检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wikle, Nathan B. Zigler, Corwin M. Department of Statistics and Actuarial Science University of Iowa United States Department of Statistics and Data Sciences University of Texas Austin United States

Causal inference with spatial environmental data is often challenging due to the presence of interference: outcomes for observational units depend on some combination of local and non-local treatment. This is especially relevant when estimating the effect of power plant emissions controls on population health, as pollution exposure is dictated by (i) the location of point-source emissions, as well as (ii) the transport of pollutants across space via dynamic physical-chemical processes. In this work, we estimate the effectiveness of air quality interventions at coal-fired power plants in reducing two adverse health outcomes in Texas in 2016: pediatric asthma ED visits and Medicare all-cause mortality. We develop methods for causal inference with interference when the underlying network structure is not known with certainty and instead must be estimated from ancillary data. Notably, uncertainty in the interference structure is propagated to the resulting causal effect estimates. We offer a Bayesian, spatial mechanistic model for the interference mapping which we combine with a flexible non-parametric outcome model to marginalize estimates of causal effects over uncertainty in the structure of interference. Our analysis finds some evidence that emissions controls at upwind power plants reduce asthma ED visits and all-cause mortality, however accounting for uncertainty in the interference renders the results largely inconclusive. Copyright © 2023, The Authors. All rights reserved.

关键词： Coal fired power plant

来源：评论

学校读者我要写书评

暂无评论

Redundancy-Free Self-Supervised Relational Learning for Graph Clustering

arXiv

引用

arXiv 2023年

作者： Yi, Si-Yu Ju, Wei Qin, Yifang Luo, Xiao Liu, Luchen Zhou, Yong-Dao Zhang, Ming School of Statistics and Data Science Nankai University Tianjin300071 China School of Computer Science Peking University Beijing100871 China Department of Computer Science University of California Los Angeles90095 United States

Graph clustering, which learns the node representations for effective cluster assignments, is a fundamental yet challenging task in data analysis and has received considerable attention accompanied by graph neural networks in recent years. However, most existing methods overlook the inherent relational information among the non-independent and non-identically distributed nodes in a graph. Due to the lack of exploration of relational attributes, the semantic information of the graph-structured data fails to be fully exploited which leads to poor clustering performance. In this paper, we propose a novel self-supervised deep graph clustering method named Relational Redundancy-Free Graph Clustering (R2FGC) to tackle the problem. It extracts the attribute- and structure-level relational information from both global and local views based on an autoencoder and a graph autoencoder. To obtain effective representations of the semantic information, we preserve the consistent relation among augmented nodes, whereas the redundant relation is further reduced for learning discriminative embeddings. In addition, a simple yet valid strategy is utilized to alleviate the over-smoothing issue. Extensive experiments are performed on widely used benchmark datasets to validate the superiority of our R2FGC over state-of-the-art baselines. Our codes are available at https://***/yisiyu95/R2FGC. © 2023, CC BY.

关键词： Redundancy

来源：评论

学校读者我要写书评

暂无评论

Abnormal Load Patterns Detection in Smart Grids Using Temporal Convolutional Neural Network Based Gated Recurrent Units Networks with Multi-Head Temporal Attention 4

Abnormal Load Patterns Detection in Smart Grids Using Tempor...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Balassem, Zayd Srikanteswara, Ramya Esakki Madura, E. Anjaneyulu, Madugula Devi, M. College of Technical Engineering The Islamic University Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Department of Computer Science and Engineering Bengaluru India Bannari Amman Institute of Technology Department of Artificial Intelligence and Data Science India Gokaraju Rangaraju Institute of Engineering and Technology Department of Artificial Intelligence and Machine Learning Hyderabad India New Prince Shri Bhavani College of Engineering and Technology Department of Electrical and Electronics Engineering Chennai India

ISBN: (纸本)9798350352931

In recent era, the advancement in smart grid technologies and the integration of renewable energy sources have modernized the power distribution landscape. The efficiency and stability of overall system is ensured by the controlling of power converters. In existing, Support Vector Machine (SVM) is utilized but it assumes the normal data follows Gaussian distribution which is not be the same for smart grid data. In this research, Temporal Convolutional Neural Network based Gated Recurrent Units Networks with Multi-Head Temporal Attention (TCN-GRU-MTA) is proposed. Initially, the input signals are considered from Smart Grid Stability (SGS) dataset. Then, the signals are further preprocessed with autoencoders to reduce noise and to improve quality of signals. The Siamese Neural Networks (SNN) feature extractor efficiently learns relevant features from smart grid data which are indicative of abnormal behavior. After that, the SNN is introduced for extracting features from preprocessed data. Next, the proposed TCN-GRU-MTA is utilized to detect the abnormal load patterns in smart grid networks. From the results, the proposed-established better results including accuracy (99.10%), precision (89.98%), recall (99.05%) and F1-score (95.20%) when compared to existing Quadratic SVM. © 2024 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Advances in Clustering Algorithms for Large-Scale data Processing with AI 3

