检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Li, Xinrui Dong, Zhenjun Zeng, Yong Jin, Shi Zhang, Rui National Mobile Communications Research Laboratory Frontiers Science Center for Mobile Information Communication and Security Southeast University Nanjing210096 China Purple Mountain Laboratories Nanjing211111 China Shenzhen Research Institute of Big Data Shenzhen518172 China Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore

In this paper, we investigate the near-field modelling and analyze the beam focusing pattern for modular extremely large-scale array (XL-array) communications. As modular XL-array is physically and electrically large in general, the accurate characterization of amplitude and phase variations across its array elements requires the non-uniform spherical wave (NUSW) model, which, however, is difficult for performance analysis and optimization. To address this issue, we first present two ways to simplify the NUSW model by exploiting the unique regular structure of modular XL-array, termed sub-array based uniform spherical wave (USW) models with different or common angles, respectively. Based on the developed models, the near-field beam focusing patterns of XL-array communications are derived. It is revealed that compared to the existing collocated XL-array with the same number of array elements, modular XL-array can significantly enhance the spatial resolution, but at the cost of generating undesired grating lobes. Fortunately, different from the conventional far-field uniform plane wave (UPW) model, the near-field USW model for modular XL-array exhibits a higher grating lobe suppression capability, thanks to the non-linear phase variations across the array elements. Finally, simulation results are provided to verify the near-field beam focusing pattern and grating lobe characteristics of modular XL-array. Copyright © 2023, The Authors. All rights reserved.

关键词： Focusing

来源：评论

学校读者我要写书评

暂无评论

Driver Gene Expression Clustering Model for Prognostic Risk Estimation Using Cancer Genomic Data

Driver Gene Expression Clustering Model for Prognostic Risk ...

引用

IEEE Annual International computer Software and Applications Conference (COMPSAC)

作者： Sin-Hua Moi Yu-Da Lin Yi-Ling Chen Chao-Ming Hung Shin-Jiun Tsai Wei-Hong Cheng Graduate Institute of Clinical Medicine College of Medicine Kaohsiung Medical University Kaohsiung Taiwan Department of Computer Science and Information Engineering National Penghu University of Science and Technology Penghu Taiwan Department of Electronic Engineering National Kaohsiung University of Science and Technology Kaohsiung Taiwan Department of General Surgery E-Da Cancer Hospital Kaohsiung Taiwan Clinical Research Center Taipei Medical University-Shung Ho hospital Ministry of Health and Welfare New Taipei Taiwan Departement of Internal Medicine Division of Hematology and Oncology Taipei Medical University-Shung Ho hospital Ministry of Health and Welfare New Taipei Taiwan

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

Breast cancer (BRCA) and head and neck cancer (HNSC) represent significant global health challenges, underscoring the critical need for accurate prognosis in these patient populations. Tumor suppressor genes (TSGs) and oncogenes (OCGs) play pivotal roles in cancer progression, yet exhibit low mutation rates in affected individuals. Consequently, distinct omics patterns are necessary for estimating prognosis risk in patients harboring wild-type OCGs and TSGs. This study investigates mRNA expression of driver genes across TSG/OCG mutant subgroups and employs hierarchical clustering to identify mRNA expression patterns associated with higher prognosis risk. Data from both cancer cohorts were analyzed using agglomerative hierarchical clustering, revealing survival discrepancies between clusters in OCG/TSG-Wild subgroups. Our results emphasize the potential utilizing driver gene expression for prognostic risk estimation in BRCA and HNSC patients with wild-type OCGs and TSGs.

