Abstract: A single-barometer device, a method for fall detection and a system are provided. The single-barometer device worn on a user is used to measure multiple barometric values continuously by a barometer inside the device. The barometric values are stored in a memory of the single-barometer device. When a current barometric value is produced, the current barometric value is compared with a previous barometric value retrieved from the memory. A barometric difference can be obtained. The barometric difference is then compared with a threshold, and a comparison result is used to determine whether or not a fall event is present. The fall event is confirmed if the barometric difference is larger than the threshold. Further, an acceleration change obtained by an accelerometer inside the single-barometer device can be used to reconfirm the fall event.

Abstract: An establishing method of a retinal layer thickness detection model includes following steps. A reference database is obtained, and an image pre-processing step, a feature selecting step, a training step and a confirming step are performed. The reference database includes reference optical coherence tomographic images. In the image pre-processing step, the reference optical coherence tomographic images are duplicated and cell segmentation lines of retinal layers are marked to obtain control optical coherence tomographic images. In the feature selecting step, the reference optical coherence tomographic images are analyzed to obtain reference image features. The training step is to train with the reference image features and obtain the retinal layer thickness detection model.

Abstract: An establishing method of a retinal layer thickness detection model includes following steps. A reference database is obtained, and an image pre-processing step, a feature selecting step, a training step and a confirming step are performed. The reference database includes reference optical coherence tomographic images. In the image pre-processing step, the reference optical coherence tomographic images are duplicated and cell segmentation lines of retinal layers are marked to obtain control optical coherence tomographic images. In the feature selecting step, the reference optical coherence tomographic images are analyzed to obtain reference image features. The training step is to train with the reference image features and obtain the retinal layer thickness detection model.

Abstract: A machine status and user behavior analysis system includes a detection side device and an analysis side device. The detection side device is electrically connected with the machine. The detection side device includes a data retrieving module, a sensing module, and a data processing module. The data retrieving module retrieves internal data of the machine. The sensing module senses the status of the machine to obtain sensed data. The data processing module processes the internal data of the machine and the sensed data to classify the internal data of the machine and the sensed data into machine status data and operation condition data. The analysis side device is wirelessly connected with the detection side device to receive the machine status data and the operation condition data. The analysis side device includes a data recognizing module which recognizes the machine status data to find a machine abnormal status and recognizes the operation condition data to find user behavior.