Training and Profiling a Pediatric Emotion Recognition Classifier on Mobile Devices
This work provides an accessible diagnostic tool for children with developmental conditions like autism by enabling efficient emotion recognition on mobile devices, though it is incremental as it adapts existing methods for mobile deployment.
The study tackled the problem of deploying accurate emotion recognition models on mobile devices by optimizing lightweight models, achieving 65.11% balanced accuracy on the CAFE dataset with only a 1.79% drop from state-of-the-art while enabling 45-millisecond inference on a mobile phone.
Implementing automated emotion recognition on mobile devices could provide an accessible diagnostic and therapeutic tool for those who struggle to recognize emotion, including children with developmental behavioral conditions such as autism. Although recent advances have been made in building more accurate emotion classifiers, existing models are too computationally expensive to be deployed on mobile devices. In this study, we optimized and profiled various machine learning models designed for inference on edge devices and were able to match previous state of the art results for emotion recognition on children. Our best model, a MobileNet-V2 network pre-trained on ImageNet, achieved 65.11% balanced accuracy and 64.19% F1-score on CAFE, while achieving a 45-millisecond inference latency on a Motorola Moto G6 phone. This balanced accuracy is only 1.79% less than the current state of the art for CAFE, which used a model that contains 26.62x more parameters and was unable to run on the Moto G6, even when fully optimized. This work validates that with specialized design and optimization techniques, machine learning models can become lightweight enough for deployment on mobile devices and still achieve high accuracies on difficult image classification tasks.