International Journal of Modern Education and Computer Science @ijmecs
Статьи журнала - International Journal of Modern Education and Computer Science
Все статьи: 1096
Selecting qualitative features of driver behavior via pareto analysis
Статья научная
Driver behavior is the main cause of road crashes; it is the key element that insures a better understanding and improves predictions of car accidents. The main goal of our study is to determine the set of driver behavior features that are the most encountered in literature; we were based on behavioral questionnaires as a source for these features. We selected the questionnaires that are most cited in literature and therefore proved their efficiency through many studies they were employed in. Then we extracted the features considered in their items and classified them by rate of appearance according to the Pareto & ABC principle. In the second part of our study we collaborated with the National Committee for Circulation Accident Prevention (CNPAC) of the Ministry of Transportation of Morocco in order to compare the findings we gathered from literature with the researches they administer. We prepared a questionnaire that contains the final set of features and we transmitted it to experts working in the road safety field to rate it according to their knowledge and experience. Data analysis showed significant differences in some features, which demonstrates the gap between theoretical results and field research.
Бесплатно
Semantic Annotation of Pedagogic Documents
Статья научная
To teach, teacher needs help for sharing these educational documents, and especially his knowledge. We present an approach to overcome the difficulty of sharing educational materials and facilitate access to content; we describe semantically these documents to make them accessible and available to different users. The main idea in our annotation approach is based on: (1) Identify key words in a document, to have a good presentation of the document, we extract the candidate words by applying a weighting process and another process using similarity measure, These keywords candidates are reconciled with ontology to determine the appropriate concepts. (2) As document reference generally other documents, we propagate the annotations of references for citing document. (3) A process of validation will be applied each time an annotation is added in order to keep the coherence of the base of annotation. After evaluation with several types of pedagogic documents, our approach achieved a good performance; this suggests that teachers can be greatly helped for the semantic annotation of their pedagogical documents.
Бесплатно
Semantic Management Information Modeling based on Theory of Concept Lattices
Статья научная
With the development of future Internet, it is of great significance to study how to realize unified management information modeling, in order to avoid a lot of repetitive work and standardize information modeling in network management domain. This paper discusses the problem from the ontology point of view and introduces the theory of concept lattices into the research on semantic management information modeling, which includes a) establishing an ontology-driven framework for semantic management information modeling, b) building unified management information modeling ontology based on concept lattices, and c) generating semantic models for network management information modeling using the theory of concept lattices.
Бесплатно
Semantic Question Generation Using Artificial Immunity
Статья научная
This research proposes an automatic question generation model for evaluating the understanding of semantic attributes in a sentence. The Semantic Role Labeling and Named Entity Recognition are used as a preprocessing step to convert the input sentence into a semantic pattern. The Artificial Immune System is used to build a classifier that will be able to classify the patterns according to the question type in the training phase. The question types considered here are the set of WH-questions like who, when, where, why, and how. A pattern matching phase is applied for selecting the best matching question pattern for the test sentence. The proposed model is tested against a set of sentences obtained from many sources such as the TREC 2007 dataset for question answering, Wikipedia articles, and English book of grade II preparatory. The experimental results of the proposed model are promising in determining the question type with classification accuracy reaching 95%, and 87% in generating the new question patterns.
Бесплатно
Semi-Supervised Personal Name Disambiguation Technique for the Web
Статья научная
Personal name ambiguity in the web arises when more than one person shares the same name. Personal name disambiguation involves disambiguating the name by clustering web page collection such that each cluster represents a person having the ambiguous name. In this paper, a personal name disambiguation technique that makes use of rich set of features like Nouns, Noun phrases, and frequent keywords as features is proposed. The proposed method consists of two phases namely clustering seed pages and then clustering the actual web page collection. In the first phase, seed pages representing different namesakes are clustered and in the second phase, web pages in the collection are clustered with the similar seed page clusters. The usage of seed pages increases the accuracy of clustering process. Since it is difficult to predict the number of clusters need to be formed beforehand, the proposed technique uses Elbow method to calculate the number of clusters. The efficiency of the proposed name disambiguation technique is tested using both synthetic and organic datasets. Experimental result shows the proposed method achieves robust results across different datasets and outperforms many existing methods.
