Gary M. Weiss and Jeffrey Lockhart Fordham University, New York, NY 1UbiMI UBICOMP Sept. 8 2012.

Slides:



Advertisements
Similar presentations
Gary M. Weiss Professor and Chair Dept. of Computer & Info. Science Fordham University or wisdmproject.com.
Advertisements

Lecture 11: Operating System Services. What is an Operating System? An operating system is an event driven program which acts as an interface between.
* Fordham University Department of Computer and Information Science ** Healthy Pet Technologies WagTag  : A Dog Collar Accessory for Monitoring Canine.
FindAll: A Local Search Engine for Mobile Phones Aruna Balasubramanian University of Washington.
CS 495 Application Development for Smart Devices Mobile Crowdsensing Current State and Future Challenges Mobile Crowdsensing. Overview of Crowdsensing.
Panoptes: A Scalable Architecture for Video Sensor Networking Applications Wu-chi Feng, Brian Code, Ed Kaiser, Mike Shea, Wu-chang Feng (OGI: The Oregon.
ManageEngine TM Applications Manager 8 Monitoring Custom Applications.
Technical Architectures
Slide 1 Written by Dr Caspar Ryan, Project Leader ATcrc project 1.2 What is MobJeX? Next Generation Java Application Framework providing transparent component.
Introduction to Networking & Telecommunications School of Business Eastern Illinois University © Abdou Illia, Spring 2007 (Week 1, Tuesday 1/9/2007)
Brent Dingle Marco A. Morales Texas A&M University, Spring 2002
Lesson 11-Virtual Private Networks. Overview Define Virtual Private Networks (VPNs). Deploy User VPNs. Deploy Site VPNs. Understand standard VPN techniques.
J2ME Prepared by: - Gaery- Ronny - Alan- Andy. Why Technology for Mobile Devices? The nature of wireless devices is changing Old devices: All the software.
WebMiningResearch ASurvey Web Mining Research: A Survey By Raymond Kosala & Hendrik Blockeel, Katholieke Universitat Leuven, July 2000 Presented 4/18/2002.
A Framework for Patient Monitoring A. L. Praveen Aroul, William Walker, Dinesh Bhatia Department of Electrical Engineering University of Texas at Dallas.
Basic Computer Networks Configurations School of Business Eastern Illinois University © Abdou Illia, Spring 2007 Week 1, Thursday 1/10/2007)
What is adaptive web technology?  There is an increasingly large demand for software systems which are able to operate effectively in dynamic environments.
Mgt 240 Lecture Website Construction: Software and Language Alternatives March 29, 2005.
Web-Enabling the Warehouse Chapter 16. Benefits of Web-Enabling a Data Warehouse Better-informed decision making Lower costs of deployment and management.
SPRING 2011 CLOUD COMPUTING Cloud Computing San José State University Computer Architecture (CS 147) Professor Sin-Min Lee Presentation by Vladimir Serdyukov.
New Challenges in Cloud Datacenter Monitoring and Management
Iridium WOCE/SVP/BP Buoy METOCEAN WOCE/SVP/BP/Iridium By Bernie Petolas, P. Eng. Product Manager METOCEAN Data Systems Ltd. Dartmouth NS B3B 1R9 Canada.
Duncan Fraiser, Adam Gambrell, Lisa Schalk, Emily Williams
1 Energy Efficient Communication in Wireless Sensor Networks Yingyue Xu 8/14/2015.
Mobile Sensor Application Group 4. Introduction Modern smartphones are often equipped with quite a large number of sensors. The sensors data can be used.
RMax – Report Maximizer. Report Designer to design your own reports in Excel / HTML Define user specific interfaces to extract data from your ERP Define.
Development in Mobile Technologies Mobile Technology is a collective term used to describe the various types of cellular communication technology.
Gary M. Weiss Fordham University
ResourceFull Authors: Matt Kaye (EE ‘12) Nitin Puri (SSE ‘12) Advisor: Dr. Alejandro Ribeiro Special Thanks.
Methods of communication
P2P Systems Meet Mobile Computing A Community-Oriented Software Infrastructure for Mobile Social Applications Cristian Borcea *, Adriana Iamnitchi + *
