Search

Copyright of Journal of Education & Science is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Baghdad Science Journal is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Deep learning is an effective data mining method that is used to analyze complex, and large quantities of data accurately and efficiently. In the last few years, the world has gone through an revolutionary change in the way of how data produced and how data are processed not similar to any time before. The data produced must be handled accurately using intelligent methods to get accurate results. For example, iris recognition is one of the applications that needs sophisticated algorithms capable to identify one person from the other via the iris data analysis. In the recent few year, it was clear how deep learning has been used in different areas of life. One of those areas is the pattern recognition area. In this review paper, we focus on the investigation of using the deep learning technologies for these purposes. The research methodology followed in this paper is based on reviewing, analyzing the academic papers published in the last couple of years in terms of the proposed paradigm used on the iris data, and the accuracy results obtained from using that paradigm as well as mentioning the datasets used in these paper. The outcomes of this paper showed that using the deep learning method, in particular, the Convolutional neural networks, has promising future due to its success in this domain. [ABSTRACT FROM AUTHOR]

Classification of birds is the area that is quite complex and involved such a lot of varieties that demands the correct as well as the professional organization of the information. This study addresses the problem of semantic interoperability in the bird categorization process by means of constructing an ontology which covers all the words used in taxonomic descriptions. The paper exploits XML/RDF standards for semantic web compatibility and Open Link Virtuoso SPARQL Query Editor that enables simple interaction with its tools and visualization in the process of querying and presentation of results. Attempt to develop a specific ontology for bird identification for the purpose of optimizing the accessibility and retrieval of heterogeneous bird-oriented data that ultimately help in building effective knowledge management system in this field. The effectiveness of an ontology is evaluated by its ability to make possible classification of diverse information. This research methodology is proposed for implementation in a broad range of researches, education, and conservation programs that can targeted to enhance their output and increase accuracy. [ABSTRACT FROM AUTHOR]

Copyright of Baghdad Science Journal is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Health Data clustering is a significant research direction aiming to extract knowledge from a continuous health data flow to support online health decisions. However, processing health data clusters is still a challenging task. Existing clustering approaches are subject to various limitations in terms of considering the neighbor clusters and conducting multiple operations during the maintenance process. In this paper, we model, design and implement a novel framework called IClustMaint for efficiently clustering and maintaining health data clusters incrementally. A two-phase algorithm is embedded in the framework. We first employ the Principal Component Analysis (PCA) method to efficiently reduce the high costs of the initial clustering phase. Next, in the maintenance phase, we propose the incremental Cluster maintenance (ICM) approach for managing the generated cluster during a period of time. Technically, when the data clusters are evolving over time and need to be maintained frequently, the ICM approach improves the performance of cluster maintenance by only tracking the edge points. The experimental results on a real medical dataset verify the efficiency of the proposed approaches. [ABSTRACT FROM AUTHOR]

Copyright of Iraqi Journal of Science is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Diyala Journal for Pure Science is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

World statistics declare that aging has direct correlations with more and more health problems with comorbid conditions. As healthcare communities evolve with a massive amount of data at a faster pace, it is essential to predict, assist, and prevent diseases at the right time, especially for elders. Similarly, many researchers have discussed that elders suffer extensively due to chronic health conditions. This work was performed to review literature studies on prediction systems for various chronic illnesses of elderly people. Most of the reviewed papers proposed machine learning prediction models combined with, or without, other related intelligence techniques for chronic disease detection of elderly patients at an early stage to avoid emergency situations. This method provides a promising approach in the analysis of either structured or unstructured datasets to produce very substantial pattern discoveries. By defining the generic architecture for the prediction model, we reviewed various papers involved in similar fields, based on suggested methodologies and their associated outcomes. The study discussed the pros and cons of different prediction models using traditional and modern machine learning techniques. [ABSTRACT FROM AUTHOR]

