Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
Workshop proceedings of the 6th International Conference on Intelligent Environments
López-Cózar R., Aghajan H., Augusto J., Cook D., O’Donoghue J., Callaghan V., Egerton S., Johnson B., IOS PRESS, Amsterdam, the Netherlands, 2010. 308 pp. Type: Book (978-1-607506-38-6)
Date Reviewed: Jun 16 2011

Despite astonishing advances in computational power over the decades that computers have been in wide use, their connection to the environment in which we live is quite limited. Many devices and systems have computer-based components, but are quite isolated from one another and from the computers we routinely interact with. This collection of papers addresses a variety of issues related to a better integration between the real-world environment we live in and the abstract-world models that computers use.

This book contains contributions to three workshops on related topics: the First International Workshop on Human-Centric Interfaces for Ambient Intelligence (HCIAmI 2010), the Fifth International Workshop on Artificial Intelligence Techniques for Ambient Intelligence (AITAmI 2010), and the First International Workshop on Creative Science--Science Fiction Prototyping for Research Innovation (CS 2010). Each workshop consists of about a dozen papers, so it is impractical to address them all individually.

HCIAmI 2010 focused on ways to make ambient intelligence systems easier to use for humans, often by focusing on the tasks users are trying to accomplish, and offering natural and intuitive interaction methods that make the presence of a computer as transparent as possible. This is especially important for users who have difficulty interacting with conventional computers, such as elderly users or people with disabilities. One approach to doing this is the use of natural language dialog systems, which is an interaction method most people are very familiar with. Although computers have limitations with natural language processing, a limited context in a specific environment often allows the use of dialog models that are suitable for particular tasks.

AITAmI 2010, emphasized the use of sensors in order to provide computers with more information about the actual environment of the users. This ranges from monitoring activities of elderly people for health reasons, to precision agriculture, to quantum computing for intelligent agents.

One paper from this conference--“Quantum Computing: Non-Deterministic Controllers for Artificial Intelligent Agents”--discusses an approach to prototyping futuristic products in the form of applying quantum computing to robots. The first half of the paper is an argument for and a preliminary structure of science fiction prototyping. The latter half of the paper is an application of said prototyping strategy to a hypothetical application (implemented in quantum computer simulators) of quantum computing for artificially intelligent robots.

After discussing science fiction prototyping and the motivation behind such an approach, the paper discusses an application of this prototyping style. The authors present a simple path-finding robot that they implement using a quantum toolkit. This quantum toolkit is the element of technology that does not exist to date, so the paper suggests a simple framework for one. The framework is designed in such a way that the technology need not exist yet. Rather, emulation of a quantum toolkit is all that is required to start building these robots. With the existence of such a toolkit, however, the paper suggests that nondeterministic robots that are capable of learning would be able to solve problems such as path finding.

The quantum toolkit that the authors propose is feasible, if not already implemented. In fact, simulators that simulate quantum space already exist. For example, quantum effects are currently simulated in Hilbert space.

The authors of this paper make an unclear connection, however, between nondeterminism, free will, and artificial intelligence (AI). The paper left us curious as to whether our own free will is really the result of our supposedly nondeterministic human brain. It also left us curious as to whether our human brain is truly nondeterministic, if that is the source of intelligence. Such questions and concerns leave us skeptical that the application of nondeterminism (as with quantum computing, for example) is really as helpful as the authors make it out to be.

Admittedly, this paper is an argument for conceptual prototyping. We agree that quantum computing and nondeterminism introduce truly interesting problems, and the application to AI should not be underestimated. We thought the paper was very well written in design; by agreeing to the statement that science fiction prototyping is a powerful form of innovation, one has no choice but to acknowledge the possibility that a quantum toolkit may empower machines to learn.