关键词： Estimation Genomics Software Data models Neck Gene expression Prognostics and health management

来源：评论

学校读者我要写书评

暂无评论

Fuzzified Federated Multi-task Unlearning for Efficient and Privacy-Preserving Swarm Consumer Electronics Systems

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Qu, Y. Neil Kong, Xiangjie Shen, Shigen Zhang, Aiqing Gao, Huynh Thi Thanh Binh Longxiang Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan250031 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan250031 China Zhejiang University of Technology College of Computer Science and Technology Hangzhou310023 China Huzhou University School of Information Engineering Huzhou313000 China Anhui Normal University School of Physics and Electronic Information Wuhu China

The proliferation of consumer electronics systems in swarm environments has heightened the need for robust privacy-preserving techniques in federated learning (FL) frameworks. Traditional FL methods, while effective in distributing model training, often fall short in efficiently handling data removal requests and safeguarding against inference attacks. Existing solutions, such as FL with Differential Privacy (FL+DP), offer some improvements but still face challenges in balancing performance, privacy, and communication efficiency. In this paper, we introduce FL+Fuzzy Unlearning, a novel FL framework that integrates Fuzzy Logic to address these challenges in federated multi-task learning for swarm consumer electronics systems. Our method aims to maintain high model performance while ensuring robust privacy and efficient communication. We evaluated FL+Fuzzy Unlearning against Traditional FL and FL+DP using two benchmark datasets: MNIST and MovieLens. Our results demonstrate that the proposed approach attains comparable or superior accuracy (0.86 on MNIST and 0.88 on MovieLens) while achieving robust unlearning performance. Moreover, FL+Fuzzy Unlearning substantially enhances privacy protection, evidenced by elevated inference attack failure rates (0.75 for MNIST and 0.78 for MovieLens), and effectively reduces communication overhead, underscoring its efficiency in data exchange. Overall, FL+Fuzzy Unlearning presents a promising, balanced solution for privacy, efficiency, and adaptability, making it highly suitable for real-world applications in swarm consumer electronics systems. © 1975-2011 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Privacy Preserving Ultra-Short-term Wind Power Prediction Based on Secure Multi Party Computation

arXiv

引用

arXiv 2023年

作者： Fan, Hang Fan, Xiaoyu Hao, Tianyi Wei, Wei Chen, Kun Wang, Guosai Jia, Xiaofeng Li, Yidong Xu, Wei PBC School of Finance Tsinghua University Beijing100084 China Institute for Interdisciplinary Information Sciences Tsinghua University Beijing100084 China Department of Electrical Engineering Tsinghua University Beijing100084 China Tsingjiao Information Technology Co. Ltd. Tsinghua Science and Technology Park Beijing100084 China Data Management Department Beijing Big Data Center Beijing100044 China School of Computer and Information Technology Beijing Jiaotong University Beijing100025 China

Mining the spatial and temporal correlation of wind farm output data is beneficial for enhancing the precision of ultra-short-term wind power prediction. However, if the wind farms are owned by separate entities, they may be reluctant to share their data directly due to privacy concerns as well as business management regulation policies. Although cryptographic approaches have been designed to protect privacy in the process of data sharing, it is still a challenging problem to encrypt the original data while extracting the nonlinear relationship among multiple wind farms in the machine learning process. This paper presents pwXGBoost, a technique based on the machine learning tree model and secure multi-party computation (SMPC) that can successfully extract complicated relationships while preserving data privacy. A maximum mean discrepancy (MMD) based scheme is proposed to effectively choose adjacent candidate wind farms to participate in the collaborative model training, therefore improving the accuracy and reducing the burden of data acquisition. The proposed method was evaluated on real world data collected from a cluster of wind farms in Inner Mongolia, China, demonstrating that it is capable of achieving considerable efficiency and performance improvements while preserving privacy. Copyright © 2023, The Authors. All rights reserved.

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

A certificateless and KGA-secure searchable encryption scheme with constant trapdoors in smart city

引用

Digital Communications and networks 2024年

作者： Hongjun Li Debiao He P. Vijayakumar Fayez Alqahtani Amr Tolba School of Cyber Science and Engineering Wuhan University Wuhan 430072 China Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan 250014 China Department of Computer Science and Engineering University College of Engineering Tindivanam Tindivanam 604001 India Software Engineering Department College of Computer and Information Sciences King Saud University Riyadh 12372 Saudi Arabia Computer Science Department Community College King Saud University Riyadh 11437 Saudi Arabia

