检索结果-内蒙古大学图书馆

IEEE International Conference on Robotics and Biomimetics

作者： De-Xing Huang Xiao-Hu Zhou Xiao-Liang Xie Shi-Qi Liu Zhen-Qiu Feng Jian-Long Hao Zeng-Guang Hou Ning Ma Long Yan The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The School of Information Shanxi University of Finance and Economics Taiyuan China The CAS Center for Excellence in Brain Science and Intelligence Technology Beijing China The Joint Laboratory of Intelligence Science and Technology Institute of Systems Engineering Macau University of Science and Technology Taipa Macau The Department of Interventional Neuroradiology Beijing Tiantan Hospital Capital Medical University Beijing China

ISBN: (纸本)9781665481106

2D/3D medical image registration of pre-operative volumes and intra-operative images plays an important role in neurological interventions. However, vast space of transformation parameters makes this task incredibly challenging. In this paper, a novel two-stage framework for 2D/3D registration is proposed. It consists of two basic modules: CNN regression for preliminarily estimating transformation parameters, and centroid alignment for further reducing estimation errors to get refined images. Experimental results on two patients show the proposed framework can achieve superior performances to baseline methods with an inference rate of 22 FPS, satisfying real-time requirements (6~12 FPS) in clinical practice. Extensive ablation studies prove the effectiveness of centroid alignment in significantly improving registration accuracies. These promising results indicate the framework has the potential to be integrated into navigation frameworks for neurological interventions, facilitating treatments of physicians.

关键词： Image registration Estimation error Three-dimensional displays Navigation Biomimetics Medical services Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Teaching Basic Concepts in Machine Learning to Engineering Students: A Hands-on Approach

Teaching Basic Concepts in Machine Learning to Engineering S...

引用

2024 ASEE Annual Conference and Exposition

作者： Obada, David O. Abolade, Simeon A. Akinpelu, Shittu B. Oyedeji, Ayodeji N. Okafor, Emmanuel Odili, Cynthia U. Ogenyi, Vanessa F. Ategbe, Victor S. Eberemu, Adrian O. Anafi, Fatai O. Ahmed, Abdulkarim S. Bako, Raymond B. Akande, Akinlolu Department of Mechanical Engineering Ahmadu Bello University Zaria810222 Nigeria Mathematical Modelling and Intelligent Systems for Health and Environment Research Group School of Science Atlantic Technological University SligoF91 YW50 Ireland Modelling and Computation for Health and Society Atlantic Technological University SligoF91 YW50 Ireland SDAIA-KFUPM Joint Research Center for Artificial Intelligence King Fahd University of Petroleum and Minerals Dhahran31261 Saudi Arabia Department of Water Resources and Environmental Engineering Ahmadu Bello University Zaria810222 Nigeria Department of Polymer and Textile Engineering Ahmadu Bello University Zaria810222 Nigeria Department of Civil Engineering Ahmadu Bello University Zaria810222 Nigeria Department of Chemical Engineering Ahmadu Bello University Zaria810222 Nigeria Department of Educational Foundations and Curriculum Ahmadu Bello University Zaria810222 Nigeria Africa Centre of Excellence on New Pedagogies in Engineering Education Ahmadu Bello University Zaria810222 Nigeria Multifunctional Materials Laboratory Shell Office Complex Department of Mechanical Engineering Ahmadu Bello University Zaria810222 Nigeria

According to a recent survey conducted by the Corporate Member Council of the American Society of Engineering Education (ASEE), there exists a notable disparity in the skill sets of engineering graduates about Artificial Intelligence (AI). To address this disparity from the African context, the Africa Centre of excellence on New Pedagogies in Engineering Education organized a machine learning (ML) workshop for engineering students from different disciplines. Seventy-three (73) students enrolled for the workshop and the modules covered during this workshop were: Introduction to ML Models, ML Frameworks, Additive Explanations in ML, Performance Metrics, and Introduction to Ensemble Learning Techniques. The hands-on session involved the use of categorical boosting (CatBoost), an ensemble learning technique, to predict the bulk modulus, a mechanical property, of 199 ABX3 perovskite materials which was used as a problem set. The input features influencing the CatBoost model decisions were subsequently established. Correlation analysis on the input feature space removed features with high collinearity. The SHapley Additive exPlanations (SHAP) was used to analyze the decision-making rationale of the model. Evaluation of the model performance based on the coefficient of determination R2 value (0.94) revealed that the model demonstrates good performance in predicting the bulk modulus of the perovskite materials used during the practical sections. The survey results after the teaching and practical sessions indicate that the learning modules are an effective introduction for novice engineering students in this domain and raise awareness of the importance of this important sub-section of AI. © American Society for Engineering Education, 2024.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Evolution and Neural Representation of Mammalian Cooperative Behavior

