Category: 7. Maths

System framework

In this paper, we propose a comprehensive framework for comparing deep learning models in predictive maintenance (PdM) applications for industrial manufacturing systems using sensor data. The proposed framework consists of several…

Experiments are conducted on the Sichuan radar echo dataset and the HKO-7³⁸ dataset. For both datasets, the first 10 frames are used as the input to the model, and the subsequent 10 frames are used as the expected output for training and…

In this section we outline our proposed approach to create a permutation matrix from a non-unitary sparse binary matrix. The class of matrices we consider are sparse binary matrices that have at most one nonzero entry in a row. Our method is…

This dataset⁵ can be found in the open science framework (https://doi.org/10.17605/OSF.IO/24Y6G). The DOI is DOI 10.17605/OSF.IO/24Y6G, and assign the license CC-By Attribution 4.0 International. It includes hard disk data processed by a large…

In this study, we propose a highway traffic flow analysis model that integrates modules for vehicle detection, tracking, and re-identification, enabling vehicle counting and interval speed measurement tasks. As illustrated in Fig. 1, the model…

To demonstrate the effectiveness of our GCN-based link prediction method, we have selected literature data from the Web of Science to conduct experiments, as described in Data acquisition. We conduct experiments to answer the following questions:

Method overview

We illustrate the main FedGA processes in Algorithms 1 and 2. The central server initializes a neural network model as the global model, sets the maximum number of global epochs T, and initializes the current epoch number \(t=0\)….