Firas Albalas

A Fog Computing Based System for Selective Forwarding Detection in Mobile Wireless Sensor Networks

Intrusions detection is one of the major issues that worry organizations in wireless sensor networks (WSNs). Many researchers have dealt with this problem and have proposed many methods for detecting different kinds of intrusions such as selective forwarding, which is a serious attack that may obstruct communications in WSNs. However, as the applications of mobile computing, vehicular networks, and internet of things (IoT) are spreading immensely, selective forwarding detection in Mobile Wireless Sensor Networks (MWSNs) has become a key demand. This paper introduces the problem of selective forwarding in MWSNs, and discusses how available techniques for mitigation this problem in WSNs are not applicable in handling the problem in MWSNs due to sensors mobility. Therefore, the paper proposes a model that provides a global monitoring capability for tracing moving sensors and detecting malicious ones. The model leverages the infrastructure of Fog Computing to achieve this purpose. Furthermore, the paper provides a complete algorithm, a comprehensive discussion and experiments that show the correctness and importance of the proposed approach.

Exploiting GPUs to accelerate clustering algorithms

Big data is a main problem for data mining methods. Fortunately, the rapid advances in affordable high performance computing platforms such as the Graphics Processing Unit (GPU) have helped researchers in reducing the execution time of many algorithms including data mining algorithms. This paper discusses the utilization of the parallelism capabilities of the GPU to improve the the performance of two common clustering algorithms, which are K-Means (KM) and Fuzzy C-Means (FCM) algorithms. Two main parallelism approaches are presented: pure and hybrid. These different versions are tested under different settings including two different GPU-equipped machines (a laptop and a server). The results show excellent improvement gains of the hybrid implementations compared with the pure parallel and sequential ones. On the laptop, the best gains of the hybrid implementations compared with the sequential ones are 11.3X for KM and 10.9X for FCM. As for the server, the best gains are 13.5X for KM and 16.3X for FCM. Moreover, the paper explores the usage of a recent memory management technique for GPU called Unified Memory (UM). The results show a decrease in the performance gain of the hybrid implementations that is equal to 44% for hybrid version of KM and 61% for FCM. On the other hand, the use of UM does introduce a small advantage for the pure parallel implementation.