This paper presents a method which detects events from floating car data (FCD). In traffic prediction, an event is one of unexpected factors which deteriorates the prediction performance. If occurrences of events are provided to prediction system beforehand, the prediction will be improved. Firstly, we confirmed contribution of event information to a traffic prediction accuracy. Then the paper will show that spatio-temporal pattern of zonal traffic attraction and generation is an intelligible trail of an event. Finally, the paper will propose an event detection and prediction method using PCA and HMM. The result shows feasibility of event prediction in high accuracy in certain condition.
The purpose of the ResilientCity.org Design Ideas Competition is to stimulate thinking and discourse about how to increase the resilience of our cities as we move into a century where our cities will be subjected to the combined environmental and economic impacts of Peak Oil and Climate Change.
Business Event Procesing Beyond The HorizonOpher Etzion
This is a presentation given in IBM Websphere IMPACT 2009, May 2009, Las Vegas together with Kyle Brown. It contains some thoughts that are demonstrated through customers' scenarios on future functionality in event processing products.
Enabling Value Added Services in the Event-based InternetYiannis Verginadis
specific presentation gives an overview of the FP7 project PLAY, along with its main objectives, latest achievements and remaining work.
We discuss thoroughly on how to enable value added services in the event-based internet. Specifically, we give details about the development of two dedicated open-source software components that can exploit distributed and heterogeneous event sources for enabling: i) efficiently and dynamically new event subscriptions (i.e. Event Subscription Recommender) and ii) the recommendation and implementation of workflow adaptations (i.e. Service Adaptation Recommender)
The purpose of the ResilientCity.org Design Ideas Competition is to stimulate thinking and discourse about how to increase the resilience of our cities as we move into a century where our cities will be subjected to the combined environmental and economic impacts of Peak Oil and Climate Change.
Business Event Procesing Beyond The HorizonOpher Etzion
This is a presentation given in IBM Websphere IMPACT 2009, May 2009, Las Vegas together with Kyle Brown. It contains some thoughts that are demonstrated through customers' scenarios on future functionality in event processing products.
Enabling Value Added Services in the Event-based InternetYiannis Verginadis
specific presentation gives an overview of the FP7 project PLAY, along with its main objectives, latest achievements and remaining work.
We discuss thoroughly on how to enable value added services in the event-based internet. Specifically, we give details about the development of two dedicated open-source software components that can exploit distributed and heterogeneous event sources for enabling: i) efficiently and dynamically new event subscriptions (i.e. Event Subscription Recommender) and ii) the recommendation and implementation of workflow adaptations (i.e. Service Adaptation Recommender)
Real time video analytics with InfoSphere Streams, OpenCV and RStephan Reimann
Unstructured data are a fast growing area and a source for many innovative Big Data & Analytics solutions. Often the first idea of unstructured data seems to be that it's probably text data, even though that is just a small part. A lot of that "new data" is sensor data and especially multimedia (audio, video). Even though this part is growing extremly fast, it is very rarely used in analytics today. And even less in a real time context.
In order to experience what does it mean and how does it feel (and if it is possible to make sense of it) to work with this new data in real time, Wilfried Hoge and I have created a demo that shows our own experience and explains important concepts & implementation. approaches. The demo we created shows a drill equipment as it is used to build tunnels and how to analyze the output on the conveyor belt visually with machine learning approaches.
Multi-media Analytics and Cognitive Computing to Provide Safe Secure Cities (...IT Arena
Lviv IT Arena is a conference specially designed for programmers, designers, developers, top managers, inverstors, entrepreneurs and startuppers. Annually it takes place at the beginning of October in Lviv at Arena Lviv stadium. In 2016 the conference gathered more than 1800 participants and over 100 speakers from companies like Microsoft, Philips, Twitter, UBER and IBM. More details about the conference at itarena.lviv.ua.
Current state of art contains several methods to achieve intelligent tracking. Some methods are machine learning oriented. In these methods, activities are learnt from the context in an unsupervised or semi supervised manner. One other method is description based event recognition. In the heart of the method , describing scenarios wrt activities employed. For the description, a language is necessarily needed. There are mathematical languages in which logic is used to represent activities and their relations.Also some graphical languages such as hidden markov models, state machines, state charts are being used. Some textual languages proposed as well.
