检索结果-内蒙古大学图书馆

3D Object Detection Algorithm for Panoramic Images With multi-scale convolutional neural network

IEEE ACCESS 2019年 7卷 171461-171470页

作者： Wang, Dianwei He, Yanhui Liu, Ying Li, Daxiang Wu, Shiqian Qin, Yongrui Xu, Zhijie Xian Univ Posts & Telecommun Ctr Image & Informat Proc Sch Commun & Informat Engn Xian 710121 Peoples R China Wuhan Univ Sci & Technol Sch Informat Sci & Engn Wuhan 430081 Peoples R China Univ Huddersfield Sch Comp & Engn Huddersfield HD1 3DH W Yorkshire England

This paper addresses the challenge of 3D object detection from a single panoramic image under severe deformation. The advent of the two-stage approach has impelled significant progress in 3D object detection. However, most available methods only can localize region proposals by a single-scale architecture network, which are sensitive to deformation and distortion. To address this issue, we propose a multi-scale convolutional neural network (MSCNN) to estimate the 3D pose of an object. To be specific, the proposed MSCNN consists of three steps for effectively detecting the distorted object on the panoramic images. The MSCNN contains the CycleGAN network that converts rectilinear images into panoramas, a fused framework that improves both accuracy and speed for object detection, and an adversarial spatial transformer network (ASTN) that extracts the deformation features of the object on panoramic images. Additionally, we recover the 3D pose of the object using a coordinate projection and a 3D bounding box. Extensive experiments demonstrate that the proposed method can achieve a 3D detection accuracy of 38.7% in high-resolution panoramic images, which is higher than the current state-of-the-art algorithm of 5.2%. Moreover, the speed of detection is only about 0.6 seconds per image, which is six times faster than Faster R-CNN (COCO).

关键词： Object detection panoramic images multi-scale convolutional neural network 3D bounding box

来源：评论

学校读者我要写书评

暂无评论

Bearing Fault Diagnosis Based on Shallow multi-scale convolutional neural network with Attention

引用

ENERGIES 2019年第20期12卷 3937页

作者： Huang, Tengda Fu, Sheng Feng, Haonan Kuang, Jiafeng Beijing Univ Technol Inst Intelligent Monitoring & Diag Beijing 100124 Peoples R China

Recently, deep learning technology was successfully applied to mechanical fault diagnosis. The convolutional neural network (CNN), as a prevalent deep learning model, occupies a place in intelligent fault diagnosis, which reduces the need for human feature extraction and prior knowledge, thereby achieving an end-to-end intelligent fault diagnosis model. However, the data for mechanical fault diagnosis in practical application are limited, the CNN model is too deep and too complex, making it prone to overfitting, and a model with too simple a structure and shallow layers cannot fully learn the effective features of the data. convolutional filters with fixed window sizes are widely used in existing CNN models, which cannot flexibly select variable pivotal features. The model may be interfered with by redundant information in feature maps during training. Therefore, in this paper, a novel shallow multi-scale convolutional neural network with attention is proposed for bearing fault diagnosis. The shallow multi-scale convolutional neural network structure can fully learn the feature information of input data without overfitting. For the first time, a feature attention mechanism is developed for fault diagnosis to adaptively select features for classification more effectively, where the pivotal feature was emphasized, and the redundant feature was weakened through an attention mechanism. The time frequency representations as the input of the model were obtained from the vibration time domain signals, which contain the complete time domain and frequency domain information of the vibration signals. Compared with the current popular diagnostic methods, the results show that the proposed diagnostic method has fairly high accuracy, and its performance is superior to the existing methods. The average recognition accuracy was 99.86%, and the weak recognition rate of I-07 and I-14 labels was improved.

关键词： Bearing fault diagnosis multi-attention mechanism multi-scale convolutional neural network time frequency representation

来源：评论

学校读者我要写书评

暂无评论

Segmentation and multi-scale convolutional neural network-Based Classification of Airborne Laser Scanner Data

引用

SENSORS 2018年第10期18卷 3347-3347页

作者： Yang, Zhishuang Tan, Bo Pei, Huikun Jiang, Wanshou Wuhan Univ State Key Lab Informat Engn Surveying Mapping & R Wuhan 430010 Hubei Peoples R China Shenzhen Power Supply Co Ltd 2018 Cuizhu Rd Shenzhen 430079 Peoples R China