The presented studies have proven that machine learning algorithms The field of machine learning (ML) is expanding as more people realize how important it can be in a variety of crucial applications, including data mining, natural language processing, picture recognition, and expert systems. As it is well known that ML offers possible answers in all these domains and more, it is destined to be one of the pillars of our future civilization. This article presents an outline of the function of machine learning in prediction. algorithms have excelled in solving prediction and classification problems. Below We highlight the machine learning algorithms and techniques used in predicting crimes in particular, and the accuracy of the results obtained by each study or research. We see the challenges faced by a study or researcher who used machine learning algorithms and we hope with this paper, providing the researcher, in particular, with information covering the most important studies or research presented during the past five years to abbreviate the time of the researcher, and in the interest of his effort. [ABSTRACT FROM AUTHOR]

Copyright of College of Basic Education Researches Journal is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Baghdad Science Journal is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Education & Science is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Text summarization is an important research topic in information technology because of the large volume of texts and the large amount of data on the Internet and social media. As a result, summarizing the text has gained significant importance, requiring finding highly efficient ways to extract knowledge in various fields. Thus, there was a need for methods of summarizing texts for one document or multiple documents. Furthermore, the summarization methods aim to obtain the main content of the set of documents simultaneously to reduce redundant information. This paper proposes an efficient method to summarize texts that depends on the word association algorithm to separate and merge sentences after summarizing them. As well as the use of data mining technology in redistributing information according to the (K-Mean) algorithm and the use of (Term Frequency Inverse Document Frequency TF-IDF) technology for measuring the properties of summarized texts. The experimental results found that the summarization ratios are good by deleting unimportant words. Also, extracting characteristics for texts was useful in grouping similartexts into clusters, which makes this method possible to be combined with other methods in artificial intelligence, such as fuzzy logic or evolutionary algorithms, in increasing summarization rates and accelerating cluster operations. [ABSTRACT FROM AUTHOR]

Loanwords are the words transferred from one language to another, which become essential part of the borrowing language. The loanwords have come from the source language to the recipient language because of many reasons. Detecting these loanwords is complicated task due to that there are no standard specifications for transferring words between languages and hence low accuracy. This work tries to enhance this accuracy of detecting loanwords between Turkish and Arabic language as a case study. In this paper, the proposed system contributes to find all possible loanwords using any set of characters either alphabetically or randomly arranged. Then, it processes the distortion in the pronunciation, and solves the problem of the missing letters in Turkish language relative to Arabic language. A graph mining technique was introduced, for identifying the Turkish loanwords from Arabic language, which is used for the first time for this purpose. Also, the problem of letters differences, in the two languages, is solved by using a reference language (English) to unify the style of writing. The proposed system was tested using 1256 words that manually annotated. The obtained results showed that the f-measure is 0.99 which is high value for such system. Also, all these contributions lead to decrease time and effort to identify the loanwords in efficient and accurate way. Moreover, researchers do not need to have knowledge in the recipient and the source languages. In addition, this method can be generalized to any two languages using the same steps followed in obtaining Turkish loanwords from Arabic. [ABSTRACT FROM AUTHOR]

Federated Learning was designed to allow collaborative learning without revealing raw data as worries about machine learning privacy grew. Vertical Federated Learning (VFL) may be utilized for a distributed dataset with the same sample ID space but differs in feature space. And may be used in a wide variety of real-world contexts when parties have the same set of samples but only have partial attributes. Achieving privacy will be a result of this technique's capacity. Federated Learning enables different repositories of data to learn a shared model collaboratively and at the same time keep the privacy of each one because of the increasing awareness of large firms compromising on data security and user privacy. To accomplish federated learning, three learning ways were suggested; horizontal federated learning, vertical federated learning, and transfer federated learning. Vertical federated learning was adopted when data were spread among different parties. However, each one has different features from the others for identical objects. This paper is related to this type of federated learning. To maximize model performance while maintaining the privacy of dispersed data, we'll create a framework based on vertical federated learning and suitable techniques. [ABSTRACT FROM AUTHOR]

