No abstract

It is particularly important for the development of agriculture to strengthen the agricultural pests monitoring, prevention and cure. The traditional methods of remote sensing (RS) for agricultural pests monitoring cannot meet the needs of agricultural development, because of their long time-consuming, high cost, and low accuracy. However, Unmanned Aerial Vehicle (UAV) remote sensing, as a new means of remote sensing, is introduced in this paper for agricultural monitoring. UAV has advantages of strong real-time, quickness, convenience, low cost, high accuracy and abundant data. With the great flexibility of UAV remote sensing, it is not only easy to focus on regional and long-term agricultural pests monitoring, but also feasible to provide scientific basis for crop pests control. Thus, it is better to meet the time needs of pests' control. In the article, Baiyangdian agricultural area is chosen as the study area. It is discussed how to process UAV images rapidly and extract disease crop information, especially which improved scale invariant feature transform (SIFT) algorithm and object-oriented information extraction are used for image-processing. Fortunately, it has been received good results for the local crop pest control in terms of fact of treatment. With the advantages of UAV remote sensing, there is a broad application prospect in precision agriculture.

Alzheimer disease (AD) is characterized as a chronic neurodegenerative disease associated with aging. The clinical manifestations of AD include latent episodes of memory and cognitive impairment, psychiatric symptoms and behavioral disorders, as well as limited activities in daily life. In developed countries, AD is now acknowledged as the third leading cause of death, following cardiovascular disease and cancer. The pathogenesis and mechanism of AD remain unclear, although some theories have been proposed to explain AD, such as the theory of β-amyloid, the theory of the abnormal metabolism of tau protein, the theory of free radical damage, the theory of the inflammatory response, the theory of cholinergic damage, etc. Effective methods to predict, prevent or reverse AD are unavailable, and thus the development of new, efficient therapeutic drugs has become a current research hot spot worldwide. The isolation and extraction of active components from natural drugs have great potential in treating AD. These drugs possess the advantages of multiple targets in multiple pathways, fewer side effects and a long duration of curative effects. This article summaries the latest research progress regarding the mechanisms of natural drugs in the treatment of AD, providing a review of the literature and a theoretical basis for improving the clinical treatment of AD.

The development of digital cancer twins relies on the capture of high-resolution representations of individual cancer patients throughout the course of their treatment. Our research aims to improve the detection of metastatic disease over time from structured radiology reports by exposing prediction models to historical information. We demonstrate that Natural language processing (NLP) can generate better weak labels for semi-supervised classification of computed tomography (CT) reports when it is exposed to consecutive reports through a patient's treatment history. Around 714,454 structured radiology reports from Memorial Sloan Kettering Cancer Center adhering to a standardized departmental structured template were used for model development with a subset of the reports included for validation. To develop the models, a subset of the reports was curated for ground-truth: 7,732 total reports in the lung metastases dataset from 867 individual patients; 2,777 reports in the liver metastases dataset from 315 patients; and 4,107 reports in the adrenal metastases dataset from 404 patients. We use NLP to extract and encode important features from the structured text reports, which are then used to develop, train, and validate models. Three models—a simple convolutional neural network (CNN), a CNN augmented with an attention layer, and a recurrent neural network (RNN)—were developed to classify the type of metastatic disease and validated against the ground truth labels. The models use features from consecutive structured text radiology reports of a patient to predict the presence of metastatic disease in the reports. A single-report model, previously developed to analyze one report instead of multiple past reports, is included and the results from all four models are compared based on accuracy, precision, recall, and F1-score. The best model is used to label all 714,454 reports to generate metastases maps. Our results suggest that NLP models can extract cancer progression patterns from multiple consecutive reports and predict the presence of metastatic disease in multiple organs with higher performance when compared with a single-report-based prediction. It demonstrates a promising automated approach to label large numbers of radiology reports without involving human experts in a time- and cost-effective manner and enables tracking of cancer progression over time.

Anti-slide piles were used in the region of the Zhenzilin landslide in Sichuan, China. The horizontal displacement of these piles exceeds specifications. Deterioration in bedrock properties may cause deformation, thereby causing landslide destabilization. An approach was developed for the analysis of anti-slide pile in two bedrocks with different strengths below the slip surface. A relationship has been established between the modulus of subgrade reaction of the first weak bedrock and reasonable embedded length for landfill slopes with strata of various strengths. Furthermore, the influence of embedding length on deformation has been studied to determine the reasonable embedded length, which helps reduce deformation and ensure landslide stability. The results reveal that (1) at a constant embedded length, horizontal displacement increases with the thickness of the first soft bedrock, meanwhile the maximum shear force remains constant, and the bending moment first increases followed by subsequent decrease; (2) with an increase in the embedded length, horizontal displacement and the maximum shear force of the pile in the embedded bedrock decrease, whereas the bending moment increases; (3) the maximum internal forces and horizontal displacement increase with a decrease in the subgrade reaction modulus of the first weak rock; and (4) the reasonable embedded length of an anti-slide pile increases with a decrease in the subgrade reaction modulus of the first weak bedrock. The proposed approach can be employed to design anti-slide piles in similar landslide regions to control pile-head deformation.