Статьи журнала - International Journal of Information Technology and Computer Science
Все статьи: 1165
Статья научная
The negative impact of out-of-school students' problems at the basic and high-school levels is always very weighty on the affected individuals, parents, and society at large. Owing to the weighty negative consequences, policymakers, different government agencies, educators and researchers have long been looking for how to effectively study and forecast the trends as a means of offering a concrete solution to the problem. This paper develops a better hybrid machine learning method, which combines the least square and support vector machine (LS-SVM) model for robust prediction improvement of out-of-school children trend patterns. Particularly, while other previous works only engaged some regional and few samples of out-of-school datasets, this paper focused on long-ranged global out-of-school datasets, collated by UNESCO between 1975- 2020. The proposed hybrid method exhibits the optimal precision accuracies with the LS-SVM model in comparison with ones made using the ordinary SVM model. The precision performance of both LS-SVM and SVM was quantified and a lower NRMSE value is preferred. From the results, the LS-SVM attained lower error values of 0.0164, 0.0221, 0.0268, 0.0209, 0.0158, 0.0201, 0.0147 and 0.0095 0.0188, compared to the SVM model that attained higher NRMSE values of 0.041, ,0.0628, 0.0381, 0.0490, 0.0501, 0.0493, 0.0514, 0.0617 and 0.0646, respectively. By engaging the MAPE indicator, which expresses the mean disconnection between the sourced and predicted values of the out-of-school data. By means of the MAPE, LS-SVM attained lower error values of 0.51, 1.88, 0.82, 2.38, 0.62, 2.55, 0.60, 0.60, 1.63 while SVM attained 1.83, 7.39, 1.79 7.01, 2.43, 8.79, 2.58, 4.13, 6.18. This implies that the LS-SVM model has better precision performance than the SVM model. The results attained in this work can serve as an excellent guide on how to explore hybrid machine-learning techniques to effectively study and predict out-of-school students among researchers and educators.
Бесплатно
Story scrambler - automatic text generation using word level RNN-LSTM
Статья научная
With the advent of artificial intelligence, the way technology can assist humans is completely revived. Ranging from finance and medicine to music, gaming, and various other domains, it has slowly become an intricate part of our lives. A neural network, a computer system modeled on the human brain, is one of the methods of implementing artificial intelligence. In this paper, we have implemented a recurrent neural network methodology based text generation system called Story Scrambler. Our system aims to generate a new story based on a series of inputted stories. For new story generation, we have considered two possibilities with respect to nature of inputted stories. Firstly, we have considered the stories with different storyline and characters. Secondly, we have worked with different volumes of the same stories where the storyline is in context with each other and characters are also similar. Results generated by the system are analyzed based on parameters like grammar correctness, linkage of events, interest level and uniqueness.
Бесплатно
Strategies for Searching Targets Using Mobile Sensors in Defense Scenarios
Статья научная
Target searching is one of the challenging research areas in defense. Different types of sensor networks are deployed for searching targets in critical zones. The selection of optimal strategies for the sensor nodes under certain constraints is the key issue in target searching problem. This paper addresses a number of target searching problems related to various defense scenarios and introduces new strategic approaches to facilitate the search operation for the mobile sensors in a two-dimensional bounded space. The paper classifies the target searching problems into two categories: preference-based and traversal distance based. In the preference based problems, the strategies for the mobile sensors are determined by Stable Marriage Problem, College Admission Problem, and voting system; they are analyzed with suitable examples. Alternatively, traversal distance based problems are solved by our proposed graph searching approaches and analyzed with randomly chosen examples. Results obtained from the examples signify that our proposed models can be applied in defense-related target searching problems.
Бесплатно
Статья научная
The rapid growth of data in various industries has led to the emergence of big data analytics as a vital component for extracting valuable insights and making informed decisions. However, analyzing such massive volumes of data poses significant challenges in terms of storage, processing, and analysis. In this context, the Hadoop ecosystem has gained substantial attention due to its ability to handle large-scale data processing and storage. Additionally, integrating machine learning models within this ecosystem allows for advanced analytics and predictive modeling. This article explores the potential of leveraging the Hadoop ecosystem to enhance big data analytics through the construction of machine learning models and the implementation of efficient data warehousing techniques. The proposed approach of optimizing stock price by constructing machine learning models and data warehousing empowers organizations to derive meaningful insights, optimize data processing, and make data-driven decisions efficiently.
