检索结果-内蒙古大学图书馆

11th International Symposium on Parallel Architectures, Algorithms and Programming, PAAP 2020

作者： Hua, Qiang Chen, Liyou Li, Pan Zhao, Shipeng Li, Yan Key Laboratory of Machine Learning and Computational Intelligence of Hebei Province College of Mathematics and Information Science Hebei University Baoding071002 China

ISBN: (纸本)9789811600098

As the neural network becomes more and more complex, a large number of parameters are to be adjusted and more unrelated information will be generated, which is more time-consuming in model training and affects the model performance. The attention mechanic is often used to address this problem in the literature. However, the current attention models only consider the correlation within the pixel domain and channel domain individually, and the computational complexity is comparatively high. This paper proposes a new type of attention module called Pixel-wise And Channel-wise attention (PAC attention module for short) in which the hybrid correlation between the pixel and channel domain is also considered. Without increasing the number of parameters, this module can be used to calculate the correlation of the convolution feature map at any position in any layer of the convolutional neural network to achieve end-to-end training. In the experiments, the proposed PAC attention module is used in typical network structures in deep learning and has been compared to current models on some benchmark big datasets. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

TempCast: A Multi-modal Transformer for Short-Term Temperature Forecasting 8

TempCast: A Multi-modal Transformer for Short-Term Temperatu...

引用

8th IEEE International Conference on Cloud Computing and intelligence Systems, CCIS 2022

作者： Zhang, Wei Cao, Yang Zhai, Jun-Hai Mu, Ziyao Zhang, Shuai Hebei University Hebei Key Laboratory of Machine Learning and Computational Intelligence College of Mathematics and Information Science Hebei071002 China Unit 78127 of the Chinese People's Liberation Army Chengdu610000 China

ISBN: (纸本)9781665477352

Accurate weather forecasting benefits us in a variety of ways, from scheduling flights to agricultural harvests. However, existing temperature forecasting models have two problems, one is the accumulation of errors caused by autoregressive models, and the other is difficult to predict complex and varying temperatures such as those in highlands. In this paper, we proposed TempCast, a multi-modal Transformer model for short-term temperature prediction. The model has two features: (i) Modeling the features entirely by self-attention, which can effectively capture the exact long-term dependent coupling between output and input. And multiple predictions are obtained at once using a generative decoder, (ii) The modeling of multi-source data through a decoupled multi-modal fusion mechanism can effectively come to cope with the drastic changes of weather in highlands and mountains, etc. The experimental results show that the method can well achieve short-term temperature prediction and significantly outperforms all traditional methods in several indicators. The method also provides a new solution idea for multi-modal temperature prediction. Our code and data are available at https://***/Adam618/Temp Cast. © 2022 IEEE.

关键词： Weather forecasting

来源：评论

学校读者我要写书评

暂无评论

SwinVI:3D Swin Transformer Model with U-net for Video Inpainting

SwinVI:3D Swin Transformer Model with U-net for Video Inpain...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Wei Zhang Yang Cao Junhai Zhai Hebei Key Laboratory of Machine Learning and Computational Intelligence College of Mathematics and Information Science Hebei University Baoding China

The goal of video inpainting is to fill in the local missingness of a given video as realistic as possible, it remains a challenging task, even with powerful deep learning methods. In recent years, Transformer has been introduced to video inpainting, and remarkable improvement has been achieved. However, it still suffers from the problems of generating blurry texture and requiring high computational cost. To address the two problems, we propose a new 3D Swin Transformer model (SwinVI) with U-net to improve the quality of video inpainting efficiently. We modify the vanilla Swin Transformer by extending the standard self-attention mechanism to a 3D self-attention mechanism, which enables the modified model to process spatio-temporal information simultaneously. SwinVI consists of U-net implemented by 3D Patch Merge and CNN-equipped upsampling module, which provides an end-to-end learning framework. This structural design empowers Swin VI to fully focus on background textures and moving objects to learn robust and more representative token vectors. Accordingly, to significantly improve the quality of video inpainting efficiently. We experimentally compare Swin VI with multiple methods on two challenging benchmarks. Experimental results demonstrate that the proposed Swin VI outperforms the state-of-the-art methods in RMSE, SSIM, and PSNR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Discriminative Score Suppression for Weakly Supervised Video Anomaly Detection

Discriminative Score Suppression for Weakly Supervised Video...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Chen Xu Chunguo Li Hongjie Xing Hebei Key Laboratory of Machine Learning and Computational Intelligence College of Mathematics and Information Science Hebei University Baoding China School of Cyber Security and Computer Hebei University Baoding China

