Pervasive Computing Research Projects

Programmable Pervasive Spaces

Goal

Research groups in both academia and industry have developed prototype systems to demonstrate the benefits of pervasive computing in various application domains. These projects have typically focused on basic system integration—interconnecting sensors, actuators, computers, and other devices in the environment. Unfortunately, many first-generation pervasive computing systems lack the ability to evolve as new technologies emerge or as an application domain matures. Integrating numerous heterogeneous elements is mostly a manual, ad hoc process. Inserting a new element requires researching its characteristics and operation, determining how to configure and integrate it, and tedious and repeated testing to avoid causing conflicts or indeterminate behavior in the overall system. The environments are also closed, limiting development or extension to the original implementers. To address this limitation, the University of Florida’s Mobile and Pervasive Computing Laboratory is developing programmable pervasive spaces in which a smart space exists as both a runtime environment and a software library. Service discovery and gateway protocols automatically integrate system components using generic middleware that maintains a service definition for each sensor and actuator in the space. Programmers assemble services into composite services and applications, which third parties can easily implement or extend.

Objectives

The objective of the programmable pervasive spaces project is to design and implement a viable reference architecture and a corresponding middleware implementation for future pervasive computing environments that are open, extensible, adaptive, self-configurable, and self-integrative. The objective is to tame the complexity of smart environments and make them more programmable and utilizable. Our approach should be contrasted with engineered and integrated environments that are very costly to build, and very difficult to change or extend. Additionally, our objective is to develop novel programming models that will assist programmers to easily and rapidly develop sapplications based on the available sensors and actuators, or by composing existing services and contexts. To ensure a commercialization path and a wider adoption of our framework, we aim at developing an integrated development environment (IDE) to enable programmers to develop and test applications effectively.

People

  • Dr. Sumi Helal
  • Dr. Choonhwa Lee
  • Erwin Jansen
  • Hen-I Yang

Publications

  • A. Helal, "Programming Pervasive Spaces," the Standards and Emerging Technologies Department, IEEE Pervasive Computing magazine, Sumi Helal, Dept. Editor, Volume 4, Number 1, January-March 2005. (pdf)
  • A. Helal, W. Mann, H. Elzabadani, J. King, Y. Kaddourah and E. Jansen, "Gator Tech Smart House: A Programmable Pervasive Space", IEEE Computer magazine, March 2005, pp 64-74. (pdf)
  • H. Yang, E. Jansen, A. Helal and W. Mann, “ An IDE for Programmable Pervasive Spaces Based on a Context-Driven Programming Model,” Submitted to the 4 th IEEE International Conference on Pervasive Computing and Communications (PerCom), Pisa, Italy, March 2006. (pdf)
  • E. Jansen, B. Abdulrazak, H. Yang, J. King and A. Helal, "A Programming Model for Pervasive Spaces," Submitted to the 3rd International Conference on Service Oriented Computing, Amsterdam, The Netherlands, December 12-15, 2005. (pdf)
  • H. Yang, E. Jansen and A. Helal, "A Comparison of Two Programming Models for Pervasive Computing," Submitted to the Workshop on Ubiquitous Networking and Enablers to Context Aware Services . In conjunction with the IEEE/IPSJ International Symposium on Applications and the Internet (SAINT), Phoenix, Arizona, January 2006. (pdf)
  • A. Helal, C. Lee and E. Jansen, "An Ontology-Enabled Pervasive Computing Middleware Architecture," University of Florida Technical Report, May 2004. Internal Report, University of Florida, 2003.


SensAble - Scalable Query Processing in Service Oriented Sensor Networks

Goal

The rapid increase in deployment of sensor networks, from industrial plants to our homes, has given rise to a vast number of applications. The need for an easy and efficient mechanism for sensor based application development led to the design of service oriented sensor networks. However, the vast amount of data being generated by them has also made information processing a key requirement for many end-user applications. Research in data querying, acquisition and processing techniques for wireless sensor networks (WSN) has been active for the last few years. But unlike traditional WSNs, in service oriented sensor networks, data processing resources are not only distributed amongst the low-level nodes but are also present at the service layer.

Our goal is to design new data processing and querying techniques which make use of multi-level resources available in service oriented sensor networks. We are working on developing a number of techniques for maintaining distributed sensor history and optimizing load distribution between the hardware nodes and the service layer. We are also working on developing information processing techniques for detecting and tracking phenomena and querying more abstract derived data types which cannot be obtained directly from sensors deployed in the network.

