bat algorithm

The bat algorithm is an example of meta-heuristic algorithms from the collective swarm intelligence, which is based on the echolocation behavior of bats. This algorithm preserves the diversity of the solution by using a frequency tuning method that can quickly and efficiently shift from exploration to exploitation. Therefore, when a fast and accurate solution is needed, this algorithm becomes an efficient optimizer for any application. Although the bat algorithm has many practical benefits, it also has some disadvantages. One of these disadvantages that reduces its efficiency is being trapped in the local optimum. To solve the mentioned problem in this research, the position and speed of the initial population is updated in three ways with different formulas, this makes the final answer of the problem not trapped in the local optimum and diversity occurs in the population. In this article, the performance of the improved bat algorithm on 11 sample objective functions has been investigated and compared with other similar algorithms, and finally the results show the superiority and accuracy of this algorithm compared to similar samples.

The solar radiation value parameter is one of the most important parameters in determining the output power value of photovoltaic panels. Accurate prediction of this parameter is crucial for dispatching and load management planning. Managers and designers encounter economic and managerial challenges due to the uncertainty and difficulty in predicting solar radiation levels. This research introduces a highly accurate prediction method utilizing tree-based methods, enhanced by meta-heuristic algorithms to boost performance. The proposed method emphasizes preventing overfitting and ensuring high reliability for use in Internet of Things systems. Meta-heuristic algorithms are utilized for optimizing tree-based methods, as well as for feature and instance selection. Employing meta-heuristic methods as the main innovation in this research not only optimizes machine learning model settings but also mitigates the impact of noise, outliers, and ineffective inputs, thereby enhancing the final output quality. Utilizing an innovative fitness function in model optimization enhances prediction accuracy and adaptability to real photovoltaic power plant environments. The final outcome is a strong model that has a score of 0.95 with the R-square criterion and is optimal model.

Choosing the right drilling and blasting methods is very important to improve mine productivity and increase profits, while increasing the safety of workers and the environment. One of the main goals in Blasting is to estimate the optimal amount of specific cost, which is described as the specific cost required for optimizing rock crushing, air blast, ground shaking, and rock throwing. In this Paper, to further improve the effect of blasting and increase the efficiency of mine production, we optimized the plan by considering the implementation of the blasting plan with respect to the drilling intervals, and a numerical simulation model was created to provide technical guidance for the optimization plan. In this Paper, data collection and analysis were done by the software and it was determined that with R^2=0.969, VAF=9.825, the lowest error is RMSE=0.031 and MAPE=0.323 with unit m^3kg/ . The polynomial function model with incorrect coefficients has a more satisfactory performance and this function model was subjected to sensitivity analysis using the cosine field method. The evaluation and analysis in this way also showed that the selected function model has a more accurate calculation of the specific cost. This proposed function was called in the bat algorithm and the crow search algorithm in MATLAB software, and the optimization operation was performed by the algorithms. In this Paper, the number of 11 data from 31 blasting series that were actually carried out in Sadat iron ore mine of Zarand series was collected. The special cost of this mine was modeled with 6 functions by spss software, and among them, the polynomial function model with incorrect coefficients was chosen to predict the special cost. The special cost optimization operation was performed by two bat algorithms and the crow search algorithm, and the special cost optimized by the algorithms was compared. By sensitivity analysis, the sensitive and effective parameters taken in this mine were identified for special spending. This analysis showed that all the input parameters used in this modeling have a strong sensitivity to the specific cost, and among them, the ratio of the height of the step to the thickness of the bar rock has the highest sensitivity and the total consumption cost has the lowest sensitivity.

