<![CDATA[Apart from being a person's identity, the face is also a supporting tool in direct socializing. A person can convey emotions experienced using expressions raised by their face. Emotion is a feeling to encourage an individual or a response to a stimulus. In consumer research, consumer testing is a method used to predict product acceptance by consumers in a market. Even though it has gone through extensive consumer testing stages before entering the market, the failure rate of new food products is still high. This shows that traditional consumer testing methods are not able to predict market performance and product acceptance by consumers in the long run. To be able to know consumer behavior more deeply, the use of emotional measurement is widely used in consumer testing because emotions affect consumer behavior. In this case, the classification of emotions based on facial characteristics is considered suitable to help improve the quality of consumer testing. The method used in this study is the Convolutional Neural Network (CNN). The data used are data obtained from the Extended Cohn-Kanade Dataset (CK +) taken from 210 subjects with a total of 327 images used. Testing the study using K-fold Cross Validation with a k value of 4. The test results show a certain learning rate value can train architecture better than other learning rate values. The best accuracy results in this study amounted to 86.4% and an average accuracy of 80.7%.]]>
Copyrights © 2019
