Abstract
With the Internet of Things development, recognizing activities of daily living usually deploy many sensors to objects and environments. However, the sensor events can be triggered by many activities which decreases the accuracy or even fails of inference. In addition, a huge number of personalized activities takes up a lot of space resources and reduces the readability of model. Therefore, this paper adds the duration and period characteristics to improve the inference performance, then adopts the structural model to increase the expendability and standardization. We show that the similar activities inference accuracy has been improved by an average of 8 times. The operating time has been decreased by an average of 0.36 times. This inference method has the good performance and can be used in the future for activity recognition.
Original language | English |
---|---|
Title of host publication | 2019 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) |
Place of Publication | Leicester, United Kingdom |
Publisher | IEEE Xplore |
Pages | 207-212 |
Number of pages | 5 |
ISBN (Electronic) | 978-1-7281-4034-6 |
ISBN (Print) | 978-1-7281-4035-3 |
DOIs | |
Publication status | Published (in print/issue) - 19 Aug 2019 |
Event | 2019 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) - Leicester, United Kingdom Duration: 19 Aug 2019 → 23 Aug 2019 |
Conference
Conference | 2019 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) |
---|---|
Period | 19/08/19 → 23/08/19 |
Keywords
- Activity recognition
- activity relationship
- markov logic network