检索结果-内蒙古大学图书馆

7th International Conference on Business and Industrial Research (ICBIR)

作者： Ohyama, Tomoya Tohoku Univ Ctr Data Driven Sci & Artificial Intelligence Sendai Miyagi Japan

ISBN: (纸本)9781665494755

Crime prediction research has been biased toward spatial factors, and insufficient research has detailed predictions regarding temporal factors. To build an industrially practical crime prediction system, it is necessary to develop a method that considers both temporal and spatial risk factors. This study estimates the effect of time-variant variables such as the day of the week, season, weather, and events for a fundamental analysis of time-based crime prediction. However, because crime data are often imbalanced data with extremely few positive classes, subdividing the data spatially and temporally makes it difficult to estimate the parameters. Therefore, we attempted to solve this problem by dividing the city into clusters with high spatial homogeneity and analyzing each cluster. We observed different effects of time-varying factors for different types of crime.

关键词： crime prediction predictive algorithm time-variant variables spatial clustering generalized linear mixed model

来源：评论

学校读者我要写书评

暂无评论

A predictive model for identification of pediatric individuals with common variable immunodeficiency through electronic medical records

引用

Journal of Allergy and Clinical Immunology 2025年

作者： Alsaati, Nouf Penney, Chris Helbig, Ingo Sullivan, Kathleen E. Division of Allergy and Immunology Children's Hospital of Philadelphia Philadelphia Pa United States Division of Neurology Epilepsy NeuroGenetics Initiative (ENGIN) Children's Hospital of Philadelphia Philadelphia Pa United States Department of Biomedical and Health Informatics Children's Hospital of Philadelphia Philadelphia Pa United States Department of Neurology University of Pennsylvania Perelman School of Medicine Philadelphia Pa United States

Introduction: Common variable immunodeficiency (CVID) is characterized by recurrent sinopulmonary infections. However, in the pediatric population, recurrent sinopulmonary infections early in life are common, which can render key clinical features of CVID less distinctive. Accordingly, the diagnosis of CVID is often delayed owing to the heterogeneous nature of the presentation and the broad range of ages of onset. A 10-year lag in diagnosis has been found for CVID, and there is a critical need for improved time to diagnosis. Objective: Our aim was to utilize machine learning techniques to identify a clinical signature of CVID in a pediatric population. Methods: Our selected cohort included 112 individuals with CVID and 627 controls. The controls were restricted from having other medical conditions associated with infection. A machine learning data set was constructed by summing patient-level counts of clinical metrics. A total of 3 supervised machine learning classifiers were trained, tuned, and performance-tested. We validated our findings using a distinct control cohort with high medical complexity and tested a logistic regression approach. Results: Key features associated with CVID were chest radiograph count, number of antibiotic prescriptions, and number of common infections. Our Extreme Gradient Boosting (XGBoost) model best predicted eventual CVID diagnosis, with an F1 score of 0.77, a total of 21 of 29 CVID diagnoses classified correctly (8 false-negative results), and 179 of 183 patients without CVID correctly classified (4 false-positive results) up to 10 years before the eventual clinical diagnosis. Key features with a robust association with pediatric CVID were the frequency of common infections and antibiotic prescriptions. Conclusion: In spite of a high frequency of infections in the comparator population, the clinical signature of pediatric CVID was sufficiently distinctive to enable early identification. © 2025 American Academy of Allergy, Asthma & I

关键词： antibody deficiency artificial intelligence inborn error of immunity machine learning predictive algorithm Primary immunodeficiency

来源：评论

学校读者我要写书评

暂无评论

A multi-energy system optimisation software for advanced process control using hypernetworks and a micro-service architecture

引用

ENERGY REPORTS 2021年 7卷 167-175页

作者： Jones, Sean Charlesworth, Richard Naik, Kevin Charlesworth, Thomas O'Dwyer, Edward Ianakiev, Anton Johnson, Jeff Boukhanouf, Rabah Gillott, Mark Sellwood, Victor Aloor, Joy Siemens Sir William Siemens House Manchester Lancs England Nottingham Trent Univ Nottingham England Imperial Coll London London England Open Univ Milton Keynes Bucks England Univ Nottingham Nottingham England

