Search

Display Omitted We proposed a new forecasting method based on mete-heuristic algorithm.The method was applied to forecast OPEC petroleum consumption.The new method outperforms previous methods in forecasting OPEC petroleum consumption.The new method is an alternative means of forecasting OPEC petroleum consumption. Petroleum is the live wire of modern technology and its operations, with economic development being positively linked to petroleum consumption. Many meta-heuristic algorithms have been proposed in literature for the optimization of Neural Network (NN) to build a forecasting model. In this paper, as an alternative to previous methods, we propose a new flower pollination algorithm with remarkable balance between consistency and exploration for NN training to build a model for the forecasting of petroleum consumption by the Organization of the Petroleum Exporting Countries (OPEC). The proposed approach is compared with established meta-heuristic algorithms. The results show that the new proposed method outperforms existing algorithms by advancing OPEC petroleum consumption forecast accuracy and convergence speed. Our proposed method has the potential to be used as an important tool in forecasting OPEC petroleum consumption to be used by OPEC authorities and other global oil-related organizations. This will facilitate proper monitoring and control of OPEC petroleum consumption.

Clustering faces several additional challenges, compared to traditional applications. The clusters tend to have imprecise boundaries and uncertainty. As a consequence of this uncertainty, we can highlight some challenges for web mining related to many problems such as: forming of clusters, the high computational complexity. Rough set theory has been used for clustering web user transactions, while managing uncertainty in clustering process. However, it suffers from high computational complexity. In this paper, we propose a framework for web clustering based on soft set theory with emphasis on reducing computational complexity.

Previous studies proposed several bio-inspired algorithms for the optimization of Neural Network (NN) to avoid local minima and to improve accuracy and convergence speed. To advance the performance of NN, a new bio-inspired algorithm called Flower Pollination Algorithm (FPA) is used to optimize the weights and bias of NN due to its ability to explore very large search space and frequent chosen of similar solution. The FPA optimized NN (FPNN) was applied to build a model for the prediction of Dubai crude oil price unlike previous studies that mainly focus on the West Texas Intermediate and Brent crude oil price benchmarks. Results suggested that the FPNN was found to improve the convergence speed and accuracy of the cuckoo search algorithm and artificial bee colony optimized NN in the prediction of Dubai crude oil price. The Middle East region that produces a significant amount of crude oil relies on the Dubai crude oil price to benchmark prices for exporting crude oil to Asian countries. Our model could be of help to the Middle East region for monitoring possible fluctuations in the Dubai crude oil market price so as to take better decision related to international crude oil price.

Within the framework of big data, energy issues are highly significant. Despite the significance of energy, theoretical studies focusing primarily on the issue of energy within big data analytics in relation to computational intelligent algorithms are scarce. The purpose of this study is to explore the theoretical aspects of energy issues in big data analytics in relation to computational intelligent algorithms since this is critical in exploring the emperica aspects of big data. In this chapter, we present a theoretical study of energy issues related to applications of computational intelligent algorithms in big data analytics. This work highlights that big data analytics using computational intelligent algorithms generates a very high amount of energy, especially during the training phase. The transmission of big data between service providers, users and data centres emits carbon dioxide as a result of high power consumption. This chapter proposes a theoretical framework for big data analytics using computational intelligent algorithms that has the potential to reduce energy consumption and enhance performance. We suggest that researchers should focus more attention on the issue of energy within big data analytics in relation to computational intelligent algorithms, before this becomes a widespread and urgent problem.

In this paper, a new framework for metaheuristic search for global optimization is introduced. It is suitable for continuous nonlinear optimization problems. This framework is mimicking the seal pup behavior and its ability to search and choose the best lair to escape from predators. The scenario starts once the seal mother gives birth to a new pup in a birthing lair that is constructed for this purpose. The seal pup strategy everytime consists of searching and selecting the best lair. For that, the seal pup performs a random walk to find a new lair. Stimulated by the sensitive nature of seals against external noise, the random walk is based on two search modes, normal mode and urgent mode. In normal mode, the pup moves between closely adjacent lairs via a Brownian walk. In urgent mode, the pup leaves the proximity area far away and performs a Levy walk to find a new lair from sparse targets. The switch between these two modes is realized by the random noise emitted by predators. The proposed framework can efficiently mimic seal pups behavior to find best location and provide a new approach to be used in global optimization problems.

The consumption of energy has significantly increased in the world during the preceding decade. Two-third of energy requirements are produced by oil and gas. Estimation of oil consumption can give clues on the future energy consumption. In this study, the effectiveness of three hybrid metaheuristic algorithms, namely, Cuckoo Search Neural Network (CSNN), Artificial Bee Colony Neural Network (ABCNN), and Genetic Algorithm Neural Network (GANN) were investigated for the estimation of oil consumption. The simulation results showed that the CSNN improved the estimation accuracy of oil consumption over ABCNN and GANN whereas GANN improved convergence speed over CSNN and ABCNN. The study has shown that in terms of accuracy, the CSNN is appropriate for the estimation of oil consumption. In terms of convergence speed, GANN is the most suitable algorithms for the application. The estimation of oil consumption is required by the Middle East region for monitoring and control of carbon dioxide emissions, development of energy efficient economy, etc. It can be used by intergovernmental organizations and government in the creation of policy issues related to global energy consumption.

Fuzzy k-partition (FkP) is an effective clustering technique, which is mathematical model based. Thus, the objective function of FkP is a nonlinear function. Membership random selection is featured by an iterative process, which results in local optima traps easily. It is important to find global optimal consider to nonlinear objective function of the problem. Moreover, Artificial Bee colony (ABC) has ability and efficiently used for multivariable, multinomial function optimization. To this, this paper proposes the hybridization of FkP based on Artificial Bee colony (ABC) a population based algorithm. Some of benchmarks data sets have been elaborated to test the proposed approach. The experiment shows that FkP ABC obtains better results in term of the dun index validity clustering as compared to the baseline algorithm.

In this study, we select Middle East countries involving Jordan, Lebanon, Oman, and Saudi Arabia for modeling oil consumption based on computational intelligence methods. The limitations associated with Levenberg-Marquardt (LM) Neural Network (NN) motivated this research to optimize the parameters of NN through Artificial Bee Colony Algorithm (ABC-LM) to build a model for the prediction of oil consumption. The proposed model was competent to predict oil consumption with improved accuracy and convergence speed. The ABC-LM performs better than the standard LMNN, Genetically optimized NN, and Back-propagation NN. The proposed model may guide policy makers in the formulation of domestic and international policies related to oil consumption and economic development. The approach presented in the study can easily be implemented into a software for use by the government of Jordan, Lebanon, Oman, and Saudi Arabia.