A weighted-profiling using an ontology base for semantic-based search
Authors : Hikmat A. M. Abdeljaber
Abstract : The information on the Web increases tremendously. A number of search engines have been developed for searching Web information and retrieving relevant documents that satisfy the inquirers needs. Search engines provide inquirers irrelevant documents among search results, since the search is text-based rather than semantic-based. Information retrieval research area has presented a number of approaches and methodologies such as profiling, feedback, query modification, human-computer interaction, etc for improving search results. Moreover, information retrieval has employed artificial intelligence techniques and strategies such as machine learning heuristics, tuning mechanisms, user and system vocabularies, logical theory, etc for capturing user's preferences and using them for guiding the search based on the semantic analysis rather than syntactic analysis. Although a valuable improvement has been recorded on search results, the survey has shown that still search engines users are not really satisfied with their search results. Using ontologies for semantic-based searching is likely the key solution. Adopting profiling approach and using ontology base characteristics, this work proposes a strategy for finding the exact meaning of the query terms in order to retrieve relevant information according to user needs. The evaluation of conducted experiments has shown the effectiveness of the suggested methodology and conclusion is presented.
Keywords :
Visit
A bivalent-profiling using an ontology base for semantic-based search
Authors : Hikmat A. M. Abdeljaber
Abstract : Keeping track of user preferences in user profile may help search for retrieving relevant information. Nevertheless, users are still not satisfied with search results that match their interests. Semantic Web provides a meaning to Web content which plays a central role for knowledge management in user profiling, hence enables agents to search, find, extract, share and integrate information more easily. Using ontologies for semantic-based searching is likely the key solution. Adopting a bivalent-profiling approach and using ontology base characteristics, we propose a strategy to find the exact meaning of the query terms that can be exploited to expand the query in order to present customized information for individual users. This research studies the Semantic Web approach to represent knowledge, specifically in user preferences, and its consequences in changing the functionalities of the search agent. Additionally, an approach to adapt the user profile based on reasoning from the ontology base is introduced. The main contribution of this work is profiling, since the focus is on a strategy adopting bivalent-profile using an ontology base for semantic-based search. Finally, evaluation and conclusion are highlighted.
Keywords :
Visit
Program Outcomes Assessment Method for Multi-Academic Accreditation Bodies: Computer Science Program as a Case Study.
Authors : Hikmat A. M. Abdeljaber, Sultan Ahmad
Abstract : In educational community, assessment process focuses on learning, teaching and outcomes. It provides information for improving learning and teaching. Therefore, a well-established assessment process plays a vital role for improving program outcomes which, in turn, results in fulfilling program educational objectives. However, such a process entails setting well-defined courses learning objectives, program outcomes, and program educational objectives. In addition, an effective assessment method is needed for measuring the extent that program outcomes meet academic accreditation body criteria. This measurement is performed by mapping courses learning objectives with program educational objectives passing through program outcomes. Such mapping for just one academic accreditation body is a straightforward process and involves no complications. However, a coherent assessment method is required for multi academic accreditation bodies. The approach of mapping program outcomes across criteria of multi academic accreditation bodies is likely a promising key for addressing this issue. The proposed assessment method along with the assignments and practices used for evaluating students’ performance such as quizzes and exams, and the associated action plans and recommendations for improvements are crucial steps for the overall assessment process. Findings based on the results of samples taken from a number of students for some courses of computer science program show the flexibility and effectiveness of the proposed assessment method.
Keywords : accreditation, assessment method, computer science, course learning objectives, program outcomes.
