Search

Semantic approaches present an efficient, detailed and easily understandable representation of knowledge from documents. Al-Quran contains a vast amount of knowledge that needs appropriate knowledge extraction. A semantic based approach can help in designing an efficient and explainable knowledge representation model for Al-Quran. This research aims to propose a semantic-graph knowledge representation model for verses of Al-Quran based on word dependencies. These features are used in the proposed knowledge representation model allowing the semantic graph matching to improve Al-Quran search applications' accuracy. The proposed knowledge representation model is essentially a formalism for generating a semantic graph representation of Quranic verses, which can be applied for knowledge base construction for other applications such as information retrieval system. A set of rules called Semantic Dependency Triple Rules are defined to be mapped into the semantic graph representing the verse's logic. The rules translate word dependencies and other NLP metadata into a triple form that holds logical information. The proposed model has been tested with English translation of Al-Quran on a document retrieval prototype The basic system has been enhanced with anaphoric pronouns correction, which has shown improvement in retrieval performance. The results have been compared with a closely related system and evaluated on the accuracy of the document retrieval in Precision, Recall and F-score measurements. The proposed model has achieved 65%, 60% and 62.4% for the measurements, respectively. It has also improved the overall accuracy of previous system by 43.8%.

The upstream capital project oil and gas industry is considered a critical sector in Malaysia. Apart from its significant monetary contribution to the country, big data analysis is also applied to the supply chain operation. The prescriptive analysis is based on Artificial intelligence (AI), specifically Machine Learning (ML), which involves algorithms and models that enable computers to make decisions based on mathematical data relationships and patterns. This study aims to identify ML analysis in Malaysia’s upstream capital projects, which may improve business decisions via the use of statistical models and ML algorithms. Incorporating ML algorithms and statistical models will produce better business decision-making by enhancing efficiency and productivity besides fast monetisation and minimising risk and returns. Overall, with the use of mixed analysis elements, it can produce better decision support for stakeholders and company owners before making crucial business decisions.

A variety of applications have been built in recent years with the aim to extract knowledge from Al-Quran. Current knowledge representations of Al-Quran give attention primarily on conceptual ontology models that describe the semantic relations between the Quranic concepts or entities. There seems to be minimal effort towards recognizing the semantic relations between words in Quranic text, which is relatively more complex. This paper aims to present a framework for semantic knowledge representation of Al-Quran using dependency relations between words, in an attempt to boost the retrieval accuracy for Al-Quran. The semantic analysis is performed on Quranic verses according to word dependency relations using dependency parsing. Based on parsed dependencies, a set of rules are formulated to build a semantic graph of Surah Ali Imran of Al-Quran. The efficiency of the semantic representation was tested by developing a prototype question answering system. The framework was evaluated using precision and recall, First Hit Success, First Answer Reciprocal Rank and Total Reciprocal Rank by comparing the retrieved and actual answers. The results indicate that the performance of the proposed framework using word dependencies improves the semantic representation of knowledge.

The needed time to send and receive a message among two nodes in an interconnection network has a fundamental role in determining the performance of this network. Therefore, taking a short period of time to send a packet between a source and destination nodes indicates a good performance network with less congestion and latency. Besides, processing data in short-term help in providing fast solutions for many complex problems. Thus, various designs of hierarchical interconnection networks (HINs) for the massively parallel computer (MPC) systems have been presented recently; the main goal of these networks is to replace the conventional ones which showed poor performance in scaling the network size. A Shifted Completely Connected Network (SCCN) proposed as a new HIN topology. Several basic modules (BMs) interconnected hierarchically to create advanced levels networks based on this topology. The structural design and a proposed routing protocol of SCCN discussed in this paper. However, the foremost focus of this work is to evaluate the time cost-effectiveness factor (TCEF) of SCCN in different levels in order to examine the effect of expanding the size of the network on the TCEF. Therefore, the TCEF for the higher levels of SCCN from level (1) to level (3) will be assessed to examine whether SCCN is an effective network in term of time. In addition, the obtained results from each level will be compared to other networks to prove the preeminence of the proposed topology.

