检索结果-内蒙古大学图书馆

Exploring Bias and prediction Metrics to Characterise the Fairness of Machine Learning for Equity-Centered Public Health Decision-Making: A Narrative Review

引用

IEEE ACCESS 2024年 12卷 180815-180829页

作者： Raza, Shaina Shaban-Nejad, Arash Dolatabadi, Elham Mamiya, Hiroshi Vector Inst Artificial Intelligence Toronto ON M5G 0C6 Canada Univ Tennessee Coll Med Dept Pediat Hlth Sci Ctr Memphis TN 38103 USA York Univ Fac Hlth Sch Hlth Policy Toronto ON M3J 1P3 Canada McGill Univ Dept Epidemiol Biostat & Occupat Hlth Montreal PQ H3A 1G1 Canada

The rapid advancement of Machine Learning (ML) represents novel opportunities to enhance public health research, surveillance, and decision-making. However, there is a lack of comprehensive understanding of algorithmic bias - systematic errors in predicted population health outcomes - resulting from the public health application of ML. The objective of this narrative review is to explore the types of bias generated by ML and quantitative metrics to assess these biases. We performed search on PubMed, MEDLINE, IEEE (Institute of Electrical and Electronics Engineers), ACM (Association for Computing Machinery) Digital Library, Science Direct, and Springer Nature. We used keywords to identify studies describing types of bias and metrics to measure these in the domain of ML and public and population health published in English between 2008 and 2023, inclusive. A total of 72 articles met the inclusion criteria. Our review identified the commonly described types of bias and quantitative metrics to assess these biases from an equity perspective. The review will help formalize the evaluation framework for ML on public health from an equity perspective.

关键词： Public healthcare Data models Reviews prediction algorithms Measurement Medical services Diseases Decision making Systematics Predictive models Public health equity evaluation machine learning fairness

来源：评论

学校读者我要写书评

暂无评论

A Novel Series-Concatenation Hybrid prediction Model of Energy Consumption in Hot Strip Roughing Process With Multi-Step Rolling

引用

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2024年第3期21卷 4585-4598页

作者： Zhong, Yanjiu Wang, Jingcheng Rao, Jun Xu, Jiahui Wu, Shunyu Shanghai Jiao Tong Univ Dept Automat Key Lab Syst Control & Informat Proc Shanghai 200240 Peoples R China

The steel industry has received serious attention under the background of carbon neutralization and carbon peaking. However, the traditional end-to-end energy consumption (EC) prediction method does not consider the effects of multi-step rolling, multi-time series, and error accumulation. To this end, a series-concatenation model based on a two-stage hybrid network is proposed to achieve EC high-precision prediction in multi-step continuous rolling. Specifically. First, this paper analyzed the mechanism between rolling EC and multiple variables. Second, a two-stage hybrid network with a deep neural network block, convolutional neural network block, long short-term memory block, and SoftBoost block (DCLS-Net) is established for EC prediction of single-step rolling. SoftBoost block is a double-layer structure method proposed in this paper for multi-block precision improvement based on two kinds of boosting strategies. Last, according to the error mechanism and multi-time series characteristics in the multi-step rolling, a series-concatenation EC prediction model is designed to suppress errors and achieve high-precision prediction. The experimental results show that the SoftBoost can effectively improve prediction performance. And the prediction precision of the two-stage DCLS-Net for single-step rolling is improved by 9.43% on average compared with the end-to-end machine learning algorithm. Furthermore, the precision of the series-concatenation model for multi-step rolling is improved by 4.96% compared with the traditional series model, which can satisfy the requirements of high accuracy and positive error in strip rolling production.

