检索结果-内蒙古大学图书馆

Controlled-source electromagnetic noise attenuation via a deep convolutional neural network and high-quality sounding curve screening mechanism

引用

Geophysics 2025年第3期90卷 WA125-WA140页

作者： Liu, Yecheng Li, Diquan Li, Jin Zhang, Xian Central South University Monitoring Ministry of Education Key Laboratory of Metallogenic Prediction of Nonferrous Metals and Geological Environment Changsha China Hunan Provincial Key Laboratory of Non-ferrous Resources and Geological Hazard Detection Changsha China Central South University School of Geoscience and Info-physics Changsha China Hunan Normal University College of Information Science and Engineering Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Changsha China Hunan University of Finance and Economics School of Information Technology and Management Hunan Provincial Key Laboratory of Finance & Economics Big Data Science and Technology Changsha China

Strong noise is one of the biggest challenges in controlled-source electromagnetic (CSEM) exploration, which severely affects the quality of the recorded signal. We develop a novel and effective CSEM noise attenuation method that integrates a deep convolutional neural network (DCNN) with a high-quality sounding curve screening mechanism. This method first uses a DCNN to learn the large-scale noise characteristics of CSEM measured data and build a DCNN denoising model for attenuating the noise. Because some impulse noise remains after DCNN denoising, the high-quality sounding curve screening mechanism is innovatively applied to optimize the DCNN denoised data. The core of this method is the smoothness value (SV), which quantitatively evaluates the smoothness of the sounding curve (apparent resistivity curve). In effect, the mechanism segments the overall DCNN denoised data and calculates the corresponding sounding curve and its SV for each segment. The highest-quality sounding curve can be screened out by comparing the SVs of all curves as well as obtaining the highest-quality data segment present in the overall DCNN denoised data. Finally, our method is validated with synthetic and field data, demonstrating its feasibility and effectiveness in attenuating large-scale CSEM noise. The quality of CSEM data, which is heavily affected by noise, is significantly improved after processing by our method. © 2025 Society of Exploration Geophysicists. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Further results on permutation pentanomials over Fq3 in characteristic two

arXiv

引用

arXiv 2025年

作者： Zhang, Tongliang Zheng, Lijing Wang, Hengtai Peng, Jie Li, Yanjun College of Science North China University of Science and Technology Hebei Tangshan063000 China Hebei Key Laboratory of Data Science and Application North China University of Science and Technology Hebei Tangshan063000 China School of Mathematics and Physics University of South China Hunan Hengyang421001 China Mathematics and Science College Shanghai Normal University Shanghai200234 China Institute of Statistics and Applied Mathematics Anhui University of Finance and Economics Anhui Bengbu233030 China

Let q = 2m. In a recent paper [31], Zhang and Zheng investigated several classes of permutation pentanomials of the form ϵ0xd0+L(ϵ1xd1+ϵ2xd2) over Fq3 (d0 = 1, 2, 4) from some certain linearized polynomial L(x) by using multivariate method and some techniques to determine the number of the solutions of some equations. They proposed an open problem that there are still some permutation pentanomials of that form have not been proven. In this paper, inspired by the idea of [12], we further characterize the permutation property of the pentanomials with the above form over Fq3 (d0 = 1, 2, 4). The techniques in this paper would be useful to investigate more new classes of permutation pentanomials. Copyright © 2025, The Authors. All rights reserved.

