Logo image
General-Purpose Scalable Distributed Wireless Load-Sensing Platform
Thesis

General-Purpose Scalable Distributed Wireless Load-Sensing Platform

Lee, Wei-Cheng
Masters, 國立清華大學, 資訊工程學系所
2017

Abstract

負載 負重 分散式 物聯網 感測 藍芽 無線 可擴充 腳步 姿態 磅秤 重量 節點 平台 主機 嵌入式 體重計 機器學習 秤重 動作偵測 辨識 BLE Bluetooth EcoMini load-sensing load sensing wireless platform scalable distributed scale weight knn gait recognition Bluetooth Low Energy node host embedded system load sensing body scale weight scale machine learning motion detection movement detection
We propose a general-purpose scalable distributed wireless load-sensing platform that serves as infrastructure for applications that necessitate the collaboration among multiple load-sensing units. The load-sensing platform consists of a host subsystem and a node subsystem. A node subsystem comprises one or multiple nodes that perform load-sensing, i.e., weight measurement, and transmit the data to the host via BLE (Bluetooth Low Energy). The host subsystem performs computation for data analysis. We demonstrate the generality of our proposed platform by building a weight scale application and a user-identification application. For the weight application, experimental results show that a four-node collaborative weight scale achieves a lower average absolute error of 0.586 grams than individual nodes, whose absolute errors range from 0.452 to 3.147 grams. In the user-identification application, which uses a kNN model for identifying a person among a small group of people based on the gait, results show the accuracy of up to 98.33%. The results confirm the mobility, flexibility, scalability, and versatility of our proposed load-sensing platform.

Metrics

1 Record Views

Details

Logo image