论文信息 - Exploring Hardware Heterogeneity to Improve Pervasive Context Inferences

Exploring Hardware Heterogeneity to Improve Pervasive Context Inferences

Context-aware inference apps have become pervasive as a result of the Internet of Things (IoT). However, most of these apps run continuously on a single device, resulting in limited sensor coverage and high energy consumption. Recent advances in IoT devices, specifically hardware heterogeneity, can be leveraged to improve the accuracy and energy efficiency of context inferences.

Mani B. Srivastava | Chenguang Shen

[1] Cecilia Mascolo,et al. DSP.Ear: leveraging co-processor support for continuous audio sensing on smartphones , 2014, SenSys.

[2] Majid Sarrafzadeh,et al. Determining the Single Best Axis for Exercise Repetition Recognition and Counting on SmartWatches , 2014, 2014 11th International Conference on Wearable and Implantable Body Sensor Networks.

[3] Richard P. Martin,et al. Toward Detection of Unsafe Driving with Wearables , 2015, WearSys@MobiSys.

[4] Zhen Wang,et al. Supporting Distributed Execution of Smartphone Workloads on Loosely Coupled Heterogeneous Processors , 2012, HotPower.

[5] Mani B. Srivastava,et al. Exploiting processor heterogeneity for energy efficient context inference on mobile phones , 2013, HotPower '13.

[6] Nicholas D. Lane,et al. DeepEar: robust smartphone audio sensing in unconstrained acoustic environments using deep learning , 2015, UbiComp.

[7] Ratul Mahajan,et al. Beam: Ending Monolithic Applications for Connected Devices , 2016, USENIX Annual Technical Conference.

[8] Jie Liu,et al. Improving energy efficiency of personal sensing applications with heterogeneous multi-processors , 2012, UbiComp '12.

[9] Bernt Schiele,et al. Discovery of activity patterns using topic models , 2008 .