SlideShare a Scribd company logo
Bringing IoT Data to Life! 
Date Dr. Joachim Schaper, 
VP Research
2 
The Potential…and Challenges…of IoT Data
DATA 
REAL 
TIME 
VAST 
AMOUNTS 
REAL WORLD 
HETEROGENEOUS 
NOISY
sense 
How do we make of IoT data?
I 
T 
A 
An IoT Analytics Platform
6 
IoTA: Analytics in Action! 
Mobility Pattern Analytics 
Behavior Learning & Prediction 
Crowd Analytics 
Anomaly Detection 
Detection
7 
Anomaly Detection Answers Difficult Questions 
What just happened that shouldn‘t have? 
•What does something that shouldn‘t have happened look like? 
How can I find it in time? 
•Before there is serious damage 
•Before supply chains, customers, competitors and VIPs are impacted 
Why are you disturbing my sleep?! 
•False alarms are costly
8 
Anomaly Detection Addresses Multiple Problems 
Anomaly Detection 
Framework 
Traffic Incidents 
Electrical Grid 
Smart Home 
Social Media 
Crowd 
Dike Stability
9 
Traffic Anomaly Detection 
86% 
14% 
Detection performance 
True 
positives 
False 
positives 
Customer problems addressed 
•Ensure road network efficiency, safety 
•Minimize impact of traffic incidents 
•Real-time, automatic detection of abnormal traffic congestion based on sensor data 
2.00 
0.11 
0.00 
5.00 
Alert rates per day and road segment 
Rule-based detection 
Detection 
Anomaly detection
10 
Traffic Anomalies Captured Live 
Different anomalies are identified depending on index threshold and event filtering. 
Abnormal traffic congestion identified 
Construction worker caused traffic changes 
Taxi parked for >15 min caused traffic changes 
28-Nov 13:15 
22-Nov 04:15 
20-Nov 21:26
11 
Engine Configuration for Traffic Incident Detection 
Use-Case Specific Plugin 
Generic Plugin 
Detection and Classification 
API 
Context Dependency Modeling 
Preprocessing 
Normality Model Learning 
Robust Density Estimation 
Support Vector Machines 
Apache Thrift 
Timestamp Discretization 
Auto Partitioning 
Discrete Context Switching 
Hypothesis & Persistence Test 
Noise Reduction 
Data Imputation 
Nearest Neighbor 
Python 
Storm 
Spark 
MapReduce 
Principal Component Analysis 
Clustering 
Manifold Learning 
Feature Extraction 
Traffic Parameter Extraction 
Enhanced HMM 
System Identification 
Random Forest 
Event Filter 
Normalization
12 
Traffic Anomaly Detection – Data and Extracted Patterns 
Raw Data: LPR, VA 
Characteristic Features 
Normal Pattern Model 
•Speed and volume per lane 
•High frequency noise (10% - 30% std. dev.) 
•Full/partial sensor outages 
•4 feature vectors: 
•Average speed 
•Total volume 
•Lane average speed 
•Lane speed difference 
•Aggregation to 1 min interval 
•Data cleaning 
•Noise filtering 
Multi-dimensional model 
•Traffic features (4 dim.) 
•Context dependency 
•Time of day 
•Day of week; public holidays 
•Covariance optimization for robustness against anomalies in training set
13 
Traffic Anomaly Detection – Anomaly Index 
Anomaly Example – Features and Model 
Mahalanobis Distance 
•Mahalanobis Distance indicates magnitude of deviation between model and measurements 
•Index threshold (red line) determines detection sensitivity 
•Anomalies affect multiple traffic characteristics 
•Deviation vectors used to further classify the type of anomaly
14 
Results from Large-scale Deployment 
1,000 LPR cameras 
16 million vehicle detections/day 
230 road segments analyzed 
Same configuration applied across highways, on-ramps, urban arterials and side streets 
Events validated on CCTV 
Low false alert rate 
Recurring congestion suppressed
15 
Moonscape Ventures 
• Corporate development and investment company 
• Launched August 2014; operates in TLV, NYC, Silicon Valley 
• Grows startups: IoT, smart cities, big data, news and media, other 
• Invests in late-seed stage, Series A round 
• Led by Tammy Mahn
16 
Bringing IoT Data to Life!

