Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Powiadomienia systemowe

Sesja wygasła!

Znaleziono wyników: 3

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Automated detection of multi-class urinary sediment particles: An accurate deep learning approach

Lyu He, Xu Fanxin, Jin Tao, Zheng Siyi, Zhou Chenchen, Cao Yang, Luo Bin, Huang Qinzhen, Xiang Wei, Li Dong

Biocybernetics and Biomedical Engineering

2023

Vol. 43, no. 4

672--683

Urine microscopy is an essential diagnostic tool for kidney and urinary tract diseases, with automated analysis of urinary sediment particles improving diagnostic efficiency. However, some urinary sediment particles remain challenging to identify due to individual variations, blurred boundaries, and unbalanced samples. This research aims to mitigate the adverse effects of urine sediment particles while improving multi-class detection performance. We proposed an innovative model based on improved YOLOX for detecting urine sediment particles (YUS-Net). The combination of urine sediment data augmentation and overall pre-trained weights enhances model optimization potential. Furthermore, we incorporate the attention module into the critical feature transfer path and employ a novel loss function, Varifocal loss, to facilitate the extraction of discriminative features, which assists in the identification of densely distributed small objects. Based on the USE dataset, YUS-Net achieves the mean Average Precision (mAP) of 96.07%, 99.35% average precision, and 96.77% average recall, with a latency of 26.13 ms per image. The specific metrics for each category are as follows: cast: 99.66% AP; cryst: 100% AP; epith: 92.31% AP; epithn: 100% AP; eryth: 92.31% AP; leuko: 99.90% AP; mycete: 99.96% AP. With a practical network structure, YUS-Net achieved efficient, accurate, end-to-end urinary sediment particle detection. The model takes native high-resolution images as input without additional steps. Finally, a data augmentation strategy appropriate for the urinary microscopic image domain is established, which provides a novel approach for applying other methods in urine microscopic images.

Process evaluation of soil treatment effect in Mu Us sandy land of Daji Khan in northern Shaanxi province based on fuzzy set

Chen Xiaowan, Liang Jichao, He Xinxin, Liu Dandan, Liu Jinbao, Jin Tao, Xie Jiancang

Acta Geophysica

2023

Vol. 71, no. 3

1579--1594

As an important resource for human survival, soil plays an important role in maintaining productivity, environmental quality, animal and plant health, etc. Soil quality evaluation, as a decision-making tool to improve understanding of soil quality, can effectively indicate soil status. Mu Us sandy land of Daji Khan in northern Shaanxi Province is one of the serious desertification areas in China. The phenomenon of soil erosion and ecological deterioration is extremely serious. Therefore, it is urgent to strengthen to pay attention to the research of Mu Us sandy land, to help the restoration of damaged soil, and to build a powerful soil ecosystem. In this paper, the soil quality in the process of development and utilization of the Mu Us sandy land was evaluated based on fuzzy sets for the purpose of sustainable utilization of compound soil. Based on soil structure and soil fertility, 16 evaluation indexes of soil quality in Mu Us sandy land were screened, and then the evaluation index system of soil quality was constructed. The fuzzy multi-objective decision-making model based on fuzzy sets was used to comprehensively evaluate the soil quality from 2013 to 2019. We calculated that the year-on-year growth rates of soil quality from 2013 to 2019 are 13.56, 0.16, 12.81, 33.84, 9.68, and 14.80%, respectively. The results showed that the overall soil quality in the study area showed a trend of increasing year by year, and the year-on-year increase was the largest in 2017. Meanwhile, the reasons for the sudden increase in soil quality in typical years were analyzed. The results showed that the dominant factor of this phenomenon was the comprehensive influence of soil fertility. Furthermore, the relationship between soil fertility and cultivated horizon in typical years was analyzed one by one, and the specific factors affecting soil fertility were discussed.

Working temperature calculation of single-core cable by nonlinear finite element method

Meng Xiaokai, Han Peijie, Liu Yongxin, Lu Zhumao, Jin Tao

Archives of Electrical Engineering

2019

Vol. 68, nr 3

643--656

By simulating the actual working conditions of a cable, the temperature variation rule of different measuring points under different load currents was analyzed. On this basis, a three-dimensional finite element model (FEM) was established, and the difference and influence factors between the simulation temperature and the experimental measured value were discussed, then the influence of thermal conductivity on the operating temperature of the conductor layer was studied. Finally, combined with the steady-state thermal conductivity model and the experimental measured data, the relation between thermal conductivity and load current was obtained.