Thesis (M. Phil.)--University of Hong Kong, 2002. / Includes bibliographical references (leaves 107-109).

Thesis (M.S.)--Oregon State University, 2010. / Printout. Includes bibliographical references (leaves 62-65). Also available on the World Wide Web.

Thesis (M.S.)--West Virginia University, 2004. / Title from document title page. Document formatted into pages; contains viii, 106 p. : ill. (some col.). Includes abstract. Includes bibliographical references (p. 105-106).

No description available.

In recent years, learning technology has become a very important addition to the toolkit of instructors at any level of education and training. Not only offered as a substitute in distance education, but often complementing traditional delivery methods, e-learning is considered an important component of modern pedagogy. Particularly in the last decade, learning technology has seen a very rapid growth following the large-scale development and deployment of e-learning financed by both Governments and commercial enterprises. These turned e-learning into one of the most profitable sectors of the new century, especially in recession times when education and retraining have become even more important and a need to maximise resources is forced by the need for savings. Interestingly, however, evaluation of e-learning has been primarily based on the consideration of users’ satisfaction and usability metrics (i.e. system engineering perspective) or on the outcomes of learning (i.e. gains in grades/task performance). Both of these are too narrow to provide a reliable effect of the real impact of learning technology on the learning processes and lead to inconsistent findings. The key purpose of this thesis is to propose a novel, data-driven framework and methodology to understand the effect of e-learning by evaluating the utility and effectiveness of e-learning systems in the context of higher education, and specifically, in the teaching of psychology courses. The concept of learning is limited to its relevance for students’ learning in courses taught using a mixture of traditional methods and online tools tailored to enhance teaching. The scope of elearning is intended in a blended method of delivery of teaching. A large sample of over 2000 students taking psychology courses in year 1 and year 2 was considered over a span of 5 five years, also providing the scope for the analysis of some longitudinal sub-samples. The analysis is accomplished using a psychologically grounded approach to evaluation, partially informed by a cognitive/ behavioural perspective (online usage) and a differential perspective (measures of cognitive and learning styles). Relations between behaviours, styles and academic performance are also considered, giving an insight and a direct comparison with existing literature. The methodology adopted draws heavily from data mining techniques to provide a rich characterisation of students/users in this particular context from the combination of three types of metrics: cognitive and learning styles, online usage and academic performance. Four different instruments are used to characterise styles: ASSIST (Approaches to learning, Entwistle), CSI (Cognitive Styles Inventory, Allinson & Hayes), TSI (Thinking Styles Inventory and the mental self-government theory, Sternberg) and VICS-WA (Verbal/Imager and Wholistc/Analytic Cognitive style, Riding, Peterson) which were intentionally selected to provide a varied set of tools. Online usage, spanning over the entire academic year for each student, is analysed applying web usage mining (WUM) techniques and is observed through different layers of interpretation accounting for behaviours from the single clicks to a student’s intentions in a single session. Academic performance was collated from the students’ records giving an insight in the end-of-year grades, but also into specific coursework submissions during the whole academic year allowing for a temporal matching of online use and assessment. The varied metrics used and data mining techniques applied provide a novel evaluation framework based on a rich profile of the learner, which in turn offers a valuable alternative to regression methods as a mean to interpret relations between metrics. Patterns emerging from styles and the way online material is used over time, proved to be valuable in discriminating differences in academic performance and useful in this context to identify significant group differences in both usage and academic performance. As a result, the understanding of the relations between e-learning usage, styles and academic performance has important practical implications to enhance students’ learning experience, in the automation of learning systems and to inform policymakers of the effects of learning technology has from a user and learner-centred approach to learning and studying. The success of the application of data mining methods offers an excellent starting point to explore further a data-driven approach to evaluation, support informed design processes of e-learning and to deliver suitable interventions to ensure better learning outcomes and provide an efficient system for institutions and organization to maximise the impact of learning technology for teaching and training.

Univ., Diss.--Ulm, 2005. / Literaturverz. S. 227 - 248.

