Landslide disasters are extremely destructive. Accurate identification of landslides plays an important role in disaster assessment, loss control and post-disaster reconstruction. This paper proposes a semantic segmen...
Landslide disasters are extremely destructive. Accurate identification of landslides plays an important role in disaster assessment, loss control and post-disaster reconstruction. This paper proposes a semantic segmentation landslide identification method based on improved U-Net. The deep convolution neural network and jump connection method is used for end-to-end semantic segmentation to achieve deep feature extraction and fusion of different receptive fields, thus enriching feature information. SENet modules are adopted to enhance the ability of the model to extract important features, so as to further improve the accuracy of model recognition. Extensive experiments show that our improved U-Net achieves better performance than the original algorithm on our landslide datasets. The results of Iou are improved by 4.12% which demonstrates our work is of great significance for the research of landslide area identification. Finally, the model is deployed to the web and applied to the geological hazard intelligent monitoring system to realize the landslide identification task.
The irradiance-power curve is an important basis for examining the operating status of photovoltaic power stations. In the actual operation process, sensor failure, abnormal communication and equipment damage will bri...
详细信息
The irradiance-power curve is an important basis for examining the operating status of photovoltaic power stations. In the actual operation process, sensor failure, abnormal communication and equipment damage will bring a large number of abnormal values to the output data of photovoltaic power plants. It will have a significant impact on a variety of applications based on photovoltaic output data. This paper analyzes the typical outliers on the irradiance-power curve and proposes a photovoltaic output data cleaning method based on fuzzy clustering algorithm and quartile algorithm. By comparing with the quartile method, it is proved that this method can effectively identify abnormal data when there are a large number of outliers in the photovoltaic output data.
A high-reliability constant current to constant voltage power supply system has the advantages of small volume of switching power supply, high power density, high efficiency was proposed. This paper use two controller...
A high-reliability constant current to constant voltage power supply system has the advantages of small volume of switching power supply, high power density, high efficiency was proposed. This paper use two controllers to control the shunt regulator(SR) circuit and single-end flyback converter part, and separate the two parts for small signal modeling and give the parameters to stabilize the closed loop. The state space average modeling idea was used to solve the state equations for the modes of the converters in a switching cycle. In order to ensure the stability of cascade system, this paper collaborative optimization of hardware filter parameters and the appropriate PI parameter design. The experimentals verify the correctness of our theory, and the system has good stability under closed-loop conditions.
Landslide is the most frequent geological hazard. Landslide susceptibility mapping (LSM) can be used to predict the possibility of landslide occurring at a certain location. In this paper, an undersampling ensemble an...
Landslide is the most frequent geological hazard. Landslide susceptibility mapping (LSM) can be used to predict the possibility of landslide occurring at a certain location. In this paper, an undersampling ensemble and deep learning - based landslide susceptibility mapping method for geological hazard warning is proposed. The Zigui to Badong section of the Three Gorges Reservoir is taken as the study area. Firstly, the correlation analysis of fourteen landslide influencing factors is carried out and two unimportant factors are eliminated. Then, an EasyEnsemble - one dimensional convolutional neural network (EE-1DCNN) model is constructed with the remaining twelve factors as inputs. Finally, the proposed EE-1DCNN model is compared with two well-known methods on test data, and a landslide susceptibility map of the study area is obtained based on the EE-1DCNN model. As the experimental result shows, the proposed EE-1DCNN model achieves superior AUC, accuracy and recall of 0.909, 91.7% and 85.1%. The applicability of the proposed method is proved.
Motion is one of the basic physiological functions of human beings. However, many brain diseases such as stroke may cause different degrees of motor dysfunctions for patients. As a commonly used rehabilitation method,...
Motion is one of the basic physiological functions of human beings. However, many brain diseases such as stroke may cause different degrees of motor dysfunctions for patients. As a commonly used rehabilitation method, active and passive exercise training may enhance patients’ neuromuscular functions and recover their motor abilities. It is known that limb movements are strongly coupled with brain activation but there is currently insufficient exploration on the coupling behaviors from the perspective of informatics. In this study, the coupling relationship between limb movements and brain activation was preliminarily studied based on three healthy subjects. Electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRS) signals were synchronously collected during lower limb movements, and time-frequency analysis (TFA) and transfer entropy (TE) analysis were performed to quantitatively study the brain activation behaviors. In the experiments, a desynchronization phenomenon of μ rhythm in EEG was observed during exercise states, and the experimental results demonstrate the activation rule of motor and prefrontal cortexes upon limb movements. Calculations show that there exists a bidirectional flow of information between EEG and cerebral oxygen metabolism signals, but with a difference between different directions. This work may support the rehabilitation for patients with motor dysfunctions with a guidance of quantitative indicators and also benefit the exploration on neuroscience.
