Predicting students’academic achievements is an essential issue in education,which can benefit many stakeholders,for instance,students,teachers,managers,*** with online courses such asMOOCs,students’academicrelatedd...
详细信息
Predicting students’academic achievements is an essential issue in education,which can benefit many stakeholders,for instance,students,teachers,managers,*** with online courses such asMOOCs,students’academicrelateddata in the face-to-face physical teaching environment is usually sparsity,and the sample size is *** makes building models to predict students’performance accurately in such an environment even *** paper proposes a Two-WayNeuralNetwork(TWNN)model based on the bidirectional recurrentneural network and graph neural network to predict students’next semester’s course performance using only theirprevious course *** experiments on a real dataset show that our model performs better thanthe baselines in many indicators.
Plug-in Hybrid Electric Vehicles(PHEVs)represent an innovative breed of transportation,harnessing diverse power sources for enhanced *** management strategies(EMSs)that coordinate and control different energy sources ...
详细信息
Plug-in Hybrid Electric Vehicles(PHEVs)represent an innovative breed of transportation,harnessing diverse power sources for enhanced *** management strategies(EMSs)that coordinate and control different energy sources is a critical component of PHEV control technology,directly impacting overall vehicle *** study proposes an improved deep reinforcement learning(DRL)-based EMSthat optimizes realtime energy allocation and coordinates the operation of multiple power *** DRL algorithms struggle to effectively explore all possible state-action combinations within high-dimensional state and action *** often fail to strike an optimal balance between exploration and exploitation,and their assumption of a static environment limits their ability to adapt to changing ***,these algorithms suffer from low sample ***,these factors contribute to convergence difficulties,low learning efficiency,and *** address these challenges,the Deep Deterministic Policy Gradient(DDPG)algorithm is enhanced using entropy regularization and a summation tree-based Prioritized Experience Replay(PER)method,aiming to improve exploration performance and learning efficiency from experience ***,the correspondingMarkovDecision Process(MDP)is ***,an EMSbased on the improvedDRLmodel is *** simulation experiments are conducted against rule-based,optimization-based,andDRL-based *** proposed strategy exhibitsminimal deviation fromthe optimal solution obtained by the dynamic programming(DP)strategy that requires global *** the typical driving scenarios based onWorld Light Vehicle Test Cycle(WLTC)and New European Driving Cycle(NEDC),the proposed method achieved a fuel consumption of 2698.65 g and an Equivalent Fuel Consumption(EFC)of 2696.77 *** to the DP strategy baseline,the proposed method improved the fuel efficiency variances(FEV)by 18.13%
The flame propagation processes of MgH_(2)dust clouds with four different particle sizes were recorded by a high-speed *** dynamic flame temperature distributions of MgH_(2)dust clouds were reconstructed by the two-co...
详细信息
The flame propagation processes of MgH_(2)dust clouds with four different particle sizes were recorded by a high-speed *** dynamic flame temperature distributions of MgH_(2)dust clouds were reconstructed by the two-color pyrometer technique,and the chemical composition of solid combustion residues were *** experimental results showed that the average flame propagation velocities of 23μm,40μm,60μm and 103μm MgH_(2)dust clouds in the stable propagation stage were 3.7 m/s,2.8 m/s,2.1 m/s and 0.9 m/s,*** dust clouds with smaller particle sizes had faster flame propagation velocity and stronger oscillation intensity,and their flame temperature distributions were more even and the temperature gradients were *** flame structures of MgH_(2)dust clouds were significantly affected by the particle sinking velocity,and the combustion processes were accompanied by micro-explosion of *** falling velocities of 23μm and 40μm MgH_(2)particles were 2.24 cm/s and 6.71 cm/s,*** the falling velocities of 60μm and 103μm MgH_(2)particles were as high as 15.07 cm/s and 44.42 cm/s,respectively,leading to a more rapid downward development and irregular shape of the ***,the dehydrogenation reaction had a significant effect on the combustion performance of MgH_(2)*** combustion of H_(2)enhanced the ignition and combustion characteristics of MgH_(2)dust,resulting in a much higher explosion power than the pure Mg *** micro-structure characteristics and combustion residues composition analysis of MgH_(2)dust indicated that the combustion control mechanism of MgH_(2)dust flame was mainly the heterogeneous reaction,which was affected by the dehydrogenation reaction.
In permissioned blockchain networks,the Proof of Authority(PoA)consensus,which uses the election of authorized nodes to validate transactions and blocks,has beenwidely advocated thanks to its high transaction throughp...
