检索结果-内蒙古大学图书馆

Scheduling Algorithm for Low Energy Consumable Parallel Task Application Based on DVFS 1

7th International Conference on Smart Computing and Communication, SmartCom 2022

作者： Liu, Xun Zhao, Hui College of Computer Science and Technology Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan China Henan University Kaifeng475000 China

ISBN: (数字)9783031281242

ISBN: (纸本)9783031281235

With the continuous improvement of various high-performance computing systems, various data centers had also been fully expanded. Energy consumption and actual performance measurement were very important indicators, which were also key issues in how to judge parallel calls for some tasks in high-performance computer systems. Modern processors were basically equipped with software control functions such as DVFS (Dynamic Voltage Frequency Scaling), in the actual system operation to ensure that the system could ensure the reasonable operation of the system while reducing energy consumption indicators. This paper considered how the designed scheduling algorithm first divides tasks reasonably to ensure that the maximum completion time and energy consumption of the processor were sufficiently reduced when the directed acyclic graph was executed. Then considered making reasonable adjustments to the processor frequency using DVFS technology to adapt to the task while ensuring the critical path of the task. At the end of the article, make sure that the experimental verification algorithm could ensure that the task was completed and could reduce the energy consumption during task execution as much as possible. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Morphotectonic Analyses of LiDAR-Derived DEMs:Insights into Tectonic Activity of the Xinhua Fault within the Three Gorges Area(Central China)

引用

Journal of Earth Science 2025年第2期36卷 823-829页

作者： Xiaofeng Wang Xiaohan Yin Tonghui Liu Xuan Li Hongming Wang Yaqi Zhong Gang Rao School of Computer and the Hubei Key Laboratory of Intelligent Geo-Information Processing China University of Geosciences(Wuhan)Wuhan 430078China School of Geoscience and Technology Southwest Petroleum UniversityChengdu 610500China School of Earth Sciences China University of Geosciences(Wuhan)Wuhan 430074China Hubei Communications Planning and Design Institute Co. Ltd.Wuhan 430051China School of Economics and Management Shandong Jiaotong UniversityJinan 250357China

0 *** global availability of digital elevation model(DEM)data,such as 90-m Shuttle Radar Topography Mission(SRTM)DEM and 30-m Advanced Spaceborne Thermal Emission and Reflection Radiometer Global Digital Elevation Model(ASTER GDEM),has been extensively utilized in morphotectonic analyses(e.g.,Wang et al.,2024;Cheng et al.,2018;Pérez-Pe?a et al.,2010;El Hamdouni et al.,2008).

关键词： xinhua fault morphotectonic analyses egwang three gorges area digital elevation model aster lidar derived dems tectonic activity morphotectonic analyses digital elevation model dem datasuch

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach Combining Decoupling Training with Prototype-based Contrastive Learning for Tracking Long-Tailed Recording in Optical Aerial Imagery

A Novel Approach Combining Decoupling Training with Prototyp...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Jianlin Xie Guanqun Wang Tong Zhang Shilong Fan Yin Zhuang He Chen National Key Laboratory of Science & Technology on Space-Born Intelligent Information Processing (SBIIP) Beijing Institute of Technology Beijing China National Key Laboratory for Multimedia Information Processing Peking University Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Scene classification is a classical task in optical aerial imagery. In practical applications, it is difficult to obtain a balanced training samples supporting model training. Therefore, the dataset usually follow the Long-Tailed distribution, which is challenge for classification task, especially for multi-categories scene classification. It would make model intend to learn the representation of head classes with majority samples, which lead to under-represent middle and tail classes with minority samples and affect a better classifier construction for long-tailed classification. In this article, a novel Prototypical Supervised Contrastive Learning Based on Decoupling Framework called PSCL-DF is proposed for Long-Tailed Classification in Optical Remote Sensing Imagery to make a better feature learning and better classifier leaning. Finally, extensive tests are performed on the two artificially generated long-tailed datasets, demonstrating the robustness and effectiveness of the proposed methods. Our results show that decoupling feature extraction and classification achieve significant performance gains.

关键词： Training Integrated optics Scene classification Heavily-tailed distribution Optical recording Contrastive learning Optical imaging Feature extraction Optical sensors Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Qinghai Embroidery Classification System and intelligent Classification Research

Qinghai Embroidery Classification System and Intelligent Cla...

引用

作者： Xiaofei Lin Zhonglin Ye Haixing Zhao College of Computer Qinghai Normal University The State Key Laboratory of Tibetan Intelligent Information Processing and Application Tibetan Information Processing and Machine Translation Key Laboratory of Qinghai Province Key Laboratory of Tibetan Information Processing Ministry of Education

Qinghai embroidery is an artistic treasure of folk embroidery in Qinghai Province. Classifying them to understand the differences between them is an important task. However, currently, there is a lack of a systematic classification method for Qinghai embroidery. First, by studying the history of Qinghai embroidery and a large number of Qinghai embroidery patterns, this paper divides Qinghai embroidery patterns into three categories: animals and plants, auspicious meanings, and geometric decoration. This method breaks through the regional classification system for the Qinghai embroidery. Second, this article utilizes four CNN models to classify the Qinghai embroidery datasets, exploring the differences in the classification of Qinghai embroidery by different models and finding the optimal classification model. The results show that the Goog Le Net model performs the best in the classification of Qinghai embroidery images, achieving the highest accuracy rate. This is mainly due to the small size of the Qinghai embroidery datasets and the application of the Inception structure and batch normalization technology in the Goog Le Net model, enabling it to better extract features and classify Qinghai embroidery images. Through this research, we can provide a certain reference and assistance for the classification of Qinghai embroidery images and provide technical support for the protection and inheritance of cultural heritage.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fre-Yolo: Feature Refinement Extraction Network with Yolo for Blade Tip Small Point Light Detection

SSRN

引用

SSRN 2024年

作者： Zheng, Wenhao Xiong, Bangshu Yi, Hui Au, Qiaofeng Chen, Jiujiu Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang330063 China China Helicopter Research and Development Institute China

Detecting blade tip point light sources based on airborne computer vision is a critical step in measuring blade tip distance for coaxial unmanned helicopters. However, detecting blade tip point light sources quickly and highly accurately in a helicopter airborne environment is a challenge due to the extremely tiny imaging size of the blade tip point light sources. To this end, we propose a FRE-YOLO for detecting blade tip point light sources based on the YOLO network structure. In this work, we focus on designing a Feature Refinement Extraction network (FRE), which can greatly enrich the feature information of small targets during Backbone downsampling. Secondly, we also design a new paradigm Smooth Gaussian Distance (SmoothGD) which measures the degree of target bounding box matching. SmoothGD is mainly applied to regression loss calculation and label assigner, which can effectively improve the small target detection accuracy. Meanwhile, we construct the Blade Tip Point Light (BTPL) dataset for the network training. In addition, in order to evaluate the effectiveness of the proposed method more fairly, this paper conducts the same experiments on BTPL and the small target dataset VisDrone on MMYOLO. A large amount of experimental data shows that the proposed method has a positive impact on the detection of tiny point sources at the tip of the blade. It is also at the advanced level in the field of generalized small object detection. © 2024, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

A comparative study of four nonlinear dynamic methods and their applications in classification of ship-radiated noise

引用

Defence Technology（防务技术） 2022年第2期18卷 183-193页

作者： Yu-xing Li Shang-bin Jiao Bo Geng Qing Zhang You-min Zhang School of Automation and Information Engineering Xi’an University of TechnologyXi’an710048China Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an University of TechnologyXi’an710048China Department of Mechanical Industrial and Aerospace EngineeringConcordia UniversityMontrealQuebec H3G 1M8Canada

Refined composite multi-scale dispersion entropy(RCMDE),as a new and effective nonlinear dynamic method,has been applied in the field of medical diagnosis and fault *** this paper,we first introduce RCMDE into the field of underwater acoustic signal processing for complexity feature extraction of ship radiated noise,and then propose a novel classification method for ship-radiated noise based on RCMDE and k-nearest neighbor(KNN),termed *** results of a comparative experiment show that the proposed RCMDE-KNN classification method can effectively extract the complexity features of ship-radiated noise,and has better classification performance under one and two scales than the other three classification methods based on multi-scale permutation entropy(MPE)and KNN,multi-scale weighted-permutation entropy(MW-PE)and KNN,and multi-scale dispersion entropy(MDE)and KNN,termed MPE-KNN,MW-PE-KNN,and *** is proved that the RCMDE-KNN classification method for ship-radiated noise is feasible and effective,and can obtain a very high recognition rate.

关键词： Nonlinear dynamic Refined composite multi-scale dispersion entropy(RCMDE) Multi-scale dispersion entropy(MDE) Multi-scale weighted-permutation entropy (MW-PE) Multi-scale permutation entropy(MPE) Classification of ship-radiated noise

来源：评论

学校读者我要写书评

暂无评论

Research on Link Prediction Algorithms Based on Multichannel Structure Modelling

Research on Link Prediction Algorithms Based on Multichannel...

