The pollution especially organic dyes pollution of water resources is an urgent issue to be *** is crucial to develop highly efficient,low cost and recyclable heterogeneous catalysts for wastewater *** this study,a he...
详细信息
The pollution especially organic dyes pollution of water resources is an urgent issue to be *** is crucial to develop highly efficient,low cost and recyclable heterogeneous catalysts for wastewater *** this study,a heterogeneous Fenton catalyst loaded with Fe_(3)O_(4)nanoparticles was prepared by one step pyrolysis using natural crop waste corncob as carbon *** prepared porous carbon catalyst can effectively degrade methyl orange(MO,25 mg·L^(-1))at room temperature,and the degradation rate is 99.7%.In addition to high catalytic degradation activity,the layered porous carbon structure of the catalyst also provides high stability and *** degradation rate can be maintained above 93%after 10 ***,the prepared catalyst is magnetic,which makes the catalyst easy to recycle in practical *** addition,the prepared Fe3O4/RCC catalyst has efficient Fenton degradation activity for bisphenol A(BPA)(96.9%)and antibiotic tetracycline hydrochloride(TC-HCl)(95.5%),which proves that it has universal applicability for the degradation of most organic *** study provides a feasible and scalable strategy to prepare a heterogeneous Fenton catalyst treating wastewater and high-value utilization of biomass waste.
As smart grid technology rapidly advances,the vast amount of user data collected by smart meter presents significant challenges in data security and privacy *** research emphasizes data security and user privacy conce...
详细信息
As smart grid technology rapidly advances,the vast amount of user data collected by smart meter presents significant challenges in data security and privacy *** research emphasizes data security and user privacy concerns within smart ***,existing methods struggle with efficiency and security when processing large-scale *** efficient data processing with stringent privacy protection during data aggregation in smart grids remains an urgent *** paper proposes an AI-based multi-type data aggregation method designed to enhance aggregation efficiency and security by standardizing and normalizing various data *** approach optimizes data preprocessing,integrates Long Short-Term Memory(LSTM)networks for handling time-series data,and employs homomorphic encryption to safeguard user *** also explores the application of Boneh Lynn Shacham(BLS)signatures for user *** proposed scheme’s efficiency,security,and privacy protection capabilities are validated through rigorous security proofs and experimental analysis.
Binary neural networks have become a promising research topic due to their advantages of fast inference speed and low energy consumption. However, most existing studies focus on binary convolutional neural networks, w...
详细信息
Binary neural networks have become a promising research topic due to their advantages of fast inference speed and low energy consumption. However, most existing studies focus on binary convolutional neural networks, while less attention has been paid to binary graph neural networks. A common drawback of existing studies on binary graph neural networks is that they still include lots of inefficient full-precision operations in multiplying three matrices and are therefore not efficient enough. In this paper, we propose a novel method, called re-quantization-based binary graph neural networks(RQBGN), for binarizing graph neural networks. Specifically, re-quantization, a necessary procedure contributing to the further reduction of superfluous inefficient full-precision operations, quantizes the results of multiplication between any two matrices during the process of multiplying three matrices. To address the challenges introduced by requantization, in RQBGN we first study the impact of different computation orders to find an effective one and then introduce a mixture of experts to increase the model capacity. Experiments on five benchmark datasets show that performing re-quantization in different computation orders significantly impacts the performance of binary graph neural network models, and RQBGN can outperform other baselines to achieve state-of-the-art performance.
Background: Collaborative Representation (CR) has been widely used in Single Image Super Resolution (SISR) with the assumption that Low-resolution (LR) and high-resolution (HR) features can be linearly represented by ...
详细信息
Researchers have recently achieved significant advances in deep learning techniques, which in turn has substantially advanced other research disciplines, such as natural language processing, image processing, speech r...
详细信息
Researchers have recently achieved significant advances in deep learning techniques, which in turn has substantially advanced other research disciplines, such as natural language processing, image processing, speech recognition, and software engineering. Various deep learning techniques have been successfully employed to facilitate software engineering tasks, including code generation, software refactoring, and fault localization. Many studies have also been presented in top conferences and journals, demonstrating the applications of deep learning techniques in resolving various software engineering tasks. However,although several surveys have provided overall pictures of the application of deep learning techniques in software engineering,they focus more on learning techniques, that is, what kind of deep learning techniques are employed and how deep models are trained or fine-tuned for software engineering tasks. We still lack surveys explaining the advances of subareas in software engineering driven by deep learning techniques, as well as challenges and opportunities in each subarea. To this end, in this study, we present the first task-oriented survey on deep learning-based software engineering. It covers twelve major software engineering subareas significantly impacted by deep learning techniques. Such subareas spread out through the whole lifecycle of software development and maintenance, including requirements engineering, software development, testing, maintenance, and developer collaboration. As we believe that deep learning may provide an opportunity to revolutionize the whole discipline of software engineering, providing one survey covering as many subareas as possible in software engineering can help future research push forward the frontier of deep learning-based software engineering more systematically. For each of the selected subareas,we highlight the major advances achieved by applying deep learning techniques with pointers to the available datasets i
In recent years,Mobile Edge Computing(MEC)has received extensive research attention due to its characteristics,such as real-time data processing and flexible application ***,traditional MEC server deployment relies on...
