sensing, tracking and ... - ppgcc.ufersa.edu.br · iii workshop do ppgcc •demography •50,000...
TRANSCRIPT
Sensing, Tracking and Contextualizing Entities in Ubiquitous Systems
(Sensoriamento, Rastreamento e Contextualização de Entidades em Computação Ubíqua)
Antonio Alfredo F. Loureiro [email protected]
Department of Computer Science Universidade Federal de Minas Gerais, Brazil
III Workshop do PPgCC
• Demography • 50,000 students
• 3,000 faculty members
• Campus • 10,000 football fields
• Other facts • More than 300 undergraduate and graduate courses
• 27 libraries with a collection of 1 million items
2
3
UFMG Campus Central area
New Computer Science Building
4
UFMG Campus Central area
5
Pampulha Lake Same region of UFMG Campus
6 Savassi Region Liberty Square
7
Serra do Curral Southern part of BH
8
Mercado Central
9
Administrative Center of the State Government Buildings designed by Niemayer
Two buildings: Minas (front) and Gerais (back)
Tiradents Palace (Governor’s Palace) Building is hanged by the ceiling
UFMG in the media
Latin-american university with the highest number of patents in the European Patent Office
10
Evolution of Computing Systems
11
Mobile Computer?
Pervasive Computing/Ubiquitous Computing
Emerging technologies are poised to personalize
the user experience radically—in real time and almost everywhere.
It’s not too early to prepare!
Processing Communication “Building Blocks” + +
Entities
Context Sensing
Elements
have
Broad spectrum
Cloud
Logical Physical
is obtained through
classified as sense
stored in
are of Different Types
must fit
12
Outline
• Sensing
• Context
• Localization and tracking
• Processing
• Concluding remarks
13
Fog Computing
Devices with sensing capability
Notification Data
Physical
entities
Logical
entities
Social sensors: • Person: social sensing • Information: origin,
evolution, dissemination • …
Physical sensors: • Objects • People • Environment • …
Virtual sensors: • Events given by a
predicate • ...
Application
Content
Communication
Finance
Event
Notification
Collaboration
Database
Runtime
Queue
Identity
Platform
Object
Storage
Cluster
Block Storage
Infrastructure
Cloud Computing
Complexity
Communication infrastructure Internet, WiFi, 3G, 4G, Bluetooth, Zigbee, ...
14
WSNs IoT
MANETs PSN VANETs Mobile Devices
...
Sensing in a broader context
Notificação Dado Notification Data
Heterogeneous data sources in the fog
HDF2 HDFn ... HDF1
WSNs IoT
MANETs PSN VANETs Mobile Devices
...
Sensing as a Service
Services & Applications
Heterogeneous data sources
In the cloud
HDC2 HDCn ... HDC1
Services & Applications
Fog #1
Fog #2
Fog #3
Fog #…
. . .
Sensing in a broader context
15
IoT
16
Participatory Sensor Networks
17
Notification Data
Physical
entities
Logical
entities
Application
Content
Communication
Finance
Event
Notification
Collaboration
Database
Runtime
Queue
Identity
Platform
Object
Storage
Cluster
Block Storage
Infrastructure
Complexity
Internet, WiFi, 3G, 4G, Bluetooth, Zigbee, ...
Some fundamental building blocks: •Heterogeneous data fusion •Localization & Tracking •Context awareness •Privacy •Cloud offloading • ….
Sensing as a Service
Fontes de dados heterogêneos
DS2 DSn ... DS1
Services and Applications
Theory
Observations/Experiments
18
WSNs IoT
MANETs PSN VANETs Mobile Devices
...
Sensing in a broader context
19
Sensing as a service
•Heterogeneous data sources
•Heterogeneous data fusion
Sensing in a broader context
What time should we go to the airport to catch our flight at 6pm?
• Location
• Traffic condition
• Weather condition
• Unexpected conditions
• Parking availability
• Flight/Airplane
20
Sensing in a broader context
Entities
• Technical name for “thing”
• Different classes with different properties • User
• Software
• Hardware
• ...
• Depending on the set of entities, we can have Internet of things, Web of things, PSNs, …
“Entities” have a key role
21
Context
• “Characterizes” a given entity • State, properties, data, …
• Classified as • physical
• logical
• Depends on the entity
22
Physical context
• Typically measured by a physical sensor
• Example: entity is a person • Define the person’s physical state
• It might depend on the person’s location (e.g., home, hospital)
23
Logical context
• There aren’t many sensors • Social “sensors” but others not currently available
• Example: entity is a person • Define the person’s logical state
• It might depend on people’s perception
24
Understanding the challenges
A broad spectrum
Challenge: treatment of individual sources and combination of them
25
A fundamental challenge
• We have a good idea of how to do information fusion in traditional sensor networks
• However, in a heterogeneous scenario we are far from there
Physical entities
Logical entities
Information fusion for physical + logical contexts
26
Information fusion in ubiquitous computing
• Entity can have different types of sensed data
• Sensed data has spatio-temporal attributes
• Information fusion becomes a dynamic process because of • mobility
• context change
• prediction
• ...
27
What do we need
• Take as an example, integrated circuit design
• For most of the fundamental building blocks in ubiquitous computing, we still need to establish the principles
28
Principles Tools Techniques Methodology
Ubiquitous computing and some fundamental building blocks • Localization and tracking (L&T) – possibly the very first one
• Communication
• Cloud computing
• Information fusion
• Mobility and topology information
• Security
• Cloud offloading
• ...