详细信息
In permissioned blockchain networks,the Proof of Authority(PoA)consensus,which uses the election of authorized nodes to validate transactions and blocks,has beenwidely advocated thanks to its high transaction throughput and fault ***,PoA suffers from the drawback of centralization dominated by a limited number of authorized nodes and the lack of anonymity due to the round-robin block proposal *** a result,traditional PoA is vulnerable to a single point of failure that compromises the security of the blockchain *** address these issues,we propose a novel decentralized reputation management mechanism for permissioned blockchain networks to enhance security,promote liveness,and mitigate centralization while retaining the same throughput as traditional *** paper aims to design an off-chain reputation evaluation and an on-chain reputation-aided ***,we evaluate the nodes’reputation in the context of the blockchain networks and make the reputation globally verifiable through smart ***,building upon traditional PoA,we propose a reputation-aided PoA(rPoA)consensus to enhance securitywithout sacrificing *** particular,rPoA can incentivize nodes to autonomously form committees based on reputation authority,which prevents block generation from being tracked through the randomness of reputation ***,we develop a reputation-aided fork-choice rule for rPoA to promote the network’s ***,experimental results show that the proposed rPoA achieves higher security performance while retaining transaction throughput compared to traditional PoA.
As a complex hot problem in the financial field,stock trend forecasting uses a large amount of data and many related indicators;hence it is difficult to obtain sustainable and effective results only by relying on empi...
详细信息
As a complex hot problem in the financial field,stock trend forecasting uses a large amount of data and many related indicators;hence it is difficult to obtain sustainable and effective results only by relying on empirical *** in the field of machine learning have proved that random forest can form better judgements on this kind of problem,and it has an auxiliary role in the prediction of stock *** study uses historical trading data of four listed companies in the USA stock market,and the purpose of this study is to improve the performance of random forest model in medium-and long-term stock trend *** study applies the exponential smoothing method to process the initial data,calculates the relevant technical indicators as the characteristics to be selected,and proposes the D-RF-RS method to optimize random *** the random forest is an ensemble learning model and is closely related to decision tree,D-RF-RS method uses a decision tree to screen the importance of features,and obtains the effective strong feature set of the model as ***,the parameter combination of the model is optimized through random parameter *** experimental results show that the average accuracy of random forest is increased by 0.17 after the above process optimization,which is 0.18 higher than the average accuracy of light gradient boosting machine *** with the performance of the ROC curve and Precision–Recall curve,the stability of the model is also guaranteed,which further demonstrates the advantages of random forest in medium-and long-term trend prediction of the stock market.
This study introduces a data-driven approach for state and output feedback control addressing the constrained output regulation problem in unknown linear discrete-time systems. Our method ensures effective tracking pe...
详细信息
This study introduces a data-driven approach for state and output feedback control addressing the constrained output regulation problem in unknown linear discrete-time systems. Our method ensures effective tracking performance while satisfying the state and input constraints, even when system matrices are not available. We first establish a sufficient condition necessary for the existence of a solution pair to the regulator equation and propose a data-based approach to obtain the feedforward and feedback control gains for state feedback control using linear programming. Furthermore, we design a refined Luenberger observer to accurately estimate the system state, while keeping the estimation error within a predefined set. By combining output regulation theory, we develop an output feedback control strategy. The stability of the closed-loop system is rigorously proved to be asymptotically stable by further leveraging the concept of λ-contractive sets.
In this work,possible short-term thermal exposure oxidation in hot processing including semi-solid processing is *** aim to investigate the short-term oxidation behavior of a novel powder metallurgy Al_(0.8)Co_(0.5)Cr...
详细信息
In this work,possible short-term thermal exposure oxidation in hot processing including semi-solid processing is *** aim to investigate the short-term oxidation behavior of a novel powder metallurgy Al_(0.8)Co_(0.5)Cr_(1.5)CuFeNi high entropy alloy(HEA)in high-temperature solid(1000-1100℃)and semi-solid(1125-1225℃)*** 1000 to 1225℃,mass gain increases from 0.31 to 0.45 mg cm^(-2)after 60 min oxidation,presenting superior oxidation resistance in the semi-solid state compared with other semi-solid ***α-Al_(2)O_(3)grains are the predominant component of oxide scales and no obvious internal oxidation layer occurs in both solid and semi-solid ***_(2)O_(3)scale growth is predominantly determined by outward Al^(3+)*** solid oxidation,different scale formation kinetics occur on various phases and the BCC(B2)phase has faster scale formation *** is attributed to outward Al^(3+)diffusion rate differences in various component *** semi-solid oxidation,the increased degree of chaos and number of vacancies in the liquid phase provide a diffusion channel,leading to rapid Al_(2)O_(3)*** resistance in the semi-solid state is attributed to dense Al_(2)O_(3)scales formed through selective oxidation of Al.
Large language models (LLMs) have been one of the most important discoveries in machine learning in recent years. LLM-based artificial intelligence (AI) assistants, such as ChatGPT, have consistently attracted the att...
详细信息
With the increasing number of edited videos, many robust video fingerprinting schemes have been proposed to solve the problem of video content authentication. However, most of them either deal with the temporal and sp...
详细信息
Due to its decentralized and tamper-proof features, blockchain is frequently employed in the financial, traceability, and distributed storage industries. The agreement algorithm, which is a crucial component of the bl...
详细信息
暂无评论