Статьи журнала - International Journal of Intelligent Systems and Applications
Все статьи: 1126
Using Rough Set Theory for Reasoning on Vague Ontologies
Статья научная
Web ontologies can contain vague concepts, which means the knowledge about them is imprecise and then query answering will not possible due to the open world assumption. A concept description can be very exact (crisp concept) or exact (fuzzy concept) if its knowledge is complete, otherwise it is inexact (vague concept) if its knowledge is incomplete. In this paper, we propose a method based on the rough set theory for reasoning on vague ontologies. With this method, the detection of vague concepts will insert into the original ontology new rough vague concepts where their description is defined on approximation spaces to be used by extended Tableau algorithm for automatic reasoning. A prototype of Tableau's extended algorithm is developed and tested on examples where encouraging results are given by this method to demonstrate that unlike other methods, it is possible to answer queries even in the presence of incomplete information.
Бесплатно
Using the Euler-Maruyama Method for Finding a Solution to Stochastic Financial Problems
Статья научная
The purpose of this paper is to survey stochastic differential equations and Euler-Maruyama method for approximating the solution to these equations in financial problems. It is not possible to get explicit solution and analytically answer for many of stochastic differential equations, but in the case of linear stochastic differential equations it may be possible to get an explicit answer. We can approximate the solution with standard numerical methods, such as Euler-Maruyama method, Milstein method and Runge-Kutta method. We will use Euler-Maruyama method for simulation of stochastic differential equations for financial problems, such as asset pricing model, square-root asset pricing model, payoff for a European call option and estimating value of European call option and Asian option to buy the asset at the future time. We will discuss how to find the approximated solutions to stochastic differential equations for financial problems with examples.
Бесплатно
Статья научная
In computational study and automatic recognition of opinions in free texts, certain words in sentences are used to decide its sentiments. While analysing each customer’s opinion per time in churn management will be effective for personalised recommendations. Oftentimes, the opinion is not sufficient for contextualised content mining. While personalised recommendations are time consuming, it also does not provide complete picture of an overall sentiment in the business community of customers. To help businesses identify widespread issues affecting a large segment of their customers towards engendering patterns and trends of different customer churn behaviour, here, we developed a clustered contextualised conversation as opinions set for integration with Roberta Model. The developed churn behavioural opinion clusters disambiguated short messages while charactering contents collectively based on context beyond keyword-based sentiment matching for effective mining. Based on the predicted opinion threshold, customer churn category for group-based personalised decision support was generated, with matching concepts. The baseline RoBERTa model on the contextually clustered opinions, trained with a batch size of 16, a learning rate of 2e-5, over 8 epochs, using a maximum sequence length of 128 and standard hyperparameters, achieved an accuracy of 92%, Precision of 88%, Recall of 86% and F1 score of 84% over a test set of 30%.
Бесплатно
VLSI Circuit Configuration Using Satisfiability Logic in Hopfield Network
Статья научная
Very large scale integration (VLSI) circuit comprises of integrated circuit (IC) with transistors in a single chip, widely used in many sophisticated electronic devices. In our paper, we proposed VLSI circuit design by implementing satisfiability problem in Hopfield neural network as circuit verification technique. We restrict our logic construction to 2-Satisfiability (2-SAT) and 3-Satisfiability (3-SAT) clauses in order to suit with the transistor configuration in VLSI circuit. In addition, we developed VLSI circuit based on Hopfield neural network in order to detect any possible error earlier than the manual circuit design. Microsoft Visual C++ 2013 is used as a platform for training, testing and validating of our proposed design. Hence, the performance of our proposed technique evaluated based on global VLSI configuration, circuit accuracy and the runtime. It has been observed that the VLSI circuits (HNN-2SAT and HNN-3SAT circuit) developed by proposed design are better than the conventional circuit due to the early error detection in our circuit.