关键词： Strips Predictive models Boosting Energy consumption Steel industry Steel prediction algorithms Strip roughing process multi-step continuous rolling energy consumption prediction two-stage strategy series-concatenation model

来源：评论

学校读者我要写书评

暂无评论

Accurate Cardiovascular Disease prediction: Leveraging Opt_hpLGBM With Dual-Tier Feature Selection

引用

IEEE ACCESS 2024年 12卷 142427-142448页

作者： Gabriel, J. Jasmine Jani Anbarasi, L. Vellore Inst Technol Sch Comp Sci & Engn Chennai 600127 Tamil Nadu India

Reliable forecasting of cardiovascular disease (CVD) outcomes is crucial for efficient patient management. While machine learning (ML) holds promise for disease prediction, challenges arise, particularly with smaller clinical datasets. Feature engineering is essential in this context, as it involves analyzing missing values, managing outliers, and addressing multicollinearity. This process is key to identifying and eliminating unnecessary features from the dataset. To tackle this, a scalable ML based Dual-Tier feature selection framework called ANOVA Chi-Squared (AnoX(2)) is proposed, utilizing a hybrid statistical method. The framework integrates validation using five different ML classifiers with the selected features from AnoX(2). The proposed model Opt_hpLGBM (Optuna hyperparameter tuned Light Gradient Boost Machine) along with AnoX(2) feature selection exhibits outstanding performance across four publicly available datasets, consistently achieving remarkable accuracy. For instance, it achieves 94.87% accuracy in the Cleveland dataset with 8 features, 95.12% in the Statlog dataset with the same number of features, 92.81% accuracy with 7 features in the heart disease dataset, and an impressive 98.85% accuracy in the z-Alizadeh Sani dataset with 12 features. These results exceed current benchmarks, establishing it as an industry leader in terms of the number of features utilized, accuracy, precision, recall, F1 score, and log loss metrics. With its potential for early diagnosis and treatment, this innovative framework can transform healthcare, significantly reducing mortality rates associated with cardiovascular disease.

关键词： Feature extraction Solid modeling Diseases Heart Predictive models Accuracy Support vector machines Machine learning prediction algorithms Data models ANOVA cardiovascular disease chi-squared feature selection hyperparameter tuning preprocessing

来源：评论

学校读者我要写书评

暂无评论

Multi-Graph Spatial-Temporal Synchronous Network for Student Performance prediction

引用

IEEE ACCESS 2024年 12卷 142306-142319页

作者： Zhou, Yifen Yu, Xian Nantong Univ Med Sch Nantong 226019 Peoples R China Nantong Univ Xinglin Coll Nantong 226019 Peoples R China

In the realm of intelligent education, which is crucial for fostering sustainable student growth, predicting student performance stands out as a pivotal element. At its heart, the challenge of forecasting academic success lies in unraveling the complex, hidden relationships within performance data. While numerous investigations have addressed this challenge, existing approaches often overlook comprehensive, multi-perspective modeling and fail to capture the intricate spatial and temporal dependencies synchronously. To bridge these gaps, this study introduces a multi-graph spatial-temporal synchronous network (MGSTSN) to enhance the precision of performance predictions. By innovatively crafting spatial trend and pattern graphs alongside temporal causal graphs, this approach enables a holistic representation of the diverse spatial-temporal dynamics at play. Furthermore, the development of dual spatial-temporal synchronous graphs and their allied synchronous modules marks a novel strategy for simultaneously learning the interplay between spatial and temporal factors affecting student performance. Rigorous evaluations on authentic datasets reveal that MGSTSN significantly outperforms existing models, demonstrating an 8.17% to 11.34% enhancement across various metrics. This validates MGSTSN's advanced capability in capturing the multifaceted nature of student performance data.

关键词： Predictive models Market research Correlation Logic gates prediction algorithms Feature extraction Deep learning Convolution Accuracy Data models Graph convolutional networks Education Performance evaluation multiple perspectives student performance prediction model

