检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Seidman, Jacob H. Kissas, Georgios Perdikaris, Paris Pappas, George J. Graduate Program in Applied Mathematics and Computational Science University of Pennsylvania United States Department of Mechanical Engineering and Applied Mechanics University of Pennsylvania United States Department of Electrical and Systems Engineering University of Pennsylvania United States

Supervised learning in function spaces is an emerging area of machine learning research with applications to the prediction of complex physical systems such as fluid flows, solid mechanics, and climate modeling. By directly learning maps (operators) between infinite dimensional function spaces, these models are able to learn discretization invariant representations of target functions. A common approach is to represent such target functions as linear combinations of basis elements learned from data. However, there are simple scenarios where, even though the target functions form a low dimensional submanifold, a very large number of basis elements is needed for an accurate linear representation. Here we present NOMAD, a novel operator learning framework with a nonlinear decoder map capable of learning finite dimensional representations of nonlinear submanifolds in function spaces. We show this method is able to accurately learn low dimensional representations of solution manifolds to partial differential equations while outperforming linear models of larger size. Additionally, we compare to state-of-the-art operator learning methods on a complex fluid dynamics benchmark and achieve competitive performance with a significantly smaller model size and training cost. © 2022, CC BY-NC-SA.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Systemic evaluation of spatio-temporal variations in travel time reliability due to a toll road over time

引用

Urban, Planning and Transport Research 2021年第1期9卷 36-59页

作者： Mathew, Sonu Pulugurtha, Srinivas S. Graduate of Infrastructure & Environmental Systems (INES) Program The University of North Carolina at Charlotte Charlotte NC United States Professor of Civil & Environmental Engineering Department Director of Infrastructure Design Environment & Sustainability (IDEAS) Center The University of North Carolina at Charlotte Charlotte NC United States

This paper evaluates the effectiveness of toll roads in reducing congestion and improving travel time reliability on streets within its vicinity, over time. The data, from the year 2013 to 2017, for the Triangle Expressway in the city of Raleigh, North Carolina was used in the systemic evaluation process. The spatial and temporal variations in the travel time distributions on the toll road, parallel route, and near-vicinity cross-streets (in a 2-mile buffer) were evaluated. The average travel time (ATT), the 95th percentile travel time (or planning time, PT), the buffer time (BT), and the buffer time index (BTI) were computed for each link by the day-of-the-week and the time-of-the-day. Though there was an improvement in travel time after the speed limit change in the year 2014, the travel time reliability got reduced on the Triangle Expressway. Over time, there was a gradual improvement in BT and BTI. The parallel route reliability decreased significantly over time, whereas the travel time reliability of cross-streets showed a consistent trend. The stabilization of travel time distributions and the reliability measures in the year 2017 indicate that further reduction in performance measures may not be expected in the next few years on the near-vicinity links. © 2020 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： buffer time buffer time index road spatial temporal Toll travel time

来源：评论

学校读者我要写书评

暂无评论

A study on estimation of traveling direction for pedestrian dead reckoning by using inertial sensors 9

A study on estimation of traveling direction for pedestrian ...

引用

9th IEEE Global Conference on Consumer Electronics, GCCE 2020

作者： Matsumoto, Takumi Fujii, Masahiro Utsunomiya University Graduate Program in Information Electrical and Electronics Systems Engineering 7-1-2 Yoto Utsunomiya Tochigi Japan

ISBN: (纸本)9781728198026

In this paper, we propose a new method to estimate the traveling direction for pedestrian by applying IMU (Inertial Measurement Unit) and PCA (Principal Component Analysis) to sensor information from a smartwatch. Because a result of PCA do not have orientation information, an estimate of the traveling direction includes an indeterminacy problem. We show that the proposed method can solve this problem and provide high accuracy in the traveling direction estimation by walking experiments. © 2020 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Measuring Sustainability of PV in Energy Transition: Mass, Energy, and Circularity

Measuring Sustainability of PV in Energy Transition: Mass, E...

