检索结果-内蒙古大学图书馆

YOLOv5-T: A precise real-time detection method for maize tassels based on UAV low altitude remote sensing images

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2024年 221卷

作者： Gao, Rui Jin, Yishu Tian, Xin Ma, Zheng Liu, Siqi Su, Zhongbin Northeast Agr Univ Inst Elect & Informat Harbin 150030 Peoples R China

Maize tassels is an important organ of maize plant, and has a very important impact on yield prediction and variety breeding. Therefore, realizing the efficient and accurate detection of maize tassels in the natural environment is the key to obtain maize phenotypes in large quantities and accurately predict maize yield. This study constructed a dataset of tassels from different growth stages, proposed a YOLOv5-Tassel (YOLOv5-T) maize tassels detection model based on UAV remote sensing platform, combined with attention mechanism, YOLOv5_l network, spatial pyramid pooling structure and multi -scale extraction advantages of Atrous convolution. The experimental results showed that the Average Precision (AP) of the model for maize tassels detection could reach 98.70 %, and the detection speed was 42.2f/s. And the method in this paper had strong robustness to changes in light intensity and maize tassels at different growth stages. It was feasible to use YOLOv5-T to detect large areas of maize tassels in real time, which provided a useful reference for the estimation of maize yield and the selection of maize varieties.

关键词： deep learning algorithm Detection of maize tassel Attention module Spatial pyramid pooling

来源：评论

学校读者我要写书评

暂无评论

RNN-LSTM model for reliable optical transmission in flexible switching network systems

引用

WIRELESS NETWORKS 2024年第3期30卷 1575-1589页

作者： Almawgani, Abdulkarem H. M. Najran Univ Coll Engn Elect Engn Dept Najran Saudi Arabia

Data traffic is rapidly growing due to e-commerce, digital communication, and the digital world. Optical networks must provide a better solution to enhance transmission and improve service with cost efficiency. Considerable investigations of the 64QAM (Quadrature Amplitude Modulation) model have been conducted on wireless and optical communication to improve transmission efficiency. The next generation 400Gb/s systems are now widely recognized to be commercially accessible. At the same time, optical communication networks need a superior method to provide the best Quality of Transmission with improved data transmission efficiency. This paper aims to improve the Quality of Transmission in Optical Communication Networks (OCN). Therefore, a simple and fast reconfigurable network model is essentially required. However, there is a problem primarily related to configuring the network parameters to improve the Quality of Transmission (QoT). Research has shown that deep learning algorithms can improve QoT. Recurrent Neural Networks and Long-Short-Term-Memory (RNN-LSTM) algorithms are employed to leverage the factors of QoT in OCN. The RNN model analyzes the physical network parameters, and LSTM analyzes the dynamic data parameters and data from OCN. The Gaussian processes and path computation elements are utilized to obtain a mean absolute Signal Noise Ratio error of merely 0.1dB as a better result by the Gaussian process. The proposed model can provide high flexibility in changing the network topologies, planning, and period with less complexity by including a dataset evolution, adjusting the parameters, and examining output. A real-time dataset is analyzed using RNN-LSTM, implemented in Python, and experimented with. The throughput, bandwidth, and modulation path following light paths are calculated in the experiment to estimate the QoT. The experimental results showed that the proposed RNN-LSTM model provides better QoT. From the comparison, the proposed model provides a

关键词： Optical communication network Quality of transmission deep learning algorithm RNN LSTM

来源：评论

学校读者我要写书评

暂无评论

Research on Behavior Analysis of Real-Time Online Teaching for College Students Based on Head Gesture Recognition

引用

IEEE ACCESS 2022年 10卷 81476-81491页

作者： Liu Qianqian Wan Qian Xie Boya Lin Churan Xie Zhenyou Pan Shu Peng Guoqing Guangxi Univ Finance & Econ Sch Business Adm Nanning 530000 Peoples R China Guilin Univ Elect Technol Sch Architecture & Transportat Engn Guilin 541004 Peoples R China Southeast Univ Sch Transportat Nanjing 211189 Peoples R China Hualan Design & Consulting Grp Nanning 530011 Peoples R China

The accessibility of online teaching makes it popular in various teaching scenarios. Most of these researches about online interaction mainly focuse on the communication network stability, facial expression/gesture recognition algorithm and statistical description analysis, and its expertise mainly comes from the fields of computer technology and algorithm engineering. The evaluation and analysis of the effect of online teaching is an important test for the adaptability of such tools in the field of education. However, from the perspective of teachers, there is still a lack of literature on data interpretation after the application of this technology. An experiment based on real online teaching was carried out in this paper. This study uses image recognition technology to process video and extract five kinds of head movement data from dozens of student samples, and then develop statistical description interpretation. Some novel and interesting conclusions indicate that diversified behaviors occurred in real-time online learning. This study obtained data of five high-frequency online learning behaviors, including blinking, yawning, nodding, shaking head and leaving. These behaviors are related to learning state and time. Teaching features, students' personal characteristics and learning environment have a comprehensive impact on online learning behaviors. The result provides a basis for personalized learning and teaching scheme design in the future. It also helps to enrich online teaching evaluation methods and accelerate the construction of online education framework and rules.

