检索结果-内蒙古大学图书馆

2nd International Conference on Mechatronics, IoT and Industrial Informatics, ICMIII 2024

作者： Qiao, Rui Zhong, Xiaolei Fu, Yang Wuhan University of Science and Technology School of Computer Science and Technology Wuhan China Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan China Dianchi College Kunming China Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9798350386639

Uncertain knowledge graphs store the relations between entities in the real world in the form of weighted triples, where the weights indicate the confidence scores of the triples to be true. However, there is limited research on the inference of uncertain knowledge graphs, especially in the integration of symbolic and numerical methods. Rules are explicit knowledge. Encoding the rules directly can provide more knowledge graph semantic information and can make full use of the interpretability and accuracy of logical rules. Unfortunately, none of the existing methods directly encode rules for uncertain knowledge graphs, but only use rules to calculate the confidence of unseen triples in training data. In this paper, we propose a new reasoning model CRLUKG for uncertain knowledge graphs, that combines the advantages of symbolic and numerical reasoning. We directly encode rules mined from the knowledge graph as one of the inputs of the CRLUKG model. Compositional representation learning with triple and rule embedding is implemented for optimizing objective function for triples and relations pairs. Experimental results demonstrate that our proposed method enhances the accuracy of reasoning, and furthermore, CRLUKG exhibits superior performance in comparison to baseline models when handling multi-task scenarios. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

RA-MP-Net: Residual attention and multi-scale perception network for microvasculature extraction in optical-resolution photoacoustic microscopy 24

RA-MP-Net: Residual attention and multi-scale perception net...

引用

7th International Conference on Image and Graphics Processing, ICIGP 2024

作者： Yu, Jialing Meng, Jing Ma, Fei Zhang, Yuanke Liu, Chengbo School of Computer Qufu Normal University Rizhao China Research Center for Biomedical Optics and Molecular Imaging Key Laboratory of Biomedical Imaging Science and System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (纸本)9798400716720

Optical-resolution photoacoustic microcopy (OR-PAM) is a non-invasive imaging technology that can achieve high-resolution vascular imaging and has been widely used in the field of vessel segmentation. Due to the low contrast of photoacoustic microvessel images and the discontinuity of vessels, existing vessel segmentation methods have some shortcomings: the accuracy of capillary extraction is insufficient, it is difficult to extract thick and thin vessels at the same time, and the vessels have deformed in some segmentation results. Therefore, we propose a deep learning network (RA-MP-Net) that integrates the residual attention(RA) module and the multi-scale perception (MP) module. Among them, RA module can focus on the vascular region in the image, and MP module can aggregate multi-scale vessel features. We conduct experiments on the normal vessel dataset from OR-PAM. Compared with existing work, the proposed microvascular segmentation algorithm can extract thick and thin vessels more accurately and continuously. In quantitative analysis, compared with the previously proposed 2D deep learning method, our evaluation indicators improved by 2.4%∼10.6%. The improvement in the accuracy of extracting vessels using our method is helpful for the diagnosis and evaluation of microvascular diseases. © 2024 ACM.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

3D printed-electrospun PCL/hydroxyapatite/MWCNTs scaffolds for the repair of subchondral bone

引用

Regenerative Biomaterials 2023年第1期10卷 294-305页

作者： Yanyan Cao Lei Sun Zixian Liu Zhizhong Shen Wendan Jia Peiyi Hou Shengbo Sang College of Information Science and Engineering Hebei North UniversityZhangjiakou 075000China Shanxi Key Laboratory of Micro Nano Sensors&Artificial Intelligence Perception College of Information and ComputerTaiyuan University of TechnologyTaiyuan 030024China Key Lab of Advanced Transducers and Intelligent Control System of the Ministry of Education Taiyuan University of TechnologyTaiyuan 030024China Shanxi Research Institute of 6D Artificial Intelligence Biomedical Science Taiyuan 030031China

