检索结果-内蒙古大学图书馆

Dynamic UAV Phenotyping for Rice Disease Resistance Analysis Based on Multisource Data

Plant Phenomics 2023年第1期5卷 110-122页

作者： Xiulin Bai Hui Fang Yong He Jinnuo Zhang Mingzhu Tao Qingguan Wu Guofeng Yang Yuzhen Wei Yu Tang Lie Tang Binggan Lou Shuiguang Deng Yong Yang Xuping Feng College of Biosystems Engineering and Food Science Zhejiang UniversityHangzhou 310058China Huzhou Institute of Zhejiang University Huzhou 313000China School of Information Engineering Huzhou UniversityHuzhou 313000China Academy of Interdisciplinary Studies Guangdong Polytechnic Normal UniversityGuangzhou 510665China Department of Agricultural and Biosystems Engineering Iowa State UniversityAmesIA 50011-3270USA College of Agriculture and Biotechnology Zhejiang UniversityHangzhou 310058China College of Computer Science and Technology Zhejiang UniversityHangzhou 310058China State Key Laboratory for Managing Biotic and Chemical Treats to the Quality and Safety of Agro-Products Key Laboratory of Biotechnology for Plant ProtectionMinistry of Agricultureand Rural AffairsZhejiang Provincial Key Laboratory of Biotechnology for Plant ProtectionInstitute of Virology and BiotechnologyZhejiang Academy of Agricultural ScienceHangzhou 31002China

Bacterial blight poses a threat to rice production and food security,which can be controlled through large-scale breeding efforts toward resistant *** aerial vehicle(UAV)remote sensing provides an alternative means for the infield phenotype evaluation of crop disease resistance to relatively time-consuming and laborious traditional ***,the quality of data acquired by UAV can be affected by several factors such as weather,crop growth period,and geographical location,which can limit their utility for the detection of crop disease and resistant ***,a more effective use of UAV data for crop disease phenotype analysis is *** this paper,we used time series UAV remote sensing data together with accumulated temperature data to train the rice bacterial blight severity evaluation *** best results obtained with the predictive model showed an R_(p)^(2) of 0.86 with an RMSE_(p) of ***,model updating strategy was used to explore the scalability of the established model in different geographical *** percent of transferred data for model training was useful for the evaluation of disease severity over different *** addition,the method for phenotypic analysis of rice disease we built here was combined with quantitative trait loci(QTL)analysis to identify resistance QTL in genetic populations at different growth *** new QTLs were identified,and QTLs identified at different growth stages were *** analysis combined with UAV high-throughput phenotyping provides new ideas for accelerating disease resistance breeding.

关键词： blight breeding cultivar

来源：评论

学校读者我要写书评

暂无评论

Research on Adaptive Grouping Method of TSP Path Planning Based on Genetic Algorithm

Research on Adaptive Grouping Method of TSP Path Planning Ba...

引用

2020 IEEE International Conference on Industrial Application of Artificial Intelligence, IAAI 2020

作者： Zhao, Xi Li, Ying Computer Engineering Technical College Guangdong Polytechnic of Science and Technology Zhuhai China

ISBN: (纸本)9781665404716

The traditional adaptive grouping of robot TSP path planning, the calculation of the adaptive function of the algorithm is insufficient, which makes the workload of the adaptive grouping larger, resulting in the data processing time of the grouping too long. Therefore, an adaptive grouping method for TSP path planning based on genetic algorithm is proposed. Firstly establish the TSP grid structure, confirm the path planning environment and working space, and use genetic algorithm to solve the grid structure path. After obtaining the data results, use the fitness function to determine the weight data in the genetic algorithm, and finally establish a mathematical model for self-adaptation Grouping. The feasibility of the above method is verified. The experimental results show that the adaptive grouping method of TSP path planning based on genetic algorithm has shorter processing time for data adaptive grouping, which proves that the method is more effective. © 2020 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Research on two-stage Feature Mining Fusion Method based on Genetic Algorithm

Research on two-stage Feature Mining Fusion Method based on ...

