检索结果-内蒙古大学图书馆

Mapping cultural heritage sites at risk: A support tool for heritage sites management

学校读者我要写书评

暂无评论

Journal of Urban Management 2025年

作者： Brandano, Maria Giovanna Conti, Chiara Modica, Marco Urso, Giulia Gran Sasso Science Institute – Social Sciences Viale Luigi Rendina 26-28 L'Aquila 67100 Italy Department of Computer Control and Management Engineering “Antonio Ruberti” of the University La Sapienza Italy

Under the threat of climate change, the world has become increasingly unsafe, with extreme weather events causing devastation and high economic costs. These impacts are heterogeneous because of the interaction between different regional climate changes and the varying socio-economic characteristics of affected places. Climate change also impacts the management of cultural heritage sites. We then propose a method to identify heritage sites at risk from climate change issues, considering the single components of risk, namely both the natural hazard and the resilient/vulnerable local characteristics that may increase or mitigate the potential damage. The link between the natural and human spheres is, in fact, crucial for the development of suitable mitigation and prevention strategies, particularly relevant for developing countries that suffer from scarce economic resources. Overall, this work aims to provide a method to detect heritage sites at risk and a decision support tool for strategically managing cultural sites. We focus on Italy since it is one of the countries with a higher endowment of cultural heritage. However, thanks to its high replicability, this tool might be exported and adopted in different contexts and scenarios. © 2025 The Authors

关键词： Climate change Cultural heritage Impacts Risks

Privacy and Security Challenges and Solutions in IOT: A review

学校读者我要写书评

暂无评论

Privacy and Security Challenges and Solutions in IOT: A revi...

2019 International Conference on Smart Power and Internet Energy Systems, SPIES 2019

作者： Alhalafi, N. Veeraraghavan, Prakash Department of Computer Science and Computer Engineering La Trobe University Australia

The Internet of Things (IoT) is a revolutionary concept that heavily relies on the network infrastructure to connect large number of devices whose main purpose is to collect data and communicate among one another in the bid to enhance their decision-making capabilities. However, with this great evolution comes various challenges that threatens the information technology industry;these include security and privacy issues. The presence of a large number of interconnected technologies open a grey area in the IT field which has been worsened by the lack of capacity of various institutions to identify, assess and monitor important components to ensure compliance with security policies. Thus, there is need for a clear understanding of the issues at hand and how they can be solved in order to fully harness this capability. © Published under licence by IOP Publishing Ltd.

关键词： Decision making

Sparse Dynamic Network Reconstruction Through L1-regularization of a Lyapunov Equation

学校读者我要写书评

暂无评论

Sparse Dynamic Network Reconstruction Through L1-regularizat...

IEEE Conference on Decision and Control

作者： Ian Xul Belaustegui Marcela Ordorica Arango Roman Rossi-Pool Naomi Ehrich Leonard Alessio Franci Department of Mechanical and Aerospace Engineering Princeton University Instituto de Fisiología Celular - Neurociencias and Centro de Ciencias de la Complejidad Universidad Nacional Autónoma de México México Department of Electrical Engineering and Computer Science University of Liege and WEL Research Institute Wavre Belgium

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

An important problem in many areas of science is that of recovering interaction networks from high-dimensional time-series of many interacting dynamical processes. A common approach is to use the elements of the correlation matrix or its inverse as proxies of the interaction strengths, but the reconstructed networks are necessarily undirected. Transfer entropy methods have been proposed to reconstruct directed networks, but the reconstructed network lacks information about interaction strengths. We propose a network reconstruction method that inherits the best of the two approaches by reconstructing a directed weighted network from noisy data under the assumption that the network is sparse and the dynamics are governed by a linear (or weakly-nonlinear) stochastic dynamical system. The two steps of our method are i) constructing an (infinite) family of candidate networks by solving the covariance matrix Lyapunov equation for the state matrix and ii) using $L_{1}$-regularization to select a sparse solution. We further show how to use prior information on the (non)existence of a few directed edges to dramatically improve the quality of the reconstruction.

关键词： Correlation Reconstruction algorithms Entropy Sparse matrices Noise measurement Covariance matrices Dynamical systems

A preliminary approach to evolutionary multitasking for dynamic flexible job shop scheduling via genetic programming 20

学校读者我要写书评

暂无评论

A preliminary approach to evolutionary multitasking for dyna...