引用

作者： Gege Li Lin Zhou Zhonglin Ye Haixing Zhao College of Computer Qinghai Normal University The State Key Laboratory of Tibetan Intelligent Information Processing and Application Tibetan Information Processing and Machine Translation Key Laboratory of Qinghai Province Key Laboratory of Tibetan Information Processing Ministry of Education

Today's link prediction methods are based on the network structure using a single-channel approach for prediction, and there is a lack of link prediction algorithms constructed from a multichannel approach, which makes the features monotonous and noncomplementary. To address this problem, this paper proposes a link prediction algorithm based on multichannel structure modelling(MCLP).First, the network is sampled three times to construct its three subgraph ***, the node representation vectors of the network are learned separately for each subgraph on a single channel. Then, the three node representation vectors are combined, and the similarity matrix is calculated for the combined vectors. Finally,the performance of the MCLP algorithm is evaluated by calculating the AUC using the similarity matrix and conducting multiple experiments on three citation network datasets. The experimental results show that the proposed link prediction algorithm has an AUC of 98.92%, which is better than the performance of the 24link prediction comparison algorithms used in this paper. The experimental results sufficiently prove that the MCLP algorithm can effectively extract the relationships between network nodes, and confirm its effectiveness and feasibility.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Wb-Lrp: Layer-Wise Relevance Propagation with Weight-Dependent Baseline

SSRN

引用

SSRN 2023年

作者： Li, Yanshan Liang, Huajie Zheng, Lirong Institute of Intelligent Information Processing Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

The message passing process of neural networks implies the feature extraction methods and inference patterns of neural networks. In this paper, we delve into the internal structure of neural networks and provide an instance-level interpretation of neural networks by investigating a Layer-wise Relevance Propagation (LRP) algorithm from the perspective of message passing. First, we derive the baselines of different existing LRP algorithms according to the theory of DeepLift algorithms, finding a problem that the baselines of these algorithms are independent of model weights or sample features, or both. Second, the Weight-dependent Baseline Layer-wise Relevance Propagation (WB-LRP) algorithm based on weight-dependent baseline is proposed to address this problem, and the norm-invariant rule (m-rule) is introduced accordingly. Then, the m-rule is extended to the positive norm-invariant rule (m+-rule) when focusing only on the forward activation of the weights. Finally, the proposed theory of WB-LRP is extended to different baselines settings to construct a framework that encompasses almost all existing LRP algorithms and a small number of interpretation algorithms that use gradient back-propagation. Experimental results show that the interpretation of relevance depends on two factors, model weights and sample features. The proposed WB-LRP algorithm can be designed with different baselines, so that the proportion of visualization results from model weights and from sample features can be adjusted to visualize the relevance of sample features and model weights for the target category, respectively. © 2023, The Authors. All rights reserved.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

A Multitask Learning Approach for Chinese National Instruments recognition and Timbre Space Regression 9th

A Multitask Learning Approach for Chinese National Instrumen...

引用

9th Conference on Sound and Music Technology, CSMT 2021

作者： Xu, Shenyang Jiang, Yiliang Li, Zijin Sun, Xiaoheng Li, Wei Central Conservatory of Music Beijing100031 China School of Computer Science and Technology Fudan University Shanghai200438 China Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai200433 China

ISBN: (纸本)9789811947025

Musical instrument recognition is an essential task in the domain of music information retrieval. So far, most existing research are focused on western instruments. In this research, we turn to Chinese national instruments recognition. First, a dataset containing 30 Chinese national instruments is created. Then, a well-designed end-to-end Convolutional Recurrent Neural Network is proposed. Moreover, we combine instrument recognition with instrument timbre space regression using a multitask learning approach to improve performances of both tasks. We conduct experiments in instrument recognition and timbre space regression to evaluate our model and multitask learning approach. Experimental results show that our proposed model outperforms previous algorithms, and the multitask approach can further improve the results. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation Strategy for MI Communication-Based UWSN in Ocean Current Scenario

Resource Allocation Strategy for MI Communication-Based UWSN...

引用

2025 IEEE Wireless Communications and Networking Conference, WCNC 2025

作者： Zhang, Tao Zhao, Yisheng Zhang, Shen Liu, Peng Hu, Zhiyi College of Physics and Information Engineering Fuzhou University Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information Fuzhou China

ISBN: (纸本)9798350368369

Aiming at the problems of low data rate and limited battery power of traditional underwater wireless sensor network (UWSN) based on acoustic communication, a resource allocation strategy for magnetic induction (MI) communication-based UWSN in ocean current scenario is investigated in this paper. Specifically, multiple sensor nodes (SNs) are distributed in seawater at different depths. First, an autonomous underwater vehicle (AUV) is introduced to charge the SNs by magnetic coupling resonant wireless power transfer (MCR-WPT) technology. Then, the SNs transmit data to the AUV through MI communication. The influence of the ocean current on the SNs and AUV is analyzed. A genetic algorithm-based particle swarm optimization algorithm is used to optimize the AUV navigation trajectory. After collecting the data from the SNs, the AUV moves to the position under a surface base station and sends the collected data to the surface base station by MI communication. To minimize system energy consumption, the transmitting power of AUV and SNs are jointly optimized under the constraints of energy causality and transmitting power. The suboptimal solution to the formulated optimization problem is obtained by adopting the improved sparrow search algorithm (ISSA) combining Cauchy variation and reverse learning. Simulation results show that the ISSA has lower system energy consumption than other benchmark methods. © 2025 IEEE.

关键词： Energy utilization

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：