检索结果-内蒙古大学图书馆

IEEE International Conference on Real-time Computing and Robotics (RCAR)

作者： Kai Li Kun Qian Rui Liu Fang Fang Hai Yu Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing China State Grid Corporation of China Global Energy Interc onnection Research Institute Company Ltd Nanjing China

ISBN: (数字)9781728172934

ISBN: (纸本)9781728172941

Semantic information of objects and environment is a basis for robots to effectively complete complicated tasks. However, scene recognition methods based on image descriptors or convolutional neural networks often have misclassifications in actual environment. One reason is that highly complex environment has inconspicuous physical boundaries. In this paper, we propose a regional semantic learning method based on convolutional neural networks (CNNs) and conditional random fields (CRFs). The method combines global information obtained by scene classification network and local object information obtained by object detection network to train a CRF scene recognition model. Then the model can be used to infer the semantics of the region. After that, the regional semantic information is applied to build a sparse semantic map based on ORB-SLAM2. The proposed method was tested on a self-built environment dataset which contains four regional categories. Experimental results have demonstrated that the proposed method is effective and can obtain better classification results.

关键词： Feature extraction Semantics Erbium Training Three-dimensional displays Robots Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Biologically inspired information integration pooling module of spiking neural networks for rolling bearing fault diagnosis

引用

Expert systems with Applications 2025年 286卷

作者： Shi, Mingfei Jiang, Feng Li, Yongbo Du, Lin MIIT Key Laboratory of Dynamics and Control of Complex Systems Northwestern Polytechnical University Xi'an710072 China Unmanned System Research Institute Northwestern Polytechnical University Xi'an710072 China School of Mechanics Civil Engineering and Architecture Northwestern Polytechnical University Xi'an710072 China School of Aeronautics Northwestern Polytechnical University Xi'an710072 China School of Mathematics and Statics Northwestern Polytechnical University Xi'an710072 China MOE Key Laboratory for Complexity Science in Aerospace Northwestern Polytechnical University Xi'an710072 China

Rolling bearings constitute critical components in mechanical systems, and their effective fault diagnosis plays a vital role in ensuring operational safety and reliability. Despite substantial advancements in diagnostic methodologies, achieving high-precision, low-latency fault detection in large-scale rolling bearing datasets remains a persistent challenge. Artificial neural networks to spiking neural networks (ANN-to-SNN) conversion algorithms offer promising solutions for reducing computational costs and hardware adaptation barriers compared to conventional approaches. However, inherent information degradation during conversion processes has been demonstrated to significantly undermine model performance in terms of accuracy, stability, and interpretability. To overcome these limitations, we propose IIPooling, a novel Information-Integration biological neural mechanism-inspired Pooling module designed to enhance global structural feature extraction. The proposed framework incorporates three core neurobiological information processing principles: (1) promotion, (2) lateral inhibition, and (3) longitudinal inhibition, effectively simulating biological neuronal spiking patterns while optimally utilizing ANN activation characteristics. Additionally, we develop two adaptive learning mechanisms — Surrogate Gradient Adaptive Learning and Spiking Spatiotemporal Adaptive Learning — to implement negative feedback mechanism and adaptive parameter adjustment, thereby improving cross-conditional generalization capabilities. Comprehensive evaluations conducted on five bearing datasets (CWRU: DE/FE, PU, and Lab-collected: 6025/N205EW) demonstrate superior performance across four metrics (ACC, AUC, AUPRC, Mean-ACC). Our method achieves state-of-the-art results, notably attaining ACC values of 0.959 (CWRU-DE) and 0.861 (Lab-N205EW) in IIPooling-ST configurations, confirming its effectiveness for real-time, high-accuracy fault detection in complex operational environments. © 2025

关键词： Failure rate

来源：评论

学校读者我要写书评

暂无评论

Nonsingular Terminal Sliding Mode control for Fuel Quantity Actuator System Using High-order Sliding Mode Observer

Nonsingular Terminal Sliding Mode Control for Fuel Quantity ...

引用

第三十八届中国控制会议

作者： Jianpei Hu Hao Sun Shihua Li School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education

Fuel quantity actuator can directly control fuel injection quantity of the diesel engine, so it is the main component of the electronic distribution pump. In this paper, a position tracking problem for fuel quantity actuator system under the influence of disturbances and system uncertainties is studied via a high-order sliding mode observer(HOSMO) based nonsingular terminal sliding mode control(NTSMC) approach. The proposed finite-time NTSMC method integrates the lumped disturbance estimation information estimated by the HOSMO into the designed control law, and realizes the finite time tracking performance under the influence of disturbances and uncertainties. The simulation results show the effectiveness of the proposed method.

