检索结果-内蒙古大学图书馆

Data efficient surrogate modeling for engineering design: Ensemble-free batch mode deep active learning for regression

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Vardhan, Harsh Timalsina, Umesh Volgyesi, Peter Sztipanovits, Janos Department of Computer Science Vanderbilt University 1400 18th Ave. S. NashvilleTN37212-2846 United States Institute for Software Integrated Systems Vanderbilt University 1025 16th Ave. S. NashvilleTN37212-2328 United States Department of Electrical and Computer Engineering Vanderbilt University 400 24th Ave. S. NashvilleTN37212 United States

In a computer-aided engineering design optimization problem that involves notoriously complex and time-consuming simulator, the prevalent approach is to replace these simulations with a data-driven surrogate that approximates the simulator’s behavior at a much cheaper cost. The main challenge in creating an inexpensive data-driven surrogate is the generation of a sheer number of data using these computationally expensive numerical simulations. In such cases, Active Learning (AL) methods have been used that attempt to learn an input–output behavior while labeling the fewest samples possible. The current trend in AL for a regression problem is dominated by the Bayesian framework that needs training an ensemble of learning models that makes surrogate training computationally tedious if the underlying learning model is Deep Neural Networks (DNNs). However, DNNs have an excellent capability to learn highly nonlinear and complex relationships even for a very high dimensional problem. To leverage the excellent learning capability of deep networks along with avoiding the computational complexity of the Bayesian paradigm, in this work we propose a simple and scalable approach for active learning that works in a student-teacher manner to train a surrogate model. By using this proposed approach, we are able to achieve the same level of surrogate accuracy as the other baselines like DBAL and Monte Carlo sampling with up to 40% fewer samples. We empirically evaluated this method on multiple use cases including three different engineering design domains:finite element analysis, computational fluid dynamics, and propeller design. © 2022, CC BY.

关键词： Deep neural networks

Blockchain Model for Enhancing Aircraft Maintenance Records Security

学校读者我要写书评

暂无评论

Blockchain Model for Enhancing Aircraft Maintenance Records ...

2019 IEEE International Symposium on Technologies for Homeland Security, HST 2019

作者： Aleshi, Ahrash Seker, Remzi Babiceanu, Radu F. Embry-Riddle Aeronautical University Department of Elecrical Computer Software and Systems Engineering Daytona BeachFL United States

ISBN: (纸本)9781728150925

This paper addresses the need to enhance the integrity and transparency of aircraft maintenance records in the aviation industry by using blockchain technologies. A physical aircraft maintenance logbook is susceptible to being lost or destroyed. A nonexistent aircraft maintenance logbook hurts the confidence in integrity and reputation of the aircraft. Furthermore, fraud can occur through forgery of Federal Aviation Administration (FAA) personnel signatures and the installation of non-official aircraft parts with implications to homeland security. The scope of this work is to develop a secure blockchain that can store aircraft service records and information in a digital distributed ledger. By keeping the maintenance logbook on a digital ledger, records can be stored indefinitely in a trusted environment with the integrity of records guaranteed. Additionally, to achieve being a distributed ledger, a consensus algorithm Proof of Elapsed Time (PoET) is used to display the global state accurately to all users. The proposed Secure Aircraft Maintenance Records (SAMR) blockchain uses the Linux Foundations open sourced software 'Hyperledger' to facilitate an environment that mimics a real-world implementation. The blockchain logic for SAMR implementation was made in Python through creation of a permission-based blockchain for holding the maintenance records. © 2019 IEEE.

关键词： Blockchain

Capture uncertainties in deep neural networks for safe operation of autonomous driving vehicles

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ding, Liuhui Li, Dachuan Liu, Bowen Lan, Wenxing Bai, Bing Hao, Qi Cao, Weipeng Pei, Ke Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Sifakis Research Institute for Trustworthy Autonomous Systems Shenzhen518055 China Huawei Technologies Co. Ltd. Shenzhen518129 China

Uncertainties in Deep Neural Network (DNN)-based perception and vehicle's motion pose challenges to the development of safe autonomous driving vehicles. In this paper, we propose a safe motion planning framework featuring the quantification and propagation of DNN-based perception uncertainties and motion uncertainties. Contributions of this work are twofold: (1) A Bayesian Deep Neural network model which detects 3D objects and quantitatively capture the associated aleatoric and epistemic uncertainties of DNNs;(2) An uncertainty-aware motion planning algorithm (PU-RRT) that accounts for uncertainties in object detection and ego-vehicle's motion. The proposed approaches are validated via simulated complex scenarios built in CARLA. Experimental results show that the proposed motion planning scheme can cope with uncertainties of DNN-based perception and vehicle motion, and improve the operational safety of autonomous vehicles while still achieving desirable *** Codes 68T40 © 2021, CC BY-NC-ND.

关键词： Deep neural networks

Corrigendum to “Remote sensing and machine learning approach for zoning of wastewater drainage system” [Desalin Water Treat 319 (2024) 100549]

学校读者我要写书评

暂无评论

Desalination and Water Treatment 2025年 321卷

作者： A. Saranya Alanoud Al Mazroa Mashael Maashi T.M. Nithya V. Priya Department of Civil Engineering VOC College of Engineering Anna University Thoothukudi Campus Thoothukudi India Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University (PNU) P.O. Box 84428 Riyadh 11671 Saudi Arabia Department of Software Engineering College of Computer and Information Sciences King Saud University PO Box 103786 Riyadh 11543 Saudi Arabia Department of Computer Science and Engineering K.Ramakrishnan College of Engineering Trichy Tamil Nadu India Department of Civil Engineering GMR Institute of Technology Razam India

An Efficient Soft Error Tolerant Approach to Enhance Reliability of TCAM 1

学校读者我要写书评

暂无评论

An Efficient Soft Error Tolerant Approach to Enhance Reliabi...

1st International Conference on Advances in Science, engineering and Robotics Technology, ICASERT 2019

作者： Afrin, Rumana Sadi, Muhammad Sheikh Jurjens, Jan Khulna University of Engineering Techonology Department of Computer Science Engineering Khulna9203 Bangladesh University of Koblenz-Landau Fraunhofer-Institute for Software and Systems Engineering ISST Department of Computer Science Koblenz Germany

ISBN: (纸本)9781728134451

Ternary Content Addressable Memory (TCAM) is a kind of extraordinary memory which is used to search operations in routers, firewalls, network address translators, and entire content in a single clock cycle. It is a special kind of memory which is used in highly reliable network applications. These systems require high reliability since a single error may interrupt any computation which may cause total system failure. However, TCAM is facing serious reliability challenges due to soft errors. The probability of soft errors in TCAM is increasing progressively due to alpha-particle, cosmic rays, high-vitality particles, and ionizing impacts of barometrical neutron. In order to minimize the risks of soft errors in TCAM, a new idea is proposed in this paper where the search key is constructed in a tricky way and the contents of the TCAM are ordered in a sequential pattern. The proposed method provides soft error tolerance with a low data overhead. Experimental study shows how the proposed method outperforms the existing method to tolerate soft error. © 2019 IEEE.

关键词： Reliability

Emergency response UAS logistics models for coastal and offshore locations

学校读者我要写书评

暂无评论

Emergency response UAS logistics models for coastal and offs...

2019 Institute of Industrial and systems Engineers Annual Conference and Expo, IISE 2019

作者： Rau, James Babiceanu, Radu F. Seker, Remzi Department of Electrical Computer Software and Systems Engineering Embry-Riddle Aeronautical University Daytona BeachFL United States

ISBN: (纸本)9781713814092

Recently there has been a rapid increase in the advancements and use of Small Unmanned Aerial systems (sUAS) for a wide range of applications ranging from precision agriculture, to environmental monitoring, and to the delivery of commercial products from logistic companies. Fixed wing, vertical takeoff-landing (FW-VTOL) sUAS offer significant usability and safety advantages over its rival systems. During emergencies, frequent transportation and delivery of medical materials, such as blood derivatives, among hospitals, and to mass causality scenes and offshore vessels are needed. This research considers sUAS logistics supply networks to all end locations within a 40 nautical miles radius, based from a central hub location. Units of medical materials will be continuously distributed outwards and return with emergency location samples. The optimization of this sUAS logistics supply model is based on transporting the most number of units between the hub and network nodes at the lowest cost of deployment and the shortest amount of time. At a first stage, the optimization model will include only one node of the network per flight, constraint to be relaxed at a second iteration where two or more nodes could be visited per each flight. © 2019 IISE Annual Conference and Expo 2019. All rights reserved.

关键词： Location

Data Resolution Improvement for Ocean of Things Based on Improved FCM

学校读者我要写书评

暂无评论

Data Resolution Improvement for Ocean of Things Based on Imp...

