This research presents a new hybridized evolutionary artificial intelligence (AI) model for modeling depth scouring under submerged weir ( d s ). The proposed model is based on the hybridization of the Extreme Gradient Boosting (XGBoost) model and genetic algorithm (GA) optimizer. The GA is hybridized to solve the hyper-parameter problem of the XGBoost model and to recognize the influential input predictors of d s . The proposed XGBoost-GA model is developed based on the incorporation of fifteen physical parameters of submerged weir. The feasibility of the XGBoost-GA model is validated against several well-established AI models introduced in the literature in addition to a hybrid XGBoost-Grid model. Several statistical performance metrics is computed for the modeling evaluation in parallel with a graphical assessment. Based on the attained prediction results, the proposed model revealed an optimistic and superior predictability performance with a maximum coefficient of determination ( R 2 = 0.933) and a minimum root mean square error ( RMSE = 0.014 m). In addition, the XGBoost-GA model demonstrated reliable feature selection for the essential physical parameters. The fifteen parameters are re-scaled to seven parameters based on their essential impacts on the d s determination.

Feature selection (FS) is a challenging data mining problem that incorporates a complex search process to find the most informative feature subset. In the brute force methods generating the entire feature space and applying an exhaustive search makes the FS NP-hard problem. Meta-heuristic algorithms are good alternative solutions that provide (near) optimal solutions through a random search process instead of a complete search. In this paper, an FS approach based on the Moth Flame optimization algorithm (MFO) and k-NN classifier are proposed. MFO is a recent meta-heuristic algorithm that has proved its effectiveness in solving different complex problems in a reasonable time. Nevertheless, the performance of MFO highly depends on achieving a balance between exploration and exploitation during the search process. To address this issue, we propose an adaptive method to update the position of a moth toward the best global solution based on the search status. The proposed MFO has been evaluated using sixteen benchmark medical data sets and the results show promising performance of the modified MFO algorithm in terms of the applied evaluation measures.

Clustering large data is one of the recently challenging tasks that is used in many application areas such as social networking, bioinformatics and many others. Traditional clustering algorithms need to be modified to handle the increasing data sizes. In this paper, a scalable design and implementation of glowworm swarm optimization clustering (MRCGSO) using MapReduce is introduced to handle big data. The proposed algorithm uses glowworm swarm optimization to formulate the clustering algorithm. Glowworm swarm optimization is used to take advantage of its ability in solving multimodal problems, which in terms of clustering means finding multiple centroids. MRCGSO uses the MapReduce methodology for the parallelization since it provides fault tolerance, load balancing and data locality. The experimental results reveal that MRCGSO scales very well with increasing data set sizes and achieves a very close to linear speedup while maintaining the clustering quality.

The increasing volume of data in large networks to be analyzed imposes new challenges to an intrusion detection system. Since data in computer networks is growing rapidly, the analysis of these large amounts of data to discover anomaly fragments has to be done within a reasonable amount of time. Some of the past and current intrusion detection systems are based on a clustering approach. However, in order to cope with the increasing amount of data, new parallel methods need to be developed in order to make the algorithms scalable. In this paper, we propose an intrusion detection system based on a parallel particle swarm optimization clustering algorithm using the MapReduce methodology. The use of particle swarm optimization for the clustering task is a very efficient way since particle swarm optimization avoids the sensitivity problem of initial cluster centroids as well as premature convergence. The proposed intrusion detection system processes large data sets on commodity hardware. The experimental results on a real intrusion data set demonstrate that the proposed intrusion detection system scales very well with increasing data set sizes. Moreover, it achieves close to the linear speedup by improving the intrusion detection and false alarm rates.

High-quality clustering techniques are required for the effective analysis of the growing data. Clustering is a common data mining technique used to analyze homogeneous data instance groups based on their specifications. The clustering based nature-inspired optimization algorithms have received much attention as they have the ability to find better solutions for clustering analysis problems. Glowworm Swarm Optimization (GSO) is a recent nature-inspired optimization algorithm that simulates the behavior of the lighting worms. GSO algorithm is useful for a simultaneous search of multiple solutions, having different or equal objective function values. In this paper, a clustering based GSO is proposed (CGSO), where the GSO is adjusted to solve the data clustering problem to locate multiple optimal centroids based on the multimodal search capability of the GSO. The CGSO process ensures that the similarity between the cluster members is maximized and the similarity among members from different clusters is minimized. Furthermore, three special fitness functions are proposed to evaluate the goodness of the GSO individuals in achieving high quality clusters. The proposed algorithm is tested by artificial and real-world data sets. The better performance of our proposed algorithm over four popular clustering algorithms is demonstrated on most data sets. The results reveal that CGSO can efficiently be used for data clustering.

In optimization problems, such as highly multimodal functions, many iterations involving complex function evaluations are required. Glowworm Swarm Optimization (GSO) has to be parallelized for such functions when large populations capturing the complete function space, are used. However, large-scale parallel algorithms must communicate efficiently, involve load balancing across all available computer nodes, and resolve parallelization problems such as the failure of nodes. In this paper, we outline how GSO can be modeled based on the MapReduce parallel programming model. We describe MapReduce and present how GSO can be naturally expressed in this model, without having to explicitly handle the parallelization details. We use highly multimodal benchmark functions for evaluating our MR-GSO algorithm. Furthermore, we demonstrate that MR-GSO is appropriate for optimizing difficult evaluation functions, and show that high function peak capture rates are achieved. We show with the experiments that adding more nodes would help to solve larger problems without any modifications to the algorithm structure.