检索结果-内蒙古大学图书馆

Physics Informed Shallow Machine Learning for Wind Speed Prediction

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lagomarsino-Oneto, Daniele Meanti, Giacomo Pagliana, Nicolò Verri, Alessandro Mazzino, Andrea Rosasco, Lorenzo Seminara, Agnese Department of Civil Chemical and Environmental Engineering University of Genoa Genoa Italy MaLGa Department of Computer Science Bioengineering Robotics and Systems Engineering University of Genoa Genoa Italy MaLGa Department of Mathematics University of Genoa Genoa Italy National Institute of Nuclear Physics Genoa Section Genoa Italy Center for Brains Minds and Machines Mit CambridgeMA United States Italian Institute of Technology Genoa Italy

The ability to predict wind is crucial for both energy production and weather forecasting. Mechanistic models that form the basis of traditional forecasting perform poorly near the ground. In this paper, we take an alternative datadriven approach based on supervised learning. We analyze a massive dataset of wind measured from anemometers located at 10 m height in 32 locations in two central and north west regions of Italy (Abruzzo and Liguria). We train supervised learning algorithms using the past history of wind to predict its value at a future time (horizon). Using data from a single location and time horizon we compare systematically several algorithms where we vary the input/output variables, the memory of the input and the linear vs non-linear learning model. We then compare performance of the best algorithms across all locations and forecasting horizons. We find that the optimal design as well as its performance vary with the location. We demonstrate that the presence of a reproducible diurnal cycle provides a rationale to understand this variation. We conclude with a systematic comparison with state of the art algorithms and show that, when the model is accurately designed, shallow algorithms are competitive with more complex deep architectures. © 2022, CC BY-NC-SA.

关键词： Wind

Levenberg-Marquardt Backpropagation for Numerical Treatment of Micropolar Flow in a Porous Channel with Mass Injection

学校读者我要写书评

暂无评论

Complexity 2021年第1期2021卷

作者： Ullah, Hakeem Khan, Imran Alsalman, Hussain Islam, Saeed Asif Zahoor Raja, Muhammad Shoaib, Muhammad Gumaei, Abdu Fiza, Mehreen Ullah, Kashif Mizanur Rahman, Sk. Md. Ayaz, Muhammad Department of Mathematics Abdul Wali Khan University Mardan MardanKP 23200 Pakistan Department of Computer Science College of Computer and Information Sciences King Saud University Riyadh11543 Saudi Arabia Future Technology Research Center National Yunlin University of Science and Technology 123 University Road Section 3 Douliou Yunlin64002 Taiwan Department of Mathematics COMSATS University Islamabad Attock Campus Attock43600 Pakistan Department of Computer Science Faculty of Applied Sciences Taiz University Taiz6803 Yemen Information and Communication Engineering Technology School of Engineering Technology and Applied Science Centennial College Toronto Canada

In this research work, an effective Levenberg-Marquardt algorithm-based artificial neural network (LMA-BANN) model is presented to find an accurate series solution for micropolar flow in a porous channel with mass injection (MPFPCMI). The LMA is one of the fastest backpropagation methods used for solving least-squares of nonlinear problems. We create a dataset to train, test, and validate the LMA-BANN model regarding the solution obtained by optimal homotopy asymptotic (OHA) method. The proposed model is evaluated by conducting experiments on a dataset acquired from the OHA method. The experimental results are obtained by using mean square error (MSE) and absolute error (AE) metric functions. The learning process of the adjustable parameters is conducted with efficacy of the LMA-BANN model. The performance of the developed LMA-BANN for the modelled problem is confirmed by achieving the best promise numerical results of performance in the range of E-05 to E-08 and also assessed by error histogram plot (EHP) and regression plot (RP) measures. © 2021 Hakeem Ullah et al.

