Saving energy in residential and commercial buildings is of great interest due to diminishing resources. Heating ventilation and air conditioning systems, and electric lighting are responsible for a significant share of energy usage, which makes it desirable to optimise their operations while maintaining user comfort. Such optimisation requires accurate occupancy estimations. In contrast to current, often invasive or unreliable methods we present an approach for accurate occupancy estimation using a wireless sensor network (WSN) that only collects non-sensitive data and a novel, hierarchical analysis method. We integrate potentially uncertain contextual information to produce occupancy estimates at different levels of granularity and provide confidence measures for effective building management. We evaluate our framework in real-world deployments and demonstrate its effectiveness and accuracy for occupancy monitoring in both low-and high-traffic area scenarios. Furthermore, we show how the system is used for analysing historical data and identify effective room misuse and thus a potential for energy saving.
The assessment of surgical skills is an essential part of medical training. The prevalent manual evaluations by expert surgeons are time consuming and often their outcomes vary substantially from one observer to another. We present a videobased framework for automated evaluation of surgical skills based on the Objective Structured Assessment of Technical Skills (OSATS) criteria. We encode the motion dynamics via frame kernel matrices, and represent the motion granularity by texture features. Linear discriminant analysis is used to derive a reduced dimensionality feature space followed by linear regression to predict OSATS skill scores. We achieve statistically significant correlation (p-value <0.01) between the ground-truth (given by domain experts) and the OSATS scores predicted by our framework.
No abstract
Human activity recognition is progressing from automatically determining what a person is doing and when, to additionally analyzing the quality of these activities—typically referred to as skill assessment. In this chapter, we propose a new framework for skill assessment that generalizes across application domains and can be deployed for near-real-time applications. It is based on the notion of repeatability of activities defining skill. The analysis is based on two subsequent classification steps that analyze (1) movements or activities and (2) their qualities, that is, the actual skills of a human performing them. The first classifier is trained in either a supervised or unsupervised manner and provides confidence scores, which are then used for assessing skills. We evaluate the proposed method in two scenarios: gymnastics and surgical skill training of medical students. We demonstrate both the overall effectiveness and efficiency of the generalized assessment method, especially compared to previous work.
It is challenging to precisely identify the boundary of activities in order to annotate the activity datasets required to train activity recognition systems. This is the case for experts, as well as non-experts who may be recruited for crowd-sourcing paradigms to reduce the annotation effort or speed up the process by distributing the task over multiple annotators. We present a method to automatically adjust annotation boundaries, presuming a correct annotation label, but imprecise boundaries, otherwise known as "label jitter". The approach maximizes the Fukunaga Class-Separability, applied to time series. Evaluations on a standard benchmark dataset showed statistically significant improvements from the initial jittery annotations.
The use of data and metrics on a professional and personal level has led to considerable discourse around the performative power and politics of 'big data' and data visualization, with academia being no exception. We have developed a university system, ResViz, which publicly visualizes the externally funded research projects of academics, and their internal collaborations. We present an interview study that engages 20 key stakeholders, academics and administrators who are part of the pilot release for the first version of this system. In doing so, we describe and problematize our design space, considering the implications of making metrics visible and their social use within a large organization. Our findings cut across the way people communicate, review and manage performance with metrics. We raise seven design issues in this spacepractical considerations that expose the tensions in making metrics available for public contestation.
The Break-Time Barometer is a social awareness system, which was developed as part of an exploratory study of the use of situated sensing and displays to promote cohesion in a newly-dispersed workplace. The Break-Time Barometer specifically aims to use an ambient persuasion approach in order to encourage people to join existing breaks, which take place within this community. Drawing upon a privacysensitive ubiquitous sensing infrastructure, the system offers information about potentially break-related activity in social spaces within this workplace, including alerts when specific events are detected. The system was developed using a user-centered iterative design approach. A qualitative mixed methods evaluation of a full deployment identified a diverse set of reactions to both the system and the design goal, and further elaborated the challenges of designing for social connectedness in this complex workplace context.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.