Owing to the ubiquity of wireless networks and the popularity of WiFi infrastructures,received signal strength(RSS)-based indoor localization systems have received much *** placement of access points(APs)significantly...
详细信息
Owing to the ubiquity of wireless networks and the popularity of WiFi infrastructures,received signal strength(RSS)-based indoor localization systems have received much *** placement of access points(APs)significantly influences localization accuracy and network ***,the indoor scenario and network access are not fully considered in previous AP placement optimization *** study proposes a practical scenario modelingaided AP placement optimization method for improving localization accuracy and network *** order to reduce the gap between simulation-based and field measurement-based AP placement optimization methods,we introduce an indoor scenario modeling and Gaussian process-based RSS prediction *** that,the localization and network access metrics are implemented in the multiple objective particle swarm optimization(MOPSO)solution,Pareto front criterion and virtual repulsion force are applied to determine the optimal AP ***,field experiments demonstrate the effectiveness of the proposed indoor scenario modeling method and RSS prediction model.A thorough comparison confirms the localization and network access improvement attributed to the proposed anchor placement method.
The application of computer technology in the financial field and the utilization of computer algorithms to enhance the accuracy of stock price prediction have drawn the attention of numerous researchers. Against this...
详细信息
Conventional Knowledge Graph Reasoning (KGR) models learn the embeddings of KG components over the structure of KGs, but their performances are limited when the KGs are severely incomplete. Recent LLM-enhanced KGR mod...
详细信息
The design of thermal conductivity enhancers(TCE) is quite critical to overcoming the disadvantage of the poor thermal conductivity of phase change materials(PCM).The main contribution of this study is firstly to disc...
详细信息
The design of thermal conductivity enhancers(TCE) is quite critical to overcoming the disadvantage of the poor thermal conductivity of phase change materials(PCM).The main contribution of this study is firstly to discuss how to actively enhance natural convection of the melted PCM in cellular structure by the fin formed in the structure under the condition of the same metal mass,apart from simultaneously improving heat conduction,which can boost the heat transfer ***,a tailored hybrid fin-lattice structure(HFS) as TCE is designed and fabricated by additive manufacturing(AM).A two-equation numerical method is applied to study the heat transfer of the PCM,and its feasibility is validated with the experimental *** numerical results indicate that enhanced natural convection and improved heat conduction can be obtained simultaneously when a well-designed fin is embedded into a lattice *** enhanced natural convection results in the improved melting rate and the decreased wall temperature;e.g.,the complete melting time and the wall temperature are reduced by 11.6% and 19.7%,respectively,because of the fin for metal ***,the parameters of HFS including the porosity,pore density,and fin dimension have a great impact on the heat *** enhancement effect of the fin for HFS on the melting rate of the PCM increases as the thermal conductivity of the base material *** example,when the fin is introduced into the lattice structure,the complete melting time is reduced by 24.1% for metal *** summary,this study enables us to obtain a good understanding of the mechanism of the heat transfer and provides necessary experimental data for the structural design of HFS fabricated by AM.
Flourishing rare earth superhydrides are a class of recently discovered materials that exhibit near-room-temperature superconductivity at high pressures,ushering in a new era of superconductivity research at high *** ...
详细信息
Flourishing rare earth superhydrides are a class of recently discovered materials that exhibit near-room-temperature superconductivity at high pressures,ushering in a new era of superconductivity research at high *** superhydrides drew the most attention among these superhydrides due to their abundance of stoichiometries and excellent ***,we carried out a comprehensive study of yttrium superhydrides in a wide pressure range of 140 GPa-300 *** successfully synthesized a series of superhydrides with the compositions of YH_(4),YH_(6),YH_(7),and YH_(9),and reported superconducting transition temperatures of 82 K at 167 GPa,218 K at 165 GPa,29 K at 162 GPa,and230 K at 300 GPa,respectively,as evidenced by sharp drops in *** structure and superconductivity of YH_(4) were taken as a representative example and were also examined using x-ray diffraction measurements and the superconductivity suppression under external magnetic fields,*** YH_(10),a candidate for room-temperature superconductor,was not synthesized within the study pressure and temperature ranges of up to 300 GPa and 2000 *** current study established a detailed foundation for future research into room-temperature superconductors in polynary yttrium-based superhydrides.
Machine learning algorithms provide new ways to solve the problem of stock prediction. Among them, the decision tree algorithm has been widely used in financial market prediction because of its strong interpretability...
详细信息
Change detection(CD)is becoming indispensable for unmanned aerial vehicles(UAVs),especially in the domain of water landing,rescue and ***,even the most advanced models require large amounts of data for model training ...
详细信息
Change detection(CD)is becoming indispensable for unmanned aerial vehicles(UAVs),especially in the domain of water landing,rescue and ***,even the most advanced models require large amounts of data for model training and ***,sufficient labeled images with different imaging conditions are *** by computer graphics,we present a cloning method to simulate inland-water scene and collect an auto-labeled simulated *** simulated dataset consists of six challenges to test the effects of dynamic background,weather,and noise on change detection ***,we propose an image translation framework that translates simulated images to synthetic *** framework uses shared parameters(encoder and generator)and 22×22 receptive fields(discriminator)to generate realistic synthetic images as model training *** experimental results indicate that:1)different imaging challenges affect the performance of change detection models;2)compared with simulated images,synthetic images can effectively improve the accuracy of supervised models.
Model-based reinforcement learning is a promising direction to improve the sample efficiency of reinforcement learning with learning a model of the *** model learning methods aim at fitting the transition data,and com...
详细信息
Model-based reinforcement learning is a promising direction to improve the sample efficiency of reinforcement learning with learning a model of the *** model learning methods aim at fitting the transition data,and commonly employ a supervised learning approach to minimize the distance between the predicted state and the real *** supervised model learning methods,however,diverge from the ultimate goal of model learning,i.e.,optimizing the learned-in-the-model *** this work,we investigate how model learning and policy learning can share the same objective of maximizing the expected return in the real *** find model learning towards this objective can result in a target of enhancing the similarity between the gradient on generated data and the gradient on the real *** thus derive the gradient of the model from this target and propose the Model Gradient algorithm(MG)to integrate this novel model learning approach with policy-gradient-based policy *** conduct experiments on multiple locomotion control tasks and find that MG can not only achieve high sample efficiency but also lead to better convergence performance compared to traditional model-based reinforcement learning approaches.
The integration of additive manufacturing and topology optimization makes it possible to fabricate complex configurations,especially for microscale structures,which can guarantee the realization of high-performance st...
详细信息
The integration of additive manufacturing and topology optimization makes it possible to fabricate complex configurations,especially for microscale structures,which can guarantee the realization of high-performance structural ***,topology results often contain microstructures(several multicellular scales)similar to the characteristic length of local macrostructures,leading to errors in structural performance analysis based on classical ***,it is necessary to consider the size effect in topology *** this paper,we establish a novel topology optimization model utilizing the integral nonlocal theory to account for the size *** approach consists of an integral constitutive model that incorporates a kernel function,enabling the description of stress at a specific point in relation to strain in a distant *** optimization structures based on nonlocal theory are presented for some benchmark examples,and the results are compared with those based on classical medium *** material layout exhibits significant differences between the two approaches,highlighting the necessity of topology optimization based on nonlocal theory and the effectiveness of the proposed method.
Deep reinforcement learning (DRL) is suitable for solving complex path-planning problems due to its excellent ability to make continuous decisions in a complex environment. However, the increase in the population size...
详细信息
暂无评论