Pengpeng Jian¹, Fucheng Guo^1,*, Yanli Wang², Yang Li¹

CMES-Computer Modeling in Engineering & Sciences, Vol.136, No.2, pp. 1707-1728, 2023, DOI:10.32604/cmes.2023.023243 - 06 February 2023

Abstract This paper presents an end-to-end deep learning method to solve geometry problems via feature learning and contrastive learning of multimodal data. A key challenge in solving geometry problems using deep learning is to automatically adapt to the task of understanding single-modal and multimodal problems. Existing methods either focus on single-modal or multimodal problems, and they cannot fit each other. A general geometry problem solver should obviously be able to process various modal problems at the same time. In this paper, a shared feature-learning model of multimodal data is adopted to learn the unified feature representation More >

Haolong Chen^1,2, Bo Yu¹, Huanlin Zhou^1*, Zeng Meng¹

CMC-Computers, Materials & Continua, Vol.53, No.4, pp. 271-290, 2017, DOI:10.3970/cmc.2017.053.271

Abstract The cuckoo search algorithm (CS) is improved by using the conjugate gradient method(CGM), and the CS-CGM is proposed. The unknown inner boundary shapes are generated randomly and evolved by Lévy flights and elimination mechanism in the CS and CS-CGM. The CS, CGM and CS-CGM are examined for the prediction of a pipe’s inner surface. The direct problem is two-dimensional transient heat conduction in functionally graded materials (FGMs). Firstly, the radial integration boundary element method (RIBEM) is applied to solve the direct problem. Then the three methods are compared to identify the pipe’s inner surfacewith the… More >