Browsing by Author "Denzinger, Joerg"
Now showing 1 - 10 of 10
Results Per Page
- ItemOpen AccessApplication of the Weka Machine Learning Library to Hospital Ward Occupancy Problems(2008-01-04) Harris, Ian; Denzinger, Joerg; Yergens, DeanWe explore the potential of applying machine learning techniques to the management of patient ow in hospitals. For this project, we have obtained the Weka machine learning library and three years of historical ward occupancy data from Rockyview Hospital. We use Weka's classifier algorithms and the Rockyview data to build a model of patient ow through each ward. Using Weka, we then attempt to predict ward occupancy problems on any given day using the model and the ward conditions from the previous day. This process is repeated for all eighteen wards. Finally, we obtain rules (sets of ward conditions that warn of an impending occupancy problem) for each ward and present the results.
- ItemOpen AccessBuild Notifications in Agile Environments(2008-01-14) Ablett, Ruth; Maurer, Frank; Sharlin, Ehud; Denzinger, Joerg; Schock, CraigIn an agile software development environment, developers write code that should work together to fulfill the wishes of the customer. Continuous integration (CI) ensures that code from different individuals integrates properly. CI compiles the entire codebase, deploys and tests it with each change. CI alerts developers of any problems as errors can be fixed more easily if caught earlier in the process. This paper compares the effectiveness of different types of mechanisms for notifying developers to a successful or unsuccessful build. Two different quantitative and qualitative user studies were performed testing the effectiveness of three types of notification devices one virtual e-mail based mechanism, one using ambient lava lamps, and one robotic device. The results show that most developers preferred an easily visible but unobtrusive ambient device combined with an e-mail describing the problem in more detail.
- ItemOpen AccessBuildBot: A Robotic Software Development Monitor in an Agile Environment(2006-05-18) Ablett, Ruth; Maurer, Frank; Sharlin, Ehud; Denzinger, JoergIn this paper, we describe BuildBot, a robot developed to assist with continuous integration of a software build in Agile development teams. BuildBot can interact physically with individual members of the team and be an active part of the development process by bringing together human-robot interaction with human group dynamics and knowledge about software engineering concepts. This paper describes the design and implementation of a robot that can sense virtual stimuli, in this case the state of a software build, and react accordingly in a physical way. By increasing awareness of the state of the software build, BuildBot assists in the self-supervision of teams.
- ItemOpen AccessCreating and Evaluating Goal Ordering Structures for Testing Harbour Patrol and Interception Policies(2010-03-24T15:29:21Z) Thornton, Chris; Flanagan, Tom; Denzinger, JoergIn this article, we discuss a method for testing policies that guide groups of agents in simulations for interactions with other agents and the environment that reveal weaknesses of these policies. Our method is based on learning interaction sequences using particle swarm systems and has as one crucial component so-called goal ordering structures that are used to guide the learning towards weakness-revealing interactions. Our discussion centers around the different ways a new measuring idea can be integrated into such an ordering structure using the example of testing patrol and interception policies for harbours. Our experimental evaluation reveals that the position of placement of a new measure in an existing ordering structure can greatly influence the testing results, positively and negatively, but mostly mirrors the intuition associated with the placement.
- ItemOpen AccessDeepCADe: A Deep Learning Architecture for the Detection of Lung Nodules in CT Scans(2018-01-16) Golan, Rotem; Jacob, Christian; Denzinger, Joerg; Gavrilova, Marina; Frayne, Richard; Cunningham, IanEarly detection of lung nodules in thoracic Computed Tomography (CT) scans is of great importance for the successful diagnosis and treatment of lung cancer. Due to improvements in screening technologies, and an increased demand for their use, radiologists are required to analyze an ever increasing amount of image data, which can affect the quality of their diagnoses. Computer-Aided Detection (CADe) systems are designed to assist radiologists in this endeavor. In this thesis, we present DeepCADe, a novel CADe system for the detection of lung nodules in thoracic CT scans which produces improved results compared to the state-of-the-art in this field of research. CT scans are grayscale images, so the terms scans and images are used interchangeably in this work. DeepCADe was trained with the publicly available Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) database, which contains 1018 thoracic CT scans with nodules of different shape and size, and is built on a Deep Convolutional Neural Network (DCNN), which is trained using the backpropagation algorithm to extract volumetric features from the input data and detect lung nodules in sub-volumes of CT images. Considering only lung nodules that have been annotated by at least three radiologists, DeepCADe achieves a 2.1% improvement in sensitivity (true positive rate) over the best result in the current published scientific literature, assuming an equal number of false positives (FPs) per scan. More specifically, it achieves a sensitivity of 89.6% with 4 FPs per scan, or a sensitivity of 92.8% with 10 FPs per scan. Furthermore, DeepCADe is validated on a larger number of lung nodules compared to other studies (Table 5.2). This increases the variation in the appearance of nodules and therefore makes their detection by a CADe system more challenging. We study the application of Deep Convolutional Neural Networks (DCNNs) for the detection of lung nodules in thoracic CT scans. We explore some of the meta parameters that affect the performance of such models, which include: 1. the network architecture, i.e. its structure in terms of convolution layers, fully-connected layers, pooling layers, and activation functions, 2. the receptive field of the network, which defines the dimensions of its input, i.e. how much of the CT scan is processed by the network in a single forward pass, 3. a threshold value, which affects the sliding window algorithm with which the network is used to detect nodules in complete CT scans, and 4. the agreement level, which is used to interpret the independent nodule annotations of four experienced radiologists. Finally, we visualize the shape and location of annotated lung nodules and compare them to the output of DeepCADe. This demonstrates the compactness and flexibility in shape of the nodule predictions made by our proposed CADe system. In addition to the 5-fold cross validation results presented in this thesis, these visual results support the applicability of our proposed CADe system in real-world medical practice.
- ItemOpen AccessThe End-to-End Use of Source Code Examples: An Exploratory Study - Appendix(2009-06-15T17:54:07Z) Holmes, Reid; Cottrell, Rylan; Walker, Robert; Denzinger, JoergThis appendix contains the details of our case studies outlined in our paper for the 2009 International Conference on Software Maintenance, as well as an expanded discussion section. The reader is directed to the main paper for introduction, motivation, and related work.
- ItemOpen AccessTEACHING MULTI-AGENT SYSTEMS WITH THE HELP OF ARES: MOTIVATION AND MANUAL(2002-11-07) Bergen, Melissa; Denzinger, Joerg; Kidney, JordanIn the last years, multi-agent systems (MAS) have become a very active research area that has connections to many other areas, both inside and outside of Computer Science. Consequently, courses about MAS are starting to be developed and even the first text books are on the market (see [AL02] and [Wo02]). Perhaps even more than in other areas of Computer Science, teaching MAS has to involve practical experiences by the students. The interaction of agents has many surprises (as has the interaction of human beings) and hands-on experiences with issues like timing of actions to achieve cooperation, communication and the effects of, changes in the surroundings, and so on, are necessary to let students understand not only the basic problems but also why certain concepts are the way they are. For getting practical experience with developing multi-agent systems the students need an environment (or testbed) in which their agents will interact, that sets the basic rules for the agents and guards these rules against violations by the agents. There are already such environments available, namely the environments used in various competitions, as for example the RoboCup Simulation League Soccer Server ([seeKu02]) or the TAC Game Servers of the Trading Agent Competition (see[W e+ 01]). But, for teaching purposes, the goals for the development of these environments do not totally agree with the goals we need for a teaching environment: having successful systems available via WWW allows for a lot of cheating (resp. requires a lot of work of the instructor spend on counter actions) and results in students not making the experiences they are supposed to make. Also, the two cited environments are rather specialized, so that certain experiences are outside of their scope. There are a lot of other didactic reasons for not using testbeds that were developed and are used to evaluate research systems, as we will see later in this report. In this report, we present the ARES system (Agent Rescue Emergency Simulator) that is intended to be a testbed for multi-agent systems and to be used for teaching MAS. ARES follows the lead of the RoboCup Rescue Initiative (see [RR02]) in choosing as the application scenario rescuing survivors in a disaster zone. The basic tasks the students have to include into the agents that form their multi-agent system that is employed within ARES are locating survivors and removing rubble to reach and rescue those survivors. ARES allows for many different variants of the basic setting, by varying the information the agents have when starting, the cost of communication, the methods for agents to regain energy, and so on. While many basic requirements of acting in a real disaster scenario are touched, nevertheless they are simplified within ARES towards a game-like scenario that allows students, resp. student teams to develop agents tat act as team in ARES in the 4 months a beginners course in MAS takes. This report is organized as follows: After this introduction, we take a closer look at the requirements on a testbed for MAS (resp. MAS concepts) that is aimed at helping in teaching MAS basics. This then leads to stating our goals in developing ARES. In Section 3, we present the system using two different views: the view of a student using it and the view of an instructor configuring ARES for his/her course (and we will also provide some information about the implementation of ARES). In Section 4, we present observations we made when using ARES for teaching MAS to a mixed class of graduate and undergraduate students at the University of Calgary. Finally, we will conclude with some remarks on future work. The report also contains as appendices descriptions of the actions ARES allows agents and their syntax, of the graphical viewer that allows building scenarios and observing a rescue team, of the installation requirements and procedure, and of the parameters for defining the \world laws".
- ItemOpen AccessTesting Self-Organizing Emergent Systems by Learning of Event Sequences(2009-12-02T17:56:29Z) Hudson, Jonathan; Denzinger, Joerg; Kasinger, Holger; Bauer, BernhardWe present an approach to test self-organizing emergent systems for unwanted behavior with respect to inefficiencies in task fulfillment based on evolutionary learning of event sequences. By using the differences in produced solution quality versus optimal quality to guide the evolutionary search and by using in addition to standard evolutionary operators targeted ones reflecting knowledge about the tested system, the usual evolutionary learning effects can take place, leading to event sequences that are solved badly by the tested systems. In our experimental evaluation of 2 variants of a self-organizing emergent system for dynamic pickup-and-delivery problems, a system using our learning testing approach created clear evidence that the basic variant of the tested system has problems regarding the efficiency of the solutions it produces and that the efficiency improved version leads even in an extremely negative setting for it to only about double the quality costs
- ItemOpen AccessA Workflow Reference Monitor for Enforcing Purpose-Based Policies(2013-09-25) Jafari, Mohammad; Denzinger, Joerg; Safavi-Naini, Reihaneh; Barker, KenPurpose is a key concept in privacy policies. Based on the purpose framework developed in our earlier work  we present an access control model for a work ow-based information system in which a work ows reference monitor ( WfRM ) enforces purpose-based policies. We use a generic access control policy language and show how it can be connected to the purpose modal logic language ( PML ) to link purpose constraints to access control rules and how such policies can be enforced. We also present a simple implementation of such a reference monitor based on extending eXtensible Access Control Markup Language( XACML ), a commonly used access control open standard.