检索结果-内蒙古大学图书馆

COVID-19 Infection Percentage Estimation from Computed Tomography Scans: Results and Insights from the International Per-COVID-19 Challenge

引用

Sensors 2024年第5期24卷 1557页

作者： Bougourzi, Fares Distante, Cosimo Dornaika, Fadi Taleb-Ahmed, Abdelmalik Hadid, Abdenour Chaudhary, Suman Yang, Wanting Qiang, Yan Anwar, Talha Breaban, Mihaela Elena Hsu, Chih-Chung Tai, Shen-Chieh Chen, Shao-Ning Tricarico, Davide Chaudhry, Hafiza Ayesha Hoor Fiandrotti, Attilio Grangetto, Marco Spatafora, Maria Ausilia Napoli Ortis, Alessandro Battiato, Sebastiano Institute of Applied Sciences and Intelligent Systems National Research Council of Italy Lecce73100 Italy Laboratoire LISSI University Paris-Est Creteil Paris Vitry sur Seine94400 France Department of Computer Science and Artificial Intelligence University of the Basque Country UPV/EHU Manuel Lardizabal 1 San Sebastian20018 Spain IKERBASQUE Basque Foundation for Science Bilbao48011 Spain UMR 8520 Universite Polytechnique Hauts-de-France Université de Lille CNRS Valenciennes59313 France Sorbonne Center for Artificial Intelligence Sorbonne University of Abu Dhabi P.O. Box 38044 Abu Dhabi United Arab Emirates College of Computer Science and Technology Taiyuan University of Technology Taiyuan030024 China School of Computing National University of Computer and Emerging Sciences Islamabad44000 Pakistan Faculty of Computer Science Alexandru Ioan Cuza University Iasi700506 Romania Institute of Data Science National Cheng Kung University No. 1 University Rd. East Dist. Tainan City701 Taiwan Dipartimento di Informatica Universita degli Studi di Torino Corso Svizzera 185 Torino10149 Italy Department of Mathematics and Computer Science University of Catania Catania95125 Italy

COVID-19 analysis from medical imaging is an important task that has been intensively studied in the last years due to the spread of the COVID-19 pandemic. In fact, medical imaging has often been used as a complementary or main tool to recognize the infected persons. On the other hand, medical imaging has the ability to provide more details about COVID-19 infection, including its severity and spread, which makes it possible to evaluate the infection and follow-up the patient’s state. CT scans are the most informative tool for COVID-19 infection, where the evaluation of COVID-19 infection is usually performed through infection segmentation. However, segmentation is a tedious task that requires much effort and time from expert radiologists. To deal with this limitation, an efficient framework for estimating COVID-19 infection as a regression task is proposed. The goal of the Per-COVID-19 challenge is to test the efficiency of modern deep learning methods on COVID-19 infection percentage estimation (CIPE) from CT scans. Participants had to develop an efficient deep learning approach that can learn from noisy data. In addition, participants had to cope with many challenges, including those related to COVID-19 infection complexity and crossdataset scenarios. This paper provides an overview of the COVID-19 infection percentage estimation challenge (Per-COVID-19) held at MIA-COVID-2022. Details of the competition data, challenges, and evaluation metrics are presented. The best performing approaches and their results are described and discussed. © 2024 by the authors.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

AI exposure predicts unemployment risk

arXiv

引用

arXiv 2023年

作者： Frank, Morgan R. Ahn, Yong-Yeol Moro, Esteban Department of Informatics and Networked Systems University of Pittsburgh PittsburghPA15216 United States Digital Economy Lab Institute for Human-Centered Artificial Intelligence Stanford University StanfordCA94305 United States Media Laboratory Massachusetts Institute of Technology CambridgeMA02139 United States Connection Science Massachusetts Institute of Technology CambridgeMA United States Center for Complex Networks and Systems Research Luddy School of Informatics Computing and Engineering Indiana University BloomingtonIN United States Indiana University Network Science Institute Indiana University BloomingtonIN United States Department of Mathematics & GISC Universidad Carlos III de Madrid Leganes28911 Spain Institute for Data Systems and Society Massachusetts Institute of Technology CambridgeMA United States

