Personalized Sensin System

12
PERSONALIZED SENSING SYSTEM Macaba Pedro MsThesis 2014 Leader Teacher: Paulo Mendes Mestrado em Engenharia Informática e Sistemas de Informação

Transcript of Personalized Sensin System

Page 1: Personalized Sensin System

http://copelabs.ulusofona.pt

PERSONALIZED SENSING SYSTEM

Macaba Pedro

MsThesis – 2014

Leader Teacher: Paulo Mendes

Mestrado em Engenharia Informática e Sistemas de Informação

Page 2: Personalized Sensin System

Overview

Introduction

Theme, Importance, Impact

Objectives

PersonalSense Framework

Tagging Module

Sensing Module

Inference Module

Networking Interface

Graphical Interface

Tests and Evaluation

Final Considerations 2 Macaba Pedro - MEISI ECATI - ULHT 2014

Page 3: Personalized Sensin System

Personalized Sensing System

3

Introduction Theme, Importance and Impact

Study the capacity to perform classification of sensory data from mobile devices, providing

information based on the user behavior and the state of the device.

Impact in mechanisms of transfer

and data sharing;

Concept of searching for data to

meet user;

Learning user behavior based in

mobile sensory data;

Pervasive and Ubiquitous

Computing.

Large-scale, long-lived, mostly

mobile

Not so energy-constrained

Mobility is a driving factor

Security, trust and privacy are

important factors

Connection with emerging

applications;

Sharing data based in users

interests;

Information be available in the

network automatically without user

interaction;

Sensing people behavior;

Sensing proximity interactions;

Page 4: Personalized Sensin System

Develop an middleware

capable to analyze sensory

data from mobile devices,

implementing techniques for

data classification (Sensing

Application) whose learning

will enable the transmission of

inferred information for network

sharing (Networking

Application) based on user’s

behaviors and device state

(Data Tagging)

4

Objective

Macaba Pedro - MEISI ECATI - ULHT 2014

Page 5: Personalized Sensin System

Middleware activation

Device configuration

Reading sensory data and

classification process

Learning process on the

inferred data

Device state sent to the

network

5

PersonalSense Framework

Macaba Pedro - MEISI ECATI - ULHT 2014

Page 6: Personalized Sensin System

6

Tagging Module

Macaba Pedro - MEISI ECATI - ULHT 2014

State

Events

Data Type

Interest

Page 7: Personalized Sensin System

Sensing Module

Maestro provide local sensors data

PersonalSense verifies the data file

Implement the classification process

Analyze sensors

Choose the best attribute

Build the Decision Tree

7

Page 8: Personalized Sensin System

Inference Module

Procedural Rules

Forward chaining

An action is executed when

conditions are satisfied.

Assign values to attributes

Evaluate conditions

Check if all conditions are

satisfied

Supervised Learning

Predictive Modules

8

Method – PersonalSense

Attributes assign

values - defined

Conditions evaluated

Rules are checked

Actions executed

Method – PersonalSense

A Counter to each rule to detect the

action

Use the action to keep track how many

condition in the rule are currently

satisfied

The rule is ready to fire if all conditions

have become true

The attribute is flagged as defined and

undefined

Gain information model

Value 3

Without Value 0

Value 2

Without Value 0

Value 1

Without Value 0

Result?

Dependent Variable: value

FALSE TRUE

Page 9: Personalized Sensin System

Networking Interface

Data-Centric Characteristics

Seeks to adapt the network architecture to the

current network usage patterns

has a founding principle that a communication

network should allow a user to focus on the data

rather than having to reference a specific, physical

location where that data is to be retrieved from.

Security into the network at the data level

The name of content sufficiently describes the

information

PersonalSense in Data Centric Networking

Focus on data treatment

Receive data and sent data to an application

User behavior to receive some kind of data

Use a data storage cache at each level of the

network

Decrease the transmission traffic

Increase the speed of response

Allows a simpler configuration of network devices

9 Macaba Pedro - MEISI ECATI - ULHT 2014

(Smart Pin, 2009)

Page 10: Personalized Sensin System

Graphical Interface

Configuration Interface

https://www.youtube.com/watch?v=mq_8ycNg160

10

(Smart Pin, 2009)

Utilization Interface

https://www.youtube.com/watch?

v=hQyGl3l7kyY

Page 11: Personalized Sensin System

Final Considerations

Service integration and

communication

Automatic provision of

information in the network

relying in opportunistics

meetings between devices

Classification of data

collected from the sensory

capabilities of devices, and

knowledge acquisition and

generation of behavioral

profiles

11

(Smart Pin, 2009)

Test more mobile sensors

Test the interaction with

Maestroo and ICON in a

mobile device

Test with other classifier

algorithms

Elaboration of an

algorithm for classification

of collected sensor data

from mobile devices

Page 12: Personalized Sensin System

12

Macaba Pedro - MEISI ECATI -

ULHT 2014