Understanding node mobility is critical for the proper simulation of mobile devices in a wireless network. However, current mobility models often do not reflect the realistic movements of users within their environments. They also do not provide the freedom to adjust their degrees of randomness or adequately mimic human movements by injecting possible crossing points and adding recurrent patterns. In this paper, we propose the recurrent self-similar Gauss–Markov mobility (RSSGM) model, a novel mobility model that is suitable for applications in which nodes exhibit recurrent visits to selected locations with semi-similar routes. Examples of such applications include daily human routines, airplane and public transportation routes, and intra-campus student walks. First, we present the proposed algorithm and its assumptions, and then we study its behavior in different scenarios. The study’s results show that different and more realistic mobility traces can be achieved without the need for complex computational models or existing GPS records. Our model can flexibly adjust its behavior to fit any application by carefully tuning and choosing the right values for its parameters.

Artificial intelligence (AI) is a fundamental part of improving information technology systems. Essential AI techniques have revolutionized communication technology, such as mobility models and machine learning classification. Mobility models use a virtual testing methodology to evaluate new or updated products at a reasonable cost. Classifiers can be used with these models to achieve acceptable predictive accuracy. In this study, we analyzed the behavior of machine learning classification algorithms—more specifically decision tree (DT), logistic regression (LR), k-nearest neighbors (K-NN), latent Dirichlet allocation (LDA), Gaussian naive Bayes (GNB), and support vector machine (SVM)—when using different mobility models, such as random walk, random direction, Gauss–Markov, and recurrent self-similar Gauss–Markov (RSSGM). Subsequently, classifiers were applied in order to detect the most efficient mobility model over wireless nodes. Random mobility models (i.e., random direction and random walk) provided fluctuating accuracy values when machine learning classifiers were applied—resulting values ranged from 39% to 81%. The Gauss–Markov and RSSGM models achieved good prediction accuracy in scenarios using a different number of access points in a defined area. Gauss–Markov reached 89% with the LDA classifier, whereas RSSGM showed the greatest accuracy with all classifiers and through various samples (i.e., 2000, 5000, and 10,000 steps during the whole experiment). Finally, the decision tree classifier obtained better overall results, achieving 98% predictive accuracy for 5000 steps.