检索结果-内蒙古大学图书馆

Angiosperm Genus Classification by RBF-SVM 1

11th International Conference on Frontiers of Intelligent Computing: Theory and Applications, FICTA 2023

作者： Chen, Shuwen Wang, Jiaji Ni, Yiyang Shao, Jiaqi Qu, Hui Wang, Ziyi School of Physics and Information Engineering Jiangsu Second Normal University Nanjing211200 China Jiangsu Province Engineering Research Center of Basic Education Big Data Application Nanjing211200 China State Key Laboratory of Millimeter Waves Southeast University Nanjing210096 China

ISBN: (数字)9789819967063

ISBN: (纸本)9789819967056

Angiosperm genus classification performance has plateaued in the last few years. This paper proposed a novel method based on gray-level co-occurrence matrix and radial basis function kernel support vector machine for angiosperm genus classification. We collected a 300-image dataset, 100 are Hibiscus, 100 are Orchis, and the rest 100 are Prunus by digital camera. The results showed that our method achieved an accuracy of 84.73 ± 0.41%. In all, this method is promising in angiosperm genus classification. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Security Performance Analysis for MIMO Systems: From Artificial Noise's Power and Dimension Perspective

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Xu, Panpan Li, Zhenling Li, Chunguo Tan, Weijie Guizhou University School of Mathematics and Statistics Guiyang550025 China Southeast University School of Information Science and Engineering Nanjing210096 China Guizhou University State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang550025 China

This paper analyzes the influence of power and dimension of artificial noise (AN) on security performance of multiple-input multiple-output (MIMO) system with multiple randomly located eavesdroppers. We derive the closed-form expressions of the secrecy outage probability (SOP) and the optimal secrecy capacity by utilizing the irrelevance among transmission channels, and the orthogonality between AN and the basis vectors of the legitimate channel matrix's null space. We use the Poisson point process to determine the number and location of eavesdroppers, then analyze the security performance of the communication system under the 3D channel condition of probability-based line-of-sight (LoS) or non-line-of-sight (NLoS) channel. The simulation results show the following conclusions. When the AN dimension reaches 1/4 highest dimension (i.e., one quarter of the number of transmitting antennae less than one) and the power splitter factor (PSF) falls in the open interval (0.6, 0.9), we can achieve a trade-off between secrecy capacity and design complexity. © 1967-2012 IEEE.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

PCQPR: Proactive Conversational Question Planning with Reflection

arXiv

引用

arXiv 2024年

作者： Guo, Shasha Liao, Lizi Zhang, Jing Li, Cuiping Chen, Hong School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education China Singapore Management University Singapore

Conversational Question Generation (CQG) enhances the interactivity of conversational question-answering systems in fields such as education, customer service, and entertainment. However, traditional CQG, focusing primarily on the immediate context, lacks the conversational foresight necessary to guide conversations toward specified conclusions. This limitation significantly restricts their ability to achieve conclusion-oriented conversational outcomes. In this work, we redefine the CQG task as Conclusion-driven Conversational Question Generation (CCQG) by focusing on proactivity, not merely reacting to the unfolding conversation but actively steering it towards a conclusion-oriented question-answer pair. To address this, we propose a novel approach, called Proactive Conversational Question Planning with self- Refining (PCQPR). Concretely, by integrating a planning algorithm inspired by Monte Carlo Tree Search (MCTS) with the analytical capabilities of large language models (LLMs), PCQPR predicts future conversation turns and continuously refines its questioning strategies. This iterative self-refining mechanism ensures the generation of contextually relevant questions strategically devised to reach a specified outcome. Our extensive evaluations demonstrate that PCQPR significantly surpasses existing CQG methods, marking a paradigm shift towards conclusion-oriented conversational question-answering systems. © 2024, CC BY-NC-SA.