Usage of Industry4.0 enablers such as cloud computing, IoT and data analytics is still not common among SMEs. Many SMEs had failed in adopting digital transformations due to the conflicting values of digitalization with the company’s organizational culture. There is a gap in examining the moderating influence of digital organizational culture and its effect on cloud computing technology adoption within the organization. Thus, we aim to explore, develop, and propose the conceptual framework consisting of constructs from the technology-organization-environment (TOE) framework combined with cloud computing as a mediator and the effect of digital organizational culture as a moderator. The study outcomes should address the gap in the role of cloud computing and digital organizational culture to further enhance the SME’s performance. The research is still ongoing work, with field data will be collected using the structured survey questionnaire with managers of SMEs, including owners, senior executives or supervisors as the target responders. Then an empirical study using Structural Equation Model (SEM) will be proposed to validate the hypotheses of the conceptual framework.

Industrial Revolution 4.0 is expected to improve the way of military training system. Most of the assistant systems use English for their Human Machine Interaction (HMI) such ‘SARA’ a virtual socially aware robot assistant which exclude Malay socio-emotional aspects. This scenario opens a suggestion, to internalize socio-emotional aspects based on Malay culture, custom and beliefs to military autonomous training systems (i.e. MIN@H) that can improve the ‘collaborative’ skills between Malaysian military personnel and the systems. Therefore, to increase the wisdom of the systems, they must have feature to capture information for their human users or helping human users to learn new knowledge and ensure the interaction is comfortable and engaging. For that reason, the systems must understand Malay language and be able to interpret emotion and expression behavior according to the Malay culture and custom, furthermore, the systems able to differentiate the level of user’s understanding and build a good rapport or feeling of harmony that makes communication possible or easy between the systems and users. This concept of the systems is referred as Malay Artificial Wisdom System (AWS). There are three fundamental aspects to achieve the AWS. First, to computationally model the conversational strategies and rapport between the system and human users based-on user’s understanding and system’s articulation. Second, to computationally model, recognize and synthesize the emotion and expression behavior according to the Malay culture, custom and beliefs. Third, the AWS can do analytical reasoning and responding in relation to falsehood analysis and users’ understanding level. Knowledge discovery and inference technique as well as HMI that cater the inputs and output of the MIN@H will be developed to accomplish the AWS concept. This program could embrace military training system in Malaysia to enhance military personnel skills and experts in various areas.

Named Entity Recognition (NER) is an early stage processing of an Information Extraction, which identifies and classify entities in text. The outcomes of the task have become the foundation of building complex Information Extraction applications. With the enormous amount of information available everywhere, the area has gained lots of attention from the research community. Currently, there are two main approaches to perform the Named Entity Recognition; rule-based approach and machine learning approach. In order to improve the accuracy of the classification and performance of the recognizer, some researchers have implemented a hybrid approach, which is the combination of both approaches. Even though many research and works have been done in the Named Entity Recognition, there is still room available for improvement. This paper proposed to increase the accuracy of entities detected by implementing anaphora resolution during the preprocessing phase and a hybrid approach to classify the detected tokens during the classification phase. The hybrid approach is combined the Conditional Random Field (CRF) classifier with a gazetteer and pattern rules to perform classification. The result has shown that the application of anaphora and gazetteer has increased 46% accuracy of the detected entities for the person class.

Contextual retrieval is a critical component for efficient usage of knowledge hidden behind the data. It is also among the most important factors for user satisfaction. It essentially comprise of two equally important parts – the retrieval mechanism and the knowledge base from which the information is retrieved. Despite the importance, context aware knowledge bases have not received much attention and thereby, limiting the efficiency of precise context aware retrieval. Such knowledge bases would not only contain information that has been efficiently stored but the knowledge contained would be context based. In other words, machines would understand the knowledge and its context rather than just storing data. This would help in efficient and context aware retrieval. The current paper proposes rules and methodologies for construction of such context aware knowledge bases. A case study to demonstrate the application of the methodology and test the efficiency of the proposed methodology has also been presented. The results indicate that knowledge bases built on these principles tend to generate more efficient and better context aware retrieval results.