关键词： Mean square error

Virtual Node Graph Neural Network for Full Phonon Prediction

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Okabe, Ryotaro Chotrattanapituk, Abhijatmedhi Boonkird, Artittaya Andrejevic, Nina Fu, Xiang Jaakkola, Tommi S. Song, Qichen Nguyen, Thanh Drucker, Nathan Mu, Sai Liao, Bolin Cheng, Yongqiang Li, Mingda Quantum Measurement Group Massachusetts Institute of Technology CambridgeMA United States Department of Chemistry Massachusetts Institute of Technology CambridgeMA United States Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA United States Department of Nuclear Science and Engineering Massachusetts Institute of Technology CambridgeMA United States Argonne National Laboratory LemontIL United States Department of Chemistry and Chemical Biology Harvard University CambridgeMA United States Applied Physics School of Engineering and Applied Sciences Harvard University CambridgeMA United States Department of Physics and Astronomy University of South Carolina ColumbiaSC United States Department of Materials University of California Santa Barbara Santa BarbaraCA United States Chemical Spectroscopy Group Spectroscopy Section Neutron Scattering Division Oak Ridge National Laboratory Oak RidgeTN United States

The structure-property relationship plays a central role in materials science. Understanding the structure-property relationship in solid-state materials is crucial for structure design with optimized properties. The past few years witnessed remarkable progress in correlating structures with properties in crystalline materials, such as machine learning methods and particularly graph neural networks as a natural representation of crystal structures. However, significant challenges remain, including predicting properties with complex unit cells input and material-dependent, variable-length output. Here we present the virtual node graph neural network to address the challenges. By developing three types of virtual node approaches - the vector, matrix, and momentum-dependent matrix virtual nodes, we achieve direct prediction of Γ-phonon spectra and full dispersion only using atomic coordinates as input. We validate the phonon bandstructures on various alloy systems, and further build a Γ-phonon database containing over 146,000 materials in the Materials Project. Our work provides an avenue for rapid and high-quality prediction of phonon spectra and bandstructures in complex materials, and enables materials design with superior phonon properties for energy applications. The virtual node augmentation of graph neural networks also sheds light on designing other functional properties with a new level of flexibility. © 2023, CC BY.

关键词： Forecasting

On the connection between least squares, regularization, and classical shadows

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhu, Zhihui Lukens, Joseph M. Kirby, Brian T. Department of Computer Science and Engineering The Ohio State University ColumbusOH43210 United States Research Technology Office and Quantum Collaborative Arizona State University TempeAZ85287 United States Quantum Information Science Section Oak Ridge National Laboratory Oak RidgeTN37831 United States DEVCOM Army Research Laboratory AdelphiMD20783 United States Tulane University New OrleansLA70118 United States

Classical shadows (CS) offer a resource-efficient means to estimate quantum observables, circumventing the need for exhaustive state tomography. Here, we clarify and explore the connection between CS techniques and least squares (LS) and regularized least squares (RLS) methods commonly used in machine learning and data analysis. By formal identification of LS and RLS "shadows" completely analogous to those in CS—namely, point estimators calculated from the empirical frequencies of single measurements—we show that both RLS and CS can be viewed as regularizers for the underdetermined regime, replacing the pseudoinverse with invertible alternatives. Through numerical simulations, we evaluate RLS and CS from three distinct angles: the tradeoff in bias and variance, mismatch between the expected and actual measurement distributions, and the interplay between the number of measurements and number of shots per measurement. Compared to CS, RLS attains lower variance at the expense of bias, is robust to distribution mismatch, and is more sensitive to the number of shots for a fixed number of state copies—differences that can be understood from the distinct approaches taken to regularization. Conceptually, our integration of LS, RLS, and CS under a unifying "shadow" umbrella aids in advancing the overall picture of CS techniques, while practically our results highlight the tradeoffs intrinsic to these measurement approaches, illuminating the circumstances under which either RLS or CS would be preferred, such as unverified randomness for the former or unbiased estimation for the latter. © 2023, CC BY.

关键词： Least squares approximations

Unified resilience model using deep learning for assessing power system performance

