In order to develop a cough recognition model, the government applied "supervised learning" based on the "convolution network" (CNN). Receive the feature of a one-second-long acoustic signal as an input signal, output a binary signal of 1 (cough) or 0 (other) and set it to lower the learning rate value if the learning rate is stagnant for a period of time to optimize the learning rate.
Professor Park Yong-hwa of the Mechanical Engineering Department (photo by KAIST)
Amid the unprecedented crisis, artificial intelligence develops the Corona 19 Diagnostic Kit in just weeks and determines whether or not it is infected in just seconds with the innovative improvement in accuracy. In the non-face-to-face untact era such as AI face recognition and thermal imaging system, AI videoconferencing and education solutions, distribution and logistics, artificial intelligence is performing brilliantly in various places and regions.
On August 3rd, an article about the "Coughing Recognition Camera" co-developed by SM Instruments with the Korea Advanced Institute of Science and Technology (KAIST) was reported through the Hankyoreh News.
At a time when the Corona 19 virus is spreading, the use of a "cough-recognition camera" in public places and many dense facilities will greatly help prevent and detect the virus early.
You can find out more at the link below.
SM Instruments will continue to make efforts to develop the most innovative and convenient products in the world.