Remind Me To Remember: A pilot study of a novel smartphone reminder application for older adults with dementia and mild cognitive impairment.

The SmartPrompt is a smartphone-based reminder application informed by a neuropsychological model of functional disability. This laboratory-based pilot study examined the SmartPrompt feasibility, efficacy, and subjective usability using a within-participant, counterbalanced, cross-over design. Ten participants (M age = 80.3 + 8.2; M education = 15.7 + 2.5; 60% female) with mild cognitive impairment or mild dementia completed the Remember to Drink Test, which required preparing a glass of water at four predetermined times, in a SmartPrompt (SP) and Unprompted condition (UP). Written cues and a clock were available in both conditions; however, in the SP, the smartphone presented auditory alarms and visual reminders to obtain the water at specified times and required photo logging. In a separate session, caregivers were trained and tested on configuring the SmartPrompt. Overall, caregivers and participants learned to effectively use the SmartPrompt. Caregivers achieved near-perfect scores on the configuration quiz and responded well to training. Participants completed significantly more Remember to Drink tasks in the SP (93%) than UP (56%); checking the cues/clock decreased by 87% in the SP. Usability ratings were excellent among caregivers and fair among participants. Results indicate that the SmartPrompt holds promise for reducing functional disability in older adults with cognitive difficulties in at-home contexts.

ARCHIE++ : A Cloud-Enabled Framework for Conducting AR System Testing in the Wild.

In this paper, we present ARCHIE++, a testing framework for conducting AR system testing and collecting user feedback in the wild. Our system addresses challenges in AR testing practices by aggregating usability feedback data (collected in situ) with system performance data from that same time period. These data packets can then be leveraged to identify edge cases encountered by testers during unconstrained usage scenarios. We begin by presenting a set of current trends in performing human testing of AR systems, identified by reviewing a selection of recent work from leading conferences in mixed reality, human factors, and mobile and pervasive systems. From the trends, we identify a set of challenges to be faced when attempting to adopt these practices to testing in the wild. These challenges are used to inform the design of our framework, which provides a cloud-enabled and device-agnostic way for AR systems developers to improve their knowledge of environmental conditions and to support scalability and reproducibility when testing in the wild. We then present a series of case studies demonstrating how ARCHIE++ can be used to support a range of AR testing scenarios, and demonstrate the limited overhead of the framework through a series of evaluations. We close with additional discussion on the design and utility of ARCHIE++ under various edge conditions.

Cross-Weather Image Alignment via Latent Generative Model with Intensity Consistency.

Image alignment/registration/correspondence is a critical prerequisite for many vision-based tasks, and it has been widely studied in computer vision. However, aligning images from different domains, such as cross-weather/season road scenes, remains a challenging problem. Inspired by the success of classic intensity-constancy-based image alignment methods and the modern generative adversarial network (GAN) technology, we propose a cross-weather road scene alignment method called latent generative model with intensity constancy. From a novel perspective, the alignment problem is formulated as a constrained 2D flow optimization problem with latent encoding, which can be decoded into an intensity-constancy image on the latent image manifold. The manifold is parameterized by a pre-trained GAN, which is able to capture statistic characteristics from large datasets. Moreover, we employ the learned manifold to constrain the warped latent image identical to the target image, thereby producing a realistic warping effect. Experimental results on several cross-weather/season road scene datasets demonstrate that our approach can significantly outperform the state-of-the-art methods.

The Virtual Kitchen Challenge: preliminary data from a novel virtual reality test of mild difficulties in everyday functioning.

Background: Efficient, objective measures of mild functional difficulties are lacking. Preliminary data from a novel, non-immersive virtual reality, performance-based task (Virtual Kitchen Challenge; VKC) were obtained to address this gap. Methods: 14 older and 21 younger adults completed cognitive tests and two everyday tasks (breakfast, lunch) in the VKC with virtual objects and a touch-screen and in the Real Kitchen with real objects (order counterbalanced). Automated performance measures were obtained from the VKC program and human coders scored VKC and Real Kitchen videos for errors. Results: Older adults made more errors than younger adults on the VKC and Real Kitchen, with similar error patterns across measures. VKC automated measures were significantly related to measures from human coders, performance on the Real Kitchen, and cognitive test scores. Conclusion: The VKC is a valid and highly efficient performance-based measure of subtle functional difficulties with great potential for future clinical and research applications.

IBE-Lite: a lightweight identity-based cryptography for body sensor networks.

A body sensor network (BSN) is a network of sensors deployed on a person's body for health care monitoring. Since the sensors collect personal medical data, security and privacy are important components in a BSN. In this paper, we developed IBE-Lite, a lightweight identity-based encryption suitable for sensors in a BSN. We present protocols based on IBE-Lite that balance security and privacy with accessibility and perform evaluation using experiments conducted on commercially available sensors.