International Journal of Information Technology and Computer Science @ijitcs
Статьи журнала - International Journal of Information Technology and Computer Science
Все статьи: 1211
Detection of Plagiarism in Arabic Documents
Статья научная
Many language-sensitive tools for detecting plagiarism in natural language documents have been developed, particularly for English. Language-independent tools exist as well, but are considered restrictive as they usually do not take into account specific language features. Detecting plagiarism in Arabic documents is particularly a challenging task because of the complex linguistic structure of Arabic. In this paper, we present a plagiarism detection tool for comparison of Arabic documents to identify potential similarities. The tool is based on a new comparison algorithm that uses heuristics to compare suspect documents at different hierarchical levels to avoid unnecessary comparisons. We evaluate its performance in terms of precision and recall on a large data set of Arabic documents, and show its capability in identifying direct and sophisticated copying, such as sentence reordering and synonym substitution. We also demonstrate its advantages over other plagiarism detection tools, including Turnitin, the well-known language-independent tool.
Бесплатно
Detection of anomalies in fetus using convolution neural network
Статья научная
Parental diagnosis is required during mid-pregnancy period from 18-22 weeks in order to know the well-being of the fetus. This diagnosis is usually done through ultrasound scanning. Ultrasound scanning which is also called as sonogram, is an ultrasound based medical imagining technique used to envision the fetus and its development during the gestation period. If there is an abnormality in the diagnosed fetus then the parents and the doctors can do emergency parental care. Anomalies in Fetus occur before birth. Detecting fetal anomalies is a difficult task since it needs expertise and also requires a considerable amount of time, which will not be convenient at an emergency situation. In order to improve the diagnosis accuracy and to reduce the diagnosis time, it has become a demanding issue to develop an efficient and reliable medical decision support system. In this paper we present machine learning approach, such as convolution neural network which is most commonly applied to examine visual pretense. The main motive behind using CNN is due to their accuracy, fewer memory requirements and better training of images. This approach have shown great potential to be applied in the development of medical decision support system for Fetal anomalies which need immediate care.
Бесплатно
Determination of representativity for Bangla vowel perceptual space
Статья научная
In this article, representativity between two multidimensional acoustical spaces of vowel has been formulated based on the geometric mean of correlation of average directional vector, variance-covariance matrices, and Mahalanobis distance. Generally, the multidimensional spaces formed by different combinations of acoustical features of vowel are considered as the vowel perceptual spaces. Therefore, ten bangla vowel-sounds (/অ/ [/a/], /আ/ [/ã/], / ই/ [/i/] , /ঈ/ [/ĩ/], /উ/ [/u/], / ঊ/ /ũ/, /এ/ [/e/], /ঐ/ [/ai/] , /ও/ [/o/] and /ঔ/ [/au/]) are collected from each native Bengali speaker to build the perceptual space of the speaker using the acoustical features of vowels. Similarly, total nine perceptual spaces are constructed from nine speakers and these are utilized to evaluate representativity. Using the proposed method, representativities of differently constructed perceptual spaces have been evaluated and compared numerically. Furthermore, dominating and representative acoustical features are also identified from the principal components of the perceptual spaces.
Бесплатно
Determining Contribution of Features in Clustering Multidimensional Data Using Neural Network
Статья научная
Feature contribution means that what features actually participates more in grouping data patterns that maximizes the system’s ability to classify object instances. In this paper, modified K-means fast learning artificial neural network (K-FLANN) was used to cluster multidimensional data. The operation of neural network depends on two parameters namely tolerance (δ) and vigilance (ρ). By setting the vigilance parameter, it is possible to extract significant attributes from an array of input attributes and thus determine the principal features that contribute to the particular output. Exhaustive search and Heuristic search techniques are applied to determine the features that contribute to cluster data. Experiments are conducted to predict the network's ability to extract important factors in the presented test data and comparisons are made between two search methods.