关键词： Behavioral sciences Education Distance learning Face recognition Real-time systems Gesture recognition Electronic learning Real-time online teaching head gesture recognition deep learning algorithm experiment

来源：评论

学校读者我要写书评

暂无评论

Intelligent fuzzy sliding mode control for complex robot system with disturbances

引用

EUROPEAN JOURNAL OF CONTROL 2020年 51卷 95-109页

作者： Zheng, Kunming Hu, Youmin Wu, Bo Huazhong Univ Sci & Technol Sch Mech Sci & Engn Wuhan Peoples R China HUST Wuxi Res Inst Wuxi Jiangsu Peoples R China

It is a challenge work to control the complex robot system with disturbances. To solve this problem, an intelligent fuzzy sliding mode control method is proposed in this paper. Firstly, the dynamics model of the complex robot system is presented under disturbances. Then, based on the combination of sliding mode control and fuzzy logic control, the double fuzzy sliding mode controller is designed. In addition, due to the complexity of the dynamics model, it is very difficult or even impossible to obtain the exact dynamics model in practical application, therefore, a deep learning algorithm is developed, which can approximate the dynamics model as close as possible. And the stability of the proposed control method is analyzed by theory. Finally, the proposed intelligent fuzzy sliding mode control method is successfully applied to a KUKA robot system, which is compared with the existing control methods, and its superiority is demonstrated. (C) 2019 European Control Association. Published by Elsevier Ltd. All rights reserved.

关键词： Fuzzy sliding mode control deep learning algorithm Complex robot control Disturbances

来源：评论

学校读者我要写书评

暂无评论

Real-time data-driven PID controller for multivariable process employing deep neural network

引用

ASIAN JOURNAL OF CONTROL 2022年第6期24卷 3240-3251页

作者： Jeyaraj, Pandia Rajan Nadar, Edward Rajan Samuel Mepco Schlenk Engn Coll Dept Elect & Elect Engn Sivakasi India

The complex industrial processes exhibiting nonstationary and multivariable with time-varying dynamics result in low accuracy. Also, stability compensation is difficult to be obtained by a conventional PID controller. Hence, a deep learning-based data-driven PID controller is designed for unmodeled dynamics compensation for complex industrial processes. In this research work, a nonlinear PID controller is designed with a deep neural network (DNN) model from unmodeled dynamics of the complex industrial processes. To validate the performance, results from stability compensation and convergence of the model parameters for closed-loop systems were obtained. When tested on a real-time twin tank system, it achieved an accurate output flowrate with 97.65% accuracy and 1.89% peak overshoot compared with conventional PID controller. Both simulated and experimental results validate that proposed controller has improved stability and uniform convergence of system variables. The proposed deep learning-based PID controller was employed on a twin tank control system. This confirms the feasibility and practical application of a real-time complex process.

关键词： closed-loop control data-driven PID deep learning algorithm twin tank control unmodeled dynamics

来源：评论

学校读者我要写书评

暂无评论

Spatial Pyramid Pooling With 3D Convolution Improves Lung Cancer Detection

引用

IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2022年第2期19卷 1165-1172页

作者： Causey, Jason Li, Keyu Chen, Xianghao Dong, Wei Walker, Karl Qualls, Jake Stubblefield, Jonathan Moore, Jason H. Guan, Yuanfang Huang, Xiuzhen Arkansas State Univ Ctr Boundary Thinking CNBT Dept Comp Sci Jonesboro AR 72467 USA Arkansas State Univ Ctr Boundary Thinking CNBT Mol Bioscicneces Program Jonesboro AR 72467 USA Univ Michigan Dept Computat Med & Bioinformat Ann Arbor MI 48109 USA Ann Arbor Algorithm Ann Arbor MI 48103 USA Univ Arkansas Pine Bluff Dept Math & Comp Sci Pine Bluff AR 55455 USA Univ Penn Inst Biomed Informat Philadelphia PA 19104 USA

Lung cancer is the leading cause of cancer deaths. Low-dose computed tomography (CT)screening has been shown to significantly reduce lung cancer mortality but suffers from a high false positive rate that leads to unnecessary diagnostic procedures. The development of deep learning techniques has the potential to help improve lung cancer screening technology. Here we present the algorithm, deepScreener, which can predict a patient's cancer status from a volumetric lung CT scan. deepScreener is based on our model of Spatial Pyramid Pooling, which ranked 16th of 1972 teams (top 1 percent)in the Data Science Bowl 2017 competition (DSB2017), evaluated with the challenge datasets. Here we test the algorithm with an independent set of 1449 low-dose CT scans of the National Lung Screening Trial (NLST)cohort, and we find that deepScreener has consistent performance of high accuracy. Furthermore, by combining Spatial Pyramid Pooling and 3D Convolution, it achieves an AUC of 0.892, surpassing the previous state-of-the-art algorithms using only 3D convolution. The advancement of deep learning algorithms can potentially help improve lung cancer detection with low-dose CT scans.