More Related Content

Viewers also liked

Low Power Processors, IoT Israel 2014
Low Power Processors, IoT Israel 2014 Low Power Processors, IoT Israel 2014
Low Power Processors, IoT Israel 2014
iotisrael
 
TechShanghai2016 - Qualcomm嵌入式解决方案,为IoT硬件开发而生
TechShanghai2016 - Qualcomm嵌入式解决方案,为IoT硬件开发而生TechShanghai2016 - Qualcomm嵌入式解决方案,为IoT硬件开发而生
TechShanghai2016 - Qualcomm嵌入式解决方案,为IoT硬件开发而生
Hardway Hou
 
Scio
ScioScio
Bringing Data to Life. Spreadsheets are boring! (ClickZ Live Singapore 2014)
Bringing Data to Life. Spreadsheets are boring! (ClickZ Live Singapore 2014)Bringing Data to Life. Spreadsheets are boring! (ClickZ Live Singapore 2014)
Bringing Data to Life. Spreadsheets are boring! (ClickZ Live Singapore 2014)
Dave Sanderson
 
Nio100 product guide 20150520
Nio100 product guide 20150520Nio100 product guide 20150520
Nio100 product guide 20150520和得 王
 
Brillo and weave - Android IOT
Brillo and weave - Android IOTBrillo and weave - Android IOT
Brillo and weave - Android IOT
Devavrata Sharma
 
Paving the path to Narrowband 5G with LTE Internet of Things
Paving the path to Narrowband 5G with LTE Internet of ThingsPaving the path to Narrowband 5G with LTE Internet of Things
Paving the path to Narrowband 5G with LTE Internet of Things
Qualcomm Research
 
LTE MTC: Optimizing LTE Advanced for Machine Type Communications
LTE MTC: Optimizing LTE Advanced for Machine Type CommunicationsLTE MTC: Optimizing LTE Advanced for Machine Type Communications
LTE MTC: Optimizing LTE Advanced for Machine Type Communications
Qualcomm Research
 
Janette Stewart, Analysys Mason - Presentation from Analysys Mason (Qualcomm ...
Janette Stewart, Analysys Mason - Presentation from Analysys Mason (Qualcomm ...Janette Stewart, Analysys Mason - Presentation from Analysys Mason (Qualcomm ...
Janette Stewart, Analysys Mason - Presentation from Analysys Mason (Qualcomm ...
techUK
 
Scio
ScioScio
Track 3 session 6 - st dev con 2016 - qualcomm - wi-fi connectivity for iot
Track 3   session 6 - st dev con 2016 - qualcomm - wi-fi connectivity for iotTrack 3   session 6 - st dev con 2016 - qualcomm - wi-fi connectivity for iot
Track 3 session 6 - st dev con 2016 - qualcomm - wi-fi connectivity for iot
ST_World
 
Molecular Sensor from SCIO
Molecular Sensor from SCIOMolecular Sensor from SCIO
Molecular Sensor from SCIO
Jeffrey Funk Business Models
 
Track 1 session 4 - st dev con 2016 - mems piezo actuators
Track 1   session 4 - st dev con 2016 - mems piezo actuatorsTrack 1   session 4 - st dev con 2016 - mems piezo actuators
Track 1 session 4 - st dev con 2016 - mems piezo actuators
ST_World
 
The Next-Gen Technologies Driving Immersion
The Next-Gen Technologies Driving ImmersionThe Next-Gen Technologies Driving Immersion
The Next-Gen Technologies Driving Immersion
Qualcomm Research
 
Paving the path to Narrowband 5G with LTE IoT
Paving the path to Narrowband 5G with LTE IoTPaving the path to Narrowband 5G with LTE IoT
Paving the path to Narrowband 5G with LTE IoT
Qualcomm Research
 
Internet of things (IoT) with Azure
Internet of things (IoT) with AzureInternet of things (IoT) with Azure
Internet of things (IoT) with Azure
Vinoth Rajagopalan
 
Driving the Gigabit LTE Evolution
Driving the Gigabit LTE EvolutionDriving the Gigabit LTE Evolution
Driving the Gigabit LTE Evolution
Qualcomm Research
 