引用

2020 IEEE International Conference on Industrial Application of Artificial Intelligence, IAAI 2020

作者： Li, Ying Zhao, Xi Computer Engineering Technical College Guangdong Polytechnic of Science and Technology Zhuhai China

ISBN: (数字)9781665404716

ISBN: (纸本)9781665404716

In the actual fusion of two-stage feature data, reconstruction errors are easy to occur in the process of feature region reconstruction in different stages, resulting in too few final fusible mining indicators. To solve this problem, this paper designs a two-stage feature mining fusion method based on genetic algorithm. Based on the two-stage mining features, the two-stage feature areas are divided, and the feature area reconstruction project is controlled by setting the background template of the feature area. Then the genetic algorithm is used to construct the mining fusion mapping relationship, and different fusion levels are set to complete the research on the feature mining fusion method. Set up a two-stage feature experiment platform, mine feature data, take the feature data obtained as the experimental object, and use two traditional fusion methods to conduct comparative experiments with this article. The results show that the method in this paper can integrate the most index values, which proves that the method is more effective. © 2020 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Information security for big data using the NTRUEncrypt method

引用

Measurement: Sensors 2023年 27卷

作者： Khalid Yousif, Mohammed Dallalbashi, Zena Ez Kareem, Shahab Wahhab Department of Electronic Techniques Mosul Technical Institute Northern Technical University Iraq Department of Technical Information Systems Engineering Erbil Technical Engineering College Erbil Polytechnic University Erbil Iraq Department of Information Technology College of Engineering and Computer Science Lebanese French University Erbil Iraq

Cloud computing processes vast quantities of data and offers a variety of flexible, secure, on-demand, and cost-effective collaboration options for consumers. Due to the increasing prevalence of hosted services, data security has become an increasingly critical concern. Hadoop, the engine at the heart of cloud computing, causes serious problems for the cloud. Any public, private, or hybrid cloud environment can use this security solution without any hassle (IaaS). Furthermore, it is compatible with the vast majority of Cloud computing's capabilities. Increase cloud security using NTRU encryption. This study made advantage of the (NTRUEncrypt) algorithms residing in Hadoop to speed up the file encryption and decryption processes. If HDFS is engaged in the Map Task, then HDFS will take care of both the encryption and decryption processes. Data on the cloud can be kept private and secure thanks to the proposed protection technique, which makes use of cryptography. Combining the proposed technique with preexisting infrastructure and web-based. © 2023 The Authors

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Test-Driven Feature Extraction of Web Components

引用

Journal of computer science & technology 2022年第2期37卷 389-404页

作者： Yong-Hao Long Yan-Cheng Chen Xiang-Ping Chen Xiao-Hong Shi Fan Zhou School of Computer Science and Engineering National Engineering Research Center of Digital Life Sun Yat-sen UniversityGuangzhou 510006China School of Design The Hong Kong Polytechnic UniversityHong KongChina Guangdong Key Laboratory for Big Data Analysis and Simulation of Public Opinion The School of Communication and DesignSun Yat-sen UniversityGuangzhou 510006China School of Information Technology and Engineering Guangzhou College of CommerceGuangzhou 511363China

With the growing requirements of web applications,web components are developed to package the implementation of commonly-used features for *** some cases,the developer may want to reuse some features which cannot be customized by the component’s ***/she has to extract the implementation by *** is labor-intensive and *** the widely-used test cases which can be useful to specify the software features,a test-driven approach is proposed to extract the implementation of the desired features in web *** satisfaction of the user^requirements is transformed into the passing rate of user-specified test *** this way,the quality of the extraction result can be evaluated ***,a record/replay-based GUI test generation method is proposed to ensure that the extraction result has the correct GUI *** extract the feature implementation,a hierarchical genetic algorithm is proposed to find the code snippet that can pass all the tests and has the approximate smallest *** compare our method with two existing feature extraction *** result shows that our method can extract the correct implementation with the minimum size.A human-subject study is conducted to show the effectiveness and weaknesses of our method in helping users extract the features.

