检索结果-内蒙古大学图书馆

Hemodynamic Analysis and Diagnosis Based on Multi-Deep Learning Models

Fluid Dynamics & Materials Processing 2023年第6期19卷 1369-1383页

作者： Xing Deng Feipeng Da Haijian Shao School of Automation Key Laboratory of Measurement and Control for CSEMinistry of EducationSoutheast UniversityNanjing210096China School of Computer Jiangsu University of Science and TechnologyZhenjiang212003China Department of Electrical and Computer Engineering University of NevadaLas Vegas89154USA

This study employs nine distinct deep learning models to categorize 12,444 blood cell images and automatically extract from them relevant information with an accuracy that is beyond that achievable with traditional *** work is intended to improve current methods for the assessment of human health through measurement of the distribution of four types of blood cells,namely,eosinophils,neutrophils,monocytes,and lymphocytes,known for their relationship with human body damage,inflammatory regions,and organ illnesses,in particular,and with the health of the immune system and other hazards,such as cardiovascular disease or infections,more in *** results of the experiments show that the deep learning models can automatically extract features from the blood cell images and properly classify them with an accuracy of 98%,97%,and 89%,respectively,with regard to the training,verification,and testing of the corresponding datasets.

关键词： Blood cell analysis deep learning models classification-detection

来源：评论

学校读者我要写书评

暂无评论

Short Term Inbound Passenger Flow Prediction of Urban Rail Transit Based on Data Denoising

Short Term Inbound Passenger Flow Prediction of Urban Rail T...

引用

2023 International Conference on Smart Transportation and City engineering, STCE 2023

作者： Wang, Zhijian Li, Qingyun Wang, Jiuzeng Zhang, Qiang Wei, Yaoquan School of Electrical and Control Engineering North China University of Technology Beijing100144 China Tangshan Expressway Group Co. Ltd. Tangshan063000 China Beijing Aerospace Measurement & Control Technology Co. Ltd. Beijing100041 China

ISBN: (纸本)9781510673540

In order to improve the accuracy of short-term traffic flow prediction, a combined prediction model based on Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Seagull Optimization Algorithm optimized Long-Short Term Memory neural network (SOA-LSTM) was proposed. Firstly, CEEMDAN is used to reduce the interference of data noise, decompose the original passenger flow sequence into multiple characteristic components and residual, and optimize the hyperparameters of the LSTM neural network using SOA. Each feature component is predicted, and the prediction results of each IMFs are summed to obtain the short-term entrance and exit passenger flow prediction results of each station. Extracting four consecutive weeks inbound passenger flow data of Beijing's urban rail transit network in 2019, and validated and compared the proposed short-term passenger flow prediction model. The experimental results demonstrate that compared with the transfer passenger flow prediction results of LSTM, ARIMA-RBF, LSTM-BP, and SOA-LSTM models, the proposed CEEMDAN-SOA-LSTM model has lower RMSE, MAE, and MAPE error values than other models, with R2 increased by 1.63%, 1.2%, 1.18%, and 0.72%, respectively. © 2024 SPIE.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

engineering Vehicle Recognition and Multi-Object Tracking System based on YOLOv5 and DeepSort Algorithm 5

Engineering Vehicle Recognition and Multi-Object Tracking Sy...

引用

5th International Conference on Video, Signal and Image Processing, VSIP 2023

作者： Wu, Yanbo Liang, Xintao Cui, Quan Wang, Qingyan Heilongjiang Government Affairs Big Data Center Harbin150028 China School Of Measurement And Control Technology And Telecommunications Engineering Harbin University Of Science And Technology Harbin150080 China

ISBN: (纸本)9798400709272

This study explores traditional object detection algorithms and deep neural network-based engineering vehicle detection algorithms. We applied preprocessing algorithms such as image denoising, enhancement, and edge detection to process the images and constructed our own trainable dataset through labeling. Next, we used the YOLOv5 algorithm, which has high detection accuracy and real-time capability, for engineering vehicle detection. To address the issues of missed targets and predicted bounding box misalignment, we introduced the DeepSORT algorithm for target prediction and tracking. This algorithm utilizes Kalman filtering for estimation and updates and employs the Hungarian algorithm to associate data between consecutive frames, thereby achieving engineering vehicle tracking. To tackle the problem of frequent identity switching due to camera motion and non-uniform vehicle movements, we adopted the modified GIoU to calculate the intersection over union between trajectories and detected target bounding boxes, reducing identity jumps during the tracking process. Finally, we designed an engineering vehicle detection and tracking system and applied this algorithm to practical production. © 2023 Owner/Author.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Based UAV Secure Transmission with Integrated Sensing and Communication

Deep Reinforcement Learning Based UAV Secure Transmission wi...

