Htc Corporation

Meng-Hsi Wu

Edward Chang

Kuo-Chen Wu

Tung-Peng Wu

Chun-Nan Chou

Chuen-Kai Shie

Chung-Hsiang Chuang

A detecting system, a mobile electronic apparatus and a method for detecting a physiological characteristic thereof are provided. The mobile electronic apparatus includes a sensor unit, a PPG photoplethysmography (PPG) sensor, and a processing unit. The sensor unit has a first, second, and third sensing electrodes. The PPG sensor senses a PPG signal. The processing unit is coupled to the sensor unit and the PPG sensor. When the first and second sensing electrodes detect a voltage difference above a threshold, the PPG sensor is triggered to detect blood volume changes, and when the third sensing electrode is triggered to detect electrical activity of a heart between the first and third sensing electrodes, the PPG sensor is disabled by the processing unit.

Detecting system and mobile electronic apparatus, and method for detecting physiological characteristic thereof method thereof

The disclosure provides a method, an electronic apparatus, and a computer readable medium of constructing a classifier for disease detection. The method includes the following steps. A codebook of representative features is constructed based on a plurality of disease-irrelevant data. Transfer-learned disease features are extracted from disease-relevant bio-signals according to the codebook without any medical domain knowledge, where both the disease-irrelevant data and the disease-relevant bio-signals are time-series data. Supervised learning is performed based on the transfer-learned disease features to train the classifier for disease detection.

Method, electronic apparatus, and computer readable medium of constructing classifier for disease detection

The disclosure provides a method, an electronic apparatus, and a computer readable medium of constructing a classifier for skin-infection detection. The method includes the following steps. A codebook of representative features is constructed based on a plurality of target-disease-irrelevant images. Transfer-learned disease features are extracted from target-disease images according to the codebook without any medical domain knowledge, where the target-disease images are captured by at least one image capturing device. Supervised learning is performed based on the transfer-learned target-disease features to train the classifier for skin-infection detection.

Growing community of inventors

Taoyuan, Taiwan

Meng-Hsi Wu