关键词： feature extraction genetic algorithm graphical user interface software reuse

来源：评论

学校读者我要写书评

暂无评论

Mobility-Aware User Association and Computation Offloading in Ultra-Dense Networks

IEEE Transactions on Green Communications and Networking

引用

IEEE Transactions on Green Communications and Networking 2025年

作者： Qiu, Bin Feng, Ke Li, Xian Xiao, Hailin Zhang, Zhongshan Guilin University of Technology School of Computer Science and Engineering Guilin541004 China Guilin University of Technology Guangxi Key Laboratory of Embedded Technology and Intelligent System Guilin541004 China Guangxi Modern Polytechnic College Hechi530700 China Shenzhen University College of Electronics and Information Engineering Shenzhen518060 China Hubei University School of Computer Science and Information Engineering Wuhan430062 China Wuhan430062 China School of Cyberspace Science and Technology Guangdong519088 China

The integration of mobile edge computing (MEC) into ultra-dense network (UDN) has emerged as a promising solution for providing uninterrupted task offloading services to computation-demanding mobile devices (MDs), leveraging densely deployed MEC servers. However, the mobility of MDs can significantly affect the computation offloading decision and system performance in UDN-MEC. To address this issue, we develop a joint optimization algorithm for mobility-aware user association and computation offloading to minimizize the total system cost, including delay and energy consumption in UDN-MEC. Specifically, a polynomial fitting algorithm based on an extended Kalman filter (PFA-EKF) is designed to predict the nonlinear moving trajectories of the MDs. Furthermore, we present a mobility-aware user-association rule based on a breadth-first search (UAR-BFS) that can realize balanced matching offloading in the overlapping coverage area of densely deployed small base stations. Accordingly, we propose an improved deep deterministic policy gradient-based greedy algorithm (IDDPG-GA) to address the joint optimization problem of multiuser dynamic offloading and resource allocation, in which an intelligently adjusted bias factor is proposed to enhance collaborative behavior among MDs. Extensive numerical results and comparisons demonstrate the promising performance improvements of the proposed scheme compared with existing benchmark schemes in various scenarios. © 2025 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Wi-Fi Sensing Based on Deep Supervised Dictionary Learning for Robust Device-Free Localization

引用

IEEE Transactions on Vehicular technology 2025年

作者： Huang, Huakun Wang, Chenyang Zhao, Lingjun Wang, Weizheng Ding, Shuxue Vasilakos, Athanasios The School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China The School of Electronics and Information Guangdong Polytechnic Normal University Guangzhou China The Department of Computer Science City University of Hong Kong Hong Kong The School of Artificial Intelligence Guilin University of Electronic Technology China The College of Computer Science and Information Technology IAU Saudi Arabia Grimstad Norway

Device-free localization (DFL) represents an emerging technology in autonomous driving assistance systems, sensing targets around a vehicle without requiring them carrying any devices. Current machine learning methodologies for DFL struggle with adaptively extracting discriminative features, resulting in weak robustness. Although dictionary learning techniques have shown potentiality in robust feature extraction for images and signals, their direct application to improving the robustness of DFL presents significant challenges. Specifically, the unsupervised mechanism of dictionary learning complicates the calibration of target location bases. The complex optimization processes also lead to inefficient parameter updating. To address these issues, we propose a deep-supervised dictionary learning (DSDL) approach for enhancing the robustness of DFL. The proposed DSDL method synergizes the advantages of sparse representation and deep learning, incorporating the robustness and interpretability of dictionary learning with the efficient parameter updating characteristic of deep learning. The supervised mechanism enables collaborative labeling of the learned signal bases. Experimental results, derived from an established DFL system, demonstrate that our DSDL outperforms existing techniques in both robustness and accuracy. DSDL maintains strong robustness and achieves high localization accuracy, surpassing 99% on clean data and sustaining over 97% accuracy under 30 dB signal-to-noise ratio (SNR) conditions. This work highlights the potential of existing WiFi infrastructure to provide cost-efficiency solutions for target localization, paving the way for future applications of wireless sensing. © 1967-2012 IEEE. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Speaker Identification Using Depthwise Separable Convolutional Network with Channel Attention

arXiv

引用

arXiv 2022年

作者： Li, Yanxiong Wang, Wucheng Chen, Hao Cao, Wenchang Li, Wei He, Qianhua School of Electronic and Information Engineering South China University of Technology Guangzhou China Computer Engineering Technical College Guangdong Polytechnic of Science and Technology Zhuhai China