关键词： Direct process refining

来源：评论

学校读者我要写书评

暂无评论

Joint-Motion Mutual Learning for Pose Estimation in Video 24

Joint-Motion Mutual Learning for Pose Estimation in Video

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Wu, Sifan Chen, Haipeng Yin, Yifang Hu, Sihao Feng, Runyang Jiao, Yingying Yang, Ziqi Liu, Zhenguang College of Computer Science and Technology Jilin University Changchun China A STAR Singapore Singapore Georgia Institute of Technology AtlantaGA United States School of Artificial Intelligence Jilin University Changchun China The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China Institute of Blockchain and Data Security Hangzhou China

ISBN: (纸本)9798400706868

Human pose estimation in videos has long been a compelling yet challenging task within the realm of computer vision. Nevertheless, this task remains difficult because of the complex video scenes, such as video defocus and self-occlusion. Recent methods strive to integrate multi-frame visual features generated by a backbone network for pose estimation. However, they often ignore the useful joint information encoded in the initial heatmap, which is a by-product of the backbone generation. Comparatively, methods that attempt to refine the initial heatmap fail to consider any spatio-temporal motion features. As a result, the performance of existing methods for pose estimation falls short due to the lack of ability to leverage both local joint (heatmap) information and global motion (feature) dynamics. To address this problem, we propose a novel joint-motion mutual learning framework for pose estimation, which effectively concentrates on both local joint dependency and global pixel-level motion dynamics. Specifically, we introduce a context-aware joint learner that adaptively leverages initial heatmaps and motion flow to retrieve robust local joint feature. Given that local joint feature and global motion flow are complementary, we further propose a progressive joint-motion mutual learning that synergistically exchanges information and interactively learns between joint feature and motion flow to improve the capability of the model. More importantly, to capture more diverse joint and motion cues, we theoretically analyze and propose an information orthogonality objective to avoid learning redundant information from multi-cues. Empirical experiments show our method outperforms prior arts on three challenging benchmarks. © 2024 ACM.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Dual Encoders for Diffusion-based Image Inpainting

Dual Encoders for Diffusion-based Image Inpainting

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Dezhi Zheng Kaijun Deng Jinbao Wang Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Current diffusion-based inpainting models struggle to preserve unmasked regions or generate highly coherent content. Additionally, it is hard for them to generate meaningful content for 3D inpainting. To tackle these challenges, we design a plug-and-play branch that runs through the entire generation process to enhance existing models. Specifically, we utilize dual encoders - a Convolutional Neural Network (CNN) encoder and the pre-trained Variational AutoEncoder (VAE) encoder, to encode masked images. The latent code and the feature map from the dual encoders are fed to diffusion models simultaneously. In addition, we apply Zero-padded initialization to solve the problem of mode collapse caused by this branch. Experiments on BrushBench and EditBench demonstrate that models with our plug-and-play branch can improve the coherence of inpainting, and our model achieves new state-of-the-art results.

关键词： Visualization Three-dimensional displays Codes Autoencoders Coherence Signal processing Diffusion models Decoding Convolutional neural networks Speech processing

来源：评论

学校读者我要写书评

暂无评论

DGA-Net: Dynamic Gaussian Attention Network for Sentence Semantic Matching 1st

DGA-Net: Dynamic Gaussian Attention Network for Sentence Se...

引用

1st CAAI International Conference on Artificial Intelligence, CICAI 2021

作者： Zhang, Kun Lv, Guangyi Wang, Meng Chen, Enhong Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China School of Computer Science and Technology University of Science and Technology of China Hefei China

