Статьи журнала - International Journal of Intelligent Systems and Applications
Все статьи: 1126
Ant colony system algorithm with dynamic pheromone updating for 0/1 knapsack problem
Статья научная
The 0/1 Knapsack (KP) is a combinatorial optimization problem that can be solved using various optimization algorithms. Ant Colony System (ACS) is one of these algorithms that is operated iteratively and converged emphatically to a matured solution. The convergence of the ACS depends mainly on the heuristic patterns that are used to update the pheromone trails throughout the optimization cycles. Although, ACS has significant advantages, it suffers from a slow convergence, as the pheromones, which are used to initiate the searching process are initialized randomly at the beginning. In this paper, a new heuristic pattern is proposed to speed up the convergence of ACS with 0/1 KP. The proposed heuristic enforces an order-critical item selection. As such, the proposed heuristic depends on considering the profit added by each item, as similar to the existing heuristics, besides the order of item selection. Accordingly, the proposed heuristic allows the items that are added at the end to get more value in order to be considered in the beginning of the next round. As such, with each cycle, the selected items are varied substantially and the pheromones are vastly updated in order to avoid long trapping with the initial values that are initialized randomly. The experiments showed that the proposed heuristic is converged more rapidly compared to the existing heuristics by reducing up to 30% of the cycles required to reach the optimal solution using difficult 0/1 KP datasets. Accordingly, the times required for convergence have been reduced significantly in the proposed work compared to the time required by the existing algorithms.
Бесплатно
Anti-Spam Software for Detecting Information Attacks
Статья научная
In this paper the development of anti-spam software detecting information attacks is offered. For this purpose it is considered spam filtration system with the multilayered, multivalent architecture, coordinating all ISP’s in the country. All users and ISPs of this system involved in spam filtration process. After spam filtering process, saved spam templates are analyzed and classified. This parameterizing of spam templates give possibility to define the thematic dependence from geographical. For example, what subjects prevail in spam messages sent from the certain countries? Analyzing origins of spam templates from spam-base, it is possible to define and solve the organized social networks of spammers. Thus, the offered system will be capable to reveal purposeful information attacks if those occur.
Бесплатно
Application Research of Ontology-enabled Process FMEA Knowledge Management Method
Статья научная
Failure Mode and Effect Analysis (FMEA) is an important method to ensure the effectiveness of manufacturing process, which can prevent the happening of various potential failure. If the knowledge of FMEA can be accumulated and utilized reasonably, the quality management in manufacturing process will get decision support timely, and the efficiency of product quality problem analysis also can be improved. But, it is impossible to integrate the dispersive FMEA knowledge in the manufacturing process because there is a lack of unified management criterion of FMEA knowledge. In order to satisfy the requirement to share, reuse, and maintain FMEA knowledge, the representation method of FMEA knowledge based on ontology is put forward in this study. The structure of FMEA knowledge ontology can be described via visual modeling tool- Unified Modeling Language. In this study, the FMEA repository has been built and the acquisition, storage and searching of FMEA knowledge has been researched to satisfy the need of sharing and reusing of the FMEA knowledge in the manufacturing process.
Бесплатно
Application Research on High Resolution Radar Target Aggregation
Статья научная
In high resolution radar system, the same target always has original data; so we need to merge multiple data from the same target as one target. Because of the system’s real-time requirement, we usually have to carry out target aggregation as quickly as possible. In this paper, we propose a quick target aggregation method based on clustering algorithm. The proposed method divides original data into subsets by single dimensional distance, and then merges subsets according to single dimensional distance and setdensity. At last we apply the proposed method to carry out target aggregation for airport scene surveillance radar system. Experimental result shows the proposed method has high execution efficiency and is not sensitive to noise data; it is useful for high resolution radar target aggregation.
Бесплатно
Application of Adaptive Neural Network Observer in Chaotic Systems
Статья научная
Chaos control is an important subject in control theory. Chaos control usually confronts with some problems due to unavailability of states or losing the system characteristics during the modeling process. In this situation, using an appropriate observer in control strategy may overcome the problem. In this paper, states are estimated using an observer without having complete prior information from nonlinear term based on neural network. Simulation results verify performance of the proposed structure in estimating nonlinear term specifically for an online practical use.
