With the rapid development of computing technology, wearable devices such as smart phones and wristbands make it easy to get access to people's health information including activities, sleep, sports, etc. Smart healthcare achieves great success by training machine learning models on large quantity of user data. However, there are two critical challenges. Firstly, user data often exists in the form of isolated islands, making it difficult to perform aggregation without compromising privacy security. Secondly, the models trained on the cloud fail on personalization. In this paper, we propose FedHealth, the first federated transfer learning framework for wearable healthcare to tackle these challenges. FedHealth performs data aggregation through federated learning, and then builds personalized models by transfer learning. It is able to achieve accurate and personalized healthcare without compromising privacy and security. Experiments demonstrate that FedHealth produces higher accuracy (5.3% improvement) for wearable activity recognition when compared to traditional methods. FedHealth is general and extensible and has the potential to be used in many healthcare applications.

No abstract

Microstructural stability and microstructure-property relationship during long-term thermal exposure in K452 alloy (a new Ni-base cast superalloy with~21 pct Cr, 11 pct Co, 3.5 pct W, 2.5 pct Al, 3.5 pct Ti, and others) are investigated. It is found that exposure temperature and time have significant effects on the microstructure and properties of the alloy. During exposure, the microstructure is degraded by c¢ coarsening, MC carbide (M mainly represents Ti, W, and Nb) degeneration, precipitation and evolution of grain interior (GI) M 23 C 6 carbide, evolution of grain boundary (GB) microstructure, and precipitation of g phase. Among them, the c¢ coarsening is the leading reason for the decrease of strength of the alloy. The GI M 23 C 6 and the g phase have negligible influence on the properties due to their relatively small populations. Blocky, closely spaced GB M 23 C 6 particles engulfed in c¢ increase the stress-rupture life, whereas the formation of a continuous GB M 23 C 6 chain has an opposite effect. A life peak occurs when the M 23 C 6 /c¢ structure at the GBs is in an optimal form. The degenerated MC is the preferred initiation site of microcracks. Its presence at the GBs promotes the onset of intergranular fracture, and leads to the decrease in mechanical properties.

Human activity recognition (HAR) aims at recognizing activities by training models on the large quantity of sensor data. Since it is time-consuming and expensive to acquire abundant labeled data, transfer learning becomes necessary for HAR by transferring knowledge from existing domains. However, there are two challenges existing in cross-dataset activity recognition. The first challenge is source domain selection. Given a target task and several available source domains, it is difficult to determine how to select the most similar source domain to the target domain such that negative transfer can be avoided. The second one is accurately activity transfer. After source domain selection, how to achieve accurate knowledge transfer between the selected source and the target domain remains another challenge. In this paper, we propose an Adaptive Spatial-Temporal Transfer Learning (ASTTL) approach to tackle both of the above two challenges in cross-dataset HAR. ASTTL learns the spatial features in transfer learning by adaptively evaluating the relative importance between the marginal and conditional probability distributions. Besides, it captures the temporal features via incremental manifold learning. Therefore, ASTTL can learn the adaptive spatial-temporal features for cross-dataset HAR and can be used for both source domain selection and accurate activity transfer. We evaluate the performance of ASTTL through extensive experiments on 4 public HAR datasets, which demonstrates its effectiveness. Furthermore, based on ASTTL, we design and implement an adaptive cross-dataset HAR system called Client-Cloud Collaborative Adaptive Activity Recognition System (3C2ARS) to perform HAR in the real environment. By collecting activities in the smartphone and transferring knowledge in the cloud server, ASTTL can significantly improve the performance of source domain selection and accurate activity transfer.