Osteochondral defect caused by trauma or osteoarthritis exhibits a major challenge in clinical treatment with limited symptomatic effects at *** regeneration and remodeling of subchondral bone play a positive effect on cartilage regeneration and further promotes the repair of osteochondral *** use of the strengths of each preparation method,the combination of 3D printing and electrospinning is a promising method for designing and constructing multi-scale scaffolds that mimic the complexity and hierarchical structure of subchondral bone at the microscale and nanoscale,*** this study,the 3D printed-electrospun poly(ɛ-caprolactone)/nano-hydroxyapatites/multi-walled carbon nanotubes(PCL/nHA/MWCNTs)scaffolds were successfully constructed by the combination of electrospinning and layer-by-layer 3D *** resulting dual-scale scaffold consisted of a dense layer of disordered nanospun fibers and a porous microscale 3D scaffold layer to support and promote the ingrowth of subchondral ***,the biomimetic PCL/nHA/MWCNTs scaffolds enhanced cell seeding efficiency and allowed for higher cell-cell interactions that supported the adhesion,proliferation,activity,morphology and subsequently improved the osteogenic differentiation of bone marrow mesenchymal stem cells in ***,this study elucidates that the construction of 3D printed-electrospun PCL/nHA/MWCNTs scaffolds provides an alternative strategy for the regeneration of subchondral bone and lays a foundation for subsequent in vivo studies.

关键词： additive manufacturing 3D printing electrospinning subchondral bone

来源：评论

学校读者我要写书评

暂无评论

Prediction of piRNA-mRNA interactions based on an interactive inference network

Prediction of piRNA-mRNA interactions based on an interactiv...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Liu, Yajun Li, Ru Li, Aimin Fei, Rong Guo, Xie Wu, Fang-Xiang Xi'an University of Technology Shaanxi Key Laboratory for Network Computing and Security Technology Xi'an China Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an China University of Saskatchewan Division of Biomedical Engineering Department of Computer Science Department of Mechanical Engineering Saskatoon Canada

ISBN: (纸本)9798350337488

As the largest class of small non-coding RNAs, piRNAs primarily present in the reproductive cells of mammals, which influence post-transcriptional processes of mRNAs in multiple ways. Effective methods for predicting piRNA and mRNA target relationships can help identify piRNA functions, investigate the possibility of piRNAs as biomarkers and therapeutic targets. In this study, we propose a computational approach for classifying the relationships of piRNA-mRNA pairs based on an interactive inference network (IIN). First, we gather piRNA-mRNA target data, collect sequence data by position alignment, and construct a benchmark dataset. Furthermore, a reliable negative set is constructed by positive-unlabeled learning. Finally, we view a piRNA and a mRNA sequence as a premise and hypothesis sentence, respectively, and IIN model is used to predict the relationship between them. The experiments demonstrate that our method effectively characterizes piRNA-mRNA interaction and could be beneficial for researchers to investigate piRNA functions. © 2023 IEEE.

关键词： interactive inference network noncoding RNA piRNA-mRNA interactions positive-unlabeled learning

来源：评论

学校读者我要写书评

暂无评论

Algorithm for Acquiring Lettuce Plant Height Based on Image Recognition Network 4

Algorithm for Acquiring Lettuce Plant Height Based on Image ...

引用

4th International Conference on Artificial Intelligence and Electromechanical Automation, AIEA 2023

作者： Guo, Xiyue Zhong, Yong Zhao, Ming Zhang, Man Wang, Minjuan Key Laboratory of Modern Precision Agriculture System Integration Research Ministry of Education China Agricultural University China Yantai Institute of China Agricultural University Yantai264670 China State Key Laboratory of Virtual Reality Technology and Systems Beihang University China College of Information and Electrical Engineering China Agricultural University China

ISBN: (纸本)9781510666412

Lettuce height is one of the important phenotypic parameters of lettuce. Currently, evaluating plant height information based on RGB images is the most convenient and fastest method. However, these tasks often require complex camera calibration operations or reference objects with known heights, which are somewhat limiting. Therefore, we utilize a deep neural network to solve this problem to directly obtain the height of lettuce from RGB images without camera calibration and reference objects. This paper integrates four high-performance image recognition networks MobileNetV1, Densenet-121, ResNext-50, and EfficientNet-B3 using average fusion and linear fusion methods to predict lettuce plant height. Experiments show that we have achieved good results, the accuracy of the four basic models has been improved, and the average absolute error has been reduced to varying degrees. The smallest reduction is Efficient-Net, which has decreased 0.01 mm, the largest drop is the ResNext-50, which is 0.15mm lower. After the model is averagely fused, the average absolute error is further reduced to 1.22 mm, and the maximum absolute error is reduced to 6.48 mm, which is not only better than linear. The fusion results are better than the prediction results of a single model. © 2023 SPIE.

