The study procedure starts with the careful collection of data from the CICIDS2018 dataset, which is then preprocessed to make it appropriate for the classifiers. Addressing missing values and transforming categorical variables into numerical…
Category: 7. Maths
-

AI-assisted technology optimization in disability support systems using fuzzy rough MABAC decision-making
Assume that the set \({\mathcal{Q}}_{altr.} = \left\{ {{\mathcal{Q}}_{altr. – 1} , {\mathcal{Q}}_{altr. – 2} , \ldots , {\mathcal{Q}}_{{altr. – {\mathfrak{n}}}} } \right\}\) denote the family of alternatives and the set \({\mathcal{E}}_{atr.} =…
Continue Reading
-

Translation of computed tomography images to T2-Weighted magnetic resonance images of lumbar spine using generative adversarial networks on sagittal images
Dataset Preparation
From January 1, 2012, to December 31, 2023, a cohort of 3,314 patients aged 18 years or older who underwent both CT and MRI for back pain within one month was identified. We excluded 1,776 patients with significant lumbar spine…
Continue Reading
-

Multi-perspective dynamic consistency learning for semi-supervised medical image segmentation
Our designed multi-perspective dynamic consistency (MPDC) framework is shown in Fig. 2. The proposed architecture is composed of three parallel branches for multi-perspective collaborative learning. Specifically, we adopt two different…
Continue Reading
-

New care pathways for supporting transitional care from hospitals to home using AI and personalized digital assistance
The proposed research process is focused on the following hypotheses:
H1
The adoption and usage of an IoT, AI, and digital assistance-based solution for transitional care can reduce the patients’…
Continue Reading
-

Distributed denial-of-service (DDoS) on the smart grids based on VGG19 deep neural network and Harris Hawks optimization algorithm
Results
The suggested approach utilizing VGG19 DNN and HHOA achieved significant improvements.
In discovering DDoS attacks on smart grids. The accuracy of DDoS attacks detection was measured using various evaluation metrics, including precision,…
Continue Reading
-

Medical image segmentation model based on local enhancement driven global optimization
As shown in Fig. 1, the structure of LEGO-Net’s encoder primarily incorporates the Channel Feature Enhancement Module (CFEM). For the decoder, it employs a bilinear interpolation method to elevate the feature map’s resolution to match that of…
Continue Reading
-

A thermodynamic inspired AI based search algorithm for solving ordinary differential equations
As a new metaheuristic optimization algorithm38 TSA operates to solve complicated optimization problems that include Ordinary Differential Equations (ODEs). TSA receives its foundation from observing how particles react to thermodynamic systems…
Continue Reading
-

An advanced three stage lightweight model for underwater human detection
Model experience
Detection performance of the model
Underwater environments are complex and diverse, with varying light intensity and frequent interference from other marine life. Additionally, the scale of human targets varies, making model…
Continue Reading
-

Design optimization of university ideological and political education system based on deep learning
Deep learning algorithm and model design
The convolution layer in the convolutional neural network (CNN) can use several convolution kernels with different sizes to convolution data such as text vectors and capture local features with different…
Continue Reading