来源：评论

学校读者我要写书评

暂无评论

Hybrid Near/Far-Field Channel prediction for RIS-Aided LEO Satellite Networks

引用

IEEE COMMUNICATIONS LETTERS 2025年第1期29卷 16-20页

作者： Xiao, Jian Wang, Ji Li, Xingwang Xie, Wenwu Luong, Nguyen Cong Nallanathan, Arumugam Cent China Normal Univ Coll Phys Sci & Technol Dept Elect & Informat Engn Wuhan 430079 Peoples R China Henan Polytech Univ Sch Phys & Elect Informat Engn Jiaozuo 454003 Peoples R China Hunan Inst Sci & Technol Sch Informat Sci & Engn Yueyang 414006 Peoples R China Phenikaa Univ Fac Comp Sci Hanoi 12116 Vietnam Queen Mary Univ London Sch Elect Engn & Comp Sci London E1 4NS England Kyung Hee Univ Dept Elect Engn Yongin 17104 South Korea

A hybrid near- and far- field cascaded channel prediction scheme is proposed for reconfigurable intelligent surface (RIS) assisted low earth orbit (LEO) satellite networks. In particular, an efficient neural network architecture, inspired by the intrinsic characteristics of wireless signals and termed the signal-informed network (SIN), is exploited to learn the precise mapping between historical uplink channels and future downlink channels. Specifically, in the proposed SIN, the time-domain autocorrelation modeling required by the channel prediction algorithm is converted into frequency-domain representation modeling, which aims to represent high-dimensional channels in terms of major frequency components. Furthermore, considering the specific non-linear phase information of hybrid-field channels, a multi-branch phase-aware module in SIN is developed to exhibit a physics-compliant channel semantic representation. Finally, a deep supervision-based encoder-decoder architecture with the auxiliary loss function is constructed as the network backbone. Simulation results demonstrate that compared to the state-of-art channel prediction models, the proposed SIN model exhibits superior channel prediction accuracy and convergence speed.

关键词： Satellites Predictive models Frequency-domain analysis Uplink Time-domain analysis prediction algorithms Doppler effect Delays Channel prediction near-field communications low earth orbit satellite reconfigurable intelligent surface low earth orbit satellite reconfigurable intelligent surface

来源：评论

学校读者我要写书评

暂无评论

Indoor-Outdoor Energy Management for Wearable IoT Devices With Conformal prediction and Rollout

引用

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 2024年第11期43卷 3370-3381页

作者： Yamin, Nuzhat Bhat, Ganapati Washington State Univ Sch Elect Engn & Comp Sci Pullman WA 99164 USA

Internet of Things (IoT) devices have the potential to enable a wide range of applications, including smart health and agriculture. However, they are limited by their small battery capacities. Utilizing energy harvesting is a promising approach to augment the battery life of IoT devices. However, relying solely on harvested energy is insufficient due to the stochastic nature of ambient sources. Predicting and accounting for uncertainty in the energy harvest (EH) is critical for optimal energy management (EM) in wearable IoT devices. This article proposes a two-step uncertainty-aware EH prediction and management framework for wearable IoT devices. First, the framework employs an energy-efficient conformal prediction (CP) method to predict future EH and construct prediction intervals. Contrasting to prior CP approaches, we propose constructing the prediction intervals using a combination of residuals from previous hours and days. Second, the framework proposes a near-optimal EM approach that utilizes a rollout algorithm. The rollout algorithm efficiently simulates various energy allocation trajectories as a function of predicted EH bounds. Using results from the rollout, the proposed approach constructs energy allocation bounds that maximize application utility (quality of service) with a high probability. Evaluations using real-world energy data from ARAS and Mannheim datasets show that the proposed CP for EH prediction provides 93% coverage probability with an average width of 9.5 J and 1.9 J, respectively. Moreover, EM using the rollout algorithm provides energy allocation decisions that are within 1.9-2.9 J of the optimal with minimal overhead.

关键词： Smart agriculture Uncertainty Smart healthcare prediction algorithms Batteries Trajectory Internet of Things Resource management Biomedical monitoring Wearable devices Conformal prediction energy harvesting energy management wearable devices

来源：评论

学校读者我要写书评

暂无评论

Quantum-Inspired Heuristic Algorithm for Secure Healthcare prediction Using Blockchain Technology

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2024年第6期28卷 3371-3378页

作者： Mazumdar, Hirak Chakraborty, Chinmay Venkatakrishnan, Satheesh Bojja Kaushik, Ajeet Gohel, Hardik A. Woxsen Univ Sch Technol Hyderabad 502345 India BIT Mesra Elect & Commun Engn Mesra 814142 Jharkhand India Florida Int Univ Miami FL 33199 USA Florida Polytech Univ Dept Environm Engn NanoBioTech Lab Lakeland FL 33805 USA Univ Petr & Energy Studies Sch Engn Dehra Dun 248007 India Univ Houston Victoria Dept Comp Informat Sci Appl AI Res Lab Victoria TX 77901 USA

People's health is adversely affected by environmental changes and poor nutritional habits, emphasizing the importance of health awareness. The healthcare system encounters significant challenges, including data insufficiency, threats, errors, and delays. To address these issues and advance medical care, we propose a secure healthcare prediction method, prioritizing patient privacy and data transmission efficiency. The Quantum-inspired heuristic algorithm combined with Kril Herd Optimization (QKHO) is introduced for healthcare prediction, along with a comparison to the Deep Forward Neural Network (DFNN) optimized using Krill Herd Optimization (KHO) and Quantum-inspired heuristic algorithm combined with Kril Herd Optimization. The proposed QKHO model outperforms conventional models and exhibits higher accuracy, precision, recall, and F1-score. Blockchain technology ensures secure data transmission to the server, surpassing the security level of existing RSA and Diffie-Hellman algorithms.

关键词： Medical services prediction algorithms Blockchains Optimization Mathematical models Quantum computing Heuristic algorithms Healthcare prediction biomedical machine learning quantum krill herd optimization (QKHO) deep forward neural network (DFNN) and blockchain

来源：评论

学校读者我要写书评

暂无评论

Modified PUMA/EPUMA Based on Forward and Backward Linear prediction for DOA Estimation

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2025年 22卷

作者： Ma, Biyun Zhu, Fu Wang, Yide Zhu, Qingqing Liu, Jiaojiao South China Univ Technol Sch Elect & Informat Engn Guangzhou 510640 Peoples R China Minist Nat Resources Key Lab Marine Environm Survey Technol & Applicat Guangzhou 510300 Peoples R China Nantes Univ Inst Elect & Technol NumeR IETR CNRS UMR 6164 F-44306 Nantes France

The principal-singular-vector utilization for modal analysis (PUMA) and its modification (Mod-PUMA), which utilize forward linear prediction (FLP) to process the signal subspace, experience significant performance degradation if there are multiple coherent sources and such a performance degradation will be further aggravated in low-SNR regions, which is primarily attributed to the outliers arising from inaccurate estimations of the signal subspace. To address these issues, we propose an extension version of PUMA-related algorithms, called FBLP-Mod-PUMA/enhanced-PUMA (EPUMA). The proposed algorithms improve the threshold performance by refining the signal subspace through forward and backward linear prediction (FBLP), effectively mitigating subspace leakage when dealing with coherent sources. The number of resolvable coherent sources has been theoretically derived and simulation results are provided to show the performance of the proposed algorithms.

关键词： Covariance matrices Eigenvalues and eigenfunctions Vectors prediction algorithms Direction-of-arrival estimation Smoothing methods Simulation Signal to noise ratio Signal processing algorithms Sensor arrays Coherent sources direction-of-arrival (DOA) estimation forward and backward linear prediction (FBLP) principal-singular-vector utilization for modal analysis (PUMA)/enhanced-PUMA (EPUMA)

来源：评论

学校读者我要写书评

暂无评论

Satellite Visibility prediction for Constrained Devices in Direct-to-Satellite IoT Systems

