检索结果-内蒙古大学图书馆

15th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2020

作者： Fu, Zhongzheng Zhang, Luping Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9789811613531

P systems are distributed and parallel computing models inspired from living cells. In this work, a variant of spiking neural P systems, cortical neural P systems, are proposed in the frame work of P systems combining the topology structure of basic P system and information processing style in spiking neurons. The computational power of cortical neural P systems is investigated. It is proved that cortical neural P systems are equivalent to Turing machines as number generators. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Turing machines

来源：评论

学校读者我要写书评

暂无评论

HSDet: A Representative Sampling Based Object Detector in Cervical Cancer Cell images 15th

HSDet: A Representative Sampling Based Object Detector in Ce...

引用

15th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2020

作者： Yan, Xiaoli Zhang, Zhongsi Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9789811613531

Automated detection of cervical cancer cells has the potential to reduce error and increase productivity in cervical cancer screening. However, the existing object detection methods to detect the cervical cancer cells make inadequate use of negative samples and fail to balance the number of hard samples and easy samples. In this work, we propose a image-level sampling method, called pair sampling, which can extract the representative negative samples and generate the sample pair image. Then, based on the sample pair image, we propose the hybrid sampling, a proposal-level sampling method, to balance the number of hard samples and easy samples. Combining the proposed sampling methods, we design a representative sampling based cervical cell detector, which can detect the cervical cancer cells effectively. In order to comprehensively evaluate our method, we use a dataset which is consisted of 16000 annotated cervical cell images with size of 1024 × 1024. The experimental result shows that our method achieves 57.1% mean Average Precision (mAP), and it is higher than cascade R-CNN and Faster R-CNN by 4.7% and 5.8%, respectively. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Causal Invariant Hierarchical Molecular Representation for Out-of-distribution Molecular Property Prediction

Causal Invariant Hierarchical Molecular Representation for O...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Wen, Xinlong Guo, Yifei Wei, Shuoying Long, Wenhan Zhu, Lida Zhu, Rongbo College of Informatics Huazhong Agricultural University Wuhan430070 China Shenzhen Institute of Nutrition and Health Huazhong Agricultural University Shenzhen518000 China Shenzhen Branch Guangdong Laboratory for Lingnan Modern Agriculture Genome Analysis Laboratory of the Ministry of Agriculture Agricultural Genomics Institute at Shenzhen Chinese Academy of Agricultural Sciences Shenzhen518000 China Engineering Research Center of Intelligent Technology for Agriculture Ministry of Education Hubei Wuhan430074 China Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Wuhan430074 China

ISBN: (纸本)9798350386226

Molecular representation learning is widely used in the field of drug discovery, due to its ability to accurately capture the complex features of compounds in high-dimensional space. However, existing molecular representation learning models are prone to be influenced by spurious parts during distribution shifts (also known as out-of-distribution, or OOD), which results in models mistakenly treating these spurious parts as crucial features of molecules, thereby limiting the generalization capability of the models. To tackle this issue, a novel invariant molecular representation learning model, called Causal Invariant Hierarchical Molecular Representation Graph Neural Networks (CHiMoGNN), is proposed for OOD molecular property prediction. In CHiMoGNN, a Feature Enhancement (FE) module is designed to leverage the multi-level molecular parts to enhance the expression of invariant features, thereby enhancing the model's capability to capture key molecular information. In addition, a Cartesian Product based Environmental Impact (EI) module is adopted to generate counterfactual samples with environmental diversity. Consequently, these samples are utilized to train a classifier that maintains consistent performance across various environments. Extensive experiments on seven real-world datasets demonstrate that CHiMoGNN outperforms 9 state-of-the-art models, achieving a 5.73% increase in average ROC-AUC, and the results also show that CHiMoGNN can effectively maintain generalization in various distribution shifts. Code and datasets are available at https://***/Chertuion/CHiMoGNN. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Trimmed Data-Driven Evolutionary Optimization Using Selective Surrogate Ensembles 15th

Trimmed Data-Driven Evolutionary Optimization Using Selectiv...

引用

15th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2020

作者： Shan, Yawen Hou, Yongjin Wang, Mengzhen Xu, Fei Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9789811613531

Data-driven evolutionary algorithms (DDEAs) have attracted much attention in recent years, due to their effectiveness and advantages in solving expensive and complex optimization problems. In an offline data-driven evolutionary algorithm, no additional information is available to update surrogate models, so we need to ensure the quality of the surrogate models built before optimization. Based on the offline data-driven evolutionary algorithm using selective surrogate ensembles (DDEA-SE), we propose a trimmed bagging based DDEA-SE (TDDEA-SE) to construct a more accurate model pool. To this end, we use trimmed bagging to prune models with large errors calculated by out-of-bag samples, thus improving the accuracy of the selective surrogate ensembles and promoting the optimization. The experimental results on benchmark problems show that the proposed algorithm can strike a balance between diversity and accuracy of models, and its competitiveness on solving offline data-driven optimization problems. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Multiobjective Brainstorm Optimization with Diversity Preservation Mechanism for Nonlinear Equation Systems 15th

Multiobjective Brainstorm Optimization with Diversity Preser...

