Search

Your search keyword '"Huang, Mengxing"' showing total 630 results
Start Over Author "Huang, Mengxing"

Refine your results

more »

more »

more »

more »
630 results on '"Huang, Mengxing"'

208. Plant Taxonomy in Hainan Based on Deep Convolutional Neural Network and Transfer Learning

Author

Huang Mengxing, Jialun Lin, Wenlong Feng, Liu Wei, and Guilai Han

Subjects
Hyperparameter, 0303 health sciences, Artificial neural network, Contextual image classification, business.industry, Computer science, Feature extraction, Pattern recognition, 02 engineering and technology, Convolutional neural network, Plant identification, 03 medical and health sciences, Identification (information), 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Artificial intelligence, business, Transfer of learning, 030304 developmental biology
Abstract

Plant play a very important role in the protection of the ecological balance. Compared to manual identification of plants, automated plant identification enable experts to process significantly greater numbers of plants with higher efficiencies in shorter periods of time. In this study, we propose an effective deep Convolutional Neural Network (CNN)-based model that is capable of automatically identifying and classifying plant species in Hainan by studying the details of their leaves. We apply transfer learning based on CNN to fine-tune the pre-trained models. Further, the optimal values of associated hyperparameters that maximize the accuracy of the proposed method are determined. Finally, experiments are carried out on two available botanical datasets: the Flavia dataset with 32 classes and the HNPlant dataset with 10 classes. The results demonstrate that the highest classification accuracies exhibited by the proposed CNN-based model on the Flavia and HNPlant datasets are 89% and 95%, respectively, thus establishing their effectiveness.

Published
2020

210. Neural network-aided sparse convex optimization algorithm for fast DOA estimation.

Author

Cong, Jingyu, Wang, Xianpeng, Wan, Liangtian, and Huang, Mengxing

Subjects
DIRECTION of arrival estimation, MATHEMATICAL optimization, HERMITIAN structures, COMPUTATIONAL complexity, PROBLEM solving
Abstract

In this paper, a fast sparse convex optimization algorithm based on a neural network is proposed to improve the direction of arrival estimation. First, a fast L 1 -sparse representation of the array covariance vector model based on the Hermitian Toeplitz structure of array covariance is established to reduce computational complexity in data dimension and variable number. Then, the estimation error upper bound problem is investigated, and a neural network-aided coefficient selection method is developed. The direction of arrival estimation problem is solved through spectral peak search. Finally, the algorithm is extended to the case of off-grid error. The algorithm's advantages in accuracy, calculation speed and robustness is verified by the simulations. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

246. Joint 2D-DOD and 2D-DOA Estimation for Coprime EMVS–MIMO Radar.

Author

Wang, Xianpeng, Huang, Mengxing, and Wan, Liangtian

Subjects
*MIMO radar, *BISTATIC radar, *RADAR, *SINGULAR value decomposition
Abstract

The issue of two-dimensional (2D) direction-of-departure and direction-of-arrival estimation for bistatic multiple-input multiple-output (MIMO) radar with a coprime electromagnetic vector sensor (EMVS) is addressed in this paper, and a tensor-based subspace algorithm is proposed. Firstly, the covariance measurement of the received data is arranged into a fourth-order tensor, which can maintain the multi-dimensional characteristic of the received data. Then, the higher-order singular value decomposition is followed to get an accurate signal subspace. By utilizing the uniformity of the subarrays in coprime EMVS–MIMO radar, the rotation invariant technique is adopted to achieve ambiguous elevation angle estimation. Thereafter, the unambiguous elevation angles are recovered by exploring the coprime characteristic of the subarrays. Finally, all azimuth angles are achieved by using the vector cross-product strategy. The tensor nature inherited from the array measurement is fully explored, and the coprime geometry enables EMVS–MIMO radar to achieve larger array aperture than the existing uniform linear configuration; thus, the proposed method offers better estimation performance than current state-of-the-art algorithms. Several computer simulations validate the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

247. Spatial-temporal evolution mechanism and dynamic simulation of the urban resilience system of the Guangdong-Hong Kong-Macao Greater Bay Area in China.

Author

Wang, Huihui, Xue, Hanyu, He, Wanlin, Han, Qiuyuan, Xu, Tingting, Gao, Xiaoyong, Liu, Suru, Jiang, Ruifeng, and Huang, Mengxing

Subjects
URBANIZATION, DYNAMIC simulation, SUSTAINABLE urban development, CITIES & towns, INTERNATIONAL trade
Abstract

As the population and industries continue to gather in cities, such cities face acute shocks caused by various natural disasters and high pressure caused by human interference. The means of accurately assessing and improving the level of urban resilience (UR) to cope with disturbances and shocks, enhance regional resilience, and improve sustainable urban development has become a hot topic. In this study, we constructed an UR assessment framework using "social-economic-institutional-ecological-engineering" to explore the dynamic evolution of spatial and temporal patterns in the Guangdong-Hong Kong-Macao Greater Bay Area (GBA) of China, to reveal the main factors influencing the evolution of this spatial pattern and the strength and interaction mechanisms among such influencing factors and to dynamically simulate the spatial and temporal evolution characteristics in the next 16 years. The results show that from 2000 to 2019, the difference in UR level in the GBA is obvious. Hong Kong and Macao are obviously ahead of other cities, and the comprehensive resilience level of Guangzhou and Shenzhen cities in the mainland is developing rapidly. The difference in per capita consumption capacity, industrial structure optimization, foreign trade vitality, infrastructure support and other factors are the main causes of the spatial differentiation of UR in the GBA. In the future, the UR level of the GBA urban agglomeration will show an overall upwards trend. The three development poles of Guangzhou-Foshan, Shenzhen-Hong Kong, and Zhuhai-Macao have obvious advantages in spatial distribution. The results of the study can enrich regional UR research, and also provide theoretical references to facilitate the high-quality development of the area. [Display omitted] • We constructed a "social-economic-institutional-ecological-engineering" urban resilience assessment framework. • The paper developed an evaluation system for the urban resilience to reveal its spatial and temporal evolution patterns. • The main factors influencing the evolution of the spatial patterns of urban resilience is investigated. • Our results provide a basis for the development of comprehensive management framework for urban resilient. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

248. Research of Underwater Image Segmentation Algorithm Based on the Improved Geometric Active Contour Models

Author

Li Shelei and Huang Mengxing

Subjects
Active contour model, business.industry, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 020206 networking & telecommunications, 02 engineering and technology, Image segmentation, Image degradation, Fuzzy logic, Robustness (computer science), 0202 electrical engineering, electronic engineering, information engineering, Image segmentation algorithm, 020201 artificial intelligence & image processing, Segmentation, Computer vision, Artificial intelligence, Underwater, business
Abstract

In this paper, the basic theory of geometric active contour model was studied, for the degradation problems of low contrast, fuzzy and color distortion of underwater image data. Combined with the problem of underwater image degradation caused by unevenness of light and water's scattering and absorption of light, the adaptive GACV image segmentation algorithm was improved, and a mathematical model of underwater image segmentation based on the improved adaptive GACV image segmentation algorithm was established, and the underwater images were emulated. The simulation results showed that the algorithm fully segmented underwater images with low contrast and fuzzy features, which achieved the expected segmentation effect and shows good robustness.

Published
2018

Catalog

Books, media, physical & digital resources
See catalog results