检索结果-内蒙古大学图书馆

Minimizing model size of CNN-based Vehicle Make Recognition for Frontal Vehicle Images

IEEE Access 2025年 13卷 97409-97420页

作者： Puisamlee, Wiput Chawuthai, Rathachai King Mongkut's Institute of Technology Ladkrabang School of Engineering Department of Electrical Engineering Bangkok Thailand King Mongkut's Institute of Technology Ladkrabang School of Engineering Department of Computer Engineering Bangkok Thailand

Vehicle Make Model Recognition (VMMR) is generally considered in any Intelligent Transport Systems (ITS), free flow image-based toll systems, and enforcement systems. These systems need to analyze and process any images of the front of vehicles as evidence of use. Currently, Convolutional Neural Networks (CNN) are well-known techniques for image classification research and they applied to solve problems in the VMMR domain. Increasing the accuracy of classification with a large number of classes requires more complex model structures and a greater number of internal parameters. It resulted in the issues larger models and potentially longer processing times. This work aims to study and develop a smaller CNN model that is suitable for devices with limited resources, such as embedded computers and embedded computer cameras, for recognizing vehicle makes from frontal images. The experimental datasets were collected from actual free-flow toll systems, and a CNN model was developed that achieved 99% accuracy in recognizing vehicle makes. The developed model is smaller than state-of-the-art CNN models tested (VGG16, InceptionV3, Yolo11m-cls, and ResNet50) and achieves over 90% accuracy. It was able to develop the CTv1 model to achieve an F1 score approximately 2.06% higher than the best one, which is InceptionV3, while reducing the number of parameters by 69.95%. The model was tested on a Raspberry Pi 3 Model B, where it processed images at the average speed of 1 second per image and a power consumption of 25 milliwatts-hour (mWh). Our study also reduces the CNN model size using Depth-wise Separable Convolutional and 1x1 Convolutional Dimension Reduction (Bottleneck) methods, as well as adjusting the Padding and Stride of the Convolutional Layer to test the accuracy, training time, processing time, and model size for vehicle make recognition. © 2013 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Biosignal Contrastive Representation Learning for Emotion Recognition of Game Users

引用

IEEE Transactions on Games 2024年第2期17卷 1-15页

作者： Li, Rongyang Ding, Jianguo Ning, Huansheng School of Computer and Communication Engineering University of Science and Technology Beijing China Department of Computer Science Blekinge Institute of Technology Karlskrona Sweden

Biosignal representation learning (BRL) plays a crucial role in emotion recognition for game users (ERGU). Unsupervised BRL has garnered attention considering the difficulty in obtaining ground truth emotion labels from game users. However, unsupervised BRL in ERGU faces challenges, including overfitting caused by limited data and performance degradation due to unbalanced sample distributions. Faced with the above challenges, we propose a novel method of biosignal contrastive representation learning (BCRL) for ERGU, which not only serves as a unified representation learning approach applicable to various modalities of biosignals but also derives generalized biosignals representations suitable for different downstream tasks. Specifically, we solve the overfitting by introducing perturbations at the embedding layer based on the projected gradient descent (PGD) adversarial attacks and develop the sample balancing strategy (SBS) to mitigate the negative impact of the unbalanced sample on the performance. Further, we have conducted comprehensive validation experiments on the public dataset, yielding the following key observations: 1) BCRL outperforms all other methods, achieving average accuracies of 76.67%, 71.83%, and 63.58% in 1D-2C Valence, 1D-2C Arousal and 2D-4C Valence/Arousal, respectively;2) The ablation study shows that both the PGD module (+7.58% in accuracy on average) and the SBS module (+14.60% in accuracy on average) have a positive effect on the performance of different classifications;3) BCRL model exhibits the certain generalization ability across the different games, subjects and classifiers. IEEE

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Fault Diagnosis Method Based on Transformer and CNN 7

