检索结果-内蒙古大学图书馆

Spatial and temporal consistency learning for monocular 6D pose estimation

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年 131卷

作者： Zhang, Hong-Bo Liang, Jia-Yu Hong, Jia-Xin Lei, Qing Liu, Jing-Hua Du, Ji-Xiang Huaqiao Univ Sch Comp Sci & Technol Xiamen 361021 Fujian Peoples R China Natl Huaqiao Univ Fujian Key Lab Big Data Intelligence & Secur Xiamen 361021 Fujian Peoples R China Huaqiao Univ Fujian Prov Univ Key Lab Comp Vis & Machine Learning Xiamen 361021 Fujian Peoples R China Huaqiao Univ Xiamen Key Lab Comp Vis & Pattern Recognit Xiamen 361021 Fujian Peoples R China

Monocular 6D pose estimation is a challenging task in the field of computer vision and robotics. Many previous works only input the cropped image of single object during training and inference, aiming to remove the noise from non-object regions. However, most of these methods ignore the viewpoint and spatial relationships of objects in the scene, which are crucial for accurate pose estimation of camera. To address this issue, this paper proposes a novel multi-view and multi-object based learning strategy for monocular 6D pose estimation, which involves the consistency of object coordinate for the same object at different viewpoints and the consistency of world coordinate for different objects in the same space. In the proposed method, the spatial and temporal groups are generated to trained the monocular 6D pose estimation network. Due to the camera motion, scene images taken at different times can be regarded as images captured from different viewpoints. Therefore, a temporal consistency loss is designed to constraint the relationship of the same object at different viewpoints, while a spatial consistency loss is designed to constraint the relationship of different objects at the same space. Finally, the proposed method is verified on the public datasets. Experimental results show that the proposed method is accurate, robust, and outperforms similar state-of-the-art approaches.

关键词： Monocular 6D pose estimation Spatial consistency Temporal consistency Spatial and temporal groups

来源：评论

学校读者我要写书评

暂无评论

Variational Graph Neural Network Based on Normalizing Flows

引用

IEEE TRANSACTIONS ON SIGNAL AND INFORMATION PROCESSING OVER NETWORKS 2025年 11卷 177-186页

作者： Su, Hailong Li, Zhipeng Yuan, Chang-An Filaretov, Vladimir F. Huang, Deshuang Tongji Univ Inst Machine Learning & Syst Biol Sch Elect & Informat Engn Shanghai 201804 Peoples R China Ningbo Inst Digital Twin Eastern Inst Technol Ningbo 315201 Zhejiang Peoples R China Univ Sci & Technol China Sch life Sci Hefei 230026 Anhui Peoples R China Guangxi Acad Sci Inst Big Data & Intelligent Comp Res Ctr Nanning 530007 Peoples R China Russian Acad Sci Inst Automat & Control Proc Far Eastern Branch Vladivostok 690041 Russia Tongji Univ Shanghai East Hosp Inst Regenerat Med Med Innovat CtrSch Life Sci & Technol Shanghai 200123 Peoples R China Tongji Univ Shanghai East Hosp Sch Life Sci & Technol State Key Lab Cardiol Shanghai 200123 Peoples R China

Graph Neural Networks (GNNs) have recently achieved significant success in processing non-Euclidean datasets, such as social and protein-protein interaction networks. However, these datasets often contain inherent uncertainties, such as missing edges between nodes that are closely related. Variational Graph Auto-Encoders (VGAE) and other Bayesian methods have been proposed to address the problem. Unfortunately, they can't handle graph data effectively. VGAE, for instance, the posterior is assumed to be Gaussian, which can not match the true posterior well. To overcome these limitations, a normalizing flows(NFs) based on variational GNN is proposed in this paper. Unlike VGAE, our approach no longer assumes that the posterior distribution is a standard Gaussian distribution, but instead utilizes NFs to learn more complex and flexible distributions. NFs transforms simple distributions into complex ones through a series of invertible transformations. The transformed distribution is more flexible and can match the true distribution better. Specifically, in order to obtain the reversible transformer, inspired by RealNVP, affine transformations on graphs are used to map a simple distribution to a complex one. The transformed distribution can infer more complex distributions like skewed. We conduct experiments in the link prediction task and our method performs excellently compared with other methods and even achieves state-of-the-art results on some datasets.

