Analysis, Assessment and Early Warning of Mudflow Disasters along the Shigatse Section of the China–Nepal Highway

Xiao, Liming; Zhang, Yonghong; Ge, Taotao; Wang, Chen; Wei, Ming

doi:10.1515/geo-2020-0004

Cited by 11 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Phase of the overall condition of the slope surface detection, so as to targeted, timely, and effective prevention and control of its disease, to avoid causing greater slope disasters is particularly important. In this case, the detection and identification of slope surface disease is an important prerequisite to avoid slope disaster effectively [3,4].…”

Section: Introductionmentioning

confidence: 99%

Slope Shape and Edge Intelligent Recognition Technology Based on Deep Neural Sensing Network

Huang

Yu²,

Wu³

et al. 2022

Journal of Sensors

View full text Add to dashboard Cite

In order to solve the problem that the slope surface diseases cannot be accurately identified, which cannot be repaired in time and cause serious slope disasters, a slope intelligent recognition technology based on deep neural network is proposed. Based on convolutional neural network (CNN) theory, the technology adopts the transfer learning method to solve the overfitting problem of slope surface samples, which is difficult to obtain a large number of marked samples, and verifies the proposed model by experiment. The results are as follows: the recognition results of various slope surface diseases by ResNet-18 network are higher than AlexNet and VGG-16, with an average accuracy of 84.1%, and the recognition effect of cracks is the best. Under the same migration strategy, the detection accuracy of ResNet-18 is 96.3%, which is much higher than the other two, and the detection time is reduced by 15% on average. It is proved that the ResNet-18 model proposed can identify slope changes very effectively, so that workers can be timely dispatched for maintenance, reducing the possibility of disaster, which has great significance.

show abstract

Section: Introductionmentioning

confidence: 99%

Slope Shape and Edge Intelligent Recognition Technology Based on Deep Neural Sensing Network

Huang

Yu²,

Wu³

et al. 2022

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…After that, the literature [16] proposes a joint maximum mean difference method to measure the relationship of joint distributions, which is used to improve the generalization ability of DCNN to perform migration learning and thus adapt the data distribution between different domains. The literature [17] points out that deep neural network models are more powerful in feature learning and can be initialized layer by layer to alleviate the complexity of deep models in training, and this paper marks the beginning of a new wave of deep learning.…”

Section: Related Workmentioning

confidence: 99%

A Study on the Intelligent Translation Model for English Incorporating Neural Network Migration Learning

Zhang

2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Under the current artificial intelligence boom, machine translation is a research direction of natural language processing, which has important scientific research value and practical value. In practical applications, the variability of language, the limited capability of representing semantic information, and the scarcity of parallel corpus resources all constrain machine translation towards practicality and popularization. In this paper, we conduct deep mining of source language text data to express complex, high-level, and abstract semantic information using an appropriate text data representation model; then, for machine translation tasks with a large amount of parallel corpus, I use the capability of annotated datasets to build a more effective migration learning-based end-to-end neural network machine translation model on a supervised algorithm; then, for machine translation tasks with parallel corpus data resource-poor language machine translation tasks, migration learning techniques are used to prevent the overfitting problem of neural networks during training and to improve the generalization ability of end-to-end neural network machine translation models under low-resource conditions. Finally, for language translation tasks where the parallel corpus is extremely scarce but monolingual corpus is sufficient, the research focuses on unsupervised machine translation techniques, which will be a future research trend.

show abstract

“…This parallel algorithm proposed in the literature [14] has the above significant advantages, but the current parallel implementation is only for two algorithms, depression filling and single flow direction-based sink accumulation calculation, which makes this parallel framework not yet complete for the entire set of algorithms for ultra-large-scale DEM hydrological information extraction, thus making this parallel framework less effective in practical applications. The literature [15] proposed a multiattribute decision-making method with uncertainty in attribute values and attribute weight values by combining evidential reasoning methods and stochastic multicriteria acceptability analysis. In the literature [16], to deal with the diversity and uncertainty of knowledge types in complex industries, a hybrid knowledge base diagnosis system based on evidence fusion is proposed to establish different types of expert knowledge systems and assign reliability weights to them adaptively, which improves the utilization of information and the correctness of the system.…”

Section: Related Studiesmentioning

confidence: 99%

Identification of Fuzzy Information in English Interpretation Based on the Digital Elevation Model

Zhang¹,

Liu

2021

Advances in Mathematical Physics

View full text Add to dashboard Cite

With the rapid development of information society, a large amount of vague or uncertain English interpretation information appears in daily life. Uncertain information processing is an important research content in the field of artificial intelligence. In this paper, we combine the three-branch concept lattice and linguistic values with the digital elevation model and propose the three-branch fuzzy linguistic concept lattice as well as the attribute approximation method. In this paper, an improved serial algorithm for sink accumulation is proposed. The improved algorithm changes the order of cell calculation; after the cumulative amount of a “sub-basin” is calculated, all cells of the next “sub-basin” are calculated until all cells are calculated. The improved algorithm reduces the overhead space in the calculation process, reduces the pressure of cells entering and leaving the queue, and improves the calculation efficiency. The improved cumulant algorithm is compared with the commonly used recursive cumulant algorithm and the nonrecursive cumulant algorithm, and the improved algorithm improves by about 17% compared with the nonrecursive algorithm at 106 cell level, and the computation time of the recursive algorithm is about 3 times of the improved algorithm. Because the sink accumulation serial algorithm is an important part of the parallel calculation of sink accumulation, and the execution time is shorter by using the improved algorithm, this paper applies the proposed improved accumulation serial algorithm to the process of parallel calculation of accumulation.

show abstract

Analysis, Assessment and Early Warning of Mudflow Disasters along the Shigatse Section of the China–Nepal Highway

Cited by 11 publications

References 15 publications

Slope Shape and Edge Intelligent Recognition Technology Based on Deep Neural Sensing Network

Slope Shape and Edge Intelligent Recognition Technology Based on Deep Neural Sensing Network

A Study on the Intelligent Translation Model for English Incorporating Neural Network Migration Learning

Identification of Fuzzy Information in English Interpretation Based on the Digital Elevation Model

Contact Info

Product

Resources

About