Gary M. Weiss Comp & Info Science Dept Fordham University or wisdmproject.com.
Web Based Applications
Presented by Amira Ahmed El-Sharkawy Ibrahim.  There are six of eight turtle species in Ontario are listed as endangered, threatened or of special concern.
1 NETE4631 Mobile Cloud Computing Lecture Notes #10.
July 25, 2010 SensorKDD Activity Recognition Using Cell Phone Accelerometers Jennifer Kwapisz, Gary Weiss, Samuel Moore Department of Computer &
September Activity Recognition and Biometric Identification Using Cell Phone Accelerometers WISDM Project Department of Computer & Info. Science.
TRANSFORMING IT.  The cloud is a group of servers.  A user interacts with the cloud without worrying about how it is implemented. Cloud computing describes.
Tufts Wireless Laboratory School Of Engineering Tufts University “Network QoS Management in Cyber-Physical Systems” Nicole Ng 9/16/20151 by Feng Xia, Longhua.
MARS: A Muscle Activity Recognition System Enabling Self-configuring Musculoskeletal Sensor Networks IPSN 2013 NSLab study group 2013/06/17 Presented by:
Presented by: Marcela D. Rodríguez CICESE/UABC, Ensenada, México 1st International Workshop on Ubiquitous Mobile Instrumentation.
SCADA. 3-Oct-15 Contents.. Introduction Hardware Architecture Software Architecture Functionality Conclusion References.
Presented By: Lauren Ball April 27, 2011 EEL 6788 Project Presentation.
Implementing a Sentient Computing System Presented by: Jing Lin, Vishal Kudchadkar, Apurva Shah.
Linked-data and the Internet of Things Payam Barnaghi Centre for Communication Systems Research University of Surrey March 2012.
Computer Emergency Notification System (CENS)
Page 1 Alliver™ Page 2 Scenario Users Contents Properties Contexts Tags Users Context Listener Set of contents Service Reasoner GPS Navigator.
TeraPaths TeraPaths: Establishing End-to-End QoS Paths through L2 and L3 WAN Connections Presented by Presented by Dimitrios Katramatos, BNL Dimitrios.
Presenter: D. Jayasakthi Advisor: Dr. Kai-Wei ke.
CONTENT DELIVERY NETWORKS
Case Study.  Client needed to build data collection agents for various mobile platform  This needs to be integrated with the existing J2ee server 
Model View Controller MVC Web Software Architecture.
Management Information Systems, 4 th Edition 1 Chapter 8 Data and Knowledge Management.
SATIRE: A Software Architecture for Smart AtTIRE R. Ganti, P. Jayachandran, T. F. Abdelzaher, J. A. Stankovic (Presented by Linda Deng)
The Benefits of Indigo SMS Aumne, Inc. Tel: Fax: Commerce Ct Suite 200, Lisle, IL USA.
Internet of Things. IoT Novel paradigm – Rapidly gaining ground in the wireless scenario Basic idea – Pervasive presence around us a variety of things.
CLOUD COMPUTING FOR MOBILE USERS: CAN OFFLOADING COMPUTATION SAVE ENERGY? Karthik Kumar and Yung-Hsiang Lu, Purdue University IEEE Software, 2010.
Monas MS is a software suite designed for displaying, processing and storing messages received in the centralized security and monitoring stations. Software.
Efficient Opportunistic Sensing using Mobile Collaborative Platform MOSDEN.
TRACE ANALYSIS AND MINING FOR SMART CITIES By G. Pan Zhejiang Univ., Hangzhou, China G. Qi ; W. Zhang ; S. Li ; Z. Wu ; L. T. Yang.
Introduction to Mobile-Cloud Computing. What is Mobile Cloud Computing? an infrastructure where both the data storage and processing happen outside of.
Mobile Activity Recognition
Weikuan Yu, Hui Cao, and Vineet Mittal The Ohio State University
System Architecture & Hardware Configurations
Mobile Sensor-Based Biometrics Using Common Daily Activities
Basic Computer Networks Configurations
Scalable, distributed database system built on multicore systems
Course Project Topics for CSE5469
WISDM Activity Recognition & Biometrics Applications of Classification
Activity Recognition Classification in Action
Presentation transcript:

Gary M. Weiss and Jeffrey Lockhart Fordham University, New York, NY 1UbiMI UBICOMP Sept

