IMPROVED ANN SEARCH ENGINE FOR CCRC NET 1H NMR XYLOGLUCAN DATABASE

CCRC-Net的1H-NMR谱数据库的人工神经网络搜索引擎 用改进的ANN引擎代替木葡聚糖寡糖。 新引擎使用更多的重复光谱进行训练 以增加其模式匹配精度。 新 引擎更强大，提供更少的“误报” 比原来的搜索引擎。 新引擎还可以 处理的光谱的信噪比只有 可以由以前的引擎处理的光谱。 还 已经记录了新的木葡聚糖数据库的1H-NMR谱; 计划为这些结构建立数据库和搜索引擎。

The ANN search engine of CCRC-Net's database of 1H-NMR spectra of xyloglucan oligosaccharides was replaced with an improved ANN engine. The new engine was trained with a greater number of duplicate spectra per structure to increase its pattern-matching accuracy. The new engine is much more robust and delivers far fewer "false-positive" matches than the original search engine. The new engine can also handle spectra that have half the signal-to-noise ratio of those spectra that could be handled by the previous engine. Also, the 1H-NMR spectra for a new xyloglucan database have been recorded; a new database and search engine is planned for these structures.