Chen Lv

May 16, 2024 | arxiv.org | Chen Lv

[Submitted on 16 May 2024] Title:Incorporating ESO into Deep Koopman Operator Modelling for Control of Autonomous Vehicles View a PDF of the paper titled Incorporating ESO into Deep Koopman Operator Modelling for Control of Autonomous Vehicles, by Hao Chen and 1 other authors View PDF Abstract:Koopman operator theory is a kind of data-driven modelling approach that accurately captures the nonlinearities of mechatronic systems such as vehicles against physics-based methods.

Jan 10, 2024 | mdpi.com | Ziyang Zhang |Chen Lv

All articles published by MDPI are made immediately available worldwide under an open access license. No specialpermission is required to reuse all or part of the article published by MDPI, including figures and tables. Forarticles published under an open access Creative Common CC BY license, any part of the article may be reused withoutpermission provided that the original article is clearly cited. For more information, please refer tohttps://www.mdpi.com/openaccess.

Oct 17, 2023 | mdpi.com | Zongshuai Li |Yali Liu |Tian Yi Ma |Chen Lv

1. IntroductionThe non-steroidal estrogenic fungal toxin zearalenone (ZEN), also known as F-2 toxin, is mainly produced by Fusarium species such as F. graminearum [1,2]. It was first isolated from moldy corn contaminated with F. graminearum and is one of nature’s most common fungal toxins [3]. ZEN (C18H22O5) has an estrogen-like structure; therefore, it has reproductive toxicity and primarily harms female animals [4,5].

Sep 3, 2023 | researchgate.net | Min Xiao |Chen Lv |Xiaomin Liu

Context 1... investigate the impacts of the Feature Pyramid Network (FPN) module on the performance of light field depth estimation, an experiment was conducted in which the FPN module was removed from the original model and retrained. The results, as presented in Table 4, demonstrate that the FPattNet model achieved a decrease of 0.521 in average Mean Squared Error (MSE) and a decrease of 3.881 in BadPix values.

Sep 3, 2023 | researchgate.net | Min Xiao |Chen Lv |Xiaomin Liu

Context 1... methods encompassed four traditional approaches [14,24,46,47] and eight deep learning methods [16,33,34,36,48,49]. The results of the BadPix 0.01, BadPix 0.03, BadPix 0.07 and MSE × 100 metrics obtained by these methods across eight scenes from the validation set are presented in Table 2. As can be seen from Table 2, our method achieves 11 best and 14 s-best results in 32 columns. ... Context 2...