The knowledge behind the data is of utmost importance. It is necessary to develop meaningful, expressive and comprehensive knowledge base for every domain in order to use the knowledge. The repositories need to be designed considering natural language interactions for better performance. A knowledge base with such features seems to be non-existent for Al-Qur'an. The current work aims to develop an efficient and comprehensive knowledge base for Al-Qur'an based on principles of logic, linguistics and semantic networks, etc. The developed knowledge base is expressive, comprehensive, meaningful and efficient, establishing and maintaining semantic relations. The developed knowledge base can be used for varied purposes such as expert systems, etc. contributing to the efficiency of these systems based on its unique design.

The exponential growth of internet access and computing devices, has led to the growth of social media usage and changed the way of our lives in society. Due to the growth of social media usage such as Facebook, Twitter, Instagram, YouTube, etc., there are possibilities that users share information which may pose a threat to the national security. For example, the threats might be propagated by a certain group of terrorists. The threats can be written either in Malay or mixed with other languages; especially English and in a short form basis. The major issue is to extract the 'meaning' of the messages for further processing tasks (e.g. categorizing and identifying the insight of threats). Therefore, a semantic-based grammar approach helps to fill this 'knowledge gap' for threat analysis at the early stage. This research will focus on knowledge extraction (based-on Malay words) through semantic relations between words and their dependents.

It is critical to have a knowledge base model for efficient storage of extracted knowledge. This ensures that the knowledge is stored in a meaningful way to be used for different applications. The efficiency of the knowledge base model depends largely on the rules of construction. Knowledge represented using logico-linguistic techniques and semantic networks lack a consistent rule based knowledge model. The current paper deals with the analysis of text from the knowledge extraction, representation and semantic network phase to formulate rules which would lay foundations of a knowledge model. The developed rules seem to be promising providing a comprehensive coverage of different scenarios. The extensive coverage is an indication that the knowledge model will cater to the entire domain knowledge, thereby laying the foundations of automatic construction of efficient knowledge bases.

A Symmetric Midimew Mesh connected network (SMMN) is a hierarchical interconnection networks (HIN) that capable to interconnect vast number of nodes that could reach up to millions of nodes in the network. SMMN has multiple basic modules of 2D-mesh networks that are recursively interconnected by Midimew network to create higher-level networks. In this paper, we explain the architectural details of SMMN,we also present the a deadlock-free routing algorithm for SMMN using four virtual channels and evaluate the performance of dynamic communication of SMMN network using proposed routing algorithm under uniform traffic pattern .We also evaluate the performance of dynamic communication of TESH network using topaz simulator. It is shown that the SMMN network has high throughput and low latency, which yield higher performance of dynamic communication compare to other Hierarchical networks.

The goal of this study was to predict visual acuity (VA) and contrast sensitivity function (CSF) with tissue redness grading after pterygium surgery.A total of 67 primary pterygium participants were selected from patients who visited an ophthalmology clinic. We developed a semi-automated computer program to measure the pterygium fibrovascular redness from digital pterygium images. The final outcome of this software is a continuous scale grading of 1 (minimum redness) to 3 (maximum redness). The region of interest (ROI) was selected manually using the software. Reliability was determined by repeat grading of all 67 images, and its association with CSF and VA was examined.The mean and standard deviation of redness of the pterygium fibrovascular images was 1.88 ± 0.55. Intra-grader and inter-grader reliability estimates were high with intraclass correlation ranging from 0.97 to 0.98. The new grading was positively associated with CSF (p0.01) and VA (p0.01). The redness grading was able to predict 25% and 23% of the variance in the CSF and the VA, respectively.The new grading of pterygium fibrovascular redness can be reliably measured from digital images and showed a good correlation with CSF and VA. The redness grading can be used in addition to the existing pterygium grading.

