Transcript Mr. José Manuel Molina

AMBIENT INTELLIGENT
José Manuel Molina López
Catedrático de Ciencia de la Computación e Inteligencia Artificial
2
Ambient Intelligence
Definition
Ubiquitous Computing
Context
Ambient Intelligence
3



Ambient Intelligence (AmI) envisions a future Information Society where
users are proactively, but sensibly provided with services that support their
activities in everyday life
AmI scenarios described by the European Commission Information Society
Technologies Advisory Group (ISTAG) depict intelligent environments
capable of recognising and responding to the presence of different
individuals in a seamless, unobtrusive and often invisible way
AmI is strongly founded on the concept of Ubiquitous Computing (UC),
introduced by Weiser in the early 90s, which presents a world where a
multitude of computational objects communicate and interact in order to
help humans in daily activities.
Ubiquitous Computing
4
“Ubiquitous computing has as its goal the enhancing computer use by
making many computers available throughout the physical environment, but
making them effectively invisible to the user”. [Weiser, 1993]


The main objective for AmI systems is to be invisible but helpful.
Requirements
 technology must be transparent to users
 services must be tailored to user context and preferences
 applications must be interoperable and easy to interact with.
Context
5

Dey defines context as any information that can be used to characterize the
situation of an entity. An entity is a person, place, or object that is
considered relevant to the interaction between a user and an application,
including the user and applications themselves
[Anind K. Dey and Gregory D. Abowd. Towards a Better Understanding of context and contextawareness. Technical Report GIT-GVU-99-22, Georgia Institute of Technology, College of
Computing, June 1999.]

Schmidt et al. define context as knowledge about the users and IT devices
state, including surroundings, situation, and to a less extent, location.
[Albrecht Schmidt, Kofi Asante Aidoo, Antti Takaluoma, Urpo Tuomela, Kristof Van Laerhoven, and
Walter Van de Velde. Advanced interaction in context. In Proceedings of First International
Symposium on Handheld and Ubiquitous Computing,HUC'99, pages 89-101, Karlsruhe,
Germany,September 1999. Springer Verlag].
Context
6




Schilit divides context into three categories:
Computing context, such as network connectivity,
communication costs, and communication bandwidth, and
nearby resources such as printers, displays, and workstations.
User context, such as the users profile, location, people nearby,
even the current social situation.
Physical context, such as lighting, noise levels, traffic conditions,
and temperature.
[Bill Schilit, Norman Adams, and Roy Want.Context-aware computing applications. In
Proceedings of IEEE Workshop on Mobile Computing Systems and Applications, pages
85-90, Santa Cruz, California, December 1994. IEEE Computer Society Press]
Context
7

Important notes about context by Schilit:
–
–
–
–
–
Who ( Identity Awareness).- It’s the way the context distinguish the user
profile to achieve the correct behavior.
What ( Task Awareness).- It concentrates what the user is doing, the task
he is managing and what he want to obtain. It has to do with the
services offered by the system.
Where ( Location Awareness).- Knowledge of the physic location,
When ( Time Awareness).- Acquisition and maintenance of the
information about time and date, static schedules and dynamism of
each user’s diary.
Why (Device behavior).- To easily communicate with the computer in
order to manage everyday tasks, as far as possible, in an implicit way.
8
Research Areas
Communication Technologies
Information Processing
Service-Providing Framework
Applications
Communication Technologies
9


Distributed devices to gather and provide information need networking
functionalities.
ad hoc technologies:

RFID (active tags)

Bluetooth

Zigbee (short-range)

Wi-Fi or WiMax (medium-range)

Broadband cell phone technologies (4G)

NOW common infrastructures based on IP protocols, Internet of Things (IoT).

The IoT, based on the next-generation IPv6, is emerging to be the
communication support of AmI, which requires the participation of
heterogeneous devices and transport technologies.
Information Processing
10

Fusion Technologies

Extract, contextualize and represent information

Areas:


Knowledge Mobilization

Data Mining

Information Fusion

Machine Learning
Ontologies to represent and reason with heterogeneous information.
Service-Providing Framework
11




Distribution of knowledge, which is essential in AmI, can be accomplished
with technologies such as MAS, Web Services and Cloud Computing.
The Multiagent Systems (MAS) paradigm proposes a scenario where
independent, goal-directed, and environment-aware units (the agents) get
coordinated (by collaborating or competing) to accomplish complex tasks.
Web Services allow remote procedures to be requested through
elaborated HTTP calls, including procedures for service choreography
(which messages are created when the service is requested) and
orchestration (which external services are required to complete the task).
Cloud Computing is a recent service-providing model oriented to guarantee
system scalability. Users access to remote computing resources on demand
without regard of the situation of the resource and the communication
technology.
Applications
12

Friendly interfaces to final users: Human-Computer Interaction

Deployment of infraestructure

Areas:

e-Health

Ambient Assisted Living

Surveillance applications

Intelligent avoiding of collisions

Hazardous drug control

Food traceability

Logistics

.. etc.
Research Areas in Ambient Intelligence
13
Users
Healthcare
Security
Disabled
people
Elder care
Accident
prevention
Intelligent
Infrastructure
Logistics
Monitoring
Surveillance
Intrusion
detection
Threat
reaction
4. Applications
Services
HCI
Intelligent Service-Providing Framework
Web
Services
MAS
3. ServiceProvision
Framework
Cloud
Computing
Knowledge
Distributed Knowledge Management
2. Information
Processing
Soft Computing Methodologies
Knowledge
Mobilization
Data Mining
Information
Fusion
Machine
Learning
Ontologies
Semantic Web
Fuzzy Logic
Intelligent Databases
Data Warehouse
Multimedia
Information Integration
Scene Recognition
Context-Awareness
User Profiling
Information
Middleware Abstraction Layer
Internet of Things
Communication
Devices
Data
Wi-Fi
Bluetooth
Sensors
RFID
Tags
UWB
Zigbee 3.5G/4G
Video cameras
1. Supporting
Technologies
14
Open Problems
Non-Intrusive Identification
Evaluation
Mobile sensors
Non-Intrusive Identification
15
• Face Recognition
• And we want context
But now people is walking
Evaluation
16
Mobile Sensors
17