检索结果-内蒙古大学图书馆

Research on Wheat Impurity Image Recognition Based on Convolutional Neural Network 1

12th International Conference on Broadband Communications, Networks, and Systems, BROADNETS 2021

作者： Zhu, Chunhua Miao, Tiantian Key Laboratory of Grain Information Processing and Control Ministry of Education Henan University of Technology Henan Zhengzhou450001 China College of Information Science and Engineering Henan University of Technology Henan Zhengzhou450001 China Henan Key Laboratory of Grain Photoelectric Detection and Control Henan University of Technology Henan Zhengzhou450001 China

ISBN: (数字)9783030934798

ISBN: (纸本)9783030934781

The doping rate is one of the important indexes to evaluate the quality grade and price of wheat. In order to accurately and quickly recognize impurities (wheat husk) in wheat grains, images of doped wheat were collected and Convolutional Neural Network (CNN) was used to realize the classification and recognition of grains and impurities in wheat grains. In this study, image segmentation and image enhancement were used to preprocess the acquired images to establish the image database of wheat grains and impurities. According to the characteristics of image data, the classic CNN, VGGNet and ResNet network models for wheat impurity images recognition were established. Simulation analysis shows that, compared with the classical CNN and VGGNet network models, the ResNet network model has the best recognition performance. The recognition accuracy of the test set is 96.94%, the recognition time is 5.60 ms. © 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

MAGPNet: Multi-Domain Attention-Guided Pyramid Network for Infrared Small Object Detection

引用

Journal of Shanghai Jiaotong university (Science) 2024年 1-18页

作者： Ding, Leqi Wang, Biyun Yao, Lixiu Cai, Yunze Department of Automation Shanghai Jiao Tong UniversityKey Laboratory of System Control and Information Processing of Ministry of Education Shanghai200240 China National Key Laboratory of Air-based Information Perception and Fusion Henan Luoyang471009 China Shanghai Institute of Aerospace Control Technology Infrared Detection Technology R&D Center of China Aerospace Science and Technology Corporation Shanghai201109 China

To overcome the obstacles of poor feature extraction and little prior information on the appearance of infrared dim small targets, we propose a multi-domain attention-guided pyramid network (MAGPNet). Specifically, we design three modules to ensure that salient features of small targets can be acquired and retained in the multi-scale feature maps. To improve the adaptability of the network for targets of different sizes, we design a kernel aggregation attention block with a receptive field attention branch and weight the feature maps under different perceptual fields with attention mechanism. Based on the research on human vision system, we further propose an adaptive local contrast measure module to enhance the local features of infrared small targets. With this parameterized component, we can implement the information aggregation of multi-scale contrast saliency maps. Finally, to fully utilize the information within spatial and channel domains in feature maps of different scales, we propose the mixed spatial-channel attention-guided fusion module to achieve high-quality fusion effects while ensuring that the small target features can be preserved at deep layers. Experiments on public datasets demonstrate that our MAGPNet can achieve a better performance over other state-of-the-art methods in terms of the intersection of union, Precision, Recall, and F-measure. In addition, we conduct detailed ablation studies to verify the effectiveness of each component in our network. © 2024, Shanghai Jiao Tong university.

关键词： Software engineering

来源：评论

学校读者我要写书评

暂无评论

Non-contact Detection of Vital Sign Based on ICCEMDAN-SpEn Combined with Wavelet Threshold Denoising

Non-contact Detection of Vital Sign Based on ICCEMDAN-SpEn C...

引用

International Conference on Microwave and Millimeter Wave technology Proceedings

作者： Wan Li Binkun Liu Chunhua Zhu Key Laboratory of Grain Information Processing and Control Henan University of Technology Ministry of Education Henan Key Laboratory of Grain Photoelectric Detection and Control Henan University of Technology Henan Engineering Laboratory of Grain Condition Intelligent Detection and Application Henan University of Technology Zhengzhou China

