检索结果-内蒙古大学图书馆

Controlled-source electromagnetic signal detection using a hybrid deep learning model: Convolutional and long short-term memory neural networks

引用

Computers and Geosciences 2025年 204卷

作者： Liu, Yecheng Li, Diquan Li, Jin Hu, Yanfang Liu, Zijie Zhang, Xian School of Geosciences and Info-Physics Central South University Changsha 410083 China Key Laboratory of Metallogenic Prediction of Non-Ferrous Metals and Geological Environment Monitor Ministry of Education Central South University Changsha 410083 China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Hunan Normal University Changsha 410081 China Hunan Provincial Key Laboratory of Finance & Economics Big Data Science and Technology School of Information Technology and Management Hunan University of Finance and Economics Changsha 410205 China

Controlled-source electromagnetic (CSEM) method using a periodic transmitted signal source suppresses random noise by superimposing and averaging the recorded signal over multiple periods. However, it still faces great challenges in strong interference environments. Here we present a CSEM signal detection method based on a hybrid architecture of convolutional neural network (CNN) and long short-term memory neural network (LSTM). Our method improves the quality of the recorded signal by filtering out all the noise periods and retaining the useful signal periods. The core lies in combining the spatial feature extraction capability of CNN with the time series modeling capability of LSTM, which can deeply excavate the feature differences between noise and CSEM useful signal. Meanwhile, a classification model of signal and noise is constructed using a large-scale training dataset. This hybrid model exhibits superior performance compared to other deep learning models such as CNN or LSTM. Also, we propose a novel signal detection mechanism that not only maintains the periodicity of CSEM signal, but also greatly enhances processing efficiency. The results of synthetic and measured data demonstrate that our method can obtain useful signals from CSEM data containing different noise types and significantly improve the quality of sounding curves. In particular, our method is useful for CSEM signal detection in strong interference. © 2025 Elsevier Ltd

关键词： Controlled-source electromagnetic method Deep learning Noise Signal detection

来源：评论

学校读者我要写书评

暂无评论

Simulation Research on Nonlinear Modeling and Control of Switched Reluctance Motor 32

Simulation Research on Nonlinear Modeling and Control of Swi...

引用

32nd Chinese Control and Decision Conference, CCDC 2020

作者： Ru, Luan Zou, Hongjian Guo, Jinru Beijing University of Civil Engineering and Architecture School of Electrical and Information Engineering Beijing100044 China Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing100044 China

ISBN: (纸本)9781728158549

The model of a switched reluctance motor (SRM) directly influences it's performance and control effect. However, the doubly salient structure, switching power supply and seriously saturated magnetic circuit, make it difficult to accurately model. Aiming to solve this problem, this paper presents a new simulation method based on BP neural network to establish the current and torque models of a SRM. Using a great deal of current, flux linkage, torque numerical solution data obtained by a finite element software as the sample data, a kind of BP neural network is trained offline, and all the expected data sets, which form a table, are outputted. By looking-up the table the nonlinear models of flux linkage and torque of the SRM are obtained. On the basis of the nonlinear models, the current closed-loop control is formed by using the torque sharing function and the fuzzy switching angles to reduce the torque ripple. The simulation results show that the proposed nonlinear models not only have a fast calculation speed, but also are high precision and can meet the requirements of real-time control. The proposed control method can effectively reduce the torque ripple of the SRM. © 2020 IEEE.

关键词： Fuzzy control

来源：评论

学校读者我要写书评

暂无评论

Graph Edit Distance Reward: Learning to Edit Scene Graph 16th

Graph Edit Distance Reward: Learning to Edit Scene Graph

引用

16th European Conference on Computer Vision, ECCV 2020

作者： Chen, Lichang Lin, Guosheng Wang, Shijie Wu, Qingyao Nanyang Technological University Singapore Singapore Zhejiang University Hangzhou China Huazhong University of Science and Technology Wuhan China School of Software Engineering South China University of Technology Guangzhou China Key Laboratory of Big Data and Intelligent Robot Ministry of Education Beijing China