Advances in Clustering Algorithms for Large-Scale Data Proce...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Sharma, Sonal Singh, Vandana Jeyalaxmi, M. Chaudhari, Prasad B. Das, Neeraj Garg, Avni Computer Science and Engineering Karnataka Bangalore India Vivekananda Global University Department of Computer Science & Engineering Jaipur India Prince Shri Venkateshwara Padmavathy Engineering College Department of Science and Humanities Chennai127 India Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

ISBN: (纸本)9798350319125

Clustering is a widely used technique in statistics mining for exploring and reading records with AI. It is an unsupervised gaining knowledge of technique, which may be used for exploratory facts evaluation. Clustering primarily aims to group similar statistics factors in a given facts set. In recent years, diverse advances in clustering algorithms have been developed for massive-scale record processing with AI. Some of the maximum popular clustering algorithms are ok-means, hierarchical clustering, fuzzy clustering, and spectral clustering. This kind of algorithm was used with AI for massive-scale records processing. Okay-approach and hierarchical clustering algorithms were widely used in diverse information mining responsibilities. They permit one to discover and organize the maximum similar statistics points. Fuzzy clustering and spectral clustering algorithms have become famous recently because of their capability to duplicate human perception and questioning when clustering records. Lately, deep learning techniques have been used with clustering algorithms to enhance their overall performance and boom the accuracy of records evaluation. Deep mastering is a subset of machine mastering which allows computers to research from repeated exposure to big datasets robotically. It permits clustering algorithms to investigate big-scale facts faster and more as it should be. Clustering with AI is an effective method for processing and analyzing huge-scale records. Recent advances in clustering algorithms and deep mastering strategies have improved performance and accuracy. Moreover, these algorithms may be used in diverse applications, which include client segmentation, community evaluation, and anomaly detection. © 2023 IEEE.

关键词： algorithms applications performance processing segmentation

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Development in Solving Critical Medical Problems 6

Machine Learning Development in Solving Critical Medical Pro...

引用

6th International Conference on Inventive Computation Technologies, ICICT 2023

作者： Fatima, Shaista Sangeetha, G. Ponmurugan, P. Arularasan, A.N. Prabhu Chakkaravarthy, A. Denis, R. Chinnasamy, A. Department of Electronics and Communication Engineering MJ College Telangana Hyderabad500053 India Department of Artificial Intelligence and Data Science R.M.K College of Engineering and Technology Puduvoyal Tamil Nadu Thiruvallur India Department of Research Meenakshi Academy of Higher Education and Research Tamil Nadu Chennai600078 India Department of Artificial Intelligence and Data Science Panimalar Engineering College Poonamallee Tamil Nadu Chennai600123 India Department of Networking and Communications School of Computing College of Engineering and Technology Tamil Nadu Kattankulathur603203 India Department of Computer Science Mount Carmel College Autonomous Karnataka Bengaluru560052 India Department of Data Science and Business Systems School of Computing SRMIST Kattankulathur campus Tamil Nadu 603203 India

ISBN: (纸本)9798350398496

As a result of ML, the healthcare industry undergoes substantial innovation and improvement. As a result, data management, clinical operations, drug research, and surgery are all progressing more quickly. The healthcare sector is now required to use this cutting-edge technology because of the Covid-19 pandemic. More importantly, people stand to benefit the most from technology because it may improve their health outcomes by identifying the best treatment alternatives for them. Thanks to ML's enhanced early disease detection capabilities, the frequency of re-admissions to hospitals and clinics can be reduced. In this article, we'll look at the main applications of machine learning in healthcare as well as its exceptional benefits in changing the industry. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A Smart Electronic Wheelchair Design Using Artificial Intelligence and Intelligent Sensors Association 2

A Smart Electronic Wheelchair Design Using Artificial Intell...

引用

2nd IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2024

作者： Balamurugan, R. Kanchana, D. Anni Princy, B. Jaisudha, J. Malathi, P. Glory, E. Ajk College of Arts and Science Department of Artificial Intelligence and Machine Learning Tamil Nadu Coimbatore India Srm Institute of Science and Technology Department of Computer Applications Tamil Nadu Chennai India Panimalar Engineering College Department of Computer and Communication Engineering Tamil Nadu Chennai India Prince Shri Venkateshwara Padmavathy Engineering College Department of Ece Tamil Nadu Chennai India Simats Saveetha College of Liberal Arts and Sciences Department of Data Analytics Tamil Nadu Chennai India Simats Department of Biosciences Saveetha School of Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350306415

Since the beginning of the seventeenth century, wheelchairs have been used to transport hospital patients and those with mobility impairments. The power of people is what spreads wheelchairs. Wheelchair users propel themselves forward using their upper bodies or, more commonly, require the assistance of another person to propel them. In this work, we examine how to build an autonomous electric wheelchair for the disabled at the lowest possible cost without sacrificing quality of design or control. This research presents the planning and development of an AI-enhanced electric wheelchair that can be controlled automatically to climb stairs, making it accessible to those with mobility impairments. The chair's controls allow the user to move it in any direction and raise the landing and staircases to varying heights. The chair's DC power source (battery used) may be recharged, allowing it to function for an extended period of time. In addition, a safety system was created that monitors and provides feedback on the user's pulse rate, as well as the wheelchair's functioning state (including acceleration, climate, and inclination position). This proposed AI based Wheelchair (AIWC) design is suitable for any aged people and the proposed model is cross-validated with the conventional wheelchair design using mobile based operations handling system called Mobile-Wheelchair (MWC) to test the efficiency of the proposed design in clear manner. © 2024 IEEE.

关键词： Accelerator AI Artificial Intelligence Batteries DC Power Intelligent Sensors Mobile-Wheelchair MWC Wheelchair

来源：评论

学校读者我要写书评

暂无评论

Setting up SLAs using a dynamic pricing model and behavior analytics in business and marketing strategies in cloud computing

引用

Personal and Ubiquitous Computing 2023年第6期27卷 2225-2241页

作者： Mehlabani, Ehsan Gorjian Javadpour, Amir Zhang, Chongqi Ja’fari, Forough Sangaiah, Arun Kumar Department of Probability and Statistics Guangzhou University Guangzhou510006 China Harbin Institute of Technology Shenzhen China ADiT-Lab Electrotechnics and Telecommunications Department Instituto Politécnico de Viana do Castelo Porto4900-347 Portugal Department of Computer Engineering Sharif University of Technology Tehran Iran International Graduate School of Artificial Intelligence National Yunlin University of Science and Technology Yunlin64002 Taiwan Department of Electrical and Computer Engineering Lebanese American University Byblos13-5053 Lebanon

Increasing amounts of data are being generated every year. Sustainable computing systems have become capable of extracting and learning information from the underlying data. Edge and AI (artificial intelligence) are expanding into industrial systems requiring new computing and networking infrastructure. Due to this, SLA computing is becoming increasingly challenging to handle in these emerging cloud environments. The cloud is a service that provides virtual resources to users. Qualitative and quantitative findings in market-oriented approaches are one of the most common methods for managing virtual and physical machines in a network. When allocating services, price is an important factor to consider. In this study, we aim to determine the initial price of VMs while considering the dynamic pricing model in a competitive, sustainable computing system. Besides negotiation-based trading, a multifactor architecture is used for trading in the marketplace. Based on the simulation results, it was found that the performance could be improved by categorizing the VMs based on regression. According to the simulation results, the cloud market system provides a better service-level agreement (SLA) and response time when assigning virtual machines to the market. Based on the results, we found that using the regression method for categorizing the VMs to manage the market improved the SLA. © 2023, The Author(s).

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

The Assessment of Human Development Index in West Java Province of Indonesia Using Regression and R Programming Technology

The Assessment of Human Development Index in West Java Provi...