SSRN

引用

SSRN 2021年

作者： Jiang, Mengping Wang, Miaoyaoxin Shi, Qianqian Wei, Lei Lin, Yongqin Wu, Dingcheng Liu, Boyi Nie, Xiupeng Qiao, Hong Xu, Lin Yang, Tianming Wang, Zuoren Institute of Neuroscience State Key Laboratory of Neuroscience CAS Center for Excellence in Brain Science &Intelligence Technology Chinese Academy of Sciences Shanghai200031 China Key Laboratory of Animal Models and Human Disease Mechanisms and Laboratory of Learning and Memory Kunming Institute of Zoology Chinese Academy of Sciences KunmingYunnan650223 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Cooperation is common in nature and has been pivotal to the development of human society. However, the details of how and why cooperation evolved remain poorly understood. Cross-species investigation of cooperation may help to elucidate the evolution of cooperative strategies. Thus, we designed a novel cooperative behavioral paradigm and quantitatively examined the cooperative abilities and strategies of mice, rats, and tree shrews. We found that social communication played a key role in the establishment of new cooperation, and that increased cooperative ability and a more efficient cooperative strategy emerged as a function of the evolutionary hierarchy of the tested species. We also found neural representations of distinct aspects of cooperation in the brains of rats through in vivo electrophysiological recording. Cooperation-preferential signals were identified in addition to material reward-preferential signals, each of which may represent internal drives for cooperation. © 2021, The Authors. All rights reserved.

关键词： Rats

来源：评论

学校读者我要写书评

暂无评论

Validity of Born-Markov master equations for single- and two-qubit systems

引用

Physical Review B 2021年第21期103卷 214308-214308页

作者： Vasilii Vadimov Jani Tuorila Tuure Orell Jürgen Stockburger Tapio Ala-Nissila Joachim Ankerhold Mikko Möttönen QCD Labs QTF Centre of Excellence Department of Applied Physics Aalto University P.O. Box 13500 FI-00076 Aalto Espoo Finland MSP Group QTF Centre of Excellence Department of Applied Physics Aalto University P.O. Box 11000 FI-00076 Aalto Espoo Finland Institute for Physics of Microstructures Russian Academy of Sciences 603950 Nizhny Novgorod GSP-105 Russia IQM Keilaranta 19 FI-02150 Espoo Finland Nano and Molecular Materials Research Unit University of Oulu P.O. Box 3000 FI-90014 Finland Institute for Complex Quantum Systems and IQST University of Ulm 89069 Ulm Germany Interdisciplinary Centre for Mathematical Modelling Department of Mathematical Sciences Loughborough University Loughborough Leicestershire LE11 3TU United Kingdom VTT Technical Research Centre of Finland Ltd. QTF Center of Excellence P.O. Box 1000 FI-02044 VTT Finland

The urgent need for reliable simulation tools to match the extreme accuracy needed to control tailored quantum devices highlights the importance of understanding open quantum systems and their modeling. To this end, we compare here the commonly used Redfield and Lindblad master equations against numerically exact results in the case of one and two resonant qubits transversely coupled at a single point to a Drude-cut ohmic bath. All the relevant parameters are varied over a broad range, which allows us to give detailed predictions about the validity and physically meaningful applicability of the weak-coupling approaches. We characterize the accuracy of the approximate approaches by comparing the maximum difference of their system evolution superoperators with numerically exact results. After optimizing the parameters of the approximate models to minimize the difference, we also explore if and to what extent the weak-coupling equations can be applied at least as phenomenological models. Optimization may lead to an accurate reproduction of experimental data, but yet our results are important to estimate the reliability of the extracted parameter values such as the bath temperature. Our findings set general guidelines for the range of validity of the usual Born-Markov master equations and indicate that they fail to accurately describe the physics in a surprisingly broad range of parameters, in particular, at low temperatures. Since quantum-technological devices operate there, their accurate modeling calls for a careful choice of methods.