Бесплатно
Application of Data Mining in the Classification of Historical Monument Places
Статья научная
The economic development and promotion of a country or region is depends on several facts such as- tourism, industries, transport, technology, GDP etc. The Government of the country is responsible to facilitate the opportunities to develop tourism, technology, transport etc. In view of this, we look into the Department of Tourism to predict and classify the number of tourists visiting historical Indian monuments such as Taj- Mahal, Agra, and Ajanta etc.. The data set is obtained from the Indian Tourist Statistics which contains year wise statistics of visitors to historical monuments places. A survey undertaken every year by the government is preprocessed to fill out the possible missing values, and normalize inconsistent data. Various classification techniques under Decision Tree approach such as- Random Tree, REPTree, Random Forest and J48 algorithms are applied to classify the historical monuments places. Performance evaluation measures of the classification models are analyzed and compared as a step in the process of knowledge discovery.
Бесплатно
Статья научная
This paper considers the impact of the Inductive Fault Current Limiter (IFCL) on directional overcurrent relays coordination. The coordination problem is formulated as a non-linear constrained mono-objective optimization problem. The objective function of this optimization problem is the minimization of the operation time of the associated relays in the systems, and the decision variables are: the time dial setting (TDS) and the pickup current setting (IP) of each relay. To solve this complex non linear optimization problem, a variant of optimization algorithms named Firefly Algorithm (FA) is used. The proposed method is tested on 8-bus power transmission systems test systems considering the influences of current relay under three-phases short-circuit with and without IFCL for different locality. The results show the effectiveness of the solution.
Бесплатно
Статья научная
This paper presents a non traditional optimization technique, genetic algorithm to seek the optimal allocation, type and size of FACTS devices to control line flows, to maintain bus voltage to desired level and to minimize system losses. The targeted objectives are maximizing the static security margins and voltage stability while minimizing losses. Congestion management is also done by optimally placing FACTS controllers with line outage. Matlab coding has been developed for the purpose of simulation. Assessments are done on IEEE 30 bus system against different loading conditions with two FACTS devices SVC and TCSC implemented in steady state and the results verify the potency of propound algorithm to find the optimal location for power system stability.
Бесплатно
Application of Generalized Measure of 'Useful' R-norm Inaccuracy and Total Ambiguity
Статья научная
In the present paper, we introduce generalized measure of 'useful' R-norm inaccuracy having two parameters and its analogue 'useful' R-norm total ambiguity measure by merging together the concepts of probability, fuzziness, R-norm, 'useful' information and inaccuracy. Along with the basic properties, some other important properties of these two proposed measures are stated. These measures are generalizations of some well-known inaccuracy measures. Further, the monotonic behaviour of the proposed 'useful' R-norm inaccuracy measures is studied and the graphical overview is given. The measure of information improvement for both the measures is also obtained. Lastly, the application of 'useful' R-norm total ambiguity measure is presented in terms of multi-criteria decision making. For all the numerical calculations R software is used.
Бесплатно
Application of Genetic Neural Network in Power Battery Charging State-of-Charge Estimation
Статья научная
With global non-renewable resources and environmental issues becoming more apparent, the development of new energy vehicles have become the trend of auto industry. Hybrid vehicle becomes the key development of new energy vehicles with its long distance, low pollution, low fuel consumption characteristics and so on. The battery performances directly influence the quality of the whole vehicle performance. Considering the importance of the battery state of charge (SOC) estimation and the nonlinear relationship between the battery SOC and the external characteristic, genetic algorithm (GA) and back propagation (BP) neural network are proposed. Because of the strong global search capability of the genetic algorithm and the generalization ability of BP neural network, the hybrid vehicle Ni-MH power battery GA-BP charging model is designed. In this approach, the network training speed is superior to the traditional BP network. According to the real-time data of the batteries, the optimal solution can be concluded in a short time and with high estimation precision.
