检索结果-内蒙古大学图书馆

predictive algorithms and racial bias: a qualitative descriptive study on the perceptions of algorithm accuracy in higher education

引用

INFORMATION AND LEARNING SCIENCES 2023年第9/10期124卷 349-371页

作者： Von Winckelmann, Stacey Lynn MiraCosta Coll Oceanside Dept Lib Oceanside CA 92056 USA

PurposeThis study aims to explore the perception of algorithm accuracy among data professionals in higher ***/methodology/approachSocial justice theory guided the qualitative descriptive study and emphasized four principles: access, participation, equity and human rights. Data collection included eight online open-ended questionnaires and six semi-structured interviews. Participants included higher education professionals who have worked with predictive algorithm (PA) recommendations programmed with student *** are aware of systemic and racial bias in their PA inputs and outputs and acknowledge their responsibility to ethically use PA recommendations with students in historically underrepresented groups (HUGs). For some participants, examining these topics through the lens of social justice was a new experience, which caused them to look at PAs in new *** limitations/implicationsSmall sample size is a limitation of the study. Implications for practice include increased stakeholder training, creating an ethical data strategy that protects students, incorporating adverse childhood experiences data with algorithm recommendations, and applying a modified critical race theory framework to algorithm ***/valueThe study explored the perception of algorithm accuracy among data professionals in higher education. Examining this topic through a social justice lens contributes to limited research in the field. It also presents implications for addressing racial bias when using PAs with students in HUGs.

关键词： Data privacy Data literacy Higher education predictive algorithms Racial bias Social justice Students

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of predictive algorithms for Performance Measurement

引用

IEEE ACCESS 2024年 12卷 33949-33958页

作者： Gupta, Swati Kishan, Bal Gulia, Preeti Maharshi Dayanand Univ MDU Dept Comp Sci & Applicat Rohtak 124001 Haryana India

predictive algorithms, also known as mathematical models, utilize historical data to accurately predict future outcomes. These algorithms identify patterns and relationships within the data, resulting in precise predictions. The growing importance of predictive algorithms in various domains, such as finance, healthcare, marketing, weather forecasting, E-commerce, etc., has led to an increasing need for robust and accurate models. Machine learning (ML) and deep learning (DL) algorithms, including supervised, unsupervised, & reinforcement learning, play a crucial role in prediction. Supervised algorithms include classification and regression, while unsupervised algorithms primarily focus on clustering. In this study, a detailed comparative analysis of eight classification algorithms, six regression algorithms, and five clustering algorithms is performed using diverse datasets and performance metrics. ROBERTA, ResNet, Random Forest Regression, and K-means clustering algorithms outperformed traditional algorithms in textual classification, image classification, regression, and clustering. This study enables data scientists and practitioners to make informed decisions when selecting appropriate models for their specific applications.

关键词： predictive algorithms supervised algorithm unsupervised algorithm classification regression clustering performance metrics

来源：评论

学校读者我要写书评

暂无评论

The robot butler: How and why should we study predictive algorithms and artificial intelligence (AI) in healthcare?

引用

DIGITAL HEALTH 2024年 10卷

作者： Gjodsbol, Iben Mundbjerg Ringgaard, Anna Kirstine Holm, Peter Christoffer Brunak, Soren Bundgaard, Henning Univ Copenhagen Ctr Med Sci & Technol Studies Dept Publ Hlth Copenhagen Denmark Copenhagen Univ Hosp Heart Ctr Dept Cardiol Copenhagen Denmark Univ Copenhagen Novo Nordisk Fdn Ctr Prot Res Copenhagen Denmark Copenhagen Univ Hosp Copenhagen Denmark Univ Copenhagen Fac Hlth & Med Sci Dept Clin Med Copenhagen Denmark Univ Copenhagen Dept Publ Hlth Oster Farimagsgade 5B DK-1014 Copenhagen K Denmark

Artificial intelligence (AI) and algorithms are heralded as significant solutions to the widening gap between the rising healthcare needs of ageing and multi-morbid populations and the scarcity of resources to provide such *** This article investigates how the PMHnet algorithm - an AI prognostication tool developed in Denmark to predict the one-year all-cause mortality risk for patients hospitalized with ischemic heart disease - was presented to cardiologists working in the hospital setting, and how they responded to this novel decision-support *** Empirically, we draw upon ethnographic fieldwork in the Danish-led international research project, PM Heart, which since 2019 has developed the PMHnet algorithm and implemented the software into the electronic health record system in hospitals in Eastern Denmark (the Capital Region and Region Zealand).Results Paying careful attention to the hopes and concerns of cardiologists who will have to embrace and adapt to algorithmic tools in their everyday work of diagnosing and treating patients, we identify three analytical themes meriting attention when AI is implemented in healthcare: 1) the re-negotiation of agency and autonomy in human-algorithm relations, 2) accountability in algorithmic prognostication and 3) the complex relationship between association and causation actualized by predictive algorithms. From these analytical themes, we elicit methodological questions to guide future ethnographic explorations of how AI and advanced algorithms are put to use in the healthcare system, with what implications, and for *** We conclude that local, qualitative investigations of how algorithms are used, embraced and contested in everyday clinical practice are needed in order to understand their implications - good and bad, intended and unintended - for clinicians, patients and healthcare provision.