Objectives

The Mobile and Pervasive Computing Laboratory at the University of Florida developed Atlas, the world's first plug-and-play service oriented sensor and actuator platform. Our objective is to create a full fledged data acquisition and query processing system running on top of Atlas. The optimizations provided by this system, in combination with the plug-and-play capability and programmability of Atlas, will allow users to easily develop and deploy applications involving complex monitoring and data analysis tasks.

People

  • Dr. Sumi Helal
  • Raja Bose
  • Anil Moola


The Sensor Platform Project - Self-Integrative Sensor Network

Goal

Our goal is to create a sensor network platform (hardware) and associated software architecture that will allow for sensors to be utilizable (programmed) within a highly programmable pervasive space framework (see Project I). Once a sensor or an actuator is powered on, it should be immediately made visible to other services and applications and can be utilized by a programmer in a new application.

Objectives

The overall self describing sensor network approach is based on the need to provide a scalable, plug and play, smart sensor network that is more flexible and maintainable. The approach leverages both mature and new technologies and standards to develop the system architecture composed of the sensor platform architecture, sensor network hierarchy, and associated software framework. The main approach consists of empowering the sensor network by using surrogate code located on the sensor node to allow interpretation of the data and sensor node control. Our sensor network hardware platform includes RF communications, EEPROM for data storage, EEPROM for surrogate storage, and microprocessor for communication and data manipulation.

An actual platform has been produced and plans are in the work to enable larger scale production to allow sensor network and sensor-based research groups to obtain our platform. For more information visit www.sensorplatform.org.

People

  • Dr. Sumi Helal
  • Steven Pickles
  • Jeffery King
  • Raja Bose
  • James Russo
  • Steve Vander Ploeg

Publications

  • www.sensorplatform.org
  • J. Russo, A. Helal, J. King, R. Bose, "Self-Describing Sensor Networks Using a Surrogate Architecture," Internal Report, June 2005. (pdf)
  • M. Ali, W. Aref, R. Bose, A. Elmagarmid, A. Helal, I. Kamel, M. Mokbel, "NILE-PDT: A Phenomenon Detection and Tracking Framework for Data Stream Management Systems", Proceedings of the Very Large Databases Conference (VLDB), Trondheim, Norway August 2005. (pdf)

 

Self Sensing Spaces

Goal

In this project we explore (1) emerging sensor network technology, (2) real world modeling techniques, (3) Computer Vision, and (4) self-organizing system principles, to realize the vision of self sensing spaces. Our vision is to create new capabilities in which smart spaces such as homes sense themselves and their residents; create their respective real world models; and enact an accurate mapping between the real world model elements and the physical world. If realized, this vision will enable many applications that rely on remote monitoring/intervention such as for the elderly and the disabled.

Objectives

Our objective is to create a technology and systems that allow spaces to automatically detect their main aspects (e.g., floor plans, type of rooms etc.), and for objects (e.g., furniture pieces, appliances, etc.) to also be identified automatically. This enables the on-the-fly and incremental creation of real-world models of the pervasive space. The identification and self-sensing encompasses sensing of the software components needed to interact - within the model - with the model elements. This renders an automatically created, interactive real-world model of the physical space. The model can be used in many applications, most noteably in remote monitoring and intervention in the case of older people and those with disability. In this application, intervention occurs by activating actuators, which are mapped in the real world model to objects in the elderly's home. Intervention is limited to objects equipped with actuators. For instance, will it is posible to monitor a chair and its exact and current location in a house, it will not be possible to remotely move the chair from one place to another. It will be possible however to monitor the location and status (on/off) of a set of stove burners, as well as intervene to alter their status.

People

  • Dr. Sumi Helal
  • Hicham Zabadani
  • Dr. Mark Schmaltz

Publications

  • H. El-Zabadani, A. Helal, W. Mann and M. Schmaltz, "PerVision: An integrated Pervasive Computing/Computer Vision Approach to Tracking Objects in a Self-Sensing Space," Submitted to the 4th IEEE International Conference on Pervasive Computing and Communications (PerCom), Pisa, Italy, 2006. (pdf).
  • H. El-Zabadani, A. Helal, B. Abudlrazak, and Erwin Jansen, “Self-Sensing Spaces: Smart Plugs for Smart Environments,” Proceedings of the third International Conference On Smart homes and health Telematic (ICOST), Sherbrooke, Québec, Canada, July 2005. (pdf)

Location Tracking Sensors/Systems in Pervasive Spaces

Goal

To investigate location tracking technologies and to create passive and active sensors that would enable application level development of location based services in a pervasive space. The goal is to achieve a high precision location and tracking of presence, position and orientation. Another goal of the project is to achieve cost-effectiveness, reliability, and to shield sensor technology developments or changes from the application development process.