引用

15th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2020

作者： Zhao, Yi Zhu, Zelin Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9789811613531

In many fields of engineering and science, it is necessary to solve nonlinear equation systems (NESs). When using multiobjective optimization to solve NESs, there are two problems: 1) how to transform an NES into a multiobjective optimization problem and 2) how to design an algorithm to solve the transformed problems. In this work, we propose a multilayer bi-objective transformation technique, which can transform an NES into a bi-objective optimization problem, and it overcomes the curse of dimensionality and the problem of missing roots caused by the decrease of solutions discernibility in previous transformation techniques. Then, combining the multilayer bi-objective transformation technique, we design a multiobjective brainstorm optimization with a diversity preservation mechanism, which can effectively locate multiple roots of NESs in a single run. Compared with several state-of-art methods on 30 NESs with different features, our approach provides very competitive performance with the highest root ratio and success ratio. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Combining permuted language model and adversarial training for Chinese machine reading comprehension

引用

Journal of intelligent and Fuzzy Systems 2024年第4期46卷 10059-10073页

作者： Liu, Jianping Chu, Xintao Wang, Jian Wang, Meng Wang, Yingfei College of Computer Science and Engineering North Minzu University Yinchuan China The Key Laboratory of Images Graphics Intelligent Processing of State Ethnic Affairs Commission North Minzu University Yinchuan China Agricultural Information Institute Chinese Academy of Agricultural Sciences Beijing China

Due to the polysemy and complexity of the Chinese language, Chinese machine reading comprehension has always been a challenging task. To improve the semantic understanding and robustness of Chinese machine reading comprehension models, we propose a model that utilizes adversarial training algorithms and Permuted Language Model (PERT). Firstly, we employ the PERT pre-training model to embed paragraphs and questions into vector space to obtain corresponding sequential representations. Secondly, we use a multi-head self-attention mechanism to extract key textual information from the sequence and employ a Bi-GRU network to semantically fuse the output feature vectors, aiming to learn deep semantic representations in the text. Finally, we introduce perturbations into the model training process. We achieve this by utilizing adversarial training algorithms such as Fast Gradient Method (FGM) and Projected Gradient Descent (PGD). These algorithms generate adversarial samples to enhance the model’s robustness and stability when facing diverse inputs. We conducted comparative experiments on the publicly available Chinese reading comprehension datasets CMRC2018 and DRCD. The experimental results show that our proposed model has achieved significant improvements in both EM and F1-Score compared to the baseline model. To validate the model’s generalization and robustness, we utilized ChatGPT to construct a scientific dataset that includes a large number of domain-specific terms, sentences with mixed Chinese and English, and complex comprehension tasks. Our model also performed remarkably well on the self-built dataset. In conclusion, the proposed model not only effectively enhances the understanding of semantic information in Chinese text but also demonstrates a certain level of generalization capability. © 2024 – IOS Press. All rights reserved.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

A Novel Brain-Inspired Hierarchical Perception-Association Circuit Based on Memristor Arrays

SSRN

引用

SSRN 2023年

作者： Chen, Liangyu Wang, Xiaoping Chen, Zhanfei Yang, Chao Zeng, Zhigang School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Education Ministry of China Wuhan430074 China Hubei Key Laboratory of Brain-inspired Intelligent Systems Wuhan430074 China

In the brain, primary sensory cells can efficiently perceive multimodal stimuli, and then associative memory cells perform an advanced bidirectional associative memory function with perceived information. Here, a brain-inspired hierarchical perception-association circuit based on memristor arrays is proposed. Firstly, a memristive reservoir computing circuit is designed to simulate a low-level perceptual function, which mainly comprises dynamic analog reservoirs, memristor arrays, and analog integrators, enabling efficient spatio-temporal information processing. Secondly, a spiking bidirectional associative memory memristive circuit, as the core of the whole circuit, is proposed to mimick a high-level associative function, which mainly consists of memristor arrays, current amplifiers, and leaky integrate-and-fire neuron circuits, implementing multimodal associative learning. The simulation results in LTspice show that the modified neuron circuit exhibits 66× improvement in energy efficiency, and the proposed circuit can precisely perform the letter association and vision-audio association tasks in a spiking fashion with an average firing energy consumption of 230 pJ/spike, which has a great potential to be embedded in mobile robotic platforms. © 2023, The Authors. All rights reserved.

