Abstract: An aerosol generating substrate, an aerosol generating article, and an electronic atomizing device are provided. The aerosol generating substrate includes a base part and a plurality of subparts, the plurality of subparts are located at an outer side of the base part in a first direction, the plurality of subparts are spaced apart from each other in a second direction of the base part, and a space between any two adjacent subparts of the plurality of subparts is a gap space, in which the first direction and the second direction intersect with each other.

Abstract: This application discloses a water quality measurement method, device, equipment and storage medium, which includes: 1) Acquiring multiple sets of training data and using them to train the baseline network iteratively, calculating the error based on the predicted values output by the baseline network and the corresponding labels. 2) Calculating the error state value based on the errors obtained from two consecutive iterations. If the error state value of the current iteration meets the preset conditions, the parameters of the baseline network are updated with the error of the current iteration. Otherwise, the parameters are not updated. The process continues until the baseline network converges. 3) Using the model to obtain water quality measurement results of the wastewater treatment plant. This application addresses the issue present in the existing technologies where effective features from the raw dataset cannot be efficiently extracted, resulting in low accuracy of the measurement results.

Abstract: The invention discloses an UWB NLOS signal recognition method based on the first path of CIR, including constructing a UWB ranging system comprising tags and anchors. The system controls communication between the anchor and tag, processes the raw CIR data obtained from each communication to construct data samples, and labels these samples to build a raw CIR dataset. Peak filtering is then performed on the CIR waveforms in the raw CIR dataset to identify the first path peak points of the data samples. Based on the first path peak points, valid data is determined as new data samples, and one-hot encoding is applied to the data labels. A training dataset is constructed using all new data samples and their corresponding data labels. A machine learning model is then developed and trained using the training dataset, and the trained model is saved for identifying unknown CIR signals.

Abstract: The invention discloses an UWB NLOS signal recognition method based on the first path of CIR, including constructing a UWB ranging system comprising tags and anchors. The system controls communication between the anchor and tag, processes the raw CIR data obtained from each communication to construct data samples, and labels these samples to build a raw CIR dataset. Peak filtering is then performed on the CIR waveforms in the raw CIR dataset to identify the first path peak points of the data samples. Based on the first path peak points, valid data is determined as new data samples, and one-hot encoding is applied to the data labels. A training dataset is constructed using all new data samples and their corresponding data labels. A machine learning model is then developed and trained using the training dataset, and the trained model is saved for identifying unknown CIR signals.