Internet of Things & Hardware Industry Report 2016
Internet of Things & Hardware Industry Report 2016Internet of Things & Hardware Industry Report 2016
Internet of Things & Hardware Industry Report 2016
Bernard Moon
 
Internet of Things
Internet of ThingsInternet of Things
Internet of Things
Cisco Services
 

Viewers also liked (19)

Low Power Processors, IoT Israel 2014
Low Power Processors, IoT Israel 2014 Low Power Processors, IoT Israel 2014
Low Power Processors, IoT Israel 2014
 
TechShanghai2016 - Qualcomm嵌入式解决方案,为IoT硬件开发而生
TechShanghai2016 - Qualcomm嵌入式解决方案,为IoT硬件开发而生TechShanghai2016 - Qualcomm嵌入式解决方案,为IoT硬件开发而生
TechShanghai2016 - Qualcomm嵌入式解决方案,为IoT硬件开发而生
 
Scio
ScioScio
Scio
 
Bringing Data to Life. Spreadsheets are boring! (ClickZ Live Singapore 2014)
Bringing Data to Life. Spreadsheets are boring! (ClickZ Live Singapore 2014)Bringing Data to Life. Spreadsheets are boring! (ClickZ Live Singapore 2014)
Bringing Data to Life. Spreadsheets are boring! (ClickZ Live Singapore 2014)
 
Nio100 product guide 20150520
Nio100 product guide 20150520Nio100 product guide 20150520
Nio100 product guide 20150520
 
Brillo and weave - Android IOT
Brillo and weave - Android IOTBrillo and weave - Android IOT
Brillo and weave - Android IOT
 
Paving the path to Narrowband 5G with LTE Internet of Things
Paving the path to Narrowband 5G with LTE Internet of ThingsPaving the path to Narrowband 5G with LTE Internet of Things
Paving the path to Narrowband 5G with LTE Internet of Things
 
LTE MTC: Optimizing LTE Advanced for Machine Type Communications
LTE MTC: Optimizing LTE Advanced for Machine Type CommunicationsLTE MTC: Optimizing LTE Advanced for Machine Type Communications
LTE MTC: Optimizing LTE Advanced for Machine Type Communications
 
Janette Stewart, Analysys Mason - Presentation from Analysys Mason (Qualcomm ...
Janette Stewart, Analysys Mason - Presentation from Analysys Mason (Qualcomm ...Janette Stewart, Analysys Mason - Presentation from Analysys Mason (Qualcomm ...
Janette Stewart, Analysys Mason - Presentation from Analysys Mason (Qualcomm ...
 
Scio
ScioScio
Scio
 
Track 3 session 6 - st dev con 2016 - qualcomm - wi-fi connectivity for iot
Track 3   session 6 - st dev con 2016 - qualcomm - wi-fi connectivity for iotTrack 3   session 6 - st dev con 2016 - qualcomm - wi-fi connectivity for iot
Track 3 session 6 - st dev con 2016 - qualcomm - wi-fi connectivity for iot
 
Molecular Sensor from SCIO
Molecular Sensor from SCIOMolecular Sensor from SCIO
Molecular Sensor from SCIO
 
Track 1 session 4 - st dev con 2016 - mems piezo actuators
Track 1   session 4 - st dev con 2016 - mems piezo actuatorsTrack 1   session 4 - st dev con 2016 - mems piezo actuators
Track 1 session 4 - st dev con 2016 - mems piezo actuators
 
The Next-Gen Technologies Driving Immersion
The Next-Gen Technologies Driving ImmersionThe Next-Gen Technologies Driving Immersion
The Next-Gen Technologies Driving Immersion
 
Paving the path to Narrowband 5G with LTE IoT
Paving the path to Narrowband 5G with LTE IoTPaving the path to Narrowband 5G with LTE IoT
Paving the path to Narrowband 5G with LTE IoT
 
Internet of things (IoT) with Azure
Internet of things (IoT) with AzureInternet of things (IoT) with Azure
Internet of things (IoT) with Azure
 
Driving the Gigabit LTE Evolution
Driving the Gigabit LTE EvolutionDriving the Gigabit LTE Evolution
Driving the Gigabit LTE Evolution
 