引用

2024 International Conference on Automation control, Algorithm, and Intelligent Bionics, ACAIB 2024

作者： Dong, Runze Wang, Buhong Chen, Guirong Cao, Kunrui Cheng, Tianhao Diao, Danyu School of Information and Navigation Air Force Engineering University Xi’an710077 China School of Information and Communications National University of Defense Technology Wuhan430035 China School of Air Traffic Control and Navigation Air Force Engineering University Xi’an710043 China

ISBN: (纸本)9781510682597

Due to its capacities in improving spectrum efficiency, reducing hardware cost, and accelerating signal processing, the integrated sensing and communication (ISAC) has been widely discussed and investigated in recent years. In this paper the secure downlink transmission of a unmanned aerial vehicle (UAV) communication network is considered, in which the terrestrial base station performs ISAC to sensing multiple targets. Aiming at maximizing the average secrecy rate (ASR) while ensuring the sensing performance is higher that a specific threshold, the trajectory of the legitimate UAV and the transmit beamforming of the base station are jointly optimized. Since the considered ASR maximization problem is non-convex, we resort to the state-of-the-art deep reinforcement learning (DRL) based algorithms. Firstly the optimization problem is transformed into a Markov decision process (MDP), then the UAV trajectory as well as the base station beamforming are jointly optimized. Simulation results demonstrate the effectiveness of the proposed algorithm and validate the superiority compared with benchmark methods. © 2024 SPIE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Research on hyperspectral image classification based on improved deep cross-domain few-shot learning 23

Research on hyperspectral image classification based on impr...

引用

Proceedings of the 2023 5th International Conference on Video, Signal and Image Processing

作者： Xinhua Luo Qingyan Wang Xintao Liang Zhen Zhang School of Measurement-Control and Communication Engineering Harbin University of Science and Technology China

ISBN: (纸本)9798400709272

In this study, an enhanced method and system for hyperspectral image classification are presented, based on deep cross-scene few-shot learning. This pertains to the domain of remote sensing image processing technology and addresses the prevalent issues of inadequate classification performance in existing techniques for hyperspectral image categorization. The core aspects of this invention encompass the following: utilization of two mapping layers to standardize the input dimensions between the source and target domains; the deployment of an embedded feature extractor to incorporate the image cubes from both the source and target domains into a space-spectral embedding environment simultaneously, ensuring that like samples are closely aligned and dissimilar ones are distanced. Through gauging the distances between each class of unlabeled and labeled samples in this space-spectral embedding zone, learning with a few number of examples in both the source and target domains is achieved. Furthermore, a conditional domain discriminator is employed to mitigate domain shifts between domains, thus solidifying the domain stability of the extracted spatial-spectral embedding features. This innovative approach allows for high-precision hyperspectral data categorization, even when only a few examples are available.

关键词： Hyperspectral image cross-scene few-shot learning

来源：评论

学校读者我要写书评

暂无评论

Network Intrusion Detection Based on Graph Neural Network and Ensemble Learning

Network Intrusion Detection Based on Graph Neural Network an...

引用

2023 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes, SAFEPROCESS 2023

作者： Zhang, Lina Wang, Yang Wu, Minyue Wang, Yanwei Zheng, Ying Huazhong University of Science and Technology The Belt and Road Joint Laboratory on Measurement and Control Technology School of Artificial Intelligence and Automation Wuhan430074 China Wuhan Institute of Technology School of Mechanical & Electrical Engineering Wuhan430073 China

ISBN: (纸本)9798350337754

Network technology has become an inseparable part of daily life, which is easily attacked by some criminals. Therefore, ensuring the security of network becomes an urgent problem. In the past few years, various deep learning techniques have been put forward for identifying network intrusions. However, the majority of these approaches overlook the non-Euclidean nature of relationships within network intrusion data. In this paper, graph neural network (GNN) is used to learn the relationship between data. The sample balancing module is to address the significant disparity between the number of intrusive samples and normal samples. The results obtained from the experiments indicate that the suggested approach can enhance the effectiveness of the intrusion detection system. © 2023 IEEE.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Ultrahigh electrochemical performance in mixed-valence Cu_(1.85)Sebased anode for supercapacitors

引用

Journal of Materiomics 2023年第1期9卷 62-71页

作者： Zhipeng Li Yi Niu Xinrui He Yalin Hu Fu Li Xing Chen Zhirong Wang Jing Jiang Chao Wang School of Electronic Science and Engineering University of Electronic Science and Technology of ChinaChengdu611731China State Key Laboratory of Precision Measurement Technology and Instruments Department of Precision InstrumentTsinghua UniversityBeijing100084China Jiangsu Key Laboratory of Hazardous Chemicals Safety and Control College of Safety Science and EngineeringNanjing Tech UniversityNanjing210009China