A Hybrid Fault Diagnosis Method Based on Transformer and CNN

引用

7th International Symposium on Autonomous Systems, ISAS 2024

作者： Gao, Zhi He, Meixuan Zhang, Bangcheng Shao, Yubo Liu, Jingru Que, Shaohua Changchun University of Technology School of Mechatronic Engineering Changchun China Changchun University of Technology College of Computer Science and Engineering Changchun China Changchun University of Technology Faculty of Mechanical and Electrical Engineering Faculty of Mechanical and Electrical Engineering Changchun Institute of Technology Changchun China Faw Tooling Die Manufacturing Changchun China

ISBN: (纸本)9798350363173

The elevator data of the welding production line has significant timing characteristics. There are more normal data and less abnormal data. Therefore, it becomes more complicated to diagnose the abnormality of the welding production line hoisting system through data analysis. This paper proposes a hybrid fault diagnosis method that combines a Transformer with a convolutional neural network. Firstly, the Transformer is used to extract the long-range dependencies in the data and identify complex faults that may not be adjacent. Then, the convolutional neural network extracted local or spatial features from the data. Finally, the multilayer perceptron maps the extracted features to the output space. The model innovatively merges the Transformer's global context analysis with the convolutional neural network's local feature detection precision, boosting fault diagnosis accuracy and efficiency. The proposed hybrid model was applied to the actual vibration data set of the hoists condition monitoring system of the white welding production line, and the results were contrasted with those of the support vector machine method, the long short-term memory network method, and the back propagation neural network method. Experimental findings demonstrate that the hybrid model achieves an accuracy of 99.98%, which is suitable for the fault diagnosis of the driving end bearing of the body of the white welding production line. © 2024 IEEE.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Lightweight Rice Planthopper Identification Method Based on YOLOv5

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer Science 2024年第8期51卷 1079-1085页

作者： Li, Siquan Wang, Yi Shi, Teng Chen, Xi Tang, Zhen Zeng, Ziyu Wen, Xin Shang, Yanling School of Automation Nanjing Institute of Technology Nanjing211167 China School of Mechanical Engineering Nanjing Institute of Technology Nanjing211167 China School of Automation Nanjing Institute of Technology Nanjing211167 China School of Computer engineering Nanjing Institute of Technology Nanjing211167 China School of Automation Nanjing Institute of Technology Nanjing211167 China

The identification and classification of pests in rice field are the prerequisites of early warning systems for pest disasters. Among these pests, the rice planthoppers cause the most serious damage. However, the existing deep learning models for rice planthopper recognition are characterized by large size and numerous parameters, which makes them unsuitable for the deployment on embedded devices with limited computational resources. To address this issue, a lightweight rice planthopper recognition model based on YOLOv5 is proposed in this paper. In the model, a lightweight convolutional network named GhostNet is employed as the backbone to reduce the operational parameters. Additionally, a convolutional attention module (CBAM) is integrated into the backbone network to effectively enhance the transmission of deep information, so as to improve the model’s ability of recognizing rice planthopper images. The original CIoU loss function is replaced by the SIoU loss function to expedite model convergence. Experimental results demonstrate that the modified model achieves the mAP@0.5 as 82.8%, with the parameter count of 3.12×106 and the model size of 7.2MB. Compared to the original model, it is a reduction of 46.7% in size and 43.3% in parameters, with a minor accuracy loss of 0.1%. Clearly, the improved model can achieve lightweight characteristics and robust performance, and thus it provides a theoretical and practical foundation for early warning systems against rice planthopper infestations in rice fields. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

PIKGMA: PrIori Knowledge-Guided Multimodal Alignment and Domain Adaptation for Emotion Recognition 17

PIKGMA: PrIori Knowledge-Guided Multimodal Alignment and Dom...