关键词： Cancer Computed tomography Lung Biological system modeling Training Testing Machine learning Lung cancer screening low-dose CT scan deep learning algorithm convolutional neural network (CNN) medical imaging

来源：评论

学校读者我要写书评

暂无评论

Research on image tagging algorithm on internet

引用

CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS 2019年第6-Sup期22卷 13619-13625页

作者： Zhang, Junyang Guo, Yang Hu, Xiao Natl Univ Def Technol Coll Comp Changsha Hunan Peoples R China

At the age of big data, the information changes quickly. How to extract the key information timely seems to be quite important. Therefore, improving the execution speed of BFS algorithm means a lot to the processing of big data. This paper firstly introduces the implementation flow, features and performance evaluation criteria of the breadth-first search algorithm, and secondly introduce the research status of BFS algorithm based on current CPU platform both at home and abroad. Thirdly, this paper optimizes the algorithm by using the local principle of program, load balancing method and so on. Finally, the comparison of the algorithm performance is shown in this paper: the program optimized in this paper gets good performance and could be popularized further in practice.

关键词： BFS algorithm Graph search deep learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter Optimization Using a Genetic algorithm Considering Verification Time in a Convolutional Neural Network

引用

JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY 2020年第2期15卷 721-726页

作者： Han, Ji-Hoon Choi, Dong-Jin Park, Sang-Uk Hong, Sun-Ki Hoseo Univ Dept Informat Control Engn Asan Chungnam South Korea Hoseo Univ Dept Digital Control Engn Asan Chungnam South Korea

Hyperparameter optimization is a very difficult problem in developing deep learning algorithms. In this paper, a genetic algorithm was applied to solve this problem. The accuracy and the verification time were considered by conducting a fitness evaluation. The algorithm was evaluated by using a simple model that has a single convolution layer and a single fully connected layer. A model with three layers was used. The MNIST dataset and a motor fault diagnosis dataset were used to train the algorithm. The results show that the method is useful for reducing the training time.

关键词： deep learning algorithm Genetic algorithm Hyper-parameter optimization Motor fault diagnosis Convolutional neural network MNIST

来源：评论

学校读者我要写书评

暂无评论

Development of sports industry under the influence of COVID-19 epidemic situation based on big data

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2020年第6期39卷 8867-8875页

作者： Wang Yile Zeng Dashuai Nanyang Normal Univ Sch Phys Educ Nanyang Henan Peoples R China Chengdu Univ Dept Phys Educ Chengdu Sichuan Peoples R China Univ Elect Sci & Technol Chengdu Sichuan Peoples R China

Based on big data, this paper studies the influence of new type of filling pneumonia on the development of sports industry. When selecting the typical economic indicators that reflect the development trend of sports industry, it is found that the data is huge according to the big industrial data, but the information that can be reflected is poor and complex. Therefore, it is necessary to process these big economic data in order to obtain the impact of new coronary pneumonia on the development of sports industry. This paper studies the feature selection algorithm of big data samples, so as to select typical economic indicators from many economic indicators of sports industry to reflect the development trend of sports industry. A deep learning algorithm based on feature selection of big data is proposed. Firstly, a feature selection framework for big data is constructed, and then data fusion and deep learning are carried out. Experiments show that the algorithm can solve the contradiction between large data and poor information. This method has a certain forward-looking, and has a certain reference value for the information discrimination of the development trend of sports industry.

关键词： Sports industry big data industrial development deep learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Object Detection for Cargo Unloading System Based on Fuzzy C Means

引用

Computers, Materials & Continua 2022年第5期71卷 4167-4181页

作者： Sunwoo Hwang Jaemin Park Jongun Won Yongjang Kwon Youngmin Kim Department of Systems Engineering Ajou UniversitySuwon16499Korea New Transportation Innovative Research Center Korea Railroad Research InstituteUiwang16105Korea Innovative Transportation and Logistics Research Center Korea Railroad Research InstituteUiwang16105Korea

With the recent increase in the utilization of logistics and courier services,it is time for research on logistics systems fused with the fourth industry *** studies related to object recognition have been actively conducted in convergence with the emerging artificial intelligence field,but so far,algorithms suitable for automatic unloading devices that need to identify a number of unstructured cargoes require further *** this study,the object recognition algorithm of the automatic loading device for cargo was selected as the subject of the study,and a cargo object recognition algorithm applicable to the automatic loading device is proposed to improve the amorphous cargo identification *** fuzzy convergence algorithm is an algorithm that applies Fuzzy C Means to existing algorithm forms that fuse YOLO(You Only Look Once)and Mask R-CNN(Regions with Convolutional Neuron Networks).Experiments conducted using the fuzzy convergence algorithm showed an average of 33 FPS(Frames Per Second)and a recognition rate of 95%.In addition,there were significant improvements in the range of actual box *** results of this study can contribute to improving the performance of identifying amorphous cargoes in automatic loading devices.

关键词： deep learning algorithm YOLOv2 Mask R-CNN Fuzzy C Means unloading system

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：