Results 21 to 30 of about 480 (135)
Zhongguo youzhi, 2023 为实现对市面上常见以及实际案件中出现的动物油样本进行快速无损识别，借助光谱分析技术和机器学习算法，基于连续分类策略，对不同动物油样本在种类及品牌/来源地方面进行区分和认定。收集了247份动物油样本(鸡油、牛油、鹅油、猪油、羊油、鸭油)，对其进行红外光谱扫描，采用自动基线校正和峰面积归一化消除样本基线漂移和量纲不一致情况；再分别采用Savitzky-Golay平滑、二项式平滑、邻域平均法、FFT滤波、一阶导数和二阶导数对红外光谱进行预处理，比较了6种预处理方法在降噪方面的差异性 ...
邱薇纶1，王晓庆2 QIU Weilun1, WANG Xiaoqing2
doaj +1 more source
A comparative study on NLOS error elimination methods based on channel measurement experiment
Xibei Gongye Daxue Xuebao, 2022 In order to study the performance of different elimination methods on the distance estimation forward error caused by the non-line-of-sight (NLOS) propagation of radio signals, this paper is based on the mean value, root mean square delay spread ...
CHANG Tiantian +5 more
doaj +1 more source
Image spam identification method based on gray-gradient co-occurrence matrix [PDF]
, 2013 In order to avoid the detection of the spam system based on text,more and more spammers have embedded text information into the image.An image spam identification method based on gray-gradient co-occurrence matrix (GGCM) was proposed to detect image spam
Bing FENG, Gang-lu HUA, Zhi-tang LI
core +1 more source
Soft-sensor modeling of silicon content in hot metal based on sparse robust LS-SVR and multi-objective optimization [PDF]
, 2016 To solve the problem that the parameter of silicon content ([Si]) in hot mental is difficult to be directly detected and obtained by manual analysis with large time delay, a method of sparse and robust least squares support vector regression (R-S-LS-SVR)
GUO Dong-wei, ZHOU Ping
core +1 more source
Zhejiang Daxue xuebao. Lixue ban, 2016 为在方案设计初期与工程造价相关信息很少的条件下，准确快速地预测住宅工程造价，在分析既往相关理论和方法优劣的基础上，选取支持向量机构建住宅工程造价预测模型，并通过主成分分析对原始数据进行降噪处理.选取住宅工程造价预测指标集与样本，对输入指标的数据进行主成分分析，消除指标相关性的同时对原始数据降维，将处理后的数据分别导入到“标准支持向量机”和“最小二乘支持向量机”模型中进行训练和预测，并对预测结果进行对比分析，选取较为合理的预测模型，通过参数寻优进一步优化预测效果.所构建预测模型的相对误差均控制在±7%以内，
QINZhongfu(秦中伏) +3 more
doaj +1 more source
Rapid detection method for pork freshness using fusion spectroscopy and improved BAS-LSSVM [PDF]
ObjectiveTo realize accurate, rapid, and non-destructive testing of meat freshness.MethodsExtracting spectral feature information based on a spectral acquisition system, proposed a fast non-destructive detection method for meat freshness (TVB-N) by ...
REN Xiaozhen, WANG Yao
core +1 more source
Non destructive detection of kiwifruit sugar content based on improved WOA-LSSVM and hyperspectral analysis [PDF]
Objective: Addressing the issues of poor accuracy and low efficiency in non-destructive testing methods for kiwifruit sugar content. Methods: Proposing a non-destructive testing method for kiwifruit sugar content that combined hyperspectral detection ...
LI Rulin +3 more
core +1 more source
Time series data aggregation algorithm with synchronous prediction for WBAN [PDF]
, 2015 Due to the nonlinearity and nonstationarity of the physiological data sensed by WBAN,data aggregation cannot be effectively achieved according to the time-domain trend of data.Therefore,a novel time series data aggregation algorithm with synchronous ...
Da-peng WU, Mei-ling ZHAI, Ru-yan WANG
core +1 more source
Evolutionary algorithms in dynamic environments [PDF]
, 2006 The file attached to this record is the author's final peer reviewed version.Evolutionary algorithms (EAs) are widely and often used for solving stationary optimization problems where the fitness landscape or objective function does not change during the
Wang, Dingwei +2 more
core
Research of Underwater Acoustic Communication Signal Modulation Recognition and Its Implementation [PDF]
, 2016 随着海洋开发、海洋权益维护、国防安全等领域信息获取和处理需求的不断提升，对水声通信信号的调制样式的自动识别研究成为重要的研究课题。然而目前无线领域常用的通信信号(BPSK，QPSK，MFSK，OFDM)的调制识别方法往往需要较多的调制参数作为先验知识（如精确载波频率、初始相位、符号速率）。由于水声信道的随机时-空-频变、窄带高噪、多途效应及多普勒频移等特性，使得上述这些先验知识在水声信号调制方式未知的情况下很难得到，因此，非合作水声通信信号的自动识别极具挑战性。 信号频谱是对信号在频域方面的一种描述 ...
江伟华
core