Recognition of handwritten numbers is a complex issue in the field of image processing. Due to being in the digital age, speed and accuracy of intelligent systems have always been developing, which is why image processing has become particularly important. On the other hand, due to the importance of handwritten numbers recognitions and its various applications, in this study, an algorithm has been proposed to recognize Persian handwritten numbers. In this research, two methods of “framing and wavelet transform” have been used to extract the feature. The KNN classification method is also used. After testing different dimensions of the mold, the accuracy percentage of the framing method has been obtained above 87% By selecting the features of the third level of wavelet transform, 95% accuracy is obtained. Using the evolutionary bat algorithm, it has been tried to reduce the features and improve the system.

The mean objective of performance based optimization of reinforced concrete frames (RC) is to reduce the cost of construction by requiring the satisfaction of the inter-story drifts and rotation of the plastic joints of the members. In this research, two 3 & 6 stories RC performance-based optimized by Particle Swarm (PSO), Enhanced Colliding Bodies (ECBO), firefly Algorithm (FA),Ants Colony (ACO) and Bat (BAT) meta-heuristic algorithms, then compare results with together. Optimization of RC is much complicated than Steel frames, because different dimensions of members & configuration of reinforcing. Due to the high cost of seismic performance evaluation of structures, in this research, neural networks used to increase the computational speed & reduce the operating time. Numerical results show the proper performance of the ECBO in comparison with other meta-heuristic algorithms.Also, the results of different algorithms do not show much difference.For further evaluation of the results, it is recommended to Calculate its Collapse Margin Ratios.

Wireless sensor networks (WSNs) consist of sensor nodes with limited energy. Energy efficiency is an important issue in WSNs as the sensor nodes are deployed in rugged and non-care areas and consume a lot of energy to send data to the central station or sink if they want to communicate directly with the sink. Recently, the IEEE 802.15.4 protocol is employed as a low-power, low-cost, and low rate communication standard for WSNs, which ensures real-time applications via Guaranteed Time Slot (GTS). Accordingly, in this paper, a new protocol energy efficient bat algorithm and a mobile sink are presented. It can choose the optimal route based on: (1) distance of a sensor node to sink, (2), bat loudness, and (3) energy level of its battery. Using the OPNET simulator version 11.5, the proposed method was simulated by bat and NODIC protocols, and IEEE 802.15.4 and the results were considered in terms of energy consumption, end to end delay, signal to noise ratio, the success probability of sending data to sink and rate of passing data. The results of the simulation showed the use of the above-mentioned parameters in the proposed method leads to the improvement of the network throughput against using the IEEE 802.15.4 protocol, Bat algorithm, and NODIC protocol.

Summary:

One of the main problems of mine planning is long-term production scheduling, which is very important in the theoretical research of open-pit mining and determines the distribution of cash flow throughout the life of the mine. In fact, the purpose is to maximize the net present value of the future profits generated. Among the uncertainties, grade uncertainty will play a major role in the accuracy of long-term production scheduling. In this paper, a hybrid model is presented by the Lagrangian relaxation method and bat algorithm to solve the problem of long-term production of open-pit mines, in which the uncertainty of the grade is also considered. The new approaches proposed are based on optimizing Lagrange coefficients and comparing them with the traditional method. The bat algorithm is used to update the Lagrange coefficients. The results of the case study show that the hybrid strategy can provide an acceptable solution compared to the traditional approximation method so that over a given period the net present value using the proposed hybrid method is 6.69% higher than the traditional one.

In recent years, a new approach to cheaper computational algorithms, such as meta-heuristic techniques, has attracted more attention from researchers to solve production scheduling problems. Although these techniques do not guarantee optimization as a final solution for production, they can provide suitable solutions for production at a lower computational cost.

Methodology and Approaches:

In this paper, an optimal hybrid model by the Lagrangian relaxation method and bat algorithm is presented to solve the problem of long-term production of open-pit mines, where the uncertainty of the grade is also considered. The newly proposed approach is based on optimizing Lagrange coefficients and comparing it with the traditional method. The results of the proposed approach are also compared with the combined approach based on the Lagrangian relaxation method and genetic algorithm. The bat algorithm is used to update the Lagrange coefficients.

