33 results about "Linear correlation analysis" patented technology

The invention discloses a method for researching correlation between sweet substances in rose essential oil and a sensor based on an electronic nose, and belongs to the technical field of tobacco flavor detection.The method comprises the following steps that firstly, main sweet substances in the rose essential oil are added into cigarettes, and the content of the sweet substances in the rose essential oil is determined by combining sensory rating and grey correlation degree analysis; screening out aroma substances and other sensory qualities which are remarkably related to the sweetness; preparing solutions with different concentration gradients from the screened aroma substances remarkably related to the sweet feeling, scoring the odor intensity and testing the electronic nose to respectively obtain original response data values of the sensor to the aroma substances, and establishing linear correlation analysis through SPSS software to obtain the original response data values of the sensor to the aroma substances. Finally, finding out the electronic nose sensor with the strongest correlation with the sweet substances as WLSGF / A, wherein the correlation between the rose oxide and the WLSGF / A is the best; according to the method, mathematical statistics is combined with sense organs and the electronic nose, so that objective and efficient evaluation of the sweet aroma is realized.

The invention provides a method for measuring, calculating and predicting carbon emission of a long-distance natural gas pipeline based on mixed feature screening and multi-model dynamic optimization. Firstly, multi-dimensional operation parameters are quantified into a historical total carbon emission sequence based on an emission factor method. And screening key feature variables influencing the historical total carbon emission through a mixed feature screening model fusing linear correlation analysis and nonlinear importance evaluation. Then, constructing a multi-model prediction framework containing a BP neural network, a long-short-term memory network model and a dual-channel attention adaptive long-short-term memory network model; the DAA-LSTM model has a parallel dual-channel structure, and a dynamic peak weighted loss function and an adaptive learning rate strategy are adopted for optimization training. And an optimal prediction model is optimized through the comprehensive performance evaluation indexes, so that a future carbon emission prediction result of the pipeline can be obtained. According to the method, the existing technical problems are effectively solved, and the prediction accuracy, efficiency and robustness are remarkably improved.