检索结果-内蒙古大学图书馆

German Workshop on Medical Image Computing, 2022

作者： Ertl, Alexandra Franz, Alfred Schmitz, Bernd Braun, Michael Faculty of Medical Engineering and Mechatronics Ulm University of Applied Sciences Ulm Germany mbits imaging GmbH Heidelberg Germany Institute of Computer Science Ulm University of Applied Sciences Ulm Germany Department of Neuroradiology District Hospital Günzburg Günzburg Germany

来源：评论

学校读者我要写书评

暂无评论

Universality of Internal Correlations of Strongly Interacting p-Wave Fermions in One-Dimensional Geometry

引用

Physical Review Letters 2023年第25期130卷 253401-253401页

作者： Przemysław Kościk Tomasz Sowiński Department of Computer Sciences University of Applied Sciences ulica Mickiewicza 8 PL-33100 Tarnów Poland Institute of Physics Polish Academy of Sciences Aleja Lotników 32/46 PL-02668 Warsaw Poland

We consider the many-body ground state of polarized fermions interacting via zero-range p-wave forces in a one-dimensional geometry. We rigorously prove that in the limit of infinite attractions spectral properties of any-order reduced density matrix describing arbitrary subsystem are completely independent of the shape of an external potential. It means that quantum correlations between any two subsystems are in this limit insensitive to the confinement. In addition, we show that the purity of these matrices quantifying the amount of quantum correlations can be obtained analytically for any number of particles without diagonalizing them. This observation may serve as a rigorous benchmark for other models and methods describing strongly interacting p-wave fermions.

关键词： Cold atoms & matter waves Entanglement in quantum gases Spinless fermions 1-dimensional systems Exact solutions for many-body systems

来源：评论

学校读者我要写书评

暂无评论

Forward +jet production in proton-proton and proton-lead collisions at LHC within the FoCal calorimeter acceptance

引用

The European Physical Journal C 2023年第9期83卷 1-10页

作者： Ganguli, Ishita Hameren, Andreas van Kotko, Piotr Kutak, Krzysztof Faculty of Physics and Applied Computer Science AGH University of Krakow Kraków Poland Institute of Nuclear Physics Polish Academy of Sciences Kraków Poland

Using the small-x improved transverse momentum dependent factorization (ITMD), which, for a general two-to-two massless scattering can be proved within the color glass condensate (CGC) theory for transverse momenta of particles greater than the saturation scale, we provide predictions for isolated forward photon and jet production in proton-proton and proton-nucleus collisions within the planned ALICE FoCal detector acceptance. We study azimuthal correlations, $$p_T$$ spectra, as well as normalized ratios of proton-proton cross sections for different energies. The only TMD distribution needed for that process is the “dipole” TMD gluon distribution, which in our computations is based on HERA data and undergoes momentum space BK evolution equation with DGLAP corrections and Sudakov resummation. We conclude, that the process provides an excellent probe of the dipole TMD gluon distribution in saturation regime.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of a multifunctional FPGA-based system for intravascular ultrasound imaging and therapy

Design and implementation of a multifunctional FPGA-based sy...

引用

IEEE International Symposium on Applications of Ferroelectrics (ISAF)

作者： Amauri A. Assef Joaquim M. Maia Paula L S. De Moura Phuong Vu Adeoye Olomodosi Stephan Strassle Rojas Brooks D. Lindsey Graduate School of Electrical Engineering and Applied Computer Sciences (CPGEI) DAELT Federal University of Technology - Parana (UTFPR) Curitiba Brazil Graduate School of Electrical Engineering and Applied Computer Sciences (CPGEI) DAELN Federal University of Technology - Parana (UTFPR) Curitiba Brazil Graduate School of Electrical Engineering and Applied Computer Sciences (CPGEI) Federal University of Technology - Parana (UTFPR) Curitiba Brazil Department of Biomedical Engineering Georgia Institute of Technology Atlanta GA USA

ISBN: (数字)9798350371901

ISBN: (纸本)9798350371918

Coronary artery disease is a leading cause of death, with 17.8 million deaths globally. Intravascular ultrasound (IVUS) imaging is used to characterize coronary lesions and guide intervention in the cardiac catheterization lab. Separately, catheter-directed thrombolysis provides therapeutic ultrasound in an intravascular form factor to treat clots. In this paper, we propose to develop a flexible, multifunctional, FPGA-based pulser/receiver system for combined IVUS imaging and therapy. The novel system consists of a computer with a Matlab-based graphical user interface, an FPGA board and a custom proprietary board. An example therapy excitation is shown for a 1000-cycle, 550 kHz output waveform with an amplitude of 102 Vpp. This excitation was applied to a custom 3 mm therapy transducer, resulting in hydrophone-measured peak negative acoustic pressure of 305.28 kPa, a mechanical index of 0.41, I spta.3 of 5.64 mW/cm 2 and I sppa.3 of 310.36 mW/cm 2 . For imaging, the system can produce waveforms such as a 160 Vpp 1-cycle, 16.67 MHz sinusoidal pulse with a -6 dB bandwidth of 21 MHz. Thus, the developed system can be used to drive simultaneous IVUS imaging to assess the coronary environment and provide image-guided therapy of clots or plaques.

关键词： Ultrasonic imaging Transducers Imaging Medical treatment Pulse width modulation Universal Serial Bus Acoustics MATLAB Field programmable gate arrays Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

Bank Note Authentication using Deep Learning

Bank Note Authentication using Deep Learning

引用

IT and Industrial Technologies (ICIT), International Conference on

作者： Reiaan Mazhar Mian Sohaib Khan Raja Hashim Ali Department of Artificial Intelligence Faculty of Computer Science & Engineering GIK Institute of Engineering Sciences & Technology Topi Pakistan Department of Business University of Europe for Applied Sciences Potsdam Germany

ISBN: (数字)9798331504465

ISBN: (纸本)9798331504472

The swift progression of technology has resulted in a surge in digital transactions, necessitating robust authentication mechanisms to avert fraudulent activities. Because genuine and counterfeit banknotes seem so identical, it is difficult, time-consuming, and error-prone for humans to determine which one is authentic. Counterfeit notes are manufactured at an alarmingly high rate, which means that systems for authenticating bank notes are essential to ensure counterfeit notes are detected and verified quickly and in due time. Such measures guarantee multiple benefits, including safe transactions, uphold the integrity of financial institutions, and guardianship against fake currency notes in the market. In this work, we show that automated solutions may be deployed to improve the accuracy and efficiency of procedures for banknote authentication. Currently, there is a lack of effective and precise models, which are especially trained for verifying or detecting bank note authentication, despite presence of an extensive research in the fields of artificial intelligence and machine learning. Our study seeks to close this gap by creating and implementing a deep learning model that can accurately identify and differentiate between real and fake banknotes. In the study, we noted that the suggested model outperformed conventional techniques with a notable degree of accuracy with the use of an extensive dataset. The model’s potential for practical implementation in banking and financial establishments is shown by its exceptional accuracy and efficiency in detecting fake banknotes. The high accuracy of the model demonstrates that deep learning may be used successfully to improve security protocols, opening the door for more developments in financial technology and otehr allied fields.

关键词： Deep learning Accuracy Protocols Fintech Current measurement Authentication Banking Security Surges Currencies

来源：评论

学校读者我要写书评

暂无评论

ASL Recognition using Deep Learning Algorithms

ASL Recognition using Deep Learning Algorithms

引用

IT and Industrial Technologies (ICIT), International Conference on

作者： Ayesha Khan Raja Hashim Ali Urooj Akmal Alishba Ramazan Department of Artificial Intelligence Faculty of Computer Science & Engineering GIK Institute of Engineering Sciences & Technology Topi Pakistan Department of Business University of Europe for Applied Sciences Potsdam Germany

ISBN: (数字)9798331504465

ISBN: (纸本)9798331504472

There is a considerably vast communication gap between deaf and hearing individuals, and one potential solution is the development of American Sign Language (ASL) recognition technology. While methods utilizing deep learning and convolutional neural networks (CNNs) have shown promising results in general ASL recognition tasks, the potential of optimized CNN architectures for ASL recognition remains untapped. This research identifies the ideal CNN structure to achieve best ASL recognition in static images. The VGG16 model has come out to be very effective; however, analyzing multiple CNN implementations may provide interesting perspectives which could in turn expose features that could potentially be helpful in ASL recognition. This experiment compares the performance of a fine-tuned ResNet50 CNN model with a baseline VGG16 model in ASL recognition. Through analysis of each model’s respective strengths and weaknesses, the study aims to identify areas within the VGG16 architecture that may be further optimized to produce precise results. This research project provides guidance for picking suitable CNN architectures and offers valuable insights for improving VGG16 model to achieve even better accuracy and robust results.

关键词： Training Deep learning Analytical models Sign language Accuracy Training data Data models Convolutional neural networks Testing Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Advancing Industrial Cybersecurity: Machine Learning-Based Detection and Mitigation of IIoT Attacks

Advancing Industrial Cybersecurity: Machine Learning-Based D...

引用

IoT Based Control Networks and Intelligent Systems (ICICNIS), International Conference on

作者： S Gouri Kiran Kumar Raavi Satya Prasad College of Computing and Information Sciences University of Technology and Applied Sciences Muscat Oman Department of Computer Science & Engineering Dhanekula Institute of Engineering & Technology Vijayawada A.P. India

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518103

A threatening entry or exploitation of vulnerabilities within an industrial network or system connected to IoT devices is an IIoT (Industrial Internet of Things) attack. Due to manufacturing delays, broken equipment, lost confidential data, and fines from the government, cyberattacks on IIoT systems can cause significant financial losses. Rapid reaction and recovery are made possible by efficient detection systems, which can lessen these losses. Many researchers have applied machine learning (ML) approaches to predict IIoT attacks in advance. Industrial networks can be highly effectively and dynamically protected against various cyber threats by utilizing MLthrough IIoT attack distinguishing. This ML methodology is a vital component of today's cybersecurity toolkit for IIoT contexts owing to its capacity for handling massive info, adjusting for novel threats, & delivering insights in real-time. Industrial networks can be highly effectively and dynamically protected against cyber threats by utilizing ML to IIoT attack identification. ML is a vital component of today's cybersecurity toolkit for IIoT contexts for its capacity to handle massive quantities of info, adjust to emerging risks, &deliver insights in real time. IIoT data can contain noise, missing values, or irrelevant information, negatively affecting model performance. Identifying and extracting relevant features from IIoT data was highly complex and time-consuming. The methodology's effectiveness is heavily related to features with high quality utilized. This paper discusses the various techniques, their limitations, and the gaps studied during the literature survey. Among the machine learning approaches, the model should adapt to the new infrastructure attacks, which is effectively possible only through meta-heuristic learning algorithms.