关键词： Artificial intelligence personalized medicine qualitative (studies) predictive algorithms clinical care ethnography methodological guidance cardiovascular disease precision medicine

来源：评论

学校读者我要写书评

暂无评论

Pursuing open-source development of predictive algorithms: the case of criminal sentencing algorithms

引用

JOURNAL OF COMPUTATIONAL SOCIAL SCIENCE 2022年第1期5卷 89-109页

作者： Waggoner, Philip D. Macmillen, Alec Univ Chicago Chicago IL 60637 USA

Currently, there is uncertainty surrounding the merits of open-source versus proprietary algorithm development. Though justification in favor of each exists, we argue that open-source algorithm development should be the standard in highly consequential contexts that affect people's lives for reasons of transparency and collaboration, which contribute to greater predictive accuracy and enjoy the additional advantage of cost-effectiveness. To make this case, we focus on criminal sentencing algorithms, as criminal sentencing is highly consequential, and impacts society and individual people. Furthermore, the popularity of this topic has surged in the wake of recent studies uncovering racial bias in proprietary sentencing algorithms among other issues of over-fitting and model complexity. We suggest that these issues are exacerbated by the proprietary and expensive nature of virtually all widely used criminal sentencing algorithms. Upon replicating a major algorithm using real criminal profiles, we fit three penalized regressions and demonstrate an increase in predictive power of these open-source and relatively computationally inexpensive options. The result is a data-driven suggestion that if judges who are making sentencing decisions want to craft appropriate sentences based on a high degree of accuracy and at low costs, then they should be pursuing open-source options.

关键词： predictive algorithms Open source Penalized regression Criminal sentencing Feature selection

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Selected predictive algorithms in Control of Machine Processes

引用

ENERGIES 2022年第5期15卷 1895页

作者： Dymora, Pawel Mazurek, Miroslaw Bomba, Slawomir Rzeszow Univ Technol Fac Elect & Comp Engn Al Powstancow Warszawy 12 PL-35959 Rzeszow Poland

The paper presents a comparative analysis of selected algorithms for prediction and data analysis. The research was based on data taken from a computerized numerical control (CNC) milling machine. Methods of knowledge extraction from very large datasets, characteristics of classical analytical methods used in datasets and knowledge discovery in database (KDD) processes were also described. The aim of the study is a comparative analysis of selected algorithms for prediction and data analysis to determine the time and degree of tool usage in order to react early enough and avoid unwanted incidents affecting production effectiveness. The research was based on K-nearest neighbor, decision tree and linear regression algorithms. The influence of the rate of learning and testing set sizes were evaluated, which may have an important impact on the optimization of the time and quality of computation. It was shown that precision decreases with the increase of the K value of the average group, while the percentage of the number of classes in a given set (recall) increases. The harmonic mean for the group mean also increases with increasing K, while a significant decrease in these values was observed for the standard deviations of the group. The numerical value of accuracy decreases with increasing K.

关键词： knowledge discovery in database machine process predictive algorithms Industry 4 0 real-time intelligent milling diagnostic system tool condition monitoring (TCM) system

来源：评论

学校读者我要写书评

暂无评论

Assessment of Satellite Contacts Using predictive algorithms for Autonomous Satellite Networks

引用

IEEE ACCESS 2020年 8卷 100732-100748页

作者： Ruiz-De-Azua, Joan A. Ramirez, Victoria Park, Hyuk Auge, Anna Calveras Camps, Adriano UPC BarcelonaTech Dept Network Engn Barcelona 08034 Spain UPC BarcelonaTech Dept Signal Theory & Commun CommSensLab UPC Barcelona 08034 Spain UPC BarcelonaTech Castelldefels Sch Telecommun & Aerosp Engn Barcelona 08034 Spain Inst Estudis Espacials Catalunya IEEC CTE UPC Barcelona 08034 Spain