Бесплатно
Application of Intelligent Agents in Wireless Prepaid Energy Meter
Статья научная
Prepaid meter (PM) is getting very popular especially in developing countries. There are many advantages to use prepaid meter as opposed to postpaid meter both to the utility provider and to the consumer. Brunei has adopted PM but it is not intelligent and not wireless enabled. Reading meters and topping up balance are still done manually. Utility provider does not have information on the usage statistics and has only limited functionalities in the grid control. So accordingly an intelligent agent based wireless prepaid energy meter been developed using JADE-LEAP Agent development kit allowing agent from utility provider to query wireless energy meter for energy values for every household. These statistics can be used for statistical computation of the power consumed and for policy and future planning. Agent from consumers' mobile devices can query the energy meter to study the power consumed and for topping up the balance. When the meter reaches the threshold, agent at energy meter would also send messages to alert consumers for topping up through mobile handset and failing to do so will lead to power being cut automatically
Бесплатно
Application of Intensified Current Search to Multiobjective PID Controller Optimization
Статья научная
The intelligent control system design has been changed from the conventional approach to the optimization framework solved by efficient metaheuristics. The intensified current search (ICS) has been recently proposed as one of the most powerful metaheuristics for solving optimization problems. The ICS, the latest modified version of the conventional current search (CS), possesses the memory list (ML) regarded as the exploration strategy and the adaptive radius (AR) and adaptive neighborhood (AN) mechanisms regarded as the exploitation strategy. The ML is used to escape from local entrapment caused by any local solution, while both AR and AN mechanisms are conducted to speed up the search process. In this paper, the application of the ICS to multiobjective PID controller design optimization for the three-phase induction motor (3Φ-IM) speed control system is proposed. Algorithms of the ICS and its performance evaluation against multiobjective functions are presented. As simulation results, the ICS can provide very satisfactory solutions for all test functions and the 3Φ;-IM control application. Moreover, the simulation results of motor control application are confirmed by the experimental results based on dSPACE technology.
Бесплатно
Статья научная
The desire to achieve an adaptive prognostics regression learning processes of physical and empirical phenomenon is a complex task and open problem in radio frequency telecommunication engineering. One key method to solving such complex task or problems is by means of numerical based optimisation algorithms. The Levenberg–Marquardt algorithm (LMA) is an efficient nonlinear parametric machine learning based modelling algorithm with optimal, fast, and accurate convergence speed. This paper proposes and demonstrates the real-time application of the LMA in developing a log-distance like propagation loss model based on received radio strength measurements conducted over deployed long term evolution (LTE) eNodeBs antennas in three different propagation areas. The LTE eNodeB signal propagation areas were selected to reflect typical urban, suburban and rural terrains which represent urban, suburban and rural terrains. The heights of the three eNodeBs are 30, 28 and 32m respectively and each operate at 2.6GHz carrier frequency with 10MHz channel bandwidths. The resultant outcome of the proposed propagation loss modelling using LMA indicates a high approximation efficacy over the popular Gauss-Newton algorithm (GNA) modelling method, which has been used to benchmark the process. Precisely, the developed propagation loss model using LMA method attained lower maximum absolute error (MABE) of 7.73, 14.57and 10.53 for urban, suburban and rural terrains compared to the ones developed by GNA which yielded 15.19, 16.59 and 13.05 MABE values. The improved approximation performance of the LMA over the GNA can be ascribed to its capacity handle multiple free parameters and attain optimum solution irrespective of the selected values of initial guess parameters.
Бесплатно
Application of Modified Ant Colony Optimization (MACO) for Multicast Routing Problem
Статья научная
It is well known that multicast routing is combinatorial problem finds the optimal path between source destination pairs. Traditional approaches solve this problem by establishment of the spanning tree for the network which is mapped as an undirected weighted graph. This paper proposes a Modified Ant Colony Optimization (MACO) algorithm which is based on Ant Colony System (ACS) with some modification in the configuration of starting movement and in local updation technique to overcome the basic limitations of ACS such as poor initialization and slow convergence rate. It is shown that the proposed Modified Ant Colony Optimization (MACO) shows better convergence speed and consumes less time than the conventional ACS to achieve the desired solution.
Бесплатно
Application of Neural Network on Burr Expert System in Micro-machining
Статья научная
The demands placed by designers on workpiece performance and functionality are increasing rapidly. Important aspects of manufacturing’s contribution to the fulfillment of these demands are the conditions at the work piece edges. However, Burrs are often created on the workpiece edges in micro-machining. In many cases, time consuming and expensive deburring processes have to be applied in order to ensure the desired part functionality. Burrs make troubles on production lines in terms of deburring cost, quality of products and cutting tool wear. To prevent problems caused by burrs in micro-machining, prediction and control of burr size is desirable. Experimental studies show that burr formation in micro-milling is a highly complex process depending on a number of parameters such as material properties, tool geometry and cutting parameters. It is very difficult to establish the relationship between burr sizes and cutting conditions. A web-based micro-machining burr expert system for burr sizes prediction and control was developed using ASP.NET platform. Burrs types and sizes prediction and cutting conditions optimization for burr controlling which based on the reasoning method of BP neural networks are realized. Operation results show that the system is reliable. It provides a new technology for burrs modelling and controlling.
