检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Żychowski, Adam Perrault, Andrew Mańdziuk, Jacek Faculty of Mathematics and Information Science Warsaw University of Technology Poland Department of Computer Science and Engineering The Ohio State University United States Faculty of Computer Science AGH University of Krakow Poland Center of Excellence in Artificial Intelligence AGH University of Krakow Poland

Decision trees are widely used in machine learning due to their simplicity and interpretability, but they often lack robustness to adversarial attacks and data perturbations. The paper proposes a novel island-based coevolutionary algorithm (ICoEvoRDF) for constructing robust decision tree ensembles. The algorithm operates on multiple islands, each containing populations of decision trees and adversarial perturbations. The populations on each island evolve independently, with periodic migration of top-performing decision trees between islands. This approach fosters diversity and enhances the exploration of the solution space, leading to more robust and accurate decision tree ensembles. ICoEvoRDF utilizes a popular game theory concept of mixed Nash equilibrium for ensemble weighting, which further leads to improvement in results. ICoEvoRDF is evaluated on 20 benchmark datasets, demonstrating its superior performance compared to state-ofthe- art methods in optimizing both adversarial accuracy and minimax regret. The flexibility of ICoEvoRDF allows for the integration of decision trees from various existing methods, providing a unified framework for combining diverse solutions. Our approach offers a promising direction for developing robust and interpretable machine learning models. © 2024, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based Robust Design for an IRS-Assisted MISO-NOMA System

IEEE Transactions on Machine Learning in Communications and ...

引用

IEEE Transactions on Machine Learning in Communications and Networking 2024年 2卷 424-441页

作者： Waraiet, Abdulhamed Cumanan, Kanapathippillai Ding, Zhiguo Dobre, Octavia A. University of York School of Physics Engineering and Technology YorkYO10 5DD United Kingdom Khalifa University Department of Computer and Communication Engineering Abu Dhabi United Arab Emirates Memorial University Faculty of Engineering and Applied Science St. John'sNLA1C 5S7 Canada

In this paper, we propose a robust design for an intelligent reflecting surface (IRS)-assisted multiple-input single output non-orthogonal multiple access (NOMA) system. By considering channel uncertainties, the original robust design problem is formulated as a sum-rate maximization problem under a set of constraints. In particular, the uncertainties associated with reflected channels through IRS elements and direct channels are taken into account in the design and they are modelled as bounded errors. However, the original robust problem is not jointly convex in terms of beamformers at the base station and phase shifts of IRS elements. Therefore, we reformulate the original robust design as a reinforcement learning problem and develop an algorithm based on the twin-delayed deep deterministic policy gradient agent (also known as TD3). In particular, the proposed algorithm solves the original problem by jointly designing the beamformers and the phase shifts, which is not possible with conventional optimization techniques. Numerical results are provided to validate the effectiveness and evaluate the performance of the proposed robust design. In particular, the results demonstrate the competitive and promising capabilities of the proposed robust algorithm, which achieves significant gains in terms of robustness and system sum-rates over the baseline deep deterministic policy gradient agent. In addition, the algorithm has the ability to deal with fixed and dynamic channels, which gives deep reinforcement learning methods an edge over hand-crafted convex optimization-based algorithms. © 2023 CCBY.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Combining image and point cloud segmentation to improve heritage understanding 10

Combining image and point cloud segmentation to improve heri...

引用

10th International Workshop 3D-ARCH "3D Virtual Reconstruction and Visualization of Complex Architectures"

作者： Bassier, Maarten Mazzacca, Gabriele Battisti, Roberto Malek, Salim Remondino, Fabio Dept. of Civil Engineering Geomatics KU Leuven Faculty of Engineering Technology Ghent Belgium Trento Italy Dept. Mathematics Computer Science and Physics University of Udine Italy

Current 2D and 3D semantic segmentation frameworks are developed and trained on specific benchmark datasets, often rich of synthetic data, and when they are applied to complex and real-world heritage scenarios they offer much lower accuracy than expected. In this work, we present and demonstrate an early and late fusion of methods for semantic segmentation in cultural heritage applications. We rely on image datasets, point clouds and BIM models. The early fusion utilizes multi-view rendering to generate RGBD imagery of the scene. In contrast, the late fusion approach merges image-based segmentation with a Point Transformer applied to point clouds. Two scenarios are considered and inference results show that predictions are primarily influenced by whether the scene has a predominantly geometric or texture-based signature, underscoring the necessity of fusion methods. © 2024 International Society for Photogrammetry and Remote Sensing. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Four-dimensional conserved topological charge vectors in plasmonic quasicrystals

引用

science (New York, N.Y.) 2025年第6734期387卷 644-648页

作