This paper discussed the idea of the computer system capable of simulating understanding with respect to reading a text document. The research is concerned with the problem of generating sophisticated knowledge representation for the purpose of understanding the natural language. Due to that, a simplification form of logical-oriented model of knowledge representation called Pragmatic Skolem Clauses (PSC) is proposed to represent the semantic formalism for the computational linguistic. Each set of pragmatic skolem clauses containing at least one skolem constant, which shows the thematic role relationship between clauses. Semantically and pragmatically-accented approach will be discussed in this paper in the context of formal grammar and linguistic semantic.

This paper presents our work on Subject-Action-Object (SAO) extraction as one component needed on patent discovery system development for Islamic Finance and Banking. There are some processes done in order to conduct SAO extraction. They are covering retrieving patents and transforming patents into structured data. We used several patent databases such as USPTO, MyIPO, WIPO, and EPO to collect patents. In patent searching, we used keywords, which were derived from Islamic Finance and Banking phrase, book's title, of which its content is related to Islamic Finance and Banking, and all concepts on Islamic Finance and Banking ontology. Result on SAO extraction will be utilized on the next component on the system i.e. analyzing patents trend using TRIZ evolution trend model.

Hierarchical Interconnection Network (HIN) is indispensable for the practical implementation of future generation massively parallel computer systems which consists of hundred thousands nodes or even millions of nodes. Because it yields good performance with low cost due to reduction of communication links and by exploring the locality in the communication & traffic patterns. A Midimew connected Mesh Network (MMN) is an HIN comprised of numerous basic modules, where the basic modules are 2D-mesh networks and they are hierarchically interconnected using midimew network to construct the higher level networks. In this paper, we present the architecture of a MMN and evaluate the time-cost effective factor of MMN, TESH, mesh, and torus networks. It is found that the proposed MMN yields slightly high time-cost effectiveness factor with small diameter and average distance as compared to other networks. Overall, performance with respect to time-cost effectiveness factor with small diameter and average distance suggests that the proposed MMN will be a indispensable choice for the next generation massively parallel computer systems.

This paper presents our work in designing system architecture for applying Malik Bennabi's ruler on Intellectual Property (IP) of Islamic Finance and Banking. We chose journal article as one form of IP for Islamic Finance and Banking. There are several components in the architecture starting from IP retrieval, structure extraction, structure classification, structure summarization, and Knowledge-based similarity measuring. The architecture will be implemented in order to measure all journal article's content and group them into two categories namely Useful and Harmful.

Objectives: This paper describes work in constructing two models of knowledge representation in order to increase the performance of retrieving information on English Quran domain. Due to many approaches available to construct knowledge representation, this paper only focused on ontology-based and graph database-based knowledge representation. Methods: Quranic Arabic Corpus that available at http://www.corpus.quran.com is used as a source to build the knowledge representation. This paper extracted several data from it which include English token, token location, and token Part Of Speech (POS). Protege is used to construct the ontology and Neo4j is utilized in developing the graph database. Findings: This paper has presented a construction process of two models of Knowledge Representation(KR)which are ontology and graph database based KR. These models will be used in developing of an English Quran question answering system in order to discover which model exhibit the best achievement in increasing question answering system performance. Improvements/Applications: The authors hope there will be useful information gained from the question answering system experiments when using both of those models.

A Midimew connected Mesh Network (MMN) is a proposed hierarchical interconnection network in which numerous basic modules are interconnected in a hierarchical fashion to construct a massively parallel computer. Here, the basic module is the first level of the network which is connected by mesh network while higher level network is connected by a midimew network. In this study, we have evaluated a dynamic communication performance of a variety of MMN using the TOPAZ simulator using a deadlock free routing algorithm with uniform traffic patterns, whereby the dimension order routing and virtual cut-through flow control are used. It is found that the saturation throughput of the Virtual MMN (VMMN) is higher than that of Horizontal MMN (HMMN), Symmetric MMN (SMMN), and Tori connected mESH network (TESH).