Although few-shot learning has attracted much attention from the fields of image and audio classification, few efforts have been made on few-shot speaker identification. In the task of few-shot learning, overfitting is a tough problem mainly due to the mismatch between training and testing conditions. In this paper, we propose a few-shot speaker identification method which can alleviate the overfitting problem. In the proposed method, the model of a depthwise separable convolutional network with channel attention is trained with a prototypical loss function. Experimental datasets are extracted from three public speech corpora: Aishell-2, VoxCeleb1 and TORGO. Experimental results show that the proposed method exceeds state-of-the-art methods for few-shot speaker identification in terms of accuracy and F-score. © 2022, CC BY.

关键词： Loudspeakers

来源：评论

学校读者我要写书评

暂无评论

Optimized Control of IoT-Monitored Microgrid Systems Using Genetic Algorithm

Optimized Control of IoT-Monitored Microgrid Systems Using G...

引用

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Vijayalakshmi, N. Yuvaraj, S. Baskar, V. Vijaya Krishnaswamy, R. Sasikala, K. Srinivasan, C. Government Polytechnic College Deputed from Annamalai University Department of Electrical and Electronics Engineering Tamilnadu Coimbatore India Srm Institute of Science and Technology Faculty of Engineering and Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India School of Electrical and Electronics Engineering Sathyabama Institute of Science and Technology Tamil Nadu Chennai India University College of Engineering Department of Electronics and Communication Engineering Tamil Nadu Ariyalur India Department of Electrical and Electronics Engineering Tamil Nadu Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350357769

Microgrid (MG) systems have become a good way to make power generation and distribution more efficient, especially when Distributed Energy Resources (DERs) are introduced. The inverter is a critical part of MGs since it regulates the voltage output to the grid. A unique method is proposed to tune the settings of a Proportional-Integral-Derivative (PID) controller for the inverter using Genetic Algorithm (GA). The main aim is to use GAs to improve the inverter control in an MG that is monitored by the Internet of Things (IoT). GA's are very useful for resolving difficult optimization issues. Optimization of voltage regulation, stability, and power transmission to the grid may be achieved by using GA-based tuning of PID controller settings. From the simulation results, the GA-based methodology provides better control performance than conventional tuning approaches, providing exact voltage regulation and improving the MG's stability and dependability. © 2023 IEEE.

关键词： Genetic algorithm and Optimization technique Microgrid Renewable energy Voltage control

来源：评论

学校读者我要写书评

暂无评论

Intelligent Line Loss Analysis of New Energy Connected to the Power Grid

Intelligent Line Loss Analysis of New Energy Connected to th...

引用

science and technology Innovation (IAECST), International Academic Exchange Conference on

作者： Yifang Tang Ruiyun Hou Dafu Zhong Yingbo Xu Computer Engineering Technical College Guangdong Polytechinic of Science and Technology Zhuhai China Zhuhai Yineng Electronic Technology Co. Ltd Zhuhai China

Under the background of rapid development of new energy, it is imperative to study its impact on power grid operation. This study analyzed the mechanism of line loss changes caused by the access of distributed photovoltaic new energy through case studies, collected operational data using IoT devices, and established an equivalent resistance power line loss prediction model. The model achieved high-precision predictions. Based on the prediction results, a line loss analysis optimization strategy was proposed to ensure the reliability and economic rationality of power supply. Case studies showed that this strategy can effectively reduce line loss. This research provides predictive and control means for large-scale integration of new energy into the power grid, with significant engineering significance.

关键词：

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：