检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Bonazzola, Rodrigo Ferrante, Enzo Ravikumar, Nishant Xia, Yan Keavney, Bernard Plein, Sven Syeda-Mahmood, Tanveer Frangi, Alejandro F. School of Computing School of Medicine University of Leeds Leeds United Kingdom Leeds Institute of Cardiovascular and Metabolic Medicine School of Medicine University of Leeds Leeds United Kingdom FICH-UNL / CONICET Santa Fe Argentina IBM Almaden Research Center San Jose United States University Hospital Gasthuisberg. Cardiovascular Sciences and Electrical Engineering Departments KU Leuven Leuven Belgium Division of Cardiovascular Sciences Faculty of Biology Medicine and Health University of Manchester Manchester United Kingdom Manchester University NHS Foundation Trust Manchester Academic Health Science Centre Manchester United Kingdom

Recent genome-wide association studies (GWAS) have been successful in identifying associations between genetic variants and simple cardiac parameters derived from cardiac magnetic resonance (CMR) images. However, the emergence of big databases including genetic data linked to CMR, facilitates investigation of more nuanced patterns of shape variability. Here, we propose a new framework for gene discovery entitled Unsupervised Phenotype Ensembles (UPE). UPE builds a redundant yet highly expressive representation by pooling a set of phenotypes learned in an unsupervised manner, using deep learning models trained with different hyperparameters. These phenotypes are then analyzed via (GWAS), retaining only highly confident and stable associations across the ensemble. We apply our approach to the UK Biobank database to extract left-ventricular (LV) geometric features from image-derived three-dimensional meshes. We demonstrate that our approach greatly improves the discoverability of genes influencing LV shape, identifying 11 loci with study-wide significance and 8 with suggestive significance. We argue that our approach would enable more extensive discovery of gene associations with image-derived phenotypes for other organs or image modalities. © 2023, CC BY-NC-SA.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

Comparative laboratory cost analysis of various activated carbon activation process

引用

IOP Conference Series: Materials science and engineering 2021年第1期1195卷

作者： J Y Lai L H Ngu Faculty of Engineering Computing and Science Swinburne University of Technology Jalan Simpang Tiga 93350 Kuching Sarawak Malaysia

Activated carbon (AC) is an established adsorbent for organic pollutants reduction, metal removal, and liquid and gas adsorption. Cost analysis corresponds to determining the best approach for AC production depending on activation techniques with different degrees of activation is still minimal in literature. A cost estimation of AC production in laboratory scale using different conventional activation and post-activation surface modification process is performed in this study. This study attempts to develop a cost-friendly selection of activation process from laboratory scale prices. Chemicals and utility costs were acquired from vendor quotes (i.e., Sigma-Aldrich and Fisher Scientific) and Sarawak industrial electricity tariffs based on 100 g production. Oil palm-based ACs produced from five different activation or surface modification methods were compared to ascertain the least expensive production approach in terms of estimated production cost. Of the five methods investigated, method that quoted the least expensive production cost is chemical activation using potassium hydroxide (KOH) with minimum estimated cost of $7.30 whereas the most expensive production cost involves surface modification by polyethyleneimine (PEI) impregnation with cost of $873.00. Therefore, the estimated production cost for KOH activation is the minimum at $0.073 g−1 while the maximum is $8.73 g−1 for PEI impregnation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Code comparison for fast flavor instability simulations

引用

Physical Review D 2022年第4期106卷 043011-043011页

作者： Sherwood Richers Huaiyu Duan Meng-Ru Wu Soumya Bhattacharyya Masamichi Zaizen Manu George Chun-Yu Lin Zewei Xiong Department of Physics University of California Berkeley California 94720 USA Department of Physics and Astronomy University of New Mexico Albuquerque New Mexico 87131 USA Institute of Physics Academia Sinica Taipei 11529 Taiwan Institute of Astronomy and Astrophysics Academia Sinica Taipei 10617 Taiwan Tata Institute of Fundamental Research Homi Bhabha Road Mumbai 400005 India Faculty of Science and Engineering Waseda University Tokyo 169-8555 Japan Department of Astronomy Graduate School of Science University of Tokyo Tokyo 113-0033 Japan National Center for High-Performance Computing National Applied Research Laboratories Hsinchu Science Park Hsinchu City 30076 Taiwan GSI Helmholtzzentrum für Schwerionenforschung Planckstraße 1 64291 Darmstadt Germany