Бесплатно
Sentiment Analysis of Twitter User Data on Punjab Legislative Assembly Election, 2017
Статья научная
Sentiment Analysis is the way of gathering and inspecting data based on the personal emotions, reviews, and contemplations. The sentimental analysis is also recognized as opinion mining since it mines the major feature from people opinions. There are various social networking platforms, out of which Twitter is praised by lawmakers, academicians, and journalists for its potential political values. In literature, numerous studies have been performed on the data ecstatic to elections on Twitter. The greater part of them has been on the U.S Presidential Elections where there are two main applicants who fight it out. Since individuals discuss so many political parties and candidates and their prospects too in rendered messages, the issues of distinguishing their political feeling become extensive and fascinating. Consideration of all these aspects along with a sheer volume of data propelled us to look into the data and find interesting inferences in it. To select the 117 members of the Punjab Legislative Assembly, Legislative Assembly election was held in Punjab, the State of India on 4 February 2017. As per the Election Commission, a total of 1.9 crore voters is eligible for voting in August 2016 in Punjab. The data set that is collected with the help of Twython was analyzed to find out trivial things and interesting patterns in the data. The central idea of this research paper is to carry out the sentiment analysis on Legislative Assembly election 2017 that was held in the Punjab, a state of India for the Political Parties like BJP, INC, and AAP. We have analyzed and fetch significant implications from the tweets gathered over the whole period of elections.
Бесплатно
Sentiment analysis on mobile phone reviews using supervised learning techniques
Статья научная
Opinion Mining or Sentiment Analysis is the process of mining emotions, attitudes, and opinions automatically from speech, text, and database sources through Natural Language Processing (NLP). Opinions can be given on anything. It may be a product, feature of a product or any sentiment view on a product. In this research, Mobile phone products reviews, fetched from Amazon.com, are mined to predict customer rating of the product based on its user reviews. This is performed by the sentiment classification of unlocked mobile reviews for the sake of opinion mining. Different opinion mining algorithms are used to identify the sentiments hidden in the reviews and comments for a specific unlocked mobile. Moreover, a performance analysis of Sentiment Classification algorithms is performed on the data set of mobile phone reviews. Results yields from this research provide the comparative analysis of eight different classifiers on the evaluation parameters of accuracy, recall, precision and F-measure. The Random Forest Classifiers offers more accurate predictions than others but LSTM and CNN also give better accuracy.
Бесплатно
Статья научная
It is difficult for higher education institutes to manage the growing volumes of educational data accurately and efficiently using conventional ways. Modern technology is required to deal with this difficulty and ICT is an emerging technology that can solve this problem. In this study, Service-Oriented Computing (SOC) is used to develop a Service-Oriented Registrar System (SORS) for Debre Markos University Burie campus registrar office. Web services are used to develop highly cohesive and loosely coupled subsystems that support location transparency and manage the academic records of students accurately and efficiently. Moreover, the developed system is secured, easily maintainable, expandable and open for either inter or intra-application integration on the campus.
Бесплатно
Shapley's Axiomatics for Lexicographic Cooperative Games
Статья научная
In classical cooperative game theory one of the most important principle is defined by Shapley with three axioms common payoff fair distribution's Shapley value (or Shapley vector). In the last decade the field of its usage has been spread widely. At this period of time Shapley value is used in network and social systems. Naturally, the question is if it is possible to use Shapley's classical axiomatics for lexicographic cooperative games. Because of this in the article for m dimensional lexicographic cooperative v= (vT ,...,vM )1T game game is introduced Shapley's axiomatics, as the principle of a fair distribution in the case of dimensional payoff functions, when the criteria are strictly ranking. It has been revealed that axioms discussed by Shapley for classical games are sufficient in lexicographic cooperative games corresponding with the payoffs of distribution. Besides we are having a very interesting case: according to the proved theorem, Shapley's classical principle simultaneously transforms on the composed scalar v1,…, vm games of a lexicographic cooperative game, nevertheless, v2,…, vm games could not be superadditive.
Бесплатно
Статья научная
Feature driven development (FDD) is a process oriented and client centric agile software development model which develops a software according to client valued features. Like other agile models it also has adaptive and incremental nature to implement required functionality in short iterations. FDD mainly focus on designing and building aspects of software development with more emphasis on quality. However less responsiveness to changing requirements, reliance on experienced staff and less appropriateness for small scale projects are the main problems. To overcome these problems a Simplified Feature Driven Development (SFDD) model is proposed in this paper. In SFDD we have modified the phases of classical FDD for small to medium scale projects that can handle changing requirements with small teams in efficient and effective manner.