Бесплатно
Determining the Degree of Knowledge Processing in Semantics through Probabilistic Measures
Статья научная
World Wide Web is a huge repository of information. Retrieving data patterns is facile by using data mining techniques. However identifying the knowledge is tough, tough because the knowledge should be meaningful. Semantics, a branch of linguistics, defines the process of supplying knowledge to the computer system. The underlying idea of semantics is to understand the language model and its correspondence with the meaning associability. Though semantics indicates a crucial ingredient for language processing, the degree of work composition done in this area is minimal. This paper presents an ongoing semantic research problem thereby investigating the theory and rule representation. Probabilistic approach for semantics is demonstrated to address the semantics knowledge representation. The inherit requirement for our system is to have the language syntactically correct. This approach identifies the meaning of the sentence at word-level. The accuracy of the proposed architecture is studied in terms of recall and precision measures. From the experiments conducted, it is clear that the probabilistic model for semantics is able to associate the language model at a preliminary level.
Бесплатно
Determining the Optimum Time Quantum Value in Round Robin Process Scheduling Method
Статья научная
The process scheduling, is one of the most important tasks of the operating system. One of the most common scheduling algorithms used by the most operating systems is the Round Robin method in which, the ready processes waiting in ready queue, seize the processor for a short period of time known as the quantum (or time slice) circularly. In this paper, a non-linear programming mathematical model is developed to determine the optimum value of the time quantum, in order to minimize the average waiting time of the processes. The model is implemented and solved by Lingo 8.0 software on four selected problems from the literature.
Бесплатно
Developing a Virtual Group Decision Support System Based on Fuzzy Hybrid MCDM Approach
Статья научная
Organizational decisions involve with unusually vague and conflicting criteria. This controversy increases empirical uncertainties, disputes, and the resulting consequences of these decisions. One possible method in subduing this problem is to apply quantitative approaches to provide a transparent process for resolute conclusions which enables decision makers to formulate accurate and decisive on time decisions. Although numerous methods are presented in the literature, the majority of them aim to develop theoretical models. However, this article aims to develop and implement an integrated fuzzy virtual MCDM model based on fuzzy AHP and fuzzy TOPSIS as a decision support system (DDS). Preventing disadvantageous face-to-face decision-making by achieving positive benefit from virtual decision making causes the proposed DDS to be suitable for making crucial decisions such as supplier selection, employee selection, employee appraisal, R&D project selection, etc. The proposed DDS has been implemented in an optical company in Iran.
Бесплатно
Developing an Efficient Model for Building Data Warehouse Using Mobile Agent
Статья научная
Data-warehouse is an emerging technology with great potential. Nowadays, businesses are competing fiercely to dominate the market where profitability is promising using every available means to reach their goal. Performance and storage are big challenges in building data-warehouse focusing by researchers recent years. In this paper a new model for developing an efficient data warehouse by using mobile agent technology has been proposed. The main idea behind this model is to use the mobile agent to extract and analyze operational data in their location. So, instead of using ETL, the mobile agent will be used. After the mobile agent completing its journey among operational databases, all tasks of ETL will be performed. By this way no need high storage media to extract the data from the operational database. As cost of time, the model proves less consuming of time. The model has been implemented using .Net Framework and C# and the results have been presented and discussed.
Бесплатно
Статья научная
This computing which runs on a web browser. It provides access to a number of web applications through internet without booting the whole OS. The purpose behind Cloud Operating System is that the full system is running on the Web browser and lives on it. Cloud OS is thought of as a new era of an Operating System in which everything inside an Operating System can be accessed from everywhere inside a specific network. The user just need to login onto the web browser and thus can have access to his personalized web-tops where all the applications and data is stored. In this paper it will discuss what is the difference between the Cloud OS and a simple Operating System and how the Cloud OS is developed defining all the requirements and functionalities of a cloud OS. We will also discuss in detail about the load balancing, Geo-replication Data Storage and Virtualization in Cloud OS.
