1 / 22

Implementing a Sentient Computing System

Implementing a Sentient Computing System. Presented by: Jing Lin , Vishal Kudchadkar , Apurva Shah. Sentient Computing Systems. Sentient computing systems are systems which can change their behavior based on a model of the environment they construct using sensor data.

ouida
Download Presentation

Implementing a Sentient Computing System

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Implementing a Sentient Computing System Presented by: Jing Lin , Vishal Kudchadkar , Apurva Shah

  2. Sentient Computing Systems • Sentient computing systems are systems which can change their behavior based on a model of the environment they construct using sensor data. • Sentient computing systems may hold the key to managing tomorrow’s device-rich mobile networks.

  3. Implementing a Sentient System: Active Bat (1) • Location sensing

  4. Implementing a Sentient System: Active Bat (2) • Current Embodiment • Accuracy and Precision • 95% of 3D Bat position readings are accurate to within 3cm • Maximum Location update rate across each radio cell • 150 updates per second

  5. Implementing a Sentient System: Active Bat (3) • Scheduling and power saving • The scheduling process allows the Bat to enter a low-power sleep state. • A 10-bit local ID is used to achieve shorter addressing message and power saving. • Nonmoving Bats are placed into a low-power sleep state.

  6. Modeling the Environment • Use data from sensors and from services • Filter the incoming location data using knowledge of tracked objects’ dynamics • Update the world model using filtered data • Increase fidelity of the model by determining if someone appears to be seated

  7. Software Support for Sentient Systems • Spatial monitor Formalizes imprecise spatial relationships in terms of containment and overlapping relationships between suitable 2D spaces • Timeline-based data storage Data generated by network appliances should be stored in a way that does not require the user to specify its destination.

  8. Applications (1) • Browsing • Model browsers display the environment’s current state, e.g., continuously updated map displaying personnel, furniture, telephones, workstations and other relevant information • Follow-me Systems • Services are made ubiquitously available to “users” by moving their interfaces to the nearest appropriate input or output device

  9. Applications (2) • Novel user interfaces • Mice • Virtual buttons • Augmented reality • Data Creation , Storage and Retrieval.

  10. Future • Sentient computing is more than a solution to the problems of configuration and personalization. • The environment itself will become the user interface.

  11. Limitations • Active Bat requires a large fixed-sensor infrastructure throughout the ceiling. • The system is sensitive to the precise placement of sensors. • Therefore, there are disadvantages in scalability, ease of deployment, and cost.

  12. Location Systems For Ubiquitous Computing By Vishal Kudchadkar ,Jing Lin , Apurva Shah

  13. Introduction • New mobile systems will need to know the location of the things. • Location sensing techniques ….. • Triangulation : uses of multiple measurements from known points to find the location • Proximity : measure nearness from known points • Scene analysis : exam a view from particular vantage point

  14. Location • Physical Location and Symbolic Location • Symbolic Location encompasses abstract ideas of where something is. • Absolute versus Relative • In absolute system a frame of reference is shared by all the objects. • In a relative system each object will have it’s own frame of reference • An absolute location can be transformed into a relative location – relative to a second point of reference

  15. Localized Location Computing • Some systems have location computing capability and insist that they compute their own locations and hence can protect their privacy. • Some systems require objects to periodically respond to a broadcast to tell their position to the system.

  16. Qualities of a Positioning system • Accuracy and Precision: The distance or grain-size denotes the accuracy. Sensor fusion can help improve accuracy. We generally determine the accuracy of the system by checking if it is suitable for the application • Scale : Consider coverage as the area per unit of infrastructure and the number of objects the system can locate per unit area.

  17. Qualities of a Positioning system • Recognition : Applications may take specific action depending on the location of the object and hence location recognition is needed in such systems • Cost : Time Cost includes time to install and setup the system and Space cost is the space the system requires • Limitations : Systems may not function in a specific environment.

  18. Survey of Location Systems • Active Bridge, • Active Bat, • Cricket, • Radar • MotionStar magnetic tracker, • Easy Living, • Smart Floor • E911 are discussed in the paper. We will present one of the systems in detail in the following paper.

  19. Research Directions • Sensor Fusion: • Defined as the use of multiple sensor technologies to create hierarchical and overlapping levels of sensing • Ad hoc Location sensing : • This method uses techniques to locate objects without the use of a central information center or a browser • In this method of locating objects , the nearby objects share information to build about the system

  20. Research Directions (Contd.) • Ad hoc Location sensing : • Triangulation, scene analysis or proximity location sensing methods are used • Location – sensing system accuracy

  21. Strength And Weaknesses • Strength • A good introductory paper on location systems. • It compares pros and cons of various location systems. • Provides a taxonomy which can be used to evaluate the suitability of a location system. • Weakness • This paper addresses only hardware issues but fails to address software issues.

More Related