Бесплатно
Статья научная
Neural network models are powerful tools for extracting the underlying dependency of a set of input/output data. However, the mentioned tools are in danger of sticking in local minima. The present study went to step forward by optimizing neural network models using three intelligent optimization algorithms, including genetic algorithm (GA), particle swarm optimization (PSO), and ant colony (AC), to eliminate the risk of being exposed to local minima. This strategy was capable of significantly improving the accuracy of a neural network by optimizing network parameters such as weights and biases. Nuclear magnetic resonance (NMR) log measures some of the most useful characteristics of reservoir rock; the capabilities of the optimized models were used for prediction of nuclear magnetic resonance (NMR) log parameters in a carbonate reservoir rock of Iran. Conventional porosity logs, which are the easily accessible tools compared to NMR log’s parameters, were introduced to the models as inputs while free fluid porosity and permeability, which were measured by NMR log, are desire outputs. The performance of three optimized models was verified by some unseen test data. The results show that PSO-based network and ACO-based network is the best and poorest method, respectively, in terms of accuracy; however, the convergence time of GA-based model is considerably smaller than PSO-based and GA-based models.
Бесплатно
Application of Particle Swarm based Neural Network to Predict Scour Depth around the Bridge Pier
Статья научная
Scour around the bridge pier is one of the major factors which affect the safety and stability of the bridge structure. Due to the presence of complexity in the scour mechanism, there is no common and simple method to estimate the scour depth. The present paper gives an idea of hybridizing two techniques such as an artificial neural network with swarm intelligence technique particle swarm optimization to estimate the scour depth around the bridge pier and abbreviated as PSO-ANN. The present discussion covers the estimation of scour depth for clear water and live bed scour condition around circular and rectangular pier shapes. The independent variables, Sediment size (d50), sediment quantity (Sq), velocity (u) and time (t) are used as input to develop the models to estimate or quantify a dependent variable scour depth (ds). The efficiency and accuracy of the model are measured using model performances indicators such as Correlation Coefficient (CC), Normalized Root Mean Square Error (NRMSE), Nash Sutcliffe Error (NSE), and Normalized Mean Bias (NMB). The predicted results of both the models are compared with each other and also compared with measured scour depth. The study concludes that the proposed PSO-ANN model is suitable to estimate the scour depth in both the cases for circular and rectangular pier shapes.
Бесплатно
Статья научная
The stochastic character of asymmetrical loads in power networks emerged due to non-simultaneous activation of phases of various single-phase and poly-phase receivers, nonlinear characteristics of transformers and other reasons have caused the occurrence of currents and voltages of zero sequence. These electrical quantities with currents and voltages of direct sequence in a negative sense affect the asymmetry of phase voltages in networks on places where loads are connected. In this paper, the presented load is induction machine with coil connection in star connected to generic distribution system TN. We analyze the possibilities of simple CL structures of filter in the role of the device for correction of asymmetries to a network, which can be entered by zero sequence current occurred for some reason in induction machine (mostly non-simultaneous switching of phase coils of induction machine).
Бесплатно
Application of SQL RAT Translation
Статья научная
Since we have already designed a flexible form of representing the Relational Algebra Tree (RAT) translated by the SQL parser, the application of this kind of object-oriented representation should be explored. In this paper, we will show you how to apply this technique to complicated scenarios. The application of Reverse Query Processing and Reverse Manipulate Processing related to this issue will be discussed.
Бесплатно
Application of Weighted Additive Fuzzy Goal Programming Approach to Quality Control System Design
Статья научная
The problem of decision-making in designing a quality control system (QCS), is one of the most difficult problems decisions facing the manager in the industrial firms , this problem of decision requires of fixing the levels of inputs and variables that meet the required output specifications. in the context of the problem a QCS, the parameters can be imprecise and expressed through intervals or fuzzy. The aim of this study is to presents the formulation for designing a QCS based on Weighted fuzzy goal programming (WAFGP) developed by Yaghoobi and Tamiz [12] and Yaghoobi et al [13], the advantage of the proposed formulation as a linear , use all types of membership functions and integrate explicitly the decision-maker’s preference . Finally, we compare the results of our model with the major important mathematical models used in the QCS It has been shown that the best model.
Бесплатно