Smart cities, as a typical application in the field of the Internet of Things, can combine cloud computing to realize the intelligent control of objects and process massive data. While cloud computing brings convenience to smart city services, a serious problem is ensuring that confidential data cannot be leaked to malicious adversaries. Considering the security and privacy of data, data owners transmit sensitive data in its encrypted form to cloud server, which seriously hinders the improvements of potential utilization and efficient sharing. Public key searchable encryption ensures that users can securely retrieve the encrypted data without decryption. However, most existing schemes cannot resist keyword guessing attacks or the size of trapdoors linearly increases with the number of data owners. In this work, by utilizing certificateless encryption and proxy re-encryption, we design an authenticated searchable encryption scheme with constant trapdoors. The designed scheme preserves the privacy of index ciphertexts and keyword trapdoors, and can resist keyword guessing attacks. In addition, data users can generate and upload trapdoors with lower computation and communication overheads. We show that the proposed scheme is suitable for smart city implementations and applications by experimentally evaluating its performance.

关键词： Smart city Data retrieval Privacy protection Certificateless cryptography

来源：评论

学校读者我要写书评

暂无评论

Real-life Human Activity Recognition with Tri-axial Accelerometer Data from Smartphone using Hybrid Long Short-Term Memory networks 15

Real-life Human Activity Recognition with Tri-axial Accelero...

引用

15th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2020

作者： Hnoohom, Narit Jitpattanakul, Anuchit Mekruksavanich, Sakorn Mahidol University Image Information and Intelligence Laboratory Department of Computer Engineering Faculty of Engineering Nakhon Pathom Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand School of Information and Communication Technology University of Phayao Department of Computer Engineering Phayao Thailand

ISBN: (纸本)9780738130682

Human activity recognition (HAR) has an enthusiastic research field in time-series classification due to its variation of successful applications in various domains. The availability of affordable wearable devices have provided many challenging and interesting research HAR problems. Current researches suggest that deep learning approaches are suited to automated feature extraction from raw sensor data, instead of conventional machine learning approaches that reply on handcrafted features. Based on the recent success of Long Short-Term Memory (LSTM) networks for HAR domains, this work proposes a generic framework for accelerometer data based on LSTM networks for real-life HAR. Four hybrid LSTM networks have been comparatively studied on a public available real-life HAR dataset. Moreover, we take advantage of Bayesian optimization techniques for tuning hyperparameter of each LSTM networks. The experimental results indicate that the CNN-LSTM network surpasses other hybrid LSTM networks. © 2020 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Bankruptcy forecasting in enterprises and its security using hybrid deep learning models

Cyber Security and Applications

引用

Cyber Security and Applications 2025年 3卷

作者： Gaurav, Akshat Gupta, Brij B. Bansal, Shavi Psannis, Konstantinos E. Ronin Institute Montclair NJ United States Department of Computer Science and Information Engineering Asia University Taiwan Taichung 413 Taiwan Symbiosis Centre for Information Technology (SCIT) Symbiosis International University Pune India Center for Interdisciplinary Research University of Petroleum and Energy Studies (UPES) Dehradun India Insights2Techinfo India UCRD Chandigarh University Chandigarh India University of Macedonia Greece

In current scenario when economic and risk management sectors need accurate predictions of enterprise bankruptcy, it is very importance issue to research in the field of security of enterprise bankruptcy. In this context, we propose an hybrid deep learning model through the use of convolutional neural network to enhance bankruptcy forecasting models. We address the high-dimensional data and imbalanced problems by introducing feature selection strategically and Synthetic Minority Over-sampling Technique (SMOTE). In a comparative evaluation, the performance of our model is over 81 %, which is better than that for Logistic Regression and Support Vector Machines. This leap in accuracy demonstrates the cutting edge unprecedented ability of our model to decrypt complex financial patterns and establishes a new precedent for deep learning applications in the nuanced field of financial analytics. © 2024 The Authors

关键词： Bankruptcy prediction Convolutional neural networks (CNN) Deep learning Financial risk management SMOTE

