检索结果-内蒙古大学图书馆

3rd International Conference on Integrated Circuits and Communication systems, ICICACS 2025

作者： Syed, Shakir Sondinti, Lakshminarayana Reddy Kothapalli Sapra, Puneet Joshi, Amit Shobana, M. Deepan Chakravarthi, A.V. Shivam hills India Us Bank LB. Nagar India Rayat Bahara University Department of Computer Science Engineering Mohali India Isma University Department of Information Technology Rīga Latvia M.Kumarasamy College of Engineering Department of Computer Science and Business Systems Karur India Velammal College of Engineering and Technology Department of Civil Engineering Madurai India

ISBN: (纸本)9798331508456

Researchers and financial entities have long been fascinated by the ability to accurately predict the success of start-ups. Modern start-ups, which are creative, tech-focused, and quickly growing companies, face this challenge more than most. This study introduces a deep learning Stacked Denoising Autoencoder (SDAE) model that uses important technology domains to forecast the likelihood of a startup's success. The three primary steps of the proposed approach are as follows: preprocessing, feature extraction, and training the model. To ensure statistical independence of signal components in multivariate datasets, preprocessing steps include min-max normalisation for data standardisation and Independent Component Analysis (ICA) for feature extraction. The predictive power of the SDAE model is then enhanced by training. The proposed model outperforms traditional methods like Decision Trees (DT) and Denoising Autoencoders (DAE) with an average accuracy of 94.28%, according to the experimental data. This makes it a strong contender for predicting startup success in changing technical contexts. © 2025 IEEE.

关键词： Independent component analysis

来源：评论

学校读者我要写书评

暂无评论

Achieving Adaptive Privacy-Preserving Graph Neural Networks Training in Cloud Environment 12

Achieving Adaptive Privacy-Preserving Graph Neural Networks ...

引用

12th IEEE International Conference on information and Communication Networks, ICICN 2024

作者： Yuan, Yanli Lei, Dian Fan, Qing Zhao, Keli Zhu, Liehuang Zhang, Chuan CSSC Systems Engineering Research Institute Beijing China School of Cyberspace Science and Technology Beijing Institute of Technology Beijing China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Guangdong China

ISBN: (纸本)9798350355802

With the widespread adoption of Graph Neural Network (GNN) technology in industry, concerns regarding graph data privacy have become increasingly prominent. Differential privacy has been demonstrated as an effective method to ensure privacy in graph learning. However, existing differential privacy-based GNN methods often overlook the individual privacy protection needs of users, offering uniform privacy guarantees to all. This approach can result in either over-protection or insufficient protection for certain users. To address this issue, we propose an adaptive privacy-preserving GNN training method that accommodates the varying privacy requirements of nodes while achieving high model training accuracy. Specifically, APPGNN allocates adaptive privacy budgets based on individual user privacy needs. Additionally, to mitigate the impact of noise on data utility, APPGNN incorporates a weighted neighborhood aggregation mechanism to enhance GNN model accuracy. Theoretical analysis indicates that APPGNN provides adaptive privacy protection while ensuring ϵ-differential privacy on node data. Experimental evaluations on four real-world graph datasets validate the effectiveness of APPGNN. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Materials property prediction using feature selection based machine learning technique

引用

Materials Today: Proceedings 2022年 69卷 710-715页

作者： Valli Priyadharshini, K. Vijay, A. Swaminathan, K. Avudaiappan, T. Banupriya, V. Department of Computer Science and Engineering K.Ramakrishnan College of Technology Trichy India Department of Information Technology M.Kumarasamy College of Engineering Karur India Department of Computer Science and Engineering K.Ramakrishnan College of Engineering Trichy India Department of Computer Science and Business Systems M.Kumarasamy College of Engineering Karur India

An essential role in increasing quality and reducing environmental damage and public safety is played by material performance prediction in materials research. There is still a long way to go before traditional regression analysis models in materials science can accurately capture non-linearities in data, time-consuming predictions, and enormous amounts of data. Because the more features you have, the less accurate your classification will be, hence you need a feature selection method to improve your results. This necessitates the use of modern computer science methods to analyse materials data. Machine learning (ML) has arose in fresh years as a powerful tool for establishing correlations between data and is finding application in the field of materials science due to its generalizability, noise tolerance, and error tolerance. Different materials servicing varied settings can be predicted for their various properties using machine learning techniques based on feature selection. In this research, feature selection-based ML techniques are demonstrated. Comparisons with various computing and input-ranking approaches demonstrate the importance of the suggested model in materials-related challenges. © 2023

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Communication-efficient Approach of Bayesian Distributed Federated Learning

A Communication-efficient Approach of Bayesian Distributed F...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Wang, Sihua Guo, Huayan Zhu, Xu Yin, Changchuan Lau, Vincent K. N. Beijing University of Posts and Telecommunications Beijing Laboratory of Advanced Information Network Beijing China Hong Kong University of Science and Technology Department of Electronics and Communication Engineering Hong Kong Hkust Shenzhen Research Institute Shenzhen China Harbin Institute of Technology School of Electronic and Information Engineering Shenzhen China

ISBN: (纸本)9798350351255

This paper investigates a fully distributed federated learning (FL) problem, in which each device is restricted to only utilize its local dataset and the information received from its adjacent devices that are defined in a communication graph to update the local model weights for minimizing the global loss function. To incorporate the communication graph constraint into the joint posterior distribution, we exploit the fact that the model weights on each device is a function of its local likelihood and local prior and then, the connectivity between adjacent devices is modeled by a Dirichlet distribution. In this way, the joint distribution can be factorized naturally by a factor graph. Based on the Dirichlet-based factor graph, we propose a novel distributed approximate Bayesian inference algorithm that combines loopy belief propagation (LBP) and variational Bayesian inference (VBI) for distributed FL. Specifically, VBI is used to approximate the non-Gaussian marginal posterior as a Gaussian distribution in local training process and then, the global training process resembles Gaussian LBP where only the mean and variance are passed among adjacent devices. Furthermore, we propose a new damping factor design according to the communication graph topology to mitigate the potential divergence and achieve consensus convergence. Simulation results verify that the proposed solution achieves faster convergence speed with better performance than baselines. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Molecular Skeletons Modification Induces Distinctive Aggregation Behaviors and Boosts the Efficiency Over 19%in Organic Solar Cells

引用

CCS Chemistry 2025年第5期7卷 1495-1508页

作者： Hanjian Lai Xue Lai Yongwen Lang Yongmin Luo Liang Han Yulin Zhu Shilong Xiong Xiangyu Shen Yafei Ding Jiaying Wu Gang Li Feng He Shenzhen Grubbs Institute and Department of Chemistry Southern University of Science and TechnologyShenzhen 518055 Department of Electronic and Information Engineering Research Institute for Smart Energy(RISE)The Hong Kong Polytechnic UniversityHung HomKowloon 999077Hong Kong The Hong Kong University of Science and Technology Function HubAdvanced Materials ThrustNansha511400 Guangzhou Guangdong Provincial Key Laboratory of Catalysis Southern University of Science and TechnologyShenzhen 518055 Institute of Innovative Materials Southern University of Science and TechnologyShenzhen 518055

Understanding the molecular packing arrangement and aggregation behaviors of organic semiconductor materials is crucial in comprehending their unique properties,particularly in complex structures required for solution processing in organic ***,there has been limited focus on studying the diverse self-assembly behaviors induced by varying molecular *** address this issue,we designed and synthesized i-9R4Cl,i-7R4Cl,and 7R4Cl with nine-and seven-membered ring backbones,*** single crystal structures revealed a standard H-type aggregate in i-9R4Cl,which is rare fully face-to-face packing in nonfullerene ***,i-7R4Cl exhibited a typical J-type aggregate,while 7R4Cl demonstrated a synergistic H/J-type aggregate as conventional Y-series ***,it reveals a unique three-dimensional(3D)network packing structure dominated by H-aggregation in i-9R4Cl,a linear packing structure in i-7R4Cl,and an elliptical 3D network packing structure in *** grazing incidence wide-angle X-ray scattering tests confirmed that the packing arrangement in crystal structures was preserved in the film *** i-9R4Cl’s favorable properties in stacking,it achieved a lower power conversion efficiency(PCE)of 1.97%compared to the other two acceptors,which should be attributed to poor exciton separation and carrier recombination induced by the morphology of aggregation ***,the electron paramagnetic resonance indicates that i-9R4Cl possesses radical properties,and when introduced as the third component in the PBDB-TF:BTIC-C9-4Cl based devices,it led to an enhancement in PCE from 18.42%to 19.08%,making it one of the highest efficiencies based on the BTIC-C9-4Cl *** underscores how even subtle changes in molecular structure can significantly impact material *** work aims to control the aggregation states of molecules,transitioning from standard H-type to J-type and to synergistic H/J-type aggreg

关键词： 3D network packing H-type aggregate J-type aggregate single crystal organic solar cells

来源：评论

学校读者我要写书评

暂无评论

Anisotropy of Electronic Spin Texture in the High-Temperature Cuprate Superconductor Bi_(2)Sr_(2)CaCu_(2)O_(8+δ)

引用

Chinese Physics Letters 2023年第3期40卷 45-48页

作者：刘文晶查鹤鸣顾根大沈晓萍叶茂乔山 State Key Laboratory of Functional Materials for Informatics Shanghai Institute of Microsystem and Information TechnologyChinese Academy of SciencesShanghai 200050China Center of Materials Science and Optoelectronics Engineering University of Chinese Academy of SciencesBeijing 100049China Condensed Matter Physics and Materials Science Department Brookhaven National LaboratoryUptonNew York11973USA State Key Laboratory of Surface Physics Department of PhysicsFudan UniversityShanghai 200433China School of Physical Science and Technology ShanghaiTech UniversityShanghai 201210China

Seeking new order parameters and the related broken symmetry and studying their relationship with phase transition have been important topics in condensed matter ***,by using spin-and angle-resolved photoemission spectroscopy,we confirm the helical spin texture caused by spin-layer locking in the nodal region in the cuprate superconductor Bi_(2)Sr_(2)CaCu_(2)O_(8+δ)and discover the anisotropy of spin polarizations at nodes alongΓ–X andΓ–Y *** breaking of C_(4)rotational symmetry in electronic spin texture may give deeper insights into understanding the ground state of cuprate superconductors.

关键词： symmetry superconductor breaking

来源：评论

学校读者我要写书评

暂无评论

Wireless Federated Learning With Hybrid Local and Centralized Training: A Latency Minimization Design

引用

IEEE Journal on Selected Topics in Signal Processing 2023年第1期17卷 248-263页

作者： Huang, Ning Dai, Minghui Wu, Yuan Quek, Tony Q. S. Shen, Xuemin State Key Lab of Internet of Things for Smart City China University of Macau Department of Computer and Information Science China University of Macau State Key Laboratory of Internet of Things for Smart City The Department of Computer and Information Science China Zhuhai Um Science and Technology Research Institute Zhuhai519031 China Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore National Cheng Kung University Taiwan University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada

Wireless federated learning (FL) is a collaborative machine learning (ML) framework in which wireless client-devices independently train their ML models and send the locally trained models to the FL server for aggregation. In this paper, we consider the coexistence of privacy-sensitive client-devices and privacy-insensitive yet computing-resource constrained client-devices, and propose an FL framework with a hybrid centralized training and local training. Specifically, the privacy-sensitive client-devices perform local ML model training and send their local models to the FL server. Each privacy-insensitive client-device can have two options, i.e., (i) conducting a local training and then sending its local model to the FL server, and (ii) directly sending its local data to the FL server for the centralized training. The FL server, after collecting the data from the privacy-insensitive client-devices (which choose to upload the local data), conducts a centralized training with the received datasets. The global model is then generated by aggregating (i) the local models uploaded by the client-devices and (ii) the model trained by the FL server centrally. Focusing on this hybrid FL framework, we firstly analyze its convergence feature with respect to the client-devices' selections of local training or centralized training. We then formulate a joint optimization of client-devices' selections of the local training or centralized training, the FL training configuration (i.e., the number of the local iterations and the number of the global iterations), and the bandwidth allocations to the client-devices, with the objective of minimizing the overall latency for reaching the FL convergence. Despite the non-convexity of the joint optimization problem, we identify its layered structure and propose an efficient algorithm to solve it. Numerical results demonstrate the advantage of our proposed FL framework with the hybrid local and centralized training as well as our proposed alg

关键词： information management

来源：评论

学校读者我要写书评

暂无评论

Calibration Method for Measuring Structural Parameters of Few-mode Multi-core Fiber

Calibration Method for Measuring Structural Parameters of Fe...

