Impact of delayed response on wearable cognitive assistance

Abstract

Wearable cognitive assistants (WCA) are anticipated to become a widely-used application class, in conjunction with emerging network infrastructures like 5G that incorporate edge computing capabilities. While prototypical studies of such applications exist today, the relationship between infrastructure service provisioning and its implication for WCA usability is largely unexplored despite the relevance that these applications have for future networks. This paper presents an experimental study assessing how WCA users react to varying end-to-end delays induced by the application pipeline or infrastructure. Participants interacted directly with an instrumented task-guidance WCA as delays were introduced into the system in a controllable fashion. System and task state were tracked in real time, and biometric data from wearable sensors on the participants were recorded. Our results show that periods of extended system delay cause users to correspondingly (and substantially) slow down in their guided task execution, an effect that persists for a time after the system returns to a more responsive state. Furthermore, the slow-down in task execution is correlated with a personality trait, neuroticism, associated with intolerance for time delays. We show that our results implicate impaired cognitive planning, as contrasted with resource depletion or emotional arousal, as the reason for slowed user task executions under system delay. The findings have several implications for the design and operation of WCA applications as well as computational and communication infrastructure, and additionally for the development of performance analysis tools for WCA.

Energy-Optimal Sampling for Edge Computing Feedback Systems: Aperiodic Case

“…In this work, we prioritise Rayleigh distribution in our mathematical formulations. This is because, past works on WCA [2], [3] and our own distribution fitting using task completion time dataset from [3] suggest that the task completion times follow Rayleigh distribution.…”

“…Within the class of such delay and latencysensitive applications, a subgroup of new applications that process snapshots of reality and provide feedback either to devices or humans are receiving an increasing amount of recent research attention. Some examples of such feedback systems are human-in-the-loop applications such as augmented reality, wearable cognitive assistants (WCA) [2], [3], and ambient safety. Another example from the domain of cyber-physical systems (CPS) is in the context of automated fault detection, where the acoustic data is processed for vibration analysis to potentially initiate some maintenance, safety or emergency procedures [4].…”

“…In our previous works, we have extensively studied the efficient capture of essential events in a video analytics system (VAS) and a general cyber-physical system (CPS) using an optimal periodic sampling [24], [25]. The VAS in our research is motivated by the WCA from [2], [3] where a human task progress is monitored continuously by a video stream processed at a remote server for the detection of a predefined task completion. The feedback generated after the task completion is used to assist a human user in continuing with the remaining tasks that together complete a whole process.…”

Smart Textiles for Improved Quality of Life and Cognitive Assessment

“…Assistive systems include [ 47 ], and those with Google Glass devices to guide the user through a complex (cognitive) task, capturing the view of the wearer and combining with remote processing to perform real-time scene interpretation [ 48 ]. WCAs are anticipated to become a widely-used application class, in conjunction with emerging network infrastructures such as 5G that incorporate edge computing capabilities [ 49 ]. The key enabling technologies are sensor technology, communication technology, and data analysis techniques [ 19 ].…”

Network QoS Impact on Spatial Perception through Sensory Substitution in Navigation Systems for Blind and Visually Impaired People

“…Additionally, commercially available devices usually need to be portable and lightweight while withstanding hours of uninterrupted operation under relatively high computational load. Therefore, common designs rely on front-end wireless sensors and low-latency computation offloading [ 2 ].…”