Another paper from this conference--“Energy Prediction in Smart Environments”--discusses a relatively new area of research: smart home environment research. The field has currently received the most attention in the areas of activity recognition, visualization, and automation. The paper contributes a new area that the authors argue is becoming especially relevant: the monitoring, analysis, and prediction of energy usage. It provides an analysis of minimum-redundancy maximum-relevancy (mRMR), three machine learning techniques for estimating energy usage, and a case study involving two volunteers.

This paper reports that buildings are responsible for 40 percent of energy use in most countries. The authors rely on a new smart environment system, Computer Augmentation for Smart Architectonics (CASAS), which was built into a three-bedroom apartment building located at Washington State University, with a blueprint figure to illustrate exactly what sensors are installed and where they are located.

The CASAS system provides a logging facility that stores time, date, sensors, and messages for such events as time-sliced concurrent activities (for example, the stove and sink are usually in use simultaneously), times of major appliance usage (the refrigerator is open, the stove is on, the shower is on), and the total power values of major appliances during a time-sliced period.

The paper concludes that the authors’ CASAS system was successfully able to predict energy usage with three machine learning techniques and mRMR feature selection.

“Intelligent Informatics Platform for Precision Agriculture” focuses on Malaysia, and discusses the importance of efficiently and effectively producing and maintaining agricultural ventures. For example, in Malaysia, the agricultural sector is a major contributor to the country’s gross domestic product (GDP). Worldwide agriculture markets have already started deploying information and communications technology (ICT) in agriculture to monitor trends in soil fertility, soil loss, nutrients, and pest management. The paper features two major approaches: precision agriculture and sensor network technologies.

The current state of the art appears to include databases, knowledge bases, and recommendation systems for farmers. These systems allow farmers to research current trends in weather, crops, pests, and more. They also allow farmers to upload photos of their crops to help them identify problems. Some of these systems incorporate the sensors that the authors mentioned to monitor nutrient amounts, soil pH, and temperature. The purpose of a precision agriculture system is to provide advice, causes, and actions that farmers should take.

The authors conclude their paper with the claim that they have successfully deployed this system, but provide no validation framework that indicates that what they did was helpful. The system uses sensor networks to collect information, as well as input data from the farmers (collected via mobile devices), but still does not provide any indication that this made the farmers’ jobs easier, more efficient, or more productive.

Finally, CS 2010 is one of the most unique and interesting conference volumes we have encountered to date. The papers in this section are a hazy blend between the state of the art in computer science, philosophy, and art, and the highly anticipated future of science. The majority of the papers in this conference are written as narratives and short stories, detailing the daily life or dilemma of an individual, robot, or consciousness. The topics range from controlling AI with metathought and metalanguage to artificially intelligent environments.

The narratives do not stop at just their proposed topics; the papers offer a comprehensive peek into the future that intends to inspire current researchers in the field. In the spirit of science fiction prototyping, the monumental leaps in technology that these papers describe are a great source of inspiration, as well as a goal that current technology can only hope to grow toward. Granted, the possibility also exists that these technological advances will have unintended and unanticipated consequences, but it appears that the emphasis at the workshop was more on positive and exciting visions.

Reviewers:  Franz KurfessStephen Holsapple Review #: CR139152 (1201-0014)
Bookmark and Share
  Featured Reviewer  
 
General (D.2.0 )
 
 
Artificial, Augmented, And Virtual Realities (H.5.1 ... )
 
 
Conference Proceedings (A.0 ... )
 
 
General (A.0 )
 
Would you recommend this review?
yes
no
Other reviews under "General": Date
Development of distributed software
Shatz S. (ed), Macmillan Publishing Co., Inc., Indianapolis, IN, 1993. Type: Book (9780024096111)
Aug 1 1994
Fundamentals of software engineering
Ghezzi C., Jazayeri M., Mandrioli D., Prentice-Hall, Inc., Upper Saddle River, NJ, 1991. Type: Book (013820432)
Jul 1 1992
Software engineering
Sodhi J., TAB Books, Blue Ridge Summit, PA, 1991. Type: Book (9780830633425)
Feb 1 1992
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy