检索结果-内蒙古大学图书馆

arXiv 2024年

作者： de Rooij, Steven A.H. Fermin, Remko Kouwenhoven, Kevin Coppens, Tonny Murugesan, Vignesh Thoen, David J. Aarts, Jan Baselmans, Jochem J.A. de Visser, Pieter J. SRON - Netherlands Institute for Space Research Niels Bohrweg 4 CA Leiden2333 Netherlands Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Mekelweg 4 Delft2628 CD Netherlands Department of Materials Science and Metallurgy University of Cambridge 27 Charles Babbage Rd CambridgeCB3 0FS United Kingdom Huygens-Kamerlingh Onnes Laboratory Leiden University Leiden2300 RA Netherlands

Disordered superconductors offer new impedance regimes for quantum circuits, enable a pathway to protected qubits and improve superconducting single photon detectors due to their high kinetic inductance and sheet resistance. However, the relaxation of quasiparticles, which cause decoherence and microwave loss, is drastically affected by disorder, which is still not understood. We address this issue by measuring the quasiparticle relaxation time in a disordered β-Ta film, which we pattern as the inductor of a microwave resonator. We observe that the quasiparticle relaxation time is governed by the phonon scattering time and is independent on the phononic environment, which is in stark contrast to the relaxation of quasiparticles in ordered superconductors. We explain these observations in terms of the recombination of localized quasiparticles that first delocalize via phonon scattering. We analyse quasiparticle relaxation measurements on superconductors with different degrees of disorder and conclude that this phenomenon is inherent to disordered superconductors. © 2024, CC BY.

关键词： Microwave resonators

来源：评论

学校读者我要写书评

暂无评论

Leveraging Generalizability of Image-to-Image Translation for Enhanced Adversarial Defense

arXiv

引用

arXiv 2025年

作者： Zhang, Haibo Yao, Zhihua Sakurai, Kouichi Saitoh, Takeshi Department of Artificial Intelligence Faculty of Computer Science and Systems Engineering Kyushu Institute of Technology Japan Faculty of Economics and Business Administration The University of Kitakyushu Japan Department of Informatics Faculty of Information Science and Electrical Engineering Kyushu University Japan

In the rapidly evolving field of artificial intelligence, machine learning emerges as a key technology characterized by its vast potential and inherent risks. The stability and reliability of these models are important, as they are frequent targets of security threats. Adversarial attacks, first rigorously defined by Ian Goodfellow et al. in 2013, highlight a critical vulnerability: they can trick machine learning models into making incorrect predictions by applying nearly invisible perturbations to images. Although many studies have focused on constructing sophisticated defensive mechanisms to mitigate such attacks, they often overlook the substantial time and computational costs of training and maintaining these models. Ideally, a defense method should be able to generalize across various, even unseen, adversarial attacks with minimal overhead. Building on our previous work on image-to-image translation-based defenses, this study introduces an improved model that incorporates residual blocks to enhance generalizability. The proposed method requires training only a single model, effectively defends against diverse attack types, and is well-transferable between different target models. Experiments show that our model can restore the classification accuracy from near zero to an average of 72% while maintaining competitive performance compared to state-of-the-art methods. Significantly, our model operates more efficiently, reducing the time needed to process individual images and speeding up the training process to achieve faster convergence. Robustness tests further confirm stable performance under varying attack strengths, demonstrating the model’s practical value in real-world adversarial settings. Copyright © 2025, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Parking Occupancy Prediction and Traffic Assignment in a University Environment

Parking Occupancy Prediction and Traffic Assignment in a Uni...

引用

Japan-Egypt International Conference on Electronics, Communications and computers (JEC-ECC)

作者： Mohamed Farag Amr Hilal Samy El-Tawab Arab Academy for Science Technology & Maritime Transport Alexandria Egypt Virginia Tech Transportation Institute Virginia Tech Blacksburg VA USA Informatics Lab Virginia Tech Blacksburg VA USA Department of Computer and Systems Engineering Alexandria University Egypt College of Integrated Science & Engineering James Madison University Harrisonburg VA USA

ISBN: (纸本)9781665464642

The fourth industrial revolution has given rise to large-scale data-driven models like smart cities and Intelligent transportation. Within these models, applications like smart parking have been growing rapidly in research and industry. However, different scenarios and environments (e.g., shopping areas, residential places, and business complexes) can require special handling due to the various factors impacting people’s schedules and behavior. In this paper, we provide an initial investigation of traffic assignment based on parking prediction for a mid-size university environment where parking is concentrated in three parking garages around the campus. Our initial investigation includes results for parking prediction using a statistical method and plans for an augmenting study using variations of Neural Networks. On top of the parking prediction layer, we propose an application layer that directs and fuses the model predictions to produce the parking options provided to the application user. The presented investigation can help the university administration in their consideration of building additional garages.

关键词： Industries Schedules Statistical analysis Smart cities Fuses Computational modeling Neural networks

来源：评论

学校读者我要写书评

暂无评论

Computational prediction and validation of specific EmbR binding site on PknH

引用

Synthetic and Systems Biotechnology 2021年第4期6卷 429-436页

作者： Insung Na Huanqin Dai Hantian Li Anvita Gupta David Kreda Powell Zhang Xiangyin Chen Lixin Zhang Gil Alterovitz Computational Health Informatics Program Boston Children’s Hospital/Harvard Medical SchoolBostonMA 02115USA Department of Medicine Brigham and Women’s Hospital/Harvard Medical SchoolBostonMA 02115USA State Key Laboratory of Mycology Institute of MicrobiologyBeijing100101 China Department of Computer Sciences Stanford UniversityStanford CA 94305USA Center for Biomedical Informatics Harvard Medical SchoolBostonMA 02115USA State Key Laboratory of Bioreactor Engineering East China University of Science and TechnologyShanghaiChina Department of Biology The Johns Hopkins UniversityBaltimoreMD 21218USA Lexington High School BostonMA 02115USA

Tuberculosis drug resistance continues to threaten global health but the underline molecular mechanisms are not ***(EMB),one of the well-known first-line drugs in tuberculosis treatment is,unfortunately,not free from drug resistance *** studies have shown that some genetic mutations in Mycobacterium tuberculosis(Mtb)EmbR,and EmbC/A/B genes cause EMB ***-PknH pair controls embC/A/B operon,which encodes EmbC/A/B genes,and EMB interacts with EmbA/B ***,the EmbR binding site on PknH was *** conducted molecular simulation on the EmbR-peptides binding structures and discovered phosphorylated PknH 273-280(N′-HEALS^(P)DPD-C′)makesβstrand with the EmbR FHA domain,asβ-MoRF(MoRF;molecular recognition feature)does at its binding *** bond number analysis also supported the peptides’β-MoRF forming activity at the EmbR FHA ***,we discovered that previously known phosphorylation residues might have their chronological order according to the phosphorylation *** discovery validated that Mtb PknH 273-280(N′-HEALSDPD-C′)has reliable EmbR binding *** approach is revolutionary in the computer-aided drug discovery field,because it is the first trial to discover the protein-protein interaction site,and find binding partner in nature from this site.

关键词： Disorder-to-order transition Protein intrinsic disorder Binding site prediction Drug resistance Molecular simulation

来源：评论

学校读者我要写书评

暂无评论

FedFTN: Personalized Federated Learning with Deep Feature Transformation Network for Multi-institutional Low-count PET Denoising

arXiv

引用

arXiv 2023年

作者： Zhou, Bo Xie, Huidong Liu, Qiong Chen, Xiongchao Guo, Xueqi Feng, Zhicheng Hou, Jun Zhou, S. Kevin Li, Biao Rominger, Axel Shi, Kuangyu Duncan, James S. Liu, Chi Department of Biomedical Engineering Yale University New HavenCT United States Department of Radiology and Biomedical Imaging Yale School of Medicine New HavenCT United States Department of Electrical Engineering Yale University New HavenCT United States Department of Biomedical Engineering University of Southern California Los AngelesCA United States Department of Computer Science University of California Irvine IrvineCA United States School of Biomedical Engineering Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou China Department of Nuclear Medicine Ruijin Hospital Shanghai Jiao Tong University School of Medicine Shanghai China Department of Nuclear Medicine Inselspital Bern University Hospital University of Bern Bern Switzerland Computer Aided Medical Procedures and Augmented Reality Institute of Informatics I16 Technical University of Munich Munich Germany

Low-count PET is an efficient way to reduce radiation exposure and acquisition time, but the reconstructed images often suffer from low signal-to-noise ratio (SNR), thus affecting diagnosis and other downstream tasks. Recent advances in deep learning have shown great potential in improving low-count PET image quality, but acquiring a large, centralized, and diverse dataset from multiple institutions for training a robust model is difficult due to privacy and security concerns of patient data. Moreover, low-count PET data at different institutions may have different data distribution, thus requiring personalized models. While previous federated learning (FL) algorithms enable multiinstitution collaborative training without the need of aggregating local data, addressing the large domain shift in the application of multi-institutional low-count PET denoising remains a challenge and is still highly under-explored. In this work, we propose FedFTN, a personalized federated learning strategy that addresses these challenges. FedFTN uses a local deep feature transformation network (FTN) to modulate the feature outputs of a globally shared denoising network, enabling personalized low-count PET denoising for each institution. During the federated learning process, only the denoising network’s weights are communicated and aggregated, while the FTN remains at the local institutions for feature transformation. We evaluated our method using a large-scale dataset of multi-institutional low-count PET imaging data from three medical centers located across three continents, and showed that FedFTN provides high-quality low-count PET images, outperforming previous baseline FL reconstruction methods across all low-count levels at all three institutions. © 2023, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Measuring fairness preferences is important for artificial intelligence in health care

引用

The Lancet Digital Health 2024年第5期6卷 e302-e304页

作者： Näher, Anatol-Fiete Krumpal, Ivar Antão, Esther-Maria Ong, Erika Rojo, Marina Kaggwa, Fred Balzer, Felix Celi, Leo Anthony Braune, Katarina Wieler, Lothar H Agha-Mir-Salim, Louis Digital Global Public Health Hasso Plattner Institute for Digital Engineering University of Potsdam Potsdam14482 Germany Institute of Medical Informatics Charité–Universitätsmedizin Berlin Berlin Germany Faculty of Social Science and Philosophy University of Leipzig Leipzig Germany College of Medicine University of the Philippines Manila Philippines Department of Public Health School of Medicine University of Buenos Aires Buenos Aires Argentina Department of Computer Science Faculty of Computing and Informatics Mbarara University of Science and Technology Mbarara Uganda Laboratory for Computational Physiology Massachusetts Institute of Technology CambridgeMA United States Division of Pulmonary Critical Care and Sleep Medicine Beth Israel Deaconess Medical Center BostonMA United States Department of Biostatistics Harvard T H Chan School of Public Health BostonMA United States

来源：评论

学校读者我要写书评

暂无评论

Word-Level Sign Language Recognition with Multi-Stream Neural Networks Focusing on Local Regions and Skeletal Information

SSRN

引用

SSRN 2022年

作者： Maruyama, Mizuki Singh, Shrey Ioue, Katsufumi Roy, Partha Pratim Iwamura, Masakazu Yoshioka, Michifumi Graduate School of Engineering Osaka Prefecture University 1-1 Gakuencho Naka Sakai Osaka599-8531 Japan Department of Computer Science and Engineering Indian Institute of Technology Uttarakhand Roorkee247667 India Graduate School of Informatics Osaka Metropolitan University 1-1 Gakuencho Naka Sakai Osaka599-8531 Japan

Word-level sign language recognition (WSLR) has attracted attention because it is expected to overcome the communication barrier between people with speech impairment and those who can hear. In the WSLR problem, a method designed for action recognition has achieved the state-of-the-art performance. Indeed, it sounds reasonable for an action recognition method to perform well on WSLR because sign language is regarded as an action. However, a closer look at the tasks reveals that the tasks of action recognition and WSLR are inherently different. Hence, in this paper, we propose a novel WSLR method that takes into account information specifically useful for the WSLR problem. We realize it as a multi-stream neural network to additionally combine various types of information such as quick and detailed hand and body movements, handshapes, facial expression, and the relative positions of the body and both hands. Experimental results on the WLASL and MS-ASL datasets show the effectiveness of the proposed method;it achieved an improvement of approximately 10%-15% in Top-1 accuracy when compared with conventional methods. © 2022, The Authors. All rights reserved.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Airplane type identification based on mask RCNN and drone images

arXiv

引用

arXiv 2021年

作者： Alshaibani, Waleed Tawfik Abdullah Helvaci, Mustafa Shayea, Ibraheem Saad, Sawsan A. Azizan, Azizul Yakub, Fitri Institute of Informatics Satellite Communication and Remote Sensing Program Istanbul Technical University ITU Ayazaga Campus Institute of Informatics Building Sariyer Istanbul34469 Turkey Istanbul34469 Turkey Faculty of Engineering and Built Environment Universiti Sains Islam Malaysia Negeri Sembilan Bandar BaruNilai71800 Malaysia Department of Computer Engineering College of Computer Science and Engineering University of Ha'il Saudi Arabia Advance Informatics Department Razak Faculty of Technology and Informatics Universiti Teknologi Malaysia Kuala Lumpur54100 Malaysia

For dealing with traffic bottlenecks at airports, aircraft object detection is insufficient. Every airport generally has a variety of planes with various physical and technological requirements as well as diverse service requirements. Detecting the presence of new planes will not address all traffic congestion issues. Identifying the type of airplane, on the other hand, will entirely fix the problem because it will offer important information about the plane's technical specifications (i.e., the time it needs to be served and its appropriate place in the airport). Several studies have provided various contributions to address airport traffic jams;however, their ultimate goal was to determine the existence of airplane objects. This paper provides a practical approach to identify the type of airplane in airports depending on the results provided by the airplane detection process using mask region convolution neural network. The key feature employed to identify the type of airplane is the surface area calculated based on the results of airplane detection. The surface area is used to assess the estimated cabin length which is considered as an additional key feature for identifying the airplane type. The length of any detected plane may be calculated by measuring the distance between the detected plane's two furthest points. The suggested approach's performance is assessed using average accuracies and a confusion matrix. The findings show that this method is dependable. This method will greatly aid in the management of airport traffic congestion. Copyright © 2021, The Authors. All rights reserved.

关键词： Aircraft detection

来源：评论

学校读者我要写书评

暂无评论

Label-Free Early Cancer Detection Using Encodable Dielectric–Graphene Terahertz Surface Plasmon Resonance Sensor with Artificial Intelligence for Behaviour Prediction

引用

Journal of The Electrochemical Society 2025年第6期172卷 067513-067513页

作者： Priti Rishi Abdulrahman Saad Alqahtani Pankaj Pathak Azath Mubarakali Gopinath S Department of Electronics & Communication Engineering SRM Institute of Science and Technology Vadapalani Campus Chennai 600026 Tamil Nadu India College of Computing and Information Technology Department of Computer Science University of Bisha Bisha Saudi Arabia Symbiosis Institute of Digital and Telecom Management (SIDTM) Symbiosis International (Deemed University) Pune Lavale India Department of Informatics and Computer Systems College of Computer Science King Khalid University Abha Saudi Arabia Department of Electronics and Communication Engineering Karpagam Institute of Technology Coimbatore Tamil Nadu India

We introduce a cutting-edge terahertz (THz) metasurface biosensor leveraging synergistic integration of graphene, magnesium oxide (MgO), barium titanate (BaTiO3), and calcium fluoride (CaF2) within a multilayered micr...

We introduce a cutting-edge terahertz (THz) metasurface biosensor leveraging synergistic integration of graphene, magnesium oxide (MgO), barium titanate (BaTiO₃), and calcium fluoride (CaF₂) within a multilayered micro-nanostructure for ultra-sensitive, label-free early cancer detection. The sensor architecture is centered around a precisely engineered square ring resonator surrounded by hybrid satellite elements, designed to harness strong plasmonic and dielectric interactions in the 0.1–1 THz range. Finite element simulations conducted in COMSOL Multiphysics reveal an exceptional refractive index sensitivity of up to 1000 GHz RIU⁻¹, a narrow full width at half maximum of 0.095 THz, and a maximum figure of merit of 10.526 RIU⁻¹. Tunability via graphene's chemical potential modulation enables dynamic resonance control, enhancing real-time adaptability for diverse biomarker detection. The device exhibits consistent and predictable redshifts in resonance frequency in response to minute changes in the analyte's refractive index, supporting detection of cancer-specific. An XGboost Regression model further validates the sensor's angular resilience, achieving coefficient of determination (R²) scores up to 87%, with optimized configurations reaching 100%. The proposed platform also exemplifies encoding ability and thus demonstrates transformative potential for next-generation point-of-care diagnostics, combining sub-wavelength field confinement, high-throughput ML validation, and scalable fabrication into a single, powerful biosensing solution for early-stage cancer diagnostics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Overheating-Avoidance Remapping Scheme for Reliability Enhancement of 3D PCM Storage Systems 20

Overheating-Avoidance Remapping Scheme for Reliability Enhan...

引用

2020 Research in Adaptive and Convergent Systems, raCS 2020

作者： Lin, Yu-Chen Wang, Tse-Yuan Tsao, Che-Wei Chang, Yuan-Hao Chen, Jian-Jia Liu, Xue Kuo, Tei-Wei Institute of Information Science Academia Sinica Taiwan Research Center for Information Technology Innovation Academia Sinica Taiwan Department of Informatics TU Dortmund University Germany School of Computer Science McGill University Canada Department of Computer Science and Information Engineering National Taiwan University Taiwan College of Engineering City University of Hong Kong Hong Kong

ISBN: (纸本)9781450380256

With the trend of 3D architecture and higher access rate, Phase Change Memory (PCM) storage devices face the overheating issue. This work is motivated by the observation that PCM devices might change states of memory cells with high temperature, and it will hurt the reliability of 3D PCM storage systems. Hence, we propose an Overheating-Avoidance Remapping Scheme (OARS) that controls the temperature of PCM layers and achieves wear-leveling of PCM cells inside PCM devices. Besides, we also take remapping overhead into consideration. The experiments were conducted based on the representative realistic workloads, and the results demonstrate the efficacy of the proposed scheme. © 2020 ACM.

关键词： Phase change memory

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：