Since its inception in the nineteenth century, the Internal Combustion Engine (ICE) remains the most prevalent technology in transportation systems to date. In order to minimize emissions, it is important that ICE is operated according to its optimized design conditions. As such, condition monitoring and Fault Detection and Diagnosis (FDD) tools can play an important role in detecting conditions that would affect the operability of the engine. In this research, different signal-based Fault Detection and Diagnosis (FDD) techniques are researched and implemented for fault condition monitoring of ICE. The implementation of prognostics for the engine in an automated form has important consequences that include cost savings, increased reliability, reduction of GHG emissions, better safety, and extended life for the vehicle. In this research, in order to carry out FDD onboard, a low-cost and flexible internet-based data-acquisition system (DAQ) was designed and implemented. The main part of the system is an embedded hardware running a full desktop version of Linux. This sensory system leverages the positive aspects of both real-time and general-purpose architectures to ensure engine monitoring at high sampling rates. Unlike other commercial DAQ systems, the software of this device is open-source, free of charge, and highly expandable to suit other FDD applications. In addition to data collection at high sampling rates, the FDD system includes advanced FDD strategies. The Fault Detection and Diagnosis strategies considered use a combination of Fourier Transforms (FT), Wavelet Transforms (WT), and Principal Component Analysis (PCA). Meanwhile, Fault Classification was carried using Neural Networks consisting of the Multi-Layer Perceptron (MLP). Three strategies were comparatively considered for the training of the Neural Network (NN), namely the Levenberg-Marquardt (LM), the Extended Kalman Filter (EKF), and the Smooth Variable Structure Filter (SVSF) techniques. The proposed FDD system was able to achieve 100% accuracy in classifying a set of engine faults. / Thesis / Master of Applied Science (MASc)

A machine learning method for synthesising human images is explored to create new images without relying on 3D modelling. Machine learning allows the creation of new images through prediction from existing data based on the use of training images. In the present study, image synthesis is performed at two levels: contour and pixel. A class of learning-based methods is formulated to create object contours from the training image for the synthetic image that allow pixel synthesis within the contours in the second level. The methods rely on applying robust object descriptions, dynamic learning models after appropriate motion segmentation, and machine learning-based frameworks. Image-based human image synthesis using machine learning is a research focus that has recently gained considerable attention in the field of computer graphics. It makes use of techniques from image/motion analysis in computer vision. The problem lies in the estimation of methods for image-based object configuration (i.e. segmentation, contour outline). Using the results of these analysis methods as bases, the research adopts the machine learning approach, in which human images are synthesised by executing the synthesis of contour and pixels through the learning from training image. Firstly, thesis shows how an accurate silhouette is distilled using developed background subtraction for accuracy and efficiency. The traditional vector machine approach is used to avoid ambiguities within the regression process. Images can be represented as a class of accurate and efficient vectors for single images as well as sequences. Secondly, the framework is explored using a unique view of machine learning methods, i.e., support vector regression (SVR), to obtain the convergence result of vectors for contour allocation. The changing relationship between the synthetic image and the training image is expressed as a vector and represented in functions. Finally, a pixel synthesis is performed based on belief propagation. This thesis proposes a novel image-based rendering method for colour image synthesis using SVR and belief propagation for generalisation to enable the prediction of contour and colour information from input colour images. The methods rely on using appropriately defined and robust input colour images, optimising the input contour images within a sparse SVR framework. Firstly, the thesis shows how contour can effectively and efficiently be predicted from small numbers of input contour images. In addition, the thesis exploits the sparse properties of SVR efficiency, and makes use of SVR to estimate regression function. The image-based rendering method employed in this study enables contour synthesis for the prediction of small numbers of input source images. This procedure avoids the use of complex models and geometry information. Secondly, the method used for human body contour colouring is extended to define eight differently connected pixels, and construct a link distance field via the belief propagation method. The link distance, which acts as the message in propagation, is transformed by improving the low-envelope method in fast distance transform. Finally, the methodology is tested by considering human facial and human body clothing information. The accuracy of the test results for the human body model confirms the efficiency of the proposed method.

