English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Background: Instagram, with millions of posts per day, can be used to informpublic health surveillance targets and policies. However, current researchrelying on image-based data often relies on hand coding of images which is timeconsuming and costly, ultimately limiting the scope of the study. Current bestpractices in automated image classification (e.g., support vector machine(SVM), Backpropagation (BP) neural network, and artificial neural network) arelimited in their capacity to accurately distinguish between objects withinimages. Objective: This study demonstrates how convolutional neural network(CNN) can be used to extract unique features within an image and how SVM canthen be used to classify the image. Methods: Images of waterpipes or hookah (anemerging tobacco product possessing similar harms to that of cigarettes) werecollected from Instagram and used in analyses (n=840). CNN was used to extractunique features from images identified to contain waterpipes. A SVM classifierwas built to distinguish between images with and without waterpipes. Methodsfor image classification were then compared to show how a CNN + SVM classifiercould improve accuracy. Results: As the number of the validated training imagesincreased, the total number of extracted features increased. Additionally, asthe number of features learned by the SVM classifier increased, the averagelevel of accuracy increased. Overall, 99.5% of the 420 images classified werecorrectly identified as either hookah or non-hookah images. This level ofaccuracy was an improvement over earlier methods that used SVM, CNN or Bag ofFeatures (BOF) alone. Conclusions: CNN extracts more features of the imagesallowing a SVM classifier to be better informed, resulting in higher accuracycompared with methods that extract fewer features. Future research can use thismethod to grow the scope of image-based studies.

jmir. journal of medical internet research/journal of medical internet research

Automated identification of hookahs (waterpipes) on Instagram: an  application in feature extraction using Convolutional Neural Network and  Support Vector Machine classification