Model-Agnostic Structural Transfer Learning for Cross-Domain Autonomous Activity Recognition.

Activity recognition using data collected with smart devices such as mobile and wearable sensors has become a critical component of many emerging applications ranging from behavioral medicine to gaming. However, an unprecedented increase in the diversity of smart devices in the internet-of-things era has limited the adoption of activity recognition models for use across different devices. This lack of cross-domain adaptation is particularly notable across sensors of different modalities where the mapping of the sensor data in the traditional feature level is highly challenging. To address this challenge, we propose ActiLabel, a combinatorial framework that learns structural similarities among the events that occur in a target domain and those of a source domain and identifies an optimal mapping between the two domains at their structural level. The structural similarities are captured through a graph model, referred to as the dependency graph, which abstracts details of activity patterns in low-level signal and feature space. The activity labels are then autonomously learned in the target domain by finding an optimal tiered mapping between the dependency graphs. We carry out an extensive set of experiments on three large datasets collected with wearable sensors involving human subjects. The results demonstrate the superiority of ActiLabel over state-of-the-art transfer learning and deep learning methods. In particular, ActiLabel outperforms such algorithms by average F1-scores of 36.3%, 32.7%, and 9.1% for cross-modality, cross-location, and cross-subject activity recognition, respectively.

Designing Deep Neural Networks Robust to Sensor Failure in Mobile Health Environments.

Missing data is a very common challenge in health monitoring systems and one reason for that is that they are largely dependent on different types of sensors. A critical characteristic of the sensor-based prediction systems is their dependency on hardware, which is prone to physical limitations that add another layer of complexity to the algorithmic component of the system. For instance, it might not be realistic to assume that the prediction model has access to all sensors at all times. This can happen in the real-world setup if one or more sensors on a device malfunction or temporarily have to be disabled due to power limitations. The consequence of such a scenario is that the model faces "missing input data" from those unavailable sensors at the deployment time, and as a result, the quality of prediction can degrade significantly. While the missing input data is a very well-known problem, to the best of our knowledge, no study has been done to efficiently minimize the performance drop when one or more sensors may be unavailable for a significant amount of time. The sensor failure problem investigated in this paper can be viewed as a spatial missing data problem, which has not been explored to date. In this work, we show that the naive known methods of dealing with missing input data such as zero-filling or mean-filling are not suitable for senors-based prediction and we propose an algorithm that can reconstruct the missing input data for unavailable sensors. Moreover, we show that on the MobiAct, MotionSense, and MHEALTH activity classification benchmarks, our proposed method can outperform the baselines by large accuracy margins of 8.2%, 15.1%, and 11.6%, respectively.

Continual Learning for Activity Recognition.

The recent success of deep neural networks in prediction tasks on wearable sensor data is evident. However, in more practical online learning scenarios, where new data arrive sequentially, neural networks suffer severely from the "catastrophic forgetting" problem. In real-world settings, given a pre-trained model on the old data, when we collect new data, it is practically infeasible to re-train the model on both old and new data because the computational costs will increase dramatically as more and more data arrive in time. However, if we fine-tune the model only with the new data because the new data might be different from the old data, the neural network parameters will change to fit the new data. As a result, the new parameters are no longer suitable for the old data. This phenomenon is known as catastrophic forgetting, and continual learning research aims to overcome this problem with minimal computational costs. While most of the continual learning research focuses on computer vision tasks, implications of catastrophic forgetting in wearable computing research and potential avenues to address this problem have remained unexplored. To address this knowledge gap, we study continual learning for activity recognition using wearable sensor data. We show that the catastrophic forgetting problem is a critical challenge for real-world deployment of machine learning models for wearables. Moreover, we show that the catastrophic forgetting problem can be alleviated by employing various training techniques.

Boosting Lying Posture Classification with Transfer Learning.

Automatic lying posture tracking is an important factor in human health monitoring. The increasing popularity of the wrist-based trackers provides the means for unobtrusive, affordable, and long-term monitoring with minimized privacy concerns for the end-users and promising results in detecting the type of physical activity, step counting, and sleep quality assessment. However, there is limited research on development of accurate and efficient lying posture tracking models using wrist-based sensor. Our experiments demonstrate a major drop in the accuracy of the lying posture tracking using wrist-based accelerometer sensor due to the unpredictable noise from arbitrary wrist movements and rotations while sleeping. In this paper, we develop a deep transfer learning method that improves performance of lying posture tracking using noisy data from wrist sensor by transferring the knowledge from an initial setting which contains both clean and noisy data. The proposed solution develops an optimal mapping model from the noisy data to the clean data in the initial setting using LSTM sequence regression, and reconstruct clean synthesized data in another setting where no noisy sensor data is available. This increases the lying posture tracking F1-Score by 24.9% for 'left-wrist' and by 18.1% for 'right-wrist' sensors comparing to the case without mapping.

Use of machine learning to predict medication adherence in individuals at risk for atherosclerotic cardiovascular disease.

Background: Medication nonadherence is a critical problem with severe implications in individuals at risk for atherosclerotic cardiovascular disease. Many studies have attempted to predict medication adherence in this population, but few, if any, have been effective in prediction, sug-gesting that essential risk factors remain unidentified. Objective: This study's objective was to (1) establish an accurate prediction model of medi-cation adherence in individuals at risk for atherosclerotic cardiovascular disease and (2) identify significant contributing factors to the predictive accuracy of medication adherence. In particular, we aimed to use only the baseline questionnaire data to assess medication adherence prediction feasibility. Methods: A sample of 40 individuals at risk for atherosclerotic cardiovascular disease was recruited for an eight-week feasibility study. After collecting baseline data, we recorded data from a pillbox that sent events to a cloud-based server. Health measures and medication use events were analyzed using machine learning algorithms to identify variables that best predict medication adherence. Results: Our adherence prediction model, based on only the ten most relevant variables, achieved an average error rate of 12.9%. Medication adherence was closely correlated with being encouraged to play an active role in their treatment, having confidence about what to do in an emergency, knowledge about their medications, and having a special person in their life. Conclusions: Our results showed the significance of clinical and psychosocial factors for predicting medication adherence in people at risk for atherosclerotic cardiovascular diseases. Clini-cians and researchers can use these factors to stratify individuals to make evidence-based decisions to reduce the risks.