Graduate School of Natural and Applied Sciences
Permanent URI for this community
Browse
Browsing Graduate School of Natural and Applied Sciences by Subject "information technology"
Now showing 1 - 7 of 7
Results Per Page
Sort Options
Item A CASE STUDY FOR DESIGNING AN ADAPTIVE LEARNING ENVIRONMENT BY APPLYING VARK MODEL(2017-05-02) Jaballa, Rabieaa Abdusalam Massaud; Eryılmaz, MeltemThe styles of learning are personal traits that affect how students relate with their learning environment, peers, and instructor. Four of the most popular are reading / writing, visual, auditory and kinetic, which used by students to gain information. Number of students is visual learners, while others are kinesthetic or audio or read /write learners. While some other students use a combination all of them to gain information, they seem to have preferences in how to learn better. Teachers must teach as more of these preferences as possible, in order to assist students learn. Teachers can put together these learning styles into core curriculum activities so that students can succeed in their classes. This study shows some parts of development framework to identify students learning styles and combination it automatically. This system is based on VARK learning style model and VARK questionnaire to measure students’ learning styles, it is hosting by internet to help students to use it. This study has used a sample of participants that consisted of 50 of engineering students from Atilim University. In addition, this study contain, an experimental design with a pre-post test Control group was utilized. Accordingly analysis of the data, the results show that distribution for t-test for two groups (Control group and Experimental group) was normality distribution and it was determined that the difference in mean scores between the Experimental group and the Control group was significantly in help of the Experimental group and the achievement level in the Experimental group, which applied the VARK teaching model, was higher compared to the Control group. In addition, student satisfaction questionnaire instrument, 10-items that measure students’ satisfaction by using the system, as the results found that students’ satisfaction with the system was significant very high.Item A FRAMEWORK FOR DESIGNING AN INFORMATION SYSTEM FOR DOWN SYNDROME PATIENTS(2022-02-15) AL-TAMEEMI, Haitham; Erkan, Turan Erman; Turhan, ÇiğdemThe possibility of setting up a framework for designing a new system for individuals with Down syndrome was studied. The idea behind this framework is to develop a remote monitoring system called Down Syndrome Information System (DSIS) that will contribute to improve the health status of individuals with Down syndrome, by allocating more resources to information technology. This framework is intended to guide developers to implement the proposed system in the future. The main objective of this thesis is to answer the question of can the proposed framework will be able to support the developers to design a DSIS. In order to answer this question, it is required to find answers to these other questions. 1) Can the proposed system satisfy end user's needs?; 2) Can the proposed system invest in IT in the healthcare field?; 3) Is the proposed system implementable by the developer? 4) What are the advantages between the newly proposed and the current system? The related works were surveyed and it was found that there is a lack in IT investment in health care services for people with Down syndrome. This lack became one of the main motivations for this thesis. In addition, the first three steps of system development life cycle approach (SDLC) will play a big role in setting the methodology of this framework. Questions 1 and 2 were addressed by the investigations illustrated. As for questions 3 and 4, they were answered by visualizing the proposed system to ensure implementing it. Limitations of this thesis include; 1) The proposed system is only applied for Down syndrome cases. 2) Using correlations functions as a statistical method to analyze the results of questionnaire form. 3) Using the first three steps of SDLC approach to set this framework. 4) Lastly, there are limitations related to the collections of feedbacks from some of Arabic countries including Iraq, and the dependent on journals and conferences for previous studies. This thesis will expected to contribute to set this framework as an educational guide for developers to build monitoring system for Down syndrome, build a hybrid system by involving the responsible people of Down syndrome in this system, and enhance the health status of individuals with Down syndrome.Item A HYBRID METHOD FOR MISSING VALUE IMPUTATION(2022-02-16) Al-Brge, Basma; Koyuncu, MuratMissing data arises in almost all serious statistical analyses. Statistical analyses have a variety of methods to handle missing data, including some relatively simple approaches that can often yield reasonable results such as the random imputation approach. The missing data imputation process must be modeled in order to perform imputations correctly. Using datasets in empirical applications is very common to perform