Internet of Things & Hardware Industry Report 2016
Internet of Things & Hardware Industry Report 2016Internet of Things & Hardware Industry Report 2016
Internet of Things & Hardware Industry Report 2016
 
Internet of Things
Internet of ThingsInternet of Things
Internet of Things
 

Similar to Bringing iot data to life, IoT Israel 2014

Anomaly Detection and Spark Implementation - Meetup Presentation.pptx
Anomaly Detection and Spark Implementation - Meetup Presentation.pptxAnomaly Detection and Spark Implementation - Meetup Presentation.pptx
Anomaly Detection and Spark Implementation - Meetup Presentation.pptx
Impetus Technologies
 
Anomaly Detection - Real World Scenarios, Approaches and Live Implementation
Anomaly Detection - Real World Scenarios, Approaches and Live ImplementationAnomaly Detection - Real World Scenarios, Approaches and Live Implementation
Anomaly Detection - Real World Scenarios, Approaches and Live Implementation
Impetus Technologies
 
Data analytics for monitoring IoT infrastructures by G.Madhusudan, Orange Labs
Data analytics for monitoring IoT infrastructures by G.Madhusudan, Orange LabsData analytics for monitoring IoT infrastructures by G.Madhusudan, Orange Labs
Data analytics for monitoring IoT infrastructures by G.Madhusudan, Orange Labs
EuroIoTa
 
Will camera technology become an ITS sensor
Will camera technology become an ITS sensorWill camera technology become an ITS sensor
Will camera technology become an ITS sensor
Allied Vision
 
Barga ACM DEBS 2013 Keynote
Barga ACM DEBS 2013 KeynoteBarga ACM DEBS 2013 Keynote
Barga ACM DEBS 2013 Keynote
Roger Barga
 
Traffic data fusion methodology
Traffic data fusion methodologyTraffic data fusion methodology
Traffic data fusion methodology
JumpingJaq
 
Arpan pal ncccs
Arpan pal ncccsArpan pal ncccs
Arpan pal ncccsArpan Pal
 
I tac tics_ntelligent infra_r&d
I tac tics_ntelligent infra_r&dI tac tics_ntelligent infra_r&d
I tac tics_ntelligent infra_r&dArpan Pal
 
NetFlow Auditor Anomaly Detection Plus Forensics February 2010 08
NetFlow Auditor Anomaly Detection Plus Forensics February 2010 08NetFlow Auditor Anomaly Detection Plus Forensics February 2010 08
NetFlow Auditor Anomaly Detection Plus Forensics February 2010 08
NetFlowAuditor
 
Benefits of enhanced event analysis in datacenter otdr testing
Benefits of enhanced event analysis in datacenter otdr testingBenefits of enhanced event analysis in datacenter otdr testing
Benefits of enhanced event analysis in datacenter otdr testing
FangXuIEEE
 
Arpan pal tac tics2012
Arpan pal tac tics2012Arpan pal tac tics2012
Arpan pal tac tics2012Arpan Pal
 
Tune Up Your Network for the New Year
Tune Up Your Network for the New YearTune Up Your Network for the New Year
Tune Up Your Network for the New Year
Savvius, Inc
 
Closing plenary and keynote from Lauren Sager Weinstein
Closing plenary and keynote from Lauren Sager WeinsteinClosing plenary and keynote from Lauren Sager Weinstein
Closing plenary and keynote from Lauren Sager Weinstein
Jisc
 
Wherecamp Navigation Conference 2015 - The unintelligent swarm
Wherecamp Navigation Conference 2015 - The unintelligent swarmWherecamp Navigation Conference 2015 - The unintelligent swarm
Wherecamp Navigation Conference 2015 - The unintelligent swarm
WhereCampBerlin
 
Jorge Sebastiao "Using AI for Smart traffic Management"
Jorge Sebastiao "Using AI for Smart traffic Management"Jorge Sebastiao "Using AI for Smart traffic Management"
Jorge Sebastiao "Using AI for Smart traffic Management"
Lviv Startup Club
 
Intelligent transport systems
Intelligent  transport systemsIntelligent  transport systems
Intelligent transport systems
Abhijit Pal
 
