The oral problems of young children are particularly serious because they are at a critical moment in developing good oral hygiene habits. How to help them maintain oral cleaning through sensors and artificial intelligence technology has become a research point of intelligent Internet of Things. We present an easy accessible monitoring system for evaluating the tooth brushing with smart devices. The system captures the users’ brushing behaviors (e.g., the motion of hands and the acoustic signals during tooth brushing) through the two build-in sensors. Then the collected data is transmitted to the smartphones and evaluated through a designed machine learning-based model. Finally, a DNN model is adopted to significantly improve the accuracy of detecting tooth brush tasks by up to 97.7%.
Narrow-band Photometry of Emission Nebula Using Small-Caliber Optical Telescope
The emission nebula is very common in interstellar matter, and its continuum has several obvious emission lines. In order to study the chemical elements in the emission nebula, this paper uses a small optical telescope with Hα, [SII], [OIII] narrow-band filters to select four emission nebulae for observation. A lot of results can be obtained by analyzing the experimental data. For example, in most of the emission nebulae, the content of Hα is much larger than [SII] and [OIII], and in the supernova remnants, the content of Hα is less. This study proposes a new method of extended source photometry, and estimates the brightness of the selected emission nebula in each band. This method also helps to plan the exposure time for large telescopes, thus can improve observation efficiency.
An Intelligent Directional Following Device Based on Ultrasonic Positioning and Robust PI Controller
The project designs an intelligent directional following device based on ultrasonic positioning and strong robust PI controller. It locates and follows directly under the beacon’s guidance, which brings fast calculation, high positioning accuracy and sensitivity, low energy consumption, and easy control. New algorithm based on four receiving sensors also makes positioning more accurate. Using robust PI controller let it move much steadier and more adaptable to complex environments, with strong anti-interference ability. Its warning system ensures safety and no touching obstacles. Moreover, 3 highly reliable Omni-Wheels, 120° apart, make it move instantaneously in any direction. The device can be widely used indoors and has been granted two patents and won the National Gold Medal.