Visit
Profile-Based Semantic Method using Heuristics for Web Search Personalization
Authors : Hikmat A. M. Abdeljaber
Abstract : User profiles play a critical role in personalizing user search. It assists search systems in retrieving relevant information that is searched on the web considering the user needs. Researchers presented a vast number of profile-based approaches that aims to improve the effectiveness of information retrieval. However, these approaches are syntactic-based which fail to achieve the user satisfaction. By the means that the search results do not meet user preferences, due to the fact that the search is keyword-based rather than semantic-based. Exploiting user profiles with the application of semantic web technology into personalization might produce a step forward in future retrieval systems. By adopting profiling approach and using ontology base characteristics, a semantic-based method using heuristics and KNN algorithm is proposed. It engages searching ontology base domains horizontally and vertically to discover and extract the closest concept to the meaning of the query keyword. The extracted concept is used to expand the user query to personalize the search result and present the customized information for individuals
Keywords : "Semantic search method; user profile; heuristics; web search personalization; information retrieval"
Visit
Effect of Stemming on Text Similarity for Arabic Language at Sentence Level
Authors : Hikmat A. M. Abdeljaber, Mohammad O. Alhawarat, Anwer Hilal
Abstract : Semantic Text Similarity (STS) has several and important applications in the field of Natural Language Processing (NLP). The Aim of this study is to investigate the effect of stemming on text similarity for Arabic language at sentence level. Several Arabic light and heavy stemmers as well as lemmatization algorithms are used in this study, with a total of 10 algorithms. Standard training and testing data sets are used from SemEval-2017 international workshop for Task 1, Track 1 Arabic (ar–ar). Different features are selected to study the effect of stemming on text similarity based on different similarity measures. Traditional machine learning algorithms are used such as Support Vector Machines (SVM), Stochastic Gradient Descent (SGD) and Naïve Bayesian (NB). Compared to the original text, using the stemmed and lemmatized documents in experiments achieve enhanced Pearson correlation results. The best results attained when using Arabic light Stemmer (ARLSTem) and Farasa light stemmers, Farasa and Qalsadi Lemmatizers and Tashaphyne heavy stemmer. The best enhancement was about 7.34% in Pearson correlation. In general, stemming considerably improves the performance of sentence text similarly for Arabic language. However, some stemmers make results worse than those for original text; they are Khoja heavy stemmer and AlKhalil light stemmer
Keywords : Semantic text similarity, Natural language processing, Stemming, Lemmatization, Machine learning, Word embedding, TF-IDF
Visit
Automatic Arabic Short Answers Scoring using Longest Common Subsequence and Arabic WordNet
Authors : Hikmat A. M. Abdeljaber
Abstract : The manual process of scoring short answers of Arabic essay questions is exhaustive, susceptible to error and consumes instructor’s time and resources. This paper explores longest common subsequence (LCS) algorithm as a string-based text similarity measure for effectively scoring short answers of Arabic essay questions. To achieve this effectiveness, the longest common subsequence is modified by developing weight-based measurement techniques and implemented along with using Arabic WordNet for scoring Arabic short answers. The experiments conducted on a dataset of 330 students’ answers reported Root Mean Square Error (RMSE) value of 0.81 and Pearson correlation r value of 0.94. Findings based on experiments have shown improvements in the accuracy of performance of the proposed approach compared to similar studies. Moreover, the statistical analysis has shown that the proposed method scores students’ answers similar to that of human estimator
Keywords : Semantics, Syntactics, Text categorization, Standards, Correlation, Analytical models, Weight measurement
Visit
Development of a Hybrid Algorithm for efficient Task Scheduling in Cloud Computing environment using Artificial Intelligence
Authors : Hikmat A. M. Abdeljaber, Mohammad Yousuf Uddin, Tariq Ahamed Ahanger
