Rasha M. Ismail

An Enhanced Resource Allocation Approach for Optimizing Sub Query on Cloud

Cloud computing is the latest evolution of computing. It provides services to numerous remote users with different requests. Managing the query workload in cloud environment is a challenge to satisfy the cloud users. Improving the overall performance and response time of the query execution can lead to users’ satisfaction. In this paper, we examine the problem of the slow query response time. Sub query merging and query resource allocation approaches are proposed to minimize the query execution time.

Efficient optimized query mesh for data streams

Most of query optimizers choose a single query plan for processing all the data based on the average data statistics. But this plan is usually not efficient with the uncertain stream datasets of modern applications as network monitoring, sensor networks and financial applications; where these data have continuous variations over time. In this paper we propose an optimized query mesh for data stream (OQMDS) frameworks. In which, process data streams over multiple query plans, each of them is optimal for the sub-set of data with the same statistics. The OQMDS solution depends on preparing multiple query plans and continuously chooses the best execution plan for each sub-set of incoming data streams based on their statistics. We also propose two optimization algorithms called Optimized Iterative Improvement Query Mesh (OII-QM) and Non-Search based Query Mesh (NS-QM) algorithms, to efficiently generate the multiple plans (the optimized QM solution) which are used to process the online data streams. Our experimental results show that, the proposed solution OQMDS improves the overall performance of data stream processing.

A novel social network mining approach for customer segmentation and viral marketing

Emergence of social networks facilitates individuals to communicate, share opinions and form communities. Organizations benefit from social networks in monitoring customers’ behavior. Social networks mining and analysis aims to segment customers and determine the most influential actors for viral marketing. In this article, we propose a novel social network mining approach for influential analysis and community detection. The community detection task benefits from the most influential users in the network. The proposed approach identifies the most influential users by using a direct mining leaders discovery algorithm and uses these leaders as core points to expand communities around them. This is based on the observation that communities tend to be formed around users of great influence. Extensive experiments have been completed on a real dataset and results show that our approach can contribute in identifying communities of high quality. WIREs Data Mining Knowl Discov 2016, 6:177–189. doi: 10.1002/widm.1183

An Efficient Hybrid Usage-based Ranking model for information retrieval systems & web search Engine

There are billions of web pages available on the Internet. Search Engines always have a challenge to find the best ranked list to the users query from those huge numbers of pages. A lot of search results that corresponding to a users query are not relevant to the user need. Most of the page ranking algorithms use Link-based ranking (web structure) or Content-based ranking to calculate the relevancy of the information to the users need, but those ranking algorithms might be not enough to provide a good ranked list. So, in this paper we proposed an Efficient Hybrid Usage-based Ranking Algorithm called EHURA. EHURA was applied to 1033 English Corpus to measure its performance. The result shows improvement of the precision for using EHURA over the Content-based ranking algorithm representation while realizing approximately the same recall percentage.

Maintenance of materialized views over peer-to-peer data warehouse architecture

The view maintenance issues are very important in the data warehouse process as its goal to make the data warehouse always consistent with its sources but it generates big challenges in the P2P environments. The materialized views maintenance problem take a lot of attention in distributed data warehouse but in the Peer to peer (P2P) systems there is little attention to it. Thus, the Peer Joining Real Time Data Warehouse Algorithm (PJRT) is introduced to maintain the materialized views on our peerDW architecture that proposed in [1] in order to reduce the maintenance time in P2P architecture. The performance of the PJRT was measured by comparing it to the existing the view maintenance algorithm (VM) algorithm [2]. Then the PJRT is compared to The Joining Real Time Data Warehouse Algorithm (JRT) that work upon Distributed DW and proposed in [3] to observe the effect of the peer architecture on the maintenance time.

