptance sampling plan based on minimizing the average sample number has been developed to determine the acceptance parameters including the first acceptance number, first rejectable, number, first sample size, second sample size, and second acceptance number in a multi-stage process. According to all runs of the simulation model, we concluded at a 95% level of confidence that ASN ranges from 530.16 to 554.93, which is given in detail in the paper.