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

A federated learning scheme meets dynamic differential privacy

引用

CAAI Transactions on Intelligence technology 2023年第3期8卷 1087-1100页

作者： Shengnan Guo Xibin Wang Shigong Long Hai Liu Liu Hai Toong Hai Sam State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyangChina School of Big Data Key Laboratory of Electric Power Big Data of Guizhou ProvinceGuizhou Institute of TechnologyGuiyangChina School of Information Guizhou University of Finance and EconomicsGuiyangChina Faculty of Business and Communication INTI International UniversityNilaiMalaysia

Federated learning is a widely used distributed learning approach in recent years,however,despite model training from collecting data become to gathering parameters,privacy violations may occur when publishing and sharing models.A dynamic approach is pro-posed to add Gaussian noise more effectively and apply differential privacy to federal deep ***,it is abandoning the traditional way of equally distributing the privacy budget e and adjusting the privacy budget to accommodate gradient descent federation learning dynamically,where the parameters depend on computation derived to avoid the impact on the algorithm that hyperparameters are created *** also incorporates adaptive threshold cropping to control the sensitivity,and finally,moments accountant is used to counting the∈consumed on the privacy‐preserving,and learning is stopped only if the∈_(total)by clients setting is reached,this allows the privacy budget to be adequately explored for model *** experimental results on real datasets show that the method training has almost the same effect as the model learning of non‐privacy,which is significantly better than the differential privacy method used by TensorFlow.

关键词： data privacy machine learning security of data

来源：评论

学校读者我要写书评

暂无评论

Enhanced hierarchical attention mechanism for mixed MIL in automatic Gleason grading and scoring

引用

Scientific Reports 2025年第1期15卷 1-14页

作者： Ren, Meili Huang, Mengxing Zhang, Yu Zhang, Zhijun Ren, Meiyan Hainan Provincial Key Laboratory of Big Data and Smart Service Hainan University Haikou 570228 China Center of Network and Information Education Technology Shanxi University of Finance and Economics Taiyuan 030006 China School of Medical Shanxi Datong University Datong 037009 China

Segmenting histological images and analyzing relevant regions are crucial for supporting pathologists in diagnosing various diseases. In prostate cancer diagnosis, Gleason grading and scoring relies on the recognition of different patterns in tissue samples. However, annotating large histological datasets is laborious, expensive, and often limited to slide-level or limited instance-level labels. To address this, we propose an enhanced hierarchical attention mechanism within a mixed multiple instance learning (MIL) model that effectively integrates slide-level and instance-level labels. Our hierarchical attention mechanism dynamically suppresses noisy instance-level labels while adaptively amplifying discriminative features, achieving a synergistic integration of global slide-level context and local superpixel patterns. This design significantly improves label utilization efficiency, leading to state-of-the-art performance in Gleason grading. Experimental results on the SICAPv2 and TMAs datasets demonstrate the superior performance of our model, achieving AUC scores of 0.9597 and 0.8889, respectively. Our work not only advances the state-of-the-art in Gleason grading but also highlights the potential of hierarchical attention mechanisms in mixed MIL models for medical image analysis. © The Author(s) 2025.

关键词： Gleason grading Hierarchical attention mechanism Multiple instance learning

来源：评论

学校读者我要写书评

暂无评论

Uniform Pricing Strategy vs. Price Differentiation Strategy in the Presence of Cost Saving and Demand Increasing

引用

Journal of Systems science & Complexity 2019年第3期32卷 932-946页

作者： CAI Qiang LUO Chunlin TIAN Xin WANG Shouyang School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy Sciences Beijing 100190 China School of Information Technology Jiangxi University of Finance and Economics Nanchang 330013 China Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing 100190 China

Price differentiation or discrimination strategy has been regarded as the best choice for firms with online and offline channels, however, recent years often witnessed the practices of the uniform pricing strategy. This paper aims to address the question whether the uniform pricing strategy may be better for the manufacturer, when the uniform pricing strategy has a positive impact on increasing the ciistomer demand and reducing the operations cost. The research shows that the uniform pricing strategy can be bet ter than the price differentiation strategy when the cost saving and demand increasing are large enough or the consumers' acceptance of online channel lies in a certain interval. Moreover, the manufac tu rers or brand owners need a tradeoff bet ween the benefit from online channel and the negative impact from the offline channel when they implement the price differentiation strategy. Finally, the authors obtain some managerial insights and implications based on the numerical analyses, which are in line with the phenomena in practice.