引用

IEEE Conference Photovoltaic Specialists (PVSC)

作者： Heather M. Mirletz Silvana Ovaitt Macarena Mendez Ribo Seetharaman Sridhar Teresa M. Barnes National Renewable Energy Lab Golden CO United States Advanced Energy Systems Graduate Program Colorado School of Mines Golden CO United States Ira A. Fulton Schools of Engineering Arizona State University Tempe AZ United States

Transition to a carbon-free energy system is crucial for global decarbonization and underpins Circular Economy (CE) goals. Photovoltaic (PV) technology is required for Energy Transition, but manufacturing and circular pathways can be material, energy, and carbon-intensive. Therefore, we need a prioritization of sustainability strategies for PV evolution and lifecycle management in the context of Energy Transition. This study employs a suite of quantitative metrics to compare different proposed sustainability strategies for PV modules on their ability to achieve Energy Transition. Proposals for sustainable PV range from high-yield, high-efficiency paradigms, to short-lived and fully recyclable, to long-lasting, indestructible modules. We leverage a global decarbonization deployment schedule through 2100 with the open-source PV in Circular Economy (PV ICE) tool to quantify the impacts of different evolving module design scenarios covering the range of proposed sustainability strategies. First, modules are compared on effective capacity and required replacements to meet and maintain decarbonization capacity targets through 2100. We demonstrate the effects of lifetime, degradation, and reliability on effective capacity. Next, we quantify and compare virgin material demands and lifecycle wastes, examining the impacts of lifetime and recycling rates. Finally, and critically for renewable energy technologies, we quantify the energy demands required to achieve the decarbonization capacity targets and calculate energy balance metrics (net energy, energy return on investment). These results are then summarized into a metric matrix, demonstrating tradeoffs and the importance of longevity. Our suite of mass and energy metrics provides stakeholders and decision-makers with quantitative data on circular economy choices for PV in the energy transition, enabling informed evaluation of tradeoffs of different PV module designs and CE pathways.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mean-variance and Safety-first Portfolio Selection Strategy for High-volume/Highvalue Traded Stocks in Philippine Stock Exchange (PSE)

Mean-variance and Safety-first Portfolio Selection Strategy ...

引用

IEEE International Conference on Industrial engineering and engineering Management

作者： T. C. De Guzman M. N. Young Y. T. Prasetyo S. F. Persada R. Nadilfatin School of Graduate Studies Mapua University Manila Philippines School of Industrial Engineering and Engineering Management Mapua University Manila Philippines Department of Industrial Engineering and Management Yuan Ze University Taoyuan City Taiwan International Bachelor Program in Engineering Yuan Ze University Taoyuan City Taiwan Entrepreneurship Business Creation Business School Binus University West Jakarta Indonesia Department of Information Systems Institut Teknologi Sepuluh Nopember Surabaya Indonesia

ISBN: (数字)9798350386097

ISBN: (纸本)9798350386103

This research evaluates the effectiveness of Mean-Variance (MV) and Safety-First (SF) portfolio selection strategies for high-volume/high-value traded stocks on the Philippine Stock Exchange (PSE). Analyzing data from 288 stocks over 7,670 trading days (30 years), we estimated stock returns, assigned probability weights, and conducted optimization models. The results show that the Mean-Variance (MV0.5) strategy achieved the best balance between risk and return, boasting the highest mean and cumulative returns with moderate volatility. The Safety-First (SF) strategy, however, yielded negative cumulative returns, indicating potential issues. The Market strategy had the lowest mean return but also the least risk, appealing to risk-averse investors. The Portfolio Mean-Variance (PMV) strategy provided a reasonable balance of returns and risk. Statistical analysis revealed that only the MV0.5 strategy outperformed market returns. These findings offer crucial insights into risk assessment and portfolio management for investors evaluating these strategies against market performance.

