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.

中文翻译：

---

在移动设备上训练和分析小儿情绪识别分类器

在移动设备上实施自动化情绪识别可以为那些难以识别情绪的人提供一种易于使用的诊断和治疗工具，包括患有自闭症等发育行为疾病的儿童。尽管最近在构建更准确的情感分类器方面取得了进展，但现有模型的计算成本太高，无法部署在移动设备上。在这项研究中，我们优化和分析了各种为边缘设备推理而设计的机器学习模型，并且能够匹配先前用于儿童情绪识别的最先进结果。我们最好的模型，一个在 ImageNet 上预训练的 MobileNet-V2 网络，在 CAFE 上实现了 65.11% 的平衡准确度和 64.19% 的 F1 分数，同时在摩托罗拉 Moto G6 手机上实现了 45 毫秒的推理延迟。这种平衡精度仅为 1。比 CAFE 的当前最先进技术低 79%，CAFE 使用的模型包含 26.62 倍的参数，即使完全优化也无法在 Moto G6 上运行。这项工作验证了通过专门的设计和优化技术，机器学习模型可以变得足够轻量级，可以部署在移动设备上，并且仍然可以在困难的图像分类任务上实现高精度。