NetFlow Analyzer Training Part II : Diagnosing and troubleshooting traffic is...
NetFlow Analyzer Training Part II : Diagnosing and troubleshooting traffic is...NetFlow Analyzer Training Part II : Diagnosing and troubleshooting traffic is...
NetFlow Analyzer Training Part II : Diagnosing and troubleshooting traffic is...
ManageEngine, Zoho Corporation
 
DEVNET-1145 How APIs are Driving City Digitization
DEVNET-1145	How APIs are Driving City DigitizationDEVNET-1145	How APIs are Driving City Digitization
DEVNET-1145 How APIs are Driving City Digitization
Cisco DevNet
 
IT Operation Analytic for security- MiSSconf(sp1)
IT Operation Analytic for security- MiSSconf(sp1)IT Operation Analytic for security- MiSSconf(sp1)
IT Operation Analytic for security- MiSSconf(sp1)
stelligence
 
Meetup 18/10/2018 - Artificiële intelligentie en mobiliteit
Meetup 18/10/2018 - Artificiële intelligentie en mobiliteitMeetup 18/10/2018 - Artificiële intelligentie en mobiliteit
Meetup 18/10/2018 - Artificiële intelligentie en mobiliteit
Digipolis Antwerpen
 

Similar to Bringing iot data to life, IoT Israel 2014 (20)

Anomaly Detection and Spark Implementation - Meetup Presentation.pptx
Anomaly Detection and Spark Implementation - Meetup Presentation.pptxAnomaly Detection and Spark Implementation - Meetup Presentation.pptx
Anomaly Detection and Spark Implementation - Meetup Presentation.pptx
 
Anomaly Detection - Real World Scenarios, Approaches and Live Implementation
Anomaly Detection - Real World Scenarios, Approaches and Live ImplementationAnomaly Detection - Real World Scenarios, Approaches and Live Implementation
Anomaly Detection - Real World Scenarios, Approaches and Live Implementation
 
Data analytics for monitoring IoT infrastructures by G.Madhusudan, Orange Labs
Data analytics for monitoring IoT infrastructures by G.Madhusudan, Orange LabsData analytics for monitoring IoT infrastructures by G.Madhusudan, Orange Labs
Data analytics for monitoring IoT infrastructures by G.Madhusudan, Orange Labs
 
Will camera technology become an ITS sensor
Will camera technology become an ITS sensorWill camera technology become an ITS sensor
Will camera technology become an ITS sensor
 
Barga ACM DEBS 2013 Keynote
Barga ACM DEBS 2013 KeynoteBarga ACM DEBS 2013 Keynote
Barga ACM DEBS 2013 Keynote
 
Traffic data fusion methodology
Traffic data fusion methodologyTraffic data fusion methodology
Traffic data fusion methodology
 
Arpan pal ncccs
Arpan pal ncccsArpan pal ncccs
Arpan pal ncccs
 
I tac tics_ntelligent infra_r&d
I tac tics_ntelligent infra_r&dI tac tics_ntelligent infra_r&d
I tac tics_ntelligent infra_r&d
 
NetFlow Auditor Anomaly Detection Plus Forensics February 2010 08
NetFlow Auditor Anomaly Detection Plus Forensics February 2010 08NetFlow Auditor Anomaly Detection Plus Forensics February 2010 08
NetFlow Auditor Anomaly Detection Plus Forensics February 2010 08
 
Benefits of enhanced event analysis in datacenter otdr testing
Benefits of enhanced event analysis in datacenter otdr testingBenefits of enhanced event analysis in datacenter otdr testing
Benefits of enhanced event analysis in datacenter otdr testing
 
Arpan pal tac tics2012
Arpan pal tac tics2012Arpan pal tac tics2012
Arpan pal tac tics2012
 
Tune Up Your Network for the New Year
Tune Up Your Network for the New YearTune Up Your Network for the New Year
Tune Up Your Network for the New Year
 
Closing plenary and keynote from Lauren Sager Weinstein
Closing plenary and keynote from Lauren Sager WeinsteinClosing plenary and keynote from Lauren Sager Weinstein
Closing plenary and keynote from Lauren Sager Weinstein
 
Wherecamp Navigation Conference 2015 - The unintelligent swarm
Wherecamp Navigation Conference 2015 - The unintelligent swarmWherecamp Navigation Conference 2015 - The unintelligent swarm
Wherecamp Navigation Conference 2015 - The unintelligent swarm
 