The fast flavor instability (FFI) is expected to be ubiquitous in core-collapse supernovae and neutron star mergers. It rapidly shuffles neutrino flavor in a way that could impact the explosion mechanism, neutrino signals, mass outflows, and nucleosynthesis. The variety of initial conditions and simulation methods employed in simulations of the FFI prevent an apples-to-apples comparison of the results. We simulate a standardized test problem using five independent codes and verify that they are all faithfully simulating the underlying quantum kinetic equations under the assumptions of axial symmetry and homogeneity in two directions. We quantify the amount of numerical error in each method and demonstrate that each method is superior in at least one metric of this error. We make the results publicly available to serve as a benchmark.

关键词： Extrasolar neutrino astronomy Neutrino oscillations Novae & supernovae Nuclear astrophysics Particle astrophysics Plasma instabilities Accretion disk & black-hole plasma Neutrinos Quantum plasmas Particle-in-cell methods Plasma kinetic theory

来源：评论

学校读者我要写书评

暂无评论

Automatic Classification of Low-Angle Fuze-Quick Craters Using Deep Learning 6th

Automatic Classification of Low-Angle Fuze-Quick Craters Usi...

引用

6th International Conference on Machine Learning, Optimization, and Data science, LOD 2020

作者： Aji, Sani Kumam, Poom Siricharoen, Punnarai Bukar, Ali Maina 126 Pracha-Uthit Road Bang Mod Thrung Khru Bangkok10140 Thailand 126 Pracha-Uthit Road Bang Mod Thrung Khru Bangkok10140 Thailand Department of Mathematics Faculty of Science Gombe State University Gombe Nigeria 126 Pracha-Uthit Road Bang Mod Thrung Khru Bangkok10140 Thailand Centre for Visual Computing Faculty of Engineering and Informatics University of Bradford Bradford West Yorkshire United Kingdom

ISBN: (纸本)9783030645793

Crater Analysis is a technique used for precautionary and investigative purpose, especially in confirming suspected locations of hostile fire and detecting the presence of enemy ammunition. Specifically, investigators have manually examined terrain disturbances due to blast craters, which are evidently caused by artillery fire. Although this manual process has been helpful in the identification of possible origins of fire, it is tedious and prone to errors. With the recent advancements in the fields of computer vision and machine learning (ML), this work investigates the automation of low-angle fuze-quick craters (LaFCs) classification using satellite imagery of the Ukranian border obtained from google earth. Due to limited volume of available satellite images (of LaFCs), we hereby propose the use of off-the-shelf ImageNet pretrained models (Resnet50, Resnet101 and ResNet152) for the automatic classification of the LaFCs. Thus, learned filters from these deep neural networks are used to extract features from the satellite images. These features are then fed into support vector machine (SVM) for classification. Promising results are obtained from our experiments, showing that it is possible to use ML to identify LaFCs. To the best of our knowledge, this is the first time classification of these type of craters has been investigated. © 2020, Springer Nature Switzerland AG.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Secure and Privacy-Preserving Automated Machine Learning Operations into End-to-End Integrated IoT-Edge-Artificial Intelligence-Blockchain Monitoring System for Diabetes Mellitus Prediction

arXiv

引用

arXiv 2022年

作者： Hennebelle, Alain Ismail, Leila Materwala, Huned Kaabi, Juma Al Ranjan, Priya Janardhanan, Rajiv School of Computing and Information Systems The University of Melbourne Australia Research Laboratory Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University United Arab Emirates National Water and Energy Center United Arab Emirates University United Arab Emirates College of Health Sciences Department of Internal Medicine United Arab Emirates University United Arab Emirates Mediclinic Al Ain Abu Dhabi United Arab Emirates Bhubaneswar Institute of Technology India Faculty of Medical & Health Sciences SRM Institute of Science & Technology India