Mixed-valence is an effective way to achieve high electrochemical performance of anodes for ***,inordinate mixed valence with more structural defects leads to structural *** development of mixed valence electrodes that can maintain a stable structure during the defect formation process is the key to resolving this ***_(2-x)Se with mixed-valence is a potential candidate,the stable monoclinic structure of Cu2Se can be transformed into another stable cubic structure(x>0.15).Herein,Cu_(1.85)Se anode with mixed valence reveals the ultrahigh specific capacity of 247.8 mA·h/g at 2 A/***,the introduction of multi-walled carbon nanotubes(MWCNTs)into Cu1.85Se further improves the specific capacity(435 mA·h/g at 2 A/g).XRD shows that the introduction of MWCNTs can improve the reversibility via chemical interactions and accelerate the electron transfer in the Cu1.85Se/***,the assembled symmetric supercapacitor(SC)device expresses a high energy density of 41.4 W·h/kg,and the capacity remains 83%even after 8000 charge/discharge *** research demonstrates the great potential of developing high specific capacity anode materials for superior performance supercapacitor.

关键词： Supercapacitor Mixed-valence Cu1.85Se/MWCNTs Anode Ultrahigh specific capacity

来源：评论

学校读者我要写书评

暂无评论

Variable Selection Method Based on Least Absolute Shrinkage and Selection Operator(LASSO) and kNN for Faults Isolation 41

Variable Selection Method Based on Least Absolute Shrinkage ...

引用

第41届中国控制会议

作者： Yuanle Liu Lang Liu Yanwei Wang Ying Zheng Housheng Su China-Belt and Road Joint Laboratory On Measurement and Control Technology School of Artificial Intelligence and AutomationHuazhong University of Science and Technology School of Mechanical & Eletrical Engineering Wuhan Institute of Technology

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In the multivariable fault isolation of industrial process,the effectiveness of fault isolation is affected by the "smearing" effect because of the correlation between *** order to isolate all the key fault variables correctly,the fault isolation problem is regarded as a variable selection ***,LASSO is applied to the sparse contribution vector based on k-nearest ***,the LASSO-KNN model based on sliding window is established,and the sparse representation of contribution vector is obtained by least angle regression(LAR) algorithm and cumulative weight contribution percent criterion,thus the main fault variables are *** an extended EWMA algorithm combined with sliding window mechanism is introduced to achieve on-line fault ***,the effectiveness of the proposed algorithm is verified by a simulation example of TE process.

关键词： Fault diagnosis Fault isolation Variable selection k-Nearest neighbour

来源：评论

学校读者我要写书评

暂无评论

A Few-shot Fault Diagnosis Method under Target Domain Data Based on Improved Metric Space SVM 41

A Few-shot Fault Diagnosis Method under Target Domain Data B...

引用

第41届中国控制会议

作者： Xinyi Xu Qilin Qu Yanwei Wang Ying Zheng Housheng Su China-Belt and Road Joint Laboratory On Measurement and Control Technology School of Artificial Intelligence and AutomationHuazhong University of Science and Technology School of Mechanical & Electrical Engineering Wuhan Institute of Technology

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

The intelligent bearing diagnosis with big data has been widely *** high performance diagnosis models are constantly being proposed,these models are difficult to apply in some practical application with limited collectable *** this paper,an Improved Metric Space Support Vector Machine with a two-stage learning strategy is proposed to overcome the challenge of few-shot scenarios under target domain ***,an improved triplet loss is designed in the metric network to select features by utilizing the similarity of ***,kernel method is used to model in few-shot scenarios by maximizing the inter-class *** on CWRU dataset verify the superiority and robustness of IMSSVM comparing with popular baseline ***,the effectiveness of IMSSVM is verified with visualizing the feature embeddings by t-distributed stochastic neighbor embedding.

关键词： fault diagnosis few-shot learning metric learning kernel method

来源：评论

学校读者我要写书评

暂无评论

Threshold Selection for Circuit Board Nodes Based on LSTM Method 6

Threshold Selection for Circuit Board Nodes Based on LSTM Me...

引用

6th International Conference on Intelligent control, measurement and Signal Processing, ICMSP 2024

作者： Liu, Huimin Lv, Fangxing Liu, Jingjing Xi'an Shiyou University Xi'an China Xi'an Shiyou University School of Electronic Engineering Xi'an China Key Laboratory of Oil and Gas Well Measurement and Control Technology Shaanxi Province Xi'an China

ISBN: (纸本)9798331516550

With the advancement of modern electronic integration technology, the complexity of circuit board composition has significantly increased, making fault detection more challenging. This study proposes a fault diagnosis method based on the current and voltage test values of circuit nodes. By setting up test points on the circuit board, the method determines whether the board is functioning correctly by evaluating if the test values fall within the specified thresholds. Leveraging existing circuit board test data, the study first performs data cleansing, followed by sliding window processing. Long Short-Term Memory (LSTM) networks are then employed to predict the test values for each window, and the 3σ method is used for conditional judgment to derive appropriate thresholds. This approach enhances detection accuracy and the ability to identify subtle anomalies, thereby significantly improving the reliability and precision of circuit board fault detection without damaging the circuit board. © 2024 IEEE.

关键词： Long short-term memory

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：