A5063208469- Multiple Sclerosis Research Studies
- Cerebral Palsy and Movement Disorders
- Balance, Gait, and Falls Prevention
- Autoimmune and Inflammatory Disorders Research
- Advanced Neural Network Applications
- Renal and Vascular Pathologies
- MRI in cancer diagnosis
- Pediatric Urology and Nephrology Studies
- Autonomous Vehicle Technology and Safety
- Social and Educational Sciences
- Domain Adaptation and Few-Shot Learning
- Remote Sensing and LiDAR Applications
- Robotics and Sensor-Based Localization
- Structural Health Monitoring Techniques
- Generative Adversarial Networks and Image Synthesis
- Digital Media Forensic Detection
- Cognitive Abilities and Testing
- Masonry and Concrete Structural Analysis
- High-Velocity Impact and Material Behavior
- Software Reliability and Analysis Research
- Innovation and Knowledge Management
- Mind wandering and attention
- Advanced Image Processing Techniques
- Vehicle Dynamics and Control Systems
- Knowledge Management and Sharing
Karolinska Institutet
2013-2025
Karolinska University Hospital
2024-2025
Volvo (United States)
2018-2021
Antaros Medical (Sweden)
2020
Semcon (Sweden)
2012
Volvo (Sweden)
2010
Automotive active safety systems can significantly benefit from real-time road friction estimates (RFE) by adapting driving styles, specific to the conditions. This work presents a 2-stage approach for indirect RFE estimation using front-view camera images captured vehicles. In stage-1, convolutional neural network model architectures are implemented learn region-specific features surface condition (RSC) classification. Texture-based drivable surface, sky and surroundings found be separate...
LiDAR-based 3D object detection plays a crucial role in modern autonomous driving systems. LiDAR data often exhibit severe changes properties across different observation ranges. In this paper, we explore cross-range adaptation for using LiDAR, i.e., far-range observations are adapted to near-range. This way, is optimized similar performance near-range one. We adopt bird-eyes view (BEV) framework perform the proposed model adaptation. Our consists of an adversarial global adaptation, and...
Abstract The UK Biobank is collecting extensive data on health-related characteristics of over half a million volunteers. biological samples blood and urine can provide valuable insight kidney function, with important links to cardiovascular metabolic health. Further information anatomy could be obtained by medical imaging. In contrast the brain, heart, liver, pancreas, no dedicated Magnetic Resonance Imaging (MRI) planned for kidneys. An image-based assessment nonetheless feasible in...
Abstract Objective The mini-Balance Evaluation Systems Test (BESTest) is a balance measure for assessment of the underlying physiological systems control in adults. Evaluations test–retest reliability mini-BESTest larger samples people with multiple sclerosis (MS) are lacking. purpose this study was to investigate total and section sum scores individual items mild moderate overall MS disability. Methods This used design movement laboratory setting. Fifty-four disability according Expanded...
In this paper, we introduce Cirrus, a new long-range bi-pattern LiDAR public dataset for autonomous driving tasks such as 3D object detection, critical to highway and timely decision making. Our platform is equipped with high-resolution video camera pair of sensors 250-meter effective range, which significantly longer than existing datasets. We record paired point clouds simultaneously using both Gaussian uniform scanning patterns. Point density varies across long different patterns further...
Reduced motor and cognitive dual-task capacity is found to be more common among people with multiple sclerosis (MS), than healthy populations. However, studies in larger samples of MS conducted using a stringent methodology, which includes comparisons controls, are needed. Thus, the primary aim this study was explore effects on dual-tasking mild moderate overall MS-disability, comparison controls. A second differences performance task between two tasks controls.This case-control evaluated...
According to ISO 26262, a recent automotive functional safety standard, verification tools shall undergo qualification, e.g. ensure that they do not fail detect faults can lead violation of requirements. We present semi-automatic qualification method involving monitor and fault injection reduce cost in the process. experiment on tool implemented LabVIEW.
Abstract Background Balance training interventions with a gradual progression of difficulty and highly challenging tasks designed specifically for people multiple sclerosis (MS) are rare. The objective was to adapt balance intervention originally developed Parkinson’s disease through co-design process then conduct pilot trial in MS evaluate the feasibility large, full-scale study. Methods Twelve mild moderate overall MS-disability were included this single-group trial. Participants received...
Abstract Objective We aimed to explore and describe the experiences of people with multiple sclerosis (MS) living impaired balance control how impairment can be managed in everyday life. Methods A qualitative design was used. Data were collected through semistructured interviews. Transcripts analyzed using inductive content analysis. Sixteen participants (12 women) MS variation level interviewed. Age ranged between 35 64 years, overall MS-disability 2.0 (mild) 5.5 (moderate) according...
In this paper, we introduce Cirrus, a new long-range bi-pattern LiDAR public dataset for autonomous driving tasks such as 3D object detection, critical to highway and timely decision making. Our platform is equipped with high-resolution video camera pair of sensors 250-meter effective range, which significantly longer than existing datasets. We record paired point clouds simultaneously using both Gaussian uniform scanning patterns. Point density varies across long different patterns further...
LiDAR-based 3D object detection plays a crucial role in modern autonomous driving systems. LiDAR data often exhibit severe changes properties across different observation ranges. In this paper, we explore cross-range adaptation for using LiDAR, i.e., far-range observations are adapted to near-range. This way, is optimized similar performance near-range one. We adopt bird-eyes view (BEV) framework perform the proposed model adaptation. Our consists of an adversarial global adaptation, and...