检索结果-内蒙古大学图书馆

IEEE Transactions on Technology and Society 2021年第3期2卷 116-121页

作者： Jacobs, Danielle McDaniel, Troy Varsani, Arvind Halden, Rolf U. Forrest, Stephanie Lee, Heewook School of Computing Informatics and Decision Systems Engineering Arizona State University TempeAZ United States Polytechnic School Arizona State University MesaAZ United States Biodesign Center for Fundamental and Applied Microbiomics Arizona State University TempeAZ United States Biodesign Center for Environmental Health Engineering Arizona State University TempeAZ United States Biodesign Center for Biocomputing Security and Society Arizona State University TempeAZ United States

Analysis of municipal wastewater, or sewage for public health applications is a rapidly expanding field aimed at understanding emerging epidemiological trends, including human and disease migration. The newly gained ability to extract and analyze genetic material from wastewater poses important societal and ethical questions, including: How to safeguard data? Who owns genetic data recovered from wastewater? and What are the ethical and legal issues surrounding its use? In the U.S., both corporate and legal policies regarding privacy have been historically reactive instead of proactive. In wastewater-based epidemiology (WBE), the pace of innovation has outpaced the ability of social and legal mechanisms to keep up. To address this discrepancy, early and robust discussions of the research, policies, and ethics surrounding WBE analysis and genetics are needed. This article contributes to this discussion by examining ownership issues for human genetic data recovered from wastewater and the uses to which it may be put. We focus particularly on the risks associated with personally identifiable data, highlighting potential risks, relevant privacy-enhancing technologies, and appropriate ethics. This article proposes an approach for people conducting WBE studies to help them systematically consider the ethical and privacy implications of their work. © 2020 IEEE.

关键词： Sewage

来源：评论

学校读者我要写书评

暂无评论

Effective submodularity of influence maximization on temporal networks

引用

Physical Review E 2022年第3期106卷 034301-034301页

作者： Şirag Erkol Dario Mazzilli Filippo Radicchi Center for Complex Networks and Systems Research Luddy School of Informatics Computing and Engineering Indiana University Bloomington Indiana 47408 USA Enrico Fermi Research Center Via Panisperna 89 A Rome Italy

We study influence maximization on temporal networks. This is a special setting where the influence function is not submodular, and there is no optimality guarantee for solutions achieved via greedy optimization. We perform an exhaustive analysis on both real and synthetic networks. We show that the influence function of randomly sampled sets of seeds often violates the necessary conditions for submodularity. However, when sets of seeds are selected according to the greedy optimization strategy, the influence function behaves effectively as a submodular function. Specifically, violations of the necessary conditions for submodularity are never observed in real networks, and only rarely in synthetic ones. The direct comparison with exact solutions obtained via brute-force search indicates that the greedy strategy provides approximate solutions that are well within the optimality gap guaranteed for strictly submodular functions. Greedy optimization appears, therefore, to be an effective strategy for the maximization of influence on temporal networks.

关键词： Collective behavior in networks Spreading

来源：评论

学校读者我要写书评

暂无评论

A Comparison Study on Generative Adversarial Networks (GANs) for Satellite Image Upscaling

A Comparison Study on Generative Adversarial Networks (GANs)...

引用

IEEE Conference on systems, Process & Control (ICSPC)

作者： Brandon Kah Wei Li Muhammed Basheer Jasser Bayan Issa Samuel-Soma M. Ajibade Hui Na Chua Richard T.K. Wong Muzaffar Hamzah Department of Computing and Information Systems School of Engineering and Technology Sunway University No. 5 Jalan Universiti Bandar Sunway Selangor Darul Ehsan Malaysia Research Centre For Human-Machine Collaboration (HUMAC)School of Engineering and Technology Sunway University No. 5 Jalan Universiti Bandar Sunway Selangor Darul Ehsan Malaysia Faculty of Informatics Engineering University of Aleppo Syria Department of Computer Engineering Istanbul Ticaret University Istanbul Turkiye Faculty of Computing and Informatics Universiti Malaysia Sabah Kota Kinabalu Sabah Malaysia

ISBN: (数字)9798350391398

ISBN: (纸本)9798350391404

Satellite images that are publicly available on the internet such as Google Maps are mostly low-quality and blurry which is not very useful for research or decision-making due to the lack of details. Recently image upscaling has been increasing in popularity to address several real-world problems where one approach is using Convolutional Neural Networks (CNNs). However, CNNs have difficulty in restoring fine details and this has led to the use of Generative adversarial networks (GANs) for image scaling. In this paper, three GAN models are trained which are Enhanced Super-Resolution Generative Adversarial Networks (Real-ESRGAN), Image Restoration Using Swin Transformer (SwinIR-Medium), and Dual Aggregation Transformer (DAT-2). The models are evaluated with well-known image metrics to determine each model’s effectiveness in upscaling low-resolution satellite images. The results show that all models can reconstruct the image to some degree where the best out of the three is DAT-2. Further fine-tuning of the best model by changing the loss functions has shown improvements in structural integrity for the upscaled image.

关键词： Training Photography Measurement Web services Generative adversarial networks Transformers Satellite images Image restoration Particle swarm optimization Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Diversity and stylization of the contemporary user-generated visual arts in the complexity-entropy plane

arXiv

引用

arXiv 2024年

作者： Kim, Seunghwan Lee, Byunghwee Lee, Wonjae Graduate School of Culture Technology KAIST Daejeon34141 Korea Republic of Center for Complex Networks and Systems Research Luddy School of Informatics Computing and Engineering Indiana University BloomingtonIN47408 United States Institute of Basic Science Sungkyunkwan University Suwon16419 Korea Republic of

The advent of computational and numerical methods in recent times has provided new avenues for analyzing art historiographical narratives and tracing the evolution of art styles therein. Here, we investigate an evolutionary process underpinning the emergence and stylization of contemporary user-generated visual art styles using the complexity-entropy (C-H) plane, which quantifies local structures in paintings. Informatizing 149,780 images curated in DeviantArt and Bēhance platforms from 2010 to 2020, we analyze the relationship between local information of the C-H space and multi-level image features generated by a deep neural network and a feature extraction algorithm. The results reveal significant statistical relationships between the C-H information of visual artistic styles and the dissimilarities of the multi-level image features over time within groups of artworks. By disclosing a particular C-H region where the diversity of image representations is noticeably manifested, our analyses reveal an empirical condition of emerging styles that are both novel in the C-H plane and characterized by greater stylistic diversity. Our research shows that visual art analyses combined with physics-inspired methodologies and machine learning, can provide macroscopic insights into quantitatively mapping relevant characteristics of an evolutionary process underpinning the creative stylization of uncharted visual arts of given groups and time. © 2024, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Advancing Privacy and Accuracy with Federated Learning and Homomorphic Encryption

TechRxiv

引用

TechRxiv 2023年

作者： Nguyen, Tuy Tan Phan, Quoc Bao Nguyen, Dinh C. The School of Informatics Computing and Cyber Systems Northern Arizona University FlagstaffAZ86011 United States The Department of Electrical and Computer Engineering University of Alabama in Huntsville HuntsvilleAL35899 United States

In this paper, we present an integrated framework that combines Federated Learning (FL) with Homomorphic Encryption (HE) using the Artificial Intelligence (AI) models and the Cheon-Kim-Kim-Song (CKKS) algorithm to address the challenges of privacy and accuracy. FL facilitates collaborative training of Convolutional Neural Network (CNN) and MultiLayer Perceptron (MLP) models across decentralized devices, allowing for data privacy preservation without sharing raw data. The integration of the CKKS algorithm for HE ensures secure computation on encrypted data during the FL process. Our experimental results on three diverse datasets demonstrate the efficacy of this approach, achieving an impressive highest average accuracy of 97.3%. Additionally, the CKKS algorithm is used to achieve efficient computation, making it a promising solution for privacy-conscious machine learning applications, and paving the way for practical deployment in various real-world scenarios, thereby revolutionizing the landscape of privacy-preserving machine learning. © 2023, CC BY.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

Determining optimal fuel strategies under uncertainty

Determining optimal fuel strategies under uncertainty

引用

2020 Institute of Industrial and systems Engineers Annual Conference and Expo, IISE 2020

作者： Edwards, Dominiqueca Davis, Lauren Mirchandani, Pitu Department of Industrial and Systems Engineering North Carolina A&T State University GreensboroNC United States School of Computing Informatics Decision Systems Engineering Arizona State University TempeAZ United States