ISBN: (纸本)9783030930486

Sentence semantic matching requires an agent to determine the semantic relation between two sentences, where much recent progress has been made by advancement of representation learning techniques and inspiration of human behaviors. Among all these methods, attention mechanism plays an essential role by selecting important parts effectively. However, current attention methods either focus on all the important parts in a static way or only select one important part at one attention step dynamically, which leaves a large space for further improvement. To this end, in this paper, we design a novel Dynamic Gaussian Attention Network (DGA-Net) to combine the advantages of current static and dynamic attention methods. More specifically, we first leverage pre-trained language model to encode the input sentences and construct semantic representations from a global perspective. Then, we develop a Dynamic Gaussian Attention (DGA) to dynamically capture the important parts and corresponding local contexts from a detailed perspective. Finally, we combine the global information and detailed local information together to decide the semantic relation of sentences comprehensively and precisely. Extensive experiments on two popular sentence semantic matching tasks demonstrate that our proposed DGA-Net is effective in improving the ability of attention mechanism. © 2021, Springer Nature Switzerland AG.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Community Discovery Algorithm via Reconstructed Graph Neural NEtwork

Unsupervised Community Discovery Algorithm via Reconstructed...

引用

2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023

作者： Wang, Jinghong Wang, Hui Yang, Jiateng Wang, Xizhao College of Computer and Cyber Security Hebei Normal University Shijiazhuang050024 China Hebei Normal University Hebei Key Laboratory of Network and Information Security Shijiazhuang050024 China Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics & Data Security Hebei Normal University Shijiazhuang050024 China College of Artificial Intelligence Big Data Hebei Polytechnic Institute Shijiazhuang050020 China College of Computer Science and Software Engineering ShenZhen University Shenzhen518060 China

ISBN: (纸本)9798350303780

Community discovery can help discover potential community structures in the network, which is a fundamental and important issue in network science. Graph neural network-based algorithms are receiving increasing attention. However, there is relatively little work on community discovery directly using graph neural networks in reconstruction design. This paper presents an Unsupervised Community Discovery Algorithm based on reconstructed graph neural network (UCDA) to resolve the above issues. To be specific, this paper proposes a framework that learns the representation based on network structure and attribute information. By designing input network features, encoders, decoders, this algorithm uses an unsupervised loss function to train neural networks to extract communities in an integrated way. These designs integrate higher-order modularity information with network features and use variational graph auto-encoders to train data end-to-end under the graph neural network framework. Based on a series of experiments with a wide range of datasets and advanced algorithms, UCDA has achieved superior performance and shows strong competitiveness. Finally, the last section reports the results analysis, t-SNE visualization and hyperparameter analysis, which depicts stable performance and powerful network modularity ability. © 2023 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Multi-Granular Decision Networks for Hierarchical Classification

SSRN

引用

SSRN 2024年

作者： Liu, Haoyang Hu, Xue gang Bai, Shengxing Lin, Yaojin Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Ministry of Education China School of Computer Science and Information Engineering Hefei University of Technology Anhui Hefei230009 China Anhui Province Key Laboratory of Industry Safety and Emergency Technology Anhui Hefei230009 China School of Computer Science Minnan Normal University Fujian Zhangzhou363000 China Key Laboratory of Data Science and Intelligence Application Minnan Normal University Fujian Zhangzhou363000 China

Hierarchical classification learning is an effective means of solving large-scale classification problems, which models classification problems at different levels of granularity according to a hierarchical structure. In hierarchical classification tasks, classification results at different levels of granularity are mutually beneficial, where coarse-grained results can reduce the number of fine-grained candidate categories, and fine-grained results can provide a basis for coarse-grained classification. However, for the final decision, the contribution of the granularity levels in the different hierarchies is different and unknown. Feedback from different granularity levels should be flexibly integrated. In addition, errors in hierarchical classification are not equivalent, and some errors can have serious results for practical applications. In order to address the above challenges, we propose a new hierarchical network to integrate multi-granularity knowledge for decision making. On the one hand, the network computes the decision scores of instances at each granularity level and learns a set of weights to combine all scores. Based on the learnable weights, the model can effectively utilize the multi-granularity classification results to obtain the final decision. On the other hand, we design local and global classification losses to guide model optimization, which allows the model to gain a hierarchical perspective and the ability to understand the degree of hierarchical misclassification. As a result, the extent to which the method results in misclassification consequences is limited. Experimental results on five benchmark datasets show that our method arises as a state-of-the-art hierarchical classification method. © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Adaptively Feature Extracting Network for Cervical Squamous Lesion Cell Detection 4th

Deep Adaptively Feature Extracting Network for Cervical Squ...

