Opportunistic sensing allows to efficiently collect information about the physical world and the persons behaving in it. This may mainstream human context and activity recognition in wearable and pervasive computing by removing requirements for a specific deployed infrastructure. In this paper we introduce the newly started European research project OPPORTUNITY within which we develop mobile opportunistic activity and context recognition systems. We outline the project's objective, the approach we follow along opportunistic sensing, data processing and interpretation, and autonomous adaptation and evolution to environmental and user changes, and we outline preliminary results.
Drowsy driving imposes a high safety risk. Current systems often use driving behavior parameters for driver drowsiness detection. The continuous driving automation reduces the availability of these parameters, therefore reducing the scope of such methods. Especially, techniques that include physiological measurements seem to be a promising alternative. However, in a dynamic environment such as driving, only non- or minimal intrusive methods are accepted, and vibrations from the roadbed could lead to degraded sensor technology. This work contributes to driver drowsiness detection with a machine learning approach applied solely to physiological data collected from a non-intrusive retrofittable system in the form of a wrist-worn wearable sensor. To check accuracy and feasibility, results are compared with reference data from a medical-grade ECG device. A user study with 30 participants in a high-fidelity driving simulator was conducted. Several machine learning algorithms for binary classification were applied in user-dependent and independent tests. Results provide evidence that the non-intrusive setting achieves a similar accuracy as compared to the medical-grade device, and high accuracies (>92%) could be achieved, especially in a user-dependent scenario. The proposed approach offers new possibilities for human–machine interaction in a car and especially for driver state monitoring in the field of automated driving.
Lack of trust in or acceptance of technology are some of the fundamental problems that might prevent the dissemination of automated driving. Technological advances, such as augmented reality aids like full-sized windshield displays or AR contact lenses, could be of help to provide a better system understanding to the user. In this work, we picked up on the question of whether augmented reality assistance has the potential to increase user acceptance and trust by communicating system decisions (i.e., transparent system behavior). To prove our hypothesis, we conducted two driving simulator studies to investigate the benefit of scenario augmentation in fully automated driving—first in normal ([Formula: see text]) and then in rearward viewing ([Formula: see text]) direction. Quantitative results indicate that the augmentation of traffic objects/participants otherwise invisible (e.g., due to dense fog), or the presentation of upcoming driving maneuvers while sitting backwards, is a feasible approach to increase user acceptance and trust. Results are further backed by qualitative findings from semistructured interviews and UX curves (a method to retrospectively report experience over time). We conclude that the application of augmented reality, in particular with the emergence of more powerful, lightweight, or integrated devices, is a good opportunity with high potential for automated driving.
PurposeConventional street lighting systems in areas with a low frequency of passersby are online most of the night without purpose. The consequence is that a large amount of power is wasted meaninglessly. With the broad availability of flexible‐lighting technology like light‐emitting diode lamps and everywhere available wireless internet connection, fast reacting, reliably operating, and power‐conserving street lighting systems become reality. The purpose of this work is to describe the Smart Street Lighting (SSL) system, a first approach to accomplish the demand for flexible public lighting systems.Design/methodology/approachThis work presents the SSL system, a framework developed for a dynamic switching of street lamps based on pedestrians' locations and desired safety (or “fear”) zones. In the developed system prototype, each pedestrian is localized via his/her smartphone, periodically sending location and configuration information to the SSL server. For street lamp control, each and every lamppost is equipped with a ZigBee‐based radio device, receiving control information from the SSL server via multi‐hop routing.FindingsThis research paper confirms that the application of the proposed SSL system has great potential to revolutionize street lighting, particularly in suburban areas with low‐pedestrian frequency. More important, the broad utilization of SSL can easily help to overcome the regulatory requirement for CO2 emission reduction by switching off lampposts whenever they are not required.Research limitations/implicationsThe paper discusses in detail the implementation of SSL, and presents results of its application on a small scale. Experiments have shown that objects like trees can interrupt wireless communication between lampposts and that inaccuracy of global positioning system position detection can lead to unexpected lighting effects.Originality/valueThis paper introduces the novel SSL framework, a system for fast, reliable, and energy efficient street lamp switching based on a pedestrian's location and personal desires of safety. Both safety zone definition and position estimation in this novel approach is accomplished using standard smartphone capabilities. Suggestions for overcoming these issues are discussed in the last part of the paper.
Summary:In this paper, a taxonomy of handover and handback (i.e., from manual to automatic control and vice versa) is proposed to be used by practitioners and researchers to help assure the duration of those periods are clearly defined, and accordingly, studies examining them are comparable and have repeatable results. Furthermore, use of this framework will help assure that those implementing automation will do so in a comprehensive manner. The taxonomy is more detailed than that in SAE Standard J3114.Handover includes the phases preparation, perception (of the handover signal), suspension (of in-vehicle tasks) and the actual process of taking over, which can be subdivided into sufficient (to steer and control speed) and full (where situation awareness is complete) control. Furthermore, handover can be imminent, scheduled, or user-initiated. For handback, the phases are initialization, the actual handback, and re-engagement (of the driver). Handback may be optional or mandatory and user-or system initiated. For both handover and handback processes, the duration and change of the control transfer (as a function of time) needs to be precisely described/specified.
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.