Diabetes Mellitus, one of the leading causes of death worldwide, has no cure to date and can lead to severe health complications, such as retinopathy, limb amputation, cardiovascular diseases, and neuronal disease, if left untreated. Consequently, it becomes crucial to take precautionary measures to avoid/predict the occurrence of diabetes. Machine learning approaches have been proposed and evaluated in the literature for diabetes prediction. This paper proposes an IoT-edge-Artificial Intelligence (AI)-blockchain system for diabetes prediction based on risk factors. The proposed system is underpinned by the blockchain to obtain a cohesive view of the risk factors data from patients across different hospitals and to ensure security and privacy of the user’s data. Furthermore, we provide a comparative analysis of different medical sensors, devices, and methods to measure and collect the risk factors values in the system. Numerical experiments and comparative analysis were carried out between our proposed system, using the most accurate random forest (RF) model, and the two most used state-of-the-art machine learning approaches, Logistic Regression (LR) and Support Vector Machine (SVM), using three real-life diabetes datasets. The results show that the proposed system using RF predicts diabetes with 4.57% more accuracy on average compared to LR and SVM, with 2.87 times more execution time. Data balancing without feature selection does not show significant improvement. The performance is improved by 1.14% and 0.02% after feature selection for PIMA Indian and Sylhet datasets respectively, while it reduces by 0.89% for MIMIC III. © 2022, CC BY.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Studying physics during the COVID-19 pandemic: Student assessments of learning achievement, perceived effectiveness of online recitations, and online laboratories

引用

Physical Review Physics Education Research 2021年第1期17卷 010117-010117页

作者： P. Klein L. Ivanjek M. N. Dahlkemper K. Jeličić M.-A. Geyer S. Küchemann A. Susac Faculty of Physics Physics Education Research University of Göttingen Friedrich-Hund-Platz 37077 Göttingen Germany Faculty of Physics Physics Education Research Technische Universität Dresden Haeckelstraße 3 01069 Dresden Germany Department of Physics Faculty of Science University of Zagreb Bijenička cesta 32 10000 Zagreb Croatia Department of Physics Physics Education Research Group Technische Universität Kaiserslautern Erwin-Schrödinger-Str. 46 67663 Kaiserslautern Germany Faculty of Electrical Engineering and Computing University of Zagreb Unska 3 10000 Zagreb Croatia

The COVID-19 pandemic has significantly affected the education system worldwide, which was forced to respond with a sudden shift to distance learning. While successful distance teaching requires careful thinking, planning, and the development of technological and human resources, there was no time for preparation in the current situation. Various physics courses, including lectures, tutorials, and laboratory courses, had to be transferred to online formats, resulting in a variety of simultaneous, asynchronous, and mixed activities. To investigate how physics students perceived the sudden shift to online learning, we developed a questionnaire and gathered data from N=578 physics students from five universities in Germany, Austria, and Croatia. In this article, we report how the problem-solving sessions (recitations) and laboratories were adapted, how students judge the different formats of the courses, and how useful and effective they perceived them. The results are correlated with the students’ self-efficacy ratings and other behavioral measures (such as self-regulated learning skills). This study is descriptive in nature, and a survey study design was implemented to examine the relationships among the variables. We found that good communication abilities (r=0.48, p<0.001) and self-organization skills (r=0.63, p<0.001) are positively correlated with perceived learning achievement. Furthermore, the previous duration of studies had a significant impact on several self-reported achievement measures, resulting in consistently lower scores of students in their first academic year compared with students who were further along academically. We draw conclusions and suggest implications for future online classes on the instructor and faculty level. Suggestions include (i) focusing on first-year courses with on-campus teaching when facing limited lecture hall capacities, (ii) offering special courses for promoting self-regulated learning skills, (iii) emphasizing the positiv

关键词： Assessment Learning environment Technology

来源：评论

学校读者我要写书评

暂无评论

Edge Based Obstacle Detection Model for Outdoor Type Obstacles

Edge Based Obstacle Detection Model for Outdoor Type Obstacl...

