检索结果-内蒙古大学图书馆

Feature Selection for Cross-Scene Hyperspectral Image Classification via Improved Ant Colony optimization algorithm

IEEE ACCESS 2022年 10卷 102992-103012页

作者： Yu, Youhua Xie, Xiaolan Tang, Yigang Liu, Yarong Guilin Univ Technol Coll Informat Sci & Engn Guilin 541000 Peoples R China Guangxi Key Lab Embedded Technol & Intelligent Guilin 541000 Peoples R China

Hyperspectral images (HSIs) generally contain a large amount of spectral bands (features), and the redundant information in them will cause the Hughes phenomenon in the classification process. And feature extraction and feature selection are the two main existing methods to effectively reduce the redundancy of spectral information in the field of HSIs classification. Compared with feature extraction methods, feature selection methods can preserve most of the features of the original HSIs data without losing their valuable details. However, most existing feature selection methods based on single scene (domain) perform poorly in some scenes (domains) with insufficient labeled samples. Therefore, how to adopt an efficient feature selection method to select the optimal feature subsets of source scene and target scene and use the sample information of source scene to assist in the classification of target scene so as to improve the classification accuracy of images in the target scene as much as possible is still very challenging. In order to solve the above problem, this paper proposes a new cross-scene algorithm: Improved Ant Colony optimization algorithm-Based Cross-Scene Feature Selection algorithm (IMACO-CSFS). In order to obtain more accurate feature subsets of the two scenes, IMACO-CSFS proposes a priority sorting-based ant colony strategy to make the subsequent search process focus on the global optimal solution (optimal feature subset) found in the previous iteration. In addition, in order to further accelerate the convergence speed of the global optimal solution, an ant colony strategy based on elite ants is proposed in IMACO-CSFS to more efficiently obtain the optimal feature subsets of the two scenes for training the classifier. Furthermore, this paper simultaneously considers overall classification accuracies of the optimal feature subsets for both scenes and dynamically adjusts their scale to ensure the consistency of the selected features between the two s

关键词： Feature extraction Ant colony optimization Support vector machines Hyperspectral imaging optimization Convergence Classification algorithms Image analysis Cross-scene IMACO-FS hyperspectral image cross-scene feature selection algorithm optimization

来源：评论

学校读者我要写书评

暂无评论

algorithm/Hardware Co-optimization for Sparsity-Aware SpMM Acceleration of GNNs

引用

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 2023年第12期42卷 4763-4776页

作者： Gao, Yingxue Gong, Lei Wang, Chao Wang, Teng Li, Xi Zhou, Xuehai Univ Sci & Technol China Dept Comp Sci Hefei 230026 Anhui Peoples R China

In recent years, graph neural networks (GNNs) have achieved impressive performance in various application fields by extracting information from graph-structured data. It contains extensive feature aggregation operations and has become a performance bottleneck, which can be abstracted as a specialized sparse-dense matrix multiplication (SpMM) operation. Previous works have leveraged the inner product or outer product to accelerate the feature aggregation process. However, inefficient execution leads to extremely unbalanced workloads and extensive intermediate data, hampering the performance of previous processors. So in this article, we demonstrate an algorithm/hardware co-optimization chance to enhance SpMM acceleration for GNNs. First, the algorithm part develops a dataflow-efficient SpMM algorithm that integrates three optimization methods to mitigate computation and memory access inefficiencies. Specifically, 1) the proposed equal-value partition method achieves fine-grained data partition and enables load balancing during data movement;2) after observing the vertex aggregation phenomenon, a vertex-clustering optimization method is presented to enable significant data locality;and 3) the adaptive dataflow based on Gustavson's algorithm is further implemented to enable the efficient distribution of sparse elements and improves computing resource utilization. Then, the hardware part features the proposed SpMM algorithm and customizes SDMA, a flexible and efficient accelerator to boost SpMM acceleration, which follows the adaptive dataflow to eliminate sparsity and explore the regular parallelism dimension. Finally, we prototype SDMA on the Xilinx Alveo U280 FPGA accelerator card. The results demonstrate that SDMA achieves 5.68x-14.68x energy efficiency over the previous GPU implementations deployed on the Nvidia GTX 1080Ti and 1.32x higher throughput over the state-of-the-art FPGA prototype.

