Author name cluster

Ming Tao

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

JBHI Journal 2024 Journal Article

A General DNA-Like Hybrid Symbiosis Framework: An EEG Cognitive Recognition Method

Hong Zeng
Yue Zhao
Fabio Babiloni
Ming Tao
Wanzeng Kong
Guojun Dai

In electroencephalogram (EEG) cognitive recognition research, the combined use of artificial neural networks (ANNs) and spiking neural networks (SNNs) plays an important role to realize different categories of recognition tasks. However, most of the existing studies focus on the unidirectional interaction between an ANN and a SNN, which may be overly dependent on the performance of ANNs or SNNs. Inspired by the symbiosis phenomenon in nature, in this study, we propose a general DNA-like Hybrid Symbiosis (DNA-HS) framework, which enables mutual learning between the ANN and the SNN generated by this ANN through parametric genetic algorithm and bidirectional interaction mechanism to enhance the optimization ability of the model parameters, resulting in a significant improvement of the performance of the DNA-HS framework in all aspects. By comparing with seven typical EEG cognitive recognition models, the performance of the seven hybrid network frameworks constructed using this method on different EEG-based cognitive recognition tasks are all improved to different degrees, verifying the effectiveness of the proposed method. This unified hybrid network framework similar to the DNA structure is expected to open up a new approach and form a new research paradigm for EEG-based cognitive recognition task.

Details DOI

EAAI Journal 2023 Journal Article

An intelligent approach for predicting overbreak in underground blasting operation based on an optimized XGBoost model

Zhixian Hong
Ming Tao
Leilei Liu
Mingsheng Zhao
Chengqing Wu

The occurrence of overbreak in tunnels excavated with the drill-and-blast technique is a common phenomenon that has significant impacts on structure safety and construction costs. Accurate prediction of overbreak is crucial for optimizing the construction schedule and diminishing damages. This study proposed a data-driven method that integrated extreme gradient boosting (XGBoost) and Bayesian optimization (BO) algorithms to predict overbreak extent. Firstly, 250 overbreak samples were collected from three underground mines, and eight independent factors that may affect overbreak were identified. Subsequently, the BO–XGBoost prediction model was established, and Spearman correlation analysis and sensitivity analysis were conducted to analyze the relation between overbreak and influencing factors. Finally, the proposed BO–XGBoost model was employed to forecast the overbreak in another two underground mines. The experimental results indicated that the proposed BO–XGBoost model outperformed other models, including Random Forests (RF), Support Vector Machine (SVM), BO–RF, BO–SVM, and XGBoost models, with root mean square error (RMSE), mean absolute error (MAE), and determination coefficient (R 2) values of 0. 888, 0. 619 and 0. 935, respectively. Additionally, statistical analysis using Friedman Test (FT) and Wilcoxon Signed-Rank Test (WSRT) demonstrated the efficacy of the proposed model. The results suggested that tunnel diameter (D) was the most significant factor affecting overbreak, followed by RMR, periphery hole burden (SP) and uniaxial compressive strength (UCS). The proposed method accurately forecasted overbreak extents at different mines, with errors between the predicted and observed overbreaks of less than 6%. In summary, the proposed BO–XGBoost model can provide valuable guidance for predicting blast-induced overbreak in mining and tunneling operations.

Details DOI

AAAI Conference 2023 Conference Paper

DE-net: Dynamic Text-Guided Image Editing Adversarial Networks

Ming Tao
Bing-Kun Bao
Hao Tang
Fei Wu
Longhui Wei
Qi Tian

Text-guided image editing models have shown remarkable results. However, there remain two problems. First, they employ fixed manipulation modules for various editing requirements (e.g., color changing, texture changing, content adding and removing), which results in over-editing or insufficient editing. Second, they do not clearly distinguish between text-required and text-irrelevant parts, which leads to inaccurate editing. To solve these limitations, we propose: (i) a Dynamic Editing Block (DEBlock) that composes different editing modules dynamically for various editing requirements. (ii) a Composition Predictor (Comp-Pred), which predicts the composition weights for DEBlock according to the inference on target texts and source images. (iii) a Dynamic text-adaptive Convolution Block (DCBlock) that queries source image features to distinguish text-required parts and text-irrelevant parts. Extensive experiments demonstrate that our DE-Net achieves excellent performance and manipulates source images more correctly and accurately.

PDF Details DOI