ISBN: (纸本)9781713827818

In preparation for a hurricane, individuals affected often are required to evacuate. Evacuations can cause high increases in the demand for gasoline fuel. The purpose of this research is to determine alternate delivery locations and times for fuel vessels scheduled to arrive at a port that is impacted by an approaching hurricane. Motivated by the impact of Hurricane Irma in Florida, we develop a multi-period stochastic scheduling model that incorporates hurricane advisories, scheduled fuel deliveries, maritime port storage capacity and vessel capacity in a maritime port network. Our model determines the best delivery schedule based on multiple objectives. The first minimizes total unmet demand at each port. The second objective captures inequity in unmet demand across the port network. We conduct a numerical study based on fuel delivery data from maritime ports in Florida. The results show we are able to determine alternative delivery schedules for each vessel. One of the key findings is that the port availability is the driving factor in determining the vessel schedules. © Proceedings of the 2020 IISE Annual. All Rights Reserved.

关键词： Hurricanes

来源：评论

学校读者我要写书评

暂无评论

A Bibliometric Analysis and Research Landscape of Artificial Intelligence in Education 14

A Bibliometric Analysis and Research Landscape of Artificial...

引用

14th IEEE International Conference on Control System, computing and engineering, ICCSCE 2024

作者： Ajibade, Samuel-Soma M. Issa, Bayan Jasser, Muhammed Basheer Hassan, Farrukh Aldharhani, Ghassan Saleh Al-Hadi, Ismail Ahmed Al-Qasem Akintoye, Kayode Akinlekan Tabuena, Almighty Cortezo School of Engineering and Technology Sunway University Department of Computing and Information Systems No. 5 Jalan Universiti Selangor Darul Ehsan Bandar Sunway47500 Malaysia Istanbul Ticaret University Department of Computer Engineering Istanbul Turkey University of Aleppo Faculty of Informatics Engineering Syria Institute of Computer Science and Digital Innovation UCSI University Kuala Lumpur Malaysia UKM University Faculty of Information Science and Technology Selangor Bangi Malaysia The Federal Polytechnic Department of Computer Science Ado Ekiti Ekiti State Nigeria University of the City of Valenzuela College of Arts and Sciences Philippines

ISBN: (纸本)9798350364507

This study examines the academic field of Artificial Intelligence in Education (AI-ED) by examining the publications and indexed documents in Scopus from 2010 to 2023. Consequently, we examined the publishing trends, exemplary articles, and the most engaged participants and funding institutions in the domain of AI-ED research. A bibliometric analysis was performed to examine the network of co-authorships, keywords, and citations in the domain of AIED research. The Scopus search resulted in the discovery of 10,474 published documents on AI-ED. Additionally, trends analysis indicated a significant increase of over 3,000% in publications between 2010 and 2023. Conference papers are the most often utilized document type, including 6757 publications or 64.5% of the overall amount. The ACM International Conference Proceeding Series is the primary source for published materials, accounting for 675 publications or 6.44% of the total publications on the topic. The most prolific researchers in the field of AI-ED are Breazeal, C and Chai C.S, each having published 18 documents. Additionally, the two institutions that have produced the highest number of published documents are Carnegie Mellon University (CMU) and the University of NC State University (NCSU). The output of the affiliations active in the topic is primarily attributed to the funders, specifically the National Science Foundation, which is the leading funding institution based in the United States and has contributed to 354 publications. An analysis of keyword co-occurrence revealed 6 main study areas that cover the essential tools, theories, methodologies, and socioeconomic and financial aspects of artificial intelligence in education (AIED). Future research in the field of artificial intelligence in education will focus on employing sophisticated deep learning, machine learning, and neural network algorithms to precisely predict students' learning patterns. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Fostering interdisciplinary data cultures through early career development: The RDA/US data share fellowship

引用

Data Science Journal 2021年第1期20卷 1-19页

作者： Kouper, Inna Scheidt, Lois A. Plale, Beth A. Department of Informatics School of Informatics Computing and Engineering Indiana University Bloomington United States School of Information Studies University of Wisconsin Milwaukee United States Department of Intelligent Systems and Engineering School of Informatics Computing and Engineering Indiana University Bloomington United States