关键词： Lettuce

来源：评论

学校读者我要写书评

暂无评论

Optimized Breast Lesion Segmentation in Ultrasound Videos Across Varied Resource-Scant Environments 17th

Optimized Breast Lesion Segmentation in Ultrasound Videos A...

引用

17th Asian Conference on computer Vision, ACCV 2024

作者： Li, Yunhao Chen, Zibin Yan, Junming Ding, Ziyu Li, Jie Huang, Teng Pei, Xiaoqing Zhang, Zheng Wang, Qiong Pang, Yan Institute of Artificial Intelligence Guangzhou University Guangzhou China Cancer Center Sun Yat-sen University Guangzhou China Moxibustion and Rehabilitation Guangzhou University of Chinese Medicine Guangzhou China Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9789819609659

Medical video segmentation plays a crucial role in clinical diagnosis and therapeutic procedures by enabling dynamic tracking of breast lesions across frames in ultrasound videos, thereby improving segmentation accuracy. However, the existing methods struggle to strike a balance between segmentation accuracy and inference speed, which impedes their real-time deployment in resource-limited medical environments. To overcome these challenges, we introduce a rapid breast lesion segmentation framework named RbS. RbS employs the Stem module and RbSBlock to enhance representations through intra-frame analysis of ultrasound videos. Moreover, we have developed two versions of RbS: RbS-S boasts enhanced segmentation accuracy, while RbS-L ensures faster inference speeds. Experimental evidence indicates that RbS surpasses current leading models in both segmentation efficiency and prediction accuracy, particularly on resource-limited devices. Our contribution significantly propels the progress of developing efficient medical video segmentation frameworks suitable for various medical platforms. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Towards Stricter Black-box Integrity Verification of Deep Neural Network Models 24

Towards Stricter Black-box Integrity Verification of Deep Ne...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： He, Chaoxiang Bai, Xiaofan Ma, Xiaojing Zhu, Bin B. Hu, Pingyi Fu, Jiayun Jin, Hai Zhang, Dongmei Huazhong University of Science and Technology Hubei Wuhan China Shanghai Jiao Tong University Shanghai China Microsoft Corporation Beijing China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security School of Cyber Science and Engineering Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

ISBN: (纸本)9798400706868

Cloud-based machine learning services offer significant advantages but also introduce the risk of tampering with cloud-deployed deep neural network (DNN) models. Black-box integrity verification (BIV) allows model owners and end-users to determine if a cloud-deployed DNN model has been tampered with by examining only the top-1 label responses. Fingerprinting generates fingerprint samples to query the model, achieving BIV with no impact on the model's accuracy. In this paper, we present BIVBench, the first comprehensive benchmark for BIV of DNN models. BIVBench covers 16 types of model modifications, providing extensive coverage of practical modification scenarios. Our analysis reveals that existing fingerprinting methods, which are typically focused on significant tampering, lack the sensitivity needed to effectively detect subtle yet common and potentially severe modifications. To address this limitation, we propose MiSentry (Model Integrity Sentry), a novel fingerprinting method that leverages meta-learning. MiSentry strategically incorporates a few subtly modified models into the meta-learning model zoo and maximizes the divergence of output predictions between the target model and the modified models in the model zoo to generate highly sensitive, generalizable, and effective fingerprint samples. Extensive evaluations using BIVBench demonstrate that MiSentry outperforms existing state-of-the-art methods overall and significantly surpasses them in detecting subtle modifications. The BIVBench and supplementary materials are available at: https://***/CGCL-codes/BIVBench. © 2024 ACM.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on Multi-modal Multi-objective Path Planning by Improved Ant Colony Algorithm 1

引用

17th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2022

作者： Jing, Juan Zhang, Ling Shen, Chaonan Zhang, Kai School of Computer Science and Technology Wuhan University of Science and Technology Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology Wuhan430065 China

