Статьи журнала - International Journal of Intelligent Systems and Applications
Все статьи: 1159
Hybrid artificial bee colony and tabu search based power aware scheduling for cloud computing
Статья научная
Load balancing is an important task on virtual machines (VMs) and also an essential aspect of task scheduling in clouds. When some Virtual machines are overloaded with tasks and other virtual machines are under loaded, the load needs to be balanced to accomplish optimum machine utilization. This paper represents an existing technique “artificial bee colony algorithm” which shows a low convergence rate to the global minimum even at high numbers of dimensions. The objective of this paper is to propose the integration of artificial bee colony with tabu search technique for cloud computing environment to enhance energy consumption rate. The main improvement is makespan 28.4 which aim to attain a well balanced load across virtual machines. The simulation result shows that the proposed algorithm is beneficial when compared with existing algorithms.
Бесплатно
IC Floorplanning Optimization using Simulated Annealing with Order-based Representation
Статья научная
Integrated Circuits (IC) floorplanning is an important step in the integrated circuit physical design; it influences the area, wire-length, delay etc of an IC. In this paper, Order Based (OB) representation has been proposed for fixed outline floorplan with Simulated Annealing (SA) algorithm. To optimize the IC floorplan, two physical quantities have been considered such as area, and wire-length for hard IP modules. Optimization of the IC floorplan works in two phases. In the first phase, floorplans are constructed by proposed representation without any overlapping among the modules. In the second phase, Simulated Annealing algorithm explores the packing of all modules in floorplan to find better optimal performances i.e. area and wire-length. The Experimental results on Microelectronic Center of North Carolina benchmark circuits show that our proposed representation with SA algorithm performs better for area and wire-length optimization than the other methods. The results are compared with the solutions derived from other algorithms. The significance of this research work is improvement in optimized area and wire-length for modern IC.
Бесплатно
IGICA: A Hybrid Feature Selection Approach in Text Categorization
Статья научная
Feature selection problem is one of the most important issues in machine learning and statistical pattern recognition. This problem is important in many applications such as text categorization because there are many redundant and irrelevant features in these applications which may reduce the classification performance. Indeed, feature selection is a method to select an appropriate subset of features for increasing the performance of learning algorithms. In the text categorization, there are many features which most of them are redundant. In this paper, a two-stage feature selection method-IGICA- based on imperialist competitive algorithm (ICA) is proposed. ICA is a new metaheuristic which is inspired by imperialist competition among countries. At the first stage of the proposed algorithm, a filtering technique using the information gain is applied and features are ranked based on their values. The top ranking features are then selected. In the second stage, ICA is applied to the select the efficient features. The presented method is evaluated on Retures-21578 dataset. The experimental results showed that the proposed method has a good ability to select efficient features compared to other methods.
Бесплатно
IKRAI: Intelligent Knee Rheumatoid Arthritis Identification
Статья научная
Rheumatoid joint inflammation is characterized as a perpetual incendiary issue which influences the joints by hurting body tissues Therefore, there is an urgent need for an effective intelligent identification system of knee Rheumatoid arthritis especially in its early stages. This paper is to develop a new intelligent system for the identification of Rheumatoid arthritis of the knee utilizing image processing techniques and neural classifier. The system involves two principle stages. The first one is the image processing stage in which the images are processed using some techniques such as RGB to grayscale conversion, rescaling, median filtering, background extracting, images subtracting, segmentation using canny edge detection, and features extraction using pattern averaging. The extracted features are used then as inputs for the neural network which classifies the X-ray knee images as normal or abnormal (arthritic) based on a backpropagation learning algorithm which involves training of the network on 400 X-ray normal and abnormal knee images. The system was tested on 400 x-ray images and the network shows good performance during that phase, resulting in a good identification rate 95.5 %.
Бесплатно
ILSHR Rumor Spreading Model by Combining SIHR and ILSR Models in Complex Networks
Статья научная
Rumor is an important form of social interaction. However, spreading harmful rumors can have a significant negative impact on social welfare. Therefore, it is important to examine rumor models. Rumors are often defined as unconfirmed details or descriptions of public things, events, or issues that are made and promoted through various tools. In this paper, the Ignorant-Lurker-Spreader-Hibernator-Removal (ILSHR) rumor spreading model has been developed by combining the ILSR and SIHR epidemic models. In addition to the characteristics of the lurker group of ILSR, this model also considers the characteristics of the hibernator group of the SIHR model. Due to the complexity of the complex network structure, the state transition function for each node is defined based on their degree to make the proposed model more efficient. Numerical simulations have been performed to compare the ILSHR rumor spreading model with other similar models on the Sina Weibo dataset. The results show more effective ILSHR performance with 95.83% accuracy than CSRT and SIR-IM models.