E-Learning has become an essential teaching approach during COVID-19 pandemic. All over the world, various internet-based learning management systems (Google classroom, Moodle, etc.) were adopted to convey knowledge and enhance learning outcomes. However, measuring learning outcomes and knowledge acquisition in E-Learning environment is a controversial issue. To this end, this paper aims to predict learning outcomes using data mining techniques. Student data are collected and analyzed to construct the prediction model. The collected data covered students from various undergraduate studies. Cross-Industry Standard Process for Data Mining is used as a research model. The obtained result shows the significant of some attributes in predicting learning outcomes. Four correlation-based attributes selection schemas are applied. The selected attributes are examined using four data mining algorithms: random forest, k-nearest neighbors, Decision Tree and neural network. The overall performance of the constructed mining models is evaluated using various performance measures: Accuracy, Precision, Recall and F1-score are calculated. Overall, an 86% accuracy is secured. [ABSTRACT FROM AUTHOR]

The performance of different Data Mining Algorithms including Classification, Clustering, Association, Prediction and others are highly related to the approaches used in Data Warehouse design and to the way the data is stored (lightly summarized, highly summarized and detailed).Detailed data is important to get detailed reports but as the amount of data is huge this represents a big challenge to the mining algorithms, on the other hand, the summarized data leads to better algorithms performance but the lack of the required knowledge may affect the overall mining process. Knowledge extraction and mining algorithms performance and complexities represent a big challenge in data analysis field, hence the work in this paper represents a proposed approach to improve the algorithms performance throughout well designed warehouse and data reduction technique. The work in this paper presents a hybrid warehouse galaxy model that stores data in three different formats including detailed, summarized and highly summarized data. The time and space complexity are the major criteria in the proposed approach. Real data was collected about schools, students and teachers from different AlNajaf AlAshraf cities, the data was preprocessed, reduced mainly through concept hierarchy and then converted into dimensions and fact tables (Warehouse Galaxy Model) which in turn are converted into multidimensional cubes. Roll up and drill down queries were highly used to get the required information. The resultant data cubes and in turn the corresponding warehouse model presented in this work showed a reasonable improvement in knowledge extraction algorithms for the data under discussion. The results of the queries showed better performance of different roll up and drill down queries compared to detailed data queries. [ABSTRACT FROM AUTHOR]

Getting knowledge from raw data has delivered beneficial information in several domains. The prevalent utilizing of social media produced extraordinary quantities of social information. Simply, social media delivers an available podium for employers for sharing information. Data Mining has ability to present applicable designs that can be useful for employers, commercial, and customers. Data of social media are strident, massive, formless, and dynamic in the natural case, so modern encounters grow. Investigation methods of data mining utilized via social networks is the purpose of the study, accepting investigation plans on the basis of criteria, and by selecting a number of papers to serve as the foundation for this article. Afterward a watchful evaluation of these papers, it has been discovered that numerous data extraction approaches were utilized with social media data to report a number of various research goals in several fields of industrial and service. Though, implementations of data mining are still raw and require more work via industry and academic world to prepare the work sufficiently. Bring this analysis to a close. Data mining is the most important rule for uncovering hidden data in large datasets, especially in social network analysis, and it demonstrates the most important social media technology. [ABSTRACT FROM AUTHOR]

The last two decades have seen a marked increase in the illegal activities on the Dark Web. Prompt evolvement and use of sophisticated protocols make it difficult for security agencies to identify and investigate these activities by conventional methods. Moreover, tracing criminals and terrorists poses a great challenge keeping in mind that cybercrimes are no less serious than real life crimes. At the same time, computer security societies and law enforcement pay a great deal of attention on detecting and monitoring illegal sites on the Dark Web. Retrieval of relevant information is not an easy task because of vastness and ever-changing nature of the Dark Web; as a result, web crawlers play a vital role in achieving this task. Thereafter, data mining techniques are applied to extract useful patterns that would help security agencies to limit and get rid of cybercrimes. The aim of this paper is to present a survey for those researchers who are interested in this topic. We started by discussing the internet layers and the properties of the Deep Web, followed by explaining the technical characters of The Onion Routing (TOR) network, and finally describing the approaches of accessing, extracting and processing Dark Web data. Understanding the Dark Web, its properties and its threats is vital for internet servers; we do hope this paper be of help in that goal. [ABSTRACT FROM AUTHOR]

