IJISA Vol. 14, No. 2, Apr. 2022
Cover page and Table of Contents: PDF (size: 129KB)
It is generally accepted that data production has experienced spectacular growth for several years due to the proliferation of new technologies such as new mobile devices, smart meters, social networks, cloud computing and sensors. In fact, this data explosion should continue and even accelerate. To find all of the documents responding to a request, any information search system develops a methodology to confirm whether or not the terms of each document correspond to those of the user's request. Most systems are based on the assumption that the terms extracted from the documents have been certain and precise. However, there are data in which this assumption is difficult to apply. The main objective of the work carried out within the framework of this article is to propose a new model of data service indexing in an uncertain environment, meaning that the data they contain can be untrustworthy, or they can be contradictory to another data source, due to failure in collection or integration mechanisms. The solution we have proposed is characterized by its Intelligent side ensured by an efficient fuzzy module capable of reasoning in an environment of uncertain and imprecise data. Concretely, our proposed approach is articulated around two main phases: (i) a first phase ensures the processing of uncertain data in a textual document and, (ii) the second phase makes it possible to determine a new method of uncertain syntactic indexing. We carried out a series of experiments, on different bases of standard tests, in order to evaluate our solution while comparing it to the approaches studied in the literature. We used different standard performance measures, namely precision, recall and F_measure. The results found showed that our solution is more efficient and more efficient than the main approaches proposed in the literature. The results show that the proposed approach realizes an efficient Big Data indexing solution in an Uncertain Environment that increases the Precision, the Recall and the F_measure measurements. Experimental results present that the proposed uncertain model obtained the best precision accuracy 0.395 with KDD database and the best recall accuracy 0.254 with the same database.[...] Read more.
The widespread adoption of Unmanned Aerial Vehicles (UAVs) can be traced to its flexibility and wide adaptability to various operating conditions and applications, comparably low cost of construction and maintenance and environmental friendliness as they can be easily configured for electric power. The use of electric power also favours its low noise applications such as surveillance. A major issue associated with surveillance, as addressed in this study is the compromise between Range and Endurance operation modes. The Range mode relates to being able to cover longer distances while the Endurance mode relates to spending longer times in the atmosphere for a fixed charge. Trying to balance the interplay of these parameters gave rise to a multi-objective optimization where the objectives are somewhat conflicting. This resulted in a set of Pareto solutions which are a set of design parameters (primarily angle of attack) that satisfy the joint requirements of the performance parameters of Range and Endurance. This study first considered a baseline aerodynamic design using traditional design methods. Design of Experiment techniques were then used to select the most favourable design points. This model was then used to build an input framework for Genetic Optimization algorithm deployed in the Global Optimization Toolbox of MATLAB. The result of this research shows that most of the region associated with medium angle of attack (AOA) setting (7 degrees) jointly satisfies good Range and Endurance performances with an average lift-to-drag ratio of 20 in the flight configuration considered. The implication of this result is that low velocity drag encountered in surveillance that requires a high AOA is largely reduced with the medium setting, albeit stabilized with other structural and aerodynamic settings, namely an aspect ratio of 13 and a taper ratio of 0.6.[...] Read more.
Due to the rapid growth of the Internet, large amounts of unlabelled textual data are producing daily. Clearly, finding the subject of a text document is a primary source of information in the text processing applications. In this paper, a text classification method is presented and evaluated for Persian and English. The proposed technique utilizes variance of fuzzy similarity besides discriminative and semantic feature selection methods. Discriminative features are those that distinguish categories with higher power and the concept of semantic feature takes into the calculations the similarity between features and documents by using only available documents. In the proposed method, incorporating fuzzy weighting as a measure of similarity is presented. The fuzzy weights are derived from the concept of fuzzy similarity which is defined as the variance of membership values of a document to all categories in the way that with some membership value at the same time, the sum of these membership values should be equal to 1. The proposed document classification method is evaluated on three datasets (one Persian and two English datasets) and two classification methods, support vector machine (SVM) and artificial neural network (ANN), are used. Comparing the results with other text classification methods, demonstrate the consistent superiority of the proposed technique in all cases. The weighted average F-measure of our method are %82 and %97.8 in the classification of Persian and English documents, respectively.[...] Read more.
Saving energy through the minimization of power losses in a distribution system is a key activity for efficient operation. Distributed Generation (DG) is one of the most efficient approaches to minimize losses. With increase in installation of Electric Vehicle Charging Stations (EVCSs) for Electrical Vehicles (EVs) in larger scale, optimal planning of EVCSs becomes a major challenge for distribution system operator. With increased EV load penetration in the electricity system, generation-demand mismatch and power losses increases. This results in poor voltage level, and deterioration in voltage stability margin. To mitigate the adverse impacts of increasing EV load penetration on Radial Distribution Systems (RDS), it is essential to integrate EVCSs at appropriate locations. The EVs integration into smart distribution systems involves Grid-to-Vehicle (G2V) and Vehicle-to-Grid (V2G) in charging and discharging modes of operation respectively for exchange of power with the grid thus resulting in energy management. The inappropriate planning of EVCSs causes a negative impact on the distribution system such as voltage deviation and an increase in power losses. In order to minimize this, DG units are integrated with EVCSs. The DGs assist in keeping the voltage profile within limitations, resulting in reduced power flows and losses, thereby enhancing power quality and reliability. Therefore, the DGs should be optimally allocated and sized along with the EVCS to avoid problems such as protection, voltage rise, and reverse power flow problems. This paper showcases a method to minimize losses using optimal location and sizing of multiple DGs and EVCS operating in G2V and V2G modes. The sizing and location of different types of DG units including renewables and non-renewables along with EV charging station is proposed in this study. This methodology overall reduces the power losses and also improves voltages of the network. The implementation is done by using the Simultaneous Particle Swarm Optimization technique (PSO) for IEEE 15, 33, 69 and 85 bus systems. The results indicate that the proposed optimization technique improves efficiency and performance of the system by optimal planning and operation of both DGs and EVs.[...] Read more.
In modern world of sensing and distributive systems, traditional Wireless Sensor Networks (WSN) has to deal with new challenges, such as multiple application requirements, dynamic and heterogeneous networks. Senor nodes in WSN are resource constrained in terms of energy, communication range, bandwidth, processing delay and memory. Numerous solutions are proposed to optimize the performance and to increase the lifetime of WSN by introducing new resource management principles. Effective and intelligent resource management in WSN involves in resource identification, resource scheduling, and resource utilization. This paper proposes a Bayesian Game Model (BGM) approach to efficiently identify the best node with the maximum resource in WSN for data transmission, considering energy, bandwidth, and computational delay. The scheme operates as follows: (1) Sensor nodes information such as residual energy, available bandwidth, and node ID, etc., is gathered (2) Energy and bandwidth of each node are used to generate the payoff matrix (3) Implementation of node identification scheme is based on payoff matrix, utilities assigned, strategies and reputation of each node (4) Find Bayesian Nash Equilibrium condition using Starring algorithm (5) Solving the Bayesian Nash Equilibrium using Law of Total Probability and identifying the best node with maximum resources (6) Adding/Subtracting reward (reputation factor) to winner/looser node. Simulation results show that the performance of the proposed Bayesian game model approach for resource identification in WSN is better as compared with the Efficient Neighbour Discovery Scheme for Mobile WSN (ENDWSN). The results indicate that the proposed scheme has up to 12% more resource identification accuracy rate, 10% increase in the average number of efficient resources discovered and 8% less computational delay as compared to ENDWSN.[...] Read more.