Бесплатно
Identification of Customer Through Voice Biometric System in Call Centres
Статья научная
In recent times, there has been a growing emphasis on adjusting communication strategies to foster strong customer relationships. This shift is driven by intensified competition, market maturation, and swift advancements in business technology. Consequently, companies have established call centers to efficiently handle customer support and fulfil customer inquiries. A pivotal aspect of enhancing service quality within these call centers involves accurately identifying customers during their interactions. The primary objective of this study is to introduce a methodology for identifying customers within call centers by analysing their voice characteristics. Voice authentication (VA) has gained prominence in critical security operations, including banking transactions and conversations within call centers. The susceptibility of automatic speaker verification systems (ASVs) to deceptive spoofing attacks has prompted the development of countermeasures (CMs). These countermeasures are designed to differentiate between authentic and fabricated speech. ASVs and CMs collectively constitute contemporary VA systems, positioned as robust access control mechanisms. To achieve this goal, various customer identification systems within call centers have been examined, along with an analysis of audio signal attributes. Ultimately, the manuscript presents a novel approach to customer identification through voice biometrics. Notably, this method excels in recognizing customers even when provided with limited voice data. Empirical findings demonstrate that the suggested speaker identity confirmation method outperforms alternative techniques utilizing different algorithms, exhibiting a higher recognition rate. The present research work is based on two important perspectives of the call centres: a. call center agents experience and b. customer experience. The data collected separately from customers and agents for understanding the effective usage of voice biometric system in call centres. The data represented and satisfies the effectiveness of voice biometric system from both the perspectives. From the data it is also cleared that, the implementation of voice biometric system in call centres still have long way to go but will be a major technological change for the industries worldwide.
Бесплатно
Identification of Parametrical Restrictions in Staic Systems in Conditions of Uncertainty
Статья научная
The approach to an estimation of area of parametrical restrictions (APR) for static linear system on parameters in the conditions of uncertainty is of-fered. For decision-making indicators of domination of an exit of model over an exit of system and the special indicator setting admissible level of errors of domination are used. The case of the representation of area of restrictions in the form of boundaries from below and from above on a modification of parameters of system is considered. The iteration algorithm of identification of restrictions and decision-making is offered. The adaptive algorithm of an estimation of boundaries of area of parametrical restrictions is synthesized. Procedure of estimation APR on the basis of the analysis of a field of secants of system is described. Method development on a case of representation APR in the form of restriction on norm of a modification of parameters of system is given. Various forms of vectorial norms and algorithms of construction of area of parametrical restrictions corresponding to them are considered.
Бесплатно
Identification of Quality Indicators Dynamic System on Basis of Analysis Data "Input-Output"
Статья научная
The problem of an estimation quality indicators of linear dynamic system in the conditions of uncertainty is considered. Quality indicators are a point of an equilibrium state and a spectrum of eigenvalues. We offer a method of an estimation a point of an equilibrium state. Method is based on identification of the particular solution system on a class of static models with the dynamic specification on an input. We offered on the basis of the general decision of system procedures and criteria of an estimation equilibrium state. After an estimation of equilibrium state system in work the problem of definition a spectrum eigenvalues of linear dynamic system is considered. We form the time series describing a modification of Lyapunov exponents. For identification of a spectrum eigenvalues we introduce special structures which describe a modification of the Lyapunov exponent. We apply a method of the secant structures and we receive spectrum tentative estimations. The special structure, allowing identifying the largest Lyapunov exponent, is offered. Generalization of the offered methods on linear non-stationary dynamic systems is given.
Бесплатно
Статья научная
This paper presents a comparison of the three fuzzy based image segmentation methods namely Fuzzy C-Means (FCM), TYPE-II Fuzzy C-Means (T2FCM), and Intuitionistic Fuzzy C-Means (IFCM) for digital images with varied levels of noise. Apart from qualitative performance, the paper also presents quantitative analysis of these three algorithms using four validity functions-Partition coefficient (V_pc), Partition entropy (V_pe), Fukuyama-Sugeno (V_fs), and Xie-Beni (V_xb) functions and also compared the performance on the basis of their execution time.
Бесплатно
Image Superresolution via Divergence Matrix and Automatic Detection of Crossover
Статья научная
The paper describes the image superresolution method with aggregate divergence matrix and automatic detection of crossover. Formulation of the problem, building extreme optimization task and its solution for solving the automation determination of the crossover coefficient is presented. Different ways for building oversampling images algorithms based on the proposed method are shows. Based on practical experiments shows the effectiveness of the procedure of automatically the determination of the crossover coefficient. Experimentally established the effectiveness of the procedures oversampling images at high zoom resolution by the developed method.