Openness and interdisciplinarity in research and data are among the challenges that are frequently discussed in the context of changing scientific and scholarly practices. Gradually, the visions of open and widely shared data are being reconciled with complex realities that stem from the disciplinary differences in data cultures. In this paper we discuss interdisciplinarity through data as a way to create research environments that are more flexible and, as a result, more amenable to change. We report our findings from facilitating and evaluating a data-oriented early-career fellowship program that was administered as part of the Research Data Alliance (RDA), a global organization that aims to enable open sharing and re-use of data. We identify ways to foster interdisciplinary data cultures among the future researchers and professionals and propose recommendations for future programs. While the short-term early career programs cannot address the systemic factors that impact openness and interdisciplinarity, such as the systems of reward and recognition or the funding structures, they can introduce mechanisms that support diversity, learning, and leadership and, ultimately, contribute to a culture change. © 2021 The Author(s).

关键词： Data culture Data stewardship Early career training Open science

来源：评论

学校读者我要写书评

暂无评论

Lessons Learned from Persona Usage in Requirements engineering Practice

Lessons Learned from Persona Usage in Requirements Engineeri...

引用

IEEE International Conference on Requirements engineering

作者： Devi Karolita John C. Grundy Tanjila Kanij Jennifer McIntosh Humphrey O. Obie Department Informatics Engineering Faculty of Engineering Palangka Raya University Palangka Raya Indonesia Department of Software Systems and Cybersecurity Faculty of IT Monash University Melbourne Australia School of Science Computing and Engineering Technologies Swinburne University of Technology Melbourne Australia Melbourne School of Population and Global Health University of Melbourne Melbourne Australia Telstra Health Melbourne Australia

ISBN: (数字)9798350395112

ISBN: (纸本)9798350395129

Personas, as a tool for characterising end-users, are widely utilised in requirements engineering (RE), primarily to enhance the understanding of end-users and their needs. However, the efficacy of persona usage in RE practice remains inadequately explored. To bridge this gap, we conducted an interview-based study with 22 international RE experts. These experts shared their experiences in utilising personas for RE-related tasks. Through thematic analysis of the collected insights, we propose recommendations for the effective creation and integration of personas in RE tasks. Our suggestions for efficient persona usage in RE emphasise the necessity of direct human interaction throughout persona development, while also con-sidering project constraints. We recommend creating personas that reflect the needs and preferences of persona consumers regarding the information included and the presentation style. Additionally, fostering organisational awareness of the benefits of personas in understanding targeted end-users is crucial. Lastly, we highlight the importance of the interpersonal skills required by requirements engineers to support the successful incorporation of personas in RE.

关键词： Bridges Requirements engineering Task analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-Junction Traffic Light Control System with Reinforcement Learning in Sunway Smart City

Multi-Junction Traffic Light Control System with Reinforceme...

引用

IEEE International Conference on Automatic Control and Intelligent systems (I2CACIS)

作者： Hao Cheng Lam Richard T. K. Wong Muhammed Basheer Jasser Hui Na Chua Bayan Issa Department of Computing and Information Systems School of Engineering and Technology Sunway University Jalan Universiti Bandar Sunway Selangor Darul Ehsan Malaysia Research Centre for Human-Machine Collaboration (HUMAC) School of Engineering and Technology Sunway University Jalan Universiti Bandar Sunway Selangor Darul Ehsan Malaysia Faculty of Informatics Engineering University of Aleppo Syria

ISBN: (数字)9798350372106

ISBN: (纸本)9798350372113

This paper presents a reinforcement learning approach to address urban traffic congestion with traffic light control optimization. The proposed system leverages Q-learning and Markov decision Processes (MDPs) to develop an adaptive control framework capable of adjusting traffic signal timings dynamically. A neural network model is employed to estimate Q-values, representing cumulative rewards for various control actions. The training process involves interactions between the agent and a simulated traffic environment using the Simulation of Urban Mobility (SUMO) tool. Experimental results showcase the efficacy of the RL-based approach in mitigating congestion and improving traffic flow. This work focuses on the case study of a network of junctions that contribute to the main traffic flow in the township of Bandar Sunway.

关键词： Training Adaptation models Q-learning Smart cities Markov decision processes Neural networks Process control

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：