关键词： algorithm optimization graph neural networks (GNNs) hardware acceleration sparse-dense matrix-multiplication (SpMM)

来源：评论

学校读者我要写书评

暂无评论

An Integrated Solution to Improve the Environment Awareness and Path Planning Efficiency of Smart Wheelchairs 5th

An Integrated Solution to Improve the Environment Awareness ...

引用

5th China Intelligent Robotics Academic Conference

作者： Liu, Chunfang Bin Lu Shang, Yan Beijing Univ Technol Beijing 10 Peoples R China

ISBN: (纸本)9789819616138;9789819616145

Given the important role and significance of smart wheelchairs in helping elderly peoplemove and improving their navigation ability in complex environments with dynamic obstacles, this paper studies a comprehensive method based on laser vision mapping and navigation to improve the environment perception and navigation ability of smart wheelchairs. We use V-LOAM for environmental mapping and mix visual and liDAR data for high-precision map construction. For global path planning, we improve the A* algorithm, introduce heuristic function optimization and path smoothing, and improve the planning efficiency and path quality. For local obstacle avoidance, the dynamic window algorithm (DWA) is used to respond to environmental changes in real time to ensure safety. The results of the experiment demonstrate that this approach excels in constructing maps, planning global paths, and avoiding local obstacles. Furthermore, it enhances the navigation capabilities of intelligent wheelchairs within dynamic environments. In the future, we will further optimize and expand the application scenario to verify its wide applicability and robustness.

关键词： Obstacle Escaping Path Planning algorithm optimization

来源：评论

学校读者我要写书评

暂无评论

Analysis of Network Coverage optimization Based on Feedback K-Means Clustering and Artificial Fish Swarm algorithm

引用

IEEE ACCESS 2020年 8卷 42864-42876页

作者： Feng, Yingying Zhao, Shasha Liu, Hui Fuyang Normal Univ Coll Informat Engn Fuyang 236041 Peoples R China

There is a certain energy loss in the process of wireless sensor network information collection. Moreover, the current network protocols and network coverage methods are not sufficient to effectively reduce system energy consumption. In order to improve the operating efficiency and service life of wireless sensor networks, this study analyzes the classic LEACH protocol, summarizes the advantages and disadvantages, and proposes a targeted clustering method based on the K-means algorithm. At the same time, in order to maximize the network coverage and minimize the energy consumption on the basis of ensuring the quality of service, a wireless sensor network coverage optimization method based on an improved artificial fish swarm algorithm was proposed. In addition, a controlled experiment is designed to analyze the effectiveness and practical effects of the proposed algorithm. The experimental results show that the method proposed in this paper has certain advantages over traditional methods and can provide theoretical references for subsequent related research.

关键词： Feedback K-means clustering artificial fish swarm algorithm network coverage algorithm optimization

来源：评论

学校读者我要写书评

暂无评论

An efficient algorithm for CCHP system sizing and an operational optimization model based on LP

引用

JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING 2015年 25卷 189-196页

作者： Qin, Chaokui Tang, Jixu Zhang, Yang TONGJI Univ Sch Mech Engn Shanghai 201804 Peoples R China

The economic benefit gained from a combined cooling heating and power (CCHP) system depends on many factors. It is essential to optimize the system configuration and operational scheme as early in the design stage as possible. In this paper, a sizing optimization model (SOM) focused on the minimum annual total cost (ATC) and an operational optimization model (OOM) focused on the minimum annual energy charge (AEC) were established. The former was used to determine the optimal capacity of a CCHP system, whereas the latter was used to provide the optimal schemes. Both the SOM and OOM contain large numbers of hourly linear programming (LP) models, and the solution processes of both models proved to be quite time-consuming when the conventional iterative method was used. In this study, a piecewise elimination method was proposed for hourly LP models, and a graphical method in which the iteration was converted to an algebraic matrix was introduced to greatly improve the computational efficiency. The results demonstrated that the calculation time was reduced from 84.496 s for the conventional solution to 0.017 s for the graphical method in the OOM. The CCHP system SOM contains an OOM, and the calculation time was only 0.41 s when using the graphical method, whereas the conventional iterative method took 2367 s. The impact of gas price upon the optimal operational schemes and the equipment capacity was discussed for a building application in Shanghai. The improved efficiency of the calculation method could be helpful to compare different schemes and to perform sensitivity analyses. (C) 2015 Elsevier B.V. All rights reserved.

