Sökresultat

Context: AI technologies are increasingly embedded in products and software engineering processes of industrial IoT, autonomous systems, and cyber-physical systems. It is therefore essential to ensure alignment with safety, reliability, and ethical standards. However, practical software engineering methods for managing misalignment risks remain underdeveloped. Objective: This study aims to explore

We address the challenges in estimating 3D human poses from multiple views under occlusion and with limited overlapping views. We approach multi-view, single-person 3D human pose reconstruction as a regression problem and propose a novel encoder-decoder Transformer architecture to estimate 3D poses from multi-view 2D pose sequences. The encoder refines 2D skeleton joints detected across different

ObjectiveDevelopment of an AI tool to assess velopharyngeal competence (VPC) in children with cleft palate, with/without cleft lip.DesignInnovation of an AI tool using retrospective audio recordings and assessments of VPC.SettingTwo datasets were used. The first, named the SR dataset, included data from follow-up visits to Skåne University Hospital, Sweden. The second, named the SC + IC dataset, w

At the emergency department (ED), it is important to quickly and accurately determine which patients are likely to have a major adverse cardiac event (MACE). Machine learning (ML) models can be used to aid physicians in detecting MACE, and improving the performance of such models is an active area of research. In this study, we sought to determine if ML models can be improved by including a prior

Vowel-based voice analysis is gaining attention as a potential non-invasive tool for COPD classification, offering insights into phonatory function. The growing need for voice data has necessitated the adoption of various techniques, including segmentation, to augment existing datasets for training comprehensive Machine Learning (ML) modelsThis study aims to investigate the possible effects of seg

Time-frequency (TF) postprocessing methods are often used to form concentrated TF representations (TFRs) for nonstationary signals. Regrettably, most such techniques are sensitive to noise and tend to underestimate weak components when dealing with transient signals, resulting in sidelobes and low-resolution TFRs. In this work, we introduce a generalized group delay (GD) weighted sparse TF (GWSTF)

Unpigmented skin cancer is the most prevalent form of cancer, and it burdens healthcare substantially even if it is not as aggressive as the more well-known malignant melanoma. Dermatoscopy images are commonly used for diagnosis, but differentiating between the many sub-diagnoses is a hard task. In this study we focus on these unpigmented cancers, performing both detection of basal cell carcinoma

Background: Chronic obstructive pulmonary disease (COPD) is a severe condition affecting millions worldwide, leading to numerous annual deaths. The absence of significant symptoms in its early stages promotes high underdiagnosis rates for the affected people. Besides pulmonary function failure, another harmful problem of COPD is the systemic effects, e.g., heart failure or voice distortion. Howeve

This article addresses the detection and estimation problems of a distributed multiple-input and multiple-output (MIMO) radar system with synchronization errors. In such cases, the outputs of all waveform-specific matched filters contain errors in the resulting time delay estimates, which will cause biases in the corresponding estimation of the active range cells. To overcome the impact resulting

Frequency diverse array (FDA) radars provide a potential solution to target localisation along the slant range and azimuth angle due to the range-angle-dependent transmit beampattern caused by the used frequency increments. However, the S -shaped beampattern resulting from the standard FDA leads to multiple candidate location estimates, introducing ambiguity in the target localization. To make ful

Abstract: Birds have evolved morphological, physiological and behavioural adaptations, encoded in their migratory programs, to enable successful migration. Sometimes, even closely related species, such as the Eurasian reed warbler and the sedge warbler, may adopt different migration strategies to reach their wintering grounds in sub-Saharan Africa. To study them in detail, we aimed to compare the

In this work, we consider the problem of estimating the directions of arrival of far-field sources impinging on a sensor array using a computationally efficient approach. A novel adaptive grid selection technique is employed to reduce the dimensionality of the used dictionary matrix. The method further makes use of a SPICE-inspired dictionary to adaptively select an appropriate regularization para

Aims: In the present study, we aimed to evaluate the performance of machine learning (ML) models for identification of acute myocardial infarction (AMI) or death within 30 days among emergency department (ED) chest pain patients. Methods and results: Using data from 9519 consecutive ED chest pain patients, we created ML models based on logistic regression or artificial neural networks. Model input

Recent advances have shown that sound fields can be accurately interpolated between microphone measurements when the spatial covariance matrix is known. This matrix may be estimated in various ways; one promising approach is to use a plane wave formulation with sparse priors, although this may require the use of a many microphones to suppress the noise. To overcome this, we introduce a time domain

The polar format algorithm (PFA) is a popular choice for general bistatic synthetic aperture radar (BiSAR) imaging due to its computational efficiency and adaptability to situations with complicated geometries or arbitrary flight trajectories. However, efficient and accurate compensation of 2-D residual phase errors induced by the wavefront curvature remains challenging when obtaining high-quality

The distinguishing feature of frequency diverse array (FDA) systems as compared to conventional phased-array and multiple-input multiple-output (MIMO) radar systems is the use of a small frequency offset (FO) across the array elements. Much of the development to date has focused on the FDA-MIMO structure, using an FO that is larger than the bandwidth of the baseband signal, thereby reducing the re

This paper examines the short-range propagation characteristics of sound wave propagation in an ice covered lake experiment. The studied measurements were made in February 2024 in the shallow Song-Hua lake in northern China. The experiment illustrates how the wave propagation notably varies as a function of depth and due to changes in the water temperature, but also how the ice cover influences th

This work is concerned with determining optimal sensor placements that allow for an accurate location estimate of structured signal sources, taking into account the expected location areas and the typical range of the parameters detailing the signals. In the presentation, we illustrate the technique for tonal sound signals, exploiting the expected harmonic structure of such signals. To determine p

Current literature show that frequency diverse arrays (FDAs) are able of producing range–angle-dependent and time-variant transmit beampatterns, but the resulting time and range dependencies and their characteristics are still not well understood. This paper examines the FDA transmission model with an emphasis on analyzing the beam auto-scanning characteristics and the equivalence with the MIMO be

This work investigates the design of beampatterns for frequency diverse arrays-multiple-input multiple-output (FDA-MIMO) in the range-angle plane, in order to improve the approximation of a desired beampattern. Recognizing that the energy radiated by the array cannot be locked at a fixed range and angle, the beampattern is designed for the equivalent beampattern at the receiving end, differing fro