Educational Data Mining (EDM) is a developing discipline, concerned with expanding the classical Data Mining (DM) methods and developing new methods for discovering the data that originate from ...educational systems. Student attendance in higher education has always been dealt with in a classical way, educators rely on counting the occurrence of attendance or absence building their knowledge about students as well as modules based on this count. This method is neither credible nor does it necessarily provide a real indication of a student performance. This study tries to formulate the extracted knowledge in a way that guarantees achieving accurate and credible results. Student attendance data, gathered from the educational system, were first cleaned in order to remove any randomness and noise, then various attributes were studied so as to highlight the most significant ones that affect the real attendance of students. The next step was to derive an equation that measures the Student Attendance Credibility (SAC) considering the attributes chosen in the previous step. The reliability of the newly developed measure was then evaluated in order to examine its consistency. Finally, the J48 DM classification technique was utilized in order to classify modules based on the strength of their SAC values. Results of this study were promising, and credibility values achieved using the newly derived formula gave accurate, credible, and real indicators of student attendance, as well as accurate classification of modules based on the credibility of student attendance on those modules.
Use of Ontology in Identifying Missing Artefact Links Gazzawe, Foziah; Lock, Russell; Dawson, Christian
Proceedings of the 2018 7th International Conference on Software and Computer Applications,
02/2018
Conference Proceeding
Odprti dostop
The techniques of requirement traceability have evolved over recent years. However, as much as they have contributed to the software engineering field, significant ambiguity remains in many software ...engineering processes. This paper reports on an investigation of requirement traceability artefacts, stakeholders, and SDLC development models. Data were collected to gather evidence of artefacts and their properties from previous studies. The aim was to find the missing link between artefacts and their relationship to one another, the stakeholders, and SDLC models. This paper undertakes the first phase of the main research project, which aims to develop a framework for guiding software developers to actively manage traceability. After inquiring into and examining previous research on this topic, the links between artefacts and their functions were identified. The analysis resulted in the development of a new model for requirement traceability, defined in the form of an ontology portraying the contributively relations between software artefacts using common properties with the aid of Protégé Software. This study thus provides an important insight into the future of the requirement artefacts relation, and thereby lays an important foundation towards increasing our understanding of their potential and limitations.
Encrypted communications lie at the heart of our ability to secure networks and prevent things like the Office of Personnel Management attacks, but certain law enforcement agencies seem intent on ...weakening encryption standards and undermining our ability to prevent future occurrences through the creation of encryption backdoors. Who covers the cost of storage systems, or the costs of implementing secondary security systems to obfuscate the required backdoors?
Mimicking player strategies in fighting games Saini, S. S.; Dawson, C. W.; Chung, P. W. H.
2011 IEEE International Games Innovation Conference (IGIC),
2011-Nov.
Conference Proceeding
The paper presented here provides an account of the research carried out in the field of Game Artificial Intelligence (AI) related to mimicking human player strategies in fighting games. The problem ...is introduced followed by a description of the Proof of Concept game that is used as a test bed for the implementation of a novel AI system. An overview of the system is also provided with the detailed results of a demonstration that alludes to the effectiveness of the system.
This thesis develops the concept, management and control of metamodels for the management of software development projects. Metamodels provide a more flexible approach for managing and controlling ...the software engineering process and are based on the integration of several software development paradigms. Generalised Activity Networks are used to provide the more powerful planning techniques required for managing metamodels. In this thesis, both new node logics, that clarify previous work in this field, and Generalised Activity-on-the-Arrow and Generalised Activity-on-the-Node representations are developed and defined. Activity-on-the-Node representations reflect the current mood of the project management industry and allow constraints to be applied directly to logical dependencies between activities. The Generalised Activity Networks defined within this thesis can be used as tools to manage risks and uncertainties in both software developments and general engineering projects. They reflect the variation and uncertainties in projects more realistically and improve the planning and scheduling of such projects.
This thesis develops the concept, management and control of metamodels for the management of software development projects. Metamodels provide a more flexible approach for managing and controlling ...the software engineering process and are based on the integration of several software development paradigms. Generalised Activity Networks are used to provide the more powerful planning techniques required for managing metamodels. In this thesis, both new node logics, that clarify previous work in this field, and Generalised Activity-on-the-Arrow and Generalised Activity-on-the-Node representations are developed and defined. Activity-on-the-Node representations reflect the current mood of the project management industry and allow constraints to be applied directly to logical dependencies between activities. The Generalised Activity Networks defined within this thesis can be used as tools to manage risks and uncertainties in both software developments and general engineering projects. They reflect the variation and uncertainties in projects more realistically and improve the planning and scheduling of such projects.
Although artificial neural networks have been applied to problems within hydrology for over ten years, there is little consensus on the 'best' type of neural network model to use and the most ...effective means of training the chosen model. In order to explore the different approaches neural network modellers use to forecasting river stage, an international comparison study was undertaken during 2004. This research was based on a set of rainfall and river stage data covering three winter periods for an unidentified river basin in England (with a catchment of 331,500 Ha in the north of the country), sampled at 15 minute intervals. Several neural network enthusiasts took part in the study from a number of different countries. The preferred methodologies and forecasting outputs from a number of 'blind' models of river stage developed by the participants have been collated and are presented in this paper.