Статьи журнала - International Journal of Modern Education and Computer Science

Все статьи: 968

A Dynamic Probabilistic Broadcasting Scheme based on Cross-Layer design for MANETs

A Dynamic Probabilistic Broadcasting Scheme based on Cross-Layer design for MANETs

Qing-wen WANG, Hao-shan Shi, Qian Qi

Статья научная

Broadcasting plays a fundamental role in transmitting a message from the sender to the rest of the network nodes in Mobile Ad hoc Networks (MANETs). The blind flooding scheme causes a broadcast storm problem, which leads to significant network performance degradation. In order to solve the problem, a dynamic probabilistic broadcasting scheme cross-layer design for MANETs (DPBSC) is proposed. DPBSC adopts the cross-layer design, which lets routing layer share the received signal power information at MAC layer while still maintaining separation between the two layers. The additional transmission range that can benefit from rebroadcast is calculated according to the received signal power, which is applied to dynamically adjust the rebroadcast probability. DPBSC reduces the redundant retransmission and the chance of the contention and collision in the networks. Simulation results reveal that the DPBSC achieves better performance in terms of the saved-rebroadcast, the average packet drop fraction, the average number of collisions and average end-to-end delay at expense of the throughput, which is respectively compared with the blind flooding and fixed probabilistic flooding applied at the routing layer while IEEE 802.11 at the MAC layer.

Бесплатно

A Face Recognition System by Embedded Hidden Markov Model and Discriminating Set Approach

A Face Recognition System by Embedded Hidden Markov Model and Discriminating Set Approach

Vitthal Suryakant Phad, Prakash S. Nalwade, Prashant M. Suryavanshi

Статья научная

Different approaches have been proposed over the last few years for improving holistic methods for face recognition. Some of them include color processing, different face representations and image processing techniques to increase robustness against illumination changes. There has been also some research about the combination of different recognition methods, both at the feature and score levels. Embedded hidden Markov model (E-HHM) has been widely used in pattern recognition. The performance of Face recognition by E-HMM heavily depends on the choice of model parameters. In this paper, we propose a discriminating set of multi E-HMMs based face recognition algorithm. Experimental results illustrate that compared with the conventional HMM based face recognition algorithm the proposed method obtain better recognition accuracies and higher generalization ability.

Бесплатно

A Frame of Intrusion Detection Learning System Utilizing Radial Basis Function

A Frame of Intrusion Detection Learning System Utilizing Radial Basis Function

S.Selvakani Kandeeban, R.S.Rajesh

Статья научная

The process of monitoring the events that occur in a computer system or network and analyzing them for signs of intrusion is known as Intrusion Detection System (IDS). Detection ability of most of the IDS are limited to known attack patterns; hence new signatures for novel attacks can be troublesome, time consuming and has high false alarm rate. To achieve this, system was trained and tested with known and unknown patterns with the help of Radial Basis Functions (RBF). KDD 99 IDE (Knowledge Discovery in Databases Intrusion Detection Evaluation) data set was used for training and testing. The IDS is supposed to distinguish normal traffic from intrusions and to classify them into four classes: DoS, probe, R2L and U2R. The dataset is quite unbalanced, with 79% of the traffic belonging to the DoS category, 19% is normal traffic and less than 2% constitute the other three categories. The usefulness of the data set used for experimental evaluation has been demonstrated. The different metrics available for the evaluation of IDS were also introduced. Experimental evaluations were shown that the proposed methods were having the capacity of detecting a significant percentage of rate and new attacks.

