Machine Learning (ML) is a science that forces computers to learn and behave like humans. As these systems interact with data, networks, and people, they automatically become smarter so that they can eventually solve or predict a practical issue in the world for us. The use of ML can be a giant leap for cannot simply be integrated as the top layer. This requires redefining workflow, architecture, data collection and storage, analytics, and other modules. This paper aims to discuss the issue of machine learning technique for analysis data of mobile user. First, we identified the machine learning benefits and drawbacks, challenges, advantages of using Machine Learning. Then, we propose a generic model of analytic mobile user data using ML, the model is centered on the machine learning component, which interacts with two other components, including mobile user data, and system. The interactions go in both directions. For instance, mobile user data serves as inputs to the learning component and the latter generates outputs; system architecture has impact on how learning algorithms should run and how efficient it is to run them, and simultaneously meeting. Mobile user data goes through several stages: prepossessing which includes the steps we need to follow to transform or encode the data so that it can be easily analyzed by the machine. Then, modelling in this step we will be clustering and classification the data obtained. Finally, evaluation, various measures of performance, accuracy, recall, precision, and F-measure were used to analyze the results of the naive Bayes, SVM, and K-nearest neighbor classification algorithms.

This paper addresses the prediction of mobility and emphasizes the main steps of our context-based mobility prediction approach that are trajectory modelling, data processing and prediction process. First, we present our context-based and prediction - oriented trajectory model, which relies on the grid technique for trajectory description. Second, we describe a data processing architecture for data coming from Wifi networks. Third, we focus on our data mining-based prediction process used for the first experimentations. Evaluation of our contributions is performed on a real dataset. First results showed the positive impact of our trajectory model on our mobility prediction process.

Privacy and Security in big data and smart cities play a major role to ensure better quality of citizens life. Privacy emphasizes on the data being collected, shared, and used in the right manner, and security focuses on protecting the data from intruders’ attack, and exploitation of data for other purposes such as criminal behavior. This paper aims to discuss the issue of privacy and security of mobile users in big data and smart cities. First, based on big data privacy and security challenges, classification, and models, we identify the privacy and security requirements for a mobile user. Then, we propose a generic architecture and an algorithm for the management of privacy and security of a mobile user in a smart environment. This architecture groups the main components required for implementing the proposed algorithm that ensure the privacy and security of mobile users in smart cities.

International audience