Kamal M. Jambi

LSHADE with semi-parameter adaptation hybrid with CMA-ES for solving CEC 2017 benchmark problems

To improve the optimization performance of LSHADE algorithm, an alternative adaptation approach for the selection of control parameters is proposed. The proposed algorithm, named LSHADE-SPA, uses a new semi-parameter adaptation approach to effectively adapt the values of the scaling factor of the Differential evolution algorithm. The proposed approach consists of two different settings for two control parameters F and Cr. The benefit of this approach is to prove that the semi-adaptive algorithm is better than pure random algorithm or fully adaptive or self-adaptive algorithm. To enhance the performance of our algorithm, we also introduced a hybridization framework named LSHADE-SPACMA between LSHADE-SPA and a modified version of CMA-ES. The modified version of CMA-ES undergoes the crossover operation to improve the exploration capability of the proposed framework. In LSHADE-SPACMA both algorithms will work simultaneously on the same population, but more populations will be assigned gradually to the better performance algorithm. In order to verify and analyze the performance of both LSHADE-SPA and LSHADE-SPACMA, Numerical experiments on a set of 30 test problems from the CEC2017 benchmark for 10, 30, 50 and 100 dimensions, including a comparison with LSHADE algorithm are executed. Experimental results indicate that in terms of robustness, stability, and quality of the solution obtained, of both LSHADE-SPA and LSHADE-SPACMA are better than LSHADE algorithm, especially as the dimension increases.

Analysis of Cybersecurity Based on Li-Fi in Green Data Storage Environments

Industrial networking has many issues based on the type of industries, data storage, data centers, and cloud computing, etc. Green data storage improves the scientific, commercial and industrial profile of the networking. Future industries are looking for cybersecurity solution with the low-cost resources in which the energy serving is the main problem in the industrial networking. To improve these problems, green data storage will be the priority because data centers and cloud computing deals with the data storage. In this analysis, we have decided to use solar energy source and different light rays as methodologies include a prism and the Li-Fi techniques. In this approach, light rays sent through the prism which allows us to transmit the data with different frequencies. This approach provides green energy and maximum protection within the data center. As a result, we have illustrated that cloud services within the green data center in industrial networking will achieve better protection with the low-cost energy through this analysis. Finally, we have to conclude that Li-Fi enhances the use of green energy and protection which are advantages to current and future industrial networking.

Double Cache Approach with Wireless Technology for Preserving User Privacy

Several methods use cache for decreasing the number of connections to protect privacy of user data and improve performance in Location Based Services (LBS). Many of these methods require users to trust other users or third parties, which could be servers. An intruder could be disguised as a user or a third party. In this article, we propose a new method, known as “Double Cache Approach”, which uses a pair of caches to reduce the vulnerability of trust between users or third party and offers a vast improvement in privacy and security of user data in healthcare and other applications that use LBS. This approach divides the area into many cells and manages the cooperation among users within two caches at the access point with wireless communication. To demonstrate the superiority, we also provide simulation results of user queries, comparing the proposed method with those using only one cache. We believe that our approach would solve the trust problem optimally, achieve a comprehensive protection for users’ data, and enhance the privacy and security levels.

Agent-Based System for Efficient kNN Query Processing with Comprehensive Privacy Protection

Recently, location based services (LBSs) have become increasingly popular due to advances in mobile devices and their positioning capabilities. In an LBS, the user sends a range of queries regarding his k-nearest neighbors (kNNs) that have common points of interests (POIs) based on his real geographic location. During the query sending, processing, and responding phases, private information may be collected by an attacker, either by tracking the real locations or by analyzing the sent queries. This compromises the privacy of the user and risks his/her safety in certain cases. Thus, the objective of this paper is to ensure comprehensive privacy protection, while also guaranteeing the efficiency of kNN query processing. Therefore, we propose an agent-based system for dealing with these issues. The system is managed by three software agents (selectorDL, fragmentorQ, and predictor). The selectorDL agent executes a Wise Dummy Selection Location (WDSL) algorithm to ensure the location privacy. The mission of the selectorDL agent is integrated with the mission of the fragmentorQ agent, which is to ensure the query privacy based on Left-Right Fragmentation (LRF) algorithm. To guarantee the efficiency of kNN processing, the predictor agent executes a prediction phase depending on a Cell Based Indexing (CBI) technique. Compared to similar privacy protection approaches, the proposed WDSL and LRF approaches showed higher resistance against location homogeneity attacks and query sampling attacks. In addition, the proposed CBI indexing technique obtains more accurate answers to kNN queries than the previous indexing techniques.