Бесплатно
Impact of Design Patterns on Software Maintainability
Статья научная
This paper mainly studies the effect of design patterns on the Software maintainability. Design patterns describe solutions for common design problems and they were introduced to improve software quality and accelerate software development. However, there are some difficulties to choose an optimal pattern adapted to a certain application and problem. So until now the results on the effect of design patterns on software quality are controversial. In this context, we propose a tool for design pattern guided that retrieves the appropriate pattern with respect to software maintainability from a repository of patterns. It measures the maintainability of design pattern by some metrics and candidate the more maintainable pattern to the designer or developer. It provides a support for decision making during system design and refactoring. As the results, the decision of applying a certain design pattern is usually a trade-off since the effect of design pattern on software maintainability is influenced by some factors such as the pattern size and the prior expertise of the developer.
Бесплатно
Impact of Multipath Routing on WSN Security Attacks
Статья научная
Multipath routing does not minimize the consequences of security attacks. Due to this many WSNs are still in danger of most security attacks even when multipath routing is used. In critical situations, for example, in military and health applications this may lead to undesired, harmful and disastrous effects. These applications need to get their data communicated efficiently and in a secure manner. In this paper, we show the results of a series of security attacks on a multipath extension to the ad hoc on-demand distance vector AODV protocol, AOMDV. It is proved that many security parameters are negatively affected by security attacks on AOMDV, which is contradictory to research claims. This means that alternative refinements have to be made to present multipath routing protocols in order to make them more effective against network security attacks.
Бесплатно
Impact of Parameter Tuning on the Cricket Chirping Algorithm
Статья научная
Most of the man-made technologies are nature-inspired including the popular heuristics or meta-heuristics techniques that have been used to solve complex computational optimization problems. In most of the meta-heuristics algorithms, adjusting the parameters has important significance to obtain the best performance of the algorithm. Cricket Chirping Algorithm (CCA) is a nature inspired meta-heuristic algorithm that has been designed by mimicking the chirping behavior of the cricket (insect) for solving optimization problems. CCA employs a set of parameters for its smooth functioning. In a meta-heuristic algorithm, controlling the values of various parameters is one of the most important issues of research. While solving the problem, the parameter values have a potential to improve the efficiency of the algorithm. The different parameters used in CCA are tuned for better performance of the algorithm through experiments conducted on a set of sample benchmark test functions and then, the fine-tuned CCA is compared with some other meta-heuristic algorithms. The results show the optimal choice of the various parameters to solve optimization problems using CCA.
Бесплатно
Impact of Social Networking Sites in Bangladesh: Few Possible Solutions
Статья научная
Bangladesh is a developing country. But in few recent years this country is going to be turned as digitalized. The first condition of being digitalization is the whole communication system of the country have to be developed tremendously. If we notice about the communication system, then Social Networking Sites can be a platform of revolution. This study is based on the perspective of Bangladesh on Social Networking Sites(SNS). In Bangladesh, Social Networking Sites are getting popular tremendously. The Social Networking Sites(SNS) like twitter and Facebook gives people in general the useful platform for disclosure of their thinking and ideas. This research paper is made with an aim to represent the positive and negative impact of Social Networking Sites(SNS) and we will also try to recommend few possible solutions to overcome these problems.
Бесплатно
Impact of TCSC on Distance Protection Setting based Modified Particle Swarm Optimization Techniques
Статья научная
This paper presents the application of the Modified Particle Swarm Optimization (MPSO) technique for optimal settings zones for MHO distance relay protect 400 kV single transmission line of Eastern Algerian transmission networks at Algerian Company of Electrical and Gas (Group Sonelgaz) compensated by series Flexible Alternative current Transmission System (FACTS) i.e. Thyristor Controlled Series Capacitor (TCSC) connected at midpoint. The effects of TCSC insertion on the total impedance of a protected transmission line with respect to injected variable reactance value (X_(TCSC)) in capacitive and inductive boost mode depending of the firing angle (α) is considered. The modified setting zone protection for three zones (Z_(1), Z_(2) and Z_(3)) is have been investigate in order to prevent circuit breaker nuisance tripping and improve the performances of distance relay protection. In this work our aim is to compare the performance of the proposed MPSO algorithm with an analytical method (AM). The findings demonstrate the outstanding performance of the proposed MPSO in terms of computation speed, rate of convergence, and feasibility. The simulation results are compared with each other, and then the more perfect algorithm is considered.
