Explore the vast range of titles available.

Mapping and monitoring coral reef benthic composition using remotely sensed imagery provides a large-scale inference of spatial and temporal dynamics. These maps have become essential components in marine science and management, with their utility being dependent upon accuracy, scale, and repeatability. One of the primary factors that affects the utility of a coral reef benthic composition map is the choice of the machine-learning algorithm used to classify the coral reef benthic classes. Current machine-learning algorithms used to map coral reef benthic composition and detect changes over time achieve moderate to high overall accuracies yet have not demonstrated spatio-temporal generalisation. The inability to generalise limits their scalability to only those reefs where in situ reference data samples are present. This limitation is becoming more pronounced given the rapid increase in the availability of high temporal (daily) and high spatial resolution (<5 m) multispectral satellite imagery. Therefore, there is presently a need to identify algorithms capable of spatio-temporal generalisation in order to increase the scalability of coral reef benthic composition mapping and change detection. This review focuses on the most commonly used machine-learning algorithms applied to map coral reef benthic composition and detect benthic changes over time using multispectral satellite imagery. The review then introduces convolutional neural networks that have recently demonstrated an ability to spatially and temporally generalise in relation to coral reef benthic mapping; and recurrent neural networks that have demonstrated spatio-temporal generalisation in the field of land cover change detection. A clear conclusion of this review is that existing convolutional neural network and recurrent neural network frameworks hold the most potential in relation to increasing the spatio-temporal scalability of coral reef benthic composition mapping and change detection due to their ability to spatially and temporally generalise.

With the continuous development of new sensor features and tracking algorithms for object tracking, researchers have opportunities to experiment using different combinations. However, there is no standard or agreed method for selecting an appropriate architecture for autonomous vehicle (AV) crash reconstruction using multi-sensor-based sensor fusion. This study proposes a novel simulation method for tracking performance evaluation (SMTPE) to solve this problem. The SMTPE helps select the best tracking architecture for AV crash reconstruction. This study reveals that a radar-camera-based centralized tracking architecture of multi-sensor fusion performed the best among three different architectures tested with varying sensor setups, sampling rates, and vehicle crash scenarios. We provide a brief guideline for the best practices in selecting appropriate sensor fusion and tracking architecture arrangements, which can be helpful for future vehicle crash reconstruction and other AV improvement research.

Digital biomarkers are increasingly used in clinical decision support for various health conditions. Speech features as digital biomarkers can offer insights into underlying physiological processes due to the complexity of speech production. This process involves respiration, phonation, articulation, and resonance, all of which rely on specific motor systems for the preparation and execution of speech. Deficits in any of these systems can cause changes in speech signal patterns. Increasing efforts are being made to develop speech-based clinical decision support systems. This systematic scoping review investigated the technological revolution and recent digital clinical speech signal analysis trends to understand the key concepts and research processes from clinical and technical perspectives. A systematic scoping review was undertaken in 6 databases guided by a set of research questions. Articles that focused on speech signal analysis for clinical decision-making were identified, and the included studies were analyzed quantitatively. A narrower scope of studies investigating neurological diseases were analyzed using qualitative content analysis. A total of 389 articles met the initial eligibility criteria, of which 72 (18.5%) that focused on neurological diseases were included in the qualitative analysis. In the included studies, Parkinson disease, Alzheimer disease, and cognitive disorders were the most frequently investigated conditions. The literature explored the potential of speech feature analysis in diagnosis, differentiating between, assessing the severity and monitoring the treatment of neurological conditions. The common speech tasks used were sustained phonations, diadochokinetic tasks, reading tasks, activity-based tasks, picture descriptions, and prompted speech tasks. From these tasks, conventional speech features (such as fundamental frequency, jitter, and shimmer), advanced digital signal processing-based speech features (such as wavelet transformation-based features), and spectrograms in the form of audio images were analyzed. Traditional machine learning and deep learning approaches were used to build predictive models, whereas statistical analysis assessed variable relationships and reliability of speech features. Model evaluations primarily focused on analytical validations. A significant research gap was identified: the need for a structured research process to guide studies toward potential technological intervention in clinical settings. To address this, a research framework was proposed that adapts a design science research methodology to guide research studies systematically. The findings highlight how data science techniques can enhance speech signal analysis to support clinical decision-making. By combining knowledge from clinical practice, speech science, and data science within a structured research framework, future research may achieve greater clinical relevance.