Optimized Elastic Query Mesh for Cloud Data Streams

Many recent applications in several domains such as sensor networks, financial applications, network monitoring and click-streams generate continuous, unbounded, rapid, time varying datasets which are called data streams. In this paper we propose the optimized and elastic query mesh (OEQM) framework for data streams processing based on cloud computing to suit the changeable nature of data streams. OEQM processes the streams tuples over multiple query plans, each plan is suitable for a sub-set of data with the nearest properties and it provides elastic processing of data streams on the cloud environment. We also propose the Auto Scaling Cloud Query Mesh (AS-CQM) algorithm that supports streams processing with multiple plans and provides elastic scaling of the processing resources on demand. Our experimental results show that, the proposed solution OEQM reduces the cost for data streams processing on the cloud environment and efficiently exploits cloud resources.

An efficient framework based on usage and semantic data for next page prediction

The World Wide Web is becoming the most important source to search for information or products. But the size and the unstructured nature of the available information makes the location of the right information a challenging task. Recommender systems and web usage mining techniques are two of the main methods used to overcome information overload. In this paper, we present a framework for the next page prediction that exploits users’ access history combined with his semantic interests to generate personalized and accurate recommendations. We are suggesting two different approaches for decision fusion between usage and semantic data. The two proposed techniques offered a 47.3% and 54.3% improvement in prediction accuracy over conventional methods for next page prediction. The suggested framework also employs user clustering to focus the search which reduced the prediction time by an average of 68.7% and 63.4%.

Queries Based Workload Management System for the Cloud Environment

Workload management for concurrent queries is one of the challenging aspects of executing queries over the cloud computing environment. The core problem is to manage any unpredictable load imbalance with respect to varying resource capabilities and performances. Key challenges raised by this problem are how to increase control over the running resources to improve the overall performance and response time of the query execution. This paper proposes an efficient workload management system for controlling the queries execution over cloud environment. The paper presents an architecture to improve the query response time by detecting any load imbalance over the resources. Also, responding to the queries dynamically by rebalancing the query executions across the resources. The results show that applying this Workload Management System improves the query response time by 68%.

An Adaptive Information Retrieval System for Efficient Web Searching

Stemming algorithms (stemmers) are used to convert the words to their root form (stem), this process is used in the pre-processing stage of the Information Retrieval Systems. The Stemmers affect the indexing time by reducing the size of index file and improving the performance of the retrieval process. There are several stemming algorithms, the most widely used is porter stemming algorithm because of its efficiency, simplicity, speed, and also it easily handles exceptions. However there are some drawbacks, although many attempts were made to improve its structure but it was incomplete. This paper provides an efficient information retrieval technique as well as proposes a new stemming algorithm called Enhanced Porter’s Stemming Algorithm (EPSA). The objective of this technique is to overcome the drawbacks of the porter algorithm and improve the web searching. The EPSA was applied to two datasets to measure its performance. The result shows improvement of the precision over the original porter algorithm while realizing approximately the same recall percentage.

Cloud-based data streams optimization

Many modern applications of sensor networks and transaction analysis require real‐time processing of their stream data sets. These data streams vary continuously over time. Current stream processing approaches focus on only one of the two optimization perspectives, proposing optimization techniques for data streams processing regardless of the processing environment or improving the processing environment only. In this paper, a brief survey of recent approaches to data streams processing coming from the two optimizations perspectives is proposed; their shortcomings are presented as well. Then, a proposal to an innovative and integrative framework is developed; it is referred to as the continuous query optimization based on multiple plans (CQOMP) for data streams over the cloud environment. CQOMP combines the two optimization perspectives and provides an optimized stream clusters processing using multiple split query plans. Each plan is constructed for a cluster of data that has nearest characteristics and it processes streams tuples over the cloud. We also propose a novel algorithm called the optimized multiple plans (OMP) for processing data streams clusters on Cloud Computing. The OMP algorithm efficiently divides data streams and generates optimized multiple split plans. Each plan is for processing a group of data streams on the cloud. We present the experimental results of the OMP solution compared to the alternative state‐of‐the‐art data stream approaches. The experiments show the efficiency and the scalability of the combined OMP algorithm on different cloud environments, the real Amazon cloud environment, and the simulated windows azure cloud environment.