This is a security awareness presentation on impact of developing and using insecure applications in organisations. Number of case studies of data leaks, defacements and regulatory fines are presented as example.
This presentation introduces the topic of computer vision, especially through the lense of Deep Learning.
Go build! https://gluon-cv.mxnet.io
Slides: Thomas Delteil
For the full video of this presentation, please visit:
https://www.edge-ai-vision.com/2021/01/video-activity-recognition-with-limited-data-for-smart-home-applications-a-presentation-from-comcast/
For more information about edge AI and computer vision, please visit:
https://www.edge-ai-vision.com
Hongcheng Wang, Director of Technical Research at Comcast, presents the “Video Activity Recognition with Limited Data for Smart Home Applications” tutorial at the September 2020 Embedded Vision Summit.
Comcast’s Xfinity Home connects millions of home smart cameras and IoT devices to improve its customers’ safety and security. The company’s teams use computer vision and deep learning to understand video and sensor data from these devices to identify relevant events so that it can improve the user experience.
Specifically, Comcast has explored the spatial-temporal relationships among objects, places and actions. The company has also developed a semi-supervised learning approach for video classification (VideoSSL) to detect certain activities using limited training data. Using these techniques, and as described in this presentation, it has achieved very promising results on activity recognition with multiple datasets.
Real time video analytics with InfoSphere Streams, OpenCV and RStephan Reimann
Unstructured data are a fast growing area and a source for many innovative Big Data & Analytics solutions. Often the first idea of unstructured data seems to be that it's probably text data, even though that is just a small part. A lot of that "new data" is sensor data and especially multimedia (audio, video). Even though this part is growing extremly fast, it is very rarely used in analytics today. And even less in a real time context.
In order to experience what does it mean and how does it feel (and if it is possible to make sense of it) to work with this new data in real time, Wilfried Hoge and I have created a demo that shows our own experience and explains important concepts & implementation. approaches. The demo we created shows a drill equipment as it is used to build tunnels and how to analyze the output on the conveyor belt visually with machine learning approaches.
Multi-media Analytics and Cognitive Computing to Provide Safe Secure Cities (...IT Arena
Lviv IT Arena is a conference specially designed for programmers, designers, developers, top managers, inverstors, entrepreneurs and startuppers. Annually it takes place at the beginning of October in Lviv at Arena Lviv stadium. In 2016 the conference gathered more than 1800 participants and over 100 speakers from companies like Microsoft, Philips, Twitter, UBER and IBM. More details about the conference at itarena.lviv.ua.
Current state of art contains several methods to achieve intelligent tracking. Some methods are machine learning oriented. In these methods, activities are learnt from the context in an unsupervised or semi supervised manner. One other method is description based event recognition. In the heart of the method , describing scenarios wrt activities employed. For the description, a language is necessarily needed. There are mathematical languages in which logic is used to represent activities and their relations.Also some graphical languages such as hidden markov models, state machines, state charts are being used. Some textual languages proposed as well.
This is a security awareness presentation on impact of developing and using insecure applications in organisations. Number of case studies of data leaks, defacements and regulatory fines are presented as example.
This presentation introduces the topic of computer vision, especially through the lense of Deep Learning.
Go build! https://gluon-cv.mxnet.io
Slides: Thomas Delteil
For the full video of this presentation, please visit:
https://www.edge-ai-vision.com/2021/01/video-activity-recognition-with-limited-data-for-smart-home-applications-a-presentation-from-comcast/
For more information about edge AI and computer vision, please visit:
https://www.edge-ai-vision.com
Hongcheng Wang, Director of Technical Research at Comcast, presents the “Video Activity Recognition with Limited Data for Smart Home Applications” tutorial at the September 2020 Embedded Vision Summit.
Comcast’s Xfinity Home connects millions of home smart cameras and IoT devices to improve its customers’ safety and security. The company’s teams use computer vision and deep learning to understand video and sensor data from these devices to identify relevant events so that it can improve the user experience.