Clustering is a significant data mining method that is used in a variety of disciplines. Clustering attempts to divide a big set of data into smaller groups that are more similar within the same group, but distinct from other groups, each subgroup referred to as a “cluster”. This paper introduces the concept of clustering, the most important clustering approaches, and the application of graph-based clustering utilizing one of the graph algorithms, the Minimum Spanning Tree (MST) algorithm, which groups related nodes into clusters. The method has been evaluated on five various data sets utilizing cluster validation measures (Adjusted Rand Index, v-measure_ scores), and its performance on all of these data sets has been demonstrated when compared to other algorithms. [ABSTRACT FROM AUTHOR]

Copyright of Iraqi Journal of Science is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Iraqi Journal of Science is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In e-government, the mining techniques are considered as a procedure for extracting data from the related web application to be converted into useful knowledge. In addition, there are different methods of mining that can be applied to different government data. The significant ideas behind this paper are to produce a comprehensive study amongst the previous research work in improving the speed of queries to access the database and obtaining specific predictions. The provided study compares data mining methods, database management, and types of data. Moreover, a proposed model is introduced to put these different methods together for improving the online applications. These applications produce the ability to retrieve the information, matching keywords, indexing database, and performing the prediction from a vast amount of data. [ABSTRACT FROM AUTHOR]

Copyright of Kirkuk University Journal for Scientific Studies is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Iraqi Journal of Science is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The World Wide Web has become crowded with different data, which makes data mining a cumbersome and tiring process. Therefore, the web uses various information mining strategies to extract useful information from the web. Among these strategies is web content mining tools that are used to collect, sort, classify and provide the best data that can be accessed by the user. Web content mining tools are necessary to scan the HTML documents, images, and texts, the results are provided for the search engines. It can assist search engines in providing productive results of each search in order of their relevance. This paper presents an introduction to the concepts related to data mining and web mining, web content mining techniques, and the study of different web content mining tools by creating a comparative table of these tools based on some pertinent criteria. [ABSTRACT FROM AUTHOR]

Image processing has an important and main role in several fields. It uses to understand and discover the image and its objects in efficiently and meaningful way. The understanding is a main step to extract information form image. The more realization has been established from different scientists in the field for image segmentation. The main segmentation purpose is to detect the edges information which available inside an image clearly. Edges are the important character for image and it has produced by summaries of the things. Mostly, Edge detection steps and its techniques have employed to evaluate and analysis of image characteristic. Many and several kinds of techniques for detecting the edges from any type of images. This paper has achieved the comprehensive analysis about the many edge detection techniques like Prewitt, Sobel and Laplacian of Gaussian. The comparisons are in terms PSNR (Peak signal to noise ratio), SNR (Signal to noise ratio) and Entropy. Finally, experimentally observed that Laplacian of Gaussian technique is working well and recorded better results than others techniques. [ABSTRACT FROM AUTHOR]

A rapid growth has occurred for the act of plagiarism with the aid of Internet explosive growth wherein a massive volume of information offered with effortless use and access makes plagiarism the process of taking someone else’s work (represented by ideas, or even words) and representing it as other's own work easy to be performed. For ensuring originality, detecting plagiarism has been massively necessitated in various areas so that the people who aim to plagiarize ought to offer considerable effort for introducing works centered on their research. In this paper, work has been proposed for improving the detection of textual plagiarism through proposing a model for candidate retrieval phase. The model proposed for retrieving candidates has adopted the vector space method VSM as a retrieval model and centered on representing documents as vectors consisting of average term weights and considering them as queries for retrieval instead of representing them as vectors of term weight. The detailed comparison task comes as the second phase wherein fuzzy semantic based string similarity has been applied. Experiments have been conducted using PAN-PC-10 as an evaluation dataset for evaluating the proposed system. As the problem statement in this paper is restricted to detect extrinsic plagiarism and works on English documents, experiments have been performed on the portion dedicated to extrinsic detection and on documents in English language only. For evaluating performance of the proposed model for retrieving candidates, Precision, Recall, and F-measure have been used as an evaluation metrics. The overall performance of the proposed system has been assessed through the use of the five standard PAN measures Precision, Recall, F-measure, Granularity and . The experimental results have clarified that the proposed model for retrieving candidates has a positive impact on the overall performance of the system and the system outperforms the other state-of-the-art methods. They clarified that the proposed model has detected about 80% of the plagiarism cases and about 90% of the detections were correct. The proposed model has the ability to detect literal plagiarism in addition to cases containing paraphrasing. Performance comparison has clarified that the proposed system is either comparable or outperforms the other baseline systems in terms of the five evaluation metrics. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Qadisiyah Computer Science & Mathematics is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of University of Anbar for Pure Science is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The advancements in modern day computing and architectures focus on harnessing parallelism and achieve high performance computing resulting in generation of massive amounts of data. The information produced needs to be represented and analyzed to address various challenges in technology and business domains. Radical expansion and integration of digital devices, networking, data storage and computation systems are generating more data than ever. Data sets are massive and complex, hence traditional learning methods fail to rescue the researchers and have in turn resulted in adoption of machine learning techniques to provide possible solutions to mine the information hidden in unseen data. Interestingly, deep learning finds its place in big data applications. One of major advantages of deep learning is that it is not human engineered. In this paper, we look at various machine learning algorithms that have already been applied to big data related problems and have shown promising results. We also look at deep learning as a rescue and solution to big data issues that are not efficiently addressed using traditional methods. Deep learning is finding its place in most applications where we come across critical and dominating 5Vs of big data and is expected to perform better. [ABSTRACT FROM AUTHOR]

