Search

We present an extension of our previous work in [1] by investigating the use of Local Septenary Patterns (LSP) for breast density classification in mammograms. The LSP operator is a variant of Local Binary Patterns (LBP) inspired by Local Ternary Patterns (LTP) and Local Quinary patterns (LQP). The main extensions in our work are i) we investigate the use of a multi-resolution technique when extracting micro texture information, ii) we investigate different neighbourhood topologies as different ways of extracting texture features, and iii) we use an additional dataset called InBreast as well as the most popular dataset in the literature, which is the Mammographic Image Analysis Society (MIAS) to further evaluate the performance of the LSP operator.

WSNs are evolving towards interconnected, sensing, processing and actuating infrastructures that are expected to provide services for multiple concurrent clients. In a multi-purpose WSN, concurrently running applications share network resources and each may have varying Quality of Data (QoD) requirements. Our middleware targets these multi-purpose WSN deployments. Specifically this paper discusses how one should express and configure QoD properties for multi-purpose WSNs. We contribute by preseting our approach; which leverages per-instance QoD configuration and a separation of operational concerns to achieve simpler configuration and improve reconfigure-ability and customize-ability of the WSN. A prototype implementation and comparison to the related state of the art in WSNs are provided. ispartof: pages:91-106 ispartof: Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering vol:57 pages:91-106 ispartof: The International ICST conference on Sensor Systems and Software location:miami, USA status: published

The emerging reality of wireless sensor networks deployed as long-lived infrastructure mandates an approach to tailor developed artefacts at run-time to avoid costly reprogramming. Support for dynamic concerns, such as adaptation, calibration or tuning of the functional and non-functional behaviour by application users and infrastructure managers raises the need for fine-grained run-time customization. This paper presents a policy-based paradigm to realize the diverse concerns of the involved actors by enabling fine-tuning and optimization of the run-time environment. Integration of the policy paradigm into various main programming models is analyzed. A prototype implementation of the paradigm in the context of an event-component based wireless sensor network platform is evaluated on the SunSPOT sensor platform. © 2011 ICST Institute for Computer Science, Social Informatics and Telecommunications Engineering. ispartof: pages:20-35 ispartof: Sensor Systems and Software, Revised Selected Papers. LNICST vol:51 pages:20-35 ispartof: S-CUBE location:Miami, FL date:13 Dec - 14 Dec 2010 status: published