引用

2022 IEEE Creative Communication and Innovative Technology, ICCIT 2022

作者： Franciscus, Ronan Pradhana, Widhi Halim, Jonathan Kingsley Diana Permai, Syarifah Arifin, Yulyani Pramudya, Fabian Surya Amirul Jabar, Bakti Bina Nusantara University Computer Science Department Jakarta Indonesia Bina Nusantara University Statistics Department Jakarta Indonesia Bina Nusantara University Mathematics Department Jakarta Indonesia

ISBN: (纸本)9781665468763

The effectiveness of economic development in developing countries is often only judged on an economic basis, even though it cannot be denied that improving the quality of human resources is also a sign of the success of economic development in a region. This study aims to determine and examine the variables that affect the HDI of West Java Province. We compared the two methods, Ordinary Least-Squares (OLS) and Weighted Geographic Regression (GWR), to represent non-spatial and spatial approaches. Twenty-seven districts in West Java Province in Indonesia were considered based on the Indonesian Central statistics Agency dataset. The method used in this research is dataset analysis sourced from the website of the Central statistics Agency (BPS). Six quantitative factors related to HDI were evaluated: life expectancy, expected length of education, the average length of education, per capita expenditure, number of the public health center, and open unemployment rate. The results of this study indicate that the variables of life expectancy, length of education, the average length of education, and expenditure per capita are four variables that have a significant effect on HDI figures in West Java, where GWR performs better than the OLS technology with a coefficient of determination (R2) and AIC value of 99.24113% and 35.10531. Further research is further developed by using robust regression to address outliers in several locations and adopting important factors that influence local policies on local policies. © 2022 IEEE.

关键词： Developing countries

来源：评论

学校读者我要写书评

暂无评论

Classification using Deep CNN Feature Extraction and Hyper parameter Tuned Random Forest in Piperaceae plant Type

Classification using Deep CNN Feature Extraction and Hyper p...

引用

New Frontiers in Communication, Automation, Management and Security (ICCAMS), International Conference on

作者： A. Pravin C. Deepa Department of Computer Science( Artificial Intelligence and Data Science) Sri Ramakrishna College of Arts and Science Coimbatore India

ISBN: (数字)9798350317060

ISBN: (纸本)9798350317077

Piperaceae otherwise known as the piper family, are a flowering plant family in large amount. This piperacease family contains around 3,600 species are presently accepted in 5 genera. The huge amount of special in this piperaceae family is two major genera: Piper (2,171 species) and (over 1,000 species) Peperomia. Piperaceae plant family may include tiny trees, climbers plants, or herbs. The allocation of this group of plants is top distributed in tropical regions of the earths. The species best-known by everyone is Black Pepper (Piper nigrum), most peppercorns yields that are mainly used as cooking spices, including piper betle, even though its connections in the family include numerous other spices. Piper nigrum is cultured for its fruit, which is typically dried and other as a spice and flavouring every food. The fruit is a (stone fruit) drupe which is about (0.20 in) 5 mm in diameter (fully and fresh mature), which encloses a single piper seed, dark red, and contains a stone like structure. The (Piper betle) or betel is a trailing plant of the Piperaceae family, which includes kava and pepper. The betel plant is indigenous to Southeast Asia. It is an dioecious perennial, evergreen plant, with shiny white catkins and heart like shaped leaves. Betel plants are cultured for their leaves which are the majority used in chewing areca nut for flavouring.

关键词： Heart Forestry Flowering plants Feature extraction Prediction algorithms Seeds (agriculture) Security

来源：评论

学校读者我要写书评

暂无评论

Large covariance matrix estimation with factor-assisted variable clustering

arXiv

引用

arXiv 2025年

作者： Li, Dong Qiao, Xinghao Yu, Cheng Department of Statistics and Data Science Tsinghua University Beijing China Faculty of Business and Economics The University of Hong Kong Hong Kong Department of Statistics London School of Economics London United Kingdom

This paper studies the covariance matrix estimation for high-dimensional time series within a new framework that combines low-rank factor and latent variable-specific cluster structures. The popular methods based on assuming the sparse error covariance matrix after taking out common factors may be invalid for many financial applications. Our formulation postulates a latent model-based error cluster structure after removing observable factors, which not only leads to more interpretable cluster patterns but also accounts for non-sparse cross-sectional correlations among the variable-specific residuals. Our method begins with using least-squares to estimate the factor loadings, followed by identifying the latent cluster structure by thresholding the scaled covariance difference measures of residuals. A novel ratio-based criterion is introduced to determine the threshold parameter when performing the developed clustering algorithm. We then establish the cluster recovery consistency of our method and derive the convergence rates of our proposed covariance matrix estimators under different norms. Finally, we demonstrate the superior finite sample performance of our proposal over the competing methods through both extensive simulations and a real data application on minimum variance portfolio. Copyright © 2025, The Authors. All rights reserved.

关键词： Time series

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：