Бесплатно

A Framework for Adaptation of Virtual Data Enumeration for Enhancing Census – Tanzania Case Study

A Framework for Adaptation of Virtual Data Enumeration for Enhancing Census – Tanzania Case Study

Ramadhani A. Duma

Статья научная

Population census is an enormous and challenging national exercise with many stakeholders whose participation is required at all levels of government or public administration. The problem of high cost in conducting the traditional census process imposes extra and unaffordable cost in most of the developing countries which resulted into ten-year defaulting for census enumerations. This challenge compels nations to seek for assistance mostly from various donors nations in every census enumerations exercise. Virtual Census enumerations play a vital role in demographic data enumerations since it does not require physical involvement in Enumeration Area as in traditional enumerations approach. In this paper the main focus is on data integration from different heterogeneous sources, addressing cleansing challenge for data integrated from data sources with no common key for integrations, building virtual data integration framework for enhancing virtual censuses enumeration process. The developed framework and algorithms can be used to guide design of any other data integration system that need to address similar challenges in related aspects. The outcome of this work is suitable and cheaper technique of demographic data enumeration as compared to traditional technique which involves a lot of manual works and processes.

Бесплатно

A Framework for Homomorphic, Private Information Retrieval Protocols in the Cloud

A Framework for Homomorphic, Private Information Retrieval Protocols in the Cloud

Mahmoud Fahsi, Sidi Mohamed Benslimane, Amine Rahmani

Статья научная

Professional use of cloud health storage around the world implies Information-Retrieval extensions. These developments should help users find what they need among thousands or billions of enterprise documents and reports. However, extensions must offer protection against existing threats, for instance, hackers, server administrators and service providers who use people's personal data for their own purposes. Indeed, cloud servers maintain traces of user activities and queries, which compromise user security against network hackers. Even cloud servers can use those traces to adapt or personalize their platforms without users' agreements. For this purpose, we suggest implementing Private Information Retrieval (PIR) protocols to ease the retrieval task and secure it from both servers and hackers. We study the effectiveness of this solution through an evaluation of information retrieval time, recall and precision. The experimental results show that our framework ensures a reasonable and acceptable level of confidentiality for retrieval of data through cloud services.

Бесплатно

A Framework for Software Defect Prediction Using Feature Selection and Ensemble Learning Techniques

A Framework for Software Defect Prediction Using Feature Selection and Ensemble Learning Techniques

Faseeha Matloob, Shabib Aftab, Ahmed Iqbal

Статья научная

Testing is one of the crucial activities of software development life cycle which ensures the delivery of high quality product. As software testing consumes significant amount of resources so, if, instead of all software modules, only those are thoroughly tested which are likely to be defective then a high quality software can be delivered at lower cost. Software defect prediction, which has now become an essential part of software testing, can achieve this goal. This research presents a framework for software defect prediction by using feature selection and ensemble learning techniques. The framework consists of four stages: 1) Dataset Selection, 2) Pre Processing, 3) Classification, and 4) Reflection of Results. The framework is implemented on six publically available Cleaned NASA MDP datasets and performance is reflected by using various measures including: F-measure, Accuracy, MCC and ROC. First the performance of all search methods within the framework on each dataset is compared with each other and the method with highest score in each performance measure is identified. Secondly, the results of proposed framework with all search methods are compared with the results of 10 well-known supervised classification techniques. The results reflect that the proposed framework outperformed all of other classification techniques.

Бесплатно

A Framework to Formulate Adaptivity for Adaptive e-Learning System Using User Response Theory

A Framework to Formulate Adaptivity for Adaptive e-Learning System Using User Response Theory

Maria Dominic, Britto Anthony Xavier, Sagayaraj Francis

Статья научная

These days different e-learning architecture provide different kinds of e-learning experiences due to “one size fits for all” concept. This is no way better than the traditional learning and does not exploit the technological advances. Thus the e-learning system began to evolve to adaptable e-learning systems which adapts or personalizes the learning experience of the learners. Systems infer the characteristics of the learners and identify the preferences of the learners and automatically generate personalized learning path and customize learning contents to the individuals needs. This process is known as adaptation and systems which adapt are known are adaptive systems. So the main objective of this research was to provide an adaptive e-learning system framework which personalizes the learning experience in an efficient way. In this paper a framework for adaptive e-learning system using user response theory is proposed to meet the research objectives identified in section 1.D.

