Computer Science, Information Technology and Telecommunications
Permanent URI for this collection
Browse
Recent Submissions
Now showing 1 - 5 of 127
- ItemPrediction of fracture dip using artificial neural networks(Universiti Teknologi Malaysia, 2017) Alizadeh, MostafaFracture characterization and fracture dip prediction can provide the desirable information about the fractured reservoirs. Fractured reservoirs are complicated and recent technology sometimes takes time and cost to provide all the desired information about these types of reservoirs. Core recovery has hardly been well in a highly fractured zone, hence, fracture dip measured from core sample is often not specific. Data prediction technology using Artificial Neural Networks (ANNs) can be very useful in these cases. The data related to undrilled depth can be predicted in order to achieve a better drilling operation, or maybe sometimes a group of data is missed then the missed data can be predicted using the other data. Consequently, this study was conducted to introduce the application of ANNs for fracture dip data prediction in fracture characterization technology. ANNs are among the best available tools to generate linear and nonlinear models and they are computational devices consisting of groups of highly interconnected processing elements called neurons, inspired by the scientists' interpretation of the architecture and functioning of the human brain. A feed forward Back Propagation Neural Network was run to predict the fractures dip angle for the third well using the image logs data of other two wells nearby. The predicted fracture dip data was compared with the fracture dip data from image logs of the third well to verify the usefulness of the ANNs. According to the obtained results, it is concluded that the ANN can be used successfully for modeling fracture dip data of the three studied wells. High correlation coefficients and low prediction errors obtained confirm the good predictive ability of ANN model, which the correlation coefficients of training and test sets for the ANN model were 0.95 and 0.91, respectively. Significantly, a non-linear approach based on ANNs allows to improve the performance of the fracture characterization technology
- ItemMagnitude-based streamlines seed point selection for unsteady flow visualization(Universiti Teknologi Malaysia, 2020) Yusoff, Yusman AzimiFlow visualization is a method utilized to obtain information from flow data sets. Proper blood flow visualization can assist surgeons in treating the patients. However, the main problem in visualizing the blood flow inside the aorta is the unsteady blood flow rate. Thus, an unsteady flow visualization method is required to show the blood flow clearly. Unfortunately, streamlines cannot be used by time-dependent flow visualization. This research aims to propose an improvement for the current streamline visualization technique and appearance by implementing an improved streamline generation method based on structured grid vector data to visualize the unsteady flow. The research methodology follows a comparative study method with the Evenly-Spaced Seed Point placement (ESSP) method as the benchmark. Magnitude-Based Seed Point placement (MBSP) and selective streamlines enhancement are introduced to produce longer, uniform, and clutter-free streamlines output. A total of 20 visualization results are produced with different streamlines separation distance. Results are then evaluated by comparing streamlines count and uniformity score. Subsequently, survey and expert reviews are carried out to strengthen the analysis. Survey questions are distributed to respondents that have data visualization knowledge background in order to get feedback related to streamlines uniformity and enhancement. In addition, experts review is conducted to get feedback based on current researches and techniques utilized in the related fields. Results indicate that streamlines count for MBSP are higher, but the differences are neglectable. Uniformity analysis shows good performance; with 80% of the MBSP results have better uniformity. Survey responses show 65% of respondents agreed MBSP results have better uniformity compared to ESSP. Majority of the respondents (92%) agreed that selective streamlines is a better approach. Experts review highlights that MBSP can distribute streamlines better in 3-dimension space compared to ESSP. Two significant findings are identified in this research: magnitude is proven to be an important input to locate seed points; and selective streamlines enhancement is a more effective approach as compared to global streamlines enhancement.
- ItemComputer based assessment acceptance model for secondary school students in Saudi Arabia(Universiti Teknologi Malaysia, 2020) Hakami, Yahya Abduh A.Computer-based assessment (CBA) has significantly remodelled educational evaluation processes and allowed teachers to better manage growing number of students especially in secondary schools in Saudi Arabia. However, secondary school students are showing resistance to accept CBA systems, and the factors causing this resistance to CBA systems have remained matters of speculation. Using a modified empirically validated model, the present study systematically established major determinants of this resistance by drawing on the well-known Computer-Based Assessment Acceptance Model (CBAAM). The CBAAM model is an efficient model but fails to consider some other factors that will maj orly affect the acceptance and use of CBA systems. The researcher carried out a systematic literature review for the period of 2007-2018, followed by a field assessment from 10 secondary schools in Saudi Arabia, where three major factors (computer attitude, computer anxiety and computer literacy) affecting CBA system acceptance were extracted from the researcher’s interaction with the students. Drawing from the field assessment, the existing CBAAM model is extended resulting in a comprehensive model with 22 hypotheses. Thereafter, a questionnaire was developed and the content is validated using 15 experts comprising of 9 academics and 6 practitioners. The model was evaluated with 565 responses which comprises of 274 males and 289 females. The Partial Least Squares Structural Equation Modelling (PLS-SEM) technique was used in the evaluation. The result showed that 17 out of the 22 hypotheses were found to be significant and explained 74% of the variance. The most important factors from the significant relationships are ‘perceived usefulness’, ‘perceived playfulness’, ‘content’ and ‘ computer attitude’ which were identified using the Importance-Performance Map Analysis (IPMA). Furthermore, results confirmed that secondary school student’s ‘behavioural intention’ towards CBA acceptance is directly influenced by ‘computer anxiety’, ‘content’, ‘perceived playfulness’ and ‘perceived usefulness’. While, ‘facilitating conditions’, ‘goal expectancy’, ‘computer attitude’ and ‘perceived ease of use’ showed indirect influence. This study’s results can effectively guide educationists and decision makers to better manage CBA resistance and improve its acceptance by secondary school students in Saudi Arabia.
