A5025841244- Social Robot Interaction and HRI
- Context-Aware Activity Recognition Systems
- Advanced Chemical Sensor Technologies
- Insect Pheromone Research and Control
- Robotics and Automated Systems
- Semantic Web and Ontologies
- Olfactory and Sensory Function Studies
- Time Series Analysis and Forecasting
- Technology Use by Older Adults
- Human-Automation Interaction and Safety
- Modular Robots and Swarm Intelligence
- Virtual Reality Applications and Impacts
- Data Management and Algorithms
- Evacuation and Crowd Dynamics
- Robot Manipulation and Learning
- Neural Networks and Applications
- AI-based Problem Solving and Planning
- AI in Service Interactions
- Speech and dialogue systems
- IoT and Edge/Fog Computing
- Natural Language Processing Techniques
- Robotic Path Planning Algorithms
- Teleoperation and Haptic Systems
- Occupational Health and Safety Research
- Anomaly Detection Techniques and Applications
Örebro University
2015-2024
Osnabrück University
2019
KU Leuven
2019
Örebro University Hospital
2001
The availability of high-resolution remote sensing (HRRS) data has opened up the possibility for new interesting applications, such as per-pixel classification individual objects in greater detail. This paper shows how a convolutional neural network (CNN) can be applied to multispectral orthoimagery and digital surface model (DSM) small city full, fast accurate classification. predicted low-level pixel classes are then used improve high-level segmentation. Various design choices CNN...
Most attempts at training computers for the difficult and time-consuming task of sleep stage classification involve a feature extraction step. Due to complexity multimodal data, size space can grow extent that it is also necessary include selection In this paper, we propose use an unsupervised learning architecture called deep belief nets (DBNs) show how apply data in order eliminate handmade features. Using postprocessing step hidden Markov model (HMM) accurately capture switching, compare...
Early detection and adaptive support to changing individual needs related ageing is an important challenge in today's society. In this paper we present a system called GiraffPlus that aims at addressing such developed on-going European project. The consists of network home sensors can be automatically configured collect data for range monitoring services; semi-autonomous telepresence robot; sophisticated context recognition give high-level long term interpretations the collected respond...
Smart home environments have a significant potential to provide for long-term monitoring of users with special needs in order promote the possibility age at home. Such are typically equipped number heterogeneous sensors that monitor both health and environmental parameters. This paper presents framework called E-care@home, consisting an IoT infrastructure, which provides information unambiguous, shared meaning across devices, end-users, relatives, care professionals organizations. We focus...
Safety in human-robot interaction can be divided into physical safety and perceived safety, where the latter is still under-addressed literature. Investigating requires a multidisciplinary perspective. Indeed, often considered as being associated with several common factors studied other disciplines, i.e., comfort, predictability, sense of control, trust. In this paper, we investigated relationship between these using subjective objective measures. We conducted two-by-five mixed-subjects...
Virtual reality (VR) is regarded as a useful tool for teleoperation systems and provides operators with immersive visual feedback on the robot environment. However, without any haptic or physical constructions, VR-based normally suffer from poor maneuverability, operational faults may be caused in some fine movements. In this article, we employ mixed (MR), which combines real virtual worlds, to develop novel system. A new system design control algorithms are proposed. For design, an MR...
Airborne chemical sensing with mobile robots has been an active research areasince the beginning of 1990s. This article presents a review work in this field,including gas distribution mapping, trail guidance, and different subtasks sourcelocalisation. Due to difficulty modelling real world environmentwith currently available simulation techniques, we focus largely on experimental donot consider publications that are purely based simulations.
Emergency situations associated with falls are a serious concern for an aging society. Yet following the recent development within ICT, significant number of solutions have been proposed to track body movement and detect using various sensor technologies, thereby facilitating fall detection in some cases prevention. A reviews on methods ICT technologies emerged literature increasingly popular approach considers combining information from several sources assess falls. The aim this paper is...
Computed tomography (CT) is the method of choice for diagnosing ureteral stones - kidney that obstruct ureter. The purpose this study to develop a computer aided detection (CAD) algorithm identifying stone in thin slice CT volumes. challenge CAD urinary lies similarity shape and intensity with non-stone structures how efficiently deal large high-resolution We address these challenges by using Convolutional Neural Network (CNN) works directly on high resolution evaluated data base 465...
SUMMARY Mobile olfactory robots can be used in a number of relevant application areas where better understanding gas distribution is needed, such as environmental monitoring and safety security related fields. In this paper, we present method to integrate the classification odours together with mapping. The resulting odour map then correlated spatial information collected from laser range scanner form combined map. Experiments are performed using mobile robot large unmodified indoor outdoor...
In this paper we present initial experiments towards environmental monitoring with a mobile platform. A prototype of pollution robot was set up which measures the gas distribution using an ldquoelectronic noserdquo and provides three dimensional wind measurements ultrasonic anemometer. We describe design experimental setup used to run trials under varying conditions. then results mapping. The were carried out in uncontrolled environments very different properties: enclosed indoor area, part...
This article presents the results from a video-based evaluation study of social robotic telepresence solution for elderly. The evaluated system is mobile teleoperated robot called Giraff that allows caregivers to virtually enter home and conduct natural visit just as if they were physically there. focuses on perspectives primary healthcare organizations collects feedback different categories health professionals. included 150 participants yielded unexpected with respect acceptance system. In...
Abstract Safety is a fundamental prerequisite that must be addressed before any interaction of robots with humans. has been generally understood and studied as the physical safety in human–robot interaction, whereas how humans perceive these received less attention. Physical necessary condition for safe interaction. However, it not sufficient condition. A robot by hardware software design can still perceived unsafe. This article focuses on We identified six factors are closely related to...
The green area factor model is a crucial tool for conserving and creating urban greenery ecosystem services within neighborhood land. This serves as valuable index, streamlining the planning, assessment, comparison of local-scale infrastructures. However, conventional on-site measurements are resource intensive. In response, this study pioneers computational approach that integrates ecological social dimensions to estimate factor. Employing satellite remote sensing advanced deep learning...
Aging population is considered to be major problem in modern healthcare. At the same time, fall incidents often occur among elderly and cause serious injuries affecting their independent living. This paper proposes a framework which uses mobile phone technology together with physiological data monitoring order detect falls. The system carries out collecting, storing processing of acceleration further alarm generating transferring all measurements remote caregiver. To perform evaluation, an...