Search

To demonstrate the value of machine learning based smart health technologies, researchers have to deploy their solutions into complex real-world environments with real participants. This gives rise to many, oftentimes unexpected, challenges for creating technology in a lab environment that will work when deployed in real home environments. In other words, like more mature disciplines, we need solutions for what can be done at development time to increase success at deployment time. To illustrate an approach and solutions, we use an example of an ongoing project that is a pipeline of voice based machine learning solutions that detects the anger and verbal conflicts of the participants. For anonymity, we call it the XYZ system. XYZ is a smart health technology because by notifying the participants of their anger, it encourages the participants to better manage their emotions. This is important because being able to recognize one's emotions is the first step to better managing one's anger. XYZ was deployed in 6 homes for 4 months each and monitors the emotion of the caregiver of a dementia patient. In this paper we demonstrate some of the necessary steps to be accomplished during the development stage to increase deployment time success, and show where continued work is still necessary. Note that the complex environments arise both from the physical world and from complex human behavior.

In smart computing, the labels of training samples for a specific task are not always abundant. However, the labels of samples in a relevant but different dataset are available. As a result, researchers have relied on unsupervised domain adaptation to leverage the labels in a dataset (the source domain) to perform better classification in a different, unlabeled dataset (target domain). Existing non-generative adversarial solutions for UDA aim at achieving domain confusion through adversarial training. The ideal scenario is that perfect domain confusion is achieved, but this is not guaranteed to be true. To further enforce domain confusion on top of the adversarial training, we propose a novel UDA algorithm, \textit{E-ADDA}, which uses both a novel variation of the Mahalanobis distance loss and an out-of-distribution detection subroutine. The Mahalanobis distance loss minimizes the distribution-wise distance between the encoded target samples and the distribution of the source domain, thus enforcing additional domain confusion on top of adversarial training. Then, the OOD subroutine further eliminates samples on which the domain confusion is unsuccessful. We have performed extensive and comprehensive evaluations of E-ADDA in the acoustic and computer vision modalities. In the acoustic modality, E-ADDA outperforms several state-of-the-art UDA algorithms by up to 29.8%, measured in the f1 score. In the computer vision modality, the evaluation results suggest that we achieve new state-of-the-art performance on popular UDA benchmarks such as Office-31 and Office-Home, outperforming the second best-performing algorithms by up to 17.9%.

A study was conducted to determine whether cooperative testing would result in better performance and less anxiety than individual testing. Two sections of a developmental psychology class used cooperative testing, and a third section used traditional testing methods. Four multiple choice tests containing 50 items were administered to each group, with items equally divided between easy and moderately difficult items. Each student had his/her own answer sheet which contained items asking for a rating of anxiety and expected performance and an indication of preferred type of testing. Test completion times were noted when students turned in their exam. Several days prior to the first cooperative exam, students were told that they could pick a partner for the next exam, but that they would each turn in their own answer sheets. They were allowed to change partners for the second cooperative examination and were not required to participate. In one class section, 7 of 34 students chose not to participate, while in the second section 9 of 24 chose not to participate. The mean test scores of the non-participating students did not differ significantly from the means of the subjects taking individual tests. At first glance, cooperative testing seemed to produce superior performance; however, not all students benefited equally from cooperative testing. The two cooperative-testing class sections showed very different patterns of performance. Though there were no differences in anxiety between students using cooperative and traditional testing methods, students who used both methods showed a strong preference for cooperative testing. (AC)