Specifically, Comcast has explored the spatial-temporal relationships among objects, places and actions. The company has also developed a semi-supervised learning approach for video classification (VideoSSL) to detect certain activities using limited training data. Using these techniques, and as described in this presentation, it has achieved very promising results on activity recognition with multiple datasets.
A Sensing Coverage Analysis of a Route Control Method for Vehicular Crowd Sen...Osamu Masutani
Simulated evaluation of crowd sensing with vehicles for a Smart City. Route cordination of sensing vehicles is a key to enhance sensing coverage of participatory crowd sensing system. We provide a simple methodology to realize suitable cordinated traffic control method by means of shortest cost finding with dedicated cost function aware of sensing demand in a city.
A Multiple Pairs Shortest Path Algorithm 解説Osamu Masutani
National Cheng Kung UniversityのWang氏の多点間最短経路探索(MPSP)に関する論文の解説。
Wang, I-Lin, Ellis L. Johnson, and Joel S. Sokol. "A multiple pairs shortest path algorithm." Transportation science 39.4 (2005): 465-476.
Clustering of time series subsequences is meaningless 解説Osamu Masutani
UCRのKeoghらの時系列クラスタリングに関する論文の解説。Keogh, Eamonn, and Jessica Lin. "Clustering of time-series subsequences is meaningless: implications for previous and future research." Knowledge and information systems 8.2 (2005): 154-177.
1. An event detection method using
floating car data
Osamu Masutani, Hirotoshi Iwasaki
Denso IT Laboratory, Inc.
Copyright (C) 2009 DENSO IT LABORATORY, INC. All Rights Reserved.
2. Summary
Background
Concept
Methodology
- Factorization
- Detection
- Prediction
Conclusions
Copyright (C) 2009 DENSO IT LABORATORY, INC. All Rights Reserved. 2/17
3. Background: Event
Ex. Festivals, sports event
As a destination
- Attractive POI
- Drivers would like to know “fresh”
information about events. Our aspect
As an obstacle
- Repellent POI.
- Drivers would like to know risk of
Event
congestion caused by an event.
Event information
- Place and time
!
Copyright (C) 2009 DENSO IT LABORATORY, INC. All Rights Reserved. 3/17
4. Background: Avoidance of event congestion
Traffic information service
- Watch and avoid
→ Congestion-aware route guidance
→ Traffic prediction
Problem
- Most of prediction method based on Google maps
stationery situation of traffic.
- Event is irregular and unpredictable. Event
ahead
Event “plan” information can
18:00
improve prediction accuracy.
- Event-aware traffic prediction
Copyright (C) 2009 DENSO IT LABORATORY, INC. All Rights Reserved. 4/17
5. Background: Event database
Manually collected database
- For web, telematics services
Not integrated
- Most of services are dedicated to
certain genre (ex. business event,
leisure event)
- Private event information isn’t provided Fireworks in Stockholm
(ex. school event)
Not real-time
- Re-schedule isn’t always tracked
Copyright (C) 2009 DENSO IT LABORATORY, INC. All Rights Reserved. 5/17
6. Concept: Event detection method with FCD
Fully automatic detection
- Extracted from floating car data (FCD)
Integrated
- Can detect any type of event.
- Private event also be detected.
Real-time
- Based on real-time fluctuation of FCD
Copyright (C) 2009 DENSO IT LABORATORY, INC. All Rights Reserved. 6/17
7. Concept: Relationship between FCD and an event
Attraction
Assumption
Count of attraction and generation of cars to/from
an event venue indicates event-specific pattern.
Stadium
Definition
- Zone : gridded areas
- Attraction : Incoming cars to the zone
- Generation : Outgoing cars from the
zone Generation
Event period
Event specific pattern: Attraction
increase before event and
generation increase after event
Attraction
Generation
Copyright (C) 2009 DENSO IT LABORATORY, INC. All Rights Reserved. 7/17
8. Concept: 3D view of attraction and generation
Events
Spatio-temporal density view
reveals the event-specific pattern
- Attraction peak (blue chunk) followed
by generation peak (red chunk)
Density mapping by iso-surface
- More interpretable than point scatter
Stadium
Similar method with “crime mapping”
Nakaya, T., Yano, K., (2008).