ISBN: (纸本)9783030585280

Scene Graph, as a vital tool to bridge the gap between language domain and image domain, has been widely adopted in the cross-modality task like VQA. In this paper, we propose a new method to edit the scene graph according to the user instructions, which has never been explored. To be specific, in order to learn editing scene graphs as the semantics given by texts, we propose a Graph Edit Distance Reward, which is based on the Policy Gradient and Graph Matching algorithm, to optimize neural symbolic model. In the context of text-editing image retrieval, we validate the effectiveness of our method in CSS and CRIR dataset. Besides, CRIR is a new synthetic dataset generated by us, which we will publish soon for future use. © 2020, Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Flow characteristics in open channels with aquatic rigid vegetation

引用

Journal of Hydrodynamics 2020年第6期32卷 1100-1108页

作者： Yan-jie Wu He-fang Jing Chun-guang Li Ying-ting Song College of Civil and Hydraulic Engineering Hefei University of TechnologyHefei230009China School of Civil Engineering North Minzu UniversityYinchuan750021China Key Laboratory of Intelligent Information and Big Data Processing of Ningxia Province Yinchuan750021China Research Institute of Numerical Computation and Engineering Applications North Minzu UniversityYinchuan750021China State Key Laboratory of Hydraulic Engineering Simulation and Safety Tianjin UniversityTianjin300350China

In order to study the flow characteristics in water bodies with rigid aquatic vegetation,series of laboratory experiments are carried out in an open channel,in which glass rods are used as plants with diameters of 6mm,8mm and 10mm,*** each diameter of glass rods,four typical cases are considered with various densities and arrangements of glass *** flow velocities in the four cases are measured by the 3-D laser Doppler velocimeter(LDV).The water surface slope,the flow velocity,the water head loss,the vegetation drag force and the hydraulic slope are calculated,analyzed and *** horizontal,vertical and total vegetation densities in the vegetation area are defined and the relationship between these physical parameters and the water surface slope are *** head loss and the hydraulic slope in the vegetation area are also calculated,compared and *** is indicated that the water surface slope and velocity,the head loss and the hydraulic slope in the vegetation area have a close relationship with the arrangement,the density,and the plant diameter of the vegetation.

关键词： Aquatic rigid vegetation flow velocity laser Doppler velocimeter(LDV) head loss hydraulic slope

来源：评论

学校读者我要写书评

暂无评论

Potree Based Building Change Detection with BIM to Point Clouds of Lidar

引用

Science Technology and Engineering 2024年第3期24卷 1176-1183页

作者： Liu, Hui Liu, Yu-Hang Zhong, Chen School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing102616 China College Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing102616 China Shenyang Fire Science and Technology Research Institute of MEM Shenyang110034 China

Building change detection provides powerful support for building management and decision making. The current challenge of building change detection is the high calculated cost of completing the task. In order to improve the detection efficiency, a method based on Potree structure for change detection between the laser point cloud and BIM point cloud of a building was proposed. The method compare the laser point cloud acquired in real-time with the BIM planned at the start of the construction, detecting and identifying the differences between them as a result of building change detection. The experimental results show that the proposed method in this paper reduces the time complexity by 22. 05% compared to the modifiable nested octree based method, while ensuring no loss of completeness and accuracy. © 2024 Beijing Kexue Jishu yu Gongcheng Zazhishe. All rights reserved.

关键词： Risk perception

来源：评论

学校读者我要写书评

暂无评论

Resilient Collaborative Caching for Multi-Edge Systems with Robust Federated Deep Learning

引用

IEEE/ACM Transactions on Networking 2024年

作者： Chen, Zheyi Liang, Jie Yu, Zhengxin Cheng, Hongju Min, Geyong Li, Jie Fuzhou University College of Computer and Data Science Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou350116 China Ministry of Education Engineering Research Center of Big Data Intelligence Fuzhou350002 China Lancaster University School of Computing and Communications LancasterLA1 4YW United Kingdom University of Exeter Faculty of Environment Science and Economy Department of Computer Science ExeterEX4 4QF United Kingdom Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai200240 China