Бесплатно
Development of Data Acquisition Console and Web Server Using Raspberry Pi for Marine Platforms
Статья научная
Marine vessels in today's age are fitted with a number of state of the art systems required for their smooth operation. The compartments which house such systems along with the restricted compartments onboard ships such as the ships galley, dry rations store, cold rooms, battery compartments etc are required to be monitored on real time basis for temperature, pressure, humidity for detecting various hazards like fire, flooding etc. In addition, military platforms also need to monitor compartments such as the armory and magazines to avoid damage to munitions and prevent unauthorized access. The present project aims to develop a proof of concept prototype real time parameter monitoring and motion detection system for critical/restricted compartments on marine platforms with data logging capability. Various sensors forming a sensor suite have been interfaced to the Raspberry Pi board, forming the Data Acquisition Console which is the nodal control center. As most marine vessels are fitted with a shipboard Local Area Network, the project utilizes this existing network for relaying data. The console is placed in the compartment where parameters are to be monitored and the measured data is acquired and transferred via wireless (using Access Points (APs) operating on Wi-Fi/ 802.11 network) or via wired connectivity with the nearest switch and be accessed by concerned personnel at various nodes/ computer on the . The performance of the DAC was successfully ascertained by comparison of sensor performance with other independent sensor readings. The measurement errors were found to be within the permissible accuracy limits of the sensors. Motion detection was achieved by using PIR motion The probability of detection (Pd) for the motion sensor was calculated by conducing iterative motion tests with favorable results. Data is displayed in a web-based dashboard Graphical User Interface. Further, provision has also been made to set visual alarms whenever a particular sensor reading crosses a pre-designated safe limit.
Бесплатно
Статья научная
UN Department of Economics and Social Affairs predicted that the world population will increase by 2 billion in 2050 with over 50% from the Sub-Saharan Africa (SSA). Considering the level of poverty and food insecurity in the region, there is an urgent need for a sustainable increase in agricultural produce. However, farming approach in the region is primarily traditional. Traditional farming is characterized by high labor costs, low production, and under/oversupply of farm inputs. All these factors make farming unappealing to many. The use of digital technologies such as broadband, Internet of Things (IoT), Cloud computing, and Big Data Analytics promise improved returns on agricultural investments and could make farming appealing even to the youth. However, initial cost of smart farming could be high. Therefore, development of a dedicated IoT cloud-based platform is imperative. Then farmers could subscribe and have their farms managed on the platform. It should be noted that majority of farmers in SSA are smallholders who are poor, uneducated, and live in rural areas but produce about 80% of the food. They majorly use 2G phones, which are not internet enabled. These peculiarities must be factored into the design of any functional IoT platform that would serve this group. This paper presents the development of such a platform, which was tested with smart irrigation of maize crops in a testbed. Besides the convenience provided by the smart system, it recorded irrigation water saving of over 36% compared to the control method which demonstrates how irrigation is done traditionally.
Бесплатно
Development of Myanmar-English Bilingual WordNet like Lexicon
Статья научная
A bilingual concept lexicon is of significance for Information Extraction (IE), Machine Translation (MT), Word Sense Disambiguation (WSD) and the like. Myanmar-English Bilingual WordNet like Lexicon (MEBWL) is developed to fulfill the requirements of Language Acquisition (LA). However, it is reasonably difficult to build such a lexicon is quite challenging in time and cost consuming. To overcome this challenging, this paper integrates linguistic resources, including Myanmar-English dictionary, English-Myanmar dictionary and WordNet to construct a Myanmar-English WordNet like lexicon by acquiring the lexical and conceptual knowledge from WordNet and Myanmar English Machine Readable Dictionaries (MRDs). The system includes three phases which include the MRD extraction phase, the link analyzing phase and the WordNet construction phase. The first phase converts the data from multiple resources with different format into a common format and joins and aligns the scattered data for smoothly access and group the data according their part of speech (POS). The link analyzing phase analyzes, classifies and generates candidates of translation links. In the constructing phase, MEBWL is constructed from the verified translation link and WordNet. Beside then, to support the inflected word of Myanmar to English words, morphological processor is designed.
