International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056 Volume: 03 Issue: 10 | Oct -2016 www.irjet.net p-ISSN: 2395-0072 © 2016, IRJET | Impact Factor value: 4.45 | ISO 9001:2008 Certified Journal | Page 736 Internet of Ambience: An IoT Based Context Aware Monitoring Strategy for Ambient Assisted Living S.Balamurugan #1 , R.P.Shermy #2 ,V.M.Prabhakaran #3 and Dr.R.Gokul Kruba Shanker *4 # Department of Computer Science and Engineering, KIT-Kalaignarkarunanidhi Institute of Technology, Coimbatore, Tamilnadu, India *Consultant Surgical Gastroenterologist, Advanced Laparoscopic and Bariatric Surgeon, VGM Hospital-Institute of Gastroenterology, Coimbatore, Tamilnadu, India 1 sbnbala@gmail.com Abstract— In this paper we enhance the innovative architectural model for context-aware monitoring, BDCaM that uses cloud computing platforms. Every generated context of Ambient Assisted Living (AAL) systems is sent to the cloud. A number of distributed servers in the cloud store and process those contexts to extract required information for decision-making using this novel technique. We develop a 2-step learning methodology. In the first step, the system identifies the correlations between context attributes and the threshold values of vital signs. Using Map Reduce Apriori algorithm, over a long term context data of a particular patient, the system generates a set of association rules that are specific to that patient. In the second step, the system uses supervised learning over a new large set of context data generated using the rules discovered in the first step. In this way, the system becomes more robust to accurately predict any patient situation. We demonstrate the performance and efficiency of BDCaM model in situation classification by implementing a case study. Our system refines patient-specific rules from big data and simplifies the job of healthcare professionals by providing early detection of anomalous situations with good accuracy. The big data producers of BDCaM model are a large number of AAL systems. The low level setup of each system varies according to the requirements of the patient. The sensors, devices and software services of each AAL system produce raw data that contain low level information of a patient’s hea lth status location, activities, surrounding ambient conditions, device status, etc. This paper would promote a lot of research in the area of application of IoT in Ambient Assisted Living. Keywords- Internet of Things, Cloud Computing, Big Data, Ambient Assisted Living, Context Aware Monitoring. I. INTRODUCTION An ambient assisted living (AAL) [1] system consists of heterogeneous sensors and devices whichgenerate huge amounts of patient-specific unstructured raw data every day. Due to diversity of sensors and devices, the captured data also have wide variations. A data element can be from a few bytes of numerical value (e.g. HR = 72 bpm) to several gigabytes of video stream [3][4]. We propose a knowledge discovery-based approach that allows the context-aware system to adapt its behavior in runtime by analyzing large amounts of data generated in ambient assisted living (AAL) systems and stored in cloud repositories. The outcomes of this learning method are then applied in context-aware decision-making processes for the patient. To identify the true abnormal conditions of patients having variations in blood pressure (BP) and heart rate (HR)[5]-[8]. Here we are using FP-Growth algorithm for mining process. The FP-Growth Algorithm [9]-[16] is an efficient and scalable method for mining the complete set of frequent patterns by pattern fragment growth, using an extended prefix-tree structure for storing compressed and crucial information about frequent patterns named frequent-pattern tree (FP-tree). So, we are using FP-Growth algorithm in our concept BD-Cam for using the medical data very efficiently. The rest of the paper is organized as follows: Section 2 describes The Object Oriented Perspective Of Context- Aware Monitoring Systems. Section 3 gives a broad overview of Discussion and Results. Section 4 concludes the paper giving the future research direction. II. THE OBJECT ORIENTED PERSPECTIVE OF CONTEXT-AWARE MONITORING SYSTEMS 2.1 USE CASE DIAGRAM The Context management system [2] collects the raw data and pre-process the data using the data collected from the database and monitors the records in the database. The big data manages all the input data and collects, Pre-process and