%0杂志文章%@ 1438-8871 %I JMIR出版物%V 20%卡塔尔世界杯8强波胆分析 N 11% P e10513% T自动识别水烟(水烟)在Instagram上:使用卷积神经网络和支持向量机分类在特征提取中的应用%A张烨山%A Allem, john - patrick %A Unger,Jennifer Beth %A Boley Cruz，南加州大学Tess %+ Keck医学院，2001 N Soto街，3楼Mail，洛杉矶，CA, 90032，美国，1 8586030812，allem@usc.edu %K卷积神经网络%K特征提取%K图像分类%K Instagram %K社交媒体%K支持向量机%D 2018 %7 21.11.2018 %9原创论文%J J医学互联网Res %G英文%X背景:Instagram，每天有数百万条帖子，可用于通知公共卫生监测目标和政策。然而，目前基于图像数据的研究往往依赖于对图像的手工编码，耗时耗力，最终限制了研究范围。目前自动化图像分类的最佳实践(如支持向量机(SVM)、反向传播神经网络和人工神经网络)在准确区分图像内物体的能力方面受到限制。目的:本研究旨在演示如何使用卷积神经网络(CNN)提取图像中的独特特征，以及如何使用支持向量机对图像进行分类。方法:从Instagram上收集水烟或水烟(一种与香烟危害相似的新兴烟草产品)的图像，并用于分析(N=840)。CNN被用来从包含水管的图像中提取独特的特征。建立支持向量机分类器来区分有水管和没有水管的图像。然后比较了图像分类的方法，以展示CNN+SVM分类器如何提高精度。 Results: As the number of validated training images increased, the total number of extracted features increased. In addition, as the number of features learned by the SVM classifier increased, the average level of accuracy increased. Overall, 99.5% (418/420) of images classified were correctly identified as either hookah or nonhookah images. This level of accuracy was an improvement over earlier methods that used SVM, CNN, or bag-of-features alone. Conclusions: A CNN extracts more features of images, allowing an SVM classifier to be better informed, resulting in higher accuracy compared with methods that extract fewer features. Future research can use this method to grow the scope of image-based studies. The methods presented here might help detect increases in the popularity of certain tobacco products over time on social media. By taking images of waterpipes from Instagram, we place our methods in a context that can be utilized to inform health researchers analyzing social media to understand user experience with emerging tobacco products and inform public health surveillance targets and policies. %M 30452385 %R 10.2196/10513 %U //www.mybigtv.com/2018/11/e10513/ %U https://doi.org/10.2196/10513 %U http://www.ncbi.nlm.nih.gov/pubmed/30452385