Copyright of Diyala Journal for Pure Science is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Al-Mustansiriyah Journal of Science is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Clustering isan unsupervised data mining technique used to extract a new knowledge. It clusters a group of objects into clusters where objects in one cluster have similar fea- tures to each other and have different features from objects in other clusters. K-means algorithm creates clusters by divides the data points into clusters according to similarity criterion. The K-means algorithm select initial centroids randomly then slow convergence points to centroids. This paper suggests a method for computing the initial centroids and fast convergence by using Quantum Particle Swarm Optimization with the global searching optimization which will give algorithm more efficient, so as to get quality clustering with reducedcomplexity. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Education & Science is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In data mining and machine learning methods, it is traditionally assumed that training data, test data, and the data that will be processed in the future, should have the same feature space distribution. This is a condition that will not happen in the real world. In order to overcome this challenge, domain adaptation-based methods are used. One of the existing challenges in domain adaptation-based methods is to select the most efficient features so that they can also show the most efficiency in the destination database. In this paper, a new feature selection method based on deep reinforcement learning is proposed. In the proposed method, in order to select the best and most appropriate features, the essential policies in deep reinforcement learning are defined, and then the selection features are applied for training random forest, k-nearest neighborhood and support vector machine classifiers. The trained classifiers with the considered features are evaluated on the target database. The results are evaluated with the criteria of accuracy, sensitivity, positive and negative predictive rates in the classifiers. The achieved results show the superiority of the proposed method of feature selection when used in domain adaptation. By implementing the RF classifier on the VisDA-2018 database and the Syn2Real database, the classification accuracy in the feature selection of the proposed deep learning reinforcement has increased compared to the two-feature selection of Laplace monitoring and feature selection states. The classification sensitivity with the help of SVM classifier on the Syn2Real databases had the highest values in the feature selection state of the proposed deep learning reinforcement. The obtained number 100 is a positive predictive rate in the Syn2Real database with the help of SVM classifier and in the case of selecting the proposed feature, it indicates its superiority. The negative predictive rate in the Syn2Real database in the state of feature selection of the proposed deep reinforcement learning was 100%, which showed its superiority in comparison with 90.1% in the state of selecting the Laplace monitoring feature. Gmean in KNN classifier on the Syn2Real database has improved in the feature selection state of the proposed deep learning reinforcement in comparison to without feature selection state. [ABSTRACT FROM AUTHOR]

