检索结果-内蒙古大学图书馆

Bayes and Biased Estimators Without Hyper-Parameter Estimation: Comparable Performance to the Empirical-Bayes-Based Regularized Estimator

引用

IEEE Control Systems Letters 2025年 9卷 294-299页

作者： Yue Ju Bo Wahlberg Håkan Hjalmarsson Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Division of Decision and Control Systems and the Competence Centre for Advanced BioProduction by Continuous Processing AdBIOPRO School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden

Regularized system identification has become a significant complement to more classical system identification. It has been numerically shown that kernel-based regularized estimators often perform better than the maximum likelihood estimator in terms of minimizing mean squared error (MSE). However, regularized estimators often require hyper-parameter estimation. This letter focuses on ridge regression and the regularized estimator by employing the empirical Bayes hyper-parameter estimator. We utilize the excess MSE to quantify the MSE difference between the empirical-Bayes-based regularized estimator and the maximum likelihood estimator for large sample sizes. We then exploit the excess MSE expressions to develop both a family of generalized Bayes estimators and a family of closed-form biased estimators. They have the same excess MSE as the empirical-Bayes-based regularized estimator but eliminate the need for hyper-parameter estimation. Moreover, we conduct numerical simulations to show that the performance of these new estimators is comparable to the empirical-Bayes-based regularized estimator, while computationally, they are more efficient.

关键词： Bayes methods Maximum likelihood estimation Covariance matrices Vectors System identification Noise measurement Linear regression Probability density function Contracts Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Optimizing Supply Chain Efficiency: Integrating Deep Learning and Blockchain Technologies 1

Optimizing Supply Chain Efficiency: Integrating Deep Learnin...

引用

1st International Conference on Intelligent Technologies for Sustainable Electric and Communications Systems, iTech SECOM 2023

作者： Shanmugapriyaa, K.R. Swetha, S. Janani, N. Bavithra, K. Padmavathi, K. Coimbatore Institute of Technology Department of Artificial Intelligence and Data Science Tamilnadu India Kathir College of Engineering Department of Computer Engineering Tamilnadu India Psg Institute of Technology and Applied Research Department of Electrical and Electronics Engineering Tamilnadu India Hindusthan Polytechnic College Department of Computer Engineering Tamilnadu India

ISBN: (纸本)9798350371185

The research introduces an innovative supply chain management system tailored for agriculture, aiming to enhance operational efficiency and transparency through cutting-edge technologies such as deep learning and blockchain. The system comprises four modules, each leveraging machine learning algorithms to optimize various agricultural processes. The first module utilizes LSTM models to predict crop yields and diseases, empowering farmers with valuable insights into crop health and potential yields. The second module focuses on inventory management optimization using DQN algorithms, enabling farmers to efficiently utilize resources and minimize waste. The third module employs GNN technology to optimize routes for accessing industry-specific points of interest, simplifying farmers' access to relevant information and resources. Lastly, the fourth module addresses significant challenges in agriculture, including crop demand, rotation planning, market trends, pricing strategies, and market identification, employing a DBN model. This study showcases the transformative power of machine learning algorithms in revolutionizing productivity and profitability within the agriculture sector, offering actionable insights and optimization tools to farmers. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Optimally Scheduling Single-Arm Multicluster Tools for Manufacturing Hybrid-Type Wafers

Optimally Scheduling Single-Arm Multicluster Tools for Manuf...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Wang, Genghong Zhu, Qinghua Hou, Yan Qiao, Yan Wu, Naiqi Zhou, Mengchu School of Computer Science and Technology Guangdong University of Technology Guangzhou China Institute of Systems Engineering Macau University of Science and Technology Macau China New Jersey Institute of Technology Department of Electrical and Computer Engineering NewarkNJ07920 United States

ISBN: (纸本)9798350337020

In semiconductor manufacturing, multicluster tools are widely employed for many wafer fabrication processes. With the demand for high-mix integrated circuit chips and shrinkage of circuit width, a scheme in which multiple wafer types are fabricated inside multicluster tools is adopted by wafer foundries to make more profits. Multiple wafer types, multiple robots, and wafer residency time constraints make the resulting scheduling problems challenging. This work focuses on scheduling a single-arm multicluster tool to process two wafer types concurrently subject to wafer residency time constraints in which a conventional one-wafer cycle and backward strategy are not efficient. With such properties, several necessary and sufficient conditions are presented to check the feasibility of a periodic schedule. Polynomial-time-complex algorithms are proposed to examine a tool's schedulability and coordinate multiple robots to handle wafers for schedulable scenarios. The cycle time of an obtained schedule can reach the lower bound. A practical example is used to show the effectiveness of the proposed algorithm. © 2023 IEEE.

关键词： hybrid-type wafers multicluster tools scheduling semiconductor manufacturing wafer fabrication

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Novel Infrared, Millimeter wave, and Terahertz Metamaterials

Deep Learning for Novel Infrared, Millimeter wave, and Terah...

引用

International Conference on Infrared and Millimeter Waves

作者： Willie Padilla Natalie Rozman Yang Deng Rixi Peng Jordan Malof Department of Electrical and Computer Engineering Duke University Durham USA Department of Electrical and Computer Engineering University of Montana Durham USA Department of Computer Science University of Montana Missoula USA

ISBN: (数字)9798350370324

ISBN: (纸本)9798350370331

Electromagnetic metamaterials and metasurfaces possess a property termed electromagnetic similitude, permitting them to operate over a large swath of the electromagnetic spectrum from radio frequencies to visible with a simple scaling of the geometry. Additionally, metamaterials are composites meaning they can be fashioned so that their metallic or dielectric constituents can serve alternative functions, i.e. metamaterials are multi-functional. These two key metamaterial features make them ideal candidates for novel devices operating across the electromagnetic spectrum. Although design of metamaterials may often follow intuition, more complex designs or unit-cells which are are not sub-wavelength present more complex challenges. We present new deep learning designed metamaterials operating as broadband detectors of W-band radiation in the millimeter wave regime, as high quality factor (Q-factor) resonators achieving the highest Q-factor published to-date, and as engineered diffusers of infrared radiation for imaging applications. Our exploration of metamaterials across diverse regimes emphasizes the great potential and significance of the metamaterial deep learning design concept for the future of photonics.

关键词： Geometry Q-factor Deep learning Terahertz metamaterials Inverse problems Surface waves Metasurfaces Metamaterials Electromagnetic spectrum Resonators

来源：评论

学校读者我要写书评

暂无评论

Robust Frequency Stabilization of Renewable-Bio-Electric Vehicle Integrated Multi Microgrid under Diverse Structure Model Predictive Controller 2

Robust Frequency Stabilization of Renewable-Bio-Electric Veh...

引用

2nd IEEE International Conference on Sustainable Energy and Future Electric Transportation, SeFeT 2022

作者： Latif, Abdul Aftab, Mohd. Asim Suhail Hussain, S.M. Khalifa University Department of Electrical Engineering and Computer Science Abu Dhabi United Arab Emirates Thapar Institute of Engineering and Technology Department of Electrical and Instrumentation Engineering Punjab India National University of Singapore Department of Computer Science Singapore Singapore

ISBN: (数字)9781665480574

ISBN: (纸本)9781665480574

The microgrid exhibits a notable change in the frequency deviation (Delta F) even for small perturbations in the connected load or weather dependent energy sources like solar, wind etc. Hence a secondary load frequency control is required for frequency stabilization in the microgrid. In this paper, a novel combination of model predictive controller (MPC) and tilt derivative called diverse structure model predictive controller (DSMPC) is proposed for multi microgrids. A multi microgrid is comprised of wind and solar tower power generation units, including bio generations and electric vehicle (EV) in both the areas. The performance of the proposed controller is compared against marine predator technique optimized DSMPC and MPC controls. Furthermore, the study investigates the impact EV in stabilizing the system frequency under the consideration of real-time wind data. A real-time hardware-in-the-loop (HIL) simulation platform is utilized to validate the proposed control approach. © 2022 IEEE.

关键词： Simulation platform

来源：评论

学校读者我要写书评

暂无评论

Toward Optimal Amount of Training Annotations for Waterfowl Detection and Classification

Toward Optimal Amount of Training Annotations for Waterfowl ...