关键词： Graph neural networks Uncertainty Gaussian distribution Mathematical models Information processing Bayes methods Transforms Symbols Urban areas Standards Graph neural network normalizing flows variational inference link prediction

来源：评论

学校读者我要写书评

暂无评论

BIM: Improving Graph Neural Networks with Balanced Influence Maximization

BIM: Improving Graph Neural Networks with Balanced Influence...

引用

International Conference on data Engineering

作者： Wentao Zhang Xinyi Gao Ling Yang Meng Cao Ping Huang Jiulong Shan Hongzhi Yin Bin Cui Center for Machine Learning Research Peking University Institute of Advanced Algorithms Research Shanghai National Engineering Labratory for Big Data Analytics and Applications The University of Queensland Australia Key Lab of High Confidence Software Technologies Peking University Apple Inc. Institute of Computational Social Science Peking University Qingdao

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

The imbalanced data classification problem has aroused lots of concerns from both academia and industry since data imbalance is a widespread phenomenon in many real-world scenarios. Although this problem has been well researched from the view of imbalanced class samples, we further argue that graph neural networks (GNNs) expose a unique source of imbalance from the influenced nodes of different classes of labeled nodes, i.e., labeled nodes are imbalanced in terms of the number of nodes they influenced during the influence propagation in GNNs. To tackle this previously unexplored influence-imbalance issue, we connect social influence maximization with the imbalanced node classification problem and propose balanced influence maximization (BIM). Specifically, BIM greedily assigns the pseudo label to the node which can maximize the number of influenced nodes in GNN training while making the influence of each class more balance. Experimental results on five public datasets demonstrate the effectiveness of our method in relieving the influence-imbalance issue. For example, when training a GCN with an imbalance ratio of 0.1, BIM significantly outperforms the most competitive baseline by 0.6% -9.8% in five public datasets in terms of the F1 score.

关键词： Training Industries data engineering Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

SDN and application layer DDoS attacks detection in IoT devices by attention-based Bi-LSTM-CNN

引用

TRANSACTIONS ON EMERGING TELECOMMUNICATIONS TECHNOLOGIES 2023年第11期34卷

作者： Priyadarshini, Ishaani Mohanty, Pinaki Alkhayyat, Ahmed Sharma, Rohit Kumar, Sachin Univ Calif Berkeley Sch Informat Berkeley CA USA Purdue Univ Dept Comp Sci W Lafayette IN USA Islamic Univ Coll Tech Engn Najaf Iraq SRM Inst Sci & Technol Dept Elect & Commun Engn Delhi NCR Campus Ghaziabad Uttar Pradesh India South Ural State Univ Big Data & Machine Learning Lab Chelyabinsk Russia

The Internet of Things (IoT) is connecting more devices every day. Security is critical to ensure that the devices operate in a trusted environment. The lack of proper IoT security encourages cybercriminals to target many smart devices across the network and gain sensitive information. Distributed Denial of Service (DDoS) attacks are common in the IoT infrastructure and involve hijacking IoT devices to consume resources and interrupt services. This may specifically vandalize the application running the service that the end users are trying to access (application layer DDoS attacks) or flood the network bandwidth leading to network failure (software defined network DDoS attacks). This article proposes a hybrid attention-based bidirectional long short term memory (LSTM) with convolutional neural networks (CNN) to identify DDoS attacks in the application layer and SDN. We deploy several other machine learning models like logistic regression, decision trees, random forests, support vector machines, K-nearest neighbors, extreme gradient boosting, artificial neural networks, CNN, LSTM, CNN-LSTM to evaluate the performance of our proposed model. The evaluation metrics considered for the study are accuracy, precision, recall, and F-1 score. The experimental analysis on multiple datasets exhibits that the proposed model performs the classification efficiently with an accuracy of 99.74% and 99.98%.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Automated Segmentation of Brain Tumor MRI Images Using Deep learning