Improvement in passive function (i.e., ease of caring for a limb) is a common goal for treatment of spasticity in the arm with botulinum toxin. A large international, observational, 2-year longitudinal study (ULIS-III, N = 953) was conducted in real-life practice. This original secondary analysis examines whether improvement in passive function goals were met over repeated injection cycles. We report changes by cycle measured by the Passive Function sub-scale of the Arm Activity measure (ArmA-PF) and examine predictors of improvement and injection occurrence. Inclusion in this analysis was based on passive function being selected as a primary or secondary goal for one or more cycle of treatment (n = 542/953). Goals were assessed at the start and end of each cycle using the Goal Attainment Test score and the ArmA-PF. Over all cycles of treatment, goals were set for 1641/2187 injections (75.0%) and achieved in 1250 (76.2%). Significant improvements in ArmA-PF score were identified for at least six cycles (p < 0.001) with evidence of cumulative benefit over successive cycles. This occurred regardless of patient-related baseline characteristics, with the possible exception of some relationship with injection localization techniques. In conclusion, repeated botulinum toxin injections provide significant improvement in passive function, which was sustained over repeated cycles of treatment.

Musical instrument recognition is a relatively unexplored area of machine learning due to the need to analyze complex spatial–temporal audio features. Traditional methods using individual spectrograms, like STFT, Log-Mel, and MFCC, often miss the full range of features. Here, we propose a hierarchical residual attention network using a scaled combination of multiple spectrograms, including STFT, Log-Mel, MFCC, and CST features (Chroma, Spectral contrast, and Tonnetz), to create a comprehensive sound representation. This model enhances the focus on relevant spectrogram parts through attention mechanisms. Experimental results with the OpenMIC-2018 dataset show significant improvement in classification accuracy, especially with the “Magnified 1/4 Size” configuration. Future work will optimize CST feature scaling, explore advanced attention mechanisms, and apply the model to other audio tasks to assess its generalizability.

Accelerating text input in augmentative and alternative communication (AAC) is a long-standing area of research with bearings on the quality of life in individuals with profound motor impairments. Recent advances in large language models (LLMs) pose opportunities for re-thinking strategies for enhanced text entry in AAC. In this paper, we present SpeakFaster, consisting of an LLM-powered user interface for text entry in a highly-abbreviated form, saving 57% more motor actions than traditional predictive keyboards in offline simulation. A pilot study on a mobile device with 19 non-AAC participants demonstrated motor savings in line with simulation and relatively small changes in typing speed. Lab and field testing on two eye-gaze AAC users with amyotrophic lateral sclerosis demonstrated text-entry rates 29–60% above baselines, due to significant saving of expensive keystrokes based on LLM predictions. These findings form a foundation for further exploration of LLM-assisted text entry in AAC and other user interfaces. Individuals with severe motor impairments use gaze to type and communicate. This paper presents a large language model-based user interface that enables gaze typing in highly abbreviated forms, achieving significant motor saving and speed gain.

In the field of 2-D image processing and computer vision, accurately detecting and segmenting objects in scenarios where they overlap or are obscured remains a challenge. This difficulty is worse in the analysis of shoeprints used in forensic investigations because they are embedded in noisy environments such as the ground and can be indistinct. Traditional convolutional neural networks (CNNs), despite their success in various image analysis tasks, struggle with accurately delineating overlapping objects due to the complexity of segmenting intertwined textures and boundaries against a background of noise. This study introduces and employs the YOLO (You Only Look Once) model enhanced by edge detection and image segmentation techniques to improve the detection of overlapping shoeprints. By focusing on the critical boundary information between shoeprint textures and the ground, our method demonstrates improvements in sensitivity and precision, achieving confidence levels above 85% for minimally overlapped images and maintaining above 70% for extensively overlapped instances. Heatmaps of convolution layers were generated to show how the network converges towards successful detection using these enhancements. This research may provide a potential methodology for addressing the broader challenge of detecting multiple overlapping objects against noisy backgrounds.