Is artificial intelligence (AI) disrupting jobs and creating unemployment? Despite many attempts to quantify occupations' exposure to AI, inconsistent validation obfuscates the relative benefits of each approach. A lack of disaggregated labor outcome data, including unemployment data, further exacerbates the issue. Here, we assess which models of AI exposure predict job separations and unemployment risk using new occupation-level unemployment data by occupation from each US state's unemployment insurance office spanning 2010 through 2020. Although these AI exposure scores have been used by governments and industry, we find that individual AI exposure models are not predictive of unemployment rates, unemployment risk, or job separation rates. However, an ensemble of those models exhibits substantial predictive power suggesting that competing models may capture different aspects of AI exposure that collectively account for AI's variable impact across occupations, regions, and time. Our results also call for dynamic, context-aware, and validated methods for assessing AI exposure. Interactive visualizations for this study are available at https://***/~mrfrank/uiRiskDemo/. © 2023, CC BY.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Nonlinear model based guidance with deep learning based target trajectory prediction against aerial agile attack patterns

arXiv

引用

arXiv 2021年

作者： Satir, Abdullah Sadik Demir, Umut Sever, Gulay Goktas Ure, N. Kemal Department of Aeronautics and Astronautics Istanbul Technical University Istanbul Turkey Department of Aeronautics and Astronautics Istanbul Technical University Istanbul Turkey Department of Defense Technologies Istanbul Technical University Istanbul Turkey ITU Artificial Intelligence and Data Science Application and Research Center Department of Aeronautics and Astronautics Istanbul Technical University Istanbul Turkey

In this work, we propose a novel missile guidance algorithm that combines deep learning based trajectory prediction with nonlinear model predictive control. Although missile guidance and threat interception is a well-studied problem, existing algorithms' performance degrade significantly when the target is pulling high acceleration attack maneuvers while rapidly changing its direction. We argue that since most threats execute similar attack maneuvers, these nonlinear trajectory patterns can be processed with modern machine learning methods to build high accuracy trajectory prediction algorithms. We train a long short-term memory network (LSTM) based on a class of simulated structured agile attack patterns, then combine this predictor with quadratic programming based nonlinear model predictive control (NMPC). Our method, named nonlinear model based predictive control with target acceleration predictions (NMPC-TAP), significantly outperforms compared approaches in terms of miss distance, for the scenarios where the target/threat is executing agile *** Codes 93-10 Copyright © 2021, The Authors. All rights reserved.

关键词： Quadratic programming

来源：评论

学校读者我要写书评

暂无评论

Estimations of cross-sections for photonuclear reaction on calcium isotopes by artificial neural networks

arXiv

引用

arXiv 2020年

作者： Akkoyun, S. Kaya, H. Department of Physics Sivas Cumhuriyet University Sivas58140 Turkey Articial Intelligence Systems and Data Science Application and Research Center Sivas Cumhuriyet University Sivas58140 Turkey

The nuclear reaction induced by photon is one of the important tools in the investigation of atomic nuclei. In the reaction, a target material is bombarded by photons with high-energies in the range of gamma-ray energy range. In the bombarding process, the photons can statistically be absorbed by a nucleus in the target material. Then the excited nucleus can decay by emitting proton, neutron, alpha and light particles or photons. By performing photonuclear reaction on the target, it can be easily investigated low-lying excited states of the nuclei. In the present work, (?, n) photonuclear reaction cross-sections on different calcium isotopes have been estimated by using artificial neural network method. The method is a mathematical model that mimics the brain functionality of the creatures. The correlation coefficient values of the method for both training and test phases being 0.99 indicate that the method is very suitable for this purpose. Copyright © 2020, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Turing patterns in simplicial complexes