学校读者我要写书评

暂无评论

Heliyon 2025年第4期11卷 e42802页

作者： Artemchuk, Volodymyr Garbuz, Iurii Jamil Alsayaydeh, Jamil Abedalrahim Shkarupylo, Vadym Oliinyk, Andrii Bin Yusof, Mohd Faizal Herawan, Safarudin Gazali Department of Mathematical and Econometric Modelling G.E. Pukhov Institute for Modelling in Energy Engineering of the NAS of Ukraine Kyiv Ukraine Department of Environmental Protection Technologies and Radiation Safety Center for Information-analytical and Technical Support of Nuclear Power Facilities Monitoring of the NAS of Ukraine Kyiv Ukraine Department of Іnformation Systems in Economics Kyiv National Economic University Named After Vadym Hetman Kyiv Ukraine Department of Computerized Control System National Aviation University Kyiv Ukraine Department of Engineering Technology Fakulti Teknologi Dan Kejuruteraan Elektronik Dan Komputer (FTKEK) Universiti Teknikal Malaysia Melaka (UTeM) Melaka 76100 Malaysia Department of Computer Systems Networks and Cybersecurity of the National University of Life and Environmental Sciences of Ukraine Kyiv Ukraine Department of Software Tools Faculty of Computer Science and Technology Zaporizhzhia Polytechnic National University Zaporizhzhia Ukraine Research Section Faculty of Resilience Rabdan Academy Abu Dhabi United Arab Emirates Industrial Engineering Department Faculty of Engineering Bina Nusantara University Jakarta 11480 Indonesia

Energy resilience in renewable energy sources dissemination components such as batteries and inverters is crucial for achieving high operational fidelity. Resilience factors play a vital role in determining the performance of power systems, regardless of their operating environment and interruptions. This article introduces a Unified Resilience Model (URM) using Deep Learning (DL) to enhance power system performance. The proposed model analyzes environmental factors impacting the resilience of batteries and energy storage devices. This deep learning approach trains performance-impacting factors using previously known low resilience drain data. The learning output is utilized to augment various strengthening factors, thereby improving resilience. Drain mitigation and performance improvements are combined for direct impact verification. This process validates the model's fidelity in enhancing power system performance, with a specific focus on the impact of weather factors. © 2025 The Authors

关键词： Deep learning Energy resilience Fidelity Weather impact

Time-series anomaly detection using dynamic programming based longest common subsequence on sensor data

学校读者我要写书评

暂无评论

Expert Systems with Applications 2023年 213卷

作者： Nguyen, Thi Phuong Quyen Phuc, Phan Nguyen Ky Yang, Chao-Lung Sutrisno, Hendri Luong, Bao-Han Le, Thi Huynh Anh Nguyen, Thanh Tung Faculty of Project Management The University of Danang- University of Science and Technology 54 Nguyen Luong Bang Danang Viet Nam Department of Industrial System Engineering International University- Ho Chi Minh City VNU Quarter 6 Linh Trung Ward Thu Duc District HCMC Viet Nam Department of Industrial Management National Taiwan University of Science and Technology No. 43 Sec. 4 Keelung Rd. Daan Dist. Taipei Taiwan Institute of Statistical Science Academia Sinica No. 128 Academia Road Section 2 Nankang Taipei11529 Taiwan Faculty of Computer Science and Engineering University of Technology- Ho Chi Minh City VNU 268 Ly Thuong Kiet Street District 10 HCMC Viet Nam

This study proposes a novel approach to time-series anomaly detection by solving the longest common subsequence (LCS) problem of two time-series data. The conventional LCS problem is used to measure the similarity of two input strings. However, it cannot be applied to real-time data collected from sensors in smart manufacturing, which are mostly real numbers instead of strings. Thus, two algorithms—an extension of fixed gap longest common subsequence (extent FGLCS) and the modified dynamic programming-based LCS (MDP-LCS) algorithm—are proposed to deal with real-time series data. Further, a gap search constraint is investigated to limit the search range in finding the LCS. This study also provides a threshold to define the matching of a pair that contains real numbers rather than a string in the conventional LCS or FGLCS problems. In addition, the proposed methods employ the gap search constraint and the threshold to reduce computational time. Furthermore, the proposed algorithms can be implemented on both univariate and multivariate time-series data. The LCS length, known as the similarity of the two time-series data, is used to detect the anomalies based on the user's expectation. The accuracy and computational time of the proposed algorithm show a significant positive result compared with the exact solution provided by the dynamic programming-based LCS algorithm. Moreover, this study also uses the proposed methods for anomaly detection in a case study of big multisensory data in smart manufacturing. The result shows that the MDP-LCS can detect approximately 98% of normal data and more than 85% of anomalies with a shorter computational time. © 2022 Elsevier Ltd

关键词： Time series

Probabilistic wind power forecasting combining deep learning architectures

学校读者我要写书评

暂无评论

Probabilistic wind power forecasting combining deep learning...