This paper describes a multi-energy system optimisation software, "Sustainable Energy Management System" (SEMS), developed as part of a Siemens, Greater London Authority and Royal Borough of Greenwich partnership in collaboration with the University of Nottingham, Nottingham Trent University and Imperial College London. The software was developed for application at a social housing estate in Greenwich, London, as part of the Borough's efforts to retrofit the energy systems and building fabric of its housing stock. Its purpose is to balance energy across vectors and networks through day-ahead forecasting and optimisations that can be interpreted as control outputs for energy plant such as a water source heat pump, district heating pumps and values, power switchgear, gas boilers, a thermal store, electric vehicle chargers and a photovoltaic array. The optimisation objectives are to minimise greenhouse gas emissions and operational cost. The tool uses Hypernetwork Theory based orchestration coupled with a microservice architecture. The distributed nature of the design ensures flexibility and scalability. Currently, microservices have been programmed to forecast domestic heating demand, domestic electricity demand, electric vehicle demand, solar photovoltaic generation, ground temperature, and to run a day-ahead energy balance optimisation. This paper presents the results from both domestic heat and electricity demand forecasting, as well as the overall design and integration of the software with a physical system. The works build on that of O'Dwyer, et al. (2020) who developed a preliminary energy management software and digital twin. Their work acts as a foundation for this real-world commercialisation-ready program that integrates with physical assets. (C) 2021 The Authors. Published by Elsevier Ltd.

关键词： Multi-energy systems Energy optimisation predictive algorithm Hypernetwork theory Microservice architecture

来源：评论

学校读者我要写书评

暂无评论

Predicting Taxi and Uber Demand in Cities: Approaching the Limit of Predictability

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2021年第6期33卷 2723-2736页

作者： Zhao, Kai Khryashchev, Denis Vo, Huy Georgia State Univ Robinson Coll Business Atlanta GA 30302 USA CUNY Grad Ctr New York NY 10016 USA CUNY City Coll New York NY 10031 USA NYU Ctr Urban Sci & Progress New York NY 10003 USA

Time series prediction has wide applications ranging from stock price prediction, product demand estimation to economic forecasting. In this article, we treat the taxi and Uber demand in each location as a time series, and reduce the taxi and Uber demand prediction problem to a time series prediction problem. We answer two key questions in this area. First, time series have different temporal regularity. Some are easy to be predicted and others are not. Given a predictive algorithm such as LSTM (deep learning) or ARIMA (time series), what is the maximum prediction accuracy that it can reach if it captures all the temporal patterns of that time series? Second, given the maximum predictability, which algorithm could approach the upper bound in terms of prediction accuracy? To answer these two question, we use temporal-correlated entropy to measure the time series regularity and obtain the maximum predictability. Testing with 14 million data samples, we find that the deep learning algorithm is not always the best algorithm for prediction. When the time series has a high predictability a simple Markov prediction algorithm (training time 0.5s) could outperform a deep learning algorithm (training time 6 hours). The predictability can help determine which predictor to use in terms of the accuracy and computational costs. We also find that the Uber demand is easier to be predicted compared the taxi demand due to different cruising strategies as the former is demand driven with higher temporal regularity.

关键词： Three-dimensional displays Shape Measurement Detectors Feature extraction Object recognition Clutter Sharing economy deep learning predictive algorithm predictability of time-series data mining

来源：评论

学校读者我要写书评

暂无评论

Tribological behavior of MgO doped alumina ceramics

Tribological behavior of MgO doped alumina ceramics

引用

Symposium on Failure and Preventive Maintenance of Machineries (FPMM)

作者： Haldar, Partha Bhattacharya, Tapas Kumar Modak, Nipu Govt Coll Engn & Ceram Technol Dept Mech Engn Kolkata 700010 India Govt Coll Engn & Ceram Technol Dept Ceram Technol Kolkata 700010 India Jadavpur Univ Dept Mech Engn Kolkata 700032 India

In this study, the coefficient of frictions under variable normal load and reciprocating frequencies of alumina ceramics have been investigated with various level (upto 4 wt%) of nano-crystalline MgO addition. A linear reciprocating tribotester was used to carry out the experimental investigations in dry condition using a silicon nitride (Si3N4) ball as a counter surface on the sintered samples. The friction tests were performed for a sliding time of 30 min with reciprocating frequency of 15, 30, 45, 60 Hz keeping the normal load fixed at 0.5 kgf and at normal loads of 0.3, 0.5, 0.7, 1.0 kgf keeping the sliding frequency fixed at 30 Hz. The friction coefficient increases with increasing sliding frequency, normal load but decreases with nano-magnesia addition. The friction coefficient data is used to develop an algorithm following the best fit topology to predict the addition level of magnesia in alumina for given friction coefficient and sliding frequency or normal load. Among various curve fitting techniques like polynomial fit of degree two, exponential fit of degree one and two, smoothing spline and Weibull fit, with minimum root mean square error, cubicspline fit method is adopted to form smooth curves in MATLAB. The validated result lies within a maximum error of 3.37% for cubicspline fit. Copyright (C) 2022 Elsevier Ltd. All rights reserved. Selection and peer-review under responsibility of the scientific committee of the Symposium on Failure and Preventive Maintenance of Machineries 2022.