Бесплатно
Vague Logic Approach to Disk Scheduling
Статья научная
Vague sets theory separates the evidences in favour and against of an element in a set which provides better mechanism to handle impreciseness and uncertainty. This research paper aims to handle the incompleteness and impreciseness of data associated with the disk access requests. Here, we propose a new disk scheduling algorithm, Vague Disk Scheduling (VDS) Algorithm, based on vague logic. The proposed framework includes Vague-Fuzzification Technique, Priority Expression, and VDS Algorithm. The Vague-Fuzzification Technique is applied to the input data of each disk access request and generates a priority for each request in the queue. Based on the priority allotted the requests are serviced. Finally work is evaluated on different datasets and finally compared with Fuzzy Disk Scheduling (FDS) Algorithm. The results prove that VDS algorithm performs better than FDS Algorithm.
Бесплатно
Varna-based optimization: a new method for solving global optimization
Статья научная
A new and simple optimization algorithm known as Varna-based Optimization (VBO) is introduced in this paper for solving optimization problems. It is inspired by the human-society structure and human behavior. Varna (a Sanskrit word, which means Class) is decided by people’s Karma (a Sanskrit word, which means Action), not by their birth. The performance of the proposed method is examined by experimenting it on six unconstrained, and five constrained benchmark functions having different characteristics. Its results are compared with other well-known optimization methods (PSO, TLBO, and Jaya) for multi-dimensional numeric problems. Our experimental results show that the VBO outperforms other optimization algorithms and have proved the better effectiveness of the proposed algorithm.
Бесплатно
Vehicle Tracking and Locking System Based on GSM and GPS
Статья научная
Currently almost of the public having an own vehicle, theft is happening on parking and sometimes driving insecurity places. The safe of vehicles is extremely essential for public vehicles. Vehicle tracking and locking system installed in the vehicle, to track the place and locking engine motor. The place of the vehicle identified using Global Positioning system (GPS) and Global system mobile communication (GSM). These systems constantly watch a moving Vehicle and report the status on demand. When the theft identified, the responsible person send SMS to the microcontroller, then microcontroller issue the control signals to stop the engine motor. Authorized person need to send the password to controller to restart the vehicle and open the door. This is more secured, reliable and low cost.
Бесплатно
Veins Based Personal Identification Systems: A Review
Статья научная
Identification of people among each other has always been a tough and challenging task for the researchers. There are many techniques which are used for identifying a person but biometric technique is the standard one which allows us for online identification of individuals on the basis of their physiological and behavioral features. The veins based systems include finger veins, face veins, palm veins, head veins, heart veins, iris, palatal veins of the rogue etc. The multi-veins based systems use the veins of different physiological traits for identifying a person. This paper illustrates an overview of veins based personal identification systems. The performance of different single and multi-veins based identification systems are analyzed in this paper. The features like reliability, security, accuracy, robustness and long term stability along with the strengths and weaknesses of various veins based biometric approaches were taken into considerations while analyzing the results of existing research papers published so far. At last the future research directions in the field of veins based identification systems have also been outlined.
Бесплатно
Velocity Feedback Control of a Mechatronics System
Статья научная
Increasing demands in performance and quality make drive systems fundamental parts in the progressive automation of industrial process. The analysis and design of Mechatronics systems are often based on linear or linearized models which may not accurately represent the servo system characteristics when the system is subject to inputs of large amplitude. The impact of the nonlinearities of the dynamic system and its stability needs to be clarified. The objective of this paper is to present a nonlinear mathematical model which allows studying and analysis of the dynamic characteristic of an electro hydraulic position control servo. The angular displacement response of motor shaft due to large amplitude step input is obtained by applying velocity feedback control strategy. The simulation results are found to be in agreement with the experimental data that were generated under similar conditions.
Бесплатно
Video shots’ matching via various length of multidimensional time sequences
Статья научная
Temporal clustering (segmentation) for video streams has revolutionized the world of multimedia. Detected shots are principle units of consecutive sets of images for semantic structuring. Evaluation of time series similarity is based on Dynamic Time Warping and provides various solutions for Content Based Video Information Retrieval. Time series clustering in terms of the iterative Dynamic Time Warping and time series reduction are discussed in the paper.
Бесплатно
Статья научная
Techniques to detect the flame at an early stage are necessary in order to prevent the fire and minimize the damage. The flame detection technique based on the physical sensor has limited disadvantages in detecting the fire early. This paper presents the results of using local binary patterns for solving flames detecting problem and proposes modifications to improve the quality of detector work. Experimentally found that using support vector machines classifier with a kernel based on Gaussian radial basis functions shows the best results compared to other SVM cores or classifier k-nearest neighbors.