International Conference on European Electricity Market, EEM

作者： Eric Lacoa Arends Simon J. Watson Sukanta Basu Bedassa Cheneka Faculty of Electrical Engineering Mathematics & Computer Science Delft University of Technology Delft The Netherlands Faculty of Aerospace Engineering Wind Energy Section Faculty of Civil Engineering and Geosciences

ISBN: (数字)9781728169194

ISBN: (纸本)9781728169200

A series of probabilistic models were bench-marked during the European Energy Markets forecasting Competition 2020 to assess their relative accuracy in predicting aggregated Swedish wind power generation using as input historic weather forecasts from a numerical weather prediction model. In this paper, we report the results of one of these models which uses a deep learning approach integrating two architectures: (a) Convolutional Neural Network (CNN) LeNet-5 based architectrure; (b) Multi-Layer Perceptron (MLP) architecture -with two hidden layers-. These are concatenated into the Smooth Pinball Neural Network (SPNN) framework for quantile regression. Hyperparameters were optimised to produce the best model for every region. When tuned, the re-forecasts from the model performed favorably compared to other machine learning approaches and showed significant improvement on the original competition results, though failed to fully capture spatial patterns in certain cases when compared to other methods.

关键词：

A Survey on Open Radio Access Networks: Challenges, Research Directions, and Open Source Approaches

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Azariah, Wilfrid Bimo, Fransiscus Asisi Lin, Chih-Wei Cheng, Ray-Guang Nikaein, Navid Jana, Rittwik Department of Electronic and Computer Engineering National Taiwan University of Science and Technology No. 43 Section 4 Keelung Rd Da'an District Taipei City106335 Taiwan Department of Communication Systems EURECOM Campus SophiaTech 450 Route des Chappes Biot06410 France Google LLC 1600 Amphitheatre Parkway Mountain ViewCA94043 United States

The open radio access network (RAN) aims to bring openness and intelligence to the traditional closed and proprietary RAN technology and offer flexibility, performance improvement, and cost-efficiency in the RAN's deployment and operation. This paper provides a comprehensive survey of the Open RAN development. We briefly summarize the RAN evolution history and the state-of-the-art technologies applied to Open RAN. The Open RAN-related projects, activities, and standardization is then discussed. We then summarize the challenges and future research directions required to support the Open RAN. Finally, we discuss some solutions to tackle these issues from the open source perspective. © 2022, CC BY-NC-ND.

关键词： Radio access networks

Wavelet-based compressed sensing of the system matrix for magnetic particle imaging

学校读者我要写书评

暂无评论

Signal, Image and Video Processing 2025年第9期19卷

作者： Atalay Aydın, Vildan Möddel, Martin Knopp, Tobias Computer Engineering Izmir Demokrasi University Izmir Turkey Section for Biomedical Imaging University Medical Center Hamburg-Eppendorf Hamburg Germany Institute for Biomedical Imaging Hamburg University of Technology Hamburg Germany Fraunhofer Research Institution for Individualized and Cell-Based Medical Engineering IMTE Lübeck Germany

Magnetic particle imaging (MPI) is a trending tracer imaging technique relatively newly proposed. In MPI, a time-consuming system matrix (SM) calibration scan is required to reconstruct the spatial distribution of superparamagnetic nanoparticles. Compressed sensing (CS) techniques are widely utilized to reduce the time required for SM calibration, with Discrete Cosine Transform (DCT) being the state-of-the-art sparsifying transform. This paper proposes a wavelet-based CS method for SM reconstruction. To the best of our knowledge, this is the first work to employ wavelets as the sparsifying transform for SM recovery in MPI. To this goal, we employ biorthogonal wavelet transform to sparsify the SM rows. We propose a variant of the iterative shrinkage/thresholding-based algorithm for SM reconstruction with the help of bivariate shrinkage to take advantage of the multiscale nature of wavelets and the dependency between wavelet subband coefficients. The performance of the proposed method is assessed by phantom image reconstructions using the state-of-the-art Kaczmarz algorithm. Experimental results using the DCT and the proposed wavelet-based methods confirm that the proposed method outperforms the state-of-the-art DCT-based compression based on the comparisons of (i) the sparsity levels of several SM frequencies, (ii) the reconstruction error of SM frequencies, where the average error for channels 1 and 2 decreased by approximately 10% when using DWT instead of DCT, and (iii) the visual quality of reconstructed phantom images at different sparsity levels, as no ground truth is available for metric-based comparisons. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Discrete cosine transforms