Objectives

  • Evaluate Sensor Network Technology in the domain of location tracking.
  • Experiment with Ultrasonic based technology and develop prototype systems to assess its usability.
  • Design and prototype a totally passive pressure sensor for use in a smart floor grid to achieve unincumbered tracking.
  • Formally model smart floors capturing sensor grid topology, sensor characteristics, foot shape, walking models, and overall cost factors.
  • Analyze the formal model using Monte Carlo simulation to answer accuracy/cost tradeoff questions.
  • Based on the experimental study, use the passive sensor grid to implement an accurate and cost/effective smart floor system.
  • Design predictive algorithms to enable smartfloor based location tracking system to function fairly accurately despite multiple failures of sensor nodes.
  • Port the system to the Smart House and integrate it as a reliable service bundle.

People

  • Dr. Sumi Helal
  • Youssef Kaddoura
  • Jeff King
  • Ahmad El-Kouch
  • Bryan Winkler

Publications

  • Y. Kaddourah, J. King and A. Helal, “Cost-Precision Tradeoffs in Unencumbered Floor-Based Indoor Location Tracking,” Proceedings of the third International Conference On Smart homes and health Telematic (ICOST), Sherbrooke, Québec, Canada, July 2005. (pdf)
  • Sumi Helal, Bryon Winkler, Choonhwa Lee, Youssef Kaddourah, Lisa Ran, Carlos Giraldo and William Mann, "Enabling Location-Aware Pervasive Computing Applications for the Elderly" Proceedings of the First IEEE Pervasive Computing Conference to be held June 2003 in Fort Worth, Texas. (pdf)


Assistive Environments - Pervasive Computing for the Elderly and the Disabled:

SmartWave: Meal Preparation System for the Elders

Goal

To help elderly people cook independently despite visual or cognitive impairments. The goal is to create a pervasive microwave based cooking system which makes it easier for elderly people to enjoy a hot meal without having to read cooking instructions or interact with the microwave buttons. Additionally, SmartWave provides memory and coordination assistance to aid elderly with minor cognitive impairment.

Objectives

The project uses a modified microwave along with an RFID reader to allow the microwave to be automatically programmed with the correct cooking instructions. In addition, the microwave is integrated into the smart house environment and uses its alert and reminder capabilities. SmartWave sets itself upon sensing a food packet near it. Video cues are optionally triggered (such as in case of elders needing cognitive assistance) and a few sensors are actuated (including the microwave over door, and the location based sensors.

People

  • Dr. Sumi Helal
  • James Russo
  • Andiputranto Sukojo
  • Dr. William Mann
  • Rick Davenport

Publications

  • J. Russo, A. Sukojo, S. Helal, R. Davenport, and W. Mann, "SmartWave Intelligent Meal Preparation System to Help Older People Live Independently," Proceedings of the Second International Conference on Smart homes and health Telematic (ICOST2004), September 2004, Singapore. (pdf)



Assistive Environments - Pervasive Computing for the Elderly and the Disabled:

Elder Cognitive Assistant

Goal

Design, and implement and extensively test an indoor/outdoor elder digital assistance and a number of associated applications and services. The goal is to overcome the challenging task of designing a powerful and capable platform that can be utilized by a simple voice based interface, that can work autonomously outdoors but that can exploit the pervasive space and its sensor networks indoor. Another challenge is to use as much commercial off the shelf components (COTS) and produce a replicable Elder Assistant platform that can be used in extensive clinical and usability studies.

Objectives

Out emphasis is directed towards elders with AD with the main goal of assisting them to overcome difficulties in carrying out basic daily activities by means of reminders, orientation, and context-sensitive training, and monitoring. Indoor, the elder cognitive assistant should provide (1) Attention Capture and (2) cueing capabilities. The assistant itself should be decoupled from the contents and the events of interests. It is currently designed to be expanded with any type of reminders, training, or cueing. It currently supports the following:

  • As a reminder for critical tasks (to take medications, to eat at meal times, to go see the doctor, to call son on his birthday, or to feed the pet). This function is proactive and obviously does not require patient initiation.
  • As a training tool to perform step-by-step tasks. Examples of currently supported training include preparing a meal and ensuring hydration. Future training will include performing hygienic routines.
  • As a monitoring tool to record the activities performed by the elder. Here mPCA acts proactively but does not interact with the elder.