关键词： CCHP Linear programming Graphical method algorithm optimization Sizing optimization Operational scheme optimization

来源：评论

学校读者我要写书评

暂无评论

optimization of adaptive media player algorithm for smart TV terminal

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2019年第5期37卷 5925-5934页

作者： Qi, Bo Harbin Normal Univ Sch Media Harbin 150080 Heilongjiang Peoples R China

The emergence of resource conflicts and overload control problems during the playback of smart TV terminals has brought many obstacles to the operation of smart TV terminals, which has seriously affected the user experience of smart TV terminal users. In this regard, the adaptive media playback algorithm is optimized for smart TV terminals. This method performs dynamic priority preemptive scheduling on exclusive resources according to resource characteristics and application priorities to optimize resource allocation and improve media playback. The feedback control algorithm is used to perform QoS scheduling on shared resources until QoS proportional fairness is achieved, and QoS proportional compression is used to eliminate resource overload. Finally, a DASH server on Apache and implements an analog DASH client using Python are built. In order to verify the performance of the algorithm, the research results show that the adaptive media playback algorithm has the overload control capability, which only solves the resource conflict and improves the response performance under heavy load of the system, and the algorithm consumes only 4.5% of the overall system QoS. Compared with the existing methods, it is about 30% lower, which is more suitable for resource scheduling of smart TV terminals. The research in this paper shows that the adoption of QoS scheduling mechanism contributes to the optimization of media playback resources and allocation ratio, thus making the playback process of smart TV terminals, which provides a reference for the optimization of smart TV terminal playback.

关键词： Smart TV terminal media playback algorithm optimization

来源：评论

学校读者我要写书评

暂无评论

optimization study of a clustering algorithm for cosmic-ray muon scattering tomography used in fast inspection

引用

NUCLEAR ENGINEERING AND TECHNOLOGY 2021年第1期53卷 208-215页

作者： Hou, Linjun Huo, Yonggang Zuo, Wenming Yao, Qingxu Yang, Jianqing Zhang, Quanhu Xian Res Inst Hitech Xian 710025 Peoples R China

Cosmic-ray muon scattering tomography (MST) technology is a new radiation imaging technology with unique advantages. As the performance of its image reconstruction algorithm has a crucial influence on the imaging quality, researches on this algorithm are of great significance to the development and application of this technology. In this paper, a fast inspection algorithm based on clustering analysis for the identification of the existence of nuclear materials is studied and optimized. Firstly, the principles of MST technology and a binned clustering algorithm were introduced, and then several simulation ex-periments were carried out using Geant4 toolkit to test the effects of exposure time, algorithm parameter, the size and structure of object on the performance of the algorithm. Based on these, we proposed two optimization methods for the clustering algorithm: the optimization of vertical distance coefficient and the displacement of sub-volumes. Finally, several sets of experiments were designed to validate the optimization effect, and the results showed that these two optimization methods could significantly enhance the distinguishing ability of the algorithm for different materials, help to obtain more details in practical applications, and was therefore of great importance to the development and application of the MST technology. (c) 2020 Korean Nuclear Society, Published by Elsevier Korea LLC. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： Radiation tomography algorithm optimization Muon scattering tomography Nuclear safety

来源：评论

学校读者我要写书评

暂无评论

Research on Configuration Data Generation algorithm for HyperParser 5

Research on Configuration Data Generation Algorithm for Hype...

引用

5th IEEE International Conference on Power, Electronics and Computer Applications, ICPECA 2025

作者： Ma, Peijun Zhao, Gongzhi Shi, Jiangyi Yao, Cong Pan, Weitao Xidian University Xi'an China

