检索结果-内蒙古大学图书馆

A Coarse Count Error Cancellation System Designed for High-Accuracy TDC 4

学校读者我要写书评

暂无评论

A Coarse Count Error Cancellation System Designed for High-A...

4th IEEE International Conference on Circuits and Systems, ICCS 2022

作者： Du, Zhouji Zhong, Xinchao Li, Haiquan Li, Yan Yu, Hang Shenzhen University Shenzhen Laboratory of Ic Design for Iot College of Computer Science and Software Engineering Shenzhen China The University of Auckland New Zealand 38 Princes St Auckland Central Auckland1010 New Zealand Runyu Sensor Technology Co. Ltd. 18 Huitong Rd Jiangmen Xinhui529100 China

ISBN: (数字)9781665460361

ISBN: (纸本)9781665460361

Time-to-Digital Converter (TDC) uses a hybrid approach to achieve both long-time interval and high resolution. However, as external input signal is asynchronous with the internal working clock of the TDC, there will be ±1 clock cycle error due to the setup time of the TDC clock, which results in coarse time error, seriously affecting TDC timing accuracy. Aiming at the problem, a coarse count error cancellation system is proposed in this work. An extra delay is added to the input pulse to obtain a delayed pulse, and a double sampling mechanism is realized to simultaneously memorize the count values of both the original input pulse and the delayed one. The error is then obtained by comparison. Implemented in a DE2-115 FPGA development platform and tested with different delay values, the proposed system shows a significant ability to effectively reduce the coarse count error in a TDC timing system. © 2022 IEEE.

关键词： Errors

A Hybrid Cross-Scale Transformer Architecture for Robust Medical Image Segmentation

学校读者我要写书评

暂无评论

A Hybrid Cross-Scale Transformer Architecture for Robust Med...

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Ning, Yang Zhang, Shouyi Zhong, Wei Liu, Peide Zhang, Caiming Shandong Jianzhu University School of Computer Science and Technology Jinan China The University of Edinburgh School of Informatics Edinburgh United Kingdom Guangdong Police College Department of Network Information Security Guangzhou China Shandong University of Finance and Economics School of Management Science and Engineering Jinan China Shandong University School of Software Jinan China

ISBN: (纸本)9781665468190

Transformer architecture has emerged to be successful in many natural language processing tasks. However, its applications to clinical practice remain largely unexplored. In this study, we propose a Robust Cross-Scale Hybrid Transformer (RCSHT) architecture for medical image segmentation, which can effectively enhance the multi-scale feature representations while integrating local features with global dependencies. Specifically, we propose two new modules based on the self-attention mechanism: PSCM and PCCM, which perform matrix low-rank transformation on cross-scale images in spatial and channel space, respectively, to effectively enhance the discriminant ability of long-range dependencies of multi-scale images and effectively reduce the computational complexity. Meanwhile, we use spatial positional encoding to perform spatial regularization on the two attention modules, so that the model has more opportunities to obtain valuable spatial details and further enhance the spatial retention ability. Besides, by fusing outputs of the two modules, the robustness and discriminant ability of the feature representations are further improved. Note that our hybrid architecture allows transformers to be initialized as convolutional networks without pre-training. Extensive experiments conducted on our newly proposed dataset have demonstrated our RCSHT notably outperforms the state-of-the-art methods by a large margin, holding the promise to generalize well on other medical image segmentation. © 2022 IEEE.

关键词： Signal encoding

A Multi-Discriminator Weighted Adversarial Network for Cross-Domain Unknown Wind Turbine Fault Diagnosis

学校读者我要写书评

暂无评论

A Multi-Discriminator Weighted Adversarial Network for Cross...

IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia)

作者： Yinghua Han Huaiyuan Qi Fangyuan Si Kangping Li Qiang Zhao School of Computer and Communication Engineering Northeastern University at Qinhuangdao Qinhuangdao China School of Control Engineering Notheastern University at Qinhuangdao Qinhuangdao China Department of Electrical Engineering Tsinghua University Beijing China The College of Smart Energy Shanghai Jiao Tong University Shanghai China

The practical cross-domain fault diagnosis methods in wind turbines based on transfer learning have been widely studied, where most of the existing transfer learning methods assume that test data and training data have the same label space. However, this assumption is not realistic in practical wind turbines because the data in the target domain wind turbine often presents new fault categories during the testing phase, which can affect the accuracy of the model. A multi-discriminator weighted adversarial network (MWAN) is proposed here to handle the above problem. The proposed method can automatically identify outliers in the source domain and unknown fault classes in the target domain by introducing a hybrid weighting balanced strategy and using an auxiliary discriminator to weigh source and target domain samples. Adversarial training is introduced to achieve shared class-level alignment in the two domains. Experiments verify that the proposed method outperforms state-of-the-art methods for wind turbine fault diagnosis applications.

