Smartdc: Mobility Prediction Based Adaptive Duty Cycling For Everyday Location Monitoring

SMARTDC: MOBILITY PREDICTION BASED ADAPTIVE DUTY CYCLING FOR EVERYDAY LOCATION MONITORING

ABSTRACT:

Monitoring a user’s mobility during daily life is an essential requirement in providing advanced mobile services. While extensive attempts have been made to monitor user mobility, previous work has rarely addressed issues with predictions of temporal behavior in real deployment. In this paper, we introduce SmartDC, a mobility prediction-based adaptive duty cycling scheme to provide contextual information about a user’s mobility: time-resolved places and paths. Unlike previous approaches that focused on minimizing energy consumption for tracking raw coordinates, we propose efficient techniques to maximize the accuracy of monitoring meaningful places with a given energy constraint. SmartDC comprises unsupervised mobility learner, mobility predictor, and Markov decision process-based adaptive duty cycling. SmartDC estimates the regularity of individual mobility and predicts residence time at places to determine efficient sensing schedules. Our experiment results show that SmartDC consumes 81 percent less energy than the periodic sensing schemes, and 87 percent less energy than a scheme employing context-aware sensing, yet it still correctly monitors 90 percent of a user’s location changes within a 160-second delay.

EXISTING SYSTEM:

Mobile phones are widely used for tracing human mobility since mobile phones,

1) have almost 100 percent penetration,

2) are closely tied to daily life, and

3) are capable of locating themselves using various approaches.

The global positioning system (GPS) and wireless positioning system (WPS) using cell tower and Wi-Fi access points (AP) are common technologies that provide a user’s raw coordinates (i.e., latitude and longitude). Ambient fingerprints are often constructed to recognize semantic places with room-level accuracy using radio beacons (e.g., cell towers, Wi-Fi APs, and Bluetooth) and surrounding factors (e.g., light, color, texture, and sound patterns). A simple choice for monitoring mobility is to periodically sense a user’s location context. Such a scheme, however, significantly reduces the battery’s lifetime in mobile devices. To optimize energy consumption for continuous sensing, various approaches have been proposed. These include sensor selection by movement detector using accelerometers minimizing energy consumption within accuracy requirements, minimizing location error for a given energy budget and utilizing a prediction-based approach. While extensive attempts have been made to continuously examine a user’s mobility with less energy consumption, we argue that previous work did not fully consider regular patterns in human mobility to reduce energy consumption in real deployments.

DISADVANTAGES OF EXISTING SYSTEM:

·       It reduces the battery’s lifetime in mobile devices.

·       It periodically senses the users location.

·       GPS is always turned on.

PROBLEM STATEMENT:

A simple choice for monitoring mobility is to periodically sense a user’s location context. Such a scheme, however, significantly reduces the battery’s lifetime in mobile devices.

SCOPE:

The main idea is that the system senses location context based on a predicted schedule. And design a framework to minimize the energy consumption.

PROPOSED SYSTEM:

Our research goal is to develop a framework that continuously provides location context with minimum energy consumption. We propose SmartDC: mobility prediction-based adaptive duty cycling for everyday location monitoring. SmartDC comprises three components: mobility learner, mobility predictor, and adaptive duty cycling. Mobility learner uses unsupervised learning to incrementally collect mobility patterns in colloquial terms. Based on our previous work, we developed a personalized scheme that collects POI’s raw coordinates and also recognizes POIs with room-level accuracy. Mobility predictor uses a location predictor to predict departure time to the next location. We implemented both location-dependent and location-independent predictors, and compared their cost and performance. Adaptive duty cycling uses a Markov decision process (MDP) to determine the efficient sensing moment for a given energy budget. The proposed scheme maximizes the accuracy of mobility monitoring based on the regularity in individual mobility.

ADVANTAGES OF PROPOSED SYSTEM:

·       An extensive performance analysis of several location predictors for the estimation of predictable regularity in human mobility.

·       Provides location context with minimum energy consumption.

·       Simultaneous learning and predicting a user’s mobility.

·       Adaptive duty cycling that covers both the regularity and the randomness in human mobility.

 

 

 

 

SYSTEM ARCHITECTURE:

 

 

 

SYSTEM CONFIGURATION:-

HARDWARE REQUIREMENTS:-

ü Processor                  -        Pentium –IV

ü Speed                        -        1.1 Ghz

ü RAM                         -        512 MB(min)

ü Hard Disk                 -        40 GB

ü Key Board                -        Standard Windows Keyboard

ü Mouse                       -        Two or Three Button Mouse

ü Monitor                     -        LCD/LED

SOFTWARE REQUIREMENTS:

•         Operating system :         Android

•         Coding Language :         Android

•         Data Base             :         SQLite

•         Tool                     :         Eclipse

REFERENCE:

Yohan Chon, Elmurod Talipov, Hyojeong Shin, and Hojung Cha “SmartDC: Mobility Prediction-Based Adaptive Duty Cycling for Everyday Location Monitoring” IEEE TRANSACTIONS ON MOBILE COMPUTING, VOL. 13, NO. 3, MARCH 2014.