关键词： Lumped Disturbances Fuel Quantity Actuator Non-singular Terminal Sliding Mode control(NTSMC) High-order Sliding Mode Observer(HOSMO)

来源：评论

学校读者我要写书评

暂无评论

Smoky Vehicle Detection Algorithm Based On Improved Transfer Learning

Smoky Vehicle Detection Algorithm Based On Improved Transfer...

引用

International Conference on systems and Informatics (ICSAI)

作者： Guangming Zhang Dexiong Zhang Xiaobo Lu Yichao Cao Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China

ISBN: (数字)9781728152561

ISBN: (纸本)9781728152578

With the demand for pollution prevention has increased. Establishing a smoky vehicle inspection and evidence collection system will help to supervise the problem of excessive emissions of vehicles. Because the sample in the training data set is insufficient and unbalanced, the existing methods cannot obtain sufficient classification accuracy in the classification task of the smoky vehicle. This paper uses the transfer learning method to compare the effects of smoky car classification tasks on the five basic networks of DenseNet, NasNet, Inception, VGG19, MobileNet. In addition, for the classification task of the smoke vehicle, it is necessary to consider both the global information of the tail of the vehicle and the detailed information of the smoke area. In this paper, the global average pooling layer is changed to the spatial pyramid pooling layer, and it has achieved better results. Finally, the classification Precision nearly 0.1, Recall 0.3 are obtained, which is much better than the traditional classification method and the shallow non-transfer deep learning method.

关键词： Informatics

来源：评论

学校读者我要写书评

暂无评论

Identity Recognition Based on Face Image 4

Identity Recognition Based on Face Image

引用

2019 4th Annual International Conference on Information System and Artificial Intelligence, ISAI 2019

作者： Qin, Chen Lu, Xiaobo Zhang, Pengguo Xie, Huibin Zeng, Wenbin School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China Zhejiang Uniview Technologies Co. Ltd Zhejiang310018 China

This article is aimed at designing a human identity recognition algorithm based on face image, which will be used in indoor environment. As the working environment is set as indoor environment, the camera will not be affected much by illumination variation. The key is how to detect human face and handle the variation of facial pose. This article divides the whole recognition process into 4 parts: image pre-processing, face detection, face alignment, feature extraction and comparison. Face detection and feature extraction are the core functions and both realized by deep learning. The process of the whole algorithm can be described as following: images after pre-processing are fed to face detection network to get the locations of face and face landmarks. Then face alignment will be conducted. Finally, deep features of face will be extracted and compared. The unique features of this algorithm are its good performance of handling the variation of facial pose and its clear framework which allows the whole method can be easily adjusted and upgraded. © 2019 Published under licence by IOP Publishing Ltd.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Adaptive Multiscale Illumination-Invariant Feature Representation for Undersampled Face Recognition

arXiv

引用

arXiv 2020年

作者： Zhang, Yang Hu, Changhui Lu, Xiaobo School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China School of Automation Nanjing University of Posts and Telecommunications Nanjing210023 China

This paper presents an novel illumination-invariant feature representation approach used to eliminate the varying illumination affection in undersampled face recognition. Firstly, a new illumination level classification technique based on Singular Value Decomposition (SVD) is proposed to judge the illumination level of input image. Secondly, we construct the logarithm edgemaps feature (LEF) based on lambertian model and local near neighbor feature of the face image, applying to local region within multiple scales. Then, the illumination level is referenced to construct the high performance LEF as well realize adaptive fusion for multiple scales LEFs for the face image, performing JLEF-feature. In addition, the constrain operation is used to remove the useless high-frequency interference, disentangling useful facial feature edges and constructing AJLEF-face. Finally, the effects of the our methods and other state-of-the-art algorithms including deep learning methods are tested on Extended Yale B, CMU PIE, AR as well as our Self-build Driver database (SDB). The experimental results demonstrate that the JLEF-feature and AJLEF-face outperform other related approaches for undersampled face recognition under varying illumination. keywords: Undersampled face recognition, Singular value decomposition, Multiple scales edgemaps, Illumination-invariant feature extraction Copyright © 2020, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Driver action recognition based on attention mechanism 6

Driver action recognition based on attention mechanism

引用

6th International Conference on systems and Informatics, ICSAI 2019

作者： Wang, Wenhao Lu, Xiaobo Zhang, Pengguo Xie, Huibin Zeng, Wenbin School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China Zhejiang Uniview Technologies Co. Ltd Hangzhou310018 China

ISBN: (纸本)9781728152561

According to the world health organization, millions of people are killed by traffic accidents worldwide every year, and more than 80 percent of accidents are caused by unsafe driving. This paper studies driver behavior recognition, aiming to standardize driver's driving behavior and reduce the probability of traffic accidents. However, the inter-class variance of drivers' different actions is small, making it difficult to identify. To improve fine-grained identification, an attention module is designed to be inserted into convolutional neural network, which consists of two parallel parts: channel level attention and space level attention. The introduction of attention mechanism can focus the weight of the network on the meaningful pixels and channels, promote the expression of effective features, and suppress the interference of noise. The experiments show that the recognition accuracy is improved after applying attention mechanism. The visualization results show that the introduction of attention mechanism can make the network focus on the prominent areas of the feature map. © 2019 IEEE.