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Weakly supervised video anomaly detection (WSVAD) often relies on Multiple Instance learning (MIL). However, selecting only the most discriminative segments for training limits the model's ability to comprehensively detect anomalous events, particularly hard anomalies. To overcome this limitation, we propose the Discriminative Score Suppression (DSS) module. This module suppresses the discriminative scores of the most prominent anomalies, shifting the model's attention to less obvious but important hard anomalies. This approach guides the model to learn the critical features of hard anomalies, enabling a more comprehensive detection of anomalous events. Additionally, the Anomaly Score Refinement (ASR) module constructs a dissimilarity-based classifier by storing normal patterns as prototypes, and integrates this with a neural network classifier. By combining the anomaly scores from both classifiers, more accurate detection of true hard anomalies is achieved. A score-sensitive inner-bag loss function not only adjusts penalties based on anomaly scores but also ensures that the model avoids erroneous selections. Our method accurately detects various anomalies, including challenging and multi-segment anomalies, while minimizing false positives for normal events. Extensive experiments show that the proposed framework outperforms state-of-the-art methods on the UCF-Crime and XD-Violence datasets.

关键词： Training Computer vision Accuracy Neural networks Prototypes Benchmark testing Feature extraction Robustness Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

A Multi-Scale Neighborhood Feature Interaction Network for Photovoltaic Cell Defect Detection

SSRN

引用

SSRN 2024年

作者： Liu, Yu Chen Hua, Qiang Chen, Lin Lin Dong, Chun Ru Zhang, Feng Zhang, Yong Hebei Key Laboratory of Machine Learning and Computational Intelligence Hebei University Baoding China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

Photovoltaic power generation is a key component of the industrial field, whose power generation efficiency is affected by surface defects of photovoltaic cells. The recent success in defect detection is largely attributed to the widespread application of deep learning detection models. However, because of the various sizes of defects on the photovoltaic cells, it is difficult to effectively detect multi-scale defects, especially small defects. Additionally, a large amount of noise information in images brings more difficulties in extracting distinguishable features. To address these issues, a novel one-stage Multi-Scale Neighborhood Feature Interaction Network (MNFI-Net) is proposed in this study to identify defects of various sizes in complex backgrounds. The MNFI-Net consists of the following components: 1) a Ghost Cross Stage Module (GCSM) that is devised to reduce redundant information;2) a Neighborhood Feature Interaction Model (NFIM), which is used to improve the capability of detecting defects with various size;3) a Global Attention Mechanism (GAM) that is devised to emphasize the key features of the fused feature maps. Furthermore, we introduce a novel Balanced Efficient (BE) loss function, which integrates the efficient iou loss and normalized weighted distance loss. Extensive comparison experiments and ablation studies on public photovoltaic electroluminescence images dataset are performed and the experimental results show that the defect classification and detection results of MNFI-Net in photovoltaic cell images achieve 94.0% precision and 95.5% mAP, outperforming the state-of-the-art methods. The code and proposed models in this study can be accessed at https://***/lyc686/MNFI-Net. © 2024, The Authors. All rights reserved.

关键词： Photovoltaics

来源：评论

学校读者我要写书评

暂无评论

Class Prototype Angle Loss for Imbalanced Data

SSRN

引用

SSRN 2023年

作者： Ma, Tingting Lu, Shuxia Hebei Key Laboratory of Machine Learning and Computational Intelligence College of Mathematics and Information Science Hebei University Baoding071002 China

Classification problems in the real world are typically characterized by an imbalanced distribution, which poses a challenge to the induction of these labels. In this study, we analyze softmax cross-entropy (CE) and reasons for poor performance of models trained on imbalanced data using cross entropy from a mathematical point of view. Then, we provide a novel explanation for the model’s poor performance on imbalanced data. In particular, the model’s poor performance on imbalanced data is related to CE limitation, which results in the insufficiently compact intraclass features of the trained model and its poor feature extraction ability. We have analyzed the causes of imbalanced problems from a mathematical point of view as well as proposed class prototype angle and class prototype cosine losses, along with new strategies to address these challenges. These two losses improve the model’s performance by increasing the angle interval between classes and focusing on difficult samples of minority classes, thus improving the feature extraction ability of minority classes. The experiment on the datasets is completely consistent with our theoretical view and confirms the superior performance of our method, effectively alleviating the problem of data overfitting. © 2023, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Instance selection for big data based on locally sensitive hashing and double-voting mechanism

引用

Advances in computational intelligence 2022年第2期2卷 1-10页

作者： Zhai, Junhai Huang, Yajie Hebei Key Laboratory of Machine Learning and Computational Intelligence College of Mathematics and Information Science Hebei University Baoding China