Бесплатно
Simulation and Analysis of AODV and DSR Routing Protocol under Black Hole Attack
Статья научная
In this paper, two routing protocols (AODV and DSR) are simulated under regular operation, single and cooperative black hole attack. This work has been performed by simulator to show consequence of black hole attacks in MANET by using various graphs which are used to collect data in term of several metrics. One common method to perform most of researches in the MANET security field is to simulate and analyze the routing protocols in various scenarios. This work has been based on the implementation and experiments in the OPNET modeler version 14.5. Finally the results have been computed and compared to stumble on which protocol is least affected by these attacks.
Бесплатно
Статья научная
Recording of ground motions with high amplitudes of acceleration and velocity play a key role for designing engineering projects. Here we try to represent a reasonable prediction of peak ground acceleration which may create more than g acceleration in different regions. In this study, applying different structures of Neural Networks (NN) and using four key parameters, moment magnitude, rupture distance, site class, and style of faulting which an earthquake may cause serious effects on a site. We introduced a radial basis function network (RBF) with mean error of 0.014, as the best network for estimating the occurrence probability of an earthquake with large value of PGA ≥1g in a region. Also the results of applying back propagation in feed forward neural network (FFBP) show a good coincidence with designed RBF results for predicting high value of PGA, with Mean error of 0.017.
Бесплатно
Статья научная
In this paper, Coded Orthogonal Frequency Division Multiplexing (COFDM) based Radio over Fiber (RoF) system is simulated (for different bit rates) for different modulation techniques to observe impact on system parameter [quality factor (Q)]. Influence of increasing bit rates has been observed for 2 km long linear multimode fiber. To reduce dispersion due to multimode fiber, convolutional encoder (code rate ½, generator polynomial 1338, 1718) and viterbi hard decision decoding algorithm are chosen for simulative model of COFDM based RoF system. Transmission of 32 sub-carriers with externally modulated continuous wave laser source gave satisfied results for Q values.
Бесплатно
Software Defect Prediction Using Variant based Ensemble Learning and Feature Selection Techniques
Статья научная
Testing is considered as one of the expensive activities in software development process. Fixing the defects during testing process can increase the cost as well as the completion time of the project. Cost of testing process can be reduced by identifying the defective modules during the development (before testing) stage. This process is known as “Software Defect Prediction”, which has been widely focused by many researchers in the last two decades. This research proposes a classification framework for the prediction of defective modules using variant based ensemble learning and feature selection techniques. Variant selection activity identifies the best optimized versions of classification techniques so that their ensemble can achieve high performance whereas feature selection is performed to get rid of such features which do not participate in classification and become the cause of lower performance. The proposed framework is implemented on four cleaned NASA datasets from MDP repository and evaluated by using three performance measures, including: F-measure, Accuracy, and MCC. According to results, the proposed framework outperformed 10 widely used supervised classification techniques, including: “Naïve Bayes (NB), Multi-Layer Perceptron (MLP), Radial Basis Function (RBF), Support Vector Machine (SVM), K Nearest Neighbor (KNN), kStar (K*), One Rule (OneR), PART, Decision Tree (DT), and Random Forest (RF)”
Бесплатно
Software Inspection in Software Industry: A Pakistan's Perspective
Статья научная
Today in software world the qualifying criterion for a software product is to be of high quality. Quality enables a software product to conform to customer's expectations. It is another name for best available services and is made acceptable through many practices like reviews, inspections and testing. Among these software inspection is the one which is cost efficient and easy to implement technique. Software inspection is composed of many activities to result in improving the underlying document better and creates consistent understanding. This research presents the different activities in the inspection and practicing of these activities in the software industry of Pakistan. This research is carried out through questionnaires. The answers demonstrate that software inspection is source of better quality products and customer satisfaction without using any proper framework of inspection.
Бесплатно
Software Testing Resource Allocation and Release Time Problem: A Review
Статья научная
Software testing Resource allocation and release time decisions are vital for the software systems. The objective behind such critical decisions may differ from firm to firm. The motive of the firm may be maximization of software reliability or maximization of number of faults to be removed from each module or it may be minimization of number of faults remaining in the software or minimization of testing resources. Taking into consideration these different aims, various authors have investigated the problem of resource allocation and release time problem. In this paper we investigate various software release policies and resource allocation problem, for example, policies based on the dual constraints of cost and reliability.