Бесплатно
Imperialist Competitive Algorithm with Adaptive Colonies Movement
Статья научная
The novel Imperialist Competitive Algorithm (ICA) that was recently introduced has a good performance in some optimization problems. The ICA inspired by socio-political process of imperialistic competition of human being in the real world. In this paper, a new Imperialist Competitive Algorithm with Adaptive Radius of Colonies movement (ICAR) is proposed. In the proposed algorithm, for an effective search, the Absorption Policy changed dynamically to adapt the radius of colonies movement towards imperialist’s position. The ICA is easily stuck into a local optimum when solves high-dimensional multi-modal numerical optimization problems. To overcome this shortcoming, we use probabilistic model that utilize the information of colonies positions to balance the exploration and exploitation abilities of the Imperialist Competitive Algorithm. Using this mechanism, ICA exploration capability will enhance. Some famous unconstraint benchmark functions used to test the ICAR performance. Simulation results show this strategy can improve the performance of the ICA algorithm significantly.
Бесплатно
Implementation of Carlson based fractional differentiators in control of fractional order plants
Статья научная
This paper presents reduced integer order models of fractional differentiators. A two step procedure is followed. Using the Carlson method of approximation, approximated second iteration models of fractional differentiators are obtained. This method yields transfer function of high orders, which increase the complexity of the system and pose difficulty in realization. Hence, three reduction techniques, Balanced Truncation method, Matched DC gain method and Pade Approximation method are applied and reduced order models developed. With these models, fractional Proportional-Derivative and fractional Proportional-Integral-Derivative controllers are implemented on a fractional order plant and closed loop responses obtained. The authors have tried to reflect that the Carlson method in combination with reduction techniques can be used for development of good lower order models of fractional differentiators. The frequency responses of the models obtained using the different reduction techniques are compared with the original model and with each other. Three illustrative examples have been considered and their performance compared with existing systems.
Бесплатно
Implementation of Transfer Learning Using VGG16 on Fruit Ripeness Detection
Статья научная
In previous studies, researchers have determined the classification of fruit ripeness using the feature descriptor using color features (RGB, GSL, HSV, and L * a * b *). However, the performance from the experimental results obtained still yields results that are less than the maximum, viz the maximal accuracy is only 76%. Today, transfer learning techniques have been applied successfully in many real-world applications. For this reason, researchers propose transfer learning techniques using the VGG16 model. The proposed architecture uses VGG16 without the top layer. The top layer of the VGG16 replaced by adding a Multilayer Perceptron (MLP) block. The MLP block contains Flatten layer, a Dense layer, and Regularizes. The output of the MLP block uses the softmax activation function. There are three Regularizes that considered in the MLP block namely Dropout, Batch Normalization, and Regularizes kernels. The Regularizes selected are intended to reduce overfitting. The proposed architecture conducted on a fruit ripeness dataset that was created by researchers. Based on the experimental results found that the performance of the proposed architecture has better performance. Determination of the type of Regularizes is very influential on system performance. The best performance obtained on the MLP block that has Dropout 0.5 with increased accuracy reaching 18.42%. The Batch Normalization and the Regularizes kernels performance increased the accuracy amount of 10.52% and 2.63%, respectively. This study shows that the performance of deep learning using transfer learning always gets better performance than using machine learning with traditional feature extraction to determines fruit ripeness detection. This study gives also declaring that Dropout is the best technique to reduce overfitting in transfer learning.
Бесплатно
Improved Adaptive Routing for Multihop IEEE 802.15.6 Wireless Body Area Networks
Статья научная
Wireless Body Area Network has the ability to collect and send data on body measurement to the server through PDA or other device. Nodes (sensors) collect vital signs from the body or environmental factor and check them. In IEEE 802.15.6 routing is discussed as a part of the link layer where multihop is not fully considered. Improving network performance, reducing energy consumption, thus extending the network lifetime is the main challenge in BANs. Several studies mention that multihop for BANs helps for achieving network performance, reducing energy consumption and extending network lifetime. One work presents the Adaptive multihop tree-based Routing (AMR) protocol that is extensively evaluated in a real testbed deployment. They use fuzzy logic to combine all metrics they use. Another limitation is that they have used Prim's algorithm which is not a realistic approach. So in this work we have improved their multihop tree-based Routing (AMR) protocol using Kruskal's algorithm instead of Prim's algorithm. The time complexity of Kruskal's algorithm is way less than prims's algorithm. We have used network simulator 3 (NS3) to simulate and found that our algorithm is better than AMR if many of nodes.
Бесплатно
Improved Harmony Search with Chaos for Solving Linear Assignment Problems
Статья научная
This paper presents an improved version of a harmony meta-heuristic algorithm, (IHSCH), for solving the linear assignment problem. The proposed algorithm uses chaotic behavior to generation a candidate solution in a behavior similar to acoustic monophony. Numerical results show that the IHSCH is able to obtain the optimal results in comparison with traditional methods (the Hungarian method). However, the benefit of the proposed algorithm is its ability to obtain the optimal solution within less computation in comparison with the Hungarian method.
Бесплатно
