Authors: Salah Eddine Henouda; Fatima Zohra Laallam; Okba Kazar; Abdessamed Sassi
Addresses: LINATI Laboratory, Department of Computer Science, Kasdi Merbah University, Ouargla, Algeria ' LINATI Laboratory, Department of Computer Science, Kasdi Merbah University, Ouargla, Algeria ' Smart Computer Science Laboratory (LINFI), Computer Science Department, University of Biskra, Algeria; Department of Information Systems and Security, College of Information Technology, United Arab Emirate University, UAE ' Department of Computer Science, Mohamed Khider University, Biskra, Algeria; Department of computer Science, L'arbi Ben Mhidi University, Oum El Bouaghi, Algeria
Abstract: This work seeks to solve the next location prediction problem of mobile users. Chiefly, we focus on ROBERTA architecture (robustly optimised BERT approach) in order to build a next location prediction model through the use of a subset of a large real mobility trace database. The latter was made available to the public through the CRAWDAD project. ROBERTA, which is a well-known model in natural language processing (NLP), works intentionally on predicting hidden sections of text based on language masking strategy. The current paper follows a similar architecture as ROBERTA and proposes a new combination of Bertwordpiece tokeniser and ROBERTA for location prediction that we call WP-BERTA. The results demonstrated that our proposed model WP-BERTA outperformed the state-of-the-art models. They also indicated that the proposed model provided a significant improvement in the next location prediction accuracy compared to the state-of-the-art models. We particularly revealed that WP-BERTA outperformed Markovian models, support vector machine (SVM), convolutional neural networks (CNNs), and long short-term memory networks (LSTMs).
Keywords: machine learning; deep learning; transformer; neural networks; Wi-Fi; mobility traces; next location prediction; big data.
International Journal of Business Intelligence and Data Mining, 2022 Vol.21 No.2, pp.247 - 263
Received: 06 Jan 2021
Accepted: 01 Mar 2021
Published online: 11 Aug 2022 *