Browsing by Author "Kremer, Robert"
Now showing 1 - 16 of 16
Results Per Page
Sort Options
Item Open Access A concept map based approach to the shared workspace(1993) Kremer, Robert; Gaines, Brian R.Item Open Access A descriptive process model for open-source software development(2001) Johnson, Kim; Kremer, RobertItem Open Access Adding an Ontology Filter to the Knowledge Base in CASA(2014-04-16) Singh, Baljeet; Kremer, RobertOntologies are being used in a lot of applications today. Ontologies provide extensive knowledge about a domain. Knowledge bases are also being used in a lot of software applications and agent based applications. Agent based systems are used in various applications ranging from biomedical applications to nancial applications and from military applications to graphic applications. This thesis presents the integration of the ontologies and the knowledge base in an agent based system called Collaborative Agent System Architecture (CASA). CASA uses a knowledge base from another agent based system called JAVA Agent Development Environment (JADE) and uses the OWL2 ontology engine. In CASA, agents are queried without using ontological knowledge, only using knowledge from the underlying knowledge base. This gives us poor quality results. The ontology lter is then added to the system. The agents are then queried with the knowledge from both the ontologies and the knowledge base (using ontology lter). The later shows improved results (more accurate results). This integration of the ontologies and the knowledge base could be extremely useful in a lot of agent based applications.Item Open Access Constraint graphs: a concept map meta-language(1997) Kremer, Robert; Gaines, Brian R.Item Open Access Content Based Spam Classification- A Deep Learning Approach(2016) Tyagi, Akshita; Li, Zongpeng; Far, Behrouz; Kremer, RobertIn this thesis, we apply Stacked Denoising Autoencoder (SDAE), a major type of deep learning networks, to spam detection. We comprehensively compare its performances with other prevalent deep learning techniques, Deep Belief Network (DBN) and Dense Multi Layer Perceptron (Dense- MLP), which can be further applied to spam filtering. We further compared the performance of these deep learning technologies against state-of-the-art, Support Vector Machines (SVM). Experiments were conducted on five benchmark corpora, namely PU1, PU2, PU3, PUA, and Enron- Spam. Accuracy, Precision, Recall and F1 measure are selected as the main criteria in analysing and discussing the results. Experimental results verify the efficacy of deep learning approaches with application in spam filtering in the real world. This project is part of the larger research in deep learning being conducted by the Wedge Networks- a leading technology vendor in security services. Wedge Networks is actively doing great work in the different realms of securing data on the internet and the cloud- including spam classification, web-page classification, and virus detection among others. This study delves deeper into applying deep learning to spam classification in particular and checks its credibility against the state-of-the-art algorithm- SVM.Item Open Access Developing applications with multiple programming languages: an investigation using C++ and Java(2005) Werbicki, Paul; Kremer, RobertItem Open Access Environmental decisions in ambient intelligent environments(2011) Becerra Ayala, Gabriel; Kremer, RobertItem Open Access Establishing conversations as the first-order agent communication mechanism(2012) Bidulock, Daniel; Kremer, RobertItem Open Access Exploratory case study: experience with a game programming assignment in an introductory computer science classroom(2009) Mason, Jessica Celeste; Jacobsen, D. Michele; Kremer, RobertItem Open Access Integrating informal and formal requirements methods; a practical approach for systems employing spatially referenced data(2000) Goodbrand, Alan D.; Kremer, RobertItem Open Access Modelling agent conversations for action(2002) Flores-Mendez, Roberta Augusto; Kremer, RobertItem Open Access Secure and authenticated communication for a multi-agent framework(2006) Prakash, Jerrall; Kremer, RobertItem Open Access Social commitments and the contract net(2001) Jones, Bradley C.; Kremer, RobertItem Open Access The application of design patterns in knowledge inference engine(1998) Pan, Dong; Kremer, RobertItem Open Access Visualization of multi-agent system conversations(2011) Yee, Ryan; Kremer, RobertItem Open Access Visualizing Agent Communications Graphical Interfaces for Conversation Paradigms(2015-11-09) Aurini, Tristan; Kremer, RobertThis research puts forth a graphical user interface for interacting with and modifying conversations used by software agents in a Multi Agent System (MAS) architecture (CASA). MAS Communications is a field of Artificial Intelligence focusing on improving the way agents communicate. Thus message exchanges are made meaningful by implementing concepts surrounding context. Additionally, they should be flexible in order to avoid problems due to unpredictability. Lastly, these paradigms should be simple to ease their adoption. Using this interface one can visualize how different conversations progress and why they do so allowing for the identification of error sources in the system. The user can also modify existing conversation types, create new ones, and instantiate implementations of them for individual agents. The conversation types are typically distinguished by what is called the performative of the communicative act. This is a concept adopted from linguistics where the performative indicates a conversation's intent/desires.