Category: 7. Maths

Complex hierarchical microstructures with controlled mesoporosity

In this study, we demonstrate the versatility of our system by engineering hierarchical microstructures with precisely controlled mesoporosity. A flexible experimental methodology…

Models’ performance on the original and resampled datasets

In our study, we trained five ML and six Deep Learning (DL) algorithms including four graph-based models and two pre-trained transformer-based models namely: Random Forest (RF), Multi…

Transformer

Figure 1 presents the basic architecture of the Transformer. The Transformer is an Encoder–Decoder model based on Multi-Head Attention. The encoder generates the corresponding syntax vector of the input sequence, whereas the decoder…

Benchmark functions

In this study, 24 typical complex benchmark functions were selected to evaluate the global search ability of the improved algorithm. Functions F1–F4 and F6–F14 are from the CEC2005 benchmark set, functions F5, F17, F19, and…

The proposed network integrates two primary components: the RGB Image module and the BodyPose-Points Data module, both of which work together to capture comprehensive spatio-temporal features critical for detecting fistfight actions in video…

Problem statement

We are given a dataset \({\mathcal{D}}={\{({{\mathcal{G}}}^{(i)},{y}^{(i)})\}}_{i = 1}^{M}\) of labeled biological graphs. Each graph \({\mathcal{G}}=({\mathcal{V}},{\mathcal{E}})\) represents a gene regulatory network (GRN)…

The data analytic model is proposed to sense the clinical data from WS devices that acquire activities vital to humans. This observation takes place periodically, ensembles the clinical data, and detects the function that represents health…

The field of underwater imaging presents significant challenges due to factors such as limited visibility, color distortion, and light scattering within the aquatic environment. To address these issues, a novel framework is proposed that combines…

Model formulation

A deterministic compartmental model on the transmission dynamics of malaria is been proposed. We sub-divided the total human population \(N_{H} \left( t \right)\), into five (5) distinct classes of susceptible humans \(S_{H}\),…

Best practices and key considerations—narrative review

As a first step to inform the construct of FAIR-AI, we conducted a narrative review to identify the best practices and key considerations related to responsibly deploying AI in healthcare,…