关键词： Open quantum systems Open quantum systems & decoherence Markovian processes Non-Markovian processes

来源：评论

学校读者我要写书评

暂无评论

Weakly Aligned Feature Fusion for Multi-modal Object Detection

arXiv

引用

arXiv 2022年

作者： Zhang, Lu Liu, Zhiyong Zhu, Xiangyu Song, Zhan Yang, Xu Lei, Zhen Qiao, Hong The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100086 China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai200031 China The Center for Biometrics and Security Research National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China The Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong The Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen518055 China

To achieve accurate and robust object detection in the real-world scenario, various forms of images are incorporated, such as color, thermal, depth, etc. However, multi-modal data often suffer from the position shift problem, i.e. the image pair is not strictly aligned, making one object has different positions in different modalities. For the deep learning method, this problem makes it difficult to fuse multi-modal features and puzzles the CNN training. In this paper, we propose a general multi-modal detector named Aligned Region CNN (AR-CNN) to tackle the position shift problem. Firstly, a region feature alignment module with adjacent similarity constraint is designed to consistently predict the position shift between two modalities and adaptively align the cross-modal region features. Secondly, we propose a novel RoI jitter strategy to improve the robustness to unexpected shift patterns. Thirdly, we present a new multi-modal feature fusion method, which selects the more reliable feature and suppresses the less useful one via feature re-weighting. Additionally, by locating bounding boxes in both modalities and building their relationships, we provide novel multi-modal labelling named KAIST-Paired. Extensive experiments on 2D and 3D object detection, RGB-T and RGB-D datasets demonstrate the effectiveness and robustness of our method. Copyright © 2022, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Ab-initio calculations and ensemble learning prediction of the structural properties of solution combustion processed strontium-doped hydroxyapatite

引用

Case Studies in Chemical and Environmental Engineering 2024年 10卷

作者： Obada, David O. Okafor, Emmanuel Salami, Kazeem A. Oyedeji, Ayodeji N. Abolade, Simeon A. Akinpelu, Shittu B. Kuburi, Laminu S. Dauda, Muhammad Akande, Akinlolu Mathematical Modelling and Intelligent Systems for Health and Environment Research Group School of Science Atlantic Technological University Ash Lane Ballytivnan Sligo F91 YW50 Ireland SDAIA-KFUPM Joint Research Center for Artificial Intelligence King Fahd University of Petroleum and Minerals 31261 Saudi Arabia Multifunctional Materials Laboratory Shell Office Complex Department of Mechanical Engineering Ahmadu Bello University Nigeria Modelling & Computation for Health And Society (MOCHAS) Atlantic Technological University Ash Lane Ballytivnan Sligo F91 YW50 Ireland Africa Centre of Excellence on New Pedagogies in Engineering Education Ahmadu Bello University Zaria Nigeria

In this study, density functional theory (DFT) based ab initio calculations were performed to complement the experimentally obtained structural properties of strontium doped hydroxyapatite (Sr-HAp) prepared through the solution combustion synthesis (SCS) route. The structural properties of the as-prepared strontium ion doped powders were collected on an X-ray diffractometer and the structure-property relation of the datasets was explored using machine learning-assisted ensemble learning techniques such as CatBoost, LightGBM, Random Forest, and XGBoost. The results show that the Random Forest technique surpassed all other ensemble learning techniques, indicating better generalization capacity. The simulated XRD signatures agree well with the experiments. © 2024 The Authors

关键词： DFT Hydroxyapatite Machine learning Solution combustion synthesis X-ray diffractometer

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to “A pathway-based network analysis of hypertension-related genes” [Physica A 444 (2016) 928–939]

