Muhammad Muzammal

Uncertainty in sequential pattern mining

We study uncertainty models in sequential pattern mining. We discuss some kinds of uncertainties that could exist in data, and show how these uncertainties can be modelled using probabilistic databases. We then obtain possible world semantics for them and show how frequent sequences could be mined using the probabilistic frequentness measure.

Test-Suite Prioritisation by Application Navigation Tree Mining

Software tend to evolve over time and so does the test-suite. Regression testing is aimed at assessing that the software evolution did not compromise the working of the existing software components. However, as the software and consequently the test-suite grow in size, the execution of the entire test-suite for each new build becomes infeasible. Techniques like test-suite selection, test-suite minimisation and test-suite prioritisation have been proposed in literature for regression testing. Whilst all of these techniques are essentially an attempt to reduce the testing effort, test-suite selection and minimisation reduce the test-suite size whereas test-suite prioritisation provides a priority order of the test cases without changing the test-suite size. In this work, we focus on test-suite prioritisation. Recently, techniques from data mining have been used for test-suite prioritisation which consider the frequent pairs of interaction among the application interaction patterns. We propose test-Suite prioritisation by Application Navigation Tree mining (t-SANT). First, we construct an application navigation tree by way of extracting both tester and user interaction patterns. Next, we extract frequent sequences of interaction using a sequence mining algorithm inspired from sequential pattern mining. The most frequent longest sequences are assumed to model complex and most frequently used work-flows and hence a prioritisation algorithm is proposed that prioritises the test cases based on the most frequent and longest sequences. We show the usefulness of the proposed scheme with the help of two case studies, an online book store and calculator.

Scene Completion Using Top-1 Similar Image

Scene Completion is an interesting Image Processing problem that has recently been studied in the context of data, i.e. by using large repositories of data. One of the requirements for such a data intensive approach is that the completion has to be done without human intervention. This is rather challenging as it may not be clear that what could be the most suitable image for the completion purpose in the data repository that potentially contains millions of images. We propose a methodology for finding the top-1 image in a data repository that could be the best candidate for scene completion. We do so by computing a representative set of features namely Gist, Texture and Colour, and then give an algorithm for scene completion. To obtain the top-1 image, we consider a ranking scheme that satisfies the value-invariance property and thus, is not affected by the individual feature scores. The scene completion algorithm completes the input image with the constraint that the completion has to be seamless. The approach is data-driven and there is no need of labelling by the user. Although, the completion process is automated, we also allow the user to select a completion image from the top-k matches in order to have a completion that is semantically valid. The experimental results show that we are able to find a matching image that is able to complete the input image seamlessly.

Evaluation of Navigational Aspects of Moodle

Learning Management System (LMS) is an effective platform for communication and collaboration among teachers and students to enhance learning. These LMSs are now widely used in both conventional and virtual and distance learning paradigms. These LMSs have various limitations as identified in the existing literature, including poor learning content, use of appropriate technology and usability issues. Poor usability leads to the distraction of users. Literature covers many aspects of usability evaluation of LMS. However, there is less focus on navigational issues. Poor navigational can lead to disorientation and cognitive overload of the users of any Web application. For this reason, we have proposed a navigational evaluation framework to evaluate the navigational structure of the LMS. We have applied this framework to evaluate the navigational structure of Moodle. We conducted a survey among students and teachers of two leading universities in Pakistan, where Moodle is in use. This work summarizes the survey results and proposes guidelines to improve the usability of Moodle based on the feedback received from its users.

A Novel Approach for Ranking Images Using User and Content Tags

In this study, a tag and content-based ranking algorithm is proposed for image retrieval that uses the metadata of images as well as the visual features of images, also known as “visual words” to retrieve more relevant images. Thus, making the retrieval process more accurate than the keyword-based retrieval approaches. Both tag and content-based image retrieval techniques have their own advantages and disadvantages. By combining the two, their disadvantages have been offset. The proposed system has been developed to bridge the gap between the existing techniques and the desired user requirements. Initially, the system extracts the metadata of images and stores them into a custom designed dictionary dataset. Then, the system creates a visual vocabulary and trains a classifier on a dataset of images belonging to different categories. Next, for any given userquery, the system makes a decision to display a class of images that best matches the query. These class images are processed in a way that we compute the relevance scores for each image and display the result based on the score.

Database Preservation: The DBPreserve Approach

In many institutions relational databases are used as a tool for managing information related to day to day activities. Institutions may be required to keep the information stored in relational databases accessible because of many reasons including legal requirements and institutional policies. However, the evolution in technology and change in users with the passage of time put the information stored in relational databases in danger. In the long term the information may become inaccessible when the operating system, database management system or the application software is not available any more or the contextual information not stored in the database may be lost thus affecting the authenticity and understandability of the information. This paper presents an approach for preserving relational databases for the long-term. The proposal involves migrating a relational database to a dimensional model which is simple to understand and easy to write queries against. Practical transformation rules are developed by carrying out multiple case studies. One of the case studies is presented as a running example in the paper. Systematic implementation of the rules ensures no loss of information in the process except for the unwanted details. The database preserved using the approach is converted to an open format but may be reloaded to a database management system in the long-term.