引用

Physical Review E 2023年第1期107卷 014216-014216页

作者： Shupeng Gao Lili Chang Matjaž Perc Zhen Wang School of Mechanical Engineering Northwestern Polytechnical University Xi'an 710072 China School of Artificial Intelligence Optics and Electronics (iOPEN) Northwestern Polytechnical University Xi'an 710072 China Complex Systems Research Center Shanxi University Taiyuan 030006 China Shanxi Key Laboratory of Mathematical Techniques and Big Data Analysis for Disease Control and Prevention Taiyuan 030006 China Faculty of Natural Sciences and Mathematics University of Maribor Koroška cesta 160 2000 Maribor Slovenia Department of Medical Research China Medical University Hospital China Medical University Taichung 404332 Taiwan Alma Mater Europaea Slovenska ulica 17 2000 Maribor Slovenia Complexity Science Hub Vienna Josefstädterstraße 39 1080 Vienna Austria Department of Physics Kyung Hee University 26 Kyungheedae-ro Dongdaemun-gu Seoul Republic of Korea

The spontaneous emergence of patterns in nature, such as stripes and spots, can be mathematically explained by reaction-diffusion systems. These patterns are often referred as Turing patterns to honor the seminal work of Alan Turing in the early 1950s. With the coming of age of network science, and with its related departure from diffusive nearest-neighbor interactions to long-range links between nodes, additional layers of complexity behind pattern formation have been discovered, including irregular spatiotemporal patterns. Here we investigate the formation of Turing patterns in simplicial complexes, where links no longer connect just pairs of nodes but can connect three or more nodes. Such higher-order interactions are emerging as a new frontier in network science, in particular describing group interaction in various sociological and biological systems, so understanding pattern formation under these conditions is of the utmost importance. We show that a canonical reaction-diffusion system defined over a simplicial complex yields Turing patterns that fundamentally differ from patterns observed in traditional networks. For example, we observe a stable distribution of Turing patterns where the fraction of nodes with reactant concentrations above the equilibrium point is exponentially related to the average degree of 2-simplexes, and we uncover parameter regions where Turing patterns will emerge only under higher-order interactions, but not under pairwise interactions.

关键词： Dynamics of networks Pattern formation Patterns in complex systems

来源：评论

学校读者我要写书评

暂无评论

Determination of photonuclear reaction cross-sections on stable p-shell nuclei by using deep neural networks

arXiv

引用

arXiv 2020年

作者： Akkoyun, Serkan Kaya, Hüseyin Seker, Abdulkadir Yesilyurt, Saliha Department of Physics Faculty of Science Sivas Cumhuriyet University Sivas Turkey Department of Computer Engineering Sivas Cumhuriyet University Faculty of Engineering Sivas Turkey Artificial Intelligence Systems and Data Science Application and Research Center Sivas Cumhuriyet University Sivas58140 Turkey

The photonuclear reactions which is induced by high-energetic photon are one of the important type of reactions in the nuclear structure studies. In this reaction, a target material is bombarded by photons with the energies in the range of gamma-ray energy scale and the photons can statistically be absorbed by a nucleus in the target material. In order to get rid of the excess energies of the excited target nuclei, it can first emit protons, neutrons, alphas and light particles according to the separation energy thresholds. After this emitting process, generally an unstable nucleus can be formed. By the investigation of this products forming after photonuclear reactions, nuclear structure information can be obtained. In the present work, (γ, n) photonuclear reaction cross-sections on stable p-shell nuclei have been estimated by using neural network method. The main purpose of this study is to find neural network structures that give the best estimations on the cross-sections and to compare them with each other and available literature data. According to the results, the method is convenient for this task. Copyright © 2020, The Authors. All rights reserved.