Бесплатно
Development of Neuro-fuzzy System for Early Prediction of Heart Attack
Статья научная
This work is aimed at providing a neuro-fuzzy system for heart attack detection. Theneuro-fuzzy system was designed with eight input field and one output field. The input variables are heart rate, exercise, blood pressure, age, cholesterol, chest pain type, blood sugar and sex. The output detects the risk levels of patients which are classified into 4 different fields: very low, low, high and very high. The data set used was extracted from the database and modeled in order to make it appropriate for the training, then the initial FIS structure was generated, the network was trained with the set of training data after which it was tested and validated with the set of testing data. The output of the system was designed in a way that the patient can use it personally. The patient just need to supply some values which serve as input to the system and based on the values supplied the system will be able to predict the risk level of the patient.
Бесплатно
Статья научная
Superior garbage collection algorithms are needed for deterministic runtime system in complex embedded systems to explore the benefits of contemporary and conquered application programming language. Android embedded operating system is greatly used world wide as a mobile platform without denying this fact it also attracted researchers and engineers to integrate in other embedded real-time systems. It exploits Java language for embedded application development and it can also enhance a certain real time capability with the adoption of real-time support at Dalvik Virtual Machine (DVM). Need for Real-time garbage collection algorithms in embedded systems is identified by achieving new insights into the existing garbage collection algorithms through finding blemishes in it. The space based technique is used in proposed new Real-time GC algorithm for execution runtime system and Real time Garbage Collection (GC) schedulability issue is also addressed. The intuitive performance analysis result demonstrates reduction in the response time and also describes the determinism characteristic of the real time applications using proposed solution.
Бесплатно
Development of System for Automated & Secure Generation of Content (ASCGS)
Статья научная
Automation of manual work and systems is a vast growing trend as it brings in efficiency and quality in work. Online and offline aptitude exams are conducted by organizations and institutions for accessing the skills of students. An aptitude test is an effective method for testing the students however the creation of database for conducting aptitude tests is an uphill task, because the organization has to maintain to a very large database consisting of thousands of questions and the content has to be changed periodically to avoid repeating of questions. An Automated & Secure Content Generation System (ASCGS) is a framework that provides automated creation of aptitude questions by converting a single of type of question into multiple questions by altering its variables. Also the system automates the process of calculating the answer for every question by using its formula. Security in the system is provided by the means of encryption. The present system lags in many perspectives like every question in has to be created manually and also the answer for the question has to be computed manually. Since the entire work is being done manually so there is a high risk that some questions may contain error due to human fault and also the cost and effort required to create the content is large. The proposed system overcomes these shortcomings of the existing system as only one format is required to be created for one type of question thus saving time and human effort. Also it is no longer required to do mathematical calculation manually as it is done by the system, the user has to insert only the formula. The present system requires the organization very long time ranging from few weeks to few months for generating ten thousand questions. With the new system the same work can be done within few days time and with minimal cost. With the development of the system organizations will be relieved from the tedious work of content creation and also management of content will become easier and efficient. The software will enable the institutions to create aptitude questions of different levels thus enabling the institute to conduct aptitude tests for all the students of different classes based on their levels.
Бесплатно
Development of a Mobile-Based Hostel Location and Recommendation Chatbot System
Статья научная
A Chabot is a conversational intelligent agent that has the capability of engaging in human-like interaction with its users. A lot of chatbots have been developed, but to the best of our knowledge, there are few or no chatbots that have been developed for hostel location integrated with a recommendation component to ease the cost, time, and stress of identifying suitable hostels for students, especially at higher institutions of learning. Therefore, this work develops a location-based chatbot system enhanced with recommendation capabilities to allow students to locate hostels that satisfy their needs in an easy and efficient way. The chatbot system was designed as a cross platform compatibility application with different tools and technologies which include Python, HTML and CSS with JavaScript to enhance the interactivity and attractiveness of the system. PHP provides access to MySQL database. The chatbot system provides good experience to its users in terms of loading speed, user friendliness, interface appearance, platform compatibility and recommendation accuracy as it allows them identify suitable hostel speedily and as well provides personalized recommendation of hostels to them.
