ABSTRACT
Ultraviolet-visible (UV-Vis) absorption spectroscopy, due to its high sensitivity and capability for real-time online monitoring, is one of the most promising tools for the rapid identification of external water in rainwater pipe networks. However, difficulties in obtaining actual samples lead to insufficient real samples, and the complex composition of wastewater can affect the accurate traceability analysis of external water in rainwater pipe networks. In this study, a new method for identifying external water in rainwater pipe networks with a small number of samples is proposed. In this method, the Generative Adversarial Network (GAN) algorithm was initially used to generate spectral data from the absorption spectra of water samples; subsequently, the multiplicative scatter correction (MSC) algorithm was applied to process the UV-Vis absorption spectra of different types of water samples; following this, the Variational Mode Decomposition (VMD) algorithm was employed to decompose and recombine the spectra after MSC; and finally, the long short-term memory (LSTM) algorithm was used to establish the identification model between the recombined spectra and the water source types, and to determine the optimal number of decomposed spectra K. The research results show that when the number of decomposed spectra K is 5, the identification accuracy for different sources of domestic sewage, surface water, and industrial wastewater is the highest, with an overall accuracy of 98.81%. Additionally, the performance of this method was validated by mixed water samples (combinations of rainwater and domestic sewage, rainwater and surface water, and rainwater and industrial wastewater). The results indicate that the accuracy of the proposed method in identifying the source of external water in rainwater reaches 98.99%, with detection time within 10 s. Therefore, the proposed method can become a potential approach for rapid identification and traceability analysis of external water in rainwater pipe networks.
ABSTRACT
Microscopic phytoplankton segmentation is an important part of water quality assessment. The segmentation of microscopic phytoplankton still faces challenges for computer vision, such as being affected by background impurities and requiring a large number of manual annotation. In this paper, the characteristics of phytoplankton emitting fluorescence under excitation light were utilized to segment and annotate phytoplankton contours by fusing fluorescence images and bright field images. Morphological operations were used to process microscopic fluorescence images to obtain the initial contours of phytoplankton. Then, microscopic bright field images were processed by Active Contour to fine tune the contours. Seven algae species were selected as the experimental objects. Compared with manually labeling the contour in LabelMe, the recall, precision, FI score and IOU of the proposed segmentation method are 85.3%, 84.5%, 84.7%, and 74.6%, respectively. Mask-RCNN was used to verify the correctness of labels annotated by the proposed method. The average recall, precision, F1 score and IOU are 97.0%, 86.5%, 91.1%, and 84.2%, respectively, when the Mask-RCNN is trained with the proposed automatic labeling method. And the results corresponding to manual labeling are 95.3%, 86.1%, 90.3%, and 82.8% respectively. The experimental results show that the proposed method can segment the phytoplankton microscopic image accurately, and the automatically annotated contour data has the same effect as the manually annotated contour data in Mask-RCNN, which greatly reduces the manual annotation workload.