关键词： Behavioral research

来源：评论

学校读者我要写书评

暂无评论

Sensing With Random Communication Signals

arXiv

引用

arXiv 2025年

作者： Lu, Shihang Liu, Fan Xiong, Yifeng Du, Zhen Cui, Yuanhao Li, Shuangyang Yuan, Weijie Yang, Jie Jin, Shi National Mobile Communications Research Laboratory Southeast University Nanjing210096 China School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China School of Electronic and Information Engineering Nanjing University of Information Science and Technology Nanjing210044 China Faculty of Electrical Engineering and Computer Science Technical University of Berlin Berlin10587 Germany Southern University of Science and Technology Shenzhen518055 China Frontiers Science Center for Mobile Information Communication and Security and also The Key Laboratory of Measurement and Control of Complex Systems of Engineering Southeast University Nanjing211189 China

Communication-centric Integrated Sensing and Communication (ISAC) has been recognized as a promising methodology to implement wireless sensing functionality over existing network architectures, due to its cost-effectiveness and backward compatibility to legacy cellular systems. However, the inherent randomness of the communication signal may incur huge fluctuations in sensing capabilities, leading to unfavorable detection and estimation performance. To address this issue, we elaborate on random ISAC signal processing methods in this article, aiming at improving the sensing performance without unduly deteriorating the communication functionality. Specifically, we commence by discussing the fundamentals of sensing with random communication signals, including the performance metrics and optimal ranging waveforms. Building on these concepts, we then present a general framework for random ISAC signal transmission, followed by an in-depth exploration of time-domain pulse shaping, frequency-domain constellation shaping, and spatial-domain precoding methods. We provide a comprehensive overview of each of these topics, including models, results, and design guidelines. Finally, we conclude this article by identifying several promising research directions for random ISAC signal transmission. © 2025, CC BY-SA.

关键词： Signaling

来源：评论

学校读者我要写书评

暂无评论

Fire Detection based on Convolutional Neural Networks with Channel Attention

Fire Detection based on Convolutional Neural Networks with C...

引用

Chinese Automation Congress (CAC)

作者： Xiaobo Zhang Kun Qian Kaihe Jing Jianwei Yang Hai Yu School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education of China Future Science & Technology Park Beijing China Global Energy Interconnection Research Institute State Grid Nanjing China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

The existing research on fire detection is basically based on a two-stage method, resulting in slower detection speed, and the positioning accuracy is limited by the first-stage candidate region extraction algorithm. In order to solve the problem of high-precision real-time fire detection, this paper proposes a Yolo detection network combined with attention mechanism. The attention module is serially added to the final three convolutional networks of different scales of Yolo v3. The channel attention module updates the feature map by weighting and summing all channels, which captures the semantic dependencies between channels in the deep layers of the network, and improves the generalization ability of the model. Experiments show that the method proposed in this paper improves the accuracy of fire detection without reducing the detection speed.

关键词： Fires Semantics Feature extraction Annotations Image color analysis Deep learning Cameras

来源：评论

学校读者我要写书评

暂无评论

A Driver Fatigue Recognition Algorithm Based on Spatio-Temporal Feature Sequence 12

A Driver Fatigue Recognition Algorithm Based on Spatio-Tempo...

引用

12th International Congress on Image and Signal Processing, BioMedical engineering and Informatics, CISP-BMEI 2019

作者： Zhang, Chen Lu, Xiaobo Huang, Zhiliang Xia, Shudong Fu, Changqing School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China Beijing PKU TransInfo Technology Co. Ltd Beijing100193 China

ISBN: (纸本)9781728148526

Researches show that fatigue driving is one of the important causes of road traffic accidents, so it is of great significance to study the driver fatigue recognition algorithm to improve road traffic safety. In recent years, with the development of deep learning, the field of pattern recognition has made great development. This paper designs a real-time fatigue state recognition algorithm based on spatio-temporal feature sequence, which can be mainly applied to the scene of fatigue driving recognition. The algorithm is divided into three task networks: face detection network, facial landmark detection and head pose estimation network, fatigue recognition network. Experiments show that the algorithm has the advantages of small volume, high speed and high accuracy. © 2019 IEEE.

关键词： Face 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：