Real-Time American Sign Language Recognition Using Desk and Wearable Computer Based Video
IEEE Transactions on Pattern Analysis and Machine Intelligence
System Level Design as Applied to CMU Wearable Computers
Journal of VLSI Signal Processing Systems - Special issue on system level design
Computers as components: principles of embedded computing system design
Computers as components: principles of embedded computing system design
JouleTrack: a web based tool for software energy profiling
Proceedings of the 38th annual Design Automation Conference
System on Chip or System on Package?
IEEE Design & Test
A System-Level Approach to Power/Performance Optimization in Wearable Computers
WVLSI '00 Proceedings of the IEEE Computer Society Annual Workshop on VLSI (WVLSI'00)
System Design Approach To Power Aware Mobile Computers
ISVLSI '03 Proceedings of the IEEE Computer Society Annual Symposium on VLSI (ISVLSI'03)
Context Awareness by Analyzing Accelerometer Data
ISWC '00 Proceedings of the 4th IEEE International Symposium on Wearable Computers
System Design and Power Optimization for Mobile Computers
ISVLSI '02 Proceedings of the IEEE Computer Society Annual Symposium on VLSI
Design of the QBIC Wearable Computing Platform
ASAP '04 Proceedings of the Application-Specific Systems, Architectures and Processors, 15th IEEE International Conference
Implementation and Evaluation of a Low-Power Sound-Based User Activity Recognition System
ISWC '04 Proceedings of the Eighth International Symposium on Wearable Computers
Power and Size Optimized Multi-Sensor Context Recognition Platform
ISWC '05 Proceedings of the Ninth IEEE International Symposium on Wearable Computers
Design methodology for context-aware wearable sensor systems
PERVASIVE'05 Proceedings of the Third international conference on Pervasive Computing
A systematic approach to the design of distributed wearable systems
IEEE Transactions on Computers
Hi-index | 0.00 |
Wearable computing places tighter constraints on architecture design than traditional mobile computing. The architecture is described in terms of; miniaturization, power-awareness, global low-power design and flexibility or suitability for an application. In this article we present a new methodology based on four metrics that represent different properties. Flexibility, Electronic Packaging, Relative Recognition Performance and Energy Consumption metrics are proposed and evaluated on practical design examples to study different trade-offs. The proof of concept case study is analyzed by studying (a) walking behavior with acceleration sensors (b) office-worker activities with a combination of acceleration and light sensors and (c) a computational task. The results show that the proposed metrics and methodology assists in selecting an optimal architecture for a given application in the domain of wearable computing.