+ All Categories
Home > Documents > Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed...

Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed...

Date post: 20-Jan-2016
Category:
Upload: stuart-weaver
View: 213 times
Download: 1 times
Share this document with a friend
Popular Tags:
26
Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi
Transcript
Page 1: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Design, Implementation and Evaluation of CenceMe Application

COSC7388 – Advanced Distributed Computing

Presentation By

Sushil Joshi

Page 2: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Outline Introduction

Architectural Design

Limitations

Split level classification

Architectural Diagram

Classifier

Phone Classifier

Backend Classifier

Performance

Power and Memory Benchmark

Experimental Deployment and feedback

Page 3: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Introduction

Mobile application that infers personal presence and updates the status to social networks.

Sensor devices like microphone, accelerometer, GPS, camera and bluetooth inbuilt in Nokia N95.

An always-on application needs to use energy in as efficient way as possible.

Page 4: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Introduction

Sense Learn Share

Information and process flow in CenseMe System

Page 5: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Introduction

Realizing vision of automatic updates to social networks.

Enablers – Integration of sensors to consumer mobile devices.

Vision about bluetooth enabled cellphone talking to

• Other devices attached in running shoes, BlueCell dongle

• Attached to other user

• Sensor available in town ecosystem like carbon-dioxide or pollen sensors.

Page 6: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Nokia N800, N95, Nokia 5500, Tmote Mini, BlueCell Dongle.

Page 7: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.
Page 8: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Architectural Design (Limitations)

Symbian OS Exception handlers

API limitations – e.g. Missing JME API to access N95 internal accelerometer

Security Limitations

Energy Management Limitations

Page 9: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Architectural Design (Split level Classification)

Page 10: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Architectural Design (Split Level Classification)

Advantages

Minimizes sensor data that needs to be uploaded

Resiliency when Radio/WiFi dropout by buffering and batching primitives

Minimizes sensor data that needs to be uploaded thus saving energy that would be used up.

Page 11: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Architectural Diagram (Phone Software)

Page 12: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Architectural Diagram (Backend)

Page 13: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Classifier (Phone Classifier)

DFT of human voice sample registered by Nokia N95 microphone

DFT of audio sample from noisy environment as registered by Nokia N95 microphone

Page 14: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Classifier (Phone Classifier)

Discriminant analysis clustering which determines the dashed lines (threshold between talking and non-talking)

Page 15: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Classifier (Phone Classifier)

Data collected by Nokia N95 on-board accelerometer for different activities like sitting and walking.

Page 16: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Classifier (Backend Classifier)

Rolling window of size N=5 used by conversation classifier

Assymetric strategy

P1 P2 P3 P4 P5

p1 p2 p3 p4 p5

Conversation

No Conversation

Primitive indicates voice

Primitive indicates no voice

Page 17: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Classifier (Backend Classifier)

Social Context classifier

Mobility Mode Detector

Location Classifier

Historical trend of user data to identify behaviorial pattern. e.g. Nerdy, party animal, health conscious.

Page 18: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Performance

Table 2 indicates false positives which could be attributed to either sensors grasping human voice from background or due to assymetric strategy for conversation classification.

Page 19: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Performance

Conversation classifier accuracy in different ambience

Page 20: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Performance

Conversation Classifier accuracy with varying duty cycle

Page 21: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Performance

Accuracy of activity classification vs different positioning of mobile phone

Page 22: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Power, Memory and CPU Usages

Power consumption during sampling/upload interval

Page 23: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Power, Memory and CPU Usages

Screen saver mode turned on while using Nokia Energy Profiler so as to decouple energy used to light up the LCD screen.

Page 24: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Feedback From Experimental Deployment

More likely to be used by population who already use social networking.

Far less deletion of random images compared to uploads.

Location feature mostly used.

Can reveal lifestyle trends e.g less physical activity

Page 25: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Questions

?

Page 26: Design, Implementation and Evaluation of CenceMe Application COSC7388 – Advanced Distributed Computing Presentation By Sushil Joshi.

Reference

[1]Miluzzo, Emiliano, Lane, Nicholas D., Fodor, Krist\'of, sPeterson, Ronald, Lu, Hong, Musolesi, Mirco, Eisenman, Shane B., Zheng, Xiao, Campbell, Andrew T., Sensing meets mobile social networks: the design, implementation and evaluation of the CenceMe application, SenSys '08: Proceedings of the 6th ACM conference on Embedded network sensor systems, pp. 337--350, ACM, New York, NY, USA, 2008.

[2] Emiliano Miluzzo, Nicholas D. Lane, Shane B. Eisenman, and Andrew T. Campbell, CenceMe – Injecting Sensing Presence into Social Networking Applications


Recommended