bat algorithm

Many studies have addressed supply chain that shows the importance of the subject and the competition in the supply chain consisting of several companies. The previous studies address the issue of reducing the Bullwhip Effect in the supply chain, which is possible by predicting the correct amount of customer demand. This paper improves the accuracy of the model prediction and reduces the existing error in the previous models to attain an accurate and very close-to-reality forecast and also to reduce the Bullwhip Effect in the supply chain. Literature shows the absence of research on the presentation of a metaheuristic algorithm consisting of a neural network and bat algorithm to forecast supply chain demand in manufacturing companies; therefore, this article is innovative. On the other hand, no researchers have addressed Bullwhip Effect reduction using mixed metaheuristic algorithms. Therefore, this article improves the previous models, reduces the number of errors in demand forecasting, and reduces the Bullwhip Effect. For this purpose, the scalable gradient algorithm method is used for better network training. The results indicate the optimal performance of neural network training with a comparable gradient and bat algorithm on reducing the Bullwhip Effect.

The main purpose of this study is to predict saffron’s binding efficiency using the meta-heuristic algorithm. This collection of information is a documentary research library and the result is quantitative research. The time period from 2018 to 2021 was 5 years and the frequency of daily frequencies of the Ministry of Agricultural Jihad and Customs of Iran were collected from the Iran Mercantile Exchange (JPI). The meta-heuristic algorithm consisting of a combination of birds, bats, and cuckoos was designed. The proposed methods were modelled by coding in a MATLAB environment using normal data. The results of the computational analysis show that all models were approved; And the artificial neural network shows that price fluctuations, cash price, the volume of transactions and liquidity are of the most importance, respectively, on the yield of saffron contracts.

One of the challenges today is capturing fake images. One type of image forgery is a copy-move forgery. In this method, a part of the image is copy and placed at the most similar point. Due to the existing algorithms and processing software, it is not easy to detect forgery areas and has created challenges in various applications. Based on the Bat algorithm, the proposed method has tried to help detect fake images by finding forgery areas. The proposed method includes a simple image segmentation and detection of forgery areas with the help of the BAT Algorithm with Mutation. According to the proposed algorithm, the image is first grayed out, then divided into 100 pieces. The optimal Bat algorithm randomly selects some component image and performs a similarity search. The mutation operator is used to avoid getting stuck in the local optimization. The proposed algorithm does not get stuck in the local optimization with the help of the mutation operator and can find forgery areas with a precision of about 81.39% for the IMD dataset and about 81.04% for the MICC-F600 dataset.

In this paper, a meta-heuristic method, the Bat Algorithm, based on the echolocation behavior of bats is used to determine the optimum service rate of a queue problem. A finite buffer M/M/1 queue with N policy, multiple working vacations and Bernoulli schedule vacation interruption is considered. Under the two customers' impatient situations, balking and reneging, the queue is studied using the matrix geometric method. Simulations show that the proposed algorithm seems much superior to other algorithms.