ISBN: (数字)9798350389968

ISBN: (纸本)9798350389975

The detection of vital signs, especially respiratory rate and heartbeat rate, is of great significance for clinical diagnosis, daily health assessment and disaster rescue. In recent years, millimeter wave based non-contact vital sign detection has become a research hotspot. Aiming to overcome the noise influence of the target signal on the detection accuracy, one improved ICEEMDAN based on sample entropy (ICCEMDAN-SpEn) combined with wavelet threshold denoising is proposed. Firstly, the adaptive noise extraction ability of ICEEMDAN is analyzed to isolate all intrinsic mode function (IMF) components of the noisy target signals, and the sample entropy is introduced as the threshold to select the main IMFs; then wavelet threshold denoising is proposed to relieve the noise adaptively, which can better deal with the nonlinear and non-stationary signal; finally, IMFs after wavelet threshold denoising are reconstructed to attain target signals. The experimental results show that the proposed method can effectively relieve the noise contained in the vital sign signals and estimate the respiratory rate and heartbeat rate of human body accurately.

关键词： Heart beat Noise reduction Noise Millimeter wave technology Millimeter wave measurements Wavelet analysis Entropy

来源：评论

学校读者我要写书评

暂无评论

MULTI-SCALE RESNET INTEGRATED WITH ATTENTION MECHANISM FOR ENHANCED WHEAT FRESHNESS DIAGNOSIS BASED ON BIOPHOTONICS

引用

Acta Scientiarum Polonorum, Technologia Alimentaria 2024年第4期23卷 525-535页

作者： Shi, Weiya Chen, Liang Key Laboratory of Grain Information Processing and Control Ministry of Education Henan 450001 China Henan Key Laboratory of Grain Photoelectric Detection and Control Henan University of Technology Henan 450001 China College of Artificial Intelligence and Big Data Henan University of Technology Henan 450001 China

Background. Accurate detection of wheat freshness is important for ensuring the quality and safety of wheat products, thereby protecting the health and interests of consumers. Material and methods. This study integrates biophoton emission technology with advanced deep learning frameworks to transform the process of wheat freshness assessment. Leveraging the powerful feature extraction capabilities of the ResNet architecture, we employ a multi-scale framework integrated with the Gaussian Context Transformer (GCT) attention mechanism. The MS-GCT-ResNet method presents a groundbreaking approach that not only enhances the accuracy and efficiency of wheat freshness discrimination but also demonstrates the potential for combining biophysical phenomena with cutting-edge Artificial Intelligence (AI) technologies for precision agriculture and food quality control. Results. This model enhances detection accuracy and adaptability, offering a powerful technique for the rapid and precise evaluation of wheat freshness. Its effectiveness is validated using years of wheat sample data. Based on the experimental results, MS-GCT-ResNet achieves a recognition accuracy of 93.6%. Compared with traditional CNN and ResNet models, the recognition accuracy increases by 1.9% and 1.1%, respectively. Conclusion. MS-GCT-ResNet is a highly promising, non-invasive, and efficient technological advancement capable of quickly and accurately assessing wheat freshness. This method holds immense potential to revolutionize the agriculture and food processing industries. © (2024), (Wydawnictwo Uniwersytetu Przyrodniczego w Poznaniu). All rights reserved.

关键词： attention mechanism biophoton emission detection multi-scale wheat freshness

来源：评论

学校读者我要写书评

暂无评论

Research on Explanation of CAM-Based CNNs

Research on Explanation of CAM-Based CNNs

引用

IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS)

作者： Shuzhi Yang Chunhua Zhu Xue Li Key Laboratory of Grain Information Processing and Control (Henan University of Technology) Ministry of Education Henan Key Laboratory of Grain Photoelectric Detection and Control Henan University of Technology Henan Engineering Laboratory of Grain Condition Intelligent Detection and Application Henan University of Technology Zhengzhou China

ISBN: (数字)9798350374315

ISBN: (纸本)9798350374322

Class activation mapping (CAM) is a post-hoc explanation method for Convolutional neural networks (CNNs), aiming to visually explain the decision-making process of CNNs. CAM demonstrates superior categorical discrimination capabilities compared to visual explanation methods rooted in backpropagation and perturbation. Five CAM methods have been comprehensively analyzed and discussed, revealing their applications in explaining CNN decision-making. Additionally, the evaluation principles and metrics for CAM and other explainable methods are summarized. A comparative analysis highlights their characteristics, applicability, and inherent limitations. Finally, the challenges faced by CAM methods in the field of explainable research are explored, and future development trends are anticipated.