引用

IEEE International Conference on Mobile Cloud Computing, Services, and engineering (MobileCloud)

作者： Yuan Feng Yang Zhang Yi Shang Department of Electrical Engineering and Computer Science University of Missouri Columbia

ISBN: (数字)9798331539856

ISBN: (纸本)9798331539863

A suitable amount of training data is important in efficiently training high-quality deep learning models. In this paper, we performed an empirical study aimed at finding optimal amount of labeled waterfowl annotations or images for training detection and classification deep learning models with real-world aerial images. We proposed a new class-aware sampling method that can generate better training sets which led to significantly better waterfowl detectors. The results show that the trained Faster R-CNN and YOLOv5 models achieved over 86% accuracy with only 300 waterfowl training annotations using the new sampling method while the basic random sampling method needs 500 annotations to achieve same performance. In addition, the class-aware sampling method significantly accelerated training convergence of all detection models we applied. For waterfowl classification, we compared experimental results of two representative supervised-learning models and two semi-supervised learning methods, and combined with two loss functions and two sampling methods to generate training sets. The results show that semi-supervised learning methods outperformed supervised learning models, achieving F1 score over 0.8 using only 100 labeled training images per waterfowl class.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TSDSI Standards Driven Implementation of Smart Radio Environment 17

TSDSI Standards Driven Implementation of Smart Radio Environ...

引用

17th IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2023

作者： Shrivastava, Amit K. Kumar, Satish Sahu, Khushboo Sonwani, Bhavesh Sharma, Dixit Srivastava, Dipti S. Garg, Navneet Kherani, Arzad Alam Bhatia, Vimal Mukherjee, Soumava Mukhopadhyay, Samrat Das, Priyanka Mahapatra, Rajarshi Das, Debanjan Lall, Brejesh Iit Department of Electrical Engineering and Computer Science Bhilai India Iiit Department of Electronics and Communication Engineering Bangalore India Iiit Department of Electronics and Communication Engineering Naya Raipur India Department of Electronics Engineering Dhanbad India Iit Department of Electrical Engineering Indore India Iit Department of Electrical Engineering Jodhpur India Iit Department of Electrical Engineering Delhi India

ISBN: (纸本)9798350307672

This paper presents a prototype implementation of a smart radio environment (SRE) based communication system. A reflecting plate, reconfigurable intelligent surface (RIS) is placed between the transmitter and receiver to build the SRE. The RIS can rotate to reflect the incident wave to a particular direction. The experimental model consists of a channel estimator (CE), a generic RIS controller (GRC), and a RIS-specific controller (RSC). The channel estimator is equipped with two universal software radio peripheral's (USRP's) that act as transmitter and receiver. Further, based on the desired throughput requirements, the CE sends commands to the GRC, which in turn sends commands to the RSC that controls the RIS. Since a RIS can be designed and fabricated in many ways, a Telecommunications Standards Development Society, India (TSDSI) standard is in place to list the interface/messages between the wireless system and the RIS. These standardized commands are used to exchange messages between the GRC and RSC. With this setup, the received power improvement of around 20 dBm has been achieved if RIS is deployed. Also, an algorithm at GRC finds the beamforming angle where the received power is maximized. © 2023 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Investigating customer churn in banking:a machine learning approach and visualization app for data science and management

引用

Data science and Management 2024年第1期7卷 7-16页

作者： Pahul Preet Singh Fahim Islam Anik Rahul Senapati Arnav Sinha Nazmus Sakib Eklas Hossain Institute for Artificial Intelligence and Data Science University at BuffaloThe State University of New YorkAmherst14068United States Department of Mechanical Engineering Khulna University of Engineering&TechnologyKhulna9203Bangladesh Department of Information Technology Kennesaw State UniversityMarietta30067United States Department of Electrical and Computer Engineering Boise State UniversityBoise83725United States

Customer attrition in the banking industry occurs when consumers quit using the goods and services offered by the bank for some time and,after that,end their connection with the ***,customer retention is essential in today’s extremely competitive banking ***,having a solid customer base helps attract new consumers by fostering confidence and a referral from a current *** factors make reducing client attrition a crucial step that banks must *** our research,we aim to examine bank data and forecast which users will most likely discontinue using the bank’s services and become paying *** use various machine learning algorithms to analyze the data and show comparative analysis on different evaluation *** addition,we developed a Data Visualization RShiny app for data science and management regarding customer churn *** this data will help the bank indicate the trend and then try to retain customers on the verge of attrition.