Pain reduction is a common goal of the treatment of upper limb spasticity with botulinum toxin (BoNT-A). ULIS-III was a large international, observational, longitudinal study (N = 953) conducted in real-life clinical practice over two years. In this secondary post hoc analysis, we examine whether goals for pain reduction were met over repeated injection cycles. We report serial changes in pain severity and explore predictors of pain reduction and injection frequency. Patients were selected if pain reduction was a primary/secondary goal for at least one cycle (n = 438/953). They were assessed at the start and end of each cycle using the goal attainment T-score alongside a self-report of pain severity (range 0–10). Across all cycles, pain-related goals were set for 1189/1838 injections (64.7%) and were achieved in 839 (70.6%). Patients continued to show a significant reduction in pain (p < 0.001) for each injection up to seven cycles, with some cumulative benefit (p < 0.001). Those requiring more frequent injections tended to have higher starting pain scores and a smaller reduction in pain score, but these differences were not significant when other covariates (age, previous injection history, time since onset, severity and distribution of spasticity) were taken into account (p > 0.713). Conclusion: Repeated BoNT-A administration continued to result in a significant reduction in upper limb spasticity-related pain, regardless of patient-related factors.

Background Prolonged Disorders of Consciousness (PDOC) resulting from severe acquired brain injury can lead to complex disabilities that make diagnosis challenging. The role of machine learning (ML) in diagnosing PDOC states and identifying intervention strategies is relatively under-explored, having focused on predicting mortality and poor outcome. This study aims to: (a) apply ML techniques to predict PDOC diagnostic states from variables obtained from two non-invasive neurobehavior assessment tools; and (b) apply network analysis for guiding possible intervention strategies. Methods The Coma Recovery Scale-Revised (CRS-R) is a well-established tool for assessing patients with PDOC. More recently, music has been found to be a useful medium for assessment of coma patients, leading to the standardization of a music-based assessment of awareness: Music Therapy Assessment Tool for Awareness in Disorders of Consciousness (MATADOC). CRS-R and MATADOC data were collected from 74 PDOC patients aged 16–70 years at three specialist centers in the USA, UK and Ireland. The data were analyzed by three ML techniques (neural networks, decision trees and cluster analysis) as well as modelled through system-level network analysis. Results PDOC diagnostic state can be predicted to a relatively high level of accuracy that sets a benchmark for future ML analysis using neurobehavioral data only. The outcomes of this study may also have implications for understanding the role of music therapy in interdisciplinary rehabilitation to help patients move from one coma state to another. Conclusions This study has shown how ML can derive rules for diagnosis of PDOC with data from two neurobehavioral tools without the need to harvest large clinical and imaging datasets. Network analysis using the measures obtained from these two non-invasive tools provides novel, system-level ways of interpreting possible transitions between PDOC states, leading to possible use in novel, next-generation decision-support systems for PDOC.

Background Representation of specialist international medical graduates (SIMGs) in specific specialties such as surgery can be expected to grow as doctor shortages are predicted in the context of additional care provision for aging populations and limited local supply. Many national medical boards and colleges provide pathways for medical registration and fellowship of SIMGs that may include examinations and short-term training. There is currently very little understanding of how SIMGs are perceived by colleagues and whether their performance is perceived to be comparable to locally trained medical specialists. It is also not known how SIMGs perceive their own capabilities in comparison to local specialists. The aim of this study is to explore the relationships between colleague feedback and self-evaluation in the specialist area of surgery to identify possible methods for enhancing registration and follow-up training within the jurisdiction of Australia and New Zealand. Methods Feedback from 1728 colleagues to 96 SIMG surgeons and 406 colleagues to 25 locally trained Fellow surgeons was collected, resulting in 2134 responses to 121 surgeons in total. Additionally, 98 SIMGs and 25 Fellows provided self-evaluation scores (123 in total). Questionnaire and data reliability were calculated before analysis of variance, principal component analysis and network analysis were performed to identify differences between colleague evaluations and self-evaluations by surgeon type. Results Colleagues rated SIMGs and Fellows in the ‘very good’ to ‘excellent’ range. Fellows received a small but statistically significant higher average score than SIMGs, especially in areas dealing with medical skills and expertise. However, SIMGs received higher scores where there was motivation to demonstrate working well with colleagues. Colleagues rated SIMGs using one dimension and Fellows using three, which can be identified as clinical management skills, inter-personal communication skills and self-management skills. On self-evaluation, both SIMGs and Fellows gave themselves a significant lower average score than their colleagues, with SIMGs giving themselves a statistically significant higher score than Fellows. Conclusions Colleagues rate SIMGs and Fellows highly. The results of this study indicate that SIMGs tend to self-assess more highly, but according to colleagues do not display the same level of differentiation between clinical management, inter-personal and self-management skills. Further research is required to confirm these provisional findings and possible reasons for lack of differentiation if this exists. Depending on the outcome, possible support mechanisms can be explored that may lead to increased comparable performance with locally trained graduates of Australia and New Zealand in these three dimensions.