The increasing data volumes impose unprecedented challenges to traditional data mining in data preprocessing, learning, and analyzing, it has attracted much attention in designing efficient compressing, indexing and searching methods recently. Inspired by locally sensitive hashing (LSH), divide-and-conquer strategy, and double-voting mechanism, we proposed an iterative instance selection algorithm, which needs to run p rounds iteratively to reduce or eliminate the unwanted bias of the optimal solution by double-voting. In each iteration, the proposed algorithm partitions the big dataset into several subsets and distributes them to different computing nodes. In each node, the instances in local data subset are transformed into Hamming space by l hash function in parallel, and each instance is assigned to one of the l hash tables by the corresponding hash code, the instances with the same hash code are put into the same bucket. And then, a proportion of instances are randomly selected from each hash bucket in each hash table, and a subset is obtained. Thus, totally l subsets are obtained, which are used for voting to select the locally optimal instance subset. The process is repeated p times to obtain p subsets. Finally, the globally optimal instance subset is obtained by voting with the p subsets. The proposed algorithm is implemented with two open source big data platforms, Hadoop and Spark, and experimentally compared with three state-of-the-art methods on testing accuracy, compression ratio, and running time. The experimental results demonstrate that the proposed algorithm provides excellent performance and outperforms three baseline methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Nonlinear dynamics of a classical rotating pendulum system with multiple excitations

引用

Chinese Physics B 2020年第11期29卷 230-243页

作者： Ning Han Pei-Pei Lu Key Laboratory of Machine Learning and Computational Intelligence College of Mathematics and Information ScienceHebei UniversityBaoding 071002China

We report an attempt to reveal the nonlinear dynamic behavior of a classical rotating pendulum system subjected to combined excitations of constant force and periodic *** unperturbed system characterized by strong irrational nonlinearity bears significant similarities to the coupling of a simple pendulum and a smooth and discontinuous(SD)oscillator,especially the phase trajectory with coexistence of Duffing-type and pendulum-type homoclinic *** order to learn the effect of constant force on this pendulum system,all types of phase portraits are displayed by means of the Hamiltonian function with large constant excitation especially the transitions of complex singular closed *** sufficiently small perturbations of the viscous damping and constant excitation,the Melnikov method is used to analyze the global structure of the phase space and the feature of *** is shown,both theoretically and numerically,that this system undergoes a homoclinic bifurcation and then bifurcates a unique attracting rotating limit ***,the estimation of the chaotic threshold of the rotating pendulum system with multiple excitations is calculated and the predicted periodic and chaotic motions can be shown by applying numerical simulations.

关键词： rotating pendulum Melnikov method rotating limit cycle chaotic dynamics

来源：评论

学校读者我要写书评

暂无评论

Research on location and similar comments in point-of-interest recommendation system for users

Research on location and similar comments in point-of-intere...

引用

2020 International Conference on Data Processing Algorithms and Models, ICDPAM 2020

作者： Liu, Yu Wei, Ning College of Mathematics and Information Science Hebei University Baoding Hebei071002 China Hebei Key Laboratory of Machine Learning and Computational Intelligence China

By combining deep learning algorithms and potential probabilistic topic models, this paper proposes a new modeling strategy for individual users and constructs an effective point of interest recommendation system. First, Doc2vec is used to vectorize the user's comments, and the Bow model is used to match the similarity of the points of interest, and then the potential probability model is used to cluster the positions of the points of interest. Finally, relying on the user's historical comment data as a basis, the Top-K ranking recommendation scheme is obtained. The experimental results show that for large-scale location-based social network data sets, the algorithm in this paper has an ideal final effect on users' personalized recommendations. The recommendation model for user location information and similar comment points of interest proposed in this paper is more subjectively and objectively in line with user behavior needs. On the premise of ensuring the real-time performance of recommendation, the model proposed in this paper effectively improves the accuracy of recommendation compared with traditional point-of-interest recommendation algorithms. © Published under licence by IOP Publishing Ltd.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

A Membership-Based Resampling and Cleaning Algorithm for Multi-Class Imbalanced Overlapping Data

SSRN

引用

SSRN 2022年

作者： Ma, Tingting Lu, Shuxia Jiang, Chen Hebei Province Key Laboratory of Machine Learning and Computational Intelligence College of Mathematics and Information Science Hebei University Baoding071002 China

Real-world datasets frequently have an imbalanced class distribution, which significantly degrades classification performance. However, some studies have suggested that the adverse effects of class imbalance occur only when datasets have other intrinsic characteristics (such as class overlap, noise, and data scarcity). Noise and class overlap have the greatest effect. To deal with other intrinsic characteristics that affect classification performance in a multi-class environment, such as class overlap, noise, and data scarcity, we propose a method that can directly handle multi-class overlapping data, called the membership-based multi-class resampling and cleaning (MC-MBRC) algorithm. The proposed method divides samples into safe, overlapping, and noisy areas based on their membership degrees, and then according to the influence of the samples in each area on classification performance, it performs various operations such as noise removal, interpolation oversampling, and energy-based cleaning of the overlapping region. An extensive comparison using various datasets shows that, compared with state-of-the-art methods, the proposed method makes significant statistical improvements in different classification performance metrics and is robust to data containing class overlap and label noise. Furthermore, for datasets that do not have complex intrinsic features, MC-MBRC will not significantly degrade classification performance. © 2022, The Authors. All rights reserved.

关键词： Cleaning

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：