This paper describes a work in constructing two models of knowledge representation (KR) in aiming to do evaluation of their achievement in contributing to increase performance of retrieving information on English Quran domain. Due to many approaches available to construct a KR in providing data for information retrieval process, there is a need to find out in what model the KR could provide a valuable contribution for retrieving information. We focused on ontology-based KR and graph database-based KR. We use Quranic Arabic corpus that available at http://www.corpus.quran.com as a source to build the KR. We extracted several data from it i.e. English token, token location, and token Part of Speech (POS). Protégé is used to construct the ontology and Neo4j is utilized in developing the graph database. Both KR models will be equipped in developing of an English Quran Question Answering system in order to evaluate their benefit.

The knowledge behind the gigantic pool of data remains largely unextracted. Techniques such as ontology design, RDF representations, hpernym extraction, etc. have been used to represent the knowledge. However, the area of logic (FOPL) and linguistics (Semantics) has not been explored in depth for this purpose. Search engines suffer in extraction of specific answers to queries because of the absence of structured domain knowledge. The current paper deals with the design of formalism to extract and represent knowledge from the data in a consistent format. The application of logic and linguistics combined greatly eases and increases the precision of knowledge translation from natural language. The results clearly indicate the effectiveness of the knowledge extraction and representation methodology developed providing intelligence to machines for efficient analysis of data. The methodology helps machines to retrieve precise results in an efficient manner.

Ontology information extraction has gain popularity due to the increasing amount of ontologies developed over the years. World Wide Web Consortium (W3C) has introduced SPARQL query language to extract information. However SPARQL query language follow a specific pattern in order to find the triple through subgraph matching. The keywords used in the SPARQL query have to be exactly same as the existing keywords in the RDF data in-order to extract the required information. The paper introduced a method to ease the job of the user by generating SPARQL query from the query entered by the user. The method uses the object property list generated from the ontology and word's synonym to aid in SPARQL query generation. The result has shown that the proposed method clearly eases the need of the user to learn SPARQL syntax.

Interconnection network topology is a pivotal factor in the performance and reliability of the parallel computer system ranging from multiprocessor to massively parallel computers (MPC). Hierarchical network topology yields better performance with low cost by exploring the locality in the communication and traffic patterns. A Midimew connected Mesh Network (MMN) is a hierarchical interconnection network comprised of numerous basic modules, where the basic module and higher level network of hierarchy is a 2D-mesh and a midimew networks, respectively. In this paper, we present the architecture of MMN and evaluate the packing density and message traffic density of MMN, TESH, mesh, and torus networks. It is revealed that the proposed MMN yields high packing density and low message traffic density which will results efficient VLSI realization and high communication performance of the MMN. Overall, performance with respect to packing and densities reveals that the MMN will be a promising choice for next generation MPC systems.

Architecture of the interconnection network has a great influence on the speed of the multi-core processor design. The main aims of any new architecture are to avoid the latency, and to decrease the cost. In this paper, we proposed new hierarchical interconnection network, in order to build fast parallel computing system. We have evaluated the static network performance of the proposed network such as: node degree, diameter, cost, arc connectivity, bisection width, and wiring complexity. The proposed topology achieved low cost and small diameter comparing to 2D-mesh, and 2D-torus topologies. As well as, it gives good results in the other static parameters. Hence, the proposed network is good solution to improve the performance, and decrease the cost of the interconnection networks for the future generation parallel computing systems.

Minimal DIstance MEsh with Wrap-around links (Midimew) connected Mesh Network (MMN) is a hierarchical interconnection network consists of several Basic Modules (BM), where the BM is a 2D-mesh network and the higher level network is a midimew network. In this paper, we present the architecture of MMN and evaluate the number of long wires, length of a long wire, and the total length for the long wire of MMN, TESH, and torus networks. It is shown that the proposed MMN possesses simple structure and moderate wire length. The long wire length of MMN is slightly higher than TESH network and far lower than that of 2D torus network. Overall performance suggests that, MMN is a good choice for future generation massively parallel computers.

