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.

As people come into contact with image data more often, high quality and clear images attract more attention. Many methods have been proposed to deal with image noise problem including deep learning (DL). However most of them is lack of capability when customers want more perceptual details of the image without information loss. In this paper, a deep residual network based on generative adversarial (GAN) network was proposed to complete the image denoising mission. Firstly, a generative-adversarial network structure based on residual blocks was designed. Secondly, a refined loss function was given to train the GAN network. The well designed loss function can help the generated image to be very close to the clear counterpart (ground truth) while enhancing more details in colours and brightness. Finally, extensive experiments show that our network is not only convincing for images denoising, but also effective for other image process tasks, such as image defogging, medical CT denoising etc., presenting impressive and competitive effects.

Kinematic modeling is essential for planning and controlling continuum robot motion. The traditional Denavit Hartenberg (DH) model involves complex matrix multiplication operations, resulting in computationally intensive inverse solutions and trajectory planning. Solving position and orientation changes in continuum robots using the double quaternion rule can reduce computational complexity. However, existing dual quaternion methods are direct equational transformations of DH rules and do not give a complete modeling process. They usually require more interpretability when applying continuum robot kinematic modeling. This paper uses the dual quaternion method to establish a kinematic model of a continuum robot. It uses a two-section continuum robot model to compare the advantages of dual quaternion and traditional modeling methods. In addition, this paper proposes a five-polynomial interpolation algorithm based on the dual quaternion method for trajectory planning of continuum robots. This method accurately models spatial bending and torsional motions of singularity-free continuum robots.

Advanced glycation end-products (AGEs) are complex compounds closely associated with several chronic diseases, especially diabetes mellitus (DM). Current methods for detecting AGEs are not suitable for screening large populations, or for long-term monitoring. This paper introduces a portable autofluorescence detection system that measures the concentration of AGEs in the skin based on the fluorescence characteristics of AGEs in biological tissues. The system employs a 395 nm laser LED to excite the fluorescence of AGEs, and uses a photodetector to capture the fluorescence intensity. A model correlating fluorescence intensity with AGEs concentration facilitates the detection of AGEs levels. To account for the variation in optical properties of different individuals’ skin, the system includes a 520 nm light source for calibration. The system features a compact design, measuring only 60 mm × 50 mm × 20 mm, and is equipped with a miniature STM32 module for control and a battery for extended operation, making it easy for subjects to wear. To validate the system’s effectiveness, it was tested on 14 volunteers to examine the correlation between AGEs and glycated hemoglobin, revealing a correlation coefficient of 0.49. Additionally, long-term monitoring of AGEs’ fluorescence and blood sugar levels showed a correlation trend exceeding 0.95, indicating that AGEs reflect changes in blood sugar levels to some extent. Further, by constructing a multivariate predictive model, the study also found that AGEs levels are correlated with age, BMI, gender, and a physical activity index, providing new insights for predicting AGEs content and blood sugar levels. This research supports the early diagnosis and treatment of chronic diseases such as diabetes, and offers a potentially useful tool for future clinical applications.