Outdoor, the cognitive assistant offers basic geographical and contextual orientation, direction and navigation. It will also provide a hands-free voice based interface to certain web services include life-line like services and other value added services. The assistant is based on a pendent I/O device form factor. The pendent is in constant communication with a smart phone and a PDA. In the future we will attempt a design that does not require a PDA.

People

  • Dr. Sumi Helal
  • Dr. William Mann
  • Carlos Giraldo
  • Youssef Kaddoura
  • Hicham Zabadani

Publications

  • C. Giraldo, S. Helal, W. Mann, "mPCA - A Mobile Patient Care-Giving Assistant for Alzheimer Patients" First International Workshop on Ubiquitous Computing for Cognitive Aids (UbiCog'02). In conjunction with The Fourth International Conference on Ubiquitous Computing (UbiComp'02).,Göteborg, Sweden, Oct 02.
  • A. Helal, W. Mann, C. Giraldo, Y. Kaddoura, C. Lee and H. Zabbadani, "Smart Phone Based Cognitive Assistant," Proceedings of the The 2nd International Workshop on Ubiquitous Computing for Pervasive Healthcare Applications, Seattle, WA, October 12, 2003.


TeCaRob: Tele-Care using Tele-presence and Robotic Technology for Assisting People with Special Needs

Goal

An imminent crisis in healthcare and People with special Needs (PwSN: elderly and people with disabilities) care threatens America's economy and quality of life. In addition to the current overextension of healthcare services and sharply rising prices, demographics adversely impact our healthcare system. Add to these factors, PwSN home HealthCare needs have been increasing, the existing HealthCare delivery faces a shortage of professionals, and the existing technology (including Assistive Robotics, Smart Houses And Tele-nursing) lack the ability to provide a complete solution for these populations. This implies that there is an urgent need for a new, more effective solution. Our vision is to create a new concept of Scalable Home Care Delivery, mainly for frail elders, that provide customized, on-demand remote assistance. The goal is to build a system based on a guided robot that interacts with the resident in his smart home, and that allows caregivers, family and friend to interact and to tele-presence to deliver detailed care or assistance that often requires close physical interaction.

Objectives

The TeCaRob project combines research in robotics, pervasive computing, tele-presence, and virtual and augmented reality to extend the definition of tele-care/tele-nursing. The objective is to create a system that includes the virtual and interactive physical presence aspect. The idea is to build a system that allows caregivers to provide assistance and services remotely. TeCaRob system is a generic platform that can be used by diverse caregivers, which enables various tele-care practices including tele-rehabilitation, tele-nursing, tele-medicine, tele-psychotherapy, or even simple tele-presence with a close family member. The system consists of two subsystems: the end-user residence subsystem and the caregiver's remote operation center subsystem.

TeCaRob end-user residence subsystem

The Tele-Care Robotic System assisting a frail elder at home

 

TeCaRob caregiver's remote operation center subsystem

 

TeCaRob robot

People

  • Dr. Sumi Helal
  • Dr. Bessam Abdulrazak

Publications

  • A. Helal and B. Abdulrazak, "TeCaRob: Tele-Care using Telepresence and Robotic Technology for Assisting People with Special Needs," International Journal of Human-friendly Welfare Robotic Systems, Vol. 7, No. 3, September 2006.(pdf)


Universal Remote Control Toolkit for Atlas

Goal

The aim of this project is to provide a universal, context-aware, plug-n-play remote control for any smart space with Atlas. With that we want to provide an intuitive WYSIWYG Configuration Utility which will enable the user to create on-the-fly user interfaces for the remote, with no code change.

Objectives

The emphasis of this project is to create a distinct separation between application programming and user interface programming. This project would enable a user to customize his own user interface without a need to write any code. There are number of widgets which can be used to create a variety of user interfaces. The user can fine tune it easily again and again.

To provide context-awareness, the infrastructure on the Pocket PC can generate the required user interface based on the user's location and proximity to devices. The description of user interfaces is provided in XML format. The user interfaces are highly customizable to each user's preference. The infrastructure processes these XML files to generate the user interfaces.

People

  • Dr. Sumi Helal
  • Rohin Sethi
  • Hen-I Yang