Bd ca m big data for context-aware monitoring - a personalized knowledge discovery framework for assisted healthcare

Download Bd ca m big data for context-aware monitoring - a personalized knowledge discovery framework for assisted healthcare

Post on 11-Apr-2017

608 views

Category:

Education

0 download

Embed Size (px)

TRANSCRIPT

<ul><li><p> Do Your Projects With Technology Experts </p><p>Copyright 2015 LeMeniz Infotech. All rights reserved </p><p>Page number 1 </p><p>LeMeniz Infotech </p><p>36, 100 Feet Road, Natesan Nagar, Near Indira Gandhi Statue, Pondicherry-605 005. Call: 0413-4205444, +91 9566355386, 99625 88976. Web : www.lemenizinfotech.com / www.ieeemaster.com Mail : projects@lemenizinfotech.com </p><p>BDCaM: Big Data for Context-aware Monitoring </p><p>- A Personalized Knowledge Discovery </p><p>Framework for Assisted Healthcare </p><p>ABSTRACT: </p><p> Context-aware monitoring is an emerging technology that provides real-time </p><p>personalised health-care services and a rich area of big data application. In this paper, we </p><p>propose a knowledge discovery-based approach that allows the context-aware system to </p><p>adapt its behaviour in runtime by analysing large amounts of data generated in ambient </p><p>assisted living (AAL) systems and stored in cloud repositories. The proposed BDCaM </p><p>model facilitates analysis of big data inside a cloud environment. It first mines the trends </p><p>and patterns in the data of an individual patient with associated probabilities and utilizes </p><p>that knowledge to learn proper abnormal conditions. The outcomes of this learning method </p><p>are then applied in context-aware ecision-making processes for the patient. A use case is </p><p>implemented to illustrate the applicability of the framework that discovers the knowledge of </p><p>classification to identify the true abnormal conditions of patients having variations in blood </p><p>pressure (BP) and heart rate (HR). The evaluation shows a much </p><p>INTRODUCTION </p><p>AN ambient assisted living (AAL) system consists of heterogeneous sensors and devices </p><p>which generate huge amounts of patient-specific unstructured raw data everyday. Due to </p><p>diversity of sensors and devices, the captured data also have wide variations. A data </p><p>element can be from a few bytes of numerical value (e.g. HR = 72 bpm) to several </p><p>gigabytes of video stream. For example, if we assume a single AAL system generates 100 </p><p>kilobytes data every second on average then it will become 2.93 abytes in one year. If any </p><p>system targets to support say, 5 million patients, then the data amount will be 14 exabytes </p><p>per year. Even if a healthcare system targets to analyse only continuous ECG of cardiac </p><p>patients in real-time inside the cloud environment, then it will produce around 7 PetaBytes </p><p>http://www.lemenizinfotech.com/http://www.ieeemaster.com/</p></li><li><p> Do Your Projects With Technology Experts </p><p>Copyright 2015 LeMeniz Infotech. All rights reserved </p><p>Page number 2 </p><p>LeMeniz Infotech </p><p>36, 100 Feet Road, Natesan Nagar, Near Indira Gandhi Statue, Pondicherry-605 005. Call: 0413-4205444, +91 9566355386, 99625 88976. Web : www.lemenizinfotech.com / www.ieeemaster.com Mail : projects@lemenizinfotech.com </p><p>data everyday from 3.5 million patients. Including these dynamically generated continuous </p><p>monitoring data there are also huge amounts of persistent data such as patient profile, </p><p>medical records, disease histories and social contacts. </p><p>EXISTING SYSTEM </p><p>In Existing System an attribute value set Ai is converted to a numerical value. Some </p><p>context attributes already have numeric values (e.g. HR, BP, room perature). Numerical </p><p>annotations are used for contexts having nominal value (e.g. activity). The static or </p><p>historical context that have boolean values (e.g. symptoms) are combined in a single </p><p>binary string which results a decimal value (e.g. 001100 converted to 12). So, after such </p><p>numerical conversion every Ai has the value set described in Definition 1. </p><p>PROPOSED SYSTEM </p><p> In Proposed System we developed BDCaM, an extended version of the </p><p>CoCaMAAL model. This includes the functionalities of learning and the knowledge </p><p>discovery process to find patient-specific anomalies using large amounts of data </p><p>ADVANTAGE OF PROPOSED SYSTEM </p><p> Faster learning with greater knowledge </p><p> Reduce the transmission of repeated false alerts </p><p> Innovative architectural model for context-aware monitoring </p><p> Step learning methodology </p><p> Demonstrate the performance and efficiency of BDCaM model </p><p>http://www.lemenizinfotech.com/http://www.ieeemaster.com/</p></li><li><p> Do Your Projects With Technology Experts </p><p>Copyright 2015 LeMeniz Infotech. All rights reserved </p><p>Page number 3 </p><p>LeMeniz Infotech </p><p>36, 100 Feet Road, Natesan Nagar, Near Indira Gandhi Statue, Pondicherry-605 005. Call: 0413-4205444, +91 9566355386, 99625 88976. Web : www.lemenizinfotech.com / www.ieeemaster.com Mail : projects@lemenizinfotech.com </p><p>ARCHITECTURE: </p><p>http://www.lemenizinfotech.com/http://www.ieeemaster.com/</p></li><li><p> Do Your Projects With Technology Experts </p><p>Copyright 2015 LeMeniz Infotech. All rights reserved </p><p>Page number 4 </p><p>LeMeniz Infotech </p><p>36, 100 Feet Road, Natesan Nagar, Near Indira Gandhi Statue, Pondicherry-605 005. Call: 0413-4205444, +91 9566355386, 99625 88976. Web : www.lemenizinfotech.com / www.ieeemaster.com Mail : projects@lemenizinfotech.com </p><p>HARDWARE REQUIREMENTS: </p><p> System : Pentium IV 2.4 GHz. </p><p> Hard Disk : 40 GB. </p><p> Floppy Drive : 44 Mb. </p><p> Monitor : 15 VGA Colour. </p><p>SOFTWARE REQUIREMENTS: </p><p> Operating system : Windows 7. </p><p> Coding Language : Java 1.7 ,Hadoop 0.8.1 </p><p> Database : MySql 5 </p><p> IDE : Eclipse </p><p>http://www.lemenizinfotech.com/http://www.ieeemaster.com/</p></li></ul>