引用

International UNIMAS STEM engineering Conference (EnCon)

作者： Khairul Azim Bin Za’aba Lau Bee Theng Faculty of Engineering Computing and Science Swinburne University of Technology Kuching Sarawak

ISBN: (纸本)9781728134956

Obstacle detection and avoidance technologies are mainly categorised into non-vision and vision-based technologies. Most of the developed technologies are not ready for public use as they may require additional stage such as production and distribution. Obstacle detection model built for a mobile device focusing on detecting outdoor obstacles is introduced in this paper. The model uses a monocular camera to obtain real-time frames then applies Canny Edge detection algorithm to obtain the surrounding information. This surrounding edge information is used to compare between frames to determine whether a path contains obstacles. In addition, the proximity light sensor, accelerometer, and gyroscope are used to ensure the model's adaptability to various environments. The model is tested in various out door scenarios. The average floor-based outdoor obstacle detection accuracy obtained by this model is 81.7%. This concludes that the model can be a supplementary assistance to the white cane, which is used by people with low vision.

关键词： Image edge detection Mobile handsets Lighting Cameras Adaptation models Real-time systems Sensitivity

来源：评论

学校读者我要写书评

暂无评论

Security-aware data offloading and resource allocation for MEC systems: A deep reinforcement learning

TechRxiv

引用

TechRxiv 2021年

作者： Elgendy, Ibrahim A. Muthanna, Ammar Hammoudeh, Mohammad Shaiba, Hadil Ahmed Unal, Devrim Khayyat, Mashael The School of Computer Science and Technology Harbin Institute of Technology China Department of Computer Science Faculty of Computers and Information Menoufia University Egypt The St. Petersburg State University of Telecommunication St. Petersburg193232 Russia Moscow117198 Russia Department of Computing Manchester Metropolitan University ManchesterM15 6BH United Kingdom The College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University Riyadh Saudi Arabia Qatar University College of Engineering KINDI Center for Computing Research Doha Qatar The University of Jeddah College of Computer Science and Engineering Department of Information Systems and Technology Jeddah Saudi Arabia

The Internet of Things (IoT) is permeating our daily lives where it can provide data collection tools and important measurement to inform our decisions. In addition, they are continually generating massive amounts of data and exchanging essential messages over networks for further analysis. The promise of low communication latency, security enhancement and the efficient utilization of bandwidth leads to the new shift change from Mobile Cloud computing (MCC) towards Mobile Edge computing (MEC). In this study, we propose an advanced deep reinforcement resource allocation and security-aware data offloading model that considers the computation and radio resources of industrial IoT devices to guarantee that shared resources between multiple users are utilized in an efficient way. This model is formulated as an optimization problem with the goal of decreasing the consumption of energy and computation delay. This type of problem is NP-hard, due to the curse-of-dimensionality challenge, thus, a deep learning optimization approach is presented to find an optimal solution. Additionally, an AES-based cryptographic approach is implemented as a security layer to satisfy data security requirements. Experimental evaluation results show that the proposed model can reduce offloading overhead by up to 13.2% and 64.7% in comparison with full offloading and local execution while scaling well for large-scale devices. © 2021, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Establishment of Dynamic Evolving Neural-Fuzzy Inference System Model for Natural Air Temperature Prediction