Nowadays, the process of ontology learning for describing heterogeneous systems is an influential phenomenon to enhance the effectiveness of such systems using Social Network representation and Analysis (SNA). This paper presents a novel scenario for constructing adaptive architecture to develop community performance for heterogeneous communities as a case study. The crawling of the semantic webs is a new approach to create a huge data repository for classifying these communities. The architecture of the proposed system involves two cascading modules in achieving the ontology data, which is represented in Resource Description Framework (RDF) format. The proposed system improves the enhancement of these environments achieving both semantic web and SNA tools. Its contribution clearly appears on the community productions and skills developments. Python 3.9.0 platform was used for data pre-processing, feature extraction and clustering via Naïve Bayesian and support vector machine. Two case studies were conducted to test the accuracy rate of the proposed system. The accuracy rate for the case studies was (90.771%) and (90.1149 %) respectively, which is considered an affective precision when it is compared with the related scenario with the same data set. [ABSTRACT FROM AUTHOR]

Heart disease, or cardiovascular illness, encompasses a wide range of disorders affecting the cardiovascular system. One of the trickiest things to do in medicine is to make predictions about cardiovascular disease. Nowadays, heart disease claims the life of almost one person every minute. Heart disease has several causes, but one of the most pressing issues is the lack of sensitive, precise methods for early identification, which makes proper management of the condition impossible. Automating the prediction process is necessary to prevent the hazards connected with cardiac disease diagnosis and to inform the patient at an early stage due to the intricacy of the condition. Data mining is extensively utilized in healthcare to forecast the occurrence of cardiovascular illness by analyzing massive and intricate medical records. To forecast cardiac problems, researchers conduct in-depth analyses of massive amounts of medical data using a wide range of data mining and machine learning algorithms. Here, we provide several heart disease characteristics and build a model using supervised learning methods like random forest and support vector machine (SVM). The Kaggle repository contains the cardiac condition dataset that is used in this research. Predicting patients' risk of heart disease is the main objective of this investigation. Confusion matrices were used for proposed system evaluation .The findings demonstrate that Random Forest achieves the highest level of accuracy, reaching 98.54 percent. [ABSTRACT FROM AUTHOR]

Copyright of Iraqi Journal of Science is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Education & Science is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Basrah Researches (Sciences) is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Data-intensive science is a critical science paradigm that interferes with all other sciences. Data mining (DM) is a powerful and useful technology with wide potential users focusing on important meaningful patterns and discovers a new knowledge from a collected dataset. Any predictive task in DM uses some attribute to classify an unknown class. Classification algorithms are a class of prominent mathematical techniques in DM. Constructing a model is the core aspect of such algorithms. However, their performance highly depends on the algorithm behavior upon manipulating data. Focusing on binarazaition as an approach for preprocessing, this paper analysis and evaluates different classification algorithms when construct a model based on accuracy in the classification task. The Mixed National Institute of Standards and Technology (MNIST) handwritten digits dataset provided by Yann LeCun has been used in evaluation. The paper focuses on machine learning approaches for handwritten digits detection. Machine learning establishes classification methods, such as K-Nearest Neighbor(KNN), Decision Tree (DT), and Neural Networks (NN). Results showed that the knowledge-based method, i.e. NN algorithm, is more accurate in determining the digits as it reduces the error rate. The implication of this evaluation is providing essential insights for computer scientists and practitioners for choosing the suitable DM technique that fit with their data. [ABSTRACT FROM AUTHOR]

E-mail is an efficient and reliable data exchange service. Spams are undesired email messages which are randomly sent in bulk usually for commercial aims. Obfuscated image spamming is one of the new tricks to bypass text-based and Optical Character Recognition (OCR)-based spam filters. Image spam detection based on image visual features has the advantage of efficiency in terms of reducing the computational cost and improving the performance. In this paper, an image spam detection schema is presented. Suitable image processing techniques were used to capture the image features that can differentiate spam images from non-spam ones. Weighted k-nearest neighbor, which is a simple, yet powerful, machine learning algorithm, was used as a classifier. The results confirm the effectiveness of the proposed schema as it is evaluated over two datasets. The first dataset is a real and benchmark dataset while the other is a real-like, modern, and more challenging dataset collected from social media and many public available image spam datasets. The obtained accuracy was 99.36% and 91% on benchmark and the proposed dataset, respectively. [ABSTRACT FROM AUTHOR]