Бесплатно
Статья научная
In this paper ‘DWT-SVD’ based Color Image Watermarking technique in YUV color space using Arnold Transform is proposed. The RGB color image is converted into YUV color space. Image is decomposed by 3 level DWT and then SVD is applied. The security is increased with watermark scrambling using Arnold Transform. The watermark is embedded in all Y,U and V color spaces in HL3 region. The decomposition is done with ‘Haar’ which is simple, symmetric and orthogonal wavelet and the direct weighting factor is used in watermark embedding and extraction process is used. PSNR and Normalized Correlations (NC) values are tested for 10 different values of flexing factor. We got maximum PSNR up to 52.3337 for Y channel and average value of NC equal to 0.99 indicating best recovery of watermark. The proposed scheme is non blind and strongly robust to different attacks like compression, scaling, rotation, cropping and Noise addition which is tested with standard database image of size 512x512 and watermark of size 64X64.
Бесплатно
Structural Conditions on Observability of Nonlinear Systems
Статья научная
In this paper parameter space and Lebesgue measurement are introduced into analysis of nonlinear systems. Structural observability rank condition is defined and together with the distinguishabililty the structural observability criterions of nonlinear systems are obtained. It proves that when the parameters are not identifiable the solutions with the same time but different parameters are also indistinguishable. Differential geometry and algebraic methods are used to investigate the observability problem, and it is proved that there are some relations between these two methods. Finally, examples are used to illustrate applications of the structural observability criterions.
Бесплатно
Study and Performance Evaluation on Recent DDoS Trends of Attack & Defense
Статья научная
Different types and techniques of DDoS attacks & defense are studied in this paper with some recent information on attacks dominated in year 2012 (1st Quarter). We further provide simulation based analysis of an FTP server’s performance in a typical enterprise network under distributed denial of service attack. Simulations in OPNET show noticeable variations in connection capacity, task processing and delay parameters of the attacked server as compared to the performance without attack. DDoS detection and mitigation mechanisms discussed in this paper mainly focus on some recently investigated techniques. Finally, conclusions are drawn on the basis of survey based study as well as simulation results.
Бесплатно
Study of Context Modelling Criteria in Information Retrieval
Статья научная
Whereas the majority of works and research about context-awareness in ubiquitous computing provide context models that make use of context features in a particular application, one of the main challenges these last years has been to come out with prospective standardization of context models. As for Information Retrieval, the lack of consensual Context Models represents the biggest issue. In this paper, we investigate the importance of good context modelling to overcome some of the issues surrounding a search task. Thus, after identifying those issues and listing and categorizing the modelling requirements, the objective of our research is to find correlations between the appreciations of context quality criteria taking into account the user dimension. Likewise, the results of a previous survey about search habits have been used such that many socio-demographic categories were considered and the Kendall's W evaluation performed together with the Friedman test provided very interesting results that encourage the feasibility of building large scale context models.
Бесплатно
Study of Covering Based Multi Granular Rough Sets and Their Topological Properties
Статья научная
The notions of basic rough sets introduced by Pawlak as a model of uncertainty, which depends upon a single equivalence relation has been extended in many directions. Over the years, several extensions to this rough set model have been proposed to improve its modeling capabilities. From the granular computing point of view these models are single granulations only. This single granulation model has been extended to multi-granulation set up by taking more than one equivalence relations simultaneously. This led to the notions of optimistic and pessimistic multi-granulation. One direction of extension of the basic rough set model is dependent upon covers of universes instead of partitions and has better modeling power as in many real life scenario objects cannot be grouped into partitions but into covers, which are general notions of partitions. So, multigranulations basing on covers called covering based multi-granulation rough sets (CBMGRS) were introduced. In the literature four types of CBMGRSs have been introduced. The first two types of CBMGRS are based on minimal descriptor and the other two are based on maximal descriptor. In this paper all these four types of CBMGRS are studied from their topological characterizations point of view. It is well known that there are four kinds of basic rough sets from the topological characterisation point of view. We introduce similar characterisation for CBMGRSs and obtained the kinds of the complement, union, and intersection of such sets. These results along with the accuracy measures of CBMGRSs are supposed to be applicable in real life situations. We provide proofs and counter examples as per the necessity of the situations to establish our claims.
Бесплатно
Study of Parametric Performance Evaluation of Machine Learning and Statistical Classifiers
Статья научная
Most of the researchers/ scientists are facing data explosion problem presently. Large amount of data is available in the world i.e. data from science, industry, business, survey and many other areas. The main task is how to prune the data and extract valuable information from these data which can be used for decision making. The answer of this question is data mining. Data Mining is popular topic among researchers. There is lot of work that cannot be explored in the field of data mining till now. A large number of data mining tools/software’s are available which are used for mining the valuable information from the datasets and draw new conclusion based on the mined information. These tools used different type of classifiers to classify the data. Many researchers have used different type of tools with different classifiers to obtained desired results. In this paper three classifiers i.e. Bayes, Neural Network and Tree are used with two datasets to obtain desired results. The performance of these classifiers is analyzed with the help of Mean Absolute Error, Root Mean-Squared Error, Time Taken, Correctly Classified Instance, Incorrectly Classified instance and Kappa Statistic parameter.