引用

17th IEEE International Conference on computer Research and Development, ICCRD 2025

作者： Lin, Chenglin Lu, Huimin Ma, Songzhe Zhang, Zexing Qi, Guolian Wang, Yilong Changchun University of Technology School of Computer Science and Engineering Changchun China Changchun University of Technology School of Mathematics and Statistics Changchun China Changchun University of Technology The First Hospital of Jilin University School of Mathematics and Statistics Changchun China

ISBN: (纸本)9798331531881

Multimodal domain adaptive emotion recognition aims to utilize the feature information of multiple modalities to achieve cross-domain emotion recognition, and how to constrain the inconsistency between inner-domain and cross-domain modality properly has been a hot spot in research. To address the above challenges, we propose a priori knowledge-guided multimodal alignment domain adaptive emotion recognition model, PIKGMA. PIKGMA is a semi-supervised multimodal physiological signal domain adaptation model for emotion recognition. It aligns multimodal emotion features draw support from inner-domain modalities alignment and cross-domain modalities alignment. Meanwhile, to better utilize the priori knowledge from the source domain (the data distribution of the source domain), we propose the priori dual-Alignment bank strategy. The memory bank can be used to assist in cross-domain modality alignment and pseudo-label generation for domain adaptation. We conducted detailed experiments using two physiological signals on the DREAMER dataset, and the experimental results show that PIKGMA performs very well and is superior to existing methods. © 2025 IEEE.

关键词： Physiological models

来源：评论

学校读者我要写书评

暂无评论

Flying robot path planning techniques and its trends

引用

Materials Today: Proceedings 2023年 80卷 2187-2192页

作者： Maity, Ritu Mishra, Ruby Kumar Pattnaik, Prasant School of Mechanical Engineering Kalinga Institute of Industrial Technology India School of Computer Engineering Kalinga Institute of Industrial Technology India

A Flying robot is a system capable of vertical take-off and landing to perform some specific task with no direct human intervention. Flying robots are distinct from other robots by their ability to fly with no direct human control and are capable of making a decision based on the situation. Drones, Aerial robots, Unmanned Aerial Vehicles (UAV) are few examples of flying robots. Path determination of flying robots is one of the most critical aspects of robot Routing design. Path planning is a technique which tells flying robot how to fly, where to fly and to find a collision-free optimal path. Numerous techniques have been put forward over the past few years to find an optimal path for flying robots. This work discusses on new trends led by artificial intelligence and safe human-robot interaction for optimal path planning of aerial robots. Furthermore, a comprehensive study is carried out on various 2D and 3D path planning algorithms done to date and different algorithms are classified based on important criteria for optimal path planning for flying robots. © 2021

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Improved Algorithm Based Optimal Stitching Line in Video Stitching Quality 4

Improved Algorithm Based Optimal Stitching Line in Video Sti...

引用

4th International Conference on Electronic Information engineering and computer Science, EIECS 2024

作者： Bai, Xuemei Wang, Yunpeng Zhang, Chenjie Hu, Hanping School of Electronic Information Engineering Changchun University of Science and Technology Changchun130012 China School of Computer Science and Technology Changchun University of Science and Technology Changchun130012 China

ISBN: (纸本)9798331531409

For the optimisation of video splicing quality in video splicing, an improved optimal stitching video splicing method is proposed. The method first extracts corner points and feature points using the improved FAST algorithm, and accurately matches these feature points by combining violent matching with GMS feature point matching;adopts a graph cutbased algorithm to transform the stitch line search problem into an energy minimisation problem to ensure the reasonableness and optimality of the stitch line position;and constructs the solution step by step in overlapping regions by means of a dynamic planning algorithm, retaining the optimal solution at each step, and finally find the globally optimal suture position. To further enhance the suture quality, the method smoothes the sutures by morphological operations (e.g., swelling and erosion) and implements fine pixel-level adjustments to eliminate artefacts and chromatic aberrations. After determining the optimal overlap region and suture line location, an advanced image fusion algorithm is used to ensure that the transition of video frames in the overlap region is natural and seamless, avoiding splice marks. The experimental results show that the method can effectively improve the quality of video stitching. © 2024 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Predicting circRNA-Disease Associations by Using Multi-Biomolecular Networks Based on Variational Graph Auto-Encoder with Attention Mechanism