The results of a case study show that the Lagrangian relaxation method can provide a suitable solution to the main problem and the combined strategy can produce a more effective solution than the traditional approximation method. It was also found that the proposed method has advantages, such as stable convergence property and prevention of early convergence. Over a given period, the net present value using the LR-BA hybrid method is 6.69% higher than the traditional method and also 5.58% higher than the LR-GA method.

The growing amount of information on the internet has made it difficult for many web users to make the decision-making and selection of information, data or goods. Recommended systems are designed to address this challenge and try to offer specific and useful information with respect to user tastes and past user experiences. So far, many offering systems have been developed in a variety of applications including movies, music, books, hotels etc. Choosing the right trip, the hotel proposal and so on, with regard to the individual's budget usually have a lot of difficulties and concerns for users and generally takes a lot of time and energy. In this paper, a travel and hotel recommendation system is developed which is constructed from combination of different filtering methods to maximize accuracy. The system is considering the current user's preferences, the quality of the service packages and past experiences of the same users with the current user in order to providing more accurate suggestions. It also eliminates the cold start problem.

In this work, a method for order reduction of unstable systems by minimizing the multi-objective weighted sum function ITSE and H∞ norm with bat algorithm is investigated. At first, the unstable model is divided into two parts: stable and unstable. Then, the order of reduced model is determined by considering the stable part and using Hankel norm. In the following, a fixed structure with unknown coefficients is considered for a reduced order model. By minimizing the weighted sum multi-objective included ITSE and H∞ norm with bat algorithm, in which the error is the difference between the step response of original system and reduced order model, unknown parameters of the reduced order model are determined. The Routh-Hurwitz criterion has been used to satisfy the stability condition, which is introduced as a constraint in the optimization problem, and thus the unconstrained optimization problem is converted to constrained optimization problem. Finally, the unstable part is joined to the reduced order part. To confirm and demonstrate the capability and efficiency of the proposed method, three large systems have been reduced and compared with some order reduction methods such as balanced truncation and optimal Hankel approximation. The results show the capability of the proposed method over classical methods.

There have been many studies on how to model problem types, develop problem assumptions to adapt to real-world application conditions, and develop or develop problem-solving methods to obtain better results. In this paper, we aim to use single-target bat algorithm for drug distribution process in Tabriz metropolitan area in order to solve the problem of vehicle routing with time window. Due to the continuous nature of the metadata algorithm, how it is generated and decoded, a new routing solution is designed that gives the shortest transport path in the shortest possible time. In this regard, the distribution of the drug has been considered by Mohyadaru Distribution Company, a non-technical business-service company. In order to evaluate the performance of the proposed method, issues of different dimensions have been applied based on the actual issues related to drug delivery to existing pharmacies in the city of Tabriz by Mohyadaroo Company. The results show that the optimal routing is done due to the nature of the meta-algorithm optimization and the costs spent for this task are significantly reduced compared to the previous work.

Bat Algorithm is a type of swarm intelligence algorithm which is inspired by the behavior of little bats which are looking for direction in hunting opportunities. Swarm intelligence algorithms are inspired by the nature which are very efficient on crucial optimization problems. These algorithms are simple, flexible and can be implemented easily as well. Analyzing swarm intelligence algorithms makes their utilization reliable and guarantees finding answers by them. Earlier, stability analysis has been accomplished for some swarm intelligence algorithms including Particle Swarm Optimization and Gravitational Search but sufficient mathematical analysis for the bat algorithm has not been done. For this purpose, in the present paper, we considered Bat Algorithm stability analysis using Lyapunov method. In this study, at first, stability analysis of standard bat algorithm has been analyzed. Because of unsuccessful attempts to analyze the stability of standard algorithm, new updating relations has been introduced to increase the degree of freedom. The stability analysis has been presented for these relations. Experimental results illustrate the stability of the new updating relations.