引用

2023 Opto-Electronics and Communications Conference, OECC 2023

作者： Liu, Ziwen Tu, Jiajing Jiang, Yongneng Shen, Lei Zhang, Lei Yang, Liubo Liu, Weiping Li, Zhaohui Jinan University College of Information Science and Technology Department of Electronic Engineering Guangzhou510632 China State Key Laboratory of Optical Fiber and Cable Manufacture Technology Yangtze Optical Fiber and Cable Joint Stock Limited Company Wuhan430073 China Sun Yat-sen University Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems Guangzhou510006 China Southern Laboratory of Ocean Science and Engineering Zhuhai Guangdong519000 China

ISBN: (纸本)9781665462136

For the parameter measurement of the fabricated few-mode multi-core fibers (FM-MCFs), the accuracy cannot be guaranteed due to the power coupling among each core or each mode in these fibers. In this paper, using the sensitivity of the differential mode delay (DMD) and inter-core skew (ICS) to the relative refractive index difference between each layer and cladding, we compare the simulated DMD and ICS with the measured values to get the range of relative refractive index difference. Assisted by the image processing algorithm, the core diameter and core pitch of FM-MCF are also corrected. This correction method can give a more accurate parameter selection range for FM-MCF, so as to provide data support for FM-MCFs in transmission and sensing fields. © 2023 IEEE.

关键词： Refractive index

来源：评论

学校读者我要写书评

暂无评论

Second-Life Lithium-Ion Battery Lifetime Early Prediction Based on Hierarchical Bayesian Model 6

Second-Life Lithium-Ion Battery Lifetime Early Prediction Ba...

引用

6th International Conference on Electrical engineering and Control Technologies, CEECT 2024

作者： Li, Ziyuan Peng, Weiwen Zhu, Rong Han, Yu Sun Yat-sen University School of Intelligent Systems Engineering Shenzhen China Guangdong Provincial Key Laboratory of Fire Science and Intelligent Emergency Technology Guangzhou China City University of Hong Kong Department of Systems Engineering Hong Kong Hong Kong

ISBN: (纸本)9798331528096

The rising adoption of electric vehicles has led to a significant increase in retired lithium-ion batteries, creating substantial economic value in their echelon utilization. Accurate lifetime early prediction of retired batteries is important to ensure the safety during their second-life applications. Lifetime early prediction of second-life batteries (SLBs) is challenging due to the large diversity among SLBs, even under the same working conditions. In this paper, we propose a novel hierarchical Bayesian learning framework for SLBs lifetime early prediction, using only condition monitoring data from the first 50 cycles. In this framework, 4 features highly related to degradation are extracted from the early aging data. The selected features are then fed into a hierarchical Bayesian model for SLBs lifetime early prediction. Additionally, batteries under similar working conditions are grouped using the k-means clustering algorithm. Each group has its own hierarchical Bayesian model (HBM), allowing the predictions to account for the specific characteristics of the batteries under various working conditions. The effectiveness of the proposed framework is demonstrated using a self-tested dataset that included 84 SLBs under 21 different working conditions, all with the capacities around 85% of their nominal capacity. The proposed method achieves a mean absolute percentage error of 13.34%, which performs better than traditional regression model. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Advances in modeling cellular mechanical perceptions and responses via the membrane-cytoskeleton-nucleus machinery

引用

Mechanobiology in Medicine 2024年第1期2卷 31-47页

作者： Hongyuan Zhu Run Miao Jin Wang Min Lin The Key Laboratory of Biomedical Information Engineering of Ministry of Education School of Life Science and TechnologyXi'an Jiaotong UniversityXi'an 710049PR China Bioinspired Engineering and Biomechanics Center(BEBC) Xi'an Jiaotong UniversityXi'an 710049PR China

Mechanical models offer a quantitative framework for understanding scientific problems,predicting novel phenomena,and guiding experimental *** the past few decades,the emerging field of cellular mechanobiology has greatly benefited from the substantial contributions of new theoretical tools grounded in mechanical *** the expansive realm of mechanobiology,the investigation of how cells sense and respond to their microenvironment has become a prominent research *** is a growing acknowledgment that cells mechanically interact with their external surroundings through an integrated machinery encompassing the cell membrane,cytoskeleton,and *** review provides a comprehensive overview of mechanical models addressing three pivotal components crucial for force transmission within cells,extending from mechanosensitive receptors on the cell membrane to the actomyosin cytoskeleton and ultimately to the *** present the existing numerical relationships that form the basis for understanding the structures,mechanical properties,and functions of these ***,we underscore the significance of developing mechanical models in advancing cellular mechanobiology and propose potential directions for the evolution of these models.

关键词： Cellular mechanobiology Mechanical models Mechanosensitive receptors Cytoskeleton Nucleus

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：