50 datasets

figshare + Loughborough Research Repository + GRANTS Data + UP Research Data Repository2026 · Astronomical catalogue

<p dir="ltr">human data and trained CNN models </p>

ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset · unknown

Antimicrobial resistance (AMR) is becoming an increasing burden on society. AMR phenotype is usually defined using laboratory-based techniques. However, laboratory-based assays can be time-consuming. Using computational techniques, we might be able to better identify the relationship between AMR phenotype and the whole genome. AMR gene identification tools are efficient at predicting the AMR genot

ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset · unknown

This dissertation focusses on modelling the data-dependent dynamic timing behaviour of modern, complex designs, in an effort to assist in evaluating the impact of timing errors early in the design cycle or navigate the selection of more optimistic operating conditions. This thesis investigates in-depth the factors that contribute to timing error manifestation in pipelined architectures and discuss

ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset

<p dir="ltr">In the MLP schematic (left), nonlinear transformations are illustrated at the nodes using a fixed activation function. ReLU is used only as an illustrative example in the visualization. In contrast, a KAN (right) places learnable nonlinear functions on the network edges, allowing each connection to adapt its transformation.</p>

ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset

<p dir="ltr">The top panel shows the mean global error obtained in each trial, with the solid line indicating the best objective value achieved up to each trial. The lower panels show the corresponding error as a function of the number of hidden layers L, neurons per layer N, grid size G, polynomial order p, and learning rate $\alpha$. The color of each marker indicates the trial number, illustrat

ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset

<p dir="ltr">Here, L denotes the number of hidden layers, N the number of neurons per layer, G the KAN grid size, p the KAN spline order, σ the activation function, and α the learning rate.</p>

ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset

With the growing demands for efficient and scalable food analysis, agriculture, and healthcare applications, the need for improved data acquisition and processing techniques has become increasingly significant. Near Infrared Spectroscopy has emerged as a powerful tool for non-invasive analysis in these domains, providing key insights into material composition at a spectral level. Hyperspectral ima

ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset

<p dir="ltr">The predicted fields and absolute errors for u and k are shown together with the MAE values measured inside, outside, and across the complete evaluation domain. The gray rectangle marks the training region [−5, 5] × [−5, 5] within the evaluation domain [−10, 10] × [−10, 10]. Gray circles indicate the observational points, which are sampled from the same distribution as the PDE colloca

ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset

<p dir="ltr">Here, L denotes the number of hidden layers, N the number of neurons per layer, σ the activation function, and α the learning rate.</p>

ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset

<p dir="ltr">(Top) Schematic workflow illustrating the formulation process, progressing from target definition and domain specification (infinite and semi-infinite) to the generation of a manufactured solution satisfying the Poisson equation −∇ · (k ∇u) = f. (Bottom) Analytical solutions u and spatially varying coefficient fields k. The infinite-domain configuration (left) uses parameters α = 0.5,

ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset · unknown

With “The 2030 Agenda for Sustainable Development” aiming to minimise road traffic accidents by halve, due to 1.3 million people dying every year in road accidents, the need for improvement in vehicle crashworthiness is required. One feasible way to improve crashworthiness is by designing mechanical meta-material structures for the design of car bumpers. However, conducting finite element analysis

ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset

<p dir="ltr">Uniform and exponential sampling are evaluated through the predicted fields, absolute errors, and MAE values measured inside, outside, and across the complete evaluation domain. The training region is [−5, 5] × [−5, 0] within the evaluation domain [−10, 10] × [−10, 0], with the top-boundary samples highlighted in blue.</p>

ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset

<p dir="ltr">Columns correspond to fixed weights, a prescribed λ_PDE schedule, and the same schedule combined with adaptive weighting. Rows show the evolution of the loss weights, individual loss components (L_u, L_k, and L_PDE), and relative L₂ errors for u and k, respectively.</p>

ZivaHub + Deakin Research Online + DMU Figshare + UCL Research Data Repository2026 · dataset · unknown

Computing systems deployed in hospital environments routinely collect a large volume of data that has not, thus far, been widely examined. There has been increasing research into the application of machine learning techniques on these data streams to predict and prevent disease states, however limitations exist around understanding the optimal methods and availability of data to train such models

ZivaHub + Deakin Research Online + DMU Figshare2026 · dataset

<p dir="ltr">This artwork visualises my doctoral research exploring how Artificial Intelligence can transform complex autism data into meaningful understanding of people’s experiences and quality of life. The four faces represent the diversity of people and experiences across the autism spectrum, while the interconnected puzzle pieces forming the brain represent complexity and individuality. Vibra

ZivaHub + Deakin Research Online + DMU Figshare + HKU DataHub + Swinburne Figshare + DaYta Ya Rona + SUNScholarData + figshare + Loughborough Research Repository + GRANTS Data + UP Research Data Repository2026 · Astronomical catalogue

<p dir="ltr">This dataset contains 3D in-air hand signatures collected using the Leap Motion Controller 2. It includes annotated CSV files for 65 users, with 10 signature instances per user (total 650 instances). The data captures finger, palm, and arm positions, velocities, rotations, etc. making it suitable for Intermittent Spatial Segmentation research. It can be extended for In-Air Signature v

HKU DataHub + figshare + Loughborough Research Repository + UP Research Data Repository2026 · Astronomical catalogue

<p>Accurate reconstruction of three-dimensional ocean current fields is critical for understanding ocean dynamics and real-time conduct of modern oceanographic field campaigns, particularly for mesoscale eddy surveys. We propose a physics-guided modeling and learning framework for multi-source data fusion to estimate the three-dimensional (3D) current structure of oceanic eddies by integrating sat

ZivaHub2026 · dataset

<p dir="ltr">Este documento é o Capítulo 3 do Toolkit do Gerente de Projetos para Gestão da Qualidade dos Dados em Projetos de Inteligência Artificial, desenvolvido pela Tribo "Dados em Projetos de IA" do Núcleo IA & GP. Ele apresenta uma Matriz RACI que define quem executa, aprova, é consultado e é informado em cada atividade de dados, ao longo das sete fases do ciclo de vida da IA, da iniciação

figshare + Loughborough Research Repository2026 · Astronomical catalogue

Supplemental Material Text

figshare2026 · Astronomical catalogue

<p>RMSE comparison across different traffic scenarios.</p>

figshare2026 · Astronomical catalogue

<p>Performance over a 5s prediction horizon for different attention mechanisms.</p>

figshare2026 · Astronomical catalogue

<p>Comparison of RMSE(meters) among various attention-based models using HighD dataset.</p>

figshare2026 · Astronomical catalogue

<div><p>Vehicle trajectory prediction (VTP) is the primary part of the perception-planning-control pipeline in autonomous driving. The inter-vehicle interactions strongly shape the trajectory of vehicles in complex traffic scenarios. Neural networks that use recurrent or convolutional architectures often exhibit performance degradation in longer prediction horizons. Many existing approaches confin

figshare2026 · Astronomical catalogue

<p>RMSE across 5s prediction horizon for varying numbers of attention heads in scaled dot-product attention on the highD dataset.</p>

figshare2026 · Astronomical catalogue

<p>Statistical validation of the proposed NL-MHA-LSTM model.</p>