Midimew-Connected Gaussian Network (MGN) is a hierarchical interconnection network which is able to interconnect millions of nodes in the network to achieve high performance and cost-effective design for massively parallel computing system (MPC). MGN consists of multiple basic modules with Wrap-around links (MIDIMEW) to form the higher level network, where the basic module of MGN is dense Gaussian network with additional links in its edge nodes. This paper focuses on the architecture design of MGN, and computes the performance parameters such as degree, arc connectivity, bisection width and wiring complexity. The results show that the MGN design has better performance than other network topologies such as hierarchical Gaussian network (HGN).

In this paper, we have proposed a new hierarchical interconnection network called Tori-connected Flattened Butterfly Network (TFBN). It is a hierarchical interconnection network which is able to interconnect millions of nodes in the network to achieve high performance and cost-effective design for massively parallel computing system. TFBN consists of multiple basic modules of flattened butterfly network whereby the basic modules are connected using 2D-torus network. This paper focuses on the architecture of the TFBN and the evaluation of its static network performance such as degree, diameter, cost, average distance, arc connectivity, bisection width and wiring complexity. The comparison of performance shows better performance in terms of distance parameters as well as other parameters.

Morphological analysis is used to study the internal structure words by reducing the number of vocabularies used while retaining the semantic meaning of the knowledge in NLP system. Most of the existing algorithms are focusing on stemmatization instead of lemmatization process. Even with technology advancement, yet none of the available lemmatization algorithms able to produce 100 % accurate result. The base words produced by the current algorithm might be unusable as it alters the overall meaning it tried to represent, which will directly affect the outcome of NLP systems. This paper proposed a new method to handle lemmatization process during the morphological analysis. The method consists three layers of lemmatization process, which incorporate the used of Stanford parser API, WordNet database and adaptive learning technique. The lemmatized words yields from the proposed method are more accurate, thus it will improve the semantic knowledge represented and stored in the knowledge base.

In this paper, we have evaluated the dynamic communication performance of the mesh and torus networks using a open source TOPAZ simulator using virtual cut through switching under uniform traffic pattern. It is found that the torus network yields low latency and high throughput than that of mesh network. Therefore, The dynamic communication performance of the torus network is better than that of the mesh network. The well known phenomenon is justified using a new open source simulator, TOPAZ simulator.

In this era of technology and ICT learners and tutors are moving towards self-learning and self-set goals. Personal Learning Environments (PLE) are systems that enable learners to manage their own learning process for attaining a specific goal. PLEs interconnect and integrate both formal and informal learning with self-regulated learning in tertiary education. Most of the PLEs are adopted at universities for learners to collaborate and share their ideas and content using different tools, communities and services. In this paper, we have created the architecture for a Personal Learning Environment specifically for the Self-help Maqam-based Search System built upon the seven maqams outlined in Al-Ghazali's Minhajul Abidin. This self-help system assesses a person's current state (maqam) of spirituality with an opportunity to learn ways of improving one's spiritual state as defined in Minhajul Abidin. Thus, we developed a pedagogical framework by combining self-regulated learning and metacognitive knowledge first, so that the framework could be used to map the Personal Learning Environment (PLE) into the Self-help Maqam-based Search System mentioned above.

World Wide Web provides vast of resources to the public. Currently, many researches have been done on resources sharing among users through implementation of ontologies. Knowledge in an ontology are represented in the form of triple(s-p-o), where concepts are brought together by a relation. In a situation where there is a need to represent a resource which exist without IRI, blank node can be implemented in placed of the resource. Increase number of blank nodes implemented will increase the complexity of ontology structure. Since it is impossible to avoid blank nodes implementation in the ontology, increase used of it might lead to the intractable of data during the information retrieval. This paper presents a new clause-based structure that able to handle N-ary, container, collection and reified knowledge issues brought by the blank node application. The result shows that the structure able to store complicated knowledge without the need to implement blank node.