| 支持向量机在电子鼻区分不同品种苹果中的应用 |
| |
| 引用本文： | 邹小波,赵杰文.支持向量机在电子鼻区分不同品种苹果中的应用[J].农业工程学报,2007,23(1):146-149. |
| |
| 作者姓名： | 邹小波 赵杰文 |
| |
| 作者单位： | 江苏大学农产品加工研究所,镇江,212013 |
| |
| 基金项目： | 国家高技术研究发展计划(863计划);国家自然科学基金;高等学校博士学科点专项科研项目 |
| |
| 摘 要： | 为了提高电子鼻检测苹果气味的精度和鲁棒性,利用6点平滑法对气体传感器的数据进行去噪处理,并用支持向量机建立识别模型。应用结果表明,经过去噪处理后,曲线变得光滑,但仍能保持原来的形状,这说明去噪处理既滤除了传感器数据中的噪声同时又保留了传感器的主要信息。提取每个传感器的最大值作为特征参数。分别运用主成分分析和两个支持向量机模型区分富士、花牛、姬娜3种不同品种苹果的气味,主成分分析结果表明3种苹果分布区域存在重叠;两个支持向量机模型可以很好的区分这3种苹果,其中对姬娜和富士的识别正确率达到90％以上,而对花牛苹果的识别正确率达到100％。
|
| 关 键 词： | 电子鼻 支持向量机 苹果 识别 气体传感器阵列 |
| 文章编号： | 1002-6819(2007)1-0146-04 |
| 收稿时间： | 2006/2/14 0:00:00 |
| 修稿时间： | 2006-02-14 |
Distinguishing different cultivar apples by electronic nose based on support vector machine |
| |
| Zou Xiaobo and Zhao Jiewen.Distinguishing different cultivar apples by electronic nose based on support vector machine[J].Transactions of the Chinese Society of Agricultural Engineering,2007,23(1):146-149. |
| |
| Authors: | Zou Xiaobo and Zhao Jiewen |
| |
| Institution: | Agricultural Product Processing Research Institutes, Jiangsu University, Zhenjiang 212013, China;Agricultural Product Processing Research Institutes, Jiangsu University, Zhenjiang 212013, China |
| |
| Abstract: | To improve the precision and robustness of electronic nose, six-point smoothing method was used to de-noise the gas sensors data, and support vector machine(SVM) was used to develop recognition models. Compared with those original gas sensors curves, the curves after pretreatment were smoother, but their shapes showed not much difference. This indicated that the major information in apple could be reserved while noise was removed by the six-point smoothing method. The maximum of each sensor response was extracted as features. Principal component analysis(PCA) and two support vector machine(SVM) models were used to analyze the features and distinguish three different cultivar apples which were "Fuji", "Huaniu" and "Jina". The PCA results show that it is difficult to distinguish the three apple cultivars by linear models. The recognition of "Haniu" was 100% obtained by the first SVM model, and the distinguishing ability of second SVM model between "Jina" and "Fuji" was 90% for calibration set and 100% for prediction set. |
| |
| Keywords: | electronic nose support vector machine apple identification gas sensor array |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《农业工程学报》浏览原始摘要信息 |
| 点击此处可从《农业工程学报》下载免费的PDF全文 |
|
