In this section. We introduce our proposed multi-scale spatio-temporal domain-invariant (MSDI) representation learning method, as shown in Fig. 1a. We first use MSDI to enhance the original signal representation to alleviate the influence of the…
Category: 7. Maths
-

Fall recognition using a three stream spatio temporal GCN model with adaptive feature aggregation
We conducted a series of experiments using four benchmark datasets aiming to validate the proposed system, and have proved in this way the superiority and effectiveness of the proposed system. We will begin by outlining the training configuration…
Continue Reading
-

Tackling copyright issues in AI image generation through originality estimation and genericization
We first evaluate our originality estimation and genericization methods as-is, without integrating them into PREGen. Although this standalone approach is not practical for actual implementation, this experiment serves as a proof of concept to…
Continue Reading
-

CTA image segmentation method for intracranial aneurysms based on MGLIA net
MGLIA-Net model
Based on the research of Ronneberger et al.17, organ and lesion region segmentation is one of the important contents in medical image analysis. Traditional methods usually require the establishment of a separate segmentation model…
Continue Reading
-

‘Open source’ AI isn’t truly open — here’s how researchers can reclaim the term
Some 50 years ago this month, the Homebrew Computer Club — a do-it-yourself group of computer enthusiasts and hobbyists — began meeting in Menlo Park, California, fostering a culture of collaboration, knowledge exchange and the open sharing…
Continue Reading
-

Towards transparency and knowledge exchange in AI-assisted data analysis code generation
Generative artificial intelligence (AI) and large language models (LLMs) in particular are changing the way we do data science. Most prominently, scientists use the technology for interacting with scientific data1, answering data analysis…
Continue Reading
-

Multi-strategy enterprise development optimizer for numerical optimization and constrained problems
In this section, we perform numerical experiments on MSEDO, EDO, and selected comparison algorithms using 41 functions from the CEC2017 test suite and the CEC2022 test suite, as well as 10 engineering constrained optimization problems. The…
Continue Reading
-

A parrot optimizer for solving multiobjective design sensor placement in helicopter main rotor blade
Zhang, L., Fu, G., Cheng, F., Qiu, J. & Su, Y. A multi-objective evolutionary approach for mining frequent and high utility itemsets. Appl. Soft Comput. 62, 974–986 (2018).
Google Scholar
Continue Reading
-

Physics-informed neural networks with hybrid Kolmogorov-Arnold network and augmented Lagrangian function for solving partial differential equations
In this section, we introduce the comprehensive architecture and computational methods of the proposed model with the aim of enhancing the interpretability and accuracy of PINNs. Meanwhile, to address the impact of the penalty factor of the…
Continue Reading
-

Predicting badminton outcomes through machine learning and technical action frequencies
Identification of critical technical movements contributing to success in competitions
In this study, we collected data from international badminton competitions from 2019 to 2023, aiming to statistically analyze the frequency of each technical…
Continue Reading