详细信息
In recent years,Mobile Edge Computing(MEC)has received extensive research attention due to its characteristics,such as real-time data processing and flexible application ***,traditional MEC server deployment relies on the terrestrial Base Stations(BSs),resulting in high deployment costs and limited coverage *** response to these challenges,air-ground coordination has emerged,which effectively combines the advantages of edge computing and Unmanned Aerial Vehicles(UAVs),providing an effective architecture for edge *** utilizing the flexibility of UAVs and empowering them into edge nodes with computing resources,the coverage range of MEC can be expanded,thereby reducing the reliance of edge devices on terrestrial ***,leveraging terrestrial BSs as supplements to the computing power compensates for relatively limited computational capabilities of *** extensive studies have been conducted on air-ground coordination,there are few related summaries of application technologies and ***,the key technologies of air-ground coordination and applications are comprehensively reviewed in this ***,to provide guidance for interested researchers,the development trends and potential applications of air-ground coordination are explored.
Stochastic gradient descent(SGD) and its variants have been the dominating optimization methods in machine learning. Compared with SGD with small-batch training, SGD with large-batch training can better utilize the co...
详细信息
Stochastic gradient descent(SGD) and its variants have been the dominating optimization methods in machine learning. Compared with SGD with small-batch training, SGD with large-batch training can better utilize the computational power of current multi-core systems such as graphics processing units(GPUs)and can reduce the number of communication rounds in distributed training settings. Thus, SGD with large-batch training has attracted considerable attention. However, existing empirical results showed that large-batch training typically leads to a drop in generalization accuracy. Hence, how to guarantee the generalization ability in large-batch training becomes a challenging task. In this paper, we propose a simple yet effective method, called stochastic normalized gradient descent with momentum(SNGM), for large-batch training. We prove that with the same number of gradient computations, SNGM can adopt a larger batch size than momentum SGD(MSGD), which is one of the most widely used variants of SGD, to converge to an?-stationary point. Empirical results on deep learning verify that when adopting the same large batch size,SNGM can achieve better test accuracy than MSGD and other state-of-the-art large-batch training methods.
Aiming at the risk issue of high-speed rail(HSR)safety operation,big data technology and uncertain mathematical method are adopted to study ***,from the perspective of system science,the risk diagnosis mode of HSR saf...
详细信息
Aiming at the risk issue of high-speed rail(HSR)safety operation,big data technology and uncertain mathematical method are adopted to study ***,from the perspective of system science,the risk diagnosis mode of HSR safety operation is put forward,which mainly includes the operation environment diagnosis mode based on multivariate product,high-speed train diagnosis mode based on failure influence,staff diagnosis mode based on management conditions,track diagnosis mode based on probability safety,*** based on comprehensive analysis,the conventional risk diagnosis index system is *** the dynamic diagnosis index system based on principal component analysis is proposed,and the risk diagnosis model of HSR safety operation is *** diagnosis model can quickly evaluate the operation situations of HSR,and the diagnosis results are conducive to grasping the situation of risk events quickly and accurately,so as to meet the timeliness requirements of emergency ***,to verify the effectiveness of this new model,the Beijing-Shanghai HSR is selected as a case *** analysis results show that the diagnosis model can quickly diagnose the safety operation situation of HSR,simplify the evaluation process and improve the efficiency of the comprehensive evaluation of emergencies.
A tracking stability control problem for the vertical electric stabilization system of moving tank based on adaptive robust servo control is *** paper mainly focuses on two types of possibly fast timevarying but bound...
详细信息
A tracking stability control problem for the vertical electric stabilization system of moving tank based on adaptive robust servo control is *** paper mainly focuses on two types of possibly fast timevarying but bounded uncertainty within the vertical electric stabilization system:model parameter uncertainty and uncertain ***,the vertical electric stabilization system is constructed as an uncertain nonlinear dynamic system that can reflect the practical mechanics transfer process of the ***,the dynamical equation in the form of state space is established by designing the angular tracking ***,the comprehensive parameter of system uncertainty is designed to estimate the most conservative effects of ***,an adaptive robust servo control which can effectively handle the combined effects of complex nonlinearity and uncertainty is *** feasibility of the proposed control strategy under the practical physical condition is validated through the tests on the experimental *** paper pioneers the introduction of the internal nonlinearity and uncertainty of the vertical electric stabilization system into the settlement of the tracking stability control problem,and validates the advanced servo control strategy through experiment for the first time.
A winding system is a time-varying system that considers complex nonlinear characteristics,and how to control the stability of the winding tension during the winding process is the primary problem that has hindered de...
详细信息
A winding system is a time-varying system that considers complex nonlinear characteristics,and how to control the stability of the winding tension during the winding process is the primary problem that has hindered development in this field in recent *** nonlinear factors affect the tension in the winding process,such as friction,structured uncertainties,unstructured uncertainties,and external *** terms severely restrict the tension tracking *** tension control strategies are mainly based on the composite control of the tension and speed loops,and previous studies involve complex decoupling *** to the large number of calculations required for this method,it is inconvenient for practical engineering *** simplify the tension generation mechanism and the influence of the nonlinear characteristics of the winding system,a simpler nonlinear dynamic model of the winding tension was *** adaptive method was applied to update the feedback gain of the continuous robust integral of the sign of the error(RISE).Furthermore,an extended state observer was used to estimate modeling errors and external *** model disturbance term can be compensated for in the designed RISE *** asymptotic stability of the system was proven according to the Lyapunov stability ***,a comparative analysis of the proposed nonlinear controller and several other controllers was *** results indicated that the control of the winding tension was significantly enhanced.
暂无评论