Search

Burn wound depth is a significant determinant of patient treatment. Typically, the evaluation of burn depth relies heavily on the clinical experience of doctors. Even experienced surgeons may not achieve high accuracy and speed in diagnosing burn depth. Thus, intelligent burn depth classification is useful and valuable. Here, an intelligent classification method for burn depth based on machine learning techniques is proposed. In particular, this method involves extracting color, texture, and depth features from images, and sequentially cascading these features. Then, an iterative selection method based on random forest feature importance measure is applied. The selected features are input into the random forest classifier to evaluate this proposed method using the standard burn dataset. This method classifies burn images, achieving an accuracy of 91.76% when classified into two categories and 80.74% when classified into three categories. The comprehensive experimental results indicate that this proposed method is capable of learning effective features from limited data samples and identifying burn depth effectively. [ABSTRACT FROM AUTHOR]

At present, scholars mainly study the relationship between nanobubbles and useful minerals, often ignoring the influence of bubbles on fine gangue minerals. When selecting nickel sulfide ore, scholars often faced with mudded and irrepressible serpentine, which seriously affects the quality of the concentrate. This mudded serpentine mineral often enters foam products with bubbles. In this study, the role of nanobubbles in the flotation behavior of hydrophilic serpentine was examined. Nanobubbles were successfully prepared via ultrasonic cavitation, with sizes ranging from 50 to 250 nm. The size and number of bubbles produced at 1 min and 2 min of sonication were significantly better than those of the prolonged test group, and it was found that longer sonication time did not produce better results. The stability of the nanobubbles produced via ultrasound was studied, and it was found that the nanobubbles were stable, with no change in size and only a slight decrease in number as the resting time increased. Nanobubbles were introduced into serpentine flotation, we found that the presence of nanobubbles significantly reduced the flotation recovery of serpentine. The presence of nanobubbles reduced the froth entrainment rate of microfine-grained serpentine, which in turn reduced its flotation rate. In the depressant group trials, it was found that the nanobubbles also reduced the amount of depressant. In short, the presence of nanobubbles can prevent the floating of fine hydrophilic gangues during flotation. [ABSTRACT FROM AUTHOR]

To investigate the flotation separation behavior of petalite and quartz, various methods were employed in this study. These included micro-flotation experiments, a contact angle analysis, zeta potential analysis, Fourier transform infrared spectroscopy (FTIR), and X-ray photoelectron spectroscopy (XPS) to explore the separation mechanism of a modified ether amine reagent (L0-503) for petalite and quartz under weakly alkaline conditions. The micro-flotation test results indicated that the modified ether amine collector had a higher collecting ability for quartz than for petalite, with a maximum recovery rate of 93.2% for quartz and a recovery rate consistently below 14% for petalite in the presence of L0-503. This indicates that the modified ether amine reagent can be used as a reverse flotation agent for separating petalite and quartz. The separation mechanism results showed that the modified ether amine reagent had a significantly higher adsorption capacity for quartz than for petalite due to a strong reaction between the quartz and the secondary amine (-NH=) on the modified ether amine collector. Additionally, the electrostatic force and hydrogen bonding between the reagent and quartz further enhanced the adsorption, while no reaction occurred between the reagent and petalite. [ABSTRACT FROM AUTHOR]