Challenge: provide useful services
29
Belo Horizonte, Brazil New York, USA
PSN Applicability: City Image
Belo Horizonte, Brazil New York, USA
School
Nightclub
Typical Monday
Bar
Work
Restaurant
Are transitions random?
Belo Horizonte, Brazil New York, USA
School
Nightclub
Typical Monday
Bar
Work
Restaurant
There are more favorable transitions than others
30
Mobility models for social communication or the city DNA
31
Next location Next location
Rejection Indiference Favoring
Mobility models for social communication or the city DNA
32
Next location Next location
Rejection Indiference Favoring
Mobility models for social communication or the city DNA • Example: checkins in Foursquare work as social sensors
33
PSN coverage
High coverage Some common geographic aspects Besides the economical aspect, cultural differences?
34
Sensing seasonality
Foursquare dataset 35
Sensing seasonality
Foursquare dataset 36
Smartphones and sensing
37
28% of American Adults use mobile and social location-based services
http://pewinternet.org/Reports/2011/Location/Report/Smartphones.aspx
Best sensing devices available in the market
L&T: Motivation
• Location awareness plays a key role in different networks
• Different entities require or can take advantage of some sort of location information: • Routing
• Data dissemination
• Applications
• Services
• Many others
Different requirements
38
Dimensions of L&T
• Types of entities
• Techniques: internal vs. external
• Roles
• QoS requirements
• Privacy
• …
39
What types of entities to L&T?
• Different possibilities depending on the scenario • User
• Application
• Service
• Protocol
40
Localization techniques
Different capabilities and possibilities
Different solutions
Interesting research/practical challenges
41
L&T: Roles
• Applications/services and protocols can benefit from location information
• Location and tracking can be used as: • Main role • Support role
• Beyond the location information, tracking techniques can be used to: • Detect and predict trajectories of single or multiple targets (basic service) • Provide customized services for users (will probably happen all time)
42
L&T: Roles
• Main role • L & T techniques are themselves the goals • For instance, driving or walking in an unknown terrain
• Support role • L & T techniques provide information for other entities • For instance, data dissemination for users, applications, …
Lots of possibilities/opportunities
43
Cooperative Target Tracking (CTT)
• Entities cooperate to perform the tracking task
• Target tracking techniques can be applied to augment the entities’ perception of the surrounding context
• Results can be used to actuate on the entity, surrounding environment, etc
44
Energy efficient GPS sensing with cloud offloading
Joint work with Microsoft Research, Redmond Best paper at ACM IPSN’12
45
Entities
Context Sensing
Elements
have
Broad spectrum
Cloud
Logical Physical
is obtained through
classified as sense
stored in
are of Different Types
must fit
How to process all these pieces of information?
46
Autonomic computing
The ability to learn and use that experience for future actions
47
Architecture of an autonomic element
• Fundamental part of the architecture • Managed elements
• Autonomic manager
• Responsible for: • providing its service
• managing its own behavior in accordance with policies
• interacting with other autonomic elements
48
Monitor Execute
Analyze Plan
Knowledge
Managed Element
Sensors Effectors
Autonomic Manager
Autonomic Element
Some perspectives
• Open data platform
• Personalized applications and services
• We need advance the state of the art in several different areas
• We need to better prepare our students!
49
Conclusion Combining the building blocks • Fusion different sensing sources
• Topology modeling, L&T
• Processing them
• Services for different wireless networks
50
Physical Sources
Logical Sources
Sensing Info Fusion L& T Context + +
Notificação Dado
Physical
entities
Logical
entities
Cloud Computing
Complexity
Fog Computing
Notification Data
Sensing Devices
Physical sensors: • Objects • People • Environment • …
Virtual sensors: • Events given
by a predicate • ...
Social sensors: • Person: social sensing • Information: origin,
evolution, dissemination • …
Application
Content
Communication
Finance
Event
Notification
Collaboration
Database
Runtime
Queue
Identity
Platform
Object
Storage
Cluster
Block Storage
Infrastructure
Sensing Actuation
Integration + Reasoning
Integration + Reasoning
Conclusion Integration & Reasoning
51
Conclusion
• Lots of opportunities!!
• This is the area of the “ice cream problem”
52
Algumas questões antes de terminarmos
• Qual é a principal função de uma universidade? • Formar pessoas
• Qual é o principal objetivo da Pós-Graduação? • Formar doutores
• Nos Estados Unidos, principal país de inovação das TICs, para onde vão os doutores formados? • Nove em 10 vão para a indústria!
• No Brasil, existe essa perspectiva? • Sim, sem inovação não teremos oportunidades como nação
• Minha sugestão: • Invista no seu doutorado!
53
Algumas questões antes de terminarmos
• O que é um doutorado? • Processo pelo qual você aprende a fazer pesquisa que gera inovação
• Em que área você deve fazer seu doutorado? • Escolha o seu “sorvete” favorito neste momento
• No futuro, você certamente experimentará outros sabores!
• Onde fazer o doutorado? • Em um bom programa
• UFMG é um deles (possivelmente o melhor do Brasil no momento)
54
• Envolve todos esses aspectos
• Seis professores
• 50+ alunos
55
Thank you!
Antonio Alfredo F. Loureiro [email protected]
Department of Computer Science Universidade Federal de Minas Gerais, Brazil