The classification of point clouds is a basic task in airborne laser scanning (ALS) point cloud processing. It is quite a challenge when facing complex observed scenes and irregular point distributions. In order to reduce the computational burden of the point-based classification method and improve the classification accuracy, we present a segmentation and multi-scale convolutional neural network-based classification method. Firstly, a three-step region-growing segmentation method was proposed to reduce both under-segmentation and over-segmentation. Then, a feature image generation method was used to transform the 3D neighborhood features of a point into a 2D image. Finally, feature images were treated as the input of a multi-scale convolutional neural network for training and testing tasks. In order to obtain performance comparisons with existing approaches, we evaluated our framework using the International Society for Photogrammetry and Remote Sensing Working Groups II/4 (ISPRS WG II/4) 3D labeling benchmark tests. The experiment result, which achieved 84.9% overall accuracy and 69.2% of average F1 scores, has a satisfactory performance over all participating approaches analyzed.

关键词： region growing segmentation multi-scale convolutional neural network ALS point clouds semantic 3D labeling feature image

来源：评论

学校读者我要写书评

暂无评论

Research on failure diagnosis analysis of plunger gas lift system using convolutional neural network with multi-scale channel attention mechanism based on wavelet transform

引用

CHEMICAL ENGINEERING SCIENCE 2025年 304卷

作者： Shi, Haowen Su, Yubin Pan, Yuan Zhang, Weihan Chen, Zhong Liao, Ruiquan Yangtze Univ Hubei Key Lab Drilling & Prod Engn Oil & Gas Wuhan 430100 Peoples R China Yangtze Univ Sch Petr Engn Wuhan 430100 Peoples R China Gas Lift Test Base CNPC Lab Multiphase Pipe Flow Wuhan 430100 Peoples R China Yangtze Univ Sch Informat & Math Jingzhou 434000 Peoples R China PetroChina Oil & Gas Technol Res Inst Changqing Oilfield Branch Co Xian 710021 Shaanxi Peoples R China Petrochina Dagang Oilfield Co Petr Engn Res Inst Tianjin 300280 Peoples R China China Petr & Chem Corp Zhongyuan Oilfield Branch Puyang 457000 Peoples R China

Plunger gas lift technology has been extensively utilized in unconventional gas fields, owing to its distinct engineering benefits. However, as development challenges intensify, fault diagnosis has grown more intricate, and conventional diagnostic techniques exhibit delays and inaccuracies. With advancements in computer science, machine learning methods have demonstrated their prowess in establishing robust correlations between data features and prediction outcomes. Consequently, this paper introduces a convolutional neural network fault diagnosis model that incorporates a multi-scale channel attention mechanism based on wavelet transform. This model dissects features across various scales using wavelet transform and leverages channel attention to adaptively select channels encompassing fault features, thereby enhancing diagnostic and recognition accuracy. Furthermore, the model integrates a hyperparameter search optimization algorithm to refine the model's architecture and comprehensively bolster its generalization capability. A comparison with actual field data reveals that the fault diagnosis accuracy of the WT-MACNN model stands at 83.33%. Digital ablation experiments underscore the limited accuracy of the basic CNN model in fault diagnosis, but the sequential introduction of the channel attention mechanism and wavelet transform layers significantly elevates model performance. When juxtaposed with SVM, KNN, and decision tree models, the WT-MACNN model exhibits a diagnostic accuracy improvement of 73.81%, 57.13%, and 54.76%, respectively. Additionally, to assess the model's adaptability under diverse well conditions, this study reacquired 128 sets of field data. The verification results indicate that the model's prediction accuracy across different well conditions is 83.59%. Despite occasional misjudgments among certain operating conditions, the overall performance remains outstanding, offering dependable support for diagnosing real-world scenarios. The outcomes

关键词： Plunger gas lift Diagnosis multi-scale convolutional neural network Wavelet Transform Channel Attention Mechanism

来源：评论

学校读者我要写书评

暂无评论

High-precision intrusion detection for cybersecurity communications based on multi-scale convolutional neural networks

引用

JOURNAL OF SUPERCOMPUTING 2025年第1期81卷 1-34页

作者： Yang, Hao Yu, Junyang Zhai, Rui Henan Univ Sch Software Kaifeng 475000 Henan Peoples R China

This study developed an advanced network intrusion detection system based on an improved multi-scale convolutional neural network architecture aimed at enhancing the accuracy of detecting network threats. By precisely capturing data features at different scales, this system significantly improves the model's ability to analyze complex network behaviors. The proposed system incorporates a novel data preprocessing method combining SMOTE and ENN techniques to address the class imbalance in datasets while resolving the overlap issue of minority and majority class samples present in the SMOTE algorithm. It also utilizes a novel feature selection approach combining Information Gain, Random Forest feature importance scoring, and Recursive Feature Elimination to optimize model performance and reduce computational load. Experiments conducted on public datasets CICIDS2017, KDDCUP99, and UNSW-NB15. The experimental results demonstrate that intrusion detection based on a multi-scale convolutional neural network exhibits high detection accuracy. Specifically, the accuracy on the KDDCUP99 and CICIDS2017 datasets all exceeded 99.85%, while on the UNSW-NB15 dataset surpassed 99.20%, indicating the method's ability to accurately identify network intrusions.