Upcoming Low Earth Orbit Satellite Networks will provide low-latency and high downlink capacity necessary for future broadband communications and Earth Observation missions. This architecture was proposed at the beginning of the 90's, although it has just recently re-gained popularity thanks to the so-called Mega-Constellations. This network is composed of satellites that have Inter-Satellite Links (ISL) to communicate between them. Due to the satellite motion, an ISL is a temporal contact between two satellites characterized by a lifetime in which the communication remains feasible. The determination of a route between distant satellites is a challenging problem in this context. However, the satellite follows a well-known deterministic orbit trajectory, being feasible the prediction of its position by propagating a trajectory model over time. The Contact Graph Routing protocol uses this feature to determine the evolution of the routes by pre-computing on-ground a planning of the satellite contacts. This centralized ground-dependent solution cannot be directly applied in the Internet of Satellites paradigm, which proposes the autonomous deployment of heterogeneous satellite networks without pre-assuming any specific satellite system architecture. Following this concept, the present work proposes a distributed algorithm by which a satellite predicts neighbor contacts, and generates a global contact plan without trajectory propagation. To achieve this solution, an ISL has been modeled as a "close approach" between two satellites, which is characterized by their relative motion. The present work details the predictive algorithm, and evaluates its performance in two scenarios with a hybrid satellite constellation and a mega-constellation.

关键词： Satellites Routing protocols Orbits Prediction algorithms Trajectory Satellite constellations Satellite networks satellite communications predictive algorithms federated satellite systems Internet of Satellites inter-satellite link

来源：评论

学校读者我要写书评

暂无评论

Adaptive learning based on AI with predictive algorithms 19

Adaptive learning based on AI with predictive algorithms

引用

7th International Conference on Technological Ecosystems for Enhancing Multiculturality (TEEM)

作者： Rincon-Flores, Elvira G. Mena, Juanjo Lopez-Camacho, Eunice Olmos, Omar Tecnol Monterrey Sch Engn Monterrey Mexico Univ Salamanca GRIAL Res Grp Salamanca Spain Salamanca Univ Educ Dept Salamanca Spain Kazan Fed Univ Inst Psychol & Educ Kazan Russia

ISBN: (纸本)9781450371919

Learning Analytics (LA) is an analysis toolset that enables collection of students' data and context data, for the purpose of visualizing indicators of performance that allow for improvements for learning and academic success. In this study, artificial intelligence (AI) algorithms like K-Nearest Neighbor and Random Forest were used. These algorithms trained a model that could predict the academic success of college-level engineering students. Under an experimental model with 182 students, three instructors leading six groups of Physics II for engineering majors of the Tecnologico de Monterrey (Mexico) administered adaptive measures for one group each and not for the other of their groups (the control groups). Three forecasts were calculated considering structured academic information (numerical grades) and unstructured academic information (student ID pictures). Unstructured data from the facial photograph and numeric academic information from the first evaluation period were considered for the study. The results show a significant difference between the control and experimental groups of only one instructor, while the results of the other two instructors' control and experimental groups were consistent. One finding of this study is that, despite the prediction not being correct for each student, a general picture of the performance of the group was given. It seems that the algorithm must be trained with more data for the forecast to be more precise in the future.

关键词： Artificial intelligence decision trees predictive algorithms Educational Innovation learning analytics adaptive learning

来源：评论

学校读者我要写书评

暂无评论

predictive algorithms for determination of reflectance data from quantity of pigments within experimental dental resin composites

引用

BIOMEDICAL ENGINEERING ONLINE 2015年第Sup2期14卷 1-14页

作者： Ghinea, Razvan Pecho, Oscar Javier Herrera, Luis Maria Ionescu, Ana de la Cruz Cardona, Juan Purificacion Sanchez, Maria Paravina, Rade D. del Mar Perez, Maria Univ Granada Dept Opt E-18071 Granada Spain Univ Granada Dept Comp Architecture & Comp Technol E-18071 Granada Spain Univ Granada Dept Inorgan Chem E-18071 Granada Spain Univ Texas Houston Dept Restorat Dent & Prosthodont Sch Dent Houston Ctr Biomat & Biomimet Houston TX 77054 USA