Preserving Privacy of Smart Cities Based on the Fog Computing

The Smart city is a modern day technological concept which uses sensors, advanced communication technologies and data analysis for maximizing operational efficiency of services offered by the government to its citizens. Mobile devices are the backbone of the smart cities. These mobile devices rely heavily on clouds or fog computing to compensate their low processing capabilities. This brings new challenges to security and privacy of the users of mobile devices. In this paper we focused on the idea of utilizing fog computing properties like caching, cooperating between themselves, playing as a broker between users and cloud. We presented three novel approaches for satisfying the required privacy of the mobile devices in smart cities using fog computing. This paper is the preliminary stage of our work in progress. In future we will present this research in a comprehensive manner.

A fedearted E-learning cloud system based on mixed reality

The continuous evolution of new technologies and devices encourage researchers and specialists, in learning and E-learning domain, to take advantage of them in order to enhance learning and E-learning tasks. Due to its flexibility and some other benefits compared to the conventional learning, E-learning gained a lot from the field of learning and training. Cloud computing presents today a very important low-cost infrastructure which can respond to all kinds of software and hardware user needs. In this paper, we propose a federated E-learning cloud system capable of enhancing, substantially, the quality of E-learning by using the mixed reality technology. Actually, our system is intended to be used by any learner including those having some special needs (talent and smart peoples). One of the attractive sides of the proposed system is its capability to use existing courses and learning objects provided on the Internet in order to deliver them to the end-user in a customized manner. The proposed system is intended to be built on a federated cloud infrastructure as a set of ubiquitous services that can be accessed by any user.

Universal metadata repository for document analysis and recognition

Document Analysis and Recognition (DAR) has two main objectives, first the analysis of the physical structure of the input image of the document, which should lead to the correct identification of the corresponding different homogeneous components and their boundaries in terms of XY coordinates. Second, each of these homogeneous components should be recognized in such a way that, if it is a text image, consequently this image should be recognized and translated into an intelligible text. DAR remains one of the most challenging topics in pattern recognition. Indeed, despite the diversity of the proposed approaches, techniques and methods, results remain very weak and away from expectations especially for several categories of documents such as complex, low quality, handwritten and historical documents. The complex structure and/or morphology of such documents are behind the weakness of results of these proposed approaches, techniques and methods. One of the challenging problems related to this topic is the creation of standard datasets that can be used by all stakeholders of this topic such as system developers, expert evaluators, and users. In addition, another challenging problem is how one could take advantages of all existing datasets that unfortunately are dispersed around the world without knowing, most of the times, any information about their locations and the way to reach them. As an attempt to solve the two mentioned above problems, we propose in this paper a Universal Datasets Repository for Document Analysis and Recognition (UMDAR) that has, in fact, a twofold advantage. First, it can help dataset creators to standardize their datasets and making them accessible to the research community once published on the proposed repository. Second, it can be used as a central which bridges in a smart manner between datasets and all DAR stakeholders.

Big Data Knowledge Mining

Big Data (BD) era has been arrived. The ascent of big data applications where information accumulation has grown beyond the ability of the present programming instrument to catch, manage and process within tolerable short time. The volume is not only the characteristic that defines big data, but also velocity, variety, and value. Many resources contain BD that should be processed. The biomedical research literature is one among many other domains that hides a rich knowledge. MEDLINE is a huge biomedical research database which remain a significantly underutilized source of biological information. Discovering the useful knowledge from such huge corpus leading to many problems related to the type of information such as the related concepts of the domain of texts and the semantic relationship associated with them. In this paper, an agent-based system of two–level for Self-supervised relation extraction from MEDLINE using Unified Medical Language System (UMLS) Knowledgebase, has been proposed . The model uses a Self-supervised Approach for Relation Extraction (RE) by constructing enhanced training examples using information from UMLS with hybrid text features. The model incorporates Apache Spark and HBase BD technologies with multiple data mining and machine learning technique with the Multi Agent System (MAS). The system shows a better result in comparison with the current state of the art and naive approach in terms of Accuracy, Precision, Recall and F-score.

Mobile Agent Framework for Distributed Network Performance Management

traditional centralized network management approach presents severe efficiency and scalability limitations in large scale networks. The process of data collection and analysis typically involves huge transfers of management data to the manager which consumes considerable network bandwidth and causes bottlenecks at the manager side. Mobile agent technology provides an effective solution to alleviate this burden by distributing the management functionality over the network elements. A Mobile Agent has the ability to autonomously move among network elements to perform the required tasks locally. Thus, the code is transferred to the data location instead of moving the entire data to the managers site. The present study aims to investigate the effectiveness of using mobile agents to overcome the limitations of the centralized structure. Focusing on the network performance management functional area, a prototype is developed to assess the effectiveness of a distributed mobile-agent-based network management system. The developed prototype installs itself automatically on remote machines and periodically checks their software and hardware status. Experiments are done to measure the network traffic volume when managing a typical network. Practical measurements are compared for the traffic generated by both the developed prototype and the current centralized network management standard (SNMP). This comparison confirms that mobile- agent-based management employs much less traffic than the centralized system. An estimation of the required management delays is provided for both sequential- and parallel- dispatching of the mobile agents.