From the lab into the wild: Design and deployment methods for multi-modal tracking platforms

详细信息    查看全文

• 作者：Philipp Sommer^a ; ^{phsommer@acm.org" class="auth_mail" title="E-mail the corresponding author} ; Branislav Kusy^a ; ^{brano.kusy@csiro.au" class="auth_mail" title="E-mail the corresponding author} ; Raja Jurdak^a ; ^{raja.jurdak@csiro.au" class="auth_mail" title="E-mail the corresponding author} ; Navinda Kottege^a ; ^{navinda.kottege@csiro.au" class="auth_mail" title="E-mail the corresponding author} ; Jiajun Liu^a ; ^{jiajun.liu@csiro.au" class="auth_mail" title="E-mail the corresponding author} ; Kun Zhao^a ; ^{kun.zhao@csiro.au" class="auth_mail" title="E-mail the corresponding author} ; Adam McKeown^b ; ^{adam.mckeown@csiro.au" class="auth_mail" title="E-mail the corresponding author} ; David Westcott^b ; ^{david.westcott@csiro.au" class="auth_mail" title="E-mail the corresponding author}
• 关键词：Wireless sensor networks ; Tracking ; Activity detection ; GPS ; Energy harvesting
• 刊名：Pervasive and Mobile Computing
• 出版年：2016
• 出版时间：August 2016
• 年：2016
• 卷：30
• 期：Complete
• 页码：1-17
• 全文大小：2155 K

文摘

The high energy consumption of GPS modules has kept long-term outdoor localisation with battery-powered devices an unsolved challenge. While low-power sensors can trigger GPS sampling to reduce energy consumption, validating the long-term reliability of these sensors in unconstrained environments is challenging due to sensor drifts and the lack of ground truth data in the field. We describe the design of our feature-rich platform and our progressive approach for characterising and validating its multiple sensing modalities in long-term deployments. Using empirical data collected from both controlled experiments and wild flying foxes, we characterise the tracking accuracy, wireless connectivity, energy harvesting, and cross-validate sensing modalities against their GPS counterparts. The results show that accelerometer, magnetometer, and pressure sensor can estimate flying speed and altitude well with relatively small errors in the wild. We further study the utility of multi-modal activity recognition under real-world conditions and demonstrate the potential for significantly increased resolution in triggering GPS samples.