Results 101 to 110 of about 13,582,659 (253)
Zhejiang Daxue xuebao. Lixue ban, 2010 提出了一种基于整体退火遗传算法的动态IR drop分析方法.该方法在经典遗传算法基础上,引入父代竞争和适应函数模拟退火处理,优化了动态分析的输入向量,加快了分析速度.实验表明,与经典遗传算法相比,该方法提高了动态IR drop分析的准确性,提高了算法收敛速度,繁殖代数平均减少了35%,分析结果改进了10%左右.
ZHOUZhi-ming(周知名) +2 more
doaj +1 more source
Power-aware mapping based-on genetic algorithm for Network-on-Chip(基于遗传算法的片上网络低功耗映射)
Zhejiang Daxue xuebao. Lixue ban, 2010 随着片上网络(Network-on-Chip)集成度的提高,功耗逐渐成为设计的焦点.本文提出了一种在延时约束条件下,基于遗传算法的片上网络通信链路的低功耗映射算法.该算法使用数组方式编码染色体,并采用非常规码的交叉和变异运算因子.它充分利用遗传算法的群体优势,能快速有效地对通信功耗作优化.实验表明,该算法能平均减少50%左右的通信功耗.
DONGWen-xiao(董文箫) +3 more
doaj +1 more source
Noise-Aware and Light-Weight VLSI Design of Bilateral Filter for Robust and Fast Image Denoising in Mobile Systems. [PDF]
Sensors (Basel), 2020 Jang SJ, Hwang Y.
europepmc +1 more source
Computational and theoretical analysis of supervised dimensionality reduction(监督降维算法的计算和理论分析)
Zhejiang Daxue xuebao. Lixue ban, 2009 在小样本条件下,由于离散矩阵的奇异性,作为监督降维的传统线性鉴别分析(LDA)并不能直接计算.许多扩展算法被提出以克服此问题,一般可分为3类：基于类内离散矩阵零空间的方法、基于总体离散矩阵列空间的方法和基于其它子空间的方法.为了深入了解前2类算法的特性,作了计算和理论分析,并得出结论：在满足一定条件下（小样本高维数据一般都满足）,基于类内离散矩阵零空间和基于总体离散矩阵列空间的方法具有等价关系,仅最优矢量集的约束条件和实现途径有所区别.在人脸数据库ORL和YALE上的比较实验结果亦证实了上述结论.
ZHAOWu-feng(赵武锋) +2 more
doaj +1 more source
A systolic architecture for the correlation and accumulation of digital sequences [PDF]
A fully systolic architecture for the implementation of digital sequence correlator/accumulators is described. These devices consist of a two-dimensional array of processing elements that are conceived for efficient fabrication in Very Large Scale ...
Deutsch, L. J., Lahmeyer, C. R.
core +1 more source
Lithographic hotspot detection based on SVM and genetic algorithm(基于支持向量机及遗传算法的光刻热点检测)
Zhejiang Daxue xuebao. Lixue ban, 2011 提出一种基于支持向量机(SVM)及遗传算法(GA)的集成电路版图光刻热点检测方法.首先对版图样本进行离散余弦变换(DCT)以提取样本的频域特征，然后基于这些样本训练SVM分类器以实现对光刻热点的检测.为了提高光刻热点检测的精度及效率，采用遗传算法(GA)对频域特征进行选择，并同时优化SVM参数.实验结果表明，基于SVM及版图频域特征并结合遗传算法进行优化的光刻热点检测方法可以有效提高版图光刻热点的检测精度.
CAOKui-kang(曹葵康) +2 more
doaj +1 more source
Additive effects under the series of EOS in space application VLSI circuits
MATEC Web of Conferences, 2017 One of the problems of space technology is the spacecraft on orbit charging effect. Series of EOS (electrical overstress) are caused by internal charging affect VLSI (very large-scale integrated) circuits, which may lead to its damage. The results of the
Diatlov Nikolai +2 more
doaj +1 more source
Design and analysis of NC-FinFET using Pb(ZryTi1−y)O3 under high ionising radiations
Scientific ReportsTransistor performance degrades in the presence of radiation due to increased interface trap charges. Radiation analysis is used to determine the impact of radiation level up to which the transistor shows its normal behaviour.
Suman Lata Tripathi +4 more
doaj +1 more source
A Sub-1-V Nanopower MOS-Only Voltage Reference
Journal of Low Power Electronics and ApplicationsA novel low-power MOS-only voltage reference is presented. The Enz–Krummenacher–Vittoz (EKV) model is adopted to provide a new perspective on the operating principle.
Siqi Wang +5 more
doaj +1 more source
Power Aware Learning for Class AB Analogue VLSI Neural Network
, 2006 Recent research into Artificial Neural Networks (ANN) has highlighted the potential of using compact analogue ANN hardware cores in embedded mobile devices, where power consumption of ANN hardware is a very significant implementation issue.
Brown, Andrew +2 more
core