Бесплатно
Development of a Web Based Environmental Health Tracking System for Nigeria
Статья научная
This paper is to address the problem of environmental health monitoring system facing Nigeria as a whole. Environment and the factors that are associated with it are the root causes of many epidemic diseases both in the developed and developing nations. In Nigeria, environmental health problems arise from population pressure on housing, poor environmental sanitation, coupled with lack of safe drink water and basic housing facilities. Despite the deplorable state of environmental health (lack of clean and safe drinking water, bad housing condition, and so on), there is no reliable and timely means of surveillance or any monitoring system. The result of this research makes it possible for environmental health workers to capture environmental health situation of any house in Nigeria real time while on the field. In conclusion, this paper presents result of a research which developed a web based environmental health tracking system for Nigeria.
Бесплатно
Development of aggression detection technique in social media
Статья научная
Due to the enormous growth of social media the potential of social media mining has increased exponentially. Individual users are producing data at unprecedented rate by sharing and interacting through social media. This user generated data provides opportunities to explore what people think and express on social media. Users exhibit different behaviors on social media towards individuals, a group, a topic or an activity. In this paper, we present a social media mining approach to perform behavior analytics. In this research study, we performed a descriptive analysis of user generated data such as users’ status, comments and replies to identify individual users or groups which can be a potential threat. Tokenization technique is used to estimate the polarity of the behavior of different users by considering their comments or feedbacks against different posts on Facebook. The proposed approach can help to identify possible threats reflected by the user’s behavior towards a specific event. To evaluate the approach, a data set was developed containing comments on the Facebook from different users in different groups. The dataset was divided into different groups such as political, religious and sports. Most negative users’ in different groups were identified successfully. In our research, we focused only on English content; however, it can be evaluated with other languages.
Бесплатно
Development of an Electronic Secure Students' Industrial Works Experience Scheme Placement System
Статья научная
This research developed a secured student industrial work experience scheme (SIWES) placement system to take care of the security challenges of the existing automated systems. There are attempts by researchers to ameliorate the challenges associated with the scheme by developing various systems. However, the developed systems are subjected to security vulnerabilities. This research, in an attempt to avert the security challenges associated with the existing automated systems, designed a new scheme which includes security architectures in the kernel and application layers. This new system was able to achieve two important tasks; first, the system automation and second, the inclusion of security architectures to cubs the application’s vulnerabilities. The present process involves students manually seeking placement to undergo the program, and due to this, students end up applying at organizations that are not relevant to what they are studying. Despite the fact there are no much existing systems that digitally caters for this component of the scheme, the available existing systems are subjected to security vulnerability. Therefore, leveraging on secure web application technologies using Unified Modelling Languages for design, HTML, CSS, JavaScript, PHP for its implementation and user privilege and password hash to ensure its security, this project developed a secure solution to this pertinent challenge. The system is tested using unit testing component of each design, integration testing and general system testing. The implementation shows the system works according to the design, by ensuring all units of the development perform necessary functions of data storage, data retrieval, error alerting, and interface/server appropriate communication. In addition, the security architecture, design and implementation of the system’s design are better than the existing ones.
Бесплатно
Статья научная
Autism Spectrum Disorder (ASD) is a neuro developmental disorder that affects a person's ability to communicate and interact with others for rest of the life. It affects a person's comprehension and social interactions. Furthermore, people with ASD experience a wide range of symptoms, including difficulties while interacting with others, repeated behaviors, and an inability to function successfully in other areas of everyday life. Autism can be diagnosed at any age and is referred to as a "behavioral disorder" since symptoms usually appear in the life's first two years. The majority of individuals are unfamiliar with the illness and so don't know whether or not a person is disordered. Rather than aiding the sufferer, this typically leads to his or her isolation from society. The problem with ASD starts in childhood and extends into adolescence and adulthood. In this paper, we studied 25 research articles on autism spectrum disorder (ASD) prediction using machine learning techniques. The data and findings of those publications using various approaches and algorithms are analyzed. Techniques are primarily assessed using four publicly accessible non-clinically ASD datasets. We found that support vector machine (SVM) and Convolutional Neural Network (CNN) provides most accurate results compare to other techniques. Therefore, we developed an interactive dashboard using Tableau and Python to analyze Autism data.
Бесплатно
