Browsing by Author "Tari, Abdelkamel"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    A distributed security protocol designed for the context of Internet of Things
    (Association for Computing Machinery, 2018) Laouid, Abdelkader; Muath, AlShaikh; Lalem, Farid; Bounceur, Ahcène; Euler, Reinhardt; Bezoui, Madani; Aissaoua, Habib; Tari, Abdelkamel
    In the field of Internet of Things (IoT), many encryption protocols for distributed wireless communication technology have been proposed for use in various applications such as monitoring, healthcare, product management, workplace, home support and surveillance [1]. An IoT system can be looked at as a highly dynamic distributed and networked system composed of a large number of smart devices. In fact, such connected devices suffer from the limitation of resources in terms of computing, energy, bandwidth and storage. Hence, IoT application scenarios require methods to adapt to highly diverse contexts with different available resources and possibly dynamic environments. In this paper, we address these issues by proposing an efficient technique for data protection in the context of IoT. A distributed network architecture is used, where each node is in charge to deliver and/or forward data. The aim is to use efficient operations to protect the exchanged data. The proposed technique ensures the exchanged data to be effectively and securely controlled with a low overhead compared to the classical approaches. The proposed protocol shows its efficiency in terms of overhead, speed, energy and security measurements.
  • No Thumbnail Available
    Item
    Using Machine Learning for Heart Disease Prediction
    (Springer, 2021) Salhi, Dhai Eddine; Tari, Abdelkamel; Tahar Kechadi, M.
    In this paper we carried out research on heart disease from data analytics point of view. Prediction of heart disease is a very recent field as the data is becoming available. Other researchers have approached it with different techniques and methods. We used data analytics to detect and predict disease’s patients. Starting with a pre-processing phase, where we selected the most relevant features by the correlation matrix, then we applied three data analytics techniques (neural networks, SVM and KNN) on data sets of different sizes, in order to study the accuracy and stability of each of them. Found neural networks are easier to configure and obtain much good results (accuracy of 93%).