Image Classification of Wheat Rust Based on Ensemble Learning.

Rust is a common disease in wheat that significantly impacts its growth and yield. Stem rust and leaf rust of wheat are difficult to distinguish, and manual detection is time-consuming. With the aim of improving this situation, this study proposes a method for identifying wheat rust based on ensemble learning (WR-EL). The WR-EL method extracts and integrates multiple convolutional neural network (CNN) models, namely VGG, ResNet 101, ResNet 152, DenseNet 169, and DenseNet 201, based on bagging, snapshot ensembling, and the stochastic gradient descent with warm restarts (SGDR) algorithm. The identification results of the WR-EL method were compared to those of five individual CNN models. The results show that the identification accuracy increases by 32%, 19%, 15%, 11%, and 8%. Additionally, we proposed the SGDR-S algorithm, which improved the f1 scores of healthy wheat, stem rust wheat and leaf rust wheat by 2%, 3% and 2% compared to the SGDR algorithm, respectively. This method can more accurately identify wheat rust disease and can be implemented as a timely prevention and control measure, which can not only prevent economic losses caused by the disease, but also improve the yield and quality of wheat.

A Deep-Learning-Based Approach for Wheat Yellow Rust Disease Recognition from Unmanned Aerial Vehicle Images.

Yellow rust is a disease with a wide range that causes great damage to wheat. The traditional method of manually identifying wheat yellow rust is very inefficient. To improve this situation, this study proposed a deep-learning-based method for identifying wheat yellow rust from unmanned aerial vehicle (UAV) images. The method was based on the pyramid scene parsing network (PSPNet) semantic segmentation model to classify healthy wheat, yellow rust wheat, and bare soil in small-scale UAV images, and to investigate the spatial generalization of the model. In addition, it was proposed to use the high-accuracy classification results of traditional algorithms as weak samples for wheat yellow rust identification. The recognition accuracy of the PSPNet model in this study reached 98%. On this basis, this study used the trained semantic segmentation model to recognize another wheat field. The results showed that the method had certain generalization ability, and its accuracy reached 98%. In addition, the high-accuracy classification result of a support vector machine was used as a weak label by weak supervision, which better solved the labeling problem of large-size images, and the final recognition accuracy reached 94%. Therefore, the present study method facilitated timely control measures to reduce economic losses.

Influence of electrical part of traction transmission on dynamic characteristics of railway vehicles based on electromechanical coupling model.

With the continuous development of rail transit industry and the acceleration of train speed, higher requirements are established for the operation quality of high-speed trains and the reliability of transmission system. In the process of train running, speed fluctuation and vibrations from various parts of the driving devices are common, which could be greatly affected by the traction torque. During traction transmission, the harmonic vibration torque exists in traction motor due to that the motor is connected with non-sinusoidal alternating current. In order to study the vibration influence of the electrical component of traction transmission system on the rail vehicles, i.e., bogie and car-body, an electro-mechanical coupling dynamic model for rail transit vehicles was established by explicitly incorporating the electric-induced traction into the transmission model. The dynamics responses of the vertical, lateral and longitudinal acceleration on vehicle components, such as axle box and car-body were quantitative analyzed. By comparison with field test, it was observed that there was a vibration peak of 12-times of the fundamental rotor frequency on the bogie frame and axle box, which existed at conditions of traction, uniform speed and braking. However, the vibration acceleration exhibit nearly little difference with or without traction force, especially at low frequency domain < 100 Hz.

Factors that associated with TB patient admission rate and TB inpatient service cost: a cross-sectional study in China.

BACKGROUND: China has recently adopted the "TB designated hospital model" to improve the quality of tuberculosis (TB) treatment and patient management. Considering that inpatient service often results in high patient financial burden, and therefore influences patient adherence to treatment, it is critical to better understand the TB patient admission rate and TB inpatient service cost, as well as their influential factors in this new model. METHODS: Quantitative and qualitative studies were conducted in two cities, Hanzhong in Shaanxi Province and Zhenjiang in Jiangsu Province, in China. Quantitative data were obtained from a sample survey of 533 TB patients and TB inpatient records from 2010-2012 in six county designated hospitals. Qualitative information was obtained through interviews with key stakeholders (40 key informant interviews, 14 focus group discussions) and reviews of health policy documents in study areas. Both univariate and multivariate statistical analyses were applied for the quantitative analysis, and the thematic framework approach was applied for the qualitative analysis. RESULTS: The TB patient admission rates in Zhenjiang and Hanzhong were 54.8 and 55.9 %, respectively. Qualitative analyses revealed that financial incentives, misunderstanding of infectious disease control and failure of health insurance regulations were the key factors associated with the admission rates and medical costs. Quantitative analyses found differences in hospitalization rate existed among patients with different health insurance and patients from different counties. Average medical costs for TB inpatients in Jurong and Zhenba were 7,215 CNY and 4,644 CNY, which was higher than the 5,500 CNY and 3,800 CNY limits set by the New Rural Cooperative Medical System. No differences in medical cost or length of stay were found between patients with and without comorbidities in county-level hospitals. CONCLUSIONS: TB patient admission rates and inpatient service costs were relatively high. Studies of related factors indicated that a package of interventions, including health education programs, reform of health insurance regulations and improvement of TB treatment guidelines, are urgently required to ensure that TB patients receive appropriate care.