 Mobile sensors becoming ubiquitous  Especially via smartphones  Various architectures are possible ranging from “smart client” to “dumb client”  Each architecture has pros and cons  Worthwhile to enumerate and compare alternative architectures 2UbiMI UBICOMP Sept

1. Sensor Collection 2. Data Processing and Transformation 3. Decision Analysis/Model Application 4. Data and Knowledge Reporting Learning/model generation Only step 1 is required 3UbiMI UBICOMP Sept

 Main focus of WISDM lab  Monitors smartphone accelerometer and uses the data to perform activity recognition  Activities: walk, jog, stairs, sit, stand, lie down  Results available via the Web 4UbiMI UBICOMP Sept

 Sensor Collection:  Actitracker client collects raw accelerometer data for 3 axes 20 times per second and transmits to server  Data Processing and Transformation  Every 10 sec. server aggregates raw samples into a single example described by several dozen features  Decision Analysis/Model Application  Server applies predictive model to examples; activity classified and saved to database  Data and Knowledge Reporting  User queries server DB any time via web interface 5UbiMI UBICOMP Sept

Client Configurations Responsibility CC-1 Dumb CC-2CC-3CC-4 Smart 1Sensor Collection 2Data Transformation 3Model Application 4Reporting Model Generation?? 6UbiMI UBICOMP Sept

 Mobile devices have CPU power to build models  Only makes sense to build a model on the client device if will apply it on the client  Thus model construction on device only for CC-3 or CC-4  In CC-1 and CC-2 either model hardcoded into client or downloaded from server  Data mining not always required  Can be done dynamically (on client or server) or statically  Our research shows dynamically generated personal models outperform general (impersonal) models 1 7UbiMI UBICOMP Sept Gary M. Weiss and Jeffrey W. Lockhart. The Impact of Personalization on Smartphone-Based Activity Recognition, Papers from the AAAI-12 Workshop on Activity Context Representation: Techniques and Languages, AAAI Technical Report WS-12-05, Toronto, Canada,

 Resource usage  battery, CPU, memory, transmission bandwidth  Scalability  Support for many mobile devices  Access to data  Researchers and others may want raw data  Transformed data loses information ▪ With raw data can alter features for data mining and regenerate results UbiMI UBICOMP Sept

 Privacy/Security  Users will want to keep data secure and/or private  User Interface  Users want aesthetics (screen size) & accessibility  Crowdsourcing  Some applications will require a central server in order to aggregate data from multiple users/devices ▪ Navigation software that tracks traffic UbiMI UBICOMP Sept

 Resource Usage  Unclear. Resource usage minimized except heaviest use of transmission bandwidth (power drain)  Scalability  Poor since maximizes server work  Actitracker’s server can handle 942 simult. users  Access to Data  Best since all raw data can be preserved on server ▪ But Actitracker requires 791 MB/month per user. UbiMI UBICOMP Sept

 Privacy/Security:  Poor: The more data sent the greater the risk  User Interface:  Good: data and results on server and can be viewed over Internet  Crowdsourcing  Best: All data available on server UbiMI UBICOMP Sept

 Similar to CC-1 except:  Less data to transmit so bandwidth/energy savings ▪ For Actitracker 95% reduction in data ▪ But more processing which takes up CPU and power  More scalable (less server work)  Less access to data (raw data not available)  Slight improvement in privacy/security (no raw data)  Minimal impact on user interface (results still on server)  Crowdsourcing only on aggregated data UbiMI UBICOMP Sept

 Resource usage:  more processing on the client (more CPU and power); but only need to transmit results  Much more scalable: server only collects results  Access to data: only results available  Much improved security/privacy  results may not be nearly as sensitive  Can still view results via web-based interface  Can only crowdsource on results UbiMI UBICOMP Sept

 About same as CC-3  not sending results saves little power  Perfectly scalable: no server  No access to data  Good security/privacy: nothing leaves device  Can only view results on the device  Not accessible from other places and small screens  Cannot even crowdsource results UbiMI UBICOMP Sept

 Resource usage: unclear  Scalability: smart client best  Access to data: dumb client best  Security/Privacy: smart client best  User Interface:smart client worst  Centralized Data:dumb client best  One approach: support multiple architectures  approach taken by our research group UbiMI UBICOMP Sept

 Go to wisdmproject.com  Actitracker should be ready for beta in 1 month  Actitracker.com  Papers available from:   My contact info:  UbiMI UBICOMP Sept