As a key technique for future networks, the performance of emerging multi-edge caching is often limited by inefficient collaboration among edge nodes and improper resource configuration. Meanwhile, achieving optimal cache hit rates poses substantive challenges without effectively capturing the potential relations between discrete user features and diverse content libraries. These challenges become further sophisticated when caching schemes are exposed to adversarial attacks that seriously impair cache performance. To address these challenges, we introduce RoCoCache, a resilient collaborative caching framework that uniquely integrates robust federated deep learning with proactive caching strategies, enhancing performance under adversarial conditions. First, we design a novel partitioning mechanism for multi-dimensional cache space, enabling precise content recommendations in user classification intervals. Next, we develop a new Discrete-Categorical Variational Auto-Encoder (DC-VAE) to accurately predict content popularity by overcoming posterior collapse. Finally, we create an original training mode and proactive cache replacement strategy based on robust federated deep learning. Notably, the residual-based detection for adversarial model updates and similarity-based federated aggregation are integrated to avoid the model destruction caused by adversarial updates, which enables the proactive cache replacement adapting to optimized cache resources and thus enhances cache performance. Using the real-world testbed and datasets, extensive experiments verify that the RoCoCache achieves higher cache hit rates and efficiency than state-of-the-art methods while ensuring better robustness. Moreover, we validate the effectiveness of the components designed in RoCoCache for improving cache performance via ablation studies. © 1993-2012 IEEE.

关键词： cache space partitioning content popularity prediction Multi-edge collaborative caching proactive cache replacement robust federated deep learning

来源：评论

学校读者我要写书评

暂无评论

6D Movable Antenna Enhanced Interference Mitigation for Cellular-Connected UAV Communications

arXiv

引用

arXiv 2024年

作者： Ren, Tianshi Zhang, Xianchao Zhu, Lipeng Ma, Wenyan Gao, Xiaozheng Zhang, Rui School of Information and Electronics Beijing Institute of Technology Beijing100081 China Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems Jiaxing University Jiaxing314001 China Engineering Research Center of Intelligent Human Health Situation Awareness of Zhejiang Province Jiaxing University Jiaxing314001 China School of Science and Engineering Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Guangdong Shenzhen518172 China

Cellular-connected unmanned aerial vehicle (UAV) communications is an enabling technology to transmit control signaling or payload data for UAVs through cellular networks. Due to the line-of-sight (LoS) dominant air-to-ground channels, efficient interference mitigation is crucial to UAV communications, while the conventional fixed-position antenna (FPA) arrays have limited degrees of freedom (DoFs) to suppress the interference between the UAV and its non-associated co-channel base stations (BSs). To address this challenge, we propose in this letter a new approach by utilizing the six-dimensional movable antenna (6DMA) arrays to enhance the interference mitigation for the UAV. Specifically, we propose an efficient block coordinate descent (BCD) algorithm to iteratively optimize the antenna position vector (APV), array rotation vector (ARV), receive beamforming vector, and associated BS of the UAV to maximize its signal-to-interference-plus-noise ratio (SINR). Numerical results show that the proposed 6DMA enhanced cellular-connected UAV communication can significantly outperform that with the traditional FPA arrays and other benchmark schemes in terms of interference mitigation. Copyright © 2024, The Authors. All rights reserved.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Elderly Fall Detection Based on Lightweight YOLOv5 and Dual Cameras

引用

Science Technology and Engineering 2024年第33期24卷 14330-14338页

作者： Xie, Zong-Yuan Ma, Hong-Yan Li, Sheng-Yan He, Wei Xu, Jie-Chuan Wen, Hao-Yu School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing100044 China Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing100044 China National Virtual Simulation Experimental Teaching Center of Smart City Beijing100044 China