引用

IEEE SENSORS JOURNAL 2024年第16期24卷 26630-26644页

作者： Ortigueira, Raydel Montejo-Sanchez, Samuel Henn, Santiago Fraire, Juan A. Cespedes, Sandra Univ Tecn Federico Santa Maria Dept Telecommun & Telemat CUJAE Dr Ortigueirais Postdoctoral Valparaiso Chile Univ Tecn Federico Santa Maria Adv Ctr Elect & Elect Engn AC3E Valparaiso Chile Univ Tecnol Metropolitana Inst Univ Invest & Desarrollo Tecnol Santiago Chile Univ Nacl Cordoba UNC CONICET Cordoba Argentina INRIA Villeurbanne France Saarland Univ Saarbrucken Germany Univ Chile Dept Elect Engn Santiago Chile Concordia Univ Dept Comp Sci & Software Engn Montreal PQ Canada Univ Tecn Federico Santa Maria Adv Ctr Elect & Elect Engn AC3E Valparaiso Chile

The Internet of Things (IoT) enables the transport of small amounts of data from/to constrained devices such as sensors and actuators. When these devices are located in remote areas without terrestrial network coverage, the direct-to-satellite IoT (DtS-IoT) systems become cost-effective solutions. DtS-IoT allows data exchange with remote nodes through low Earth orbit (LEO) nanosatellites, which are reachable only during short intervals, even during passes with high elevation angles. Therefore, if the constrained nodes become active late concerning a visibility interval, they may miss a transmission opportunity. In the same way, if the nodes become active prematurely, they may incur unnecessary energy consumption. Knowing the duration and start of each visibility interval beforehand allows the constrained devices to increase the probability of successful transmissions and save energy simultaneously. The precise prediction of satellite visibility intervals requires sizable energy and computational costs, a significant challenge for constrained devices, particularly for devices devoid of Internet access on the ground. In this article, we propose a fast and efficient algorithm for satellite visibility prediction that considers the two-body model as a reference and includes a mechanism for the constrained ground nodes to update the orbital information. Numerical and simulation results show that our solution decreases the computation cost by up to 66.53% compared to state-of-the-art visibility prediction algorithms. Furthermore, we show that for each pass of the satellite, the constrained devices successfully update the orbital information 87.12% of the time, this process being completely independent of any supplementary Internet connectivity.

关键词： Orbits Satellites Internet of Things Satellite broadcasting prediction algorithms Interpolation Sensors Constrained devices direct-to-satellite Internet of Things (DtS-IoT) low Earth orbit (LEO) nanosatellites satellite visibility prediction

来源：评论

学校读者我要写书评

暂无评论

A systematic review and comprehensive analysis of building occupancy prediction

引用

RENEWABLE & SUSTAINABLE ENERGY REVIEWS 2024年 193卷

作者： Li, Tao Liu, Xiangyu Li, Guannan Wang, Xing Ma, Jiangqiaoyu Xu, Chengliang Mao, Qianjun Wuhan Univ Sci & Technol Sch Urban Construct Wuhan 430065 Peoples R China Wuhan Univ Sci & Technol Hubei Prov Engn Res Ctr Urban Regenerat Wuhan 430081 Peoples R China Xian Univ Architecture & Technol State Key Lab Green Bldg Western China Xian 710055 Peoples R China

Buildings account for a significant portion of the global energy consumption. Forecasting personnel occupancy is critical for reducing energy consumption in buildings. This study explored the general process of building occupancy prediction models, and specifically analyzed the evolution and application of various data collection methods and predictive algorithms. A comprehensive research framework is established. The main findings indicate that prediction accuracy can be substantially improved by leveraging the Internet of Things technology to enhance data collection and employing hybrid machine learning algorithms. These advancements are vital to optimize building operation strategies, reduce energy consumption, and minimize carbon dioxide emissions. Additionally, the assessment metrics for validating predictive models are discussed and a novel idea based on integrated selection methods is presented. Differing from existing research, this study explores data collection methods and predictive algorithms from a broader perspective, also examining their interplay. Finally, potential directions for further development and improvement in the field are identified. The findings emphasize the necessity to continually innovate in data collection and algorithm development to meet evolving environmental needs and sustainability goals. New insights for engineering design and energy system optimization are offered.

关键词： Building energy consumption Occupancy detection Data collection Occupancy prediction prediction algorithms Methodological choices

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：