关键词： Statistical analysis Optimization models Oils Safety Risk management Stock markets Portfolios Standards Monitoring Investment

来源：评论

学校读者我要写书评

暂无评论

Utilizing Graph Neural Networks for Breast Cancer Prognosis Prediction with High-dimensional Genomic Data

Utilizing Graph Neural Networks for Breast Cancer Prognosis ...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Tzu-Chen Huang Te-Cheng Hsu Yi-Hsien Hsieh Che-Lin Graduate Institute of Communication Engineering National Taiwan University (NTU) Taipei Taiwan Institute of Communications Engineering National Tsing-Hua University Hsinchu Taiwan Department of Electrical Engineering NTU Taipei Taiwan Master’s Program in Smart Medicine and Health Informatics NTU Taipei Taiwan Center for Computational and Systems Biology NTU Taipei Taiwan

An accurate prediction of breast cancer is essential to help physicians make appropriate treatment recommendations to reduce the chance of excessive treatment, avoiding unnecessary anxiety for patients. Cancer prognosis is highly related to patients’ genomic features, which are high-dimensional in nature. In this study, we utilize a systems biology feature selector for dimension reduction to select 20 prognostic biomarkers that are considered closely related to breast cancer prognosis from the high dimensional RNA Sequencing (RNA-Seq) data. Furthermore, we establish a graph neural network (GNN) and a multi-layer perception (MLP) graph-level readout method to better extract the underlying gene interactions from the corresponding gene interaction network (GIN). With the help of GINs, the model performs the best among all baseline models, especially in the area under the precision-recall curve (AUPRC) by as large as 23%. The results demonstrate that our approach using GNNs can successfully extract high-dimensional and complicated interactions within genomic data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Time Stacking Decision Tree for Oscillatory Failure Case Detection in a Flight Control System

引用

IFAC-PapersOnLine 2023年第2期56卷 354-359页

作者： Giberto Reynoso-Meza Victor Henrique Alves Ribeiro Marcelo Feliciano Filho Bianca Zavadisk de Abreu Industrial and Systems Engineering Graduate Program (PPGEPS) Pontifícia Universidade Católica do Paraná (PUCPR) Rua Imaculada Conceição 1155 Zip code 80215-901 Curitiba PR Brazil Silex Curitiba PR Brazil Colégio Estadual da Polícia Militar Curitiba PR Brazil

Flight control systems are an essential part of aircraft, consisting of all elements between the pilot and the movable parts, such as actuators, controllers, and sensors, to control the aircraft's attitude, trajectory and speed. In this context, oscillatory failure cases are problems that can occur in any part of the flight control system, causing undesired oscillatory behavior that affects the aircraft's structural load. On the one hand, correctly detecting such failures enables weight saving to improve aircraft performance in different aspects; on the other hand, such detection enables reconfiguring the control law to keep the aircraft in its path. This work describes a data-driven oscillatory fault detection model and the control law reconfiguration for a fight control system for the Aerospace Industrial Benchmark. Preliminary results indicate that the developed system can accurately detect faults in several scenarios and properly reconfigure the control loop.

关键词： Aerospace Guidance, navigation and control of vehicles Fault detection and diagnosis Machine learning

来源：评论

学校读者我要写书评

暂无评论

Drone Application Model for Image Acquisition of Plantation Areas and Oil Palm Trees Counting 7

Drone Application Model for Image Acquisition of Plantation ...

引用

7th International Conference on Information Management and Technology, ICIMTech 2022

作者： Sastrohartono, Hermantoro Suryotomo, Andiko Putro Saifullah, Shoffan Suparyanto, Teddy Perbangsa, Anzaludin Samsinga Pardamean, Bens Instiper Yogyakarta Faculty of Agricultural Technology Department of Agricultural Engineering Yogyakarta55281 Indonesia Universitas Pembangunan Nasional Veteran Yogyakarta Department of Informatics Yogyakarta55283 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia School of Information Systems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia BINUS Graduate Program - Master of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (数字)9781665450904

