Real-time fire detection system based on dynamic time warping of multichannel sensor networks

Quantifying the Natural Climate Solution Potential of Agricultural Systems by Combining Eddy Covariance and Remote Sensing

“…To understand how well hourly and monthly average daily NEE time series corresponded, we determined the mean absolute percent error (MAPE), Pearson correlation coefficient ( r ), and the dynamic time warping Euclidian distance (DTW d ) between gapfilled and non‐gapfilled time series of the US‐DFK tower and ERF timeseries consisting of IWG, soybeans, corn, alfalfa, pasture, and forest. DTW d was used to understand similarity among time series (Baek et al., 2021; Bellman & Kalaba, 1959), which was computed using the function dtw from the package “dtw” in R (Giorgino, 2009).…”

“…Because RS model input data were daytime only, we compared gapfilled average daytime ERF data (Rs > 10 W m −2 ) for each crop field and vegetation type and converted to daily sums of NEP (g C m −2 ), which resulted in a better fit between the two timeseries. For the comparison of annual NEP from harvest, RS models, and ERF NEP, we assumed that-NEE from ERF approximates NEP in the crop fields on an annual basis, as the cumulative, total difference between all CO 2 sources and sinks within the entire system (Teets et al, 2018) (Baek et al, 2021;Bellman & Kalaba, 1959), which was computed using the function dtw from the package "dtw" in R (Giorgino, 2009).…”

Research on Multi-Sensor Fusion Indoor Fire Perception Algorithm Based on Improved TCN

“…The described methods ameliorated the problem that BP neural networks tended to fall into local minima during the training process. Baek et al [20] used a dynamic time warping (DTW) algorithm to evaluate the similarity of sensor data before and after a fire. In addition, the k-out-of-p rule based on p-channel sensor data was proposed to make decisions adaptively.…”

“…To begin with, the time dimension information of sensor data was not sufficiently considered. In the early stage of a fire, the sensor data showed a steady upward or downward trend in the long term, but showed a random opposite trend or even irregular fluctuation in the short term [20]. Therefore, false alarms or missing alarms were prone to occur, which challenged accuracy and stability of fire perception systems.…”

Signal Feature Extraction Method of Three-Band Infrared Flame Sensor

“…Modern fire-detecting technologies include video-image flame detection 5,6 and multi-sensor detection. [7][8][9] Modern flame detection technology pays more attention to the essence of flame, and achieves accurate flame identification with detection algorithm, which has higher practical value than conventional methods. 10,11 Indeed, any well-established detection technique can be selected to detect the flame.…”