Phishing techniques have not only grown in number, but also in sophistication. Phishers might have a lot of approaches and tactics to conduct a well-designed phishing attack. The targets of the phishing attacks, which are mainly on-line banking consumers and payment service providers, are facing substantial financial loss and lack of trust in Internet-based services. In order to overcome these, there is an urgent need to find solutions to combat phishing attacks. Detecting phishing website is a complex task which requires significant expert knowledge and experience. So far, various solutions have been proposed and developed to address these problems. Most of these approaches are not able to make a decision dynamically on whether the site is in fact phished, giving rise to a large number of false positives. This is mainly due to limitation of the previously proposed approaches, for example depending only on fixed black and white listing database, missing of human intelligence and experts, poor scalability and their timeliness. In this research we investigated and developed the application of an intelligent fuzzy-based classification system for e-banking phishing website detection. The main aim of the proposed system is to provide protection to users from phishers deception tricks, giving them the ability to detect the legitimacy of the websites. The proposed intelligent phishing detection system employed Fuzzy Logic (FL) model with association classification mining algorithms. The approach combined the capabilities of fuzzy reasoning in measuring imprecise and dynamic phishing features, with the capability to classify the phishing fuzzy rules. Different phishing experiments which cover all phishing attacks, motivations and deception behaviour techniques have been conducted to cover all phishing concerns. A layered fuzzy structure has been constructed for all gathered and extracted phishing website features and patterns. These have been divided into 6 criteria and distributed to 3 layers, based on their attack type. To reduce human knowledge intervention, Different classification and association algorithms have been implemented to generate fuzzy phishing rules automatically, to be integrated inside the fuzzy inference engine for the final phishing detection. Experimental results demonstrated that the ability of the learning approach to identify all relevant fuzzy rules from the training data set. A comparative study and analysis showed that the proposed learning approach has a higher degree of predictive and detective capability than existing models. Experiments also showed significance of some important phishing criteria like URL & Domain Identity, Security & Encryption to the final phishing detection rate. Finally, our proposed intelligent phishing website detection system was developed, tested and validated by incorporating the scheme as a web based plug-ins phishing toolbar. The results obtained are promising and showed that our intelligent fuzzy based classification detection system can provide an effective help for real-time phishing website detection. The toolbar successfully recognized and detected approximately 92% of the phishing websites selected from our test data set, avoiding many miss-classified websites and false phishing alarms.

In the automotive industry test drives are conducted during the development of new vehicle models or as a part of quality assurance for series vehicles. During the test drives, data is recorded for the use of fault analysis resulting in millions of data points. Since multiple vehicles are tested in parallel, the amount of data that is to be analysed is tremendous. Hence, manually analysing each recording is not feasible. Furthermore the complexity of vehicles is ever-increasing leading to an increase of the data volume and complexity of the recordings. Only by effective means of analysing the recordings, one can make sure that the effort put in the conducting of test drives pays off. Consequently, effective means of test drive analysis can become a competitive advantage. This Thesis researches ways to detect unknown or unmodelled faults in recordings from test drives with the following two aims: (1) in a data base of recordings, the expert shall be pointed to potential errors by reporting anomalies, and (2) the time required for the manual analysis of one recording shall be shortened. The idea to achieve the first aim is to learn the normal behaviour from a training set of recordings and then to autonomously detect anomalies. The one-class classifier “support vector data description” (SVDD) is identified to be most suitable, though it suffers from the need to specify parameters beforehand. One main contribution of this Thesis is a new autonomous parameter tuning approach, making SVDD applicable to the problem at hand. Another vital contribution is a novel approach enhancing SVDD to work with multivariate time series. The outcome is the classifier “SVDDsubseq” that is directly applicable to test drive data, without the need for expert knowledge to configure or tune the classifier. The second aim is achieved by adapting visual data mining techniques to make the manual analysis of test drives more efficient. The methods of “parallel coordinates” and “scatter plot matrices” are enhanced by sophisticated filter and query operations, combined with a query tool that allows to graphically formulate search patterns. As a combination of the autonomous classifier “SVDDsubseq” and user-driven visual data mining techniques, a novel, data-driven, semi-autonomous approach to detect unmodelled faults in recordings from test drives is proposed and successfully validated on recordings from test drives. The methodologies in this Thesis can be used as a guideline when setting up an anomaly detection system for own vehicle data.