Jorge Sebastiao "Using AI for Smart traffic Management"
Jorge Sebastiao "Using AI for Smart traffic Management"Jorge Sebastiao "Using AI for Smart traffic Management"
Jorge Sebastiao "Using AI for Smart traffic Management"
 
Intelligent transport systems
Intelligent  transport systemsIntelligent  transport systems
Intelligent transport systems
 
NetFlow Analyzer Training Part II : Diagnosing and troubleshooting traffic is...
NetFlow Analyzer Training Part II : Diagnosing and troubleshooting traffic is...NetFlow Analyzer Training Part II : Diagnosing and troubleshooting traffic is...
NetFlow Analyzer Training Part II : Diagnosing and troubleshooting traffic is...
 
DEVNET-1145 How APIs are Driving City Digitization
DEVNET-1145	How APIs are Driving City DigitizationDEVNET-1145	How APIs are Driving City Digitization
DEVNET-1145 How APIs are Driving City Digitization
 
IT Operation Analytic for security- MiSSconf(sp1)
IT Operation Analytic for security- MiSSconf(sp1)IT Operation Analytic for security- MiSSconf(sp1)
IT Operation Analytic for security- MiSSconf(sp1)
 
Meetup 18/10/2018 - Artificiële intelligentie en mobiliteit
Meetup 18/10/2018 - Artificiële intelligentie en mobiliteitMeetup 18/10/2018 - Artificiële intelligentie en mobiliteit
Meetup 18/10/2018 - Artificiële intelligentie en mobiliteit
 

Recently uploaded

The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
Jemma Hussein Allen
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance
 
Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?
Nexer Digital
 
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
Neo4j
 
PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)
Ralf Eggert
 
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
BookNet Canada
 
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptxSecstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
nkrafacyberclub
 
DevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA ConnectDevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA Connect
Kari Kakkonen
 
Video Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the FutureVideo Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the Future
Alpen-Adria-Universität
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
DianaGray10
 
Essentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FMEEssentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FME
Safe Software
 
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
James Anderson
 
Microsoft - Power Platform_G.Aspiotis.pdf
Microsoft - Power Platform_G.Aspiotis.pdfMicrosoft - Power Platform_G.Aspiotis.pdf
Microsoft - Power Platform_G.Aspiotis.pdf
Uni Systems S.M.S.A.
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
Prayukth K V
 
Uni Systems Copilot event_05062024_C.Vlachos.pdf
Uni Systems Copilot event_05062024_C.Vlachos.pdfUni Systems Copilot event_05062024_C.Vlachos.pdf
Uni Systems Copilot event_05062024_C.Vlachos.pdf
Uni Systems S.M.S.A.
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
ControlCase
 
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
James Anderson
 
National Security Agency - NSA mobile device best practices
National Security Agency - NSA mobile device best practicesNational Security Agency - NSA mobile device best practices
National Security Agency - NSA mobile device best practices
Quotidiano Piemontese
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance
 
UiPath Test Automation using UiPath Test Suite series, part 5
UiPath Test Automation using UiPath Test Suite series, part 5UiPath Test Automation using UiPath Test Suite series, part 5
UiPath Test Automation using UiPath Test Suite series, part 5
DianaGray10
 

Recently uploaded (20)

The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
 
Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?
 
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
 
PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)
 
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
 
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptxSecstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
 
DevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA ConnectDevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA Connect
 
Video Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the FutureVideo Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the Future
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
 
Essentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FMEEssentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FME
 
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
 
Microsoft - Power Platform_G.Aspiotis.pdf
Microsoft - Power Platform_G.Aspiotis.pdfMicrosoft - Power Platform_G.Aspiotis.pdf
Microsoft - Power Platform_G.Aspiotis.pdf
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
 
Uni Systems Copilot event_05062024_C.Vlachos.pdf
Uni Systems Copilot event_05062024_C.Vlachos.pdfUni Systems Copilot event_05062024_C.Vlachos.pdf
Uni Systems Copilot event_05062024_C.Vlachos.pdf
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
 