引用

IEEE ACCESS 2023年 11卷 64758-64768页

作者： Rajendran, Surendran Rajagopal, Suresh Kumar Thanarajan, Tamilvizhi Shankar, K. Kumar, Sachin Alsubaie, Najah M. Ishak, Mohamad Khairi Mostafa, Samih M. Saveetha Inst Med & Tech Sci Saveetha Sch Engn Dept Comp Sci & Engn Chennai 602105 India Chennai Inst Technol Ctr Syst Design Chennai 600069 India Panimalar Engn Coll Dept Comp Sci & Engn Chennai 600123 India South Ural State Univ Big Data & Machine Learning Lab Chelyabinsk 454080 Russia Princess Nourah Bint Abdulrahman Univ Coll Comp & Informat Sci Dept Comp Sci Riyadh 454080 Saudi Arabia Univ Sains Malaysia Sch Elect & Elect Engn Engn Campus George Town 14300 Malaysia South Valley Univ Fac Comp & Informat Comp Sci Dept Qena 83523 Egypt New Assiut Technol Univ NATU Fac Ind & Energy Technol Assiut 71515 Egypt

Segmenting brain tumors automatically using MR data is crucial for disease investigation and monitoring. Due to the aggressive nature and diversity of gliomas, well-organized and exact segmentation methods are used to classify tumors intra-tumorally. The proposed technique uses a Gray Level Co-occurrence matrix extraction of features approach to strip out unwanted details from the images. In comparison with the current state of the art, the accuracy of brain tumor segmentation was significantly improved using Convolutional Neural Networks, which are frequently used in the field of biomedical image segmentation. By merging the results of two separate segmentation networks, the proposed method demonstrates a major but simple combinatorial strategy that, as a direct consequence, yields much more precise and complete estimates. A U-Net and a Three-Dimensional Convolutional Neural Network. These networks are used to break up images into their component parts. Following that, the prediction was constructed using two distinct models that were combined in a number of ways. In comparison to existing state-of-the-art designs, the proposed method achieves the mean accuracy (%) of 99.40, 98.46, 98.29, precision (%) of 99.41, 98.51, 98.35, F-Score (%) of 99.4, 98.29, 98.46 and sensitivity (%) of 99.39, 98.41, 98.25 for the whole tumor, enhanced tumor, tumor core on the validation set, respectively.

关键词： Brain tumor medical imaging segmentation three dimensional CNN U-Net

来源：评论

学校读者我要写书评

暂无评论

Combined compression and encryption of linear wireless sensor network data using autoencoders

引用

Scientific Reports 2025年第1期15卷 1-16页

作者： Shylashree, N. Kumar, Sachin Min, Hong Department of Electronics and Communication RV College of Engineering Affiliated to VTU Belagavi Bengaluru 560059 India Big Data and Machine Learning Lab South Ural State University Chelyabinsk Russian Federation Akian College of Science and Engineering American University of Armenia Yerevan 0019 Armenia School of Computing Gachon University Seongnam South Korea

In a linear wireless sensor network (LWSN), sensor nodes are deployed in a linear fashion to monitor and gather data along a linear path or route. Generally, the base station collects the data from the contiguously placed nodes in the same order. When the sensors are deployed closely and with a gradual variation of sensor data along the route, a high degree of correlation exists among the sensed data. The sensed data sequence can be compressed with very low loss in such a situation. In this paper, a joint compression and encryption method for LWSN data is presented. The method is based on the dimension reduction property of an autoencoder at the bottleneck section. The Encoder part of the trained Autoencoder, housed at the Base Station (BS), reduces the number of data samples at the encoded output. Hence, the data gets compressed at the output of the Encoder. The output of the Encoder is encrypted using an asymmetric encryption that provides immunity to the Chosen Plaintext Attack. Thus, both data compression and encryption are achieved together at the BS. Therefore, the procedure at the BS is denoted as joint compression and encryption. The encrypted data is sent to the Cloud Server for secured storage and further distribution to the End User, where it is decrypted and subsequently decompressed by the Decoder part of the trained Autoencoder. The decompressed data sequence is very nearly equal to the original data sequence. The proposed lossy compression has a mean square reconstruction error of less than 0.5 for compression ratios in the range of 5 to 10. The compression time taken is short even though the Autoencoder training process, which occurs once in a while, takes a relatively long time. © The Author(s) 2025.