关键词： Cost saving demand increasing dual-channel price differentiation strategy uniform pricing strategy

来源：评论

学校读者我要写书评

暂无评论

Single inclusive hadron production at the LHC with an improved impact parameter dependent saturation model

引用

Chinese Physics C 2023年第6期47卷 89-98页

作者：弓晓锋蔡燕兵周代翠向文昌 Guizhou Science and Technology Information Center Guiyang 550002China Guizhou Key Laboratory of Big Data Statistic Analysis and Guizhou Key Laboratory in Physics and Related AreasGuizhou University of Finance and EconomicsGuiyang 550025China Key Laboratory of Quark and Lepton Physics(MOE) and Institute of Particle PhysicsCentral China Normal UniversityWuhan 430079China Physics Division Guangzhou Maritime UniversityGuangzhou 510725China

To obtain a reasonable description of the hadron production at the LHC energies,the impact parameter dependent saturation model is modified by inclusion of an anomalous dimensionγ,which controls the slope of the scattering amplitude in the transition from the dilute region to the saturation *** calculate the transverse momentum distribution and nuclear modification factor of theπ^(0)and charged hadrons with the improved model,and the results are consistent with measurements performed at the ***,we use the original impact parameter dependent model to study the aforementioned measurements performed at the LHC by adjusting its *** find that the improved model is more consistent with the experimental data than the original one,as the anomalous dimension plays a significant role in the suppression of the evolution of the scattering amplitude.

关键词： gluon saturation high energy heavy ion collisions small-x physics

来源：评论

学校读者我要写书评

暂无评论

LNAD: Towards Lightweight Network Anomaly Detection in Software-Defined Networking 22

LNAD: Towards Lightweight Network Anomaly Detection in Softw...

引用

22nd IEEE International Conference on High Performance Computing and Communications, 18th IEEE International Conference on Smart City and 6th IEEE International Conference on data science and Systems, HPCC-SmartCity-DSS 2020

作者： Cui, Yunhe Qian, Qing Xing, Huanlai Li, Saifei Guizhou University State Key Laboratory of Public Big Data School of Computer Science and Technology Guiyang China Guizhou University of Finance and Economics School of Information Guiyang China Southwest Jiaotong University School of Information Science and Technology Chengdu China

ISBN: (纸本)9781728176499

As an emerging architecture, Software-Defined Networking (SDN) is suffering from a lot of security issues. Network anomaly detection technology plays a crucial role in addressing SDN security issues. In SDN, the network status can be denoted by the packets or flow entries. Hence, the existing network anomaly detection methods are commonly designed based on inspecting packets or flow entries. Subsequently, these anomaly detection methods have to collect packets or flow entries from the underlying switches. More seriously, some anomaly detection methods even need to add extra modules to the switches. Unlike these existing network anomaly detection methods, this work proposes a lightweight network anomaly detection method. The main design principle of the proposed method is mining the inherent OpenFlow messages in SDN to represent the network status and further detect the network anomaly. The proposed method does not need to collect any additional messages from the underlying switches or add any additional modules to the underlying switches. The evaluation results demonstrate that the proposed network anomaly detection method can afford high detection accuracy and reduce the overhead of SDN controller. © 2020 IEEE.

关键词： Software defined networking

来源：评论

学校读者我要写书评

暂无评论

The Spatiotemporal Traffic Accident Risk Analysis in Urban Traffic Network 9th

The Spatiotemporal Traffic Accident Risk Analysis in Urban T...