Бесплатно
Статья научная
An inclement dusty weather can significantly reduce the visual quality of captured images and this consequently leads to hamper the observation of meaningful image details. Capturing images in such weather often leads to undesirable artifacts such as poor contrast, deficient colors or color cast. Hence, various methods have been proposed to process such unwanted event and recover vivid results with acceptable colors. These methods vary from simple to complex due to the variation of the used processing concepts. In this article, an innovative technique that utilizes tuned fuzzy intensification operators is introduced to expeditiously process poor quality images captured in an inclement dusty weather. Intensive experiments were carried out to check the processing ability of the proposed technique, wherein the obtained results exhibited its competence in filtering various degraded images. Specifically, it performed well in providing acceptable colors and unveiling fine details for the processed images.
Бесплатно
Статья научная
Parkinson is a neurological disease and occurs due to lack of dopamine neurons. These dopamine neurons manage all body movements. Parkinson patients have difficulty in doing all daily routine activities, and also have disturbed vocal fold movements. Using voice analysis disease can be diagnosed remotely at an early stage with more reliability and in an economic way. In this paper, we have used 23 features dataset, all the features are analyzed and 15 features are selected from the total dataset. As in Parkinson tremor is present in the voice box muscles, so the variation in the period and amplitude of consecutive vocal cycles is present. The feature dataset selected consist of jitter, shimmer, harmonic to noise ratio, DFA, spread1 and PPE. Various classifiers are used and their comparison is done to find out which classifier is perfect in this environment. It is concluded that support vector classifiers as the best one with an accuracy of 96%. In the neural network classifiers with different transfer functions, there is tradeoff among the performance parameters.
Бесплатно
Wart Treatment Decision Support Using Support Vector Machine
Статья научная
Warts are noncancerous benign tumors caused by the Human Papilloma Virus (HPV). The success rates of cryotherapy and immunotherapy, two common treatment methods for cutaneous warts, are 44% and 72%, respectively. The treatment methods, therefore, fail to cure a significant percentage of the patients. This study aims to develop a reliable machine learning model to accurately predict the success of immunotherapy and cryotherapy for individual patients based on their demographic and clinical characteristics. We employed support vector machine (SVM) classifier utilizing a dataset of 180 patients who were suffering from various types of warts and received treatment either by immunotherapy or cryotherapy. To balance the minority class, we utilized three different oversampling methods- synthetic minority oversampling technique (SMOTE), borderline-SMOTE, and adaptive synthetic (ADASYN) sampling. F-score along with sequential backward selection (SBS) algorithm were utilized to extract the best set of features. For the immunotherapy treatment method, SVM with radial basis function (RBF) kernel obtained an overall classification accuracy of 94.6% (sensitivity = 96.0%, specificity = 89.5%), and for the cryotherapy treatment method, SVM with polynomial kernel obtained an overall classification accuracy of 95.9% (sensitivity = 94.3%, specificity = 97.4%). The obtained results are competitive and comparable with the congeneric research works available in the literature, especially for the immunotherapy treatment method, we obtained 4.6% higher accuracy compared to the existing works. The developed methodology could potentially assist the dermatologists as a decision support tool by predicting the success of every unique patient before starting the treatment process.
Бесплатно
Статья научная
This Paper investigates the mean to design the reduced order observer and observer based controllers for a class of delayed uncertain nonlinear system subjected to actuator saturation. A new design approach of wavelet based adaptive reduced order observer is proposed. The proposed wavelet adaptive reduced order observer performs the task of identification of unknown system dynamics in addition to the reconstruction of states of the system. Wavelet neural network (WNN) is used to approximate the uncertainties present in the system as well as to identify and compensate the nonlinearities introduced in the system due to actuator saturation. Using the feedback control, based on reconstructed states, the behavior of closed loop system is investigated. In addition robust control terms are also designed to attenuate the approximation error due to WNN. Adaptation laws are developed for the online tuning of the wavelet parameters and the stability of the overall systems is assured by using the Lyapunov- Krasovskii functional. A numerical example is provided to verify the effectiveness of theoretical development.