Canola production increased significantly in Iran due to its high yield in recent years. Khuzestan province is the main centre of canola production in Iran. This paper presents a data mining study of samples of canola obtained from farms in Amirkabir Agro-Industry of Khuzestan province. Data were collected from 48 farms. The farms were chosen by random sampling method. The purpose of this study is to determine energy consumption of input and output used in canola production. And Output energy of canola farms is predicted using data mining and multi-layer perceptron neural network. This is an analytic research and its database consists of 432 records. Data required for this research was obtained during growing seasons in 2017-2018. Data analysis was done by IBM SPSS modeler 14.2. The results showed that the amount of energy consumed in canola production was 28927.43 MJ ha-1. About 40% of this was generated by fertilizers and 37% from electricity and diesel fuel. Concerning the model used in the research, it was found that variables of chemical fertilizer, fuel, electricity energy and irrigation, respectively had the highest effect on output variable (productive energy). Amount of prediction precision in neural network algorithm meaning ratio of correctly predicted records to total records was 86.5%. Also, linear correlation between actual values and predicted values was 0.84 and 0.88 respectively for training data and testing data suggesting strong correlation. Results obtained in this research can be effective for canola farmers in Amirkabir Agro-Industry in direction of evaluation and optimization of energy consumption in process of canola production and reduction of consumption of energy inputs. [ABSTRACT FROM AUTHOR]

Inn then last two decades the Content Based Image Retrieval (CBIR) considered as one of the topic of interest for the researchers. It depending one analysis of the image's visual content which can be done by extracting the color, texture and shape features. Therefore, feature extraction is one of the important steps in CBIR system for representing the image completely. Color feature is the most widely used and more reliable feature among the image visual features. This paper reviews different methods, namely Local Color Histogram, Color Correlogram, Row sum and Column sum and Colors Coherences Vectors were used to extract colors features taking in consideration the spatial information of the image. [ABSTRACT FROM AUTHOR]

In mathematics, it's very easy to find the maximum point or minimum point of a function or a set of functions, but it's difficult to find a set of function simultaneously in the real world due to the different kinds of mathematical relationships between objective functions. So the multi objective optimization algorithm has the ability to deal with a many objectives instead of one objective, because of the difficulties in the classical methods of multi objectives optimization, the evolutionary algorithm (EA) is effective to eliminate these difficulties, in order to apply the evolutionary algorithms to improve the multi-objective optimization algorithm, the multi - objective evolutionary algorithm based on decomposition is one of the algorithms that solve multi objective optimization problems. This paper aims to enhance the e-mail spam filtering by using multi - objective evolutionary algorithm for classifying the e-mail messages to spam or non-spam in high accuracy. The first step in the proposal is applying normalization. The second step is applying feature selection which is implemented to choose the best features. Finally, implement multi - objective evolutionary algorithm based on decomposition. The evaluation of the performance of model by using testing databases from the spam database. The model depended accuracy as a criterion to evaluate model performance. The experimental results showed that the proposed system provides good accuracy in the experiment 1 (91%), very good accuracy in the experiment 2 (92%) and excellent accuracy in the experience 3 (98%). [ABSTRACT FROM AUTHOR]

Copyright of Journal of the College Of Basic Education is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Data collection is presently managed by using classic relational database systems like SQL, MySQL and Oracle. In recent years, data collection has grown up, and it has become more complex than conventional Relational Database Management System (RDBMS); which are incompetent to deal with it. To handle this problem, organizations and large companies like Google, Facebook, Yahoo and others bring up with new data management technique called NoSQL database; which is designed for a large-scale data storage and analysis. In this paper, a new technique is presented and used to convert SQL to NoSQL database, and also it can migrate, process and retrieve data between them. Because of the NoSQL database (Big Data), it sometimes needs to store in an untrusted or semi-trusted third party, the proposed system allows users to protect their database by encrypting database sensitive attributes before performing conversion and migration processes. Furthermore, the proposed system gives users the ability for retrieving NoSQL data from Big Data storage just like retrieve SQL data; that means users can write a SQL query to retrieve NoSQL data. The proposed system used Apache HBase for NoSQL BigData storage and Apache Sqoop and Hive for data conversion, migration, processing and retrieving processes. The implementation and results of the proposed system are showed the ability of converting, migrating, processing and retrieving data with high efficiency and good performance. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Thi-Qar Sciences is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)