关键词： Memristors

来源：评论

学校读者我要写书评

暂无评论

An Integrated intelligent Autonomous Driving Bulldozer System: Pose Estimation, Object Detection, and Work Planning for Dumping Operations

引用

Journal of Field Robotics 2025年第0期

作者： Peng, Gang Gao, Qiang Liu, Xingyu Zhou, Yicheng Duan, Hangqi Wu, ZhanGang Hu, Bin Zhu, Xukang Xu, Daosheng School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan China Engineering Research Center of Autonomous Intelligent Unmanned Systems Ministry of Education Wuhan China Shantui Construction Machinery Co. Ltd. Jining China

In recent years, the rapid advancement of automation control and intelligent sensing technologies has positioned autonomous driving as a focal point of interest for both academia and industry. As core equipment in modern construction and industrial production, engineering machinery urgently requires intelligent transformation. To promote the intelligent development of engineering machinery, we have designed an integrated intelligent autonomous driving bulldozer system, which can be extended to various types of engineering machinery. For the specific mine dumping operation environment, we propose a multisensor fusion pose estimation algorithm framework based on the Global Navigation Satellite System, inertial measurement unit, visual cameras, and light detection and ranging (LiDAR) to address issues arising from sensor failures under harsh construction conditions. Furthermore, to ensure safety during task execution, we design a three-dimensional object detection method based on the optimal observation plane from LiDAR data. By integrating pose estimation and environmental perception results, we develop a comprehensive work planning and path-tracking algorithm to maintain task efficiency. Experimental results demonstrate that our intelligent autonomous driving bulldozer system performs excellently under various working conditions. The accuracy of its pose estimation, object detection, and path tracking meets the requirements of actual construction environments, showcasing its significant potential in engineering applications. © 2025 Wiley Periodicals LLC.

关键词： Construction equipment

来源：评论

学校读者我要写书评

暂无评论

Fast Node Selection of Networked Radar Based on Transfer Reinforcement Learning 5th

Fast Node Selection of Networked Radar Based on Transfer R...

引用

5th IFIP TC 12 International Conference on Intelligence Science, ICIS 2022

作者： Cao, Yanjun Wang, Yuan Guo, Jingjing Han, Li Zhang, Chao Zhu, Jin Zhang, Tianyang Zhang, Xiangrong The 54th Research Institute of China Electronics Technology Group Corporation Beijing China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xidian University Shaanxi Xian710071 China National Laboratory of Radar Signal Processing Xidian University Xian710071 China

ISBN: (纸本)9783031149023

The networked radar system can synthesize different echo signals received by various radars and realize the cooperative detection of multiple radars, becoming more and more critical for data fusion sharing and network collaboration. However, due to the large number and wide range of nodes in the networked radar system, there exists a redundancy problem in radar node assignment, which causes additional resource consumption and slows down the task execution speed of radar node selection. To solve the above problem, this paper proposes a fast radar node selection method based on transfer reinforcement learning to quickly select the optimal and minimum node resources. The proposed method devises a novel reward function for the Monte Carlo Tree and a different termination state of iteration to select the minimize the number of radar nodes. In order to further accelerate the selection of radar nodes, transfer reinforcement learning is presented to fully leverage the previous knowledge. Experimental results show that our proposed method can quickly select the optimal and minimum radar nodes in a brief period, significantly improving the speed of radar node selection in the networked radar. © 2022, IFIP International Federation for Information processing.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Research Progress of Encoder-Decoder Network in image Fusion

SSRN

引用

SSRN 2023年

作者： Zhou, Tao Zhang, Xiangxiang Cheng, Qianru Li, Qi Lu, Huiling School of Computer Science and Engineering North Minzu University Yinchuan750021 China Key Laboratory of Image and Graphics Intelligent Processing of State Ethnic Affairs Commission North Minzu University Yinchuan750021 China School of Science Ningxia Medical University Yinchuan750004 China

A B S T R A C Timage fusion is a research hotspot in the field of computer vision, which obtains complementary information from the different modal images and then presents it in a comprehensive, highly information-cohesive fused image. Encoder-decoder networks are an important technical method in the field of image fusion. This paper reviewed the research status and development of the Encoder-decoder networks in the field of image fusion from the following aspects: Firstly, the18 image fusion-related datasets and the 22 open-source codes of deep learning-based image fusion are summarized. Secondly, the model structure of encoder-decoder networks and the basic principles for image fusion based on the encoder-decoder network are described. Thirdly, encoder-decoder networks fusion models are summarized into 4 aspects: Convolutional Auto-encoder network(CAE Net), Sparse Auto-encoder network(SAE Net), U-shape Encoder-decoder network(U-net) and Variational Auto-encoder network(VAE Net),in U-net, there are 5 types: U-net incorporating residual connection mechanism (Res U-net), U-net incorporating dense connection mechanism (Dens U-net), U-net incorporating multiscale connection mechanism (MS U-net), U-net incorporating attention mechanism (Att U-net) and U-shaped Encoder-decoder networks(U-net) combined with Generative Adversarial Network(GAN U-net). Fourthly, the existing image fusion evaluation metrics are summarized from both subjective and objective aspects. Fifthly, the application of Encoder-decoder network in 5 kinds of image fusion, such as multi-exposure image fusion, multi-focus image fusion, infrared and visible image fusion, medical image fusion and remote sensing image fusion are summarized. Finally, there is a discussion of the main challenges faced by encoder-decoder networks in the image fusion domain and an outlook on future directions. This paper systematically analyzed the application of encoder-decoder networks in the image fusion areas, which has posi

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：