Бесплатно
Статья научная
This paper explores the possibility of applying techniques for segmenting the regions of medical image. For this we need to investigate the use of different techniques which helps for detection and classification of image regions. We also discuss some segmentation methods classified by researchers. Region classification is an essential process in the visualization of brain tissues of MRI. Brain image is basically classified into three regions; WM, GM and CSF. The forth region can be called as the tumor region, if the image is not normal. In the paper; Segmentation and characterization of Brain MR image regions using SOM and neuro fuzzy techniques, we integrate Self Organizing Map(SOM) and Neuro Fuzzy scheme to automatically extract WM, GM, CSF and tumor region of brain MRI image tested on three normal and three abnormal brain MRI images. Now in this paper this scheme is further tested on axial view images to classify the regions of brain MRI and compare the results from the Keith‘s database. Using some statistical tests like accuracy, precision, sensitivity, specificity, positive predictive value, negative predictive value, false positive rate, false negative rate, likelihood ratio positive, likelihood ratio negative and prevalence of disease we calculate the effectiveness of the scheme.
Бесплатно
Study of the Characteristics and Computation Analysis Results of Electromechanical Systems Models
Статья научная
Today, simulation of electrical drives with asynchronous motors based on systems of differential equations is regarded as one of the principal means of their research study. The difficulty of the simulation is determined by the need for accuracy of the results obtained and the complexity of the mathematical model’s differential equations. In this article, we present a study of the particularities of the simulation of electrical drives systems with asynchronous motors. We have studied models composed of three-phase and orthogonal coordinates systems and we have shown that qualitative and quantitative differences exist in the process of changing the angular speed of the rotor and electromagnetic torque. The result obtained is above all influenced by the non-linear character of the load opposing a fan-type or “dry friction”-type resistant torque. For dual-earthed electromagnetic actuation with the moments of the resistant torques indicated, integration of differential equation systems was carried out with various digital methods used in professional mathematical software for simulation.
Бесплатно
Study on QoS Gains in Migration from IPv4 to IPv6 Internet
Статья научная
IPv6 has features, like a) "no header checksum calculation" and b) "no IP packet fragmentation at intermediate routers", which makes it better than IPv4 from router/routing point of view. Existing Internet technology supports both IPv6 and IPv4 protocols for transport of packets and hence dual addressed machines are widely present. Maximizing QoS in IPv6 networks, as compared to IPv4 networks, for sites having dual addresses is an active area of research. Results of our study on QoS gains in networks connected to IPv6 Internet as compared to IPv4 Internet for a network of about 2500 nodes are presented here. The technique used to estimate QoS gains in the migration from IPv4 to IPv6 is also presented. The test-bed data of one month with 25000 most visited websites was analyzed. The results show that an alternate IPv6 channel exists for a large number of major global websites and substantial QoS gains in terms of reduced access times – averaging up to 35% for some websites - can be expected by intelligent per site IP address selection for dual stack machines.
Бесплатно
Study on the Effectiveness of Spam Detection Technologies
Статья научная
Nowadays, spam has become serious issue for computer security, because it becomes a main source for disseminating threats, including viruses, worms and phishing attacks. Currently, a large volume of received emails are spam. Different approaches to combating these unwanted messages, including challenge response model, whitelisting, blacklisting, email signatures and different machine learning methods, are in place to deal with this issue. These solutions are available for end users but due to dynamic nature of Web, there is no 100% secure systems around the world which can handle this problem. In most of the cases spam detectors use machine learning techniques to filter web traffic. This work focuses on systematically analyzing the strength and weakness of current technologies for spam detection and taxonomy of known approaches is introduced.
Бесплатно
Study on the Impact Breakup Model of the Space Target Based on the Thin Plate
Статья научная
In the paper, an engineering model for the im-pact breakup of the space target is studied based on the thin plate. The average fragment size model for the impact breakup of the thin plate is established depending on the strain rate, according as Poisson statistic fragments are discrete and distribution model is figured out. On the foundation of the constitution analysis for the target and projectile, the target equivalent model based on the thin plate is established, and projectile equivalent model is also given. The length and velocity degraded model are set up against the cylindrical projectile. The simulation case is analyzed and the result indicates that the paper model is effective, flexible and has important engineering reference value.
