Automated Identification of Hookahs (Waterpipes) on Instagram: An Application in Feature Extraction Using Convolutional Neural Network and Support Vector Machine Classification.
Automated Identification of Hookahs (Waterpipes) on Instagram: An Application in Feature Extraction Using Convolutional Neural Network and Support Vector Machine Classification.
复制标题
DOI：
10.2196/10513
复制
发表时间：
2018-11-21
影响因子：
7.4
通讯作者：
Boley Cruz T
中科院分区：
文献类型：
--
作者：
Zhang Y;Allem JP;Unger JB;Boley Cruz T
Instagram每天有数百万条帖子，可以用来为公共卫生监测目标和政策提供信息。然而，目前依赖于基于图像数据的研究往往依赖于对图像进行手工编码，这既耗时又昂贵，最终限制了研究的范围。目前自动图像分类的最佳实践（例如，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。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。从Instagram上收集了水烟或水烟（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）。使用CNN从识别出包含水管的图像中提取独特的特征。建立了一种支持向量机分类器来区分带有和不带有水管的图像。然后比较了图像分类的方法，以显示CNN+SVM分类器如何提高准确率。随着经过验证的训练图像数量的增加，提取的特征总数也会增加。此外，随着SVM分类器学习到的特征数量的增加，平均准确率水平也随之提高。总体而言，99.5%（418/420）的图像分类被正确识别为水烟或非水烟图像。这种精度水平是对早期仅使用SVM、CNN或特征袋的方法的改进。CNN提取了更多的图像特征，使SVM分类器获得了更好的信息，与提取较少特征的方法相比，准确率更高。未来的研究可以利用这种方法来扩大基于图像的研究范围。本文提出的方法可能有助于发现某些烟草产品在社交媒体上的受欢迎程度随着时间的推移而增加。通过从Instagram上获取水烟的图像，我们将我们的方法置于一个可用于卫生研究人员分析社交媒体的背景下，以了解新兴烟草产品的用户体验，并为公共卫生监测目标和政策提供信息。
Instagram, with millions of posts per day, can be used to inform public health surveillance targets and policies. However, current research relying on image-based data often relies on hand coding of images, which is time-consuming and costly, ultimately limiting the scope of the study. Current best practices in automated image classification (eg, support vector machine (SVM), backpropagation neural network, and artificial neural network) are limited in their capacity to accurately distinguish between objects within images. This study aimed to demonstrate how a convolutional neural network (CNN) can be used to extract unique features within an image and how SVM can then be used to classify the image. Images of waterpipes or hookah (an emerging tobacco product possessing similar harms to that of cigarettes) were collected from Instagram and used in the analyses (N=840). A CNN was used to extract unique features from images identified to contain waterpipes. An SVM classifier was built to distinguish between images with and without waterpipes. Methods for image classification were then compared to show how a CNN+SVM classifier could improve accuracy. 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. 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.
登录
查看更多内容
影响因子：
7.8
作者：
Ciresan, Dan;Meier, Ueli;Schmidhuber, Juergen
通讯作者：
Schmidhuber, Juergen
影响因子：
7.4
作者：
Myslín M;Zhu SH;Chapman W;Conway M
通讯作者：
Conway M
影响因子：
4.8
作者：
Burges, CJC
通讯作者：
Burges, CJC
影响因子：
5.1
作者：
Escalera, Sergio;Pujol, Oriol;Radeva, Petia
通讯作者：
Radeva, Petia
影响因子：
8.5
作者：
Allem JP;Ramanujam J;Lerman K;Chu KH;Boley Cruz T;Unger JB
通讯作者：
Unger JB