关键词： MgO-Alumina ceramic system Dry Reciprocating Friction Coefficient of friction predictive algorithm RMSE Cubicspline fit

来源：评论

学校读者我要写书评

暂无评论

Vehicle Collision Avoidance System Using Localization algorithm And predictive Analysis 6

Vehicle Collision Avoidance System Using Localization Algori...

引用

6th Annual Conference on Computational Science and Computational Intelligence (CSCI)

作者： John, Samuel Ndueso Noma-Osaghae, Etinosa Okokpujie, Kennedy Okereke, Chinonso Ananaba, Joshua Omoruyi, Osemwegie Nigeria Def Acad Dept Elect & Elect Engn Afaka Kaduna State Nigeria Covenant Univ Dept Elect & Informat Engn Ota Ogun State Nigeria

ISBN: (纸本)9781728155845

Road crashes account for over a million deaths around the world every year. It is one of the leading causes of death for young people between the ages of fifteen and twenty-ine. Road accidents cause a whooping loss of up to three percent of the many nations' Gross Domestic Product (GDP) and ninety percent of these accidents occur in low to middle income countries with a sizable fifty-four percent share of the world's vehicular population. One of the Sustainable Development Goals (SDG5) is the reduction of road accidents around the world by half of its current value by 2020. This goal becomes a hit if low to medium-income nations get safer roads. This paper proposes a collision avoidance system that provides drivers with an automated preemptive response to impending car accidents with the aid of distance predictive analysis via sensors connected to the braking system of the vehicle, which in turn slows down the speed of the vehicle or completely stops it from moving altogether. The proposed collision avoidance system makes use of ultrasonic sensors and a unique localization algorithm to deliver a largely user-based vehicular protection from collision.

关键词： wireless sensor network collision avoidance localization predictive algorithm

来源：评论

学校读者我要写书评

暂无评论

predictive algorithm FOR SUSTAINABLE SYSTEM ARCHITECTURE

PREDICTIVE ALGORITHM FOR SUSTAINABLE SYSTEM ARCHITECTURE

引用

26th IEEE Annual Canadian Conference on Electrical and Computer Engineering (CCECE)

作者： Grebenyuk, Vladimir Ascent Syst Technol Sun Peaks BC Canada

ISBN: (纸本)9781479900336;9781479900312

Every system, however big or small, is always a part of a bigger system and in turn consists of a number of smaller subsystems. This is true for both technical and natural systems, including biological, ecological and social. The discipline of Systems Architecture teaches that to be successful, any complex technical system has to take into account this system hierarchy as well as interdependency and interaction between the components of the system on each level. The principles of Systems Architecture: modularity, cohesion, scalability, evolvability and others are universal, but there is hardly a more important and more challenging area where they need to be applied than the area of sustainability and sustainable development. In recent years, issues of pollution, global warming, rising energy costs, natural and human-induced disasters, and other environmental and economic problems are becoming of more concern than ever. Problems such as this can be solved only with a system approach to sustainable development. An interesting consequence of applying the principles of Systems Architecture to sustainable development is the conclusion that the system itself must be sustainable. This paper presents an approach to sustainable system architecture, using a predictive algorithm based on a specific example of a building-integrated energy control system.

关键词： sustainable system architecture predictive algorithm integrated energy control system high-performance building

来源：评论

学校读者我要写书评

暂无评论

Whisper of Website Object Preparation: A Systematic Literature Review on Web Prefetching and Precaching 6

Whisper of Website Object Preparation: A Systematic Literatu...

引用

6th International Conference on Informatics, Multimedia, Cyber and Information System, ICIMCIS 2024

作者： Hamzah Santosa, Paulus Insap Putra, Guntur Dharma Universitas Gadjah Mada Department of Electrical and Information Engineering Yogyakarta Indonesia

ISBN: (纸本)9798331533243

The present systematic literature review explores different methods of web prefetching and precaching to improve website performance, which examines relevant studies related to the decrease of overall latency and improvement of user experience through client-side enhancements. The present paper assesses conventional techniques in web prefetching, such as ML-based algorithms, AI-driven caching, and hybrid algorithms combined with data mining technology (DMT). The assessment focuses on key metrics such as load time, hit rate, and user satisfaction. The results indicate that AI, ML, and DMT, are effective techniques for prefetching and precaching, which indicates a notable enhancement in the overall performance. In addition, the survey highlights how these high-performing methods can be useful for both publicly accessible websites and internal websites accessed through an intranet, aiming to uphold user satisfaction and website performance. Future studies are anticipated to investigate how they can be used in private website supporting internal business processes to improve the quality of business operations. © 2024 IEEE.