- ItemEnhanced edge detection and restoration methods for stroke width transform algorithm(Universiti Teknologi Malaysia, 2018) Wong, Lih FongText localisation in images has gained widespread interests. A notable work, which is the Stroke Width Transform (SWT) has been attracting much interests due to its simplicity and efficiency. However, the problems of imperfect edge map and stroke-liked objects have limited the SWT performance. Imperfect edge map can affect text localisation ability while stroke-liked objects will cause faulty judgement to real text. This research attempted to solve the problems by enhancing the localisation capability in three different phases in the SWT. First, an Edge Restoration (ER) algorithm for restoring broken edges based on the characteristic of the SWT for better edge map production was introduced. Next, to reduce SWT dependency on image colour based on the edge map inherited from the previous stage, Stroke Width Map (SWM) generation algorithm was developed. Finally, a Text Filtering (TF) algorithm distinguishing stroke-liked objects in the image based on the features obtained from the previous stages was developed. Two experiments were conducted to evaluate the performance of the proposed algorithms. The first experiment evaluated the ER algorithm on the completeness of the generated edge map whereas the second experiment evaluated the text localisation performance of SWT after implementing SWM generation and TF algorithms. Experiment results showed that all algorithms have successfully improve the localisation performance of SWT. Firstly, the ER algorithm has the ability to recover broken edge structure and identify noise in the edge map. Secondly, the SWM generation algorithm generated a more accurate SWM with less interference from text colour and excess edges. Lastly, the TF algorithm distinguished between real text and the stroke-liked non-text objects. These results indicate that the ER, SWM generation and TF algorithms have overcome the imperfect edge map and stroke-liked objects problems, and improve the localisation capability in SWT.
- ItemEnhanced priority-based adaptive energy-aware mechanisms for wireless sensor networks(Universiti Teknologi Malaysia, 2021) Uzougbo, Onwuegbuzie InnocentWireless Sensor Networks (WSN) continues to find its use in our lives. However, research has shown that it has barely attained an optimal performance, particularly in the aspects of data heterogeneity, data prioritization, data routing, and energy efficiency, all of which affects its operational lifetime. The IEEE 802.15.4 protocol standard, which manages data forwarding across the Data Link Layer (DLL) does not address the impact of heterogeneous data and node Battery-Level (BL) which is an indicator for node battery life. Likewise, mechanisms proposed in the literature – TCP-CSMA/CA, QWL-RPL and SSRA have not proffered optimal solution as they encourage excessive computational overhead which results in shortened operational lifetime. These problems are inherited on the Network Layer (NL) where data routing is implemented. Mitigating these challenges, this research presents an Enhanced Priority-based Adaptive Energy-Aware Mechanisms (EPAEAM) for Wireless Sensor Networks. The first mechanism is the Optimized Backoff Mechanism for Prioritized Data (OBMPD) in Wireless Sensor Networks. This mechanism proposed the Class of Service Traffic Priority-based Medium Access Control (CSTP-MAC). The CSTP-MAC is implemented on the DLL. In this mechanism, unique backoff period expressions compute backoff periods according to the class and priority of the heterogeneous data. This approach improved network performances which enhanced network lifetime. The second mechanism is the Shortest Path Priority-Based Objective Function (SPPB-OF) for Wireless Sensor Networks. SPPB-OF is implemented across the NL. SPPB-OF implements a unique shortest path computation algorithm to generate energy-efficient shortest path between the source and destination nodes. The third mechanism is the Cross-Layer Energy-Efficient Priority-based Data Path (CL-EEPDP) for Wireless Sensor Networks. CL-EEPDP is implemented across the DLL and NL with considerations for node battery-level. A unique mathematical expression, Node Battery-Level Estimator (NBLE) is used to estimate the BL of neighbouring nodes. The knowledge of the BL together with the priority of data are used to decide an energy-efficient next-hop node. Benchmarking the EPAEAM with related mechanisms - TCP-CSMA/CA, QWL-RPL and SSRA, results show that EPAEAM achieved improved network performance with a packet delivery ratio (PDR) of 95.4%, and power-saving of 90.4%. In conclusion, the EPAEAM mechanism proved to be a viable energy-efficient solution for a multi-hop heterogeneous data WSN deployment with support for extended operational lifetime. The limitations and scope of these mechanisms are that their application is restricted to the data-link and network layers, moreover, only two classes of data are considered, that is; High Priority Data (HPD) and Low Priority Data (LPD).