关键词：

An Assessment of Multilevel Converters Submodules EMI Emissions Considering Three Configurations Including Parasitic Parameters

学校读者我要写书评

暂无评论

An Assessment of Multilevel Converters Submodules EMI Emissi...

IEEE International Symposium on Electromagnetic Compatibility - EMC Europe

作者： Amr Madi Waseem Elsayed Ahmed Hebala Michal Przybylski Piotr Lezynski Robert Smolenski Institute of Automatic Control Electronics and Electrical Engineering Doctoral School of Exact and Technical Sciences University of Zielona Gora Zielona Gora Poland Electrical Engineering Mathematics & Computer Science (EEMCS) University of Twente Enschede Netherlands Electrical and Control Engineering College of Engineering Arab Academy for Science Technology and Maritime Transport Alexandria Egypt Institute of Automatic Control Electronics and Electrical Engineering University of Zielona Gora Zielona Gora Poland

With the expanding use of modular multilevel converters in power installations it became more important to lower the total conducted emissions. One of the most important key factors in controlling electromagnetic interference emissions is the type of submodules used and the utilized switches. This paper compares three well-known submodules which are half bridge, full bridge and double-clamped half bridge effect on the electromagnetic interference emissions. For making the model more accurate the parasitic components were included in all the circuits Additionally, the same configurations are carried out and compared under two switches which are insulated gate bipolar transistors and metal oxide semiconductor field effect transistors operating at two different switching frequencies. The results were obtained by a simulation in a Matlab/Simulink environment.

关键词：

Analysis of Financial Risk Behavior Prediction Using Deep Learning and Big Data Algorithms

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Haowei Cheng, Zhan Zhang, Zhaoyang Luo, Yuanshuai Huang, Shuaishuai Xiang, Ao University of Houston Cullen College of Engineering Industrial Engineering Houston United States University of California Irvine Donald Bren School of Information & Computer Science Master of Computer Science Irvine United States University of California San Diego Computational Science San Diego United States Southwest Jiaotong University School of Computing and Artificial Intelligence Computer Science and Technology Chengdu China University of Science and Technology of China Department of Software Software system design Hefei China Northern Arizona University Information Security and Assurance AZ United States

As the complexity and dynamism of financial markets continue to grow, traditional financial risk prediction methods increasingly struggle to handle large datasets and intricate behavior patterns. This paper explores the feasibility and effectiveness of using deep learning and big data algorithms for financial risk behavior prediction. First, the application and advantages of deep learning and big data algorithms in the financial field are analyzed. Then, a deep learning-based big data risk prediction framework is designed and experimentally validated on actual financial datasets. The experimental results show that this method significantly improves the accuracy of financial risk behavior prediction and provides valuable support for risk management in financial institutions. Challenges in the application of deep learning are also discussed, along with potential directions for future research. © 2024, CC BY.

关键词： Data accuracy

Large Point-to-Gaussian Model for Image-to-3D Generation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lu, Longfei Gao, Huachen Dai, Tao Zha, Yaohua Hou, Zhi Wu, Junta Xia, Shu-Tao Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China Tencent Hunyuan Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Tsinghua Shenzhen International Graduate School Tsinghua University Peng Cheng Laboratory Shenzhen China

Recently, image-to-3D approaches have significantly advanced the generation quality and speed of 3D assets based on large reconstruction models, particularly 3D Gaussian reconstruction models. Existing large 3D Gaussian models directly map 2D image to 3D Gaussian parameters, while regressing 2D image to 3D Gaussian representations is challenging without 3D priors. In this paper, we propose a large Point-to-Gaussian model, that inputs the initial point cloud produced from large 3D diffusion model conditional on 2D image to generate the Gaussian parameters, for image-to-3D generation. The point cloud provides initial 3D geometry prior for Gaussian generation, thus significantly facilitating image-to-3D Generation. Moreover, we present the Attention mechanism, Projection mechanism, and Point feature extractor, dubbed as APP block, for fusing the image features with point cloud features. The qualitative and quantitative experiments extensively demonstrate the effectiveness of the proposed approach on GSO and Objaverse datasets, and show the proposed method achieves state-of-the-art performance. Copyright © 2024, The Authors. All rights reserved.