引用

9th International Conference on Mobile Wireless Middleware, Operating Systems and Applications, MOBILWARE 2020

作者： Zhang, Chijun jin, Jing Huang, Qiuyang Du, Zhanwei Yuan, Zhilu Tang, Shengjun Liu, Yang School of Management Science and Information Engineering Jilin University of Finance and Economics Changchun130117 China Jilin Province Key Laboratory of Fintech Jilin University of Finance and Economics Changchun130117 China College of Computer Science and Technology Jilin University Changchun130012 China Research Institute for Smart Cities and Shenzhen Key Laboratory of Spatial Information Smart Sensing and Services School of Architecture and Urban Planning Shenzhen University Shenzhen China Jilin Big Data Research Center for Business Jilin University of Finance and Economics Changchun130117 China

ISBN: (纸本)9783030622046

Traffic accidents seriously threaten people’s lives and property all over the world. Therefore, it is of great significance to human society to have a long-term traffic accidents data with detail temporal and geographic information in a specific space, which can be used for traffic accident hotspots identification to reduce the incidence of traffic accidents. Here, we obtain a one-year dataset of traffic accidents of the city center in Changchun, Northeast China, in 2017. In this paper, we analyze the risk of traffic accident in urban area, and then discover the characteristics of traffic accidents at the temporal and spatial aspect. We construct a traffic network, which takes crossings as nodes and road sections as edges and weighted by the total number of traffic accidents. In addition, we integrate road structure data and meteorological data to explore the characteristics of the traffic network. © 2020, ICST Institute for Computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Risk analysis

来源：评论

学校读者我要写书评

暂无评论

System Design of a Mobile Dual-Arms Robot with Autonomous Navigation 4

System Design of a Mobile Dual-Arms Robot with Autonomous Na...

引用

4th International Conference on Robotics, Intelligent Control and Artificial Intelligence, RICAI 2022

作者： Guo, Jinjia Zhang, Zhijun School of Automation Science and Engineering South China University of Technology China The Shaanxi Provincial Key Laboratory of Industrial Automation School of Mechanical Engineering Shaanxi University of Technology School of Information Technology and Management Hunan University of Finance and Economics School of Automation Science and Engineering East China Jiaotong University School of Automation Guangdong University of Petrochemical Technology China

ISBN: (纸本)9781450398343

In this paper, a mobile dual-arms robot with autonomous navigation is designed and built. In order to build the robot, a four levels mobile chassis is firstly designed and set up at the bottom of the robot, which can realize the function of automatic navigation and obstacle avoidance. For the purpose of grasping and transporting objects or interaction with human beings or environment, two humanoid arms with eight degrees-of-freedoms are designed and fixed on the trunk of robot. A depth camera is installed on the robot's head to detect and locate objects in front of it. There is a touch screen on the chest of the robot, which can be used to operate the robot or display its status. With these combined functions, the robot can be used as a guider in the bank, business hall or as a housekeeper at home. © 2022 ACM.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

A Fragile Watermarking Algorithm for Speech Authentication by Modifying Least Significant Digits

A Fragile Watermarking Algorithm for Speech Authentication b...

引用

International Conference on Computers, Communications, and Systems (ICCCS)

作者： Qing Qian Yunhe Cui School of Information International Joint Research Center for Data Science and High-Performance Computing Guizhou University of Finance and Economics Guiyang China School of Computer Science and Technology Guizhou Provincial Key Laboratory of Public Big Data Guizhou University Guiyang China

ISBN: (数字)9781728161365

ISBN: (纸本)9781728161372

Speech content is often faced with malicious forgery and tampering in transit. Therefore, we introduce a novel fragile watermarking algorithm by modifying the least significant digits for speech content authentication and tampering recovery. In this letter, the proposed authentication scheme consists of two processes: the first one is watermark generation and embedding, the second one is content authentication and recovery. In the former process, the compressed speech signal, frame number and check information are generated based on speech content to form a watermark. Subsequently, the generated watermark is embedded into the least significant digits of speech sampling points using the proposed watermarking algorithm. In the latter process, the embedded watermark is utilized to locate the tampered area and recover that tampered content synchronously. Experimental results show that the proposed watermarking algorithm is fragile to common signal processing. Additionally, it has favorable inaudibility, accurate location ability and high recovery quality.

关键词： Watermarking Authentication Speech coding Signal to noise ratio Speech processing

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：