Real-time/online activity recognition (AR) is an important technology in smart Internet of Things (IoT) systems where usersare assisted by smart devices in their daily activities. How to generate appropriate feature representation from sensor event streamingis a challenging issue for accurate and efficient real-time AR. Previous AR models that rely on explicit domain knowledge are notappropriate for online recognition of complex human activities. We propose to use unsupervised learning to learn about the latentknowledge and embed the activity probability distribution prediction as high-level features to boost real-time AR performance. Theproposed approach first learns the latent knowledge from explicit-activity window sequences using unsupervised learning, and derivesthe probability distribution prediction of activity classes for a given sliding window. Our approach then feeds the prediction with otherbasic features of the sliding window into a classifier to produce the final class result on each event-count sliding window. Experimentson five smart home datasets show that the proposed method achieves a higher accuracy by at least 20% improvement on F1 scorethan previous traditional algorithms, while maintaining a lower time cost than deep learning based methods. An analysis on the featureimportance shows that the addition of probability distribution prediction about activity classes leads to a promising direction forreal-time AR.
To View the Base Paper Abstract Contents
Now it is Your Time to Shine.
Great careers Start Here.
We Guide you to Every Step
Success! You're Awesome
Thank you for filling out your information!
We’ve sent you an email with your Final Year Project PPT file download link at the email address you provided. Please enjoy, and let us know if there’s anything else we can help you with.
To know more details Call 900 31 31 555
The WISEN Team