关键词： Autoencoder with supervised learning Chosen plaintext attack Integer matrix keys Joint compression and encryption Linear wireless sensor network Secured cloud storage

来源：评论

学校读者我要写书评

暂无评论

Frequency Bias Causes Overestimation of Climate Change Impacts on Global Flood Occurrence

引用

GEOPHYSICAL RESEARCH LETTERS 2024年第16期51卷 e2024GL108855-e2024GL108855页

作者： Zhao, Fang Lange, Stefan Goswami, Bedartha Frieler, Katja East China Normal Univ Sch Geog Sci Minist Educ Key Lab Geog Informat Sci Shanghai Peoples R China Minist Nat Resources Key Lab Spatial temporal Big Data Anal & Applicat Shanghai Peoples R China Leibniz Assoc Potsdam Inst Climate Impact Res PIK Potsdam Germany Int Inst Appl Syst Anal IIASA Biodivers & Nat Resources Program Water Secur Res Grp Laxenburg Austria Univ Tubingen Machine Learning Climate Sci Tubingen Germany

The frequency change of 100-year flood events is often determined by fitting extreme value distributions to annual maximum discharge from a historical base period. This study demonstrates that this approach may significantly bias the computed flood frequency change. An idealized experiment shows frequency bias exceeding 100% for a 50-year base period. Further analyses using Monte Carlo simulations, mathematical derivations, and hydrological model outputs reveal that bias magnitude inversely relates to base period length and is weakly influenced by the generalized extreme value distribution's shape parameter. The bias, persisting across different estimation methods, implies floods may exceed local defenses designed based on short historical records more often than expected, even without climate change. We introduce a frequency bias adjustment method, which significantly reduces the projected rise in global flood occurrence. This suggests a substantial part of the earlier projected increase in flood occurrence and impacts is not attributable to climate change. We report a previously overlooked bias in a common method for projecting the frequency of extreme floods, like 100-year events. This method typically uses a short period of historical data for two primary purposes: first, to define local thresholds for extreme floods, such as 100-year events, and second, to serve as a base for projecting future changes in flood occurrences. Our study, utilizing random data, demonstrates that this method can lead to inaccurate projections, increasing the number of expected extreme floods in future years and decreasing them in historical baseline years, even when no change is indicated by the data. Additionally, we find that the longer the historical period used, the smaller the bias. By simulating the characteristics of real hydrological model projections with artificial data, we are able to estimate a bias similar to that observed in these projections, and thus propose a simple

关键词：

来源：评论

学校读者我要写书评

暂无评论

Inconsistency Distillation For Consistency: Enhancing Multi-View Clustering via Mutual Contrastive Teacher-Student Leaning 22

Inconsistency Distillation For Consistency: Enhancing Multi-...

引用

22nd IEEE International Conference on data Mining (ICDM)

作者： Liu, Dunqiang Peng, Shu-Juan Liu, Xin Zhu, Lei Cui, Zhen Li, Taihao Huaqiao Univ Dept Comp Sci Xiamen Peoples R China Huaqiao Univ Fujian Key Lab Big Data Intelligence & Secur Xiamen Peoples R China Zhejiang Lab Hangzhou Peoples R China Huaqiao Univ Xiamen Key Lab Comp Vis & Pattern Recognit Xiamen Peoples R China Fujian Prov Univ Key Lab Comp Vis & Machine Learning Huaqiao Univ Xiamen Peoples R China Shandong Normal Univ Sch Informat Sci & Engn Jinan Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing Peoples R China

ISBN: (纸本)9781665450997

Multi-view clustering has attracted more attention recently since many real-world data are comprised of different representations or views. Recent multi-view clustering works mainly exploit the instance consistency to obtain the shared representations across different views, and apply a single-view clustering method to perform data partitions. However, these existing methods often ignore the inconsistency of instance associations within the views, which may enlarge the intra-class diversity among the views and therefore degrade the clustering performance. To address this issue, this paper proposes an efficient mutual contrastive teacher-student leaning (MC-TSL) model to enhance the multi-view clustering, which is the first attempt to study the inconsistency distillation for consistency learning. First, the proposed MC-TSL approach exploits a viewspecific encoder with two heads, an instance encoding head and a semantic distillation head, respectively, for capturing the consistent and discriminative feature representations. To be specific, the former head exploits a cross-view contrastive learning method to obtain a redundancy-free consistent representation at the instance level, while the latter head designs a mutual teacher-student learning module to capture the intraview information at semantic level. By training these two heads in an end-to-end manner, the discriminative multi-view embeddings are efficiently obtained and refined by minimizing the weighted sum of the reconstruction loss, contrastive loss and contrast distillation loss. Extensive experiments verify the superiorities of the proposed MC-TSL framework and show its competitive clustering performances.