ISBN: (数字)9789819915491

ISBN: (纸本)9789819915484

A research about the path planning problem has been popular topic nowadays and some effective algorithms have been developed to solve this kind of problem. However, the existing algorithms to solve the path problem can only find a single optimal path, cannot satisfactorily find multiple groups of optimal solutions at the same time, and it is very necessary to propose as many solutions as possible. So this paper carries out a research on the Multi-modal Multi-Objective Path Planning (MMOPP), the objective is to find all sets of Pareto optimal path solutions from the start point to the end point in a grid map. This paper proposes a multi-modal multi-objective ant colony path planning optimization algorithm based on matrix preprocessing technology and Dijkstra algorithm (MD-ACO). Firstly, a new method of storing maps that reduces the size of the map and reduces the size of the decision space has been proposed in this paper. Secondly, using the characteristics of the Dijkstra algorithm that can quickly find the optimal path, generate an initial feasible solution about the problem, and improve the problem that the initial pheromone of ant colony algorithm is insufficient and searching for solutions is slow. Thirdly, a reasonable threshold is set for the pheromone to avoid algorithm getting stuck in local optimal solution. Finally, the algorithm is tested on the MMOPP test sets to evaluate the performance of the algorithm, and the results show that MD-ACO algorithm can solve MMOPP and get the optimal solution set. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Interference Suppression and Jitter Elimination Ability-Based Adaption Tracking Guidance for Robotic Fishes

引用

IEEE/CAA Journal of Automatica Sinica 2025年第1期12卷 126-137页

作者： Dongfang Li Jie Huang Rob Law Xin Xu Limin Zhu Edmond Q.Wu IEEE the School of Electrical Engineering and Automation Fuzhou University the Key Laboratory of System Control and Information Processing Ministry of Education the School of Electrical Engineering and Automation Fuzhou University 5G+Industrial Internet Institute Fuzhou University the University of Macau the College of Mechatronics and Automation National University of Defense Technology the School of Mechanical Engineering Shanghai Jiao Tong University the Department of Computer Science and Engineering Shanghai Jiao Tong University

This work presents an adaptive tracking guidance method for robotic fishes. The scheme enables robots to suppress external interference and eliminate motion jitter. An adaptive integral surge line-of-sight guidance rule is designed to eliminate dynamics interference and sideslip issues. Limited-time yaw and surge speed observers are reported to fit disturbance variables in the model. The approximation values can compensate for the system's control input and improve the robots' tracking ***, this work develops a terminal sliding mode controller and third-order differential processor to determine the rotational torque and reduce the robots' run jitter. Then, Lyapunov's theory proves the uniform ultimate boundedness of the proposed method. Simulation and physical experiments confirm that the technology improves the tracking error convergence speed and stability of robotic fishes.

关键词： Adaptive integral surge line-of-sight approximation robotic fish speed observer

来源：评论

学校读者我要写书评

暂无评论

Solving Constrained Multi-objective Optimization Problems with Passive Archiving Mechanism 1

引用

17th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2022

作者： Jia, Huijuan Zhang, Kai Shen, Chaonan School of Computer Science and Technology Wuhan University of Science and Technology Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology Wuhan430065 China

ISBN: (数字)9789819915491

ISBN: (纸本)9789819915484

During these years, many advanced constrained multi-objective evolutionary algorithms (CMOEAs) have been developed to solve constrained multi-objective optimization problems (CMOPs). However, some existing constrained multi-objective algorithms do not use an archiving mechanism, which leads to easy loss of the searched feasible solutions during the search process. In addition, even if some algorithms use an archiving mechanism, an unsuitable archiving update strategy can cause difficulty in balancing the diversity and convergence of the archive set. To address these challenges, a two-stage constrained multi-objective evolutionary algorithm based on a passive archiving mechanism (PA-CMOEA) is proposed in this paper. In the first stage, the constrained multi-objective problem is modeled as an unconstrained multi-objective problem, which allows the population to fully explore the decision space. The archive set is passively updated in a constraint-domination principle (CDP) criterion using population information. The goal of this stage is for the archive set to converge to the constrained Pareto front region of the problem with the help of population information. In the second stage, a local search is performed on the archive set. Specifically, the convergence and diversity of the archived solution set is improved while ensuring that the feasibility of the archived set is not worse. Finally, the algorithm outputs the archive set. To estimate the performance of the proposed algorithm, experiments are conducted on the LIRCMOP and CF benchmarks in comparison with some of the most popular algorithms. The experimental results demonstrate that the proposed algorithm has a competitive advantage compared with the comparative algorithms. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Benchmarking

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：