ISBN: (纸本)9781665450904

The area of oil palm plantations in Indonesia increased by 7% from 14 million ha in 2017 to 15 million ha in 2021. The vast land requires the support of effective and efficient management techniques to maintain sustainable productivity. The high-performance computing technologies, Internet of Things (IoT), Big Data, Artificial Intelligence, spatial modeling, and drones are the answers to these needs. This study aims to design an application that can obtain plantation image data and analyze the calculation of the number of oil palm trees. The image of oil palm plantations is obtained from processing photo data from drones through a mosaic and composite process. This study also employed Scrum and UML as a system model development method. The image of the oil palm plantation area is used to build a tree counting model using the Viola-Jones algorithm. The oil palm tree count information generated by this system can then be used by management for fertilizing, harvesting, and monitoring the condition of oil palm trees. © 2022 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

LE-DTA: Local Extrema Convolution for Drug Target Affinity Prediction

LE-DTA: Local Extrema Convolution for Drug Target Affinity P...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Tanoj Langore Te-Cheng Hsu Yi-Hsien Hsieh Che Lin Graduate Institute of Communication Engineering National Taiwan University (NTU) Taipei Taiwan Institute of Communications Engineering National Tsing Hua University Hsinchu Taiwan Department of Electrical Engineering NTU Taipei Taiwan Center for Computational and Systems Biology and Center for Biotechnology NTU Taipei Taiwan Smart Medicine and Health Informatics Program NTU Taipei Taiwan

One of the essential parts of drug discovery and design is the prediction of drug-target affinity (DTA). Researchers have proposed computational approaches for predicting DTA to circumvent the more expensive in vivo and in vitro tests. More recent approaches employed deep network architectures to obtain the features from the drug molecules and protein sequences. The drug compounds are represented as graphs and the target protein as a sequence to extract this information. In this work, we develop a new graph-based prediction model, termed LE-DTA, that utilizes local extrema convolutions for effective feature extraction. It focuses on the local and global extrema of graphs for node embedding. We investigated the performances of both the proposed models on three different benchmark datasets. Our proposed model showed improvement in CI by 1.12% and 0.35% and a reduction in MSE by 7.7% and 3.33% on the KIBA and BindingDB datasets, respectively. we also showed that despite using various pooling operations on our proposed model, we achieved an average reduction in MSE by 7% on the KIBA dataset and 3% improvement on the BindingDB dataset.

关键词： Drugs In vivo Neural networks Predictive models Network architecture Feature extraction Protein sequence

来源：评论

学校读者我要写书评

暂无评论

NG-DTA: Drug-target affinity prediction with n-gram molecular graphs

NG-DTA: Drug-target affinity prediction with n-gram molecula...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Lok-In Tsui Te-Cheng Hsu Che Lin Graduate Institute of Communication Engineering National Taiwan University (NTU) Taipei Taiwan Institute of Communication Engineering National Tsing-Hua University Hsinchu Taiwan Department of Electrical Engineering NTU Taipei Taiwan Center for Computational and Systems Biology and Center for Biotechnology NTU Taipei Taiwan Smart Medicine and Health Informatics Program NTU Taipei Taiwan

Drug–target affinity (DTA) prediction is crucial to speed up drug development. The advance in deep learning allows accurate DTA prediction. However, most deep learning methods treat protein as a 1D string which is not informative to models compared to a graph representation. In this paper, we present a deep-learning-based DTA prediction method called N-gram Graph DTA (NG-DTA) that takes molecular graphs of drugs and n-gram molecular sub-graphs of proteins as inputs which are then processed by graph neural networks (GNNs). Without using any prediction tool for protein structure, NG-DTA performs better than other methods on two datasets in terms of concordance index (CI) and mean square error (MSE) (CI: 0.905, MSE: 0.196 for the Davis dataset; CI: 0.904, MSE: 0.120 for Kiba dataset). Our results showed that using n-gram molecular sub-graphs of proteins as input improves deep learning models’ performance in DTA prediction.

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：