关键词： Intrusion detection system multi-scale convolutional neural network Feature selection Information gain Recursive feature elimination

来源：评论

学校读者我要写书评

暂无评论

Adaptive classification of artistic images using multi-scale convolutional neural networks

引用

PEERJ COMPUTER SCIENCE 2024年 10卷 e2336-e2336页

作者： Xiang, Jin Yang, Yi Bai, Junwei Wuhan Polytech Univ Sch Art & Design Wuhan Peoples R China Hubei Inst Fine Arts Sch Ind Design Wuhan Hubei Peoples R China

The current art image classification methods have low recall and accuracy rate issues . To improve the classification performance of art images, a new adaptive classification method is designed employing multi-scale convolutional neural networks (CNNs). Firstly, the multi-scale Retinex algorithm with color recovery is used to complete the enhancement processing of art images. Then the extreme pixel ratio is utilized to evaluate the image quality and obtain the art image that can be analyzed. Afterward, edge detection technology is implemented to extract the key features in the image and use them as initial values of the item to be trained in the classification model. Finally, a multi-scale convolutional neural network (CNN) is constructed by using extended convolutions, and the characteristics of each level network are set. The decision fusion method based on maximum output probability is employed to calculate different subclassifies' probabilities and determine the final category of an input image to realize the art image adaptive classification. The experimental results show that the proposed method can effectively improve the recall rate and precision rate of art images and obtain reliable image classification results.

关键词： multi-scale convolutional neural network Artistic images Image classification Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Research on Human Action Recognition Model Based on Computer Laplacian Matrix and convolutional neural network 6

Research on Human Action Recognition Model Based on Computer...

引用

2023 IEEE 6th International Conference on Information Systems and Computer Aided Education, ICISCAE 2023

作者： Pei, Yubo Zhang, Xiongzhi Nanyang Technological University School of Electrical and Electronic Engineering 50 Nanyang Ave Singapore639798 Singapore Zhengzhou University School of International College Zhengzhou450001 China

ISBN: (纸本)9798350313444

This project intends to study a new human action recognition system based on Laplacian matrix multi-scale convolutional neural network (MCNN) algorithm, in order to overcome the shortcomings of the action recognition process in the recognition system. Firstly, a de-correlation network architecture is established by using matrix transformation to solve the correlation problem. When the network performance is poor, it can replace the existing BN layer to standardize the data. Finally, the dual flow characteristics of time and space are integrated to realize the automatic recognition of human behavior. Comparative experiments were conducted on UCF101 and HMDB51, and the results showed that the algorithm proposed in this paper achieved accuracy of 83.22% and 79.41% for UCF101 and HMDB51, respectively. © 2023 IEEE.

关键词： Graph convolutional neural networks Human Action Recognition Laplacian Matrix multi-scale convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

EEG emotion recognition approach using multi-scale convolution and feature fusion

引用

VISUAL COMPUTER 2025年第6期41卷 4157-4169页

作者： Zhang, Yong Shan, Qingguo Chen, Wenyun Liu, Wenzhe Huzhou Univ Sch Informat Engn East 2nd Rd Huzhou 313000 Zhejiang Peoples R China

Electroencephalogram (EEG) signal has been widely applied in emotion recognition due to its objectivity and reflection of an individual's actual emotional state. However, current EEG-based emotion recognition methods still suffer from limitations such as single-feature extraction, missing local features, and low feature extraction rates, all of which affect emotion recognition accuracy. To address these challenges, we propose an EEG emotion recognition approach based on multi-scale convolution and feature fusion, aimed at integrating low-dimensional and high-dimensional EEG features to enhance classification performance. The proposed approach first extracts multi-scale features of EEG using a multi-scale convolutional neural network. Subsequently, it employs the convolutional block attention module to further refine the obtained multi-scale features, highlighting emotion-related high-quality features while suppressing unimportant features. Finally, emotion-related time series are extracted by long short-term memory (LSTM) networks to achieve time-space-frequency feature fusion of EEG. We conducted fivefold cross-validation on the DEAP and SEED datasets to demonstrate the effectiveness of the proposed approach. For the DEAP dataset, the proposed approach achieved average accuracies of 97.48% and 97.75% for valence and arousal dimensions, respectively, and 96.98% for the SEED dataset, outperforming other models in terms of recognition accuracy.