引用

Chinese Journal of Electronics 2024年第6期33卷 1526-1537页

作者： Jing YANG Xiujuan LEI Yi PAN School of Computer Science Shaanxi Normal University Faculty of Computer Science and Control Engineering Shenzhen Institute of Advanced TechnologyChinese Academy of Sciences Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced Technology

CircRNA-disease association(CDA) can provide a new direction for the treatment of diseases. However,traditional biological experiment is time-consuming and expensive, this urges us to propose the reliable computational model to predict the associations between circRNAs and diseases. And there is existing more and more evidence indicates that the combination of multi-biomolecular information can improve the prediction accuracy. We propose a novel computational model for CDA prediction named MBCDA, we collect the multi-biomolecular information including circRNA, disease, miRNA and lncRNA based on 6 databases, and construct three heterogeneous network among them, then the multi-heads graph attention networks are applied to these three networks to extract the features of circRNAs and diseases from different views, the obtained features are put into variational graph auto-encoder(VGAE) network to learn the latent distributions of the nodes, a fully connected neural network is adopted to further process the output of VGAE and uses sigmoid function to obtain the predicted probabilities of circRNA-disease *** a result, MBCDA achieved the values of AUC and AUPR under 5-fold cross-validation of 0.893 and 0.887. MBCDA was applied to the analysis of the top-25 predicted associations between circRNAs and diseases, these experimental results show that our proposed MBCDA is a powerful computational model for CDA prediction.

关键词： Knowledge engineering Attention mechanisms Computational modeling Biological system modeling Predictive models Feature extraction Heterogeneous networks Topology Data mining Diseases

来源：评论

学校读者我要写书评

暂无评论

Interstitial-oxygen-induced γ-phase precipitation and martensitic transformation behavior in Ni-Mn-Sn-Co alloy prepared through binder jetting and sintering

引用

材料科学技术（英文版） 2025年第11期214卷 272-277页

作者： Shijiang Zhong Mingfang Qian Xinxin Shen Shuhe Gong Liangbo Sun Ping Shen Xuexi Zhang Lin Geng Key Laboratory of Automobile Materials(Ministry of Education) School of Materials Science and EngineeringJilin UniversityChangchun 130025China School of Materials Science and Engineering Harbin Institute of TechnologyHarbin 150001China School of Materials Science and Engineering Harbin Institute of TechnologyHarbin 150001China Center of Analysis Measurement and ComputingHarbin Institute of TechnologyHarbin 150001China

*** Ni-Mn-X(X=Ga,In,Sn,or Sb)Heusler alloys have versatile properties[1-4],such as shape memory effect[1],superelastic-ity[5],magnetocaloric effect[3],elastocaloric effect[6],and even multicaloric effect[7],that indicate their potential for use in actu-ators,sensors,micropumps,energy harvesters,and solid-state re-frigeration[8-10].Among the alloys,Ni-Mn-Sn-based alloys are environment-friendly and cost-effective[6,7,11],and hence,they have received widespread attention.

关键词： binder through behavior oxygen phase alloy induced interstitial jetting martensitic

来源：评论

学校读者我要写书评

暂无评论

Online Convex Optimization with Switching Cost and Delayed Gradients

引用

Performance Evaluation Review 2024年第4期51卷 22-23页

作者： Senapati, Spandan Vaze, Rahul Department of Computer Science & Engineering Indian Institute of Technology Kanpur India School of Technology and Computer Science Tata Institute of Fundamental Research India

We consider the online convex optimization (OCO) problem with quadratic and linear switching cost when at time t only gradient information for functions fτ, τ 16(Lµ+5) for the quadratic switching cost, and also show the bound to be order-wise tight in terms of L, µ. In addition, we show that the competitive ratio of any online algorithm is at least max{Ω(L), Ω(pLµ )} when the switching cost is quadratic. For the linear switching cost, the competitive ratio of the OMGD algorithm is shown to depend on both the path length and the squared path length of the problem instance, in addition to L, µ, and is shown to be order-wise, the best competitive ratio any online algorithm can achieve. Copyright is held by author/owner(s).

关键词： Convex optimization

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：