关键词： Multi-view clustering inconsistency distillation cross-view contrastive learning mutual teacher-student learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Relational Graph Representation learning with Bayesian Gaussian Process Network 36

Multi-Relational Graph Representation Learning with Bayesian...

引用

36th AAAI Conference on Artificial Intelligence / 34th Conference on Innovative Applications of Artificial Intelligence / 12th Symposium on Educational Advances in Artificial Intelligence

作者： Chen, Guanzheng Fang, Jinyuan Meng, Zaiqiao Zhang, Qiang Liang, Shangsong Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou Peoples R China Guangdong Key Lab Big Data Anal & Proc Guangzhou Peoples R China Univ Glasgow Sch Comp Sci Glasgow Lanark Scotland Zhejiang Univ Hangzhou Innovat Ctr Hangzhou Peoples R China Zhejiang Univ Coll Comp Sci & Technol Hangzhou Peoples R China Mohamed bin Zayed Univ Artificial Intelligence Dept Machine Learning Abu Dhabi U Arab Emirates

ISBN: (纸本)9781577358763

learning effective representations of entities and relations for knowledge graphs (KGs) is critical to the success of many multi-relational learning tasks. Existing methods based on graph neural networks learn a deterministic embedding function, which lacks sufficient flexibility to explore better choices when dealing with the imperfect and noisy KGs such as the scarce labeled nodes and noisy graph structure. To this end, we propose a novel multi-relational graph Gaussian Process network (GGPN), which aims to improve the flexibility of deterministic methods by simultaneously learning a family of embedding functions, i.e., a stochastic embedding function. Specifically, a Bayesian Gaussian Process (GP) is proposed to model the distribution of this stochastic function and the resulting representations are obtained by aggregating stochastic function values, i.e., messages, from neighboring entities. The two problems incurred when leveraging GP in GGPN are the proper choice of kernel function and the cubic computational complexity. To address the first problem, we further propose a novel kernel function that can explicitly take the diverse relations between each pair of entities into account and be adaptively learned in a data-driven way. We address the second problem by reformulating GP as a Bayesian linear model, resulting in a linear computational complexity. With these two solutions, our GGPN can be efficiently trained in an end-to-end manner. We evaluate our GGPN in link prediction and entity classification tasks, and the experimental results demonstrate the superiority of our method.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

A Tailored Particle Swarm and Egyptian Vulture Optimization-Based Synthetic Minority-Oversampling Technique for Class Imbalance Problem

引用

INFORMATION 2022年第8期13卷 386页

作者： Rout, Subhashree Mallick, Pradeep Kumar Reddy, Annapareddy V. N. Kumar, Sachin Deemed Univ Kalinga Inst Ind Technol KIIT Sch Comp Engn Bhubaneswar 751024 Odisha India Lakireddy Bali Reddy Coll Engn Dept Informat Technol Mylavaram 521230 Andhra Pradesh India South Ural State Univ Big Data & Machine Learning Lab Chelyabinsk 454080 Russia

Class imbalance is one of the significant challenges in classification problems. The uneven distribution of data samples in different classes may occur due to human error, improper/unguided collection of data samples, etc. The uneven distribution of class samples among classes may affect the classification accuracy of the developed model. The main motivation behind this study is the design and development of methodologies for handling class imbalance problems. In this study, a new variant of the synthetic minority oversampling technique (SMOTE) has been proposed with the hybridization of particle swarm optimization (PSO) and Egyptian vulture (EV). The proposed method has been termed SMOTE-PSOEV in this study. The proposed method generates an optimized set of synthetic samples from traditional SMOTE and augments the five datasets for verification and validation. The SMOTE-PSOEV is then compared with existing SMOTE variants, i.e., Tomek Link, Borderline SMOTE1, Borderline SMOTE2, Distance SMOTE, and ADASYN. After data augmentation to the minority classes, the performance of SMOTE-PSOEV has been evaluated using support vector machine (SVM), Naive Bayes (NB), and k-nearest-neighbor (k-NN) classifiers. The results illustrate that the proposed models achieved higher accuracy than existing SMOTE variants.

关键词： class imbalance problem data augmentation SMOTE particle swarm optimization Egyptian vulture

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：