ISBN: (纸本)9798331533694

The evolution of technologies such as Big Data, Cloud Computing, and Artificial Intelligence is inextricably linked to the transmission of network data. Programmable network devices that facilitate high-speed processing are becoming increasingly crucial. The significance of programmable parsers, as a constituent element of programmable network devices, is readily apparent. HyperParser has the advantages of low latency, high throughput, small area, low power consumption, and full programmability, but its configuration data generation algorithm is inefficient and has limited optimality. In this paper, the inefficiency in running speed is first optimized by subtree partitioning, and the preference for removing certain columns more conducive to approaching the global optimal solution is then analyzed from a probabilistic point of view. Using the big-union, edge network and enterprise network three kinds of parse graph test, the original algorithm in processing big-union in 10min failed to end the run, processing the rest of the two parse graphs consumed 0.1545s, 0.1513s, extracted the number of key bits 7 and 18;the algorithm proposed in this paper processing the three kinds of parse graphs consumed 3.679s, 0.019s and 0.019s, 3.679s, 0.019s and 0.027s, and the number of key bits extracted are 160, 7 and 17 respectively. © 2025 IEEE.

关键词： algorithm optimization HyperParser Programmable Parser

来源：评论

学校读者我要写书评

暂无评论

Design and optimization of Privacy Protection algorithms in Hospital Information Systems 24

Design and Optimization of Privacy Protection Algorithms in ...

引用

Proceedings of the 7th International Conference on Information Technologies and Electrical Engineering

作者： Hong Chang Xijie Dong State Grid Beijing Electric Power Hospital Information Center Beijing China Guozhong Healthcare Co. Ltd. Beijing China

ISBN: (纸本)9798400707087

This study aims to enhance privacy protection algorithms in hospital information systems by proposing a differential privacy approach to secure patients' sensitive data. The study initially looked into the necessity for privacy protections in hospital information systems, stressing the significance of balancing privacy and data usefulness when handling medical information. The differential privacy mechanism was implemented to address privacy leakage risks during data anonymization, leading to enhanced data processing efficiency. The experimental design used a simulated hospital information system data set to analyze and verify the performance of the proposed algorithm, proving its effectiveness under different privacy parameter settings. The experimental results show that the algorithm can achieve a good balance between data practicality and privacy protection, and improve computational efficiency, which is suitable for large-scale medical data processing. The research also investigated how various privacy settings affect algorithm efficiency, offering valuable insight for implementing hospital information systems. The study's successful execution established the groundwork for using privacy protection algorithms in the medical sector, and introduced a privacy protection technique that can serve as a model for other industries with sensitive data.

关键词： algorithm optimization

来源：评论

学校读者我要写书评

暂无评论

optimization of Forward Collision Warning algorithm Considering Truck Driver Response Behavior Characteristics

引用

ACCIDENT ANALYSIS AND PREVENTION 2024年 198卷 107450页

作者： Bao, Yanli Wang, Xuesong Tongji Univ Coll Transportat Engn Shanghai Peoples R China Minist Educ Key Lab Rd & Traff Engn Shanghai Peoples R China Natl Engn Lab Integrated Optimizat Rd Traff & Safe Wuxi Peoples R China

Forward collision warning (FCW) systems have been widely used in trucks to alert drivers of potential road situations so they can reduce the risk of crashes. Research on FCW use shows, however, that there are differences in drivers' responses to FCW alerts under different scenarios. Existing FCW algorithms do not take differences in driver response behavior into account, with the consequence that the algorithms' minimum safe distance assessments that trigger the warnings are not always appropriate for every driver or situation. To reduce false alarms, this study analyzed truck driver behavior in response to FCW warnings, and k-means clustering was adopted to classify driver response behavior into three categories: Response Before Warning (RBW), Response After Warning (RAW), and No Response (NR). Results showed that RBW clusters tend to occur at long following distances (>19 m), and drivers applied braking before the warning. In RAW clusters, deceleration after warning is significantly more forceful than before warning. NR clusters occur at short distances, and deceleration fluctuates only slightly. To optimize the FCW algorithm, the warning distance was divided into reaction distance and braking distance. The linear support vector machine was used to fit the driver reaction distance. The long shortterm memory method was used to predict braking distance based on each of the three response scenarios: R2 was 0.896 for RAW scenarios, 0.927 for RBW scenarios, and 0.980 for NR scenarios. Verification results show that the optimized truck FCW algorithm improved safety by 1 % to 5.1 %;accuracy reached 97.92 %, and the false alarm rate was 1.73 %.

关键词： Truck forward collision warning algorithm optimization Active safety system data Response behavior 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：