关键词： Photons

来源：评论

学校读者我要写书评

暂无评论

Smart online charging algorithm for electric vehicles via customized actor-critic learning

arXiv

引用

arXiv 2021年

作者： Cao, Yongsheng Wang, Hao Li, Demin Zhang, Guanglin College of Information Science and Technology Donghua University Engineering Research Center of Digitized Textile and Apparel Technology Ministry of Education Shanghai201620 China The Department of Data Science and Artificial Intelligence Faculty of Information Technology Monash University MelbourneVIC3800 Australia The Stanford Sustainable Systems Lab Stanford University StanfordCA94305 United States

With the advances in the Internet of Things technology, electric vehicles (EVs) have become easier to schedule in daily life, which is reshaping the electric load curve. It is important to design efficient charging algorithms to mitigate the negative impact of EV charging on the power grid. This paper investigates an EV charging scheduling problem to reduce the charging cost while shaving the peak charging load, under unknown future information about EVs, such as arrival time, departure time, and charging demand. First, we formulate an EV charging problem to minimize the electricity bill of the EV fleet and study the EV charging problem in an online setting without knowing future information. We develop an actor-critic learning-based smart charging algorithm (SCA) to schedule the EV charging against the uncertainties in EV charging behaviors. The SCA learns an optimal EV charging strategy with continuous charging actions instead of discrete approximation of charging. We further develop a more computationally efficient customized actor-critic learning charging algorithm (CALC) by reducing the state dimension and thus improving the computational efficiency. Finally, simulation results show that our proposed SCA can reduce EVs' expected cost by 24.03%, 21.49%, 13.80%, compared with the Eagerly Charging Algorithm, Online Charging Algorithm, RL-based Adaptive Energy Management Algorithm, respectively. CALC is more computationally efficient, and its performance is close to that of SCA with only a gap of 5.56% in the cost. Copyright © 2021, The Authors. All rights reserved.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Estimations of first 2+energy states of even-even: Nuclei by using artificial neural networks

arXiv

引用

arXiv 2020年

作者： Akkoyun, Serkan Kaya, Hüseyin Torun, Yunis Department of Physics Sivas Cumhuriyet University Sivas58140 Turkey Artificial Intelligence Systems and Data Science Application and Research Center Sivas Cumhuriyet University Sivas58140 Turkey Department of Electric and Electronic Engineering Sivas Cumhuriyet University Sivas58140 Turkey

The first excited 2+energy states of nuclei give much substantial information related to the nuclear structure. Including these levels, all excited states of nuclei are shown regularities in spin, parity and energy. In the even-even nuclei, the first excited state is generally 2+and the energy values of them increase as the closed shells are approached. The excited levels in nuclei can be investigated by using theoretical nuclear models such as nuclear shell model. In the present study for the first time, we have used artificial neural networks for the determination of the energies of the first 2+states in the even-even nuclei in the nuclidic chart as a function of Z and N numbers. According to the results, the method is convenient for this goal and one can confidently use the method for the prediction of the first 2+state energy values whose experimental values do not exist in the literature. Copyright © 2020, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Improvement Studies of an Effective Interaction for N=Z sd-shell Nuclei by Neural Networks

arXiv

引用

arXiv 2020年

作者： Akkoyun, Serkan Laouet, Nadjet Benrachi, Fatima Department of Physics Faculty of Sciences Sivas Cumhuriyet University Sivas Turkey Artificial Intelligence Systems and Data Science Application and Research Center Sivas Cumhuriyet University Sivas Turkey LPMPS Laboratory Frres Mentouri Constantine-1 University Constantine25017 Algeria

