Search

The node deployment problem is a non-deterministic polynomial time (NP-hard). This study proposes a new and efficient method to solve this problem without the need for predefined circumstances about the environments independent of terrain. The proposed method is based on a metaheuristic algorithm and mimics the grey wolf optimizer (GWO) algorithm. In this study, we also suggested an enhanced version of the GWO algorithm to work adaptively in such problems and named it Mutant-GWO (MuGWO). Also, the suggested model ensures connectivity by generating topology graphs and potentially supports data transmission mechanisms. Therefore, the proposed method based on MuGWO can enhance resources utilization, such as reducing the number of nodes, by maximizing the coverage rate and maintaining the connectivity. While most studies assume classical rectangle uniform environments, this study also focuses on custom (environment-aware) maps in line with the importance and requirements of the real world. The motivation of supporting custom maps by this study is that environments can consist of custom shapes with prioritized and critical areas. In this way, environment awareness halts the deployment of nodes in undesired regions and averts resource waste. Besides, novel multi-purpose fitness functions of the proposed method satisfy a convenient approach to calculate costs instead of using complicated processes. Accordingly, this method is suitable for large-scale networks thanks to the capability of the distributed architecture and the metaheuristic-based approach. This study justifies the improvements in the suggested model by presenting comparisons with a Deterministic Grid-based approach and the Original GWO. Moreover, this method outperforms the fruit fly optimization algorithm, bat algorithm (BA), Optimized BA, harmony search, and improved dynamic deployment technique based on genetic algorithm methods in declared scenarios in literature, considering the results of simulations. [ABSTRACT FROM AUTHOR]

The performance of a model in machine learning problems highly depends on the dataset and training algorithms. Choosing the right training algorithm can change the tale of a model. While some algorithms have a great performance in some datasets, they may fall into trouble in other datasets. Moreover, by adjusting hyperparameters of an algorithm, which controls the training processes, the performance can be improved. This study contributes a method to tune hyperparameters of machine learning algorithms using Grey Wolf Optimization (GWO) and Genetic algorithm (GA) metaheuristics. Also, 11 different algorithms including Averaged Perceptron, FastTree, FastForest, Light Gradient Boost Machine (LGBM), Limited memory Broyden Fletcher Goldfarb Shanno algorithm Maximum Entropy (LbfgsMxEnt), Linear Support Vector Machine (LinearSVM), and a Deep Neural Network (DNN) including four architectures are employed on 11 datasets in different biological, biomedical, and nature categories such as molecular interactions, cancer, clinical diagnosis, behavior related predictions, RGB images of human skin, and X-rays images of Covid19 and cardiomegaly patients. Our results show that in all trials, the performance of the training phases is improved. Also, GWO demonstrates a better performance with a p-value of 2.6E-5. Moreover, in most experiment cases of this study, the metaheuristic methods demonstrate better performance and faster convergence than Exhaustive Grid Search (EGS). The proposed method just receives a dataset as an input and suggests the best-explored algorithm with related arguments. So, it is appropriate for datasets with unknown distribution, machine learning algorithms with complex behavior, or users who are not experts in analytical statistics and data science algorithms. [Display omitted] • The proposed method can improve the performance of the machine learning model independent from the composition of datasets. • It assists to gain a better performance faster than tuning by blindly and randomly chosen hyperparameters. • The idea of this method is general and it is not specific to a limited number of training algorithms and optimizers. • This method is convenient to use for users who are not experts in algorithm designing, also for real-world problems. • Generally, metaheuristic methods give better result and converge faster than blind approaches like Exhaustive Grid Search. [ABSTRACT FROM AUTHOR]