Recent PublicationsView all

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper discusses the development and evaluation of distribution models for predicting alluvial mineral potential mapping. A number of existing models includes Weight of Evidence, Knowledge-driven Fuzzy, Data-driven Fuzzy, Neural-Network, Bayesian Classifier and Geostatistical Kriging. We offer classification models developed in our laboratory, where point pattern analysis was used to identify presence or absence of a known secondary alluvial (cassiterite) deposits in the Nigerian Younger Granite Region (NYGR) and the model performance assessed. We focused on the training and testing data split using longitudinal spatial data splitting (strips and halves) to ensure predictive attribute's independence. The spatial data split runs counter to the traditional random sample data selection as a procedure for checking overfitting of models mainly due to spatial data autocorrelation. Specifically, we used classification algorithms such as; Naive Bayes, Support Vector Machine, K-Nearest Neighbour, Decision Tree Bagging and Discriminant Analysis algorithms for training and testing. We analysed the model's performance results using model predictive accuracy and ROC curve values in two different approaches that improve spatial data independence among predictive attributes to give a meaningful model performance.
    Full-text · Article · Dec 2014 · Procedia Computer Science
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper studies a multi-criteria optimization problem which appears in the context of booking chemotherapy appointments. The main feature of the model under study is the requirement to book for each patient multiple appointments which should follow a pre-specified multi-day pattern. Each appointment involves several nurse activities which should also follow a pre-specified intra-day pattern. The main objectives are to minimize patients’ waiting times and peaks of nurses’ workload for an outpatient clinic. Our solution approach is based on the concept of a multi-level template schedule which is generated for a set of artificial patients with typical treatment patterns. There are two stages in template generation: the multi-day stage, which fixes appointment dates for all artificial patients, and the intra-day stage, which fixes for each day appointment starting times and patient allocation to nurses. The running schedule is created by considering actual patients one by one as they arrive to the clinic. Booking appointments for each new patient is performed by assigning appropriate dates and times of the template schedule following the prescribed multi-day and intra-day patterns. Additional rescheduling procedure is used to re-optimize intra-day schedules on a treatment day or shortly beforehand. The key stages of the scheduling process are modeled as integer linear programs and solved using CPLEX solver. We demonstrate the effectiveness of our approach through case-based scenarios derived from a real clinic and discuss the advantages that the multi-level template can bring.
    Preview · Article · Sep 2014 · Operations Research for Health Care
  • [Show abstract] [Hide abstract]
    ABSTRACT: In order to fully exploit the concept of Smart Home, challenges associated with multiple device management in consumer facing applications have to be addressed. Specific to this is the management of resource usage in the home via the improved utilization of devices, this is achieved by integration with the wider environment they operate in. The traditional model of the isolated device no longer applies, the future home will be connected with services provided by third parties ranging from supermarkets to domestic appliance manufacturers. In order to achieve this risk based integrated device management and contextualization is explored in this paper based on the cloud computing model. We produce an architecture and evaluate risk models to assist in this management of devices from a security, privacy and resource management perspective. We later propose an expansion on the risk based approach to wider data sharing between the home and external services using the key indicators of TREC (Trust, Risk, Eco-efficiency and Cost). The paper contributes to Smart Home research by defining how Cloud service management principles of risk and contextualization for virtual machines can produce solutions to emerging challenges facing a new generation of Smart Home devices.
    No preview · Article · Sep 2014 · Future Generation Computer Systems
Information provided on this web page is aggregated encyclopedic and bibliographical information relating to the named institution. Information provided is not approved by the institution itself. The institution’s logo (and/or other graphical identification, such as a coat of arms) is used only to identify the institution in a nominal way. Under certain jurisdictions it may be property of the institution.