2020 Genetic and Evolutionary Computation Conference, GECCO 2020

作者： Zhang, Fangfang Mei, Yi Nguyen, Su Zhang, Mengjie School of Engineering and Computer Science Victoria University of Wellington New Zealand Centre for Data Analytics and Cognition La Trobe University Melbourne Australia

ISBN: (纸本)9781450371278

Genetic programming, as a hyper-heuristic approach, has been successfully used to evolve scheduling heuristics for job shop scheduling. However, the environments of job shops vary in configurations, and the scheduling heuristic for each job shop is normally trained independently, which leads to low efficiency for solving multiple job shop scheduling problems. This paper introduces the idea of multitasking to genetic programming to improve the efficiency of solving multiple dynamic flexible job shop scheduling problems with scheduling heuristics. It is realised by the proposed evolutionary framework and knowledge transfer mechanism for genetic programming to train scheduling heuristics for different tasks simultaneously. The results show that the proposed algorithm can dramatically reduce the training time for solving multiple dynamic flexible job shop tasks. © 2020 Owner/Author.

关键词： Genetic programming

A Gradient-Based Optimization Method Using the Koopman Operator

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hu, Mengqi Li, Bian Ma, Yi-An Lou, Yifei Yang, Xiu Department of Mathematics School of Data Science and Society University of North Carolina Chapel HillNC United States Department of Industrial and Systems Engineering Lehigh University BethlehemPA United States Halicioğlu Data Science Institute Department of Computer Science and Engineering University of California La Jolla San DiegoCA United States

In this paper, we propose a novel approach to solving optimization problems by reformulating the optimization problem into a dynamical system, followed by the adaptive spectral Koopman (ASK) method. The Koopman operator, employed in our approach, approximates the evolution of an ordinary differential equation (ODE) using a finite number of eigenfunctions and eigenvalues. We begin by providing a brief overview of the Koopman operator and the ASK method. Subsequently, we adapt the ASK method for solving a general optimization problem. Moreover, we provide an error bound to aid in understanding the performance of the proposed approach, marking the initial step in a more comprehensive numerical analysis. Experimentally, we demonstrate the applicability and accuracy of our method across a diverse range of optimization problems, including min-max problems. Our approach consistently yields smaller gradient norms and higher success rates in finding critical points compared to state-of-the-art gradient-based methods. We also observe the proposed method works particularly well when the dynamical properties of the system can be effectively modeled by the system's behaviors in a neighborhood of critical *** Codes 37N30, 37N40, 37Mxx, 46N10, 47N10 © 2023, CC BY-SA.

关键词： Ordinary differential equations

Can Personalized Medicine Coexist with Health Equity? Examining the Cost Barrier and Ethical Implications

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Francisco, Kishi Kobe Yee Apuhin, Andrane Estelle Carnicer Tan, Myles Joshua Toledo Byers, Mickael Cavanaugh Maravilla, Nicholle Mae Amor Tan Karim, Hezerul Abdul AlDahoul, Nouar Biology Program College of Arts and Science University of St. La Salle Negros Occidental Bacolod City Philippines Department of Electrical and Computer Engineering Herbert Wertheim College of Engineering University of Florida GainesvilleFL United States Department of Epidemiology College of Public Health & Health Professions College of Medicine University of Florida GainesvilleFL United States Department of Natural Sciences College of Arts and Science University of St. La Salle Negros Occidental Bacolod City Philippines Department of Chemical Engineering College of Engineering and Technology University of St. La Salle Negros Occidental Bacolod City Philippines Department of Electronics Engineering College of Engineering and Technology University of St. La Salle Negros Occidental Bacolod City Philippines Yo-Vivo Corporation Negros Occidental Bacolod City Philippines Department of Civil and Coastal Engineering Herbert Wertheim College of Engineering University of Florida GainesvilleFL United States Faculty of Engineering Multimedia University Selangor Cyberjaya Malaysia Department of Computer Science Division of Science New York University Abu Dhabi Saadiyat Marina District Abu Dhabi United Arab Emirates

Personalized medicine (PM) promises to transform healthcare by providingtreatments tailored to individual genetic, environmental, and lifestylefactors. However, its high costs and infrastructure demands raise concernsabout exacerbating health disparities, especially between high-income countries(HICs) and low- and middle-income countries (LMICs). While HICs benefit fromadvanced PM applications through AI and genomics, LMICs often lack theresources necessary to adopt these innovations, leading to a wideninghealthcare divide. This paper explores the financial and ethical challenges ofPM implementation, with a focus on ensuring equitable access. It proposesstrategies for global collaboration, infrastructure development, and ethicalframeworks to support LMICs in adopting PM, aiming to prevent furtherdisparities in healthcare accessibility and outcomes. © 2024, CC BY.