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
 
National Security Agency - NSA mobile device best practices
National Security Agency - NSA mobile device best practicesNational Security Agency - NSA mobile device best practices
National Security Agency - NSA mobile device best practices
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
 
UiPath Test Automation using UiPath Test Suite series, part 5
UiPath Test Automation using UiPath Test Suite series, part 5UiPath Test Automation using UiPath Test Suite series, part 5
UiPath Test Automation using UiPath Test Suite series, part 5
 

Bringing iot data to life, IoT Israel 2014

  • 1. Bringing IoT Data to Life! Date Dr. Joachim Schaper, VP Research
  • 2. 2 The Potential…and Challenges…of IoT Data
  • 3. DATA REAL TIME VAST AMOUNTS REAL WORLD HETEROGENEOUS NOISY
  • 4. sense How do we make of IoT data?
  • 5. I T A An IoT Analytics Platform
  • 6. 6 IoTA: Analytics in Action! Mobility Pattern Analytics Behavior Learning & Prediction Crowd Analytics Anomaly Detection Detection
  • 7. 7 Anomaly Detection Answers Difficult Questions What just happened that shouldn‘t have? •What does something that shouldn‘t have happened look like? How can I find it in time? •Before there is serious damage •Before supply chains, customers, competitors and VIPs are impacted Why are you disturbing my sleep?! •False alarms are costly
  • 8. 8 Anomaly Detection Addresses Multiple Problems Anomaly Detection Framework Traffic Incidents Electrical Grid Smart Home Social Media Crowd Dike Stability
  • 9. 9 Traffic Anomaly Detection 86% 14% Detection performance True positives False positives Customer problems addressed •Ensure road network efficiency, safety •Minimize impact of traffic incidents •Real-time, automatic detection of abnormal traffic congestion based on sensor data 2.00 0.11 0.00 5.00 Alert rates per day and road segment Rule-based detection Detection Anomaly detection
  • 10. 10 Traffic Anomalies Captured Live Different anomalies are identified depending on index threshold and event filtering. Abnormal traffic congestion identified Construction worker caused traffic changes Taxi parked for >15 min caused traffic changes 28-Nov 13:15 22-Nov 04:15 20-Nov 21:26
  • 11. 11 Engine Configuration for Traffic Incident Detection Use-Case Specific Plugin Generic Plugin Detection and Classification API Context Dependency Modeling Preprocessing Normality Model Learning Robust Density Estimation Support Vector Machines Apache Thrift Timestamp Discretization Auto Partitioning Discrete Context Switching Hypothesis & Persistence Test Noise Reduction Data Imputation Nearest Neighbor Python Storm Spark MapReduce Principal Component Analysis Clustering Manifold Learning Feature Extraction Traffic Parameter Extraction Enhanced HMM System Identification Random Forest Event Filter Normalization
  • 12. 12 Traffic Anomaly Detection – Data and Extracted Patterns Raw Data: LPR, VA Characteristic Features Normal Pattern Model •Speed and volume per lane •High frequency noise (10% - 30% std. dev.) •Full/partial sensor outages •4 feature vectors: •Average speed •Total volume •Lane average speed •Lane speed difference •Aggregation to 1 min interval •Data cleaning •Noise filtering Multi-dimensional model •Traffic features (4 dim.) •Context dependency •Time of day •Day of week; public holidays •Covariance optimization for robustness against anomalies in training set
  • 13. 13 Traffic Anomaly Detection – Anomaly Index Anomaly Example – Features and Model Mahalanobis Distance •Mahalanobis Distance indicates magnitude of deviation between model and measurements •Index threshold (red line) determines detection sensitivity •Anomalies affect multiple traffic characteristics •Deviation vectors used to further classify the type of anomaly
  • 14. 14 Results from Large-scale Deployment 1,000 LPR cameras 16 million vehicle detections/day 230 road segments analyzed Same configuration applied across highways, on-ramps, urban arterials and side streets Events validated on CCTV Low false alert rate Recurring congestion suppressed
  • 15. 15 Moonscape Ventures • Corporate development and investment company • Launched August 2014; operates in TLV, NYC, Silicon Valley • Grows startups: IoT, smart cities, big data, news and media, other • Invests in late-seed stage, Series A round • Led by Tammy Mahn
  • 16. 16 Bringing IoT Data to Life!