2020 International Conference on Computing, Networking and Communications, ICNC 2020

作者： Yang, Jiachen Wen, Jiabao Jiang, Bin Song, Hoibing Kong, Fanhii Zhen, Zhizhio Tianjin University School of Electrical and Information Engineering Tianjin China Embry-Riddle Aeronautical University Department of Electrical Computer Software and Systems Engineering Daytona Beach United States Tianjin University of Technology School of Management Tianiin China Hebei University of Technology School of Artificial Intelligence Tianiin China

ISBN: (纸本)9781728149059

In Ocean of Things, information prediction is an important part of marine data processing. Due to a variety of marine acquisition devices, the distribution of marine information is discrete. The marine area is wide, and the resolution of the collected data is small, which causes the IoT device to accurately calculate the information of a small sea area. Processing discrete and sparse data is the main job of marine information processing equipment. The main purpose of this paper is to predict the information of the blind area based on the collected data. In order to increase the resolution of sea surface information, the availability of marine data in the Internet of Things is improved. This paper proposes a method for predicting information on marine blind spots. This method is based on the improved machine learning algorithm FCM. This method is used to predict sea surface temperature and improve the resolution of sea surface data. Finally, this paper has done a number of simulation experiments, based on different methods to predict the sea surface temperature. The experimental results are discussed and the performance of the proposed method is analyzed. © 2020 IEEE.

关键词： Surface temperature

An Exploratory Study on the Introduction and Removal of Different Types of Technical Debt

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Jiakun Huang, Qiao Xia, Xin Shihab, Emad Lo, David Li, Shanping College of Computer Science and Technology Zhejiang University China PengCheng Laboratory China College of Computer Science and Technology Zhejiang University China Faculty of Information Technology Monash University Melbourne Australia Department of Computer Science and Software Engineering Concordia University Canada School of Information Systems Singapore Management University Singapore

To complete tasks faster, developers often have to sacrifice the quality of the software. Such compromised practice results in the increasing burden to developers in future development. The metaphor, technical debt, describes such practice. Prior research has illustrated the negative impact of technical debt, and many researchers investigated how developers deal with a certain type of technical debt. However, few studies focused on the removal of different types of technical debt in practice. To fill this gap, we use the introduction and removal of different types of self-admitted technical debt (i.e., SATD) in 7 deep learning frameworks as an example. This is because deep learning frameworks are some of the most important software systems today due to their prevalent use in life-impacting deep learning applications. Moreover, the field of the development of different deep learning frameworks is the same, which enables us to find common behaviors on the removal of different types of technical debt across projects. By mining the file history of these frameworks, we find that design debt is introduced the most along the development process. As for the removal of technical debt, we find that requirement debt is removed the most, and design debt is removed the fastest. Most of test debt, design debt, and requirement debt are removed by the developers who introduced them. Based on the introduction and removal of different types of technical debt, we discuss the evolution of the frequencies of different types of technical debt to depict the unresolved sub-optimal trade-offs or decisions that are confronted by developers along the development process. We also discuss the removal patterns of different types of technical debt, highlight future research directions, and provide recommendations for practitioners. © 2021, CC BY.

关键词： Economic and social effects

Natidroid: Cross-language android permission specification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Chaoran Chen, Xiao Sun, Ruoxi Xue, Jason Wen, Sheng Ahmed, Muhammad Ejaz Camtepe, Seyit Xiang, Yang School of Software and Electrical Engineering Swinburne University of Technology HawthornVIC3122 Australia Department of Software Systems and Cybersecurity Faculty of IT Monash University ClaytonVIC3800 Australia School of Computer Science University of Adelaide North TerraceSA5005 Australia CSIRO Data61 Australia

The Android system manages access to sensitive APIs by permission enforcement. An application (app) must declare proper permissions before invoking specific Android APIs. However, there is no official documentation providing the complete list of permission-protected APIs and the corresponding permissions to date. Researchers have spent significant efforts extracting such API protection mapping from the Android API framework, which leverages static code analysis to determine if specific permissions are required before accessing an API. Nevertheless, none of them has attempted to analyze the protection mapping in the native library (i.e., code written in C and C++), an essential component of the Android framework that handles communication with the lower-level hardware, such as cameras and sensors. While the protection mapping can be utilized to detect various security vulnerabilities in Android apps, such as permission over-privilege and component hijacking, imprecise mapping will lead to false results in detecting such security vulnerabilities. To fill this gap, we thereby propose to construct the protection mapping involved in the native libraries of the Android framework to present a complete and accurate specification of Android API protection. We develop a prototype system, named NATIDROID, to facilitate the cross-language static analysis to benchmark against two state-of-the-art tools, termed AXPLORER [1] and ARCADE [2]. We evaluate NATIDROID on more than 11,000 Android apps, including system apps from custom Android ROMs and third-party apps from the Google Play. Our NATIDROID can identify up to 464 new API-permission mappings, in contrast to the worst-case results derived from both AXPLORER and ARCADE, where approximately 71% apps have at least one false positive in permission over-privilege and up to 3.6% apps have at least one false negative in component hijacking. Additionally, we identify that 24 components with at least one Native-triggered component hij

关键词： Mobile security