Бесплатно
Study the Performance of SLM for Different Number of Subcarriers
Статья научная
Orthogonal Frequency Division Multiplexing (OFDM) is an attractive modulation technique for transmitting large amounts of digital data over radio waves. One major disadvantage of OFDM is that the time domain OFDM signal which is a sum of several sinusoids leads to high peak to average power ratio (PAPR) which leads to power inefficiency in RF section of the transmitter and increased complexity in the analog to digital and digital to analog Converter. Selected mapping (SLM) is a well-known method for reducing the PAPR in OFDM. In this paper, we have studied the performance of SLM for Different Number of Subcarriers. Simulation result shows that the PAPR is reduced significantly when the number of phase sequences is increased and PAPR is increased when the number of subcarriers is increased. It also shows that data speed increases when subcarriers increase where N-point IFFT/FFT circuit depends on N-subcarriers.
Бесплатно
Subset matching based selection and ranking (SMSR) of web services
Статья научная
Web service is a software application, which is accessible using platform independent and language neutral web protocols. However, selecting the most relevant services became one of the vital challenges. Quality of services plays very important role in web service selection, as it determines the quality and usability of a service, including its non-functional properties such as scalability, accessibility, integrity, efficiency, etc. When agent application send request with a set of quality attributes, it becomes challenging to find out the best service for satisfying maximum quality requirements. Among the existing approaches, the single value decomposition technique is popular one; however, it suffers for computational complexity. To overcome this limitation, this paper proposed a subset matching based web service selection and ranking by considering the quality of service attributes. This proposed method creates a quality-web matrix to store available web services and associated quality of service attributes. Then, matrix subsets are created using web service repository and requested quality attributes. Finally, web services are efficiently selected and ranked based on calculated weights of corresponding web services to reduce composition time. Experimental results showed that proposed method performs more efficient and scalable than existing several techniques such as single value decomposition.
Бесплатно
Substitute and Communication Pattern for an Internet Banking System
Статья научная
The design patterns are the reusable component used in the development of the software, which delivers enhanced quality software to the end users. The design patterns are available for user interface, mobile applications, text classification and so on. There are no design patterns for internet banking applications. This motivated to mine the design patterns for internet banking application from the document of Business Process Management (BPM) by using the qualitative research technique. The nonfunctional quality attribute of software architecture is enhanced by using the design patterns. In this paper the mined two patterns are presented namely substitute pattern and communication pattern for internet banking application.
Бесплатно
Suggestive Approaches to Create a Recommender System for GitHub
Статья научная
Recommender system suggests users with options that may be of use to them or may be of their interest or liking. These days recommender systems are used widely on most systems and especially on those which are connected to World Wide Web, it may be a mobile app, a desktop application, or a website. Most advertisements on these systems are focused on targeting a specific group. Recommender systems provide a solution to such a scenario where the recommendations need to be targeted based on a user profile. Almost all commercial, collaborative or even social networking websites rely on recommender systems. In this paper, we specifically focus on GitHub, a source code hosting site and one of the most popular platforms for online collaborative coding and sharing. GitHub offers an opportunity for researchers to perform analysis by providing REST-based APIs for downloading its data. GitHub hosts a vast amount of user repositories so it is quite difficult for a GitHub user to decide to which repository she should contribute on GitHub. So, our paper aims to review different approaches that can be used for creating a recommender system for GitHub, to provide personalized suggestions to GitHub users to which repositories they should contribute. In this paper, we have discussed collaborative filtering, content-based filtering, and hybrid filtering, knowledge-based and utility-based approaches of a recommender system.
Бесплатно
Статья научная
Internal combustion (IC) engines are optimized to meet exhaust emission requirements with the best fuel economy. Closed loop combustion control is a key technology that is used to optimize the engine combustion process to achieve this goal. In order to conduct research in the area of closed loop combustion control, a control oriented cycle-to-cycle engine model, containing engine combustion information for each individual engine cycle as a function of engine crank angle, is a necessity. In this research, the IC engine is modeled according to fuel ratio, which is represented by the mass of air. In this research, a multi-input-multi-output baseline computed fuel control scheme is used to simultaneously control the mass flow rate of both port fuel injection (PFI) and direct injection (DI) systems to regulate the fuel ratio of PFI to DI to desired levels. The control target is to maintain the fuel ratio at stoichiometry and the fuel ratio to a desired value between zero and one. The performance of the baseline computed fuel controller is compared with that of a baseline proportional, integral, and derivative (PID) controller.
Бесплатно
