Abstract: The present invention provides a contactless-type sport training monitor method, comprising: selecting at least an image database to recognize a plurality of expressions in the image database; making pre-processing for the plurality of expressions: using a convolutional neural network as a feature point extraction model; acquiring a human image; tracking a first target region and a second target region in the human image; making chrominance-based rPPG trace extraction; using the deep level model to compare the second target region image; and to calculate a post-exercise heart rate recovery achievement ratio, to judge the Rating of Perceived Exertion, and judging whether the human body is under overtraining status or not.

Abstract: The present invention provides an image based blood pressure monitoring method, comprising: acquiring at least a human image information of at least a human skin area; according to the human image information to locate at least a ROI; extracting the human image information of the ROI, and calculate; filtering the average value of the human image information; monitoring the filtered signal; calculating an image pulse transmit time of the filtered signal, and calculating an inter-beat interval of the filtered signal; and employ the specific prediction model, to calculate a systolic pressure value and a diastolic pressure value.

Abstract: The present invention provides an image based blood pressure monitoring method, comprising: acquiring at least a human image information of at least a human skin area; according to the human image information to locate at least a ROI; extracting the human image information of the ROI, and calculate; filtering the average value of the human image information; monitoring the filtered signal; calculating an image pulse transmit time of the filtered signal, and calculating an inter-beat interval of the filtered signal; and employ the specific prediction model, to calculate a systolic pressure value and a diastolic pressure value.

Abstract: The present invention provides an imaging-type heart rate monitoring device and method thereof. It acquires the human image information tracks the target area in the human image information, and extracts the target image in the target area. It transforms the human image information through the first frequency domain transform. It filters the residual noise of the continuous wavelet transform information. It rebuilds the residual noise filtered information by the continuous wavelet transform. It transforms the continuous wavelet transform rebuilt information by the Fourier transform. It obtains a heart rate value through the second frequency domain transformed information.

Abstract: The present invention provides a contactless-type sport training monitor method, comprising: selecting at least an image database to recognize a plurality of expressions in the image database; making pre-processing for the plurality of expressions: using a convolutional neural network as a feature point extraction model; acquiring a human image; tracking a first target region and a second target region in the human image; making chrominance-based rPPG trace extraction; using the deep level model to compare the second target region image; and to calculate a post-exercise heart rate recovery achievement ratio, to judge the Rating of Perceived Exertion, and judging whether the human body is under overtraining status or not.

Abstract: A method for generating a power distribution network (PDN) is provided. A heterogeneous circuit data is input. A plurality of horizontal power lines and a plurality of vertical power lines are determined according to the heterogeneous circuit data. A PDN model of the heterogeneous circuit is determined according to the horizontal power lines and the vertical power lines. Power consumption value is assigned to a plurality of internal nodes of the PDN model of the heterogeneous circuit. The PDN model of the heterogeneous circuit is adjusted to meet a target voltage drop limitation of the heterogeneous circuit data.

Abstract: A method for generating a power distribution network (PDN) is provided. A heterogeneous circuit data is input. A plurality of horizontal power lines and a plurality of vertical power lines are determined according to the heterogeneous circuit data. A PDN model of the heterogeneous circuit is determined according to the horizontal power lines and the vertical power lines. Power consumption value is assigned to a plurality of internal nodes of the PDN model of the heterogeneous circuit. The PDN model of the heterogeneous circuit is adjusted to meet a target voltage drop limitation of the heterogeneous circuit data.