ABSTRACT
The safeguarding of scarce water resources is critically dependent on continuous water quality monitoring. Traditional methods like satellite imagery and automated underwater observation have limitations in cost-efficiency and frequency. Addressing these challenges, a ground-based remote sensing system for the high-frequency, real-time monitoring of water parameters has been developed. This system is encased in a durable stainless-steel shell, suited for outdoor environments, and features a compact hyperspectral instrument with a 4 nm spectral resolution covering a 350-950 nm wavelength range. In addition, it also integrates solar power, Wi-Fi, and microcomputers, enabling the autonomous long-term monitoring of water quality. Positioned on a rotating platform near the shore, this setup allows the spectrometer to quickly capture the reflective spectrum of water within 3 s. To assess its effectiveness, an empirical method correlated the reflective spectrum with the actual chlorophyll a(Chla) concentration. Machine learning algorithms were also used to analyze the spectrum's relationship with key water quality indicators like total phosphorus (TP), total nitrogen (TN), and chemical oxygen demand (COD). Results indicate that the band ratio algorithm accurately determines Chla concentration (R-squared = 0.95; RMSD = 0.06 mg/L). For TP, TN, and COD, support vector machine (SVM) and linear models were highly effective, yielding R-squared values of 0.93, 0.92, and 0.88, respectively. This innovative hyperspectral water quality monitoring system is both practical and reliable, offering a new solution for effective water quality assessment.
ABSTRACT
Cervical cancer is a serious threat to the lives and health of women. The accurate analysis of cervical cell smear images is an important diagnostic basis for cancer identification. However, pathological data are often complex and difficult to analyze accurately because pathology images contain a wide variety of cells. To improve the recognition accuracy of cervical cell smear images, we propose a novel deep-learning model based on the improved Faster R-CNN, shallow feature enhancement networks, and generative adversarial networks. First, we used a global average pooling layer to enhance the robustness of the data feature transformation. Second, we designed a shallow feature enhancement network to improve the localization and recognition of weak cells. Finally, we established a data augmentation network to improve the detection capability of the model. The experimental results demonstrate that our proposed methods are superior to CenterNet, YOLOv5, and Faster R-CNN algorithms in some aspects, such as shorter time consumption, higher recognition precision, and stronger adaptive ability. Its maximum accuracy is 99.81%, and the overall mean average precision is 89.4% for the SIPaKMeD and Herlev datasets. Our method provides a useful reference for cervical cell smear image analysis. The missed diagnosis rate and false diagnosis rate are relatively high for cervical cell smear images of different pathologies and stages. Therefore, our algorithms need to be further improved to achieve a better balance. We will use a hyperspectral microscope to obtain more spectral data of cervical cells and input them into deep-learning models for data processing and classification research. First, we sent training samples of cervical cells into our proposed deep-learning model. Then, we used the proposed model to train eight types of cervical cells. Finally, we utilized the trained classifier to test the untrained samples and obtained the classification results. Fig 1. Deep-learning cervical cell classification framework.
