A service for showing real-time busyness of locations

Slides:



Advertisements
Similar presentations
Performance Testing - Kanwalpreet Singh.
Advertisements

BreadCrumbs: Forecasting Mobile Connectivity Anthony Nicholson and Brian Noble University of Michigan Presented by: Scott Winkleman.
Networking Some of the basics. What is a Network Simply put, its two or more computer connected together through a communication medium. A communication.
Blue Tears Project Bluetooth Tracking: Distributed Information Systems.
An Introduction to Cloud Computing. The challenge Add new services for your users quickly and cost effectively.
ROOT: A Data Mining Tool from CERN Arun Tripathi and Ravi Kumar 2008 CAS Ratemaking Seminar on Ratemaking 17 March 2008 Cambridge, Massachusetts.
Google PowerMeter. Overview Google PowerMeter is a new application from Google that allows users to observe the power usage in their environment shown.
M i SMob i S Mob i Store - Mobile i nternet File Storage Platform Chetna Kaur.
Enhancing the Security of Corporate Wi-Fi Networks using DAIR PRESENTED BY SRAVANI KAMBAM 1.
NEARBY: HYBRID NETWORK MOBILE APPLICATION Shuai Zhang, Ziwen Zhang, Jikai Yin.
COMP 410 Update. The Problems Story Time! Describe the Hurricane Problem Do this with pictures, lots of people, a hurricane, trucks, medicine all disconnected.
Enter Dept name in Title Master Wait Watcher Midway Design Review Alexander Gutowski Mat Barros Steve Mitchell Advisor: Professor Gong.
Cloud Computing Characteristics A service provided by large internet-based specialised data centres that offers storage, processing and computer resources.
BASIC CONCEPTS OF COMPUTING.  What is a computer? What is a computer?  An expanded model of a computer An expanded model of a computer  The role of.
Ran aware flow control tool
Implementing a Sentient Computing System Presented by: Jing Lin, Vishal Kudchadkar, Apurva Shah.
Julien Freudiger, PARC (A Xerox Company)
MIS 105 LECTURE 1 INTRODUCTION TO COMPUTER HARDWARE CHAPTER REFERENCE- CHP. 1.
1 Database Management Systems (DBMS). 2 Database Management Systems (DBMS) n Overview of: ä Database Management Components ä Database Systems Architecture.
Human Tracking System Using DFP in Wireless Environment 3 rd - Review Batch-09 Project Guide Project Members Mrs.G.Sharmila V.Karunya ( ) AP/CSE.
1 © 2003, Cisco Systems, Inc. All rights reserved. CCNA 3 v3.0 Module 9 Virtual Trunking Protocol.
What is it? CLOUD COMPUTING.  Connects to the cloud via the Internet  Does computing tasks, or  Runs applications, or  Stores Data THE AVERAGE CLOUD.
FCM Workflow using GCM.
Internet of Things. IoT Novel paradigm – Rapidly gaining ground in the wireless scenario Basic idea – Pervasive presence around us a variety of things.
Confidential, Copyright and Patent Pending, Ping4 Group, Inc. 1 Investor Summary Investor Summary.
A Review of ALNBench by Dendronic Systems Inc. Bruce Matichuk Shengjiu Wang.
Introduction to Cloud Computing What is cloud? Use of computing resources (hardware and software) that are delivered as a service over a network Why cloud.
Data-Centric Systems Lab. A Virtual Cloud Computing Provider for Mobile Devices Gonzalo Huerta-Canepa presenter 김영진.
Thepul Ginige Lecture-5 Implementation of Information System Part - I Thepul Ginige.
Final Presentation Smart-Home Smart-Switch using Arduino
CHAPTER -II NETWORKING COMPONENTS CPIS 371 Computer Network 1 (Updated on 3/11/2013)
BYOD Technical workshop Simon Bright - E2BN Philip Pearce – E2BN.
An Introduction to SaaS and Cloud Computing Ross Cooney.
Virtual Local Area Networks In Security By Mark Reed.
SPIN: Sensor Protocols for Information via Negotiation
WHY VIDEO SURVELLIANCE
Introduction to Operating Systems
Security service management of tomorrow
HELLO WORLD!!! Run Project 2: WELCOME Subject: Virtual LAN’s
The Client-Server Model
The Internet and Its Uses
Technology What’s Here and What’s Coming.
Microsoft office setup tech support
An Introduction to Cloud Computing
Crowd Density Estimation for Public Transport Vehicles
System Architecture & Hardware Configurations
UNIT 4 – THE COST OF FREE LESSON 4.
Introduction to Computers
Computer Basics Section 2.1 YOU WILL LEARN TO… Identify hardware
2018 CODE-IT CATEGORY .
Know How Wifi Installation Services can help us in Vari ous Ways
Elinar Ai Miner powered by IBM watson.
Introduction to Operating Systems
به نام خدا Big Data and a New Look at Communication Networks Babak Khalaj Sharif University of Technology Department of Electrical Engineering.
Lecture-5 Implementation of Information System Part - I Thepul Ginige
DATABASE SYSTEM UNIT I.
Understanding Your Numbers: Data Visualisation with PowerBI
Network Hardware – LO’s
Network Models, Hardware, Protocols and number systems
Computer communications
“Location Privacy Protection for Smartphone Users”
UNIT 4 – THE COST OF FREE LESSON 6.
WHY VIDEO SURVELLIANCE
DRC Central Office Services
Nir Zaidman and Michael Tahar
WJEC GCSE Computer Science
Ecology, Environment, Climate Change and Disaster Management
LAN Addresses and ARP IP address: drives the packet to destination network LAN (or MAC or Physical) address: drives the packet to the destination node’s.
Department of Engineering Science EE 465 (CES 440) - Intro
Presentation transcript:

A service for showing real-time busyness of locations CrowdFlow A service for showing real-time busyness of locations CrowdFlow Service/App that shows the real-time busyness of locations

Main Idea App shows users live wait-times and future busyness Free flow of information is good (economics 101) Users will save time More distributed stress on services Inexpensive to set up (<$15 per location, one-time cost) Main idea: tell the user how much they are going to wait Economics, free flow of information is good for growing the economy because people can make better decisions You want a coffee, app will tell you, Starbucks is 15 min, Tim Hortons is 5 min. You’re going to save 10 min of time. This scales really well, if everyone uses the app, everyone can save 10 minutes. Distributes the stress on a system, it can distribute people to different locations, and to different times. (Come back later, see graph) The service costs about $15 to set up

The App User sees: Updates every 60 seconds Basic indication of busyness People in vicinity People in line (if applicable) Wait time (if applicable) Chart with predicted data Updates every 60 seconds Web interface, accessible from any device Here’s what the app looks like (also shows graphs) Data can update every 60 seconds, but there are ways of shortening that Accessible from any device

Applying the system at UBC 40+ food service locations run by UBC Students will choose to eat at least busy location, and at the least busy time Distributes the load over time and over locations Shorter lineups overall, more students going to eat Idea: install this system at UBC and see what the changes are Have several controls and several experiments Release at the start of September

The “Nodes” Small, low power USB devices Can be installed in any outlet using a USB adapter Total cost to make: $15 Require access to ubcvisitor network to function (to upload data) Need to be placed near the line- up Service requires a node Be places at every location you want to monitor Really cheap, needs WIFI.

User Interface Neural Net 1 7 4 Neural Net 2 3 Node Web API ANN Service 1 5 Neural Net 2 2 6 How is works: You need a node, piece of hardware that tracks “probe requests”. System uses a web API, stores the data in a DB, then sends if to a ANN to be analyzed Database Neural Net 3

Why CrowdFlow’s Technology Advantages Disadvantages CrowdFlow Tracking probe requests with nodes Cheap. Very scalable. Transparent system. Not as accurate as other methods. Monitoring router connections Slightly more accurate than probe requests. Very expensive to set up. Not worth it to expand to small businesses. Tracking mobile devices Can track users no matter where they are. Requires large initial userbase. Not transparent to users. Huge privacy risk.

Privacy Concerns Nodes rely on probe requests, which are broadcasted publicly Nodes cannot access or intercept data other than probe requests Probe requests contain a MAC address (unique identifier), MAC addresses are stripped before transmission. No personal information is ever stored. Even if system was compromised, no personal information could be extracted.

Neural Network Analysis CrowdFlow uses an Artificial Neural Network to predict how many people are around and what the lineup is like. Needs to be “trained” by processing lots of data and having a person make observations from nearby Raw data is summarized (mean, std_dev, skewness, etc..), then fed into system Accurate given enough data

New Invention? Papers have been written on location tracking using probe requests (triangulation) Possibly a new application of existing technologies: WiFi probe request tracking for lineup display Not sure if patent is possible Regardless, would like to launch pilot program very soon Full launch in September

Commercialization Advertisements Charge Businesses API Calls Place an advertisement on the interface Higher PPC because of return users Charge Businesses Setup cost is very low Reoccurring cost is even lower Can charge $100/year and provide statistics API Calls A service like Yelp or Google Maps would like real-time data Sell access to data, charge $1/100 calls

The End