关键词： Measurement Backpropagation Visualization Perturbation methods Decision making Market research Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Loosely Synchronized Search for Multi-Objective Multi-Agent Path Finding with Asynchronous Actions

引用

Journal of Shanghai Jiaotong university(Science) 2024年第4期29卷 667-677页

作者： DU Haikuo GUO Zhengyu ZHANG Lulu CAI Yunze Department of Automation Shanghai Jiao Tong UniversityShanghai200240China Key Laboratory of System Control and Information Processing Ministry of EducationShanghai200240China China Airborne Missile Academy LuoyangHenan471000China National Key Laboratory of Air-based Information Perception and Fusion LuoyangHenan471000China

In recent years,the path planning for multi-agent technology has gradually matured,and has made breakthrough *** main difficulties in path planning for multi-agent are large state space,long algorithm running time,multiple optimization objectives,and asynchronous action of multiple *** solve the above problems,this paper first introduces the main problem of the research:multi-objective multi-agent path finding with asynchronous action,and proposes the algorithm framework of multi-objective loose synchronous(MO-LS)*** combining A*and M*,MO-LS-A*and MO-LS-M*algorithms are respectively *** completeness and optimality of the algorithm are proved,and a series of comparative experiments are designed to analyze the factors affecting the performance of the algorithm,verifying that the proposed MO-LS-M*algorithm has certain advantages.

关键词： multi-agent path finding multi-objective path planning asynchronous action loosely synchronous search

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation of Ship Wakes in SAR Images Based on Improved CycleGAN

引用

Journal of Shanghai Jiaotong university(Science) 2024年第4期29卷 702-711页

作者： YAN Congqiang GUO Zhengyun CAI Yunze Department of Automation Shanghai Jiao Tong UniversityShanghai200240China Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai200240China China Airborne Missile Academy Luoyang471009HenanChina National Key Laboratory of Air-Based Information Perception and Fusion Luoyang471000HenanChina

The study on ship wakes of synthetic aperture radar(SAR)images holds great importance in detecting ship targets in the *** this study,we focus on the issues of low quantity and insufficient diversity in ship wakes of SAR images,and propose a method of data augmentation of ship wakes in SAR images based on the improved cycle-consistent generative adversarial network(CycleGAN).The improvement measures mainly include two aspects:First,to enhance the quality of the generated images and guarantee a stable training process of the model,the least-squares loss is employed as the adversarial loss function;Second,the decoder of the generator is augmented with the convolutional block attention module(CBAM)to address the issue of missing details in the generated ship wakes of SAR images at the microscopic *** experiment findings indicate that the improved CycleGAN model generates clearer ship wakes of SAR images,and outperforms the traditional CycleGAN models in both subjective and objective aspects.

关键词： synthetic aperture radar(SAR) ship wake data augmentation cycle-consistent generative adversarial network(CycleGAN) attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Temperature Prediction for Stored grain: A Multi- model Fusion Approach Based on Machine Learning

Temperature Prediction for Stored Grain: A Multi- model Fusi...

引用

Electronic technology and information Science (ICETIS), International Conference on

作者： Donghao Chen Binkun Liu Key Laboratory of Grain Information Processing and Control Henan University of Technology Zhengzhou China Henan Engineering Laboratory of Grain Condition Intelligent Detection and Application Henan University of Technology Zhengzhou China

ISBN: (数字)9798350388343

ISBN: (纸本)9798350388350

Temperature fluctuations significantly affect microorganism growth and pest activities in grain pile, precise monitoring and forecasting temperature of stored grain are essential for maintaining the quality and safety of grain storage. This paper proposes a multi-model fusion approach to predict grain temperature using historical temperature data of stored grain and meteorological data from the region. Firstly, four distinct machine learning models, namely Adaboost, decision tree, extra trees, and random forest, are fine-tuned through parameter optimization to enhance their predictive capabilities respectively; Subsequently, these optimized models are fused to form different ensemble models, which are compared for prediction accuracy to obtain the optimal fusion model. In essence, the fusion process integrates the predictions of each individual model as new feature inputs into the fusion models. Furthermore, random forest is utilized to identify the key factors influencing grain temperature, providing insights into the importance of different influencing factors. The experimental results demonstrate that the proposed fusion models can achieve higher prediction accuracy and robustness compared with the single-model prediction methods. Additionally, the analysis of feature importance also offers empirical evidence for understanding the factors influencing grain temperature.