关键词： 3D reconstruction

Simplify Implant Depth Prediction as Video Grounding: A Texture Perceive Implant Depth Prediction Network

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Xinquan Li, Xuguang Luo, Xiaoling Zeng, Leilei Zhang, Yudi Shen, Linlin Deng, Yongqiang College of Computer Science and Software Engineering Shenzhen University Shenzhen China AI Research Center for Medical Image Analysis and Diagnosis Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Stomatology Shenzhen University General Hospital Shenzhen China

Surgical guide plate is an important tool for the dental implant surgery. However, the design process heavily relies on the dentist to manually simulate the implant angle and depth. When deep neural networks have been applied to assist the dentist quickly locates the implant position, most of them are not able to determine the implant depth. Inspired by the video grounding task which localizes the starting and ending time of the target video segment, in this paper, we simplify the implant depth prediction as video grounding and develop a Texture Perceive Implant Depth Prediction Network (TPNet), which enables us to directly output the implant depth without complex measurements of oral bone. TPNet consists of an implant region detector (IRD) and an implant depth prediction network (IDPNet). IRD is an object detector designed to crop the candidate implant volume from the CBCT, which greatly saves the computation resource. IDPNet takes the cropped CBCT data to predict the implant depth. A Texture Perceive Loss (TPL) is devised to enable the encoder of IDPNet to perceive the texture variation among slices. Extensive experiments on a large dental implant dataset demonstrated that the proposed TPNet achieves superior performance than the existing methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Forecasting

Understanding Heterophily for Graph Neural Networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Junfu Guo, Yuanfang Yang, Liang Wang, Yunhong State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China Shen Yuan Honors College Beihang University Beijing China School of Artificial Intelligence Hebei University of Technology Tianjin China

Graphs with heterophily have been regarded as challenging scenarios for Graph Neural Networks (GNNs), where nodes are connected with dissimilar neighbors through various patterns. In this paper, we present theoretical understandings of heterophily for GNNs by incorporating the graph convolution (GC) operations into fully connected networks via the proposed Heterophilous Stochastic Block Models (HSBM), a general random graph model that can accommodate diverse heterophily patterns. Our theoretical investigation comprehensively analyze the impact of heterophily from three critical aspects. Firstly, for the impact of different heterophily patterns, we show that the separability gains are determined by two factors, i.e., the Euclidean distance of the neighborhood distributions and pE [deg], where E [deg] is the averaged node degree. Secondly, we show that the neighborhood inconsistency has a detrimental impact on separability, which is similar to degrading E [deg] by a specific factor. Finally, for the impact of stacking multiple layers, we show that the separability gains are determined by the normalized distance of the lpowered neighborhood distributions, indicating that nodes still possess separability in various regimes, even when over-smoothing occurs. Extensive experiments on both synthetic and real-world data verify the effectiveness of our theory. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

Multi-View Fusion Based for Intrusion Detection with Deep Learning Architectures

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Li, Min Qiao, Yuansong Lee, Brian Software Research Institute Technological University of the Shannon: Midlands Midwest University Road Co.Westmeath AthloneN37 HD68 Ireland Computer Engineering College Jingchu University of Technology No.33 Xiangshan Road Jingmen448000 China

As the Internet of Things (IoT) proliferates, the complexity of enterprise network security challenges increases, with IoT devices potentially introducing new vulnerabilities. This paper proposes a novel approach for host-based intrusion detection systems (IDS) in enterprise Internet of Things (EIoT) environments, utilizing deep multi-view learning (DMVL). This method transcends the limitations of conventional single-view analyses by synthesizing and examining data from diverse perspectives, including processor, network, memory, and disk ***, DMVL effectively uncovers intricate attack patterns that might elude singleview inspections, thereby enhancing the precision and efficiency of potential threat detection. This study assesses various deep learning models, such as autoencoders (AE), convolutional neural networks (CNN), and deep canonical correlation analysis (DGCCA), to identify the most effective strategy for analyzing multi-view data. The findings indicate that the DMVL approach significantly outperforms traditional single-view methods in anomaly detection, notably improving accuracy and minimizing false positives. This research contributes to advancing cybersecurity anomaly detection in EIoT settings, offering robust solutions to the challenges confronting contemporary digital infrastructures. © 2024, The Authors. All rights reserved.

关键词： Anomaly detection