Da Data Science and It Its Applications in Smart Cities Mohadeseh - - PowerPoint PPT Presentation
Da Data Science and It Its Applications in Smart Cities Mohadeseh Ganji, Senior Data Scientist, Research fellow 15 Nov 2017 About me Currently, I am a post-doctoral research fellow at University of Melbourne Mohadeseh.ganji@unimelb.edu.au
15 Nov 2017
Pixabay free illustrations
1+1
Mohadeseh.ganji@unimelb.edu.au
3.8+ billion people on
the Web
30+ billion RFID
tags
4.6 billion
camera phones world wide
100s of millions
devices sold annually
200 million smart
meters
12+ TBs
every day
25+ TBs of
log data every day
? TBs of
data every day
6.5 PB of user data 50 TB/day
3.5 billions of search query every day 100 hours of video uploads per minutes
World Economic Forum
Connected Devices Lab
Connected Devices Lab
Chris Anderson
Drew Conway’s Venn diagram
Data science algorithms that describe data and provide insight A Collection
Patterns / Insights Descriptive Algorithms
Data science algorithms that make predictions
Descriptive and Predictive Algorithms Social Media Text Images Video Geospatial Data Meters Data Sensors Data Patterns / Insight / Recommendations / Actions GPS Data
15
IBM inforgraphic
Deep Learning Machine Learning Artificial Intelligence Data Science
Free vector graphics on Pixabay
Optimize traffic flow using traffic signals, the number of vehicles and pedestrians; Recognize traffic patterns by analysing the data Better utilization of parking space Monitoring of parking spaces availability in the city.
Implementing smart traffic light and signals designed by the Traffic21 project in Pittsburgh, Pennsylvania, USA reduced traffic jams and waiting times and resulted in reduced emissions by over 20%
Reduce road congestions by predicting traffic conditions and adjusting traffic controls, alternative roads or informing commuters
Travel time prediction using Bluetooth data and information on traffic situation Pedestrian behaviour analysis In different traffic situation, weather, etc. Crossing behaviour Transport infrastructure maintenance analysis
Communicate to drivers using on- vehicle devices to inform them about traffic situation or to take action to alleviate the problem. Traffic accident prediction (crash frequency and crash severity) Better public transportation planning using the tap-in tap-out data Optimize traffic flow using traffic signals, the number of vehicles and pedestrians; Recognize traffic patterns by analysing the data Better utilization of parking space Monitoring of parking spaces availability in the city. Reduce road congestions by predicting traffic conditions and adjusting traffic controls, alternative roads or informing commuters
Road network resilience, traffic demand prediction during disaster ( e.g. flash floods and bush fires)
Predict future environmental changes or natural disasters Using historical data, spatial temporal data, satellite information etc. Natural hazard management using social network data generated by citizens and first responders, spatial temporal data, satellite images of the affected areas, flood maps generated by drones. Manage information flow in disaster social media mining and information dissemination during disasters. Monitoring, analyzing and identifying the risks vibrations and material conditions data in buildings, bridges and historical monuments along with data from from weather forecasts, geologic surveys, maintenance reports, video feeds to detect unusual patterns, identify red-light situations and create a clearer picture of risk Track resources. Data analytics can help map the locations of critical resources like ambulances and medical facilities. Prioritize urgent sites and situations. Responders want up-to-date intelligence about survivors' locations and available resources. Data analytics shows these kinds of details. Actual mapping applications are emerging that can prioritize which zones need attention first, all based on what users post during a crisis.
Smart grid
from sensors and meters on production, transmission, distribution systems and consumer access points.
between producers and consumer
Total potential value generated in the United States from a fully deployed smart grid reaching as high as $130
billion annually by 2019.
McKinsey on Smart Grid
Smart grid
from sensors and meters on production, transmission, distribution systems and consumer access points.
between producers and consumer Demand forecasting capacity planning, demand- response modelling and power distribution Smart Buildings: Optimize building electricity usage with motion sensor lights which can dim or shut off when a room is empty; Alert when there is a leaking pipe using smart meters; monitor energy use of an electric meter and alert when it reaches a specific threshold Network Reliability prevent power outages, interruptions and quality issues
Load Modeling: Understanding the behaviour
in different situations Smart Pricing based on demand and supply data Accident prevention Smart monitoring the infrastructure and analyse the data
Resource scheduling based on demand prediction, Medical staff, equipment, ambulances,…
Patient profiling Smart gathering, analyzing and utilizing
Smart health monitoring devices Smart monitoring of blood sugar, blood pressure, sleep patterns for accurate and timely responses to health issues Health Economics: performance- based pricing plans based on real- world patient outcomes data to arrive at fair economic compensation Identify at risk patients: Based
the patient profile, Monitor, analyze and flag potential health issues to identify who would benefit from proactive care or lifestyle change Better statistical tools and algorithms to improve clinical trial design Patient stay and treatment
prediction to study patient characteristics and the cost and outcomes of treatments Personalized medicine: understanding genetic variation and individual treatment response Analyzing disease patterns: analyzing disease patterns, trends and spread patterns for prevention and make strategic decisions Medical decision support systems: Diagnosing and treatment
Healthcare Analytics/Medical Analytics Market is expected to reach around 18.7 Billion USD by 2020 at a CAGR of 26.5% from 2015 to 2020.
www.marketwatch.com
Resource scheduling based on demand prediction, Medical staff, equipment, ambulances,…
Patient profiling Smart gathering, analyzing and utilizing
Smart health monitoring devices Smart monitoring of blood sugar, blood pressure, sleep patterns for accurate and timely responses to health issues Health Economics: performance- based pricing plans based on real- world patient outcomes data to arrive at fair economic compensation Identify at risk patients: Based
the patient profile, Monitor, analyze and flag potential health issues to identify who would benefit from proactive care or lifestyle change Better statistical tools and algorithms to improve clinical trial design Patient stay and treatment
prediction to study patient characteristics and the cost and outcomes of treatments Personalized medicine: understanding genetic variation and individual treatment response Analyzing disease patterns: analyzing disease patterns, trends and spread patterns for prevention and make strategic decisions Medical decision support systems: Diagnosing and treatment
Get real time feedback on campaigns, events, etc Sentiment analysis on peoples satisfaction using their social media posts Provide real-time city event info; leverage GPS locations and combine with the user profiles for personalized event recommendation
Identify and prioritize urgent sites and situations during natural disasters. Actual mapping applications are emerging that can prioritize which zones need attention first, all based on what users post during a crisis. Identify the key concerns of people in a proximate location area and analyse the patterns
Identify social media influencers And their impact on news spread and promoting social good Better costumer engagement Profiling based on their interests, concerns, location, etc
Chris Anderson Artificial Intelligence
Chris Anderson Artificial Intelligence
Chris Anderson Artificial Intelligence
Artificial Intelligence
Mohadeseh.ganji@unimelb.edu.au