In the era of artificial intelligence, assessing road damage in autonomous driving applications is of paramount importance. Accurate and timely identification of road surface damage is critical for ensuring safety and...
详细信息
The emerging reconfigurable circuit technology, which can establish circuit connections among switches, has been proposed as a promising paradigm for datacenter networks. This paper investigates how to accelerate the ...
详细信息
ISBN:
(纸本)9788995004395
The emerging reconfigurable circuit technology, which can establish circuit connections among switches, has been proposed as a promising paradigm for datacenter networks. This paper investigates how to accelerate the non-preemptive multicast flows in a demand-aware manner in reconfigurable datacenter networks. Firstly, the problem of scheduling the circuit switch to minimize the average completion time is introduced and proved to be NP-hard. A two-round matching algorithm is proposed to handle the conflicts between different multicast flows under the bandwidth constraint. The approximation ratio of the proposed algorithm is proved to be 2√2n, where n denotes the number of Top-of-Rack (ToR). Finally, we have demonstrated that the proposed algorithm can effectively reduce the average completion time of the flow compared to state-of-the-art algorithms through extensive simulations. Copyright 2023 KICS.
The Internet of Things (IoT) stands as a revolutionary technology which impacts smart agriculture and different sectors beyond it. The research describes an intelligent IoT-enabled monitoring system which uses sensors...
详细信息
This study proposes a novel approach based on the DenseNet deep learning architecture to address the demand for traffic sign recognition in intelligent transportation systems. The proposed method leverages the powerfu...
详细信息
The Swarm intelligence algorithm is a very prevalent field in which some scholars have made outstanding *** a representative,Slime mould algorithm(SMA)is widely used because of its superior initial ***,this paper focu...
详细信息
The Swarm intelligence algorithm is a very prevalent field in which some scholars have made outstanding *** a representative,Slime mould algorithm(SMA)is widely used because of its superior initial ***,this paper focuses on the improvement of the SMA and the mitigation of its stagnation *** this aim,the structure of SMA is adjusted to develop the efficiency of the original *** a stochastic optimizer,SMA mainly stimulates the behavior of slime mold in *** the harmony of the exploration and exploitation of SMA,the paper proposed an enhanced algorithm of SMA called ECSMA,in which two mechanisms are embedded into the structure:elite strategy,and chaotic stochastic *** details of the original SMA and the two introduced strategies are given in this ***,the advantages of the improved SMA through mechanism comparison,balance-diversity analysis,and contrasts with other counterparts are *** experimental results demonstrate that both mechanisms have a significant enhancing effect on ***,SMA is applied to four structural design issues of the welded beam design problem,PV design problem,I-beam design problem,and cantilever beam design problem with excellent results.
The Electroencephalogram (EEG) is a widely used fundamental signal for monitoring brain activity and diagnosing sleep disorders. The manual staging of artificial sleep is a time-consuming and laborious task for sleep ...
详细信息
Hydrogen storage plays a pivotal role in the hydrogen industry,yet its current status presents a *** strategies have emerged in recent years to address this ***_(2) has stood out as a promising solid-state hydrogen st...
详细信息
Hydrogen storage plays a pivotal role in the hydrogen industry,yet its current status presents a *** strategies have emerged in recent years to address this ***_(2) has stood out as a promising solid-state hydrogen storage material due to its impressive gravimetric and volumetric hydrogen density,but its practical application is hampered by elevated thermal stability and sluggish *** this study,we introduce a solution by synthesizing Pd metallene through a one-pot solvothermal method,revealing a distinctive highly curved lamellar structure with a thickness of around 1.6 *** this Pd metallene into MgH_(2) results in a composite system wherein the starting dehydrogenation temperature is significantly lowered to 439 K and complete dehydrogenation occurs at 583 K,releasing 6.14 wt.%*** activation energy of dehydrogenation for MgH_(2) was reduced from 170.4 kJ mol^(-1) to 79.85 kJ mol^(-1) after Pd metallene *** enthalpy of dehydrogenation of the MgH_(2)-10 wt.%Pd sample was calculated to be 73 kJ mol^(-1) H_(2)^(-1) and decreased by 4.4 kJ mol^(-1) H_(2)^(-1) from that of dehydrogenation of pure MgH_(2)(77.4 kJ mol^(-1) H_(2)-1).Theoretical calculations show that the average formation energy and average adsorption energy of hydrogen vacancies can be significantly reduced in the presence of both Pd clusters and Pd single atoms on the surface of MgH_(2)/Mg,*** suggests that the synergistic effect of in situ formed Pd single atoms and clusters significantly improves the hydrogenation and dehydrogenation *** identified active sites in this study hold potential as references for forthcoming multi-sized active site catalysts,underscoring a significant advancement toward resolving hydrogen storage limitations.
Represented by evolutionary algorithms and swarm intelligence algorithms, nature-inspired metaheuristics have been successfully applied to recommender systems and amply demonstrated effectiveness, in particular, for m...
详细信息
Coreset selection is powerful in reducing computational costs and accelerating data processing for deep learning algorithms. It strives to identify a small subset from large-scale data, so that training only on the su...
Coreset selection is powerful in reducing computational costs and accelerating data processing for deep learning algorithms. It strives to identify a small subset from large-scale data, so that training only on the subset practically performs on par with full data. Practitioners regularly desire to identify the smallest possible coreset in realistic scenes while maintaining comparable model performance, to minimize costs and maximize acceleration. Motivated by this desideratum, for the first time, we pose the problem of refined coreset selection, in which the minimal coreset size under model performance constraints is explored. Moreover, to address this problem, we propose an innovative method, which maintains optimization priority order over the model performance and coreset size, and efficiently optimizes them in the coreset selection procedure. Theoretically, we provide the convergence guarantee of the proposed method. Empirically, extensive experiments confirm its superiority compared with previous strategies, often yielding better model performance with smaller coreset sizes. The implementation is available at https://***/xiaoboxia/LBCS. Copyright 2024 by the author(s)
As global agricultural production and supply chains become increasingly complex, the demand for food safety and transparency is also growing. Agricultural traceability, as a process of tracing products from production...
详细信息
暂无评论