Бесплатно

A Fuzzy Based Comprehensive Study of Factors Affecting Teacher's Performance in Higher Technical Education

A Fuzzy Based Comprehensive Study of Factors Affecting Teacher's Performance in Higher Technical Education

Sunish Kumar O S

Статья научная

The main objective of this paper is to suggest a model for improving and retaining the highly qualified teachers in higher technical education. There are numerous researches going on all over the world regarding the key quality factors which are directly linked with teacher's performance and the methods to improve them. Whatever the methods and measures, the teacher's active participation and dedication is very important to achieve these objectives. A detailed questionnaire was distributed to highly qualified and experienced teachers who are working in engineering colleges for more than five years. Since the variables in this study are quality factors, the collected data is analyzed using the fuzzy logic and inference is drawn for getting more accurate results compared to probability study of the same case. Based on the results obtained from fuzzy inference system, a new model called Adaptive Performance-Incentive-Development (PID) control system for improving the quality as well as retaining the highly qualified teachers in the teaching profession is created.

Бесплатно

A Fuzzy Logic Approach to Assess Web Learner's Joint Skills

A Fuzzy Logic Approach to Assess Web Learner's Joint Skills

Mousumi Mitra, Atanu Das

Статья научная

Skill assessment is an important but complicated task in the entire web based teaching and learning process. The learner's performance assessment has a strong influence on learners' approaches to learn and their learning outcomes like professional acceptability on desired skills. Most educators focus either on assessing a learner's technical skill set or non-technical skill set, individually, rather than focusing on both the aspects. This paper bridges the gap by applying fuzzy logic approach to analyze a learner's joint skills incorporating both skills-set. An already proven e-commerce website's evaluation technique has been chosen and applied in two situations of learner's skill assessment through case studies namely: technical skills evaluation, and non-technical skills evaluation. Experiments show that the learner's success depends on both sets of skill attributes. This work then proposed a novel method for skill assessment considering two (instead of one) sets of skill attributes invoking parallel or joint application of the technique. This new technique has also been analysed through a case study.

Бесплатно

A GA-Tabu Based User Centric Approach for Discovering Optimal Qos Composition

A GA-Tabu Based User Centric Approach for Discovering Optimal Qos Composition

Vivek Gaur, Praveen Dhyani, O. P. Rishi

Статья научная

Cloud computing is an emerging internet-based paradigm of rendering services on pay- as -per -use basis. Increasing growth of cloud service providers and services creates the need to provide a tool for retrieval of the high-quality optimal cloud services composition with relevance to the user priorities. Quality of Service rank-ings provides valuable information for making optimal cloud service selection from a set of functionally equiva-lent service candidates. To obtain weighted user-centric Quality of Service Composition, real-world invocations on the service candidates are usually required. To avoid the time-consuming and expensive real-world service invocations, this paper proposes framework for predic-tion of optimal composition of services requested by the user. Taking advantage of the past service usage experi-ences of the consumers more cost effective results are achieved. Our proposed framework enables the end user to determine the optimal service composition based on the input weight for individual service Quality of Service. The Genetic algorithm and basic Tabu search is applied for the user-centric Quality of Service ranking prediction and the optimal service composition. The experimental results proves that our approaches outperform other competing approaches.

Бесплатно

A Gaussian Filter based SVM Approach for Vehicle Class Identification

A Gaussian Filter based SVM Approach for Vehicle Class Identification

Gargi, Sandeep Dahiya

Статья научная

Vehicle identification or classification is one of the application areas that come under real time image processing. Vehicle recognition is having the significance in various applications including the traffic monitoring, load monitoring, number plate recognition, vehicle theft prevention, traffic violation detection, management of traffic etc. As the images are captured as primary data source, it can have number of associated impurities which include the background inclusion, object overlapping etc. Because of this, object detection and recognition is always a challenge in real time scenario. In present work, a robust feature based model is presented for feature extraction and classification of vehicle images. The presented model is applied on real time captured image to categorize the vehicle in light, medium and heavy vehicle. Firstly, the vehicle area segmentation is performed and later on the Gaussian filter is applied to extract the image features. This featured dataset is processed under Support Vector Machine (SVM) based distance analysis model for vehicle recognition and vehicle class identification. The experimentation results of present investigation shows the recognition rate of devised system over 90%.

Бесплатно

A Harmony Search Algorithm with Multi-pitch Adjustment Rate for Symbolic Time Series Data Representation

A Harmony Search Algorithm with Multi-pitch Adjustment Rate for Symbolic Time Series Data Representation

Almahdi M. Ahmed, Azuraliza Abu Bakar, Abdul Razak Hamdan

Статья научная

The representation task in time series data mining has been a critical issue because the direct manipulation of continuous, high-dimensional data is extremely difficult to complete efficiently. One time series representation approach is a symbolic representation called the Symbolic Aggregate Approximation (SAX). The main function of SAX is to find the appropriate numbers of alphabet symbols and word size that represent the time series. The aim is to achieve the largest alphabet size and maximum word length with the minimum error rate. The purpose of this study is to propose an integrated approach for a symbolic time series data representation that attempts to improve SAX by improving alphabet and word size. The Relative Frequency (RF) binning method is employed to obtain alphabet size and is integrated with the proposed Multi-pitch Harmony Search (HSMPAR) algorithm to calculate the optimum alphabet and word size. RF is used because of its ability to obtain a sufficient number of intervals with a low error rate compared to other related techniques. HSMPAR algorithm is an optimization algorithm that randomly generates solutions for alphabet and word sizes and selects the best solutions. HS algorithms are compatible with multi-pitch adjustment. The integration of the RF and HSMPAR algorithms is developed to maximize information rather than to improve the error rate. The algorithms are tested on 20 standard time series datasets and are compared with the meta-heuristic algorithms GENEBLA and the original SAX algorithm. The experimental results show that the proposed method generates larger alphabet and word sizes and achieves a lower error rate than the compared methods. With larger alphabet and word sizes, the proposed method is capable of preserving important information.

Бесплатно

A High-Performance Communication Service for Parallel Servo Computing

A High-Performance Communication Service for Parallel Servo Computing

Cheng Xin, Zhou Yunfei, Hu Yongbin, Kong Xiangbin

Статья научная

Complexity of algorithms for the servo control in the multi-dimensional, ultra-precise stage application has made multi-processor parallel computing technology needed. Considering the specific communication requirements in the parallel servo computing, we propose a communication service scheme based on VME bus, which provides high-performance data transmission and precise synchronization trigger support for the processors involved. Communications service is implemented on both standard VME bus and user-defined Internal Bus (IB), and can be redefined online. This paper introduces parallel servo computing architecture and communication service, describes structure and implementation details of each module in the service, and finally provides data transmission model and analysis. Experimental results show that communication services can provide high-speed data transmission with sub-nanosecond-level error of transmission latency, and synchronous trigger with nanosecond-level synchronization error. Moreover, the performance of communication service is not affected by the increasing number of processors.

Бесплатно

A Lightweight Face Recognition Model Using Convolutional Neural Network for Monitoring Students in E-Learning

A Lightweight Face Recognition Model Using Convolutional Neural Network for Monitoring Students in E-Learning

Duong Thang Long

Статья научная

Using convolution neural network (CNN) for face recognition is being widely research with a promising significant in applications and it is interested by many authors. Moreover, the CNN model has brought successful applications in practice such as detection and identification face of people on Facebook users' photos application, they use DeepFace model. There are many articles which proposed CNN models for face recognition with using some modifications of popular models of large architectures such as VGG, ResNet, OpenFace or FaceNet. However, these models are large complexity for some applications in reality with limitations of computing resources. This paper proposes a design of CNN model with moderate complexity but still ensures the quality and efficiency of face recognition. We run experiments for evaluating the model on some popular datasets, the experiment shows effective results and indicates that the proposed model can be practically used.

Бесплатно

A Low Cost High Speed FPGA-Based Image Processing Framework

A Low Cost High Speed FPGA-Based Image Processing Framework

Mohammad Reza Mahmoodi, Sayed Masoud Sayedi

Статья научная

In this paper, a high-speed and low-cost image processing framework based on MATLAB-FPGA interface is proposed that can be used in researches aiming at developing wide variety of not only image processing tasks but also many signal processing applications. In addition, this new framework could be exploited for several other tasks such as on-chip verification, using PC as an enormous external RAM for FPGA while preserving high speed data access, developing hardware-software co-designs, etc. The communication between FPGA and MATLAB is via 1Gbs Ethernet based on UDP/IP protocol which is very promising for high speed data transmission in point-to-point communications. UDP stack is efficiently designed in FPGA based on a fully pipelined architecture with minimum level of logic in order to reach high performance.. Dynamic data transmission between the UDP stack, memory and an arbitrary image processing module makes it possible to practically simulate, debug and implement most relevant applications. The hardware system is relatively low-cost and it consumes a negligible area of a Spartan-6 LXT45 Xilinx FPGA. Operating at 1 Gb/s, theoretically, the system is capable of processing 132 frames of 640*480 color images in a second. The effectiveness of the system is evaluated by means of both place and route simulation and practical implementation of a skin detection algorithm and a motion detector.

Бесплатно

A Match or Mismatch Between Learning Styles of the Learners and Teaching Styles of the Teachers

A Match or Mismatch Between Learning Styles of the Learners and Teaching Styles of the Teachers

Abbas Pourhosein Gilakjani

Статья научная

It is important to study learning styles because recent studies have shown that a match between teaching and learning styles helps to motivate students´ process of learning. That is why teachers should identify their own teaching styles as well as their learning styles to obtain better results in the classroom. The aim is to have a balanced teaching style and to adapt activities to meet students´ style and to involve teachers in this type of research to assure the results found in this research study. Over 100 students complete a questionnaire to determine if their learning styles are auditory, visual, or kinesthetic. Discovering these learning styles will allow the students to determine their own personal strengths and weaknesses and learn from them. Teachers can incorporate learning styles into their classroom by identifying the learning styles of each of their students, matching teaching styles to learning styles for difficult tasks, strengthening weaker learning styles. The purpose of this study is to explain learning styles, teaching styles match or mismatch between learning and teaching styles, visual, auditory, and kinesthetic learning styles among Iranian learners, and pedagogical implications for the EFL/ESL classroom. A review of the literature along with analysis of the data will determine how learning styles match the teaching styles.

Бесплатно

A Metaheuristic Algorithm for Job Scheduling in Grid Computing

A Metaheuristic Algorithm for Job Scheduling in Grid Computing

Hedieh Sajedi, Maryam Rabiee

Статья научная

These days the number of issues that we can not do on time is increasing. In the mean time, scientists are trying to make questions simpler and using computers. Still, more problems that are complicated need more complex calculations by using highly advanced technology. Grid computing integrates distributed resources to solve complex scientific, industrial, and commercial problems. In order to achieve this goal, an efficient scheduling system as a vital part of the grid is required. In this paper, we introduce CUckoo-Genetic Algorithm (CUGA), which inspired from cuckoo optimization algorithm (COA) with genetic algorithm (GA) for job scheduling in grids. CUGA can be applied to minimize the completion time of machines, and it could avoid trapping in a local minimum effectively. The results illustrate that the proposed algorithm, in comparison with GA, COA, and Particle Swarm Optimization (PSO) is more efficient and provides higher performance.

Бесплатно

A Methodology for Reliable Code Plagiarism Detection Using Complete and Language Agnostic Code Clone Classification

A Methodology for Reliable Code Plagiarism Detection Using Complete and Language Agnostic Code Clone Classification

Sanjay B. Ankali, Latha Parthiban

Статья научная

Code clone detection plays a vital role in both industry and academia. Last three decades have seen more than 250 clone detection techniques with lack of single framework that can detect and classify all 4 basic types of code clones with high precision. This serious lack of clone classification impacts largely on the universities and online learning platforms that fail to validate the projects or coding assignments submitted online. In this paper, we propose a complete and language agnostic technique to detect and classify all 4 clone types of C, C++, and Java programs. The method first generates the parse tree then extracts the functional tree to eliminate the need for the preprocessing stage employed by previous clone detection techniques. The generated parse tree contains all the necessary information for detecting code clones. We employ TF-IDF cosine similarity for the proper classification of clone types. The proposed technique achieves incredible precision rate of 100% in detecting the first two types of clones and 98% precision in detecting type-3 and type-4 clones for small codes of C, C++, and Java containing an average line count of 5. The proposed technique outperforms the existing tree-based clone detection tools by providing the average precision of 98.07% on the C, C++, and Java programs crawled from Github with an average line count of 15 which signifies that cosine similarity measure on ANTLR functional tree accurately detects all 4 types of small clones and act as proper validation tools for identifying the learning level in the submitted programming assignment.

Бесплатно

A Methodology for Teaching Computer Programming: first year students’ perspective

A Methodology for Teaching Computer Programming: first year students’ perspective

Bassey Isong

Статья научная

The teaching of computer programming is one of the greatest challenges that have remained for years in Computer Science Education. A particular case is computer programming course for the beginners. While the traditional objectivist lecture-based approaches do not actively engage students to achieve their learning outcome, we believe that integrating some cutting-edge processes and practices like agile method into the teaching approaches will be leverage. Agile software development has gained widespread popularity and acceptance in the software industry and integrating the ideas into teaching will be constructive. In the educational system, while the positive impact of agile principles has been felt on students’ projects, none has been experienced on the teaching aspect. Therefore, this paper proposes the use of agile process in the teaching of first year programming courses. The goal is to help the beginners develop their programming skills, proffer a teaching technology that maximizes students’ chances of engagement, improve teaching as teachers reflects on what they are teaching and what the students are learning. Additionally, beginners will be able to operate the computer, program, and improve their programming skills through active team collaboration as well as managing large classes effectively by the teacher.

Бесплатно

A Modernized Voting System Using Fuzzy Logic and Blockchain Technology

A Modernized Voting System Using Fuzzy Logic and Blockchain Technology

Mousumi Mitra, Aviroop Chowdhury

Статья научная

Voting is a formal expression of one’s choice. Though the process is simple, it has far-reaching and deep-lying impacts. Through a vote, people get a channel to voice their opinion anonymously. There are issues with the orthodox traditional voting system, which is used across the world today. Studies, presented throughout the paper, would highlight how millions of people have missed out on voicing their opinion, or get proper representation, due to the many short-comings of the dated traditional voting systems. Blockchain is a comparatively new technology. There have been advances and research made to make use of blockchains in the world of finance and ledger management. But precious little has been done to tackle simpler but wider-reaching problems of voting. The novel approach suggested here would give the voters a chance to vote from the comfort of their homes, or, without adjusting their busy everyday schedules, and make sure everyone gets a proper representation as well. A combination of blockchain technology and fuzzy logic has been used here, to achieve a solution, that we think would help modernize the voting system and ensure greater satisfaction among the voters that their views have been represented in one way or the other. Using this novel approach, we believe that more people would be encouraged to vote and a greater number of voices would get proper representation.

Бесплатно

Журнал