引用

Physica A: Statistical Mechanics and its Applications 2016年 447卷 569-570页

作者： Huan Wang Jing-Bo Hu Chuan-Yun Xu De-Hai Zhang Qian Yan Ming Xu Ke-Fei Cao Xu-Sheng Zhang School of Computer Science and Technology Baoji University of Arts and Sciences Baoji Shaanxi 721016 China Center for Nonlinear Complex Systems Department of Physics School of Physics Science and Technology Yunnan University Kunming Yunnan 650091 China School of Electronic and Electrical Engineering Baoji University of Arts and Sciences Baoji Shaanxi 721016 China School of Software Yunnan University Kunming Yunnan 650091 China School of Physics and Electronic Science Chuxiong Normal University Chuxiong Yunnan 675000 China School of Mathematical Sciences Kaili University Kaili Guizhou 556011 China Modelling and Economics Unit Centre for Infectious Disease Surveillance and Control Public Health England 61 Colindale Avenue London NW9 5EQ UK Medical Research Council Centre for Outbreak Analysis and Modelling Department of Infectious Disease Epidemiology School of Public Health Imperial College London Norfolk Place London W2 1PG UK

来源：评论

学校读者我要写书评

暂无评论

Nearest-Better Network for Fitness Landscape Analysis of Continuous Optimization Problems

引用

IEEE Transactions on Evolutionary Computation 2024年

作者： Diao, Yiya Li, Changhe Zeng, Sanyou Yang, Shengxiang Coello, Carlos A. Coello China University of Geosciences School of Automation Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan China Anhui University of Sciences and Technology School of Artificial Intelligence Hefei China China University of Geosciences School of Mechanical Engineering and Electronic Information Wuhan China De Montfort University School of Computer Science and Informatics LeicesterLE1 9BH United Kingdom Department of Computer Science CINVESTAV-IPN 07360 Mexico Tecnologico de Monterrey Faculty of Excellence The School of Engineering and Sciences N.L. Monterrey Mexico

Fitness landscape analysis (FLA) is quite important in evolutionary computation. In this paper, we propose a novel FLA method, the nearest-better network (NBN), which uses the nearest-better relationship to simplify the original fitness landscape of continuous optimization problems. We introduce an efficient algorithm to calculate NBN for continuous problems. We also propose four numerical measurements and a 3D visualization method based on NBN. Experiments show that compared to the other main FLA methods, the four numerical measurements proposed here can effectively measure the four intended features: neutrality, ruggedness, modality, and basin of attraction, respectively, and common features of the fitness landscape can be maintained in 3D NBN visualization, regardless of the scale of the problem. NBN also provides a view of how algorithms search in high-dimensional problems with the help of the 3D NBN visualization. © 1997-2012 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Validity of Born–Markov master equations for single and two-qubit systems

arXiv

引用

arXiv 2020年

作者： Vadimov, Vasilii Tuorila, Jani Orell, Tuure Stockburger, Jürgen Ala-Nissila, Tapio Ankerhold, Joachim Möttönen, Mikko QCD Labs QTF Centre of Excellence Department of Applied Physics Aalto University P.O. Box 13500 Aalto EspooFI-00076 Finland MSP Group QTF Centre of Excellence Department of Applied Physics Aalto University P.O. Box 11000 Aalto EspooFI-00076 Finland Institute for Physics of Microstructures Russian Academy of Sciences Nizhny Novgorod603950 Russia IQM Keilaranta 19 EspooFI-02150 Finland Nano and Molecular Materials Research Unit University of Oulu P.O. Box 3000 FI-90014 Finland Institute for Complex Quantum Systems IQST University of Ulm Ulm89069 Germany Interdisciplinary Centre for Mathematical Modelling Department of Mathematical Sciences Loughborough University LoughboroughLeicestershireLE11 3TU United Kingdom VTT Technical Research Centre of Finland Ltd. QTF Center of Excellence P.O. Box 1000 VTTFI-02044 Finland

The urgent need for reliable simulation tools to match the extreme accuracy needed to control tailored quantum devices highlights the importance of understanding open quantum systems and their modeling. To this end, we compare here the commonly used Redfield and Lindblad master equations against numerically exact results in the case of one and two resonant qubits transversely coupled at a single point to a Drude-cut ohmic bath. All the relevant parameters are varied over a broad range which allows us to give detailed predictions about the validity and physically meaningful applicability of the weak-coupling approaches. We characterize the accuracy of the approximate approaches by comparing the maximum difference of their system evolution superoperators with numerically exact results. After optimizing the parameters of the approximate models to minimize the difference, we also explore if and to what extent the weak-coupling equations can be applied at least as phenomenological models. Optimization may lead to an accurate reproduction of experimental data, but yet our results are important to estimate the reliability of the extracted parameter values such as the bath temperature. Our findings set general guidelines for the range of validity of the usual Born–Markov master equations and indicate that they fail to accurately describe the physics in surprisingly broad range of parameters, in particular at low temperatures. Since quantum-technological devices operate there their accurate modeling calls for a careful choice of methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Cell proliferation

