With the rapid advances in computer vision, human action recognition has gradually received attention, but the current methods still exhibit some problems in indoor environments. The human skeleton, as the framework o...
With the rapid advances in computer vision, human action recognition has gradually received attention, but the current methods still exhibit some problems in indoor environments. The human skeleton, as the framework of human motion, contains high-quality actional feature information, and the skeleton-based action recognition method effectively avoid the interference of interior background noise and has advantages in indoor action recognition. The outstanding effect of graph convolutional networks on graph structure data processing has led to its rapid development and wide application in skeleton-based action recognition. Second-order skeletal information also contains a large number of actional features but is not effectively utilized. The artificial predefined topology of the human skeleton map has limitations, and cannot reflect the interaction between limbs. To solve the above problems, this article designs an adaptive weighted multi-stream graph convolutional network (AM-GCN) based on skeletal information, using an attention mechanism to enhance the network's ability to extract actional features, and an adaptive layer to make the construction graph more flexible, incorporating second-order skeletal features through a dual-stream architecture. In this article, the NTU-RGB+D dataset has been used for the experiments, the results show that the method in this article has good results.
The utilization of solar energy in grid-connected photovoltaic installations has become increasingly significant. This article introduces a photovoltaic system seamlessly integrated with a three-phase network. The sys...
详细信息
ISBN:
(数字)9798350349740
ISBN:
(纸本)9798350349757
The utilization of solar energy in grid-connected photovoltaic installations has become increasingly significant. This article introduces a photovoltaic system seamlessly integrated with a three-phase network. The system employing a five-level Neutral Point Clamped (NPC) voltage source inverter is designed for a single-step connection to enhance power quality in the distribution network. The control technique employed for the efficient functioning of the photovoltaic system is based on the notion of instantaneous reactive power. Notably, this strategy is straightforward, operates the system throughout the day, and eliminates the need for Phase-Locked Loop (PLL) usage. The Pulse-Width Modulated (PWM) Current controller sends switching signals to the NPC multilevel inverter, which does a great job of dynamic performance under steady-state and transient situations. The proportional-integral controller regulates the voltage of the Uninterruptible Power Supply DC bus capacitors. The proposed system undergoes comprehensive simulation validation under various irradiation levels.
In this paper, a partially double pass configuration in serial hybrid fiber amplifier is experimentally demonstrated. In the proposed design, a double pass erbium gain and single pass Raman gain are achieved serially....
In this paper, a partially double pass configuration in serial hybrid fiber amplifier is experimentally demonstrated. In the proposed design, a double pass erbium gain and single pass Raman gain are achieved serially. A total pump power of 450 mW (400 mW for 1495 nm Raman amplifier and 50 mW for1480 nm in erbium amplifier) were used. At -30 dBm input signal power and optimum pumps conditions, the achieved flatness bandwidth is 80 nm (1530–1610 nm) in the conventional and long bands (C+L) bands. In addition, the obtained average gain level is 33 dB. While the obtained flatness gain is 85 nm (1525–1610 nm) within the large input signal power region at -5 dBm. By choosing a proper pump wavelength that avoid the overlapping between Raman and erbium peaks gain, a wide flatness gain is obtained.
We report a new approach to generate waveguide-coupled emission from deterministically implanted boron vacancy spin defects in hBN using single-crystal AlN-on-sapphire ring resonators. This facilitates the eventual de...
详细信息
ISBN:
(纸本)9798350369311
We report a new approach to generate waveguide-coupled emission from deterministically implanted boron vacancy spin defects in hBN using single-crystal AlN-on-sapphire ring resonators. This facilitates the eventual development of hBN-based integrated quantum technologies.
Efficient and accurate segmentation of the point cloud for indoor scenes is an important task for 3D scene understanding. Due to the complexity of indoor environments. It is difficult to fully extract the details of p...
详细信息
In this paper we explore some of the potential applications of robustness criteria for machine learning (ML) systems by way of tangible “demonstrator” scenarios. In each demonstrator, ML robustness metrics are appli...
In this paper we explore some of the potential applications of robustness criteria for machine learning (ML) systems by way of tangible “demonstrator” scenarios. In each demonstrator, ML robustness metrics are applied to real-world scenarios with military relevance, indicating how they might be used to help detect and handle possible adversarial attacks on ML systems. We conclude by sketching promising future avenues of research in order to: (1) help establish useful verification methodologies to facilitate ML robustness compliance assessment; (2) support development of ML accountability mechanisms; and (3) reliably detect, repel, and mitigate adversarial attack.
Surrogate models, which have become an effective and popular method to close loop reservoir management problems, use a data-driven approach to predict dynamic injection and production wells parameters and optimize wat...
Surrogate models, which have become an effective and popular method to close loop reservoir management problems, use a data-driven approach to predict dynamic injection and production wells parameters and optimize waterflooding development. In this study, a deep learning-based surrogate model method is proposed to estimate bottomhole pressure (BHP) of production wells in waterflooding reservoirs. Bidirectional long short-term memory (BiLSTM) network, as an efficient deep learning approach, is applied to BHP estimation using fluctuation data. Extended Fourier amplitude sensitivity test (EFAST) method is employed to analyse the influence of different input factors on BHP dynamics, and a reduced dataset is rebuilt to predict BHP parameter based on BiLSTM-EFAST algorithm. The estimation results are tested on a dataset from Volve oilfield in North Sea, and compared with other deep learning methods. The test results indicate that the proposed method can achieve higher prediction accuracy. A reduced dataset-based approach provides a new attempt to reduce model complexity and improve calculation speed for big data-driven surrogate model in oil and gas industry.
Unlike for Linear Time-Invariant (LTI) systems, for nonlinear systems, there exists no general framework for systematic convex controller design which incorporates performance shaping. The Linear Parameter-Varying (LP...
详细信息
Identifying systems with high-dimensional inputs and outputs, such as systems measured by video streams, is a challenging problem with numerous applications in robotics, autonomous vehicles and medical imaging. In thi...
详细信息
Identifying systems with high-dimensional inputs and outputs, such as systems measured by video streams, is a challenging problem with numerous applications in robotics, autonomous vehicles and medical imaging. In this paper, we propose a novel non-linear state-space identification method starting from high-dimensional input and output data. Multiple computational and conceptual advances are combined to handle the high-dimensional nature of the data. An encoder function, represented by a neural network, is introduced to learn a reconstructability map to estimate the model states from past inputs and outputs. This encoder function is jointly learned with the dynamics. Furthermore, multiple computational improvements, such as an improved reformulation of multiple shooting and batch optimization, are proposed to keep the computational time under control when dealing with high-dimensional and large datasets. We apply the proposed method to a video stream of a simulated environment of a controllable ball in a unit box. The study shows low simulation error with excellent long term prediction capability of the model obtained using the proposed method.
A general upper bound for topological entropy of switched nonlinear systems is constructed, using an asymptotic average of upper limits of the matrix measures of Jacobian matrices of strongly persistent individual mod...
详细信息
暂无评论