TransNet: Minimally Supervised Deep Transfer Learning for Dynamic Adaptation of Wearable Systems
TransNet: Minimally Supervised Deep Transfer Learning for Dynamic Adaptation of Wearable Systems
复制标题
DOI：
10.1145/3414062
复制
发表时间：
2020-09
期刊：
影响因子：
--
通讯作者：
Seyed Ali Rokni;Marjan Nourollahi;Parastoo Alinia;Seyed Iman Mirzadeh;Mahdi Pedram;H. Ghasemzadeh
中科院分区：
文献类型：
--
作者：
Seyed Ali Rokni;Marjan Nourollahi;Parastoo Alinia;Seyed Iman Mirzadeh;Mahdi Pedram;H. Ghasemzadeh
可穿戴设备有望通过自动化的成本效益，客观和实时的健康监测来改变健康和健康。然而，这些系统的机器学习模型是基于在受控环境中收集的标记数据和设计的特征表示来设计的。这种方法限制了可穿戴设备的可扩展性，因为（i）收集和标记足够大量的传感器数据是劳动密集型和昂贵的过程;以及（ii）可穿戴设备部署在其上下文经历一致变化的终端用户的高度动态环境中。我们引入了TransNet，这是一个深度学习框架，通过构建可扩展的计算方法，最大限度地减少了数据标记，特征工程和算法再训练的成本。TransNet在框架的较低层中学习通用和可重用的功能，并从新域中的少量标记实例中快速重新配置底层模型，例如当系统被新用户采用时，或者当以前看不见的事件被添加到系统的事件词汇表时。在四个活动数据集上使用TransNet，TransNet在跨学科学习场景中仅使用每个活动类的一个标记实例，平均准确率达到88.1%。使用5个标记实例时，此性能提高到92.7%的准确率。
Wearables are poised to transform health and wellness through automation of cost-effective, objective, and real-time health monitoring. However, machine learning models for these systems are designed based on labeled data collected, and feature representations engineered, in controlled environments. This approach has limited scalability of wearables because (i) collecting and labeling sufficiently large amounts of sensor data is a labor-intensive and expensive process; and (ii) wearables are deployed in highly dynamic environments of the end-users whose context undergoes consistent changes. We introduce TransNet, a deep learning framework that minimizes the costly process of data labeling, feature engineering, and algorithm retraining by constructing a scalable computational approach. TransNet learns general and reusable features in lower layers of the framework and quickly reconfigures the underlying models from a small number of labeled instances in a new domain, such as when the system is adopted by a new user or when a previously unseen event is to be added to event vocabulary of the system. Utilizing TransNet on four activity datasets, TransNet achieves an average accuracy of 88.1% in cross-subject learning scenarios using only one labeled instance for each activity class. This performance improves to an accuracy of 92.7% with five labeled instances.