关键词： Bank customer attrition Churn prediction Machine learning XGboost Random forest

来源：评论

学校读者我要写书评

暂无评论

CircR2Disease v2.0:An Updated Web Server for Experimentally Validated circRNA–disease Associations and Its Application

引用

Genomics, Proteomics & Bioinformatics 2022年第3期20卷 435-445页

作者： Chunyan Fan Xiujuan Lei Jiaojiao Tie Yuchen Zhang Fang-Xiang Wu Yi Pan School of Computer Science Shaanxi Normal UniversityXi’an 710119China Division of Biomedical Engineering University of SaskatchewanSaskatoonSK S7N 5A9Canada Department of Computer Science Georgia State UniversityAtlantaGA 30302USA

With accumulating dysregulated circular RNAs(circRNAs)in pathological processes,the regulatory functions of circRNAs,especially circRNAs as microRNA(miRNA)sponges and their interactions with RNA-binding proteins(RBPs),have been widely ***,the collected information on experimentally validated circRNA-disease associations is only ***,an updated CircR2Disease database providing a comprehensive resource and web tool to clarify the relationships between circRNAs and diseases in diverse species is ***,we present an updated CircR2Disease v2.0 with the increased number of circRNA-disease associations and novel ***2Disease v2.0 provides more than 5-fold experimentally validated circRNA-disease associations compared to its previous *** version includes 4201 entries between 3077 circRNAs and 312 disease ***,the information of circRNA-miRNA,circRNA-miRNA-target,and circRNA-RBP interactions has been manually collected for various ***,the gene symbols of circRNAs and disease name IDs can be linked with various nomenclature *** descriptions such as samples and journals have also been integrated into the updated ***,CircR2Disease v2.0 can serve as a platform for users to systematically investigate the roles of dysregulated circRNAs in various diseases and further explore the posttranscriptional regulatory function in ***,we propose a computational method named circDis based on the graph convolutional network(GCN)and gradient boosting decision tree(GBDT)to illustrate the applications of the CircR2Disease v2.0 ***2Disease v2.0 is available at http://***/CircR2Disease_v2.0 and https://***/bioinforlab/CircR2Disease-v2.0.

关键词： circRNA circRNA-disease association Graph convolutional network Gradient boosting decision tree Machine learning

来源：评论

学校读者我要写书评

暂无评论

Supplementing Sensitive Survey Data by Leveraging Social Listening with Machine Learning Models

Supplementing Sensitive Survey Data by Leveraging Social Lis...

引用

2023 Big Data Meets Survey science, BigSurv 2023

作者： Smalley, Heather Kitada Walker Orr, J. Willamette University School of Computing and Information Science SalemOR United States George Fox University Department of Electrical Engineering and Computer Science NewbergOR United States

ISBN: (纸本)9798350345278

In December 2017, the US department of Justice requested the reinstatement of the citizenship question on the 2020 Decennial Census questionnaire;however, perceptions of the Trump administration's stance on immigration caused concern for how these data would be used and gave rise to Twitter movements. Although this request for the 2020 Decennial Census was ultimately rejected by the Supreme Court in June 2019, the American Community Survey (ACS) continued to include the citizenship question. Due to this, we wish to explore the association between the movements, such as #leaveitblank, and rates of missingness in the ACS from 2017 to 2020. This project is novel because we combine data from a long established government survey obtained from a probability sample with social media data, which comes from a non-probability sample with different frequencies. There are 73 gigabytes of ACS data, containing both individual and household records from 2005 to 2020. The data from Twitter consists of 13.3 million tweets collected from 2011 to 2020. We employ supervised and unsupervised machine learning methods for natural language processing, including S-BERT and neural networks in order to geolocate and classify relevant tweets. These Twitter data are aggregated over space and time in order to assess possible correlations with trends in non-response. © 2023 IEEE.

关键词： Machine learning

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：