关键词： Attention mechanism Electroencephalogram Emotion recognition Long short-term memory network multi-scale convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

A new adaptive multi-scale attention adversarial network for cross-domain fault diagnosis

引用

KNOWLEDGE-BASED SYSTEMS 2025年 311卷

作者： Kong, Lingtan Wang, Jinrui Wang, Dawei Bao, Huaiqian Zhang, Zongzhen Han, Baokun Man, Xuhao Qin, Ranran Yang, Xiaoli Shandong Univ Sci & Technol Coll Mech & Elect Engn Qingdao 266000 Peoples R China Rizhao Emergency Management Bureaua Rizhao 276800 Peoples R China

The fault diagnosis of rotating components such as bearings and gearboxes is crucial for ensuring the safe operation of machinery. However, traditional deep learning diagnostic models often exhibit poor performance when facing changes in operating conditions. To address this issue, this paper proposes an adaptive multi-scale attention adversarial network (AMSAAN). First, a combination of one-dimensional (1-D) wide convolution and two-dimensional (2-D) multi-scale convolution is employed to extract long-term temporal features and shortterm multi-scale features from the samples. Second, to reduce the impact of noise, a multi-layer attention feature refinement mechanism is utilized to progressively refine the extracted features layer by layer. Cross- domain adaptation is carried out in two parts: domain shift reduction and feature alignment. The first part uses a dual-domain distance approach combining correlation alignment (CORAL) distance and Wasserstein distance to reduce domain distribution differences. The second part integrates contrastive loss and domain adversarial mechanisms to achieve domain feature alignment. This method comprehensively considers both supervised domain adaptation (SDA) and unsupervised domain adaptation (UDA). The proposed AMSAAN effectively extracts domain-invariant features, reduces noise impact, and achieves domain adaptation. The effectiveness of AMSAAN is demonstrated through experimental results based on two datasets of bearings and planetary gearboxes. AMSAAN achieves a diagnostic accuracy of over 97 % across multiple transfer tasks under varying operating conditions, and the noise resistance of the model has been demonstrated to be superior to that of other methods.

关键词： multi-scale convolutional neural network multi-layer attention mechanism Joint cross-domain adaptation Fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

Adaptive multi-domain capacity estimation for battery energy storage system based on multi-scale random sequence feature fusion

引用

ENERGY 2025年 319卷

作者： Wang, Zuolu Zhao, Xiaoyu Han, Te Zhu, Yanzheng Gu, Fengshou Ball, Andrew Shandong Univ Sci & Technol Coll Elect Engn & Automat Qingdao 266590 Peoples R China Univ Huddersfield Ctr Efficiency & Performance Engn Huddersfield HD1 3DH England Beijing Inst Technol Sch Management Beijing 100081 Peoples R China

Monitoring battery capacity degradation in lithium-ion battery energy storage systems (BESSs) is crucial for ensuring safe and reliable operations. However, conventional data-driven methods primarily focus on single- domain estimation and feature engineering from fixed charging/discharging stages, limiting their adaptability in real-world scenarios. Therefore, this paper proposes an adaptive multi-domain capacity estimation method for BESSs based on multi-scale random sequence feature fusion. Firstly, this paper proposes the adaptive multi- domain capacity estimation theory, which utilizes the Pearson correlation coefficient (PCC) for health feature screening and maximum mean discrepancy (MMD) for domain discrepancy identification and domain classification. Secondly, an optimal random sequence feature is proposed based on short-duration raw voltage and incremental capacity, considering the effects of both sampling interval and duration. Subsequently, a multi-scale convolutional neural network (MSCNN) is developed to fuse ageing information from the random sequence feature and enable accurate adaptive multi-domain capacity estimation. Finally, the validation is conducted using 130 batteries operating under various working conditions, and it shows the proposed method is more robust compared to the single-domain estimation. The overall RMSE and MAE are reduced to within 1.53 % and 1.18 %, with the overall R2 value up to 99 %. This demonstrates the superiority of the proposed method for real- world applications.

关键词： Battery energy storage system multi-domain capacity estimation Random sequence feature fusion multi-scale convolutional neural network

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：