来源：评论

学校读者我要写书评

暂无评论

Burdens of type 2 diabetes and cardiovascular disease attributable to sugar-sweetened beverages in 184 countries (06 Jan, 10.1038/s41591-024-03345-4, 2025)

引用

NATURE MEDICINE 2025年第2期31卷 696-696页

作者： Lara-Castor, Laura O'Hearn, Meghan Cudhea, Frederick Miller, Victoria Shi, Peilin Zhang, Jianyi Sharib, Julia R. Cash, Sean B. Barquera, Simon Micha, Renata Mozaffarian, Dariush Food Is Medicine Institute Friedman School of Nutrition Science and Policy Tufts University Boston MA USA Institute of Health Metrics and Evaluation University of Washington Seattle WA USA Food Systems for the Future Institute Chicago IL USA Department of Medicine McMaster University Hamilton Ontario Canada Population Health Research Institute Hamilton Ontario Canada University of Thessaly Volos Greece Tufts University School of Medicine Boston MA USA Department of Medicine Tufts Medical Center Boston MA USA Center for Surgery and Public Health Brigham and Women’s Hospital Boston MA USA Friedman School of Nutrition Science and Policy Tufts University Boston MA USA Research Center on Nutrition and Health National Institute of Public Health Cuernavaca Mexico National Institute of Public Health (INSP) Cuernavaca Mexico Academy of Athens Athens Greece Acibadem University Istanbul Turkey Addis Ababa University Addis Ababa Ethiopia Aga Khan Foundation Geneva Switzerland All India Institute of Medical Sciences New Delhi India American University of Beirut Beirut Lebanon Amrita School of Dentistry Eranakulum India Andalas University Padang Indonesia Arab Center for Nutrition Manama Bahrain Ardabil University of Medical Sciences Ardabil Iran Bacha Khan University Charsadda Pakistan Biodiversity International Nairobi Kenya Brighton and Sussex Medical School Brighton UK Center for Studies of Sensory Impairment Aging and Metabolism (CeSSIAM) Guatemala City Guatemala Centre For Media Studies New Delhi India Centro de Atencion Nutricional Antimano (CANIA) Miami FL USA Centro de Estudios sobre Nutrición Infantil (CESNI) Buenos Aires Argentina Child Growth and Development Research Center Isfahan University of Medical Sciences Isfahan Iran College of Applied Sciences Department of Food Science and Applied Nutrition Addis Ababa Science and Technology University Addis Ababa Ethiopia Consultative Group on International Agricultural Research (CGIAR) M

The consumption of sugar-sweetened beverages (SSBs) is associated with type 2 diabetes (T2D) and cardiovascular diseases (CVD). However, an updated and comprehensive assessment of the global burden attributable to SSBs remains scarce. Here we estimated SSB-attributable T2D and CVD burdens across 184 countries in 1990 and 2020 globally, regionally and nationally, incorporating data from the Global Dietary Database, jointly stratified by age, sex, educational attainment and urbanicity. In 2020, 2.2 million (95% uncertainty interval 2.0–2.3) new T2D cases and 1.2 million (95% uncertainty interval 1.1–1.3) new CVD cases were attributable to SSBs worldwide, representing 9.8% and 3.1%, respectively, of all incident cases. Globally, proportional SSB-attributable burdens were higher among men versus women, younger versus older adults, higher- versus lower-educated adults, and adults in urban versus rural areas. By world region, the highest SSB-attributable percentage burdens were in Latin America and the Caribbean (T2D: 24.4%; CVD: 11.3%) and sub-Saharan Africa (T2D: 21.5%; CVD: 10.5%). From 1990 to 2020, the largest proportional increases in SSB-attributable incident T2D and CVD cases were in sub-Saharan Africa (+8.8% and +4.4%, respectively). Our study highlights the countries and subpopulations most affected by cardiometabolic disease associated with SSB consumption, assisting in shaping effective policies and interventions to reduce these burdens globally.

关键词：

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：