some tasks; however, missing values in datasets should be extracted from the datasets or should be estimated before they are used for processing to produce correct association rules or clustering in the preprocessing stage of data mining and processing. In this thesis, a hybrid approach is used that combines K-Nearest Neighbor (KNN) with Singular Value Decomposition (SVD) algorithm to improve the data imputation and produce data with high correlation with original missing values. The test results of the proposed hybrid method are compared with the results of several alternative methods for different rate of missing values and the results of the proposed method yields better performance than the others. The results are also compared with the reported results in the literature to give an idea about its performance.Item ENHANCEMENTS IN FINGERPRINT AUTHENTICATION(2017-06-02) Alsubaihawi, Mohammed Abdulraheem Taqi; BOSTAN, AtilaFingerprint identification and verification tasks are among the most challenging tasks in image processing and machine learning domains. Fingerprint processing presents a key issue in the biometric technologies and information security. According to the fraction of the people population based on the complete detection of the biometric fingerprint feature such as ridge structure, incomplete (portion) fingerprint image identification and verification task is very difficult to be accomplished. The main challenge in this problem is that the partial loss of the ridge structure in the incomplete fingerprint image. In this thesis, we studied the effectiveness of global feature approach in fingerprint identification and verification task that can deal with the partial image loss or incomplete fingerprint image. Global feature vector extraction is the main global approach that we contribute in this thesis. In this case, we implemented global geometrics based feature extraction for fingerprint identification and verification task. A set of global features (seven-moment values) were extracted from the partial fingerprint (incomplete fingerprint image). The study shows that global feature vector can more efficiently deal with incomplete fingerprint recognition problem when compared with the classical approach to the fingerprint identification and verification problem which is based on extracting minutia features from the fingerprint rides as well as the pores in different feature extraction levels. The studied system has been tested using a database that was randomly generated out of some random incomplete fingerprint images. Randomly generated incomplete fingerprint images were sorted into 10 groups according to the size of the missing part in each image. Then we randomly selected random images from each group to compose a new challenge dataset to be tested in two different approaches which are global, and Local feature extraction approaches. The experimental results show that global approach has about 87% while the local approach has 17% of identification and verification effectiveness. This means global approach improves the performance of the fingerprint identification and verification system on partial (incomplete) fingerprint images by 70% more than the classical approach.Item PERCEPTIONS AND ATTITUDES OF LIBYAN HEALTHCARE PROVIDER TOWARDS ELECTRONIC HEALTH RECORDS(2022-02-17) Osman, Magdah; Çağıltay, Nergiz ErcilElectronic health records may have several benefits for hospitals, health professionals as well as patients. Electronic Health Record (EHR) systems provide basic clinical data that increase the quality of healthcare provided to citizens and benefits the community. The aim of this study is to evaluate and estimate the healthcare providers’ perceptions and attitudes towards the use of EHR in their environments in Libya. A sample of 110 health sector participants from various medical specialties in Libyan hospitals was targeted. The purpose of this research was to determine the perceptions and attitudes of Libyan healthcare providers towards EHR usage, by analyzing their demographics, organizational characteristics and the social, technical factors that possibly affect the EHR usage. Accordingly, survey method based on the previous studies is implemented through Survey Monkey environment; after the data collection was completed SPSS was used for statistical analysis, the results of the research lead to EHR factors Management support, Involvement and Adequate training have positive correlations with healthcare provider’s perceptions and Attitudes, while Autonomy and healthcare provider-patient communication have negative correlations with healthcare provider’s perceptions and had significant strong positive correlations with Attitude.Item STUDY OF WORD EMBEDDING RULES AND MACHINE LEARNING BASED TEXT CLASSIFICATION(2022-01-26) AUBAID, Asmaa; Mishra, Alok; GÖRÜR, AbdülkadirWith the growth of online information and the sudden growth in the number of electronic documents provided on the Web and in digital libraries, there is difficulty in categorizing text documents. Therefore, embedding, rule-based and machine learning approaches are the best solutions to this problem as the