关键词： predictive algorithm Systematic Literature Review User Satisfaction Web Caching Web Prefetching

来源：评论

学校读者我要写书评

暂无评论

A neonatal sepsis prediction algorithm using electronic medical record data from Mbarara Regional Referral Hospital

引用

Intelligence-Based Medicine 2025年 11卷 100198-100198页

作者： Ezeobi Dennis, Peace Musiimenta, Angella Wasswa, William Kyoyagala, Stella Mbarara University of Science and Technology (MUST) Uganda Mbarara Regional Referral Hospital (MRRH) Uganda

Introduction: Neonatal sepsis is a global challenge that contributes significantly to neonatal morbidity and mortality. The current diagnostic methods depend on conventional culture methods, a procedure that takes time and leads to delays in making timely treatment decisions. This study proposes a machine learning algorithm utilizing electronic medical record (EMR) data from Mbarara Regional Referral Hospital (MRRH) to enhance early detection and treatment of neonatal sepsis. Methods: We performed a retrospective study on a dataset of neonates hospitalized for at least 48 h in the Neonatal Intensive Care Unit (NICU) at MRRH between October 2015 to September 2019 who received at least one sepsis evaluation. 482 records of neonates met the inclusion criteria and the dataset comprises 38 neonatal sepsis screening parameters. The study considered two outcomes for sepsis evaluations: culture-positive if a blood culture was positive, and clinically positive if cultures were negative but antibiotics were administered for at least 120 h. We implemented k-fold cross-validation with k set to 10 to guarantee robust training and testing of the models. Seven machine learning models were trained to classify inputs as sepsis positive or negative, and their performance was compared with physician diagnoses. Results: The results of this study show that the proposed algorithm, combining maternal risk factors, neonatal clinical signs, and laboratory tests (the algorithm demonstrated a sensitivity and specificity of at least 95 %) outperformed the physician diagnosis (Sensitivity = 89 %, Specificity = 11 %). SVM model with radial basis function, polynomial kernels, and DT model (with the highest AUROC values of 98 %) performed better than the other models. Conclusions: The study shows that the combination of maternal risk factors, neonatal clinical signs, and laboratory tests can help improve the prediction of neonatal sepsis. Further research is warranted to assess the potential perfo

关键词： Early onset sepsis (EOS) Electronic medical record (EMR) Neonatal sepsis prediction predictive algorithm Screening parameters Supervised machine learning

来源：评论

学校读者我要写书评

暂无评论

Non – Invasive, smartphone image-based screening for sickle cell disease at the point-of-need

引用

Heliyon 2025年第2期11卷 e41830页

作者： Vital, Eudorah F. LiCalzi, Meredith Haak Mannino, Robert G. McGann, Patrick T. Lam, Wilbur A. Wallace H. Coulter Department of Biomedical Engineering Georgia Institute of Technology and Emory University Atlanta 30332 GA United States Sanguina Inc Atlanta 30092 GA United States Lifespan Comprehensive Sickle Cell Center Providence Rhode Island 02903 United States Alpert Medical School of Brown University Department of Pediatrics Providence Rhode Island 02903 United States Department of Pediatrics Division of Pediatric Hematology/Oncology Aflac Cancer Center and Blood Disorders Service of Children's Healthcare of Atlanta Emory University School of Medicine Atlanta 30322 GA United States Winship Cancer Institute of Emory University Atlanta 30322 GA United States Parker H. Petit Institute of Bioengineering and Biosciences Georgia Institute of Technology Atlanta 30332 GA United States Institute for Matter and Systems Georgia Institute of Technology Atlanta 30332 GA United States

Leveraging the increasing accessibility of smartphones in healthcare settings, we developed a smartphone app aimed at enhancing sickle cell disease (SCD) screening, particularly in resource-limited settings. Our application provides accurate and non-invasive SCD screening with instant results at the point-of-need. The app operates by analyzing patient fingernail images via a smartphone image to gauge anemia severity and by using targeted inquiries to identify SCD-related symptoms. These inputs collectively generate an SCD IMage and Patient profile-based Likelihood Estimation (SIMPLE) score, which estimates disease probability. The accuracy of the score depends on two inputs: the patient's anemia status and their health survey responses. We tested the app on 485 pediatric patients at Children's Healthcare of Atlanta (CHOA), achieving an overall sensitivity of 74 % and specificity of 76 % in screening for SCD among children aged 6 months to 21 years. Notably, the app demonstrated enhanced performance in the target demographic, with 100 % sensitivity and 75 % specificity for screening SCD in children aged 6 months to 5 years. This cost-effective and scalable app efficiently pinpoints and stratifies individuals, particularly those who missed early screening, for formal screening programs. © 2025 The Author(s)

关键词： Non-invasive Point-of-need predictive algorithm Screening Sickle cell disease Smartphone app

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：