关键词： Surveys Adaptation models Machine learning algorithms Prevention and mitigation Noise Feature extraction Real-time systems Classification algorithms computer crime Industrial Internet of Things

来源：评论

学校读者我要写书评

暂无评论

A Pruned Multi-Scale Skip Connected and Asymmetric-Convolution-Based U-Net Model for Land Cover Classification

A Pruned Multi-Scale Skip Connected and Asymmetric-Convoluti...

引用

2024 International Conference on Distributed Systems, computer Networks and Cybersecurity, ICDSCNC 2024

作者： Almusawi, Muntather Parameshachari, B.D. Sunil, G. Reddy Muvva, Vijaya Bhaskar Siri, Dharmapuri The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Department of Ece Bengaluru India Sr University Department of Computer Science & Artificial Intelligence Warangal India University of Technology and Applied Sciences -Shinas College of Computing and Information Sciences Department of Information Technology Shinas Oman Gokaraju Rangaraju Institute of Engineering and Technology Department of Cse Hyderabad India

ISBN: (纸本)9798350375442

Recently, land cover classification became an evolutionary study in Remote Sensing (RS) satellite interpretations. While extracting features from satellite images, spatial information causes the overfitting issue. In addition, computational complexity is occurring in land cover segmentation due to the usage of complex architectures. Thus, in this research, Multi-scale Skip connected and Asymmetric-Convolution-based U-Net (MACUNet) with pruning method is introduced to reduce the computational complexity. To reduce the overfitting, Batch Normalization (BN) layer is employed, simultaneously 3D Convolutional Neural Network (3D CNN) for feature extraction. Initially, the input is taken as satellite images from the GID dataset, where spatial and temporal features are extracted using 3D CNN model with BN layer. After that, these features are given as input to the MACUNet method to improve segmentation performance. Then, classification is done with class_num value utilization based on identified pixel region maps and classified into six classes such as build up, forest, water, farmland, meadows and others. From the results, the proposed pruned-MACUNet model produces better results than existing GeohashNet in terms of Mean Intersection over Union (MIoU) as 80.45% and f1-score as 90.23% respectively. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Heartbeat Driven Network Health Assessment

Heartbeat Driven Network Health Assessment

引用

International Scientific Conference on Information Technology and Management Science of Riga Technical University (ITMS)

作者： Kristaps Felzenbergs Linas Bukauskas Ginta Majore Sociotechnical Systems Engineering Institute Vidzeme University of Applied Sciences Valmiera Latvia Institute of Computer Science Vilnius University Vilnius Lithuania

We live in a fast-growing digital century where devices such as light bulbs, electrical cords, air refreshers, and other home appliances are becoming part of smart devices, leading to a fast-growing network with less trusted and less predictable computer network ecosystems than ever. This growth poses new threats that could not be easily identified using a common threat assessment and even with industry-leading anomaly-detecting machine learning solutions. Such solutions involve hard manual work on filtering out anomalies as network data patterns change similarly to human behavior. To get a trusted network health measurement, we propose a technique where we attempt to identify commonly known network errors or diseases. Further, we measure the network's heartbeat to see the current stress level, similar to a doctor's visit for a human. Finally, we show results from our experiments, giving an example of what the proposed methodology would output.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neural Transformation Fields for Arbitrary-Styled Font Generation

Neural Transformation Fields for Arbitrary-Styled Font Gener...

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Bin Fu Junjun He Jianjun Wang Yu Qiao ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shanghai Artificial Intelligence Laboratory

Few-shot font generation (FFG), aiming at generating font images with a few samples, is an emerging topic in recent years due to the academic and commercial values. Typically, the FFG approaches follow the style-content disentanglement paradigm, which transfers the target font styles to characters by combining the content representations of source characters and the style codes of reference samples. Most existing methods attempt to increase font generation ability via exploring powerful style representations, which may be a sub-optimal solution for the FFG task due to the lack of modeling spatial transformation in transferring font styles. In this paper, we model font generation as a continuous transformation process from the source character image to the target font image via the creation and dissipation of font pixels, and embed the corresponding transformations into a neural transformation field. With the estimated transformation path, the neural transformation field generates a set of intermediate transformation results via the sampling process, and a font rendering formula is developed to accumulate them into the target font image. Extensive experiments show that our method achieves state-of-the-art performance on few-shot font generation task, which demonstrates the effectiveness of our proposed model. Our implementation is available at: https://***/fubinfb/NTF.

关键词：

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：