Background: Being able to estimate (predict) the final spectrum of reflectance of a biomaterial, especially when the final color and appearance are fundamental for their clinical success (as is the case of dental resin composites), could be a very useful tool for the industrial development of these type of materials. The main objective of this study was the development of predictive models which enable the determination of the reflectance spectrum of experimental dental resin composites based on type and quantity of pigments used in their chemical formulation. Methods: 49 types of experimental dental resin composites were formulated as a mixture of organic matrix, inorganic filler, photo activator and other components in minor quantities (accelerator, inhibitor, fluorescent agent and 4 types of pigments). Spectral reflectance of all samples were measured, before and after artificial chromatic aging, using a spectroradiometer. A Multiple Nonlinear Regression Model (MNLR) was used to predict the values of the Reflectance Factors values in the visible range (380 nm-780 nm), before and after aging, from % Pigment (% P1, % P2, % P3 and % P4) within the formulation. Results: The average value of the prediction error of the model was 3.46% (SD: 1.82) across all wavelengths for samples before aging and 3.54% (SD: 1.17) for samples after aging. The differences found between the predicted and measured values of the chromatic coordinates are smaller than the acceptability threshold and, in some cases, are even below the perceptibility threshold. Conclusions: Within the framework of this pilot study, the nonlinear predictive models developed allow the prediction, with a high degree of accuracy, of the reflectance spectrum of the experimental dental resin composites.

关键词： Experimental dental composites predictive algorithms reflectance color coordinates

来源：评论

学校读者我要写书评

暂无评论

Enhancing grid stability with machine learning: A smart predictive approach to residential energy management

引用

ENERGY AND BUILDINGS 2025年 338卷

作者： Olawumi, Mattew A. Oladapo, B. I. De Montfort Univ Sch Engn & Sustainable Dev Leicester England Afe Babalola Univ Sch Sci & Engn Ado Ekiti Nigeria

This research focuses on enhancing energy efficiency and grid stability in residential buildings by developing and evaluating advanced demand response (DR) strategies, explicitly comparing a Rule-Based model with a predictive model leveraging machine learning. The predictive Model utilised a neural network with ReLU activation functions, optimised using grid search and cross-validation, and incorporated real-time data from smart meters and environmental sensors. Evaluation metrics demonstrated that the predictive Model outperformed the RuleBased Model, achieving a 15% reduction in electricity costs, a 20% improvement in energy efficiency, and a 15% reduction in peak load demands while maintaining a high predictive accuracy of 0.95%. However, these benefits came with increased computational complexity and resource requirements. The Rule-Based Model, while more straightforward and less resource-intensive, was less effective in dynamic environments. This study underscores the potential of integrating machine learning with real-time data for optimising residential energy management, offering significant cost savings and contributing to sustainable energy practices. The findings suggest that, despite higher computational demands, the predictive Model provides superior adaptability and accuracy, making it a valuable tool for future smart grid applications.

关键词： Demand response Machine learning Energy efficiency Grid stability predictive algorithms

来源：评论

学校读者我要写书评

暂无评论

A novel geometric predictive algorithm for assessing compressive elastic modulus in MEX additive processes, based on part nonlinearities and layers stiffness, validated with PETG and PLA materials

引用

POLYMER TESTING 2024年 133卷

作者： Mercado-Colmenero, Jorge Manuel Martin-Donate, Cristina Univ Jaen Dept Engn Graph Design & Projects Jaen Spain Univ Jaen Res Grp INGDISIG Jaen Jaen 23071 Spain Campus Lagunillas S-N Bldg A3-210 Jaen 23071 Spain

MEX (Material Extrusion) is an intrusive technological process that inherently induces alterations in the elastic and mechanical parameters of plastic materials. Manufacturers provide initial mechanical parameters for plastic filaments, which undergo modifications during MEX manufacturing, influenced by intrinsic manufacturing factors such as temperature and pressure changes, as well as geometric and technological parameters of the 3D additive process. These factors, compounded by the inherent geometric nonlinearities in plastic components, directly impact the post-manufacture mechanical and elastic properties of the material. Presently, material characterization in MEX manufacturing relies on manual experimental testing, necessitating new tests for any variation in manufacturing parameters. In this scenario of mechanical uncertainty, rigorously validating component behavior involves costly experimental trials. Intending to solve the problems of MEX components manufacturing, the paper presents an innovative methodology based on the use of a new predictive algorithm created by the researchers capable of obtaining the elastic modulus of a plastic material manufactured with MEX and its mechanical behavior in the elastic zone under compressive loads. The predictive algorithm only needs as input the compressive elastic modulus of the isotropic plastic material filament and the manufacturing parameters of the MEX process. The smart developed algorithm calculates the stiffness of each layer considering the number of holes in the projected area. The innovative predictive algorithm has been experimentally and numerically validated using PETG (Polyethylene Terephthalate Glycol) material and PLA (Polylactic Acid) on test specimens and on a case study of variable topology. The results show deviations from [0.2%-4.3%] for PETG and [0.4%] for PLA concerning the experimental tests and [1.1%-13.5%], to the numerical analyses. In this line, the presented algorithm greatly improves t

关键词： Industrial design CAD Numerical simulations Material extrusion predictive algorithms

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：