Бесплатно
Статья научная
Computer vision applications face various challenges while detection and classification of objects in real world like large variation in appearances, cluttered back ground, noise, occlusion, low illumination etc.. In this paper a Wavelet based Histogram of Oriented Gradients (WHOG) feature descriptors are proposed to represent shape information by storing local gradients in image. This results in enhanced representation of shape information. The performance of the feature descriptors are tested on multiclass image data set having partial occlusion, different scales and rotated object images. The performance of WHOG feature based object classification is compared with HOG feature based classification. The matching of test image with its learned class is performed using Back Propagation Neural Network (BPNN) algorithm. Proposed features not only performed superior than HOG but also beat wavelet, moment invariant and Curvelet.
Бесплатно
Статья научная
This paper is concerned with the observer designing problem for a class of uncertain delayed nonlinear systems using reinforcement learning. Reinforcement learning is used via two Wavelet Neural networks (WNN), critic WNN and action WNN, which are combined to form an adaptive WNN controller. The “strategic” utility function is approximated by the critic WNN and is minimized by the action WNN. Adaptation laws are developed for the online tuning of wavelets parameters. By Lyapunov approach, the uniformly ultimate boundedness of the closed-loop tracking error is verified. Finally, a simulation example is shown to verify the effectiveness and performance of the proposed method.
Бесплатно
Web Video Object Mining: A Novel Approach for Knowledge Discovery
Статья научная
The impact of social Medias such as YouTube, Twitter, and FaceBook etc on the modern world is led to huge growth in the size of video data over the cloud and web. The evolution of smart phones/Tabs could be one of the reasons for increasing in the rate of huge video data over the web. Due to the rapid evolution of web videos over the web, it is becoming difficult to identify popular, non-popular and average popular videos without watching the content of it. To cluster web videos based on their metadata into 'Popular', 'Non-Popular', and 'Average Popular' is one of the complex research questions for the Social Media and Computer Science researchers'. In this work, we propose two effective methods to cluster web videos based on their meta-objects. Large scale web video meta-objects such as- length, view counts, numbers of comments, rating information are considered for knowledge discovery process. The two clustering algorithms-Expectation Maximization (EM) and Distribution Based (DB) clustering are used to form three types of clusters. The resultant clusters are analyzed to find popular video cluster, average popular video cluster and non-popular video clusters. And also the results of EM and DB clusters are compared as a step in the process of knowledge discovery.
Бесплатно
Web data extraction from scientific publishers’ website using heuristic algorithm
Статья научная
WWW is a huge repository of information and the amount of information available on the web is growing day by day in an exponential manner. End users make use of search engines like Google, Yahoo, and Bingo etc. for retrieving information. Search engines use web crawlers or spiders which crawl through a sequence of web pages in order to locate the relevant pages and provide a set of links ordered by relevancy. Those indexed web pages are part of surface web. Getting data from deep web requires form submission and is not performed by search engines. Data analytics and data mining applications depend on data from deep web pages and automatic extraction of data from deep web is cumbersome due to diverse structure of web pages. In the proposed work, a heuristic algorithm for automatic navigation and information extraction from journal’s home page has been devised. The algorithm is applied to many publishers website such as Nature, Elsevier, BMJ, Wiley etc. and the experimental results show that the heuristic technique provides promising results with respect to precision and recall values.
Бесплатно
Weight assignment algorithms for designing fully connected neural network
Статья научная
Soft computing is used to solve the problems where input data is incomplete or imprecise. This paper demonstrate designing fully connected neural network system using four different weight calculation algorithms. Input data for weight calculation is constructed in the matrix format based on the pairwise comparison of input constraints. This comparison is performed using saaty’s method. This input matrix helps to build judgment between several individuals, forming a single judgment. Algorithm considered here are Geometric average mean, Linear algebra calculation, Successive matrix squaring method, and analytical hierarchical processing method. Based on the quality parameter of performance, it is observed that analytical hierarchical processing is the most promising mathematical method for finding appropriate weight. Analytical hierarchical processing works on structuration of the problem into sub problems, Hence it the most prominent method for weight calculation in fully connected NN.
Бесплатно