rule-based approach is considered to be one of the most flexible methods by which the black box of the process of the text classification technique can be shown. The details of a process of classification can be seen and it can add some tools or new instructions to obtain good results. This approach has high value for information retrieval, e-governments, information filtering, text databases, digital libraries, and other applications. The problem of the embedding technique and generating rule-based is very significant for text categorization. The general idea of any embedding technique is to determine the importance of keywords using a technique that can keep informative words and remove non-informative words, which can then help the text-categorization engine to categorize a document into a category. This thesis deals with the rule-based approach using the embedding technique for the word to vector (word2vec) and document to vector (doc2vec) approaches. It will use these two techniques to prepare keywords depending on the computation of similarity. After that, we use those keywords to apply the rule-based approach for a classifier to achieve to the best performance of the system by computing performance evaluation measures such as accuracy, recall, precision, and F-Measures. Experiments were performed on the Reuter 21578 and 20 Newsgroups datasets to classify the top ten categories of Reuter 21578 and 20 Newsgroups datasets. The Python language was used to create a rule-based approach followed by the overall effectiveness of the approach being measured with the F-Measure score, error rate, and accuracy. The results of rule-based with the embedding technique using the doc2vec model (d2vRule) in the case of the Reuter 21578 dataset were 79% precision, 75% recall, 76.75% F-Measures, 9.28% error rate and 90.72% accuracy measurements. For the 20 Newsgroups dataset, the results were 76% precision, 66.64% recall, 70.98% F-Measures, 9.93% error rate and 90.07% accuracy measurement. In addition, when the machine learning algorithms J-RIPPER (JRip), One Rule (OneR) and ZeroR were applied to the Reuter 21578 dataset, we obtained F-Measures and accuracy metrics of 0.713 − 0.752, 0.506 − 0.598 and 0.219 − 0.39 for JRip, One R and ZeroR, respectively. In addition, when applying those algorithms to our dataset, there was agreement and it appeared that our algorithm (d2vRule) performed better than these three algorithms mentioned above. Moreover, it provides a good classification process according to the evaluation metrics. On the other hand, when using the embedding technique with the word2vec model, it is predictable that these results depended on precision, recall and F-Measures approaches. Finally, it is clear that our rule-based approach is better than the results of machine learning, namely Naïve Bayes, Naive Bayes Updateable, Rules.DecisionTable, Lazy. IBL and Lazy.IBK. When it is validated for our rule-based (w2vRule), it can be seen that the rule-based (RB) classifier of a certain reference has the highest accuracy with 82.19% of correctly classified instances, while Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF), and Bayes Net (BN) have accuracies of 81.72%, 81.49%, 81.19%, and 77.85%, respectively, and the Temporal Specificity Score (TSS) classifier correctly classified 77.19% of instances referenced. However, our word-to-vector rule-based classifier (w2vRule) has an observed level of measurements in the case of the Reuter 21578 dataset were 73% precision, 77.71% recall, 75.09% F-Measures, 10.09% error rate and 89.91% accuracy. Therefore, it achieved the best result when we compared it with previous rule-based and machine learning classifiers.Item UNIVERSITY STUDENTS’ ATTITUDES TOWARDS CAPTCHA USE(2022-02-15) ELATRESH, Khalid; KOYUNCU, MuratCompletely Automated Public Turing test to tell Computers and Humans Apart (CAPTCHA) is a type of techniques that is utilized in order to be able to distinguish the actual human users from bots or for determining the users that are authorized to access a website or a file on the Internet. This thesis aims at determining attitudes of Libyan students towards different types of CAPTCHA in WWW environment. It also analyzes user attitudes according to demographic and Internet usage information including gender, age, education level, for how many years they have been using the Internet, and how often they use the Internet. To fulfill the purpose of the study, a questionnaire was prepared and Libyan students studying in different levels and departments answered to the questionnaire that is published through the Internet. The data obtained is processed using SPSS 18.0 software package. The obtained results reflect that the participants are familiar with all of types of CAPTCHA since they use them every day through navigating in the Web for books or scientific articles. However, user familiarity for text-based CAPTCHA is higher than the others. The No CAPTCHA reCAPTCHA type is the most favored one from different perspectives including error freeness, easiness, and security. Therefore, we conclude that the No CAPTCHA reCAPTCHA type is the most preferred type by users.