- Volume 0
- Issue 1
- (4) Articles
MAHMOUD A. SALAM
,
M.M.EL-GAYAR
There are many challenges facing the service composition process. These challenges include, how to integrate services to satisfy global user requirements, missing or changeable values of QoS, and how to reduce the large solution space of candidate services. In this paper, we proposed a framework to address these challenges. The proposed framework consists of three phases. The Normalizer phase gives a certain range for all QoS attributes and historical user orders. During the Clustering phase, the search space is reduced. Finally, the composition process is done, and a list of candidate composite services is generated through the Service composer phase. We present the hybrid bio-inspiration technique to implement the proposed framework and prove its applicability. In addition, we introduced the MR-FPSO algorithm to implement this phase by merging PSO and FOA optimization algorithms over the MapReduce framework to handle the large scale of data in the cloud environment. Our technique is compared to different techniques, including MR-GA, MR-IDPSO, and MRPSO. The simulation results proved that our technique outperforms the other techniques.
Read More
Doi: https://doi.org/10.54216/JCIM.000101
Vol. 0
Issue. 1
PP. 05-14, (2019)
Hisham Elhoseny
,
Hazem EL-Bakry
The Service Oriented Architecture (SOA) are used to integrate and manage the city services through a standard framework that has the capacity to develop, deploy and managed the functions that support the components of the city infrastructure. The objective of SOA implementation is to employ sophisticated IT processes that produce continuous, rapid business change outcomes. The aim of this paper is to present current research of the emergence of SOAs considering the trends in urbanization along with the evolution of technology and ubiquitous computing. This paper will explore current trends in development and utilization of Service Oriented Architectures (SOAs) in Smart Cities and propose an SOA framework that will address the challenges of urban planning and development. Advantages of the SOA if we used it for a Smart City Application can be described as the following: Integrate the physical infrastructures of the city such as the transportation sector, utilities, land, and city services, Flexibility, Scalability and Business agility, Easier Testing and Debugging, Reusability, Platform independence, Increased Productivity, SOA enables business decisions to be translated rapidly into technology. Internet of things (IoT) brings unprecedented changes to all contexts of our lives, as they can be informed by smart devices and real-time data. Among the various IoT application settings, e-government seems to be one that can be greatly benefited using IoT, transforming and augmenting public services.
Read More
Doi: https://doi.org/10.54216/JCIM.000102
Vol. 0
Issue. 1
PP. 15-31, (2019)
Andino Maseleno
Cybersecurity is the process of protecting critical systems and confidential data from digital attacks. With the advent of machine learning, cybersecurity systems can examine the patterns and learns them from preventing similar attacks and responds to fluctuating behavior. Cybersecurity intrusion detection system helps to detect the existence of intrusions in the network and achieves security in confidential data storage and transmission. In this view, this study designs an efficient cockroach optimization (CSO) with kernel extreme learning machine (KELM) model for cybersecurity intrusion detection. The proposed CSO-KELM model can accomplish cybersecurity by the detection and classification of intrusions. The proposed CSO-KELM technique encompasses a three-level process, namely preprocessing, classification, and parameter tuning. The design of the CSO algorithm for the appropriate selection of KELM parameters results in improved classification performance. For examining the betterment of the CSO-KELM technique, a series of experiments were performed on benchmark datasets. The experimental results pointed out the superiority of the CSO-KELM technique concerning several measures.
Read More
Doi: https://doi.org/10.54216/JCIM.000103
Vol. 0
Issue. 1
PP. 32-43, (2019)
Salah-ddine KRIT
Botnet detection becomes a challenging issue in several domains like cybersecurity, finance, healthcare, law, order, etc. The botnet represents a set of cooperated Internet-linked devices managed by cyber criminals to start coordinated attacks and carry out different malicious events. As the botnets are seamlessly dynamic with the developing countermeasures presented by network and host-based detection schemes, conventional methods have failed to achieve enough safety for botnet threats. Therefore, machine learning (ML) models have been developed to detect and classify botnets for cybersecurity. In this view, this paper performs a comprehensive evaluation of different ML-based botnet detection and classification models. The botnet detection model involves a three-stage process, namely preprocessing, feature extraction, and classification. In this study, four ML models such as C4.5 Decision Tree, bagging, boosting, and Adaboost are employed for classification purposes. To highlight the performance of the four ML models, an extensive set of simulations was performed. The obtained results pointed out that the ML models can attain enhanced botnet detection performance.
Read More
Doi: https://doi.org/10.54216/JCIM.000104
Vol. 0
Issue. 1
PP. 44-53, (2019)