Abstract : Cloud computing is developing as a platform for next generation systems where users can pay as they use facilities of cloud computing like any other utilities. Cloud environment involves a set of virtual machines, which share the same computation facility and storage. Due to rapid rise in demand for cloud computing services several algorithms are being developed and experimented by the researchers in order to enhance the task scheduling process of the machines thereby offering optimal solution to the users by which the users can process the maximum number of tasks through minimal utilization of the resources. Task scheduling denotes a set of policies to regulate the task processed by a system. Virtual machine scheduling is essential for effective operations in distributed environment. The aim of this paper is to achieve efficient task scheduling of virtual machines, this study proposes a hybrid algorithm through integrating two prominent heuristic algorithms namely the BAT Algorithm and the Ant Colony Optimization (ACO) algorithm in order to optimize the virtual machine scheduling process. The performance evaluation of the three algorithms (BAT, ACO and Hybrid) reveal that the hybrid algorithm performs better when compared with that of the other two algorithms
Keywords : Cloud Computing, virtual machines, Task Scheduling, Ant Colony Optimizationalgorithm, Bat Algorithm, Hybrid algorithm
Visit
A post COVID Machine Learning approach in Teaching and Learning methodology to alleviate drawbacks of the e-whiteboards
Authors : Hikmat A. M. Abdeljaber, Sudan Jha, A A Hamad, Malik Bader Alazzam
Abstract : Deep learning has paved the way for critical and revolutionary applications in almost every field of life in general. Ranging from engineering to healthcare, machine learning and deep learning has left its mark as the state-of-the-art technology application which holds the epitome of a reasonable high benchmarked solution. Incorporating neural network architectures into applications has become a common part of any software development process. In this paper, we perform a comparative analysis on the different transfer learning approaches in the domain of hand-written digit recognition. We use two performance measures, loss and accuracy. We later visualize the different results for the training and validation datasets and reach to a unison conclusion. This paper aims to target the drawbacks of the electronic whiteboard with simultaneous focus on the suitable model selection procedure for the digit recognition problem.
Keywords : Learning; Transfer Learning; Deep Learning; Machine Learning; Electronic Whiteboard
Visit
A Novel AI-Based Stock Market Prediction Using Machine Learning Algorithm
Authors : Hikmat A. M. Abdeljaber, Sultan Ahmad, Iyyappan. M, Afroj Alam, Muhammad Yaseen, Sudan Jha
Abstract : The time series forecasting system can be used for investments in a safe environment with minimized chances of loss. *e Holt–Winters algorithm followed various procedures and observed the multiple factors applied to the neural network. *e final module helps filter the system to predict the various factors and provides a rating for the system. *is research work uses real-time dataset of fifteen stocks as input into the system and, based on the data, predicts or forecasts future stock prices of different companies belonging to different sectors. *e dataset includes approximately fifteen companies from different sectors and forecasts their results based on which the user can decide whether to invest in the particular company or not; the forecasting will give an accurate result for the customer investments
Keywords :
Visit
Issues of Clinical Identity Verification for Healthcare Applications over Mobile Terminal Platform
Authors : Hikmat A. M. Abdeljaber, Sultan Ahmad, Jabeen Nazeer, Mohammed Yousuf Uddin, Velmurugan Lingamuthu, Amandeep Kaur
Abstract : According to recent research, attacks on USIM cards are on the rise. In a 5G setting, attackers can also employ counterfeit USIM cards to circumvent the identity authentication of specified standard applications and steal user information. Under the assumption that the USIM can be replicated, the identity authentication process of common mobile platform applications is investigated. The identity authentication tree is generated by examining the application behavior of user login, password reset, and sensitive operations. We tested 58 typical applications in 7 categories, including social communication and personal health. We found that 29 of them only needed the SMS verification code received by the USIM card to pass the authentication. In response to this problem, it is recommended to enable two-step verification and use USIM anti-counterfeiting methods to complete the verification
Keywords :
Visit
An Integration of IoT, IoC, and IoE towards Building a Green Society
Authors : Ahmad, S., Sudan Jha, Abdeljaber, H. A., Imam Rahmani M. K., Maqbool Waris M., Singh A. and Yaseen M.