来源：评论

学校读者我要写书评

暂无评论

Entanglement Verification of Hyperentangled Photon Pairs

引用

Physical Review Applied 2022年第5期18卷 054025-054025页

作者： Christopher K. Zeitler Joseph C. Chapman Eric Chitambar Paul G. Kwiat Illinois Quantum Information Science and Technology Center University of Illinois Urbana-Champaign Urbana Illinois 61801 USA Department of Physics University of Illinois Urbana-Champaign Urbana Illinois 61801 USA Oak Ridge National Laboratory Oak Ridge Tennessee 37831 USA Department of Electrical & Computer Engineering University of Illinois Urbana-Champaign Urbana Illinois 61801 USA

We experimentally investigate the properties of hyperentangled states displaying simultaneous entanglement in multiple degrees of freedom and find that Bell tests beyond the standard Clauser-Horne-Shimony-Holt inequality can reveal a higher-dimensional nature in a device-independent way. Specifically, we show that hyperentangled states possess more than just simultaneous entanglement in separate degrees of freedom but also entanglement in a higher-dimensional Hilbert space. We also verify the steerability of hyperentangled quantum states by steering different photonic degrees of freedom.

关键词： Entanglement detection Entanglement production Nonlocality Optical quantum information processing Photon pairs & parametric down-conversion Quantum communication Quantum cryptography Optical interferometry

来源：评论

学校读者我要写书评

暂无评论

TransSounder: A hybrid TransUNet-TransFuse architectural framework for semantic segmentation of radar sounder data

TechRxiv

引用

TechRxiv 2021年

作者： Ghosh, Raktim Bovolo, Francesca The Center of Digital Society Fondazione Bruno kessler Trento38123 Italy The Department of Information Engineering and Computer Science University of Trento Trento38123 Italy

Radar Sounders (RSs) are nadir-looking sensors operating in high frequency (HF) or very high frequency (VHF) bands that profile subsurface targets to retrieve miscellaneous scientific information. Due to complex electromagnetic interaction between back-scattered returns, the interpretation of RS data is challenging. The investigations of ice-sheet subsurface structures require automatic techniques to account for both the sequential spatial distribution of subsurface targets and relevant statistical properties embedded in RS signals. Automatic techniques exists for characterizing these targets either related to probabilistic inference model or convolutional neural network (CNN) deep learning methods. Unfortunately, CNN-based methods capture local spatial context and merely model the long-range sequential context. In contrast to CNN, the Transformer-based models are reliable architectures for capturing long-range sequence-to-sequence global spatial contextual prior. Motivated by the aforementioned fact, we propose a novel Transformer-based semantic segmentation architecture named TransSounder to effectively encode the sequential structures of the RS signals. The TransSounder was constructed on a hybrid TransUNet-TransFuse architectural framework to systematically augment the modules from TransUNet and TransFuse architectures. Experimental results obtained on Multi-channel Coherent Radar Depth Sounder (MCoRDS) dataset confirm the robustness and capability of Transformers to accurately characterize the different subsurface targets. © 2021, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

All-Optical, Tunable Third Harmonic Generation in the Ultraviolet Range using Reconfigurable Chalcogenide Metasurfaces

All-Optical, Tunable Third Harmonic Generation in the Ultrav...

引用

CLEO: QELS_Fundamental science, QELS 2022

作者： Gao, Jiannan Vincenti, Maria Antonietta Frantz, Jesse Clabeau, Anthony Qiao, Xingdu Feng, Liang Scalora, Michael Litchinitser, Natalia M. Department of Electrical and Computer Engineering Duke University DurhamNC27708 United States Department of Information Engineering University of Brescia Via Branze 38 Brescia25123 Italy US Naval Research Laboratory 4555 Overlook Ave. SW WashingtonDC20375 United States University Research Foundation 6411 Ivy Ln. 110 GreenbeltMD20770 United States Department of Electrical and Systems Engineering University of Pennsylvania PhiladelphiaPA19104 United States Department of Materials Science and Engineering University of Pennsylvania PhiladelphiaPA19104 United States Aviation and Missile Center US Army CCDC Redstone ArsenalAL35898-5000 United States

We theoretically predict and experimentally demonstrate ultra-high-speed, tunable third harmonic generation (THG) in the opaque spectral range of Arsenic trisulfide (As2S3) glass metasurfaces. © Optica Publishing... 详细信息

ISBN: (纸本)9781557528209

关键词： Harmonic generation

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：