关键词： Temperature sensors Temperature measurement Temperature distribution Humidity Predictive models Prediction algorithms Robustness

来源：评论

学校读者我要写书评

暂无评论

Prediction Method of Axial Compression Capacity of CCFST Columns Based on Deep Learning

IAENG International Journal of Computer Science

引用

IAENG International Journal of Computer Science 2024年第3期51卷 243-251页

作者： Cheng, Yong Tao, Huawei Lu, Xiangying Xu, Zhijun Fu, Hongliang Zhu, Chunhua Key Laboratory of Food Information Processing and Control Ministry of Education Henan University of Technology Zhengzhou450001 China Henan Engineering Laboratory of Grain IOT Technology Henan University of Technology Zhengzhou450001 China Key Laboratory of Food Information Processing and Control Ministry of Education Henan University of Technology Zhengzhou450001 China School of Civil Engineering Henan University of Technology Zhengzhou450001 China Henan Engineering Laboratory of Grain IOT Technology Henan University of Technology Zhengzhou450001 China Henan Engineering Laboratory of Grain IOT Technology Henan University of Technology Zhengzhou450001 China

Accurate prediction of axial compression capacity (ACC) is crucial for evaluating the performance of circular concrete-filled steel tubes (CCFST). Traditional methods face challenges in dealing with the intricate nonlinear relationship inherent in the structure. This paper presents a deep learning (DL) method to predict ACC. The proposed method standardizes parameters, including steel yield strength, column length, and other relevant characteristics of CCFST. Subsequently, a three-layer Long Short-Term Memory (LSTM) network is constructed to capture the complex relationships among these parameters. To enhance the model’s capability for nonlinear fitting, the Rectified Linear Unit (ReLU) activation function is applied between network layers. Additionally, an attention mechanism is introduced to improve feature extraction capabilities. Comprehensive simulations demonstrate that the proposed method surpasses state-of-the-art techniques, achieving optimal values for Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and the coefficient of determination (R2). The simulation results validate the efficacy of the proposed method. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Cinnamaldehyde inactivates Listeria monocytogenes at a low temperature in ground pork by disturbing the expression of stress regulatory genes

引用

Food Bioscience 2023年第1期51卷 472-482页

作者： Peng Guan Xiaojie Wang Zijie Dong Miao Song Hongshuai Zhu Biao Suo College of Food Science and Technology Henan Agricultural UniversityZhengzhouChina Key Laboratory of Staple Grain Processing Ministry of Agriculture and Rural AffairsZhengzhouChina National R&D Center for Frozen Rice&Wheat Products Processing Technology Henan Engineering Laboratory of Quick-Frozen Flour-Rice Food and Prepared FoodHenan Agricultural UniversityZhengzhouChina

Listeria monocytogenes is a cold tolerant foodborne pathogen that frequently detected in ground pork stored at low *** study firstly evaluated the inhibitory effect of cinnamaldehyde on Listeria monocytogenes at 4℃ and the mechanism by which cinnamaldehyde interferes with the adaptive gene regulation *** low temperature and cinnamaldehyde were combined for treating ***,the time required to cause a reduction by 2 log CFU/g(t 2.0)was decreased along with the increase of cinnamaldehyde concentration,although cinnamaldehyde may produce an unpleasant but acceptable *** electron microscopy(TEM)results showed severe rupture of the cell envelope and leakage of cytoplasmic contents in cells treated with a combination treatment of cinnamaldehyde and low temperature,but the effect of individual treatment is not ***-time quantitative PCR results revealed that the stress resistance genes(gbuA,gbuB,gadD2,groEL,rli60 and ilvD),regulatory genes(prfA,sigB,codY and luxS)and cold shock response genes(cspA,cspB and cspD)were actively involved in the response to the low ***,the combination of cinnamaldehyde and low temperature treatment disturb the gene *** docking results further indicate that cinnamaldehyde may interact with protein PrfA and LuxS amino acid residues through hydrogen bonding,thus interfering with regulator *** results firstly indicates that cinnamaldehyde has a synergistic inhibition effect on *** in cold stored ground pork by rupturing cell envelop and disturbing stress regulatory gene expression,which provides a new idea for the safety control of chilled meat.

关键词： Listeria monocytogenes Cinnamaldehyde Weibull model Real-time quantitative PCR Molecular docking

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：