The nuclear shell model is one of the successful models in theoretical understanding of nuclear structure. If a convenient effective interaction can be found between nucleons, various observables such as energies of nuclear states are accurately predicted by this model. The basic requirements for the shell model calculations are a set of single particle energies and two-body interaction matrix elements (TBME) which construct the residual interaction between nucleons. This latter could be parameterized in different ways. In this study, we have used a different approach to improve existing USD type Hamiltonians for the shell model calculations of N = Z nuclei in the A=16-40 region. After obtaining the SDNN new effective interaction, shell model calculations have been performed for all N = Z nuclei in sd shell. In which, 16O doubly magic nucleus has been assumed as an inert core and active particles are distributed in the d5/2, s1/2 and d3/2 single particle orbits. The rms deviations from experimental energy values are lower for the newly generated effective interaction than those obtained using the original one for the studied nuclei. Copyright © 2020, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Volumetric measurement of manually drawn segmentations in cone beam computed tomography images of newly formed bone after sinus floor augmentation with bovine-derived bone substitutes

引用

Journal of Stomatology, Oral and Maxillofacial Surgery 2025年 102221页

作者： Grün, Pascal Hatamikia, Sepideh Lakes, Tim Schneider, Benedikt Pfaffeneder-Mantai, Florian Fitzek, Sebastian von See, Constantin Turhani, Dritan Center for Oral and Maxillofacial Surgery Department of Dentistry Faculty of Medicine and Dentistry Danube Private University Steiner Landstraße 124 3500 Krems an der Donau Austria Clinical Application of Artificial Intelligence in Dentistry (CAAID) Group Department of Dentistry Faculty of Medicine and Dentistry Danube Private University Steiner Landstraße 124 Krems an der Donau 3500 Austria Research Center for Clinical AI-Research in Omics and Medical Data Science (CAROM) Department of Medicine Faculty of Medicine and Dentistry Danube Private University Steiner Landstraße 124 Krems an der Donau 3500 Austria Austrian Center for Medical Innovation and Technology Viktor Kaplan-Straße 2/1 Wiener Neustadt 2700 Austria Division for Chemistry and Physics of Materials Department of Medicine Faculty of Medicine and Dentistry Danube Private University Steiner Landstraße 124 Krems an der Donau 3500 Austria Health Services Research Group Medical Images Analysis and Artificial Intelligence (MIAAI) Department of Medicine Faculty of Medicine and Dentistry Danube Private University Steiner Landstraße 124 Krems an der Donau 3500 Austria Center for Digital Technologies in Dentistry and CAD/CAM Department of Dentistry Faculty of Medicine and Dentistry Danube Private University Krems an der Donau Steiner Landstraße 124 3500 Austria

Introduction: Precise volumetric measurement of newly formed bone after maxillary sinus floor augmentation (MSFA) can help clinicians in planning for dental implants. This study aimed to introduce a novel modular framework to facilitate volumetric calculations based on manually drawn segmentations of user-defined areas of interest on cone-beam computed tomography (CBCT) images Material & Methods: Two interconnected networks for manual segmentation of a defined volume of interest and dental implant volume calculation, respectively, were used in parallel. The volume data of dental implant manufacturers were used for reference. The efficacy of this framework was demonstrated through practical applications for collecting CBCT data from patients after MSFA with the same quantity of two different bovine-derived bone substitutes: xenohybrid composite bone (Group I, n = 10) and hydroxyapatite (Group II, n = 10). The study was approved by the central Ethical Review Board of the federal state of Lower Austria (approval number: GS4-EK-4/451–2021). The volumes were measured immediately (T1) and 6 months (T2) after MSFA and before insertion of the dental implant. All measurements were analyzed for inter- and intravariability. P-values of >0.05 were obtained from the t-test analysis Results: The manual delineation of Group II (n = 10) was easier than that of Group I (n = 10) due to the visual contrast of the CBCT scan. The mean volume was 861.65 ± 290.02 mm³ at T1 and 875.9 ± 288.96 mm³ at T2. This shows a moderate dispersion around the mean value, which indicates variability of the analyzed data Discussion: The proposed network may be useful for the development of computer-based diagnostic systems for assessing the success of MSFA with bone replacement materials. The volumetric stability achieved with the two bone replacement materials were comparable. © 2025 The Author(s)

关键词： Augmentation Cone-beam computed tomography Hydroxyapatite

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：