Spatio-temporal three-dimensional mapping of crime events:
visualizing spatio-temporal clusters of snatch-and-run offences
Copyright (C) 2009 DENSO IT LABORATORY, INC. All Rights Reserved. 8/17
9. Factorization: For accurate detection
An event venue isn’t
identical with a grid zone
- Some sets of zones are related
with one event Stadium
Event specific pattern might
be hidden in stationery
traffic Event fluctuation
- Various factors of fluctuation are
coincident in a zone
-
Stationary fluctuation
Event related factor should be
properly separated
Copyright (C) 2009 DENSO IT LABORATORY, INC. All Rights Reserved. 9/17
10. Factorization: Spatio-temporal factorization
PCA on spatio-temporal space
- Factor is a pair of zone and time
series.
Factored zones are zones which
have coincident traffic.
Factored time series are
separated according to its
pattern.
Similar method with image factorization
Oliver, N. M., Rosario, B., Pentland, A. P., (2000).
A Bayesian Computer Vision System for
Modeling Human Interactions
Copyright (C) 2009 DENSO IT LABORATORY, INC. All Rights Reserved. 10/17
11. Factorization: Factors for density of attraction
Categorization of factors
- Single zone / set of zones
- Periodic / irregular /
transitory fluctuation
Factor 1 : Weekday morning peaks on central
station and business area
Factor 2 : Evening peaks on night spot
Factor 3 : Transitory peaks on a sports center
Factor 4 : Weekday midnight peaks on central
station
Factor 5 : Transitory peak on a spot
Copyright (C) 2009 DENSO IT LABORATORY, INC. All Rights Reserved. 11/17
12. Factorization: Event related factor
Zones: nearby area of the stadium
Time series: corresponding to the
dates of baseball games
Stadium
Weighted combination of zones
: baseball games
Copyright (C) 2009 DENSO IT LABORATORY, INC. All Rights Reserved. 12/17
13. Detection: Event pattern detection by HMM
In-event Non-event
Event “state” definition
- 4 states (non, pre, in, post)
- Pre- and post- event states defined as
2 hours before and after the event
period. Pre-event Post-event
Detection of pre-event can be
regarded as prediction of event
4 state HMM
- Trained by pair of actual event data and
FCD
Copyright (C) 2009 DENSO IT LABORATORY, INC. All Rights Reserved. 13/17
14. Detection: Detection results
Evaluation on the stadium
events
- 1.5 month, near a stadium, 17
events (baseball games)
Event states and raw data
Results confirms our
method works well
- Event states detection:
precision = 86%
- Event occurrence detection:
precision = 100%
Recall = 100%
Detected events
Copyright (C) 2009 DENSO IT LABORATORY, INC. All Rights Reserved. 14/17
15. Prediction: Event aware traffic prediction
Benefit of event information
- Based on statistical prediction
- Enhanced by adding a prediction pattern for event
Normal Event aware
Weekday Weekday
Holiday Holiday
Event
Copyright (C) 2009 DENSO IT LABORATORY, INC. All Rights Reserved. 15/17
16. Prediction: Evaluation result
Evaluation
- Comparison event aware and normal (baseline) prediction
- 1.5 month, near a stadium, 17 events (baseball games) Stadium and traffic
Event information improves prediction accuracy
- Overall accuracy of event-aware prediction outperforms 38% over
normal prediction
Event period
38%
Copyright (C) 2009 DENSO IT LABORATORY, INC. All Rights Reserved. 16/17
17. Conclusions
FCD attraction and generation statistics
is good clue to event occurrence
Factorization and HMM can detect
relatively large scale events
Event can refine traffic prediction ability
Future works
- Smaller events
- Event classification
Copyright (C) 2009 DENSO IT LABORATORY, INC. All Rights Reserved. 17/17