Abstract : Energy waste altogether adds to expanded expenses in the car fabricating industry, which is liable to energy use limitations and tax assessment from national and global strategy creators and confinements and charges from national energy suppliers. This checking is essential for energy sparing since it empowers organizations to roll out operational improvements to diminish energy utilization and expenses. The primary test to energy observation is the need to incorporate assembling and energy checking and control gadgets that help diverse correspondence conventions and are generally dispersed over a wide region. One of the most significant challenges in the advancement of the Internet of Things (IoT) has been the powering of billions of connected devices. Evaluation of digital services considering an energy impression of the Internet normally requires models of the energy intensity of the Internet. A typical way to deal with the display of the energy intensity is to consolidate assessments of market studies of introduced gadgets on a national or worldwide scale and their related power utilization with the aggregate information volume transported at a similar scale. Energy sources are a fundamental part of society development, and a steady power supply is essential for today’s progress. End-use energy is transferred to various consumers via power transmission and circulation networks after being transformed to optional energy as electricity by various power facilities. The power grid serves as the physical stage for both wide-area electric power sharing and display exchanges, and it is at the heart of auxiliary energy sources. In this manner, it attempts to connect the part of a center point between essential energy and end-use energy. With the bidirectional power stream given by the Energy Internet, different techniques are elevated to enhance and increase the energy usage between Energy Internet and Main-Grid. Energy proficiency and, in addition, quick information transmission are fundamental to green correspondences-based applications for IoT. Here, we are trying to provide a state-of-the-art survey over various Internet of Energy techniques along with IoT.
Keywords :
Visit
XAI-Based Reinforcement Learning Approach for Text Summarization of Social IoT-Based Content
Authors : Abdeljaber, H. A., Ahmad, S., Alharbi A., and Kumar S.
Abstract : The purpose of automatic text summarising technology is to condense a given text while properly portraying the main information in the original text in a summary. To present generative text summarising approaches, on the other hand, restructure the original language and introduce new words when constructing summary sentences, which can easily lead to incoherence and poor readability. This research proposes a XAI (explainable artificial intelligence)-based Reinforcement Learning-based Text Summarization of Social IoT-Based Content using Reinforcement Learning. Furthermore, standard supervised training based on labelled data to improve the coherence of summary sentences has substantial data costs, which restricts practical applications. In order to do this, a ground-truth-dependent text summarization (generation) model (XAI-RL) is presented for coherence augmentation. On the one hand, based on the encoding result of the original text, a sentence extraction identifier is generated, and the screening process of the vital information of the original text is described. Following the establishment of the overall benefits of the two types of abstract writings, the self-judgment approach gradient assists the model in learning crucial sentence selection and decoding the selected key phrases, resulting in a summary text with high sentence coherence and good content quality. Experiments show that the proposed model's summary content index surpasses text summarising ways overall, even when there is no pre-annotated summary ground-truth; information redundancy, lexical originality, and abstract perplexity also outperform the current methods.
Keywords :
Visit
Effective Return Rate Prediction of Blockchain Financial Products Using Machine Learning
Authors : K. Kalyani1, Velmurugan Subbiah Parvathy2, Hikmat A. M. Abdeljaber3, T. Satyanarayana Murthy4, Srijana Acharya5, Gyanendra Prasad Joshi6, Sung Won Kim7,*
Abstract : In recent times, financial globalization has drastically increased in different ways to improve the quality of services with advanced resources. The successful applications of bitcoin Blockchain (BC) techniques enable the stockholders to worry about the return and risk of financial products. The stockholders focused on the prediction of return rate and risk rate of financial products. Therefore, an automatic return rate bitcoin prediction model becomes essential for BC financial products. The newly designed machine learning (ML) and deep learning (DL) approaches pave the way for return rate predictive method. This study introduces a novel Jellyfish search optimization based extreme learning machine with autoencoder (JSO-ELMAE) for return rate prediction of BC financial products. The presented JSO-ELMAE model designs a new ELMAE model for predicting the return rate of financial products. Besides, the JSO algorithm is exploited to tune the parameters related to the ELMAE model which in turn boosts the classification results. The application of JSO technique assists in optimal parameter adjustment of the ELMAE model to predict the bitcoin return rates. The experimental validation of the JSO-ELMAE model was executed and the outcomes are inspected in many aspects. The experimental values demonstrated the enhanced performance of the JSO-ELMAE model over recent state of art approaches with minimal RMSE of 0.1562.
Keywords : Financial products; blockchain; return rate; prediction model; machine learning; parameter optimization
Visit