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Peng, Zhonghua Hu, Rong Wang, Fuen Fan, Haoyi Eng, Yee Wei Li, Zuoyong Zhou, Liwei Fujian Provincial Key Laboratory of Big Data Mining and Applications School of Computer Science and Mathematics Fujian University of Technology Fujian Fuzhou350118 China School of Computer and Artificial Intelligence Zhengzhou University Henan Zhengzhou450001 China School of Computer Sciences Universiti Sains Malaysia Penang11800 Malaysia Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fujian Fuzhou350121 China Department of Nutrition The First Affiliated Hospital of Zhengzhou University Henan Zhengzhou450052 China

ISBN: (纸本)9783031200984

Cervical cancer is one of the most widespread malignancies affecting women’s health worldwide today. However, the task of detection is particularly difficult due to the complex background of the cervical smear, where cells are previously stacked in clusters. To address this problem, we utilize the YOLOv5 as the baseline and build on YOLOv5 by using the simple Transformer Block which only combines with multi-head self attention layers and MLP to better extract cell features as well as to obtain global information. In addition, we allow the model to refine features adaptively to assist with detection by using Convolutional Block Attention Module (CBAM), an attention module being simple and effective for feed-forward convolutional neural networks, in the complex background information. Finally, we compare the model with YOLOv5 as baseline. In CDetector dataset, our model obtains 52.5% mAP@.5, which is 6% better than baseline. In transfer learning, it is 62.2%, which outperforms baseline by 3.2%. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Cells

来源：评论

学校读者我要写书评

暂无评论

Feature deformation network with multi-range feature enhancement for agricultural machinery operation mode identification

引用

International Journal of Agricultural and Biological engineering 2024年第4期17卷 265-275页

作者： Weixin Zhai Zhi Xu Jinming Liu Xiya Xiong Jiawen Pan Sun-Ok Chung Dionysis Bochtis Caicong Wu College of Information and Electrical Engineering China Agricultural UniversityBeijing 100083China Key Laboratory of Agricultural Machinery Monitoring and Big Data Application Ministry of Agriculture and Rural AffairsBeijing 100083China Department of Smart Agricultural Systems Graduate SchoolChungnam National UniversityDaejeon 34134Republic of Korea Institute for Bio-Economy and Agri-Technology(iBO) Centre for Research and Technology-Hellas(CERTH)Thessaloniki 57001Greece

Utilizing the spatiotemporal features contained in extensive trajectory data for identifying operation modes of agricultural machinery is an important basis task for subsequent agricultural machinery trajectory *** the present study,to effectively identify agricultural machinery operation mode,a feature deformation network with multi-range feature enhancement was ***,a multi-range feature enhancement module was developed to fully explore the feature distribution of agricultural machinery trajectory ***,to further enrich the representation of trajectories,a feature deformation module was proposed that can map trajectory points to high-dimensional space to form feature ***,EfficientNet-B0 was used to extract features of different scales and depths from the feature map,select features highly relevant to the results,and finally accurately predict the mode of each trajectory *** validate the effectiveness of the proposed method,experiments were conducted to compare the results with those of other methods on a dataset of real agricultural *** the corn and wheat harvester trajectory datasets,the model achieved accuracies of 96.88%and 96.68%,as well as F1 scores of 93.54%and 94.19%,exhibiting improvements of 8.35%and 9.08%in accuracy and 20.99%and 20.04%in F1 score compared with the current state-of-the-art method.

关键词： road-field trajectory classification efficientNet feature deformation network multi-range feature enhancement agricultural machinery operation mode recognition

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：