To solve the problem that the traditional fall detection algorithm is affected by light and cannot continuously detect the elderly living alone day and night, and has high false detection and missed detection rates, a fall detection system combining lightweight YOLOv5 and dual cameras was proposed. Firstly, the elderly indoors were detected by improving YOLOv5, and the position of the elderly indoors was located. Secondly, a monocular camera and an infrared thermal camera were used to detect falls of the elderly indoors alternately day and night. Through the target positioning and fall detection system, while greatly improving the accuracy of fall detection for the elderly, it also improved the lightweight of the model and reduced the rate of false detection and missed detection of falls. The results show that the improved elderly fall detection model has a missed detection rate as low as 1. 6% and a false detection rate of only 1. 2%, with good accuracy and real-time performance. It can be seen that this system can effectively realize day and night detection and solve the limitations of traditional algorithms. © 2024 Beijing Kexue Jishu yu Gongcheng Zazhishe. All rights reserved.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

Learning Semantic Context from Normal Samples for Unsupervised Anomaly Detection 35

Learning Semantic Context from Normal Samples for Unsupervis...

引用

35th AAAI Conference on Artificial Intelligence / 33rd Conference on Innovative Applications of Artificial Intelligence / 11th Symposium on Educational Advances in Artificial Intelligence

作者： Yan, Xudong Zhang, Huaidong Xu, Xuemiao Hu, Xiaowei Heng, Pheng-Ann South China Univ Technol Guangzhou Peoples R China Minist Educ Key Lab Big Data & Intelligent Robot Beijing Peoples R China Guangdong Prov Key Lab Computat Intelligence & Cy Guangzhou Peoples R China State Key Lab Subtrop Bldg Sci Guangzhou Peoples R China Chinese Univ Hong Kong Hong Kong Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen Key Lab Virtual Real & Human Interact Te Shenzhen Peoples R China

ISBN: (纸本)9781577358664

Unsupervised anomaly detection aims to identify data samples that have low probability density from a set of input samples, and only the normal samples are provided for model training The inference of abnormal regions on the input image requires an understanding of the surrounding semantic *** work presents a Semantic Context based Anomaly Detection Network, SCADN, for unsupervised anomaly detection by learning the semantic context from the normal samples. To achieve this, we first generate multi-scale striped masks to remove a part of regions from the normal samples, and then train a generative adversarial network to reconstruct the unseen regions. Note that the masks are designed in multiple scales and stripe directions, and various training examples are generated to obtain the rich semantic context. In testing, we obtain an error map by computing the difference between the reconstructed image and the input image for all samples, and infer the abnormal samples based on the error maps. Finally, we perform various experiments on three public benchmark datasets and a new dataset LaceAD collected by us, and show that our method clearly outperforms the current state-of-the-art methods.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Towards Feature Distribution Alignment and Diversity Enhancement for data-Free Quantization

Towards Feature Distribution Alignment and Diversity Enhance...

引用

IEEE International Conference on data Mining (ICDM)

作者： Yangcheng Gao Zhao Zhang Richang Hong Haijun Zhang Jicong Fan Shuicheng Yan School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China Department of Computer Science Harbin Institute of Technology (Shenzhen) Xili University Town Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen China Shenzhen Research Institute of Big Data Shenzhen China National University of Singapore Singapore

To obtain lower inference latency and less memory footprint of deep neural networks, model quantization has been widely employed in deep model deployment, by converting the floating points to low-precision integers. However, previous methods (such as quantization aware training and post training quantization) require original data for the fine-tuning or calibration of quantized model, which makes them inapplicable to the cases that original data are not accessed due to privacy or security. This gives birth to the data-free quantization method with synthetic data generation. While current data-free quantization methods still suffer from severe performance degradation when quantizing a model into lower bit, caused by the low inter-class separability of semantic features. To this end, we propose a new and effective data-free quantization method termed ClusterQ, which utilizes the feature distribution alignment for synthetic data generation. To obtain high inter-class separability of semantic features, we cluster and align the feature distribution statistics to imitate the distribution of real data, so that the performance degradation is alleviated. Moreover, we incorporate the diversity enhancement to solve class-wise mode collapse. We also employ the exponential moving average to update the centroid of each cluster for further feature distribution improvement. Extensive experiments based on different deep models (e.g., ResNet-18 and MobileNet-V2) over the ImageNet dataset demonstrate that our proposed ClusterQ model obtains state-of-the-art performance.

关键词： Degradation Training Quantization (signal) Semantics Neural networks Memory management data models

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：