Troublesome incidents like sudden water inflows increase the risk of collapse accidents in tunnel excavation. In this study, a data-driven underground water prediction method is proposed based on trend features extrac...
Troublesome incidents like sudden water inflows increase the risk of collapse accidents in tunnel excavation. In this study, a data-driven underground water prediction method is proposed based on trend features extracted from apparent resistivity. A novel framework is developed for extracting trend features from the contour lines of apparent resistivity. These trend features are subsequently integrated with numerical features from the resistivity matrix for classification. The effectiveness of the proposed method is demonstrated by apparent resistivity data from real tunnel engineering. The result indicates that the classification accuracy of the proposed method outperforms the method without feature extraction.
This paper uses the wave equation to explain the torsional motion of the drill-string system. Solving the wave equation with the D'Alembert method, a neutral time-delay model of the drill-string system is obtained...
This paper uses the wave equation to explain the torsional motion of the drill-string system. Solving the wave equation with the D'Alembert method, a neutral time-delay model of the drill-string system is obtained. The disturbance input, caused by the bit-rock interaction, is given consideration, and an equivalent-input-disturbance (EID) based controller is designed to mitigate the disturbance in the established model. In the actual drilling procedure, the system input time-delay increases as the length of the drill columns increases. If the influence of system input time-delay in the drilling procedure is ignored, it will most likely lead to the drill-string system instability and cause serious consequences. The essential contribution of this paper is the incorporation of input time-delay into the EID based control structure. Considering the system's input time-delay, the proposed model is more practical and has significant implications for stick-slip vibration assessment and control in drilling procedures.
Ground Penetrating Radar (GPR) features are vital for accurately predicting the formation environment in the tunnel engineering. In this paper, a novel intelligent method for extracting the multi-domain (time domain, ...
Ground Penetrating Radar (GPR) features are vital for accurately predicting the formation environment in the tunnel engineering. In this paper, a novel intelligent method for extracting the multi-domain (time domain, time frequency domain, and spatial domain) features of ground penetrating radar data is proposed. Firstly, the GPR exploration data is read to obtain the relative amplitude matrix. Secondly, multi-domain features are obtained using the following methods. The relative amplitude matrix of GPR is averaged by rows to obtain the time domain feature called the average relative amplitude(ARA). The S-transform is used to extract the time frequency domain feature called the average maximum weight frequency(AMWF) of the electromagnetic waves. And the events of the GPR images are highlighted by using Gaussian filtering and edge detection, and the spatial domain feature called the maximum event length(M EL) is obtained through contour detection. Finally, the three extracted multi-domain features are stored in the GPR feature database. Compared simulation results verify the effectiveness of the proposed method.
Networked Traffic Signal control (NTSC) is a fundamental component of Intelligent Transportation systems (ITS) and the broader vision of smart city development. While a plethora of intelligent strategies have been dev...
Networked Traffic Signal control (NTSC) is a fundamental component of Intelligent Transportation systems (ITS) and the broader vision of smart city development. While a plethora of intelligent strategies have been developed, the Sim2Real challenge often impedes their full realization. In response, this paper introduces the Parallel Learning-based Adaptive Network for Traffic Signal control (PLANT) as a foundation model for NTSC. We employ the Wasserstein GAN with Gradient Penalty (WGAN-GP) to generate a wide range of artificial scenarios for robust PLANT training. Further, the Transformer-based Cooperation Mechanism (TCM) is integrated as the primary learner within PLANT, facilitating effective capture of traffic dynamics and knowledge accumulation. This knowledge is readily transferable to real-world applications through meticulous fine-tuning, equipping PLANT to adapt and evolve in alignment with shifting transportation paradigms. Our empirical study on the Hangzhou road network demonstrates PLANT's superiority over both traditional and emerging DRL-based approaches, emphasizing its viability as a potential foundation model for NTSC.
This paper focuses on the bounded tracking control of general linear multi-agent systems(MASs), considering the effects of inevitable communication time-delays, measurement noises, and uncertain disturbances in practi...
详细信息
This paper focuses on the bounded tracking control of general linear multi-agent systems(MASs), considering the effects of inevitable communication time-delays, measurement noises, and uncertain disturbances in practical applications. Firstly, the bounded tracking control problem of uncertain MASs under multiplicative noises is transformed into the boundedness problem of stochastic differential delay equations. Then, the upper bound of agent tracking is calculated by means of linear variation, variation of constants formula and stochastic analysis theory, and sufficient conditions are given for the system to achieve the bounded tracking control.
暂无评论