引用

Complexity 2022年第0期2022卷

作者： Bhagat, Suraj Kumar Tiyasha, Tiyasha Al-Khafaji, Zainab Laux, Patrick Ewees, Ahmed A. Rashid, Tarik A. Salih, Sinan Yonaba, Roland Beyaztas, Ufuk Yaseen, Zaher Mundher Faculty of Civil Engineering Ton Duc Thang University Ho Chi Minh Viet Nam Building and Construction Techniques Engineering Department AL-Mustaqbal University College Hillah51001 Iraq Karlsruhe Institute of Technology Campus Alpin Garmisch-Partenkirchen Germany Department of Information Systems College of Computing and Information Technology University of Bisha Bisha61922 Saudi Arabia Department of Computer Damietta University Damietta Egypt Computer Science and Engineering Department University of Kurdistan Hewler KRI Erbil Iraq Dijlah University College Al-Dora Baghdad Iraq 01 P. O. Box 594 01 Ouagadougou Burkina Faso Department of Statistics Marmara University Istanbul Turkey Civil and Environmental Engineering Department King Fahd University of Petroleum and Minerals Dhahran31261 Saudi Arabia

Air temperature (AT) prediction can play a significant role in studies related to climate change, radiation and heat flux estimation, and weather forecasting. This study applied and compared the outcomes of three advanced fuzzy inference models, i.e., dynamic evolving neural-fuzzy inference system (DENFIS), hybrid neural-fuzzy inference system (HyFIS), and adaptive neurofuzzy inference system (ANFIS) for AT prediction. Modelling was done for three stations in North Dakota (ND), USA, i.e., Robinson, Ada, and Hillsboro. The results reveal that FIS type models are well suited when handling highly variable data, such as AT, which shows a high positive correlation with average daily dew point (DP), total solar radiation (TSR), and negative correlation with average wind speed (WS). At the Robinson station, DENFIS performed the best with a coefficient of determination (R2) of 0.96 and a modified index of agreement (md) of 0.92, followed by ANFIS with R2 of 0.94 and md of 0.89, and HyFIS with R2 of 0.90 and md of 0.84. A similar result was observed for the other two stations, i.e., Ada and Hillsboro stations where DENFIS performed the best with R2: 0.953/0.960, md: 0.903/0.912, then ANFIS with R2: 0.943/0.942, md: 0.888/0.890, and HyFIS with R2: 0.908/0.905, md: 0.845/0.821, respectively. It can be concluded that all three models are capable of predicting AT with high efficiency by only using DP, TSR, and WS as input variables. This makes the application of these models more reliable for a meteorological variable with the need for the least number of input variables. The study can be valuable for the areas where the climatological and seasonal variations are studied and will allow providing excellent prediction results with the least error margin and without a huge expenditure. © 2022 Suraj Kumar Bhagat et al.

关键词： Weather forecasting

来源：评论

学校读者我要写书评

暂无评论

UFA-FastSLAM: The New Hybrid of Firefly Algorithm and FastSLAM Algorithm

UFA-FastSLAM: The New Hybrid of Firefly Algorithm and FastSL...

引用

International Conference on Green engineering Technology and Applied computing 2019, IConGETech2 019 and International Conference on Applied computing 2019, ICAC 2019

作者： Musridho, R.J. Hasan, H. Haron, H. Department of Computer Science School of Computing Faculty of Engineering Universiti Teknologi Malaysia Johor Johor Bahru Malaysia Applied Industrial Analytics Research Group Johor Johor Bahru Malaysia

Simultaneous Localization and Mapping (SLAM) is a challenging and fundamental issue in autonomous mobile robots. One of two main solutions of SLAM problem is FastSLAM. In terms of accuracy, FastSLAM is known to degenerate over time. This work hybridized Firefly Algorithm (FA) and FastSLAM to optimize FastSLAM. But in FA, there is a ranking process which ranked the fireflies based on their light intensity. It caused the output needed by particles in FastSLAM came in different sequence. Thus, the FA in this work is modified before it is applied to FastSLAM, the ranking process is deleted. The result has shown that the modified FA, that is unranked Firefly Algorithm (uFA) has been successfully hybridized with FastSLAM. © 2019 Published under licence by IOP Publishing Ltd.

关键词： Bioluminescence

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：