关键词： Personalized medicine

Towards memristive deep learning systems for real-time mobile epileptic seizure prediction

学校读者我要写书评

暂无评论

arXiv 2021年

作者： lammie, Corey Xiang, Wei Azghadi, Mostafa Rahimi College of Science and Engineering James Cook University Queensland4814 Australia Department of Computer Science and Information Technology La Trobe University VIC3086 Australia

The unpredictability of seizures continues to distress many people with drug-resistant epilepsy. On account of recent technological advances, considerable efforts have been made using different hardware technologies to realize smart devices for the real-time detection and prediction of seizures. In this paper, we investigate the feasibility of using Memristive Deep Learning Systems (MDLSs) to perform real-time epileptic seizure prediction on the edge. Using the MemTorch simulation framework and the Children’s Hospital Boston (CHB)-Massachusetts Institute of Technology (MIT) dataset we determine the performance of various simulated MDLS configurations. An average sensitivity of 77.4% and a Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.85 are reported for the optimal configuration that can process Electroencephalogram (EEG) spectrograms with 7,680 samples in 1.408ms while consuming 0.0133W and occupying an area of 0.1269mm2 in a 65nm Complementary Metal–Oxide–Semiconductor (CMOS) process. Copyright © 2021, The Authors. All rights reserved.

关键词： Neurodegenerative diseases

Multiple-level Point Embedding for Solving Human Trajectory Imputation with Prediction

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Qin, Kyle K. Ren, Yongli Shao, Wei lake, Brennan Privitera, Filippo Salim, Flora D. RMIT University 124 La Trobe St MelbourneVIC3000 Australia Cuebiq Inc. 15 West 27th Street New YorkNY10001 United States University of New South Wales School of Computer Science and Engineering Engineering Rd KensingtonNSW2052 Australia

Sparsity is a common issue in many trajectory datasets, including human mobility data. This issue frequently brings more difficulty to relevant learning tasks, such as trajectory imputation and prediction. Nowadays, little existing work simultaneously deals with imputation and prediction on human trajectories. This work plans to explore whether the learning process of imputation and prediction could benefit from each other to achieve better outcomes. And the question will be answered by studying the coexistence patterns between missing points and observed ones in incomplete trajectories. More specifically, the proposed model develops an imputation component based on the self-attention mechanism to capture the coexistence patterns between observations and missing points among encoder-decoder layers. Meanwhile, a recurrent unit is integrated to extract the sequential embeddings from newly imputed sequences for predicting the following location. Furthermore, a new implementation called Imputation Cycle is introduced to enable gradual imputation with prediction enhancement at multiple levels, which helps to accelerate the speed of convergence. The experimental results on three different real-world mobility datasets show that the proposed approach has significant advantages over the competitive baselines across both imputation and prediction tasks in terms of accuracy and *** Codes 68T07 Copyright © 2023, The Authors. All rights reserved.

关键词： Trajectories

Provably efficient model-based policy adaptation 37

学校读者我要写书评

暂无评论

Provably efficient model-based policy adaptation

37th International Conference on Machine Learning, ICML 2020

作者： Song, Yuda Mavalankar, Aditi Sun, Wen Gao, Sicun Department of Computer Science and Engineering University of California San Diego La Jolla United States Department of Computer Science Cornell University Ithaca United States

ISBN: (纸本)9781713821120

The high sample complexity of reinforcement learning challenges its use in practice. A promising approach is to quickly adapt pre-trained policies to new environments. Existing methods for this policy adaptation problem typically rely on domain randomization and meta-learning, by sampling from some distribution of target environments during pre-training, and thus face difficulty on out-of-distribution target environments. We propose new model-based mechanisms that are able to make online adaptation in unseen target environments, by combining ideas from no-regret online learning and adaptive control. We prove that the approach learns policies in the target environment that can recover trajectories from the source environment, and establish the rate of convergence in general settings. We demonstrate the benefits of our approach for policy adaptation in a diverse set of continuous control tasks, achieving the performance of state-of-the-art methods with much lower sample complexity. Our project website, including code, can be found at https://***/PADA. © 2020 37th International Conference on Machine Learning, ICML 2020. All rights reserved.

关键词： Reinforcement learning