Бесплатно
Solution and Level Identification of Sudoku Using Harmony Search
Статья научная
Different optimization techniques have been used to solve Sudoku. Zong Woo Geem have applied harmony search in Sudoku to get better result. He has taken a Sudoku and time complexity has been optimized by different values of parameters. But, he has not given way of solution in details. He has also not given any idea to recognize the level of Sudoku. In this paper, an algorithm has been proposed based on harmony search to solve and identify the Sudoku efficiently. It has been observed that time complexity i.e. the maximum number of iteration has been reduced by choosing appropriate parameter values. The level of Sudoku has also been identified using probability metric. Finally, the number of iterations has been calculated with different values of parameters and the level of different Sudoku has been identified.
Бесплатно
Solution for Using FEMM in Electrostatic Problems with Discrete Distribution Electric Charge
Статья научная
Finite Element Method Magnetics (FEMM) is an open source software package for solving electromagnetic problems based on the finite element method. The application can numerically solve linear electrostatic problems and magnetostatic 2D problems, respectively low frequency magnetic, linear harmonic and nonlinear. FEMM is a product much used in science and engineering that, in the last 15 years, has begun to be used more and more in the academic environment. Despite the fact that FEMM can be used to solve complex problems in science and engineering, electrostatic FEMM cannot work directly with discrete electric charge distributions, that is, point electric charge. This work presents a FEMM model for simulating point electric charge that can be used in case of electrostatic problems with discrete charge distributions. The numerical solution for the electrostatic field is compared with the analytical solution. This model can be used in the case of an assembly of point electric charges with axial symmetry.
Бесплатно
Spam Mail Detection through Data Mining – A Comparative Performance Analysis
Статья научная
As web is expanding day by day and people generally rely on web for communication so e-mails are the fastest way to send information from one place to another. Now a day's all the transactions all the communication whether general or of business taking place through e-mails. E-mail is an effective tool for communication as it saves a lot of time and cost. But e-mails are also affected by attacks which include Spam Mails. Spam is the use of electronic messaging systems to send bulk data. Spam is flooding the Internet with many copies of the same message, in an attempt to force the message on people who would not otherwise choose to receive it. In this study, we analyze various data mining approach to spam dataset in order to find out the best classifier for email classification. In this paper we analyze the performance of various classifiers with feature selection algorithm and without feature selection algorithm. Initially we experiment with the entire dataset without selecting the features and apply classifiers one by one and check the results. Then we apply Best-First feature selection algorithm in order to select the desired features and then apply various classifiers for classification. In this study it has been found that results are improved in terms of accuracy when we embed feature selection process in the experiment. Finally we found Random Tree as best classifier for spam mail classification with accuracy = 99.72%. Still none of the algorithm achieves 100% accuracy in classifying spam emails but Random Tree is very nearby to that.
Бесплатно
Статья научная
This study employed geographic information systems (GIS) to analyze the spatial factors related to dengue fever (DF), dengue hemorrhagic fever (DHF), and dengue shock syndrome (DSS) epidemics. Chachoengsao province, Thailand, was chosen as the study area. This study examines the diffusion pattern of disease. Clinical data including gender and age of patients with disease were analyzed. The hotspot zonation of disease was carried out during the outbreaks for years 2001 and 2007 by using local spatial autocorrelation statistics (LSAS) and kernel-density estimation (KDE) methods. The mean center locations and movement patterns of the disease were found. A risk zone map was generated for the incidence. Data for spatio-temporal analysis and risk zonation of DF/DHF/DSS were employed for years 2000 to 2007. Results found that the age distribution of the cases was different from the general population’s age distribution. Taking into account that the quite high incidence of DF/DHF/DSS cases was in the age group of 13-24 years old and the percentage rate of incidence was 42.9%, a DF/DHF/DSS virus transmission out of village is suspected. An epidemic period of 20 weeks, starting on 1st May and ending on 31st September, was analyzed. Approximately 25% of the cases occurred between Weeks 6-8. A pattern was found using mean centers of the data in critical months, especially during rainy season. Finally, it can be identified that from the total number of villages affected (821), the highest risk zone covered 7 villages (0.85%); the moderate risk zone comprised 39 villages (4.75%); for the low risk zone 22 villages (2.68%) were found; the very low risk zone consisted of 120 villages (14.62%); and no case occurred in 633 villages (77.10%). The zones most at risk were shown in districts Mueang Chachoengsao, Bang Pakong, and Phanom Sarakham. This research presents useful information relating to the DF/DHF/DSS. To analyze the dynamic pattern of DF/DHF/DSS outbreaks, all cases were positioned in space and time by addressing the respective villages. Not only is it applicable in an epidemic, but this methodology is general and can be applied in other application fields such as dengue outbreak or other diseases during natural disasters.
Бесплатно
