Статьи журнала - International Journal of Intelligent Systems and Applications
Все статьи: 1159
A Glowworm Optimization Method for the Design of Web Services
Статья научная
A method for adaptive usability evaluation of B2C eCommerce web services is proposed. For measuring eCommerce usability a checklist integrating eCommerce quality and usability is developed. By a Glowworm swarm optimization (GSO) neural networks-based model the usability dimensions and their checklist items are adaptively selected. A case study for usability evaluation of an eCommerce anthurium retail website is carried out. The experimental results show that GSO with neural networks supports the allocation of usability problems and the defining of relevant improvement measures. The main advantage of the approach is the adaptive selection of most significant checklist dimensions and items and thus significant reduction of the time for usability evaluation and design.
Бесплатно
A Growing Evolutionary Algorithm and Its Application for Data Mining
Статья научная
An unsuitable representation will make the task of mining classification rules very hard for a traditional evolutionary algorithm (EA). But for a given dataset, it is difficult to decide which one is the best representation used in the mining progress. In this paper, we analyses the effects of different representations for a traditional EA and proposed a growing evolutionary algorithm which was robust for mining classification rules in different datasets. Experiments showed that the proposed algorithm is effective in dealing with problems of deception, linkage, epistasis and multimodality in the mining task.
Бесплатно
A Heterogeneous Access Remote Integrating Surveillance Heuristic Model for a Moving Train in Tunnel
Статья научная
Many number of real time applications are available for train monitoring using satellite based navigation system with high level of speed and precision. But these systems have faced lot of issues such as multipath loss and line of sight which results in lesser accuracy measurements. When the train is moving in low satellite visible areas such as tunnels, mountains, forest etc, then no position information is available. The service failure in tunnel made big challenge to demonstrate a self supporting innovative platform for navigation of train. This paper is focused on designing a novel approach by integrating Wireless Sensor Network (WSN) and Radio Frequency Identification (RFID) system for continuous monitoring of train moving in tunnel. The wireless tracking controller based on quadratic optimal control theory is considering for analysis. Overall performance of the control design is based on Liapunov approach, where quadratic performance index is directly related to Liapunov functions. By minimizing and maximizing the performance index value corresponding to control inputs will trace the tracking error inaccuracies. As maximizing the performance index, the tracking error produces 0.04% inaccuracy. The data loss is 0.06% when minimizing the performance value. Simulation is carried out using Mat lab.
Бесплатно
A High Performance Image Authentication Algorithm on GPU with CUDA
Статья научная
There has been large amounts of research on image authentication method. Many of the schemes perform well in verification results; however, most of them are time-consuming in traditional serial manners. And improving the efficiency of authentication process has become one of the challenges in image authentication field today. In the future, it’s a trend that authentication system with the properties of high performance, real-time, flexible and ease for development. In this paper, we present a CUDA-based implementation of an image authentication algorithm with NVIDIA’s Tesla C1060 GPU devices. Comparing with the original implementation on CPU, our CUDA-based implementation works 20x-50x faster with single GPU device. And experiment shows that, by using two GPUs, the performance gains can be further improved around 1.2 times in contras to single GPU.
Бесплатно
A Hybrid Algorithm for Privacy Preserving in Data Mining
Статья научная
With the proliferation of information available in the internet and databases, the privacy-preserving data mining is extensively used to maintain the privacy of the underlying data. Various methods of the state art are available in the literature for privacy-preserving. Evolutionary Algorithms (EAs) provide effective solutions for various real-world optimization problems. Evolutionary Algorithms are efficiently employed in business practice. In privacy-preserving domain, the existing EA solutions are restricted to specific problems such as cost function evaluation. In this work, it is proposed to implement a Hybrid Evolutionary Algorithm using Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). Both GA and PSO in the proposed system work with the same population. In the proposed framework, k-anonymity is accomplished by generalization of the original dataset. The hybrid optimization is used to search for optimal generalized feature set.
Бесплатно
Статья научная
Combinatorial Interaction Testing (CIT) is a cost effective testing technique that aims to detect interaction faults generated as a result of interaction between components or parameters in a software system. CIT requires the generation of effective test sets that cover all possible t-way (t denotes the strength of testing) interactions between parameters. Covering array (CA) and mixed covering array (MCA) are often used to represent test sets. This paper presents a hybrid algorithm that integrates artificial bee colony algorithm (ABC) and harmony search algorithm (HS) to construct CAs for testing all 2-way interactions (pair-wise testing) in software systems. The performance of the proposed hybrid algorithm ABCHS-CAG is compared and analyzed by performing experiments on a set of benchmark problems on pair-wise testing. The results show that ABCHS-CAG generates smaller CAs than its greedy counterparts whereas its performance is comparable to the existing state-of-the-art meta-heuristic algorithms.
Бесплатно
A Hybrid RBF-SVM Ensemble Approach for Data Mining Applications
Статья научная
One of the major developments in machine learning in the past decade is the ensemble method, which finds highly accurate classifier by combining many moderately accurate component classifiers. This paper addresses using an ensemble of classification methods for data mining applications like intrusion detection, direct marketing, and signature verification. In this research work, new hybrid classification method is proposed for heterogeneous ensemble classifiers using arcing and their performances are analyzed in terms of accuracy. A Classifier ensemble is designed using a Radial Basis Function (RBF) and Support Vector Machine (SVM) as base classifiers. Here, modified training sets are formed by resampling from original training set; classifiers constructed using these training sets and then combined by voting. The proposed RBF-SVM hybrid system is superior to individual approach for intrusion detection, direct marketing, and signature verification in terms of classification accuracy.
Бесплатно
A Hybrid Unsupervised Density-based Approach with Mutual Information for Text Outlier Detection
Статья научная
The detection of outliers in text documents is a highly challenging task, primarily due to the unstructured nature of documents and the curse of dimensionality. Text document outliers refer to text data that deviates from the text found in other documents belonging to the same category. Mining text document outliers has wide applications in various domains, including spam email identification, digital libraries, medical archives, enhancing the performance of web search engines, and cleaning corpora used in document classification. To address the issue of dimensionality, it is crucial to employ feature selection techniques that reduce the large number of features without compromising their representativeness of the domain. In this paper, we propose a hybrid density-based approach that incorporates mutual information for text document outlier detection. The proposed approach utilizes normalized mutual information to identify the most distinct features that characterize the target domain. Subsequently, we customize the well-known density-based local outlier factor algorithm to suit text document datasets. To evaluate the effectiveness of the proposed approach, we conduct experiments on synthetic and real datasets comprising twelve high-dimensional datasets. The results demonstrate that the proposed approach consistently outperforms conventional methods, achieving an average improvement of 5.73% in terms of the AUC metric. These findings highlight the remarkable enhancements achieved by leveraging normalized mutual information in conjunction with a density-based algorithm, particularly in high-dimensional datasets.
Бесплатно
A Hybrid Wavelet-ANN-Based Protection Scheme for FACTS Compensated Transmission Lines
Статья научная
This paper proposes an approach for the protection of transmission lines with FACTS based on Artificial Neural Networks (ANN) using Wavelet Transform (WT). The required features for the proposed algorithm are extracted from the measured transient current and voltage waveforms using discrete wavelet transform (DWT). Those features are employed for fault detection and faulted phase selection using ANN. The type of FACTS compensated transmission lines is the Thyristor-Controlled Series Capacitor (TCSC). System simulation and test results indicate the feasibility of using neural networks using wavelet transforms in the fault detection, classification and faulted phase selection of FACTS compensated transmission lines.
Бесплатно
A Hyper-chaotic Medical Image Encryption with Optimized Key Value
Статья научная
This article delves into a medical image encryption/decryption method based on hyper chaotic dynamics and genetic algorithms. The proposed algorithm boasts simplicity in implementation, featuring straightforward operations that render it well-suited for real-time applications while elevating its security measures. Leveraging the sensitivity of chaotic behavior to initial conditions, a genetic algorithm is employed to select optimal initial conditions for the 5D multi-wing hyper-chaotic system. Initially, a secret key generation method based on the input image is applied, followed by stages of diffusion and encryption utilizing the chaotic system. The secret key undergoes optimization through a genetic algorithm, considering specific parameters within the encrypted image as encryption factors. Subsequently, the encrypted image with the optimized secret key is finalized, serving as the basis for decrypting the cipher image. The proposed method undergoes simulation, testing, and comparison against other image encryption algorithms. Both experimental results and computer simulations affirm the robustness of this cryptographic system, showcasing a significant key space value (2^256), high key sensitivity (Number of Pixels Change Rate: NPCR > 99.55%, Unified Average Changing Intensity: UACI > 33.37%), and its ability to fend off various types of attack.
Бесплатно
A Low-cost, Installable Intelligent Helper Module for Automobiles
Статья научная
Ground vehicles are being intelligent day by day. But in today’s market the price of an autonomous, which is still in its experimental phase, or a semi-autonomous intelligent vehicular system is too high. Apart from the usage of expensive sensors, previously proposed vehicular networking systems for intelligent vehicles need network provider and communication towers like cellular communication networks which is both time consuming and costly to implement. Moreover, the mechatronics part, which controls the vehicle is very much different from a traditional intra-vehicular mechanism making it very difficult to convert a regular vehicle, e.g. a car, into an intelligent one. Due to these facts, these overpriced systems are not suitable for the underdeveloped countries where, these are somewhat more needed. In this paper, I have developed a very cheap intelligent system for providing guidance to the driver while driving. This module will not be connected to the hardware directly, which made it an easy-to-install “helper module” for any kind of ground vehicles. However, this module will reduce the accident rate by collecting and analyzing surrounding data, communicating with nearby vehicles (peer to peer) while overtaking and providing continuous guidelines for safe driving. Unlike other systems this could easily be deployed in the underdeveloped countries because of its ultra-low cost.
Бесплатно
A Method for Solving Fuzzy Transportation Problem (FTP) using Fuzzy Russell's Method
Статья научная
The basic transportation problem was originally developed by Hitchcock. In the literature several methods are proposed for solving Fuzzy transportation problem. In this paper, we propose a new algorithm called Fuzzy Russell’s method for the initial basic feasible solution to a Fuzzy transportation problem. To examine the proposed method a numerical example is solved. Fuzzy numbers may be normal or abnormal, triangular or trapezoidal or any LR fuzzy number. We can use this proposed method for any kind of Fuzzy numbers.
Бесплатно
Статья научная
The weight updates are required for group decision-making which has similar parameters used by the decision maker (DM). Each DM as the stakeholder may have similar or different parameters in selecting parameters. Therefore, we have to accommodate the interests of all decision makers (DMs) to obtain alternative decisions. DM who has selected the parameters inputs the initial weight (W_Pi) based on the classical methods, and then recalculates to obtain the updated weights (W_j) until the final weight (W_j^i) is obtained for the alternative of group decision-making (GDM). The initial weight uses a weighting directly or multi criteria decision-making (MCDM). This method aims to provide the fairness for all DMs who have different knowledge in determining the value of the weights and the selection parameters. In order to obtain alternative decisions, we used technique for order preference by similarity to ideal solution (TOPSIS) method to update weight. In this paper, the alternative output of the decisions is applied in two stages: the decisions of each DM and the group, where this output consists of four types of alternatives. Based on the proposed method, the result of GDM shows that the third alternative is recommended in decision-making. This method is effectively performed in decision-making which has different parameters and weights of each DM to support group decision.
Бесплатно
A Model for Object-Oriented Software Maintainability Measurement
Статья научная
Software maintenance is one of the main quality characteristics of the software product. The maintainability of a system is a measure of the ability of the system to undergo maintenance or to return to normal operation after a failure. In this paper, a new model to improve the maintainability of object-oriented software has been proposed. The proposed model is based on newer versions of software quality standard and it is according to the measurement of several new metric. This model has been evaluated on famous PHP framework and the results showed that the proposed model is effective compared with the previous models.
Бесплатно
A Model of a Generic Natural Language Interface for Querying Database
Статья научная
Extracting information from database is typically done by using a structured language such as SQL (Structured Query Language). But non expert users can't use this later. Wherefore using Natural Language (NL) for communicating with database can be a powerful tool. But without any help, computers can't understand this language; that is why it is essential to develop an interface able to translate user's query given in NL into an equivalent one in Database Query Language (DBQL). This paper presents a model of a generic natural language query interface for querying database. This model is based on machine learning approach which allows interface to automatically improve its knowledge base through experience. The advantage of this interface is that it functions independently of the database language, content and model. Experimentations are realized to study the performance of this interface and make necessary corrections for its amelioration.
Бесплатно
A Modified Particle Swarm Optimization Technique for Economic Load Dispatch with Valve-Point Effect
Статья
This paper presents a new approach for solution of the economic load dispatch (ELD) problem with valve-point effect using a modified particle swarm optimization (MPSO) technique. The practical ELD problems have non-smooth cost function with equality and inequality constraints, which make the problem of finding the global optimum difficult when using any mathematical approaches. In this paper, a modified particle swarm optimization (MPSO) mechanism is proposed to deal with the equality and inequality constraints in the ELD problems through the application of Gaussian and Cauchy probability distributions. The MPSO approach introduces new diversification and intensification strategy into the particles thus preventing PSO algorithm from premature convergence. To demonstrate the effectiveness of the proposed approach, the numerical studies have been performed for three different test systems, i.e. six, thirteen and forty generating unit systems, respectively. The results shows that performance of the proposed approach reveal the efficiently and robustness when compared results of other optimization algorithms reported in literature.
Бесплатно
Статья научная
Cervical cancer is the fourth most prevalent cancer in women which has claimed 3,41,831 lives and accounted for 6,04,127 new cases in 2020 worldwide. To reduce such a vast mortality rate, early detection of the disease is essential. A fast, accurate, and interpretable machine learning model is a research subject. Fewer features reduce the computational effort and improve interpretation. A 3-Stage Hybrid feature selection approach and a Stacked Classification model are evaluated on the cervical cancer dataset obtained from the UCI Machine Learning Repository with 35 features and one outcome variable. Stage-1 uses a Genetic Algorithm and Logistic Regression Architecture for Feature Selection and selects twelve features well correlated with the class but not among themselves. Stage-2 utilizes the same Genetic Algorithm and Logistic Regression Architecture for Feature Selection to select five features. In Stage-3, Logistic Regression (LR), Naïve Bayes (NB), Support Vector Machine (SVM), Extra Trees (ET), Random Forest (RF), and Gradient Boosting (GDB) are used with the five features to identify patients with or without cancer. Data splitting, several metrics, and statistical tests are used, along with 10-fold cross validation, to do a comparative analysis. LR, NB, SVM, ET, RF, and GDB demonstrate improvement across performance measures by reducing the number of features to five. In the 66-34 split, all five machine learning methods except NB recorded 97% accuracy with 5 features. Also, the Stacked model produced higher than 96% accuracy with five features in 66-34 and 80-20 splits, and in 10-fold cross validation. Various performance aggregators have shown improved results with reduced features when compared to previous studies. Finally, with approximately 100% performance in classification results, the suggested ensemble model showed its promise. The output results were compared to those of other studies on the same dataset, and the proposed classifiers were found to be the most effective across all performance dimensions.
Бесплатно
A Multi-intelligent Agent System for Automatic Construction of Rule-based Expert System
Статья научная
The main general purpose of this research is the automatic construction of rule-based expert system in diagnosis domain based on an expert system tool and a multi-intelligent agent system. The first goal is used an expert system tool (shell) which is called Diagnosis Domain Tool for Rule-based Expert System (DDTRES) [1]. The second goal is used a multi-intelligent agent architecture for knowledge extraction to elicit knowledge from its resources (domain experts, text documents, databases) for automatic construction of a knowledge base. That means, instead of using traditional methods for knowledge base construction, we used automatic way for that job. In order to achieve second objective, the following agents have been used: The Expert Mining Intelligent Agent (EMIA), The Text Mining Intelligent Agent (TMIA) [2], and The Multi-Intelligent Agent for Knowledge Discovery in Database (MIAKDD) [3]. We are aim to produce an effective final knowledge base by cooperation between EMIA, TMIA, and MIAKDD approaches and integrated with the diagnosis domain tool (DDTRES) to produce a complete rule-based expert system in diagnosis domain. We applied the captured rule-based expert system on heart diseases diagnosis, we found system performance is between a good and a very good range.
Бесплатно
A Multiagent Planning Approach to Model a Tele-Surgery Domain
Статья научная
Technological advancements have led to the development of few commercially available tele-surgery systems till date. However such systems are very expensive. In tele-surgery, the task of a surgeon (the activities related to a surgery) is partially executed by a robot. Typically, the robot is under the control of a surgeon; it executes the instructions of the controlling surgeon. In this paper we give formal model of a tele-surgery domain (heart surgery) as a multiagent planning problem. The actions related to the surgery are represented as planning operators. The model consists of two interactive agents, referred to as EXPERT and INTERN. The EXPERT controls the activities of the INTERN. The INTERN executes the actions suggested by the EXPERT. The state space of each agent is modeled as a transition system. The communication of the agents is modeled using CCS. We have defined a condition to establish the success of the surgery using notions of finite games. We have also developed a prototype implementation incorporating the above features.
Бесплатно
A Multidimensional Extended Neo-Fuzzy Neuron for Facial Expression Recognition
Статья научная
An article introduces a modified architecture of the neo-fuzzy neuron, also known as a "multidimensional extended neo-fuzzy neuron" (MENFN), for the face recognition problems. This architecture is marked by enhanced approximating capabilities. A characteristic property of the MENFN is also its computational plainness in comparison with neuro-fuzzy systems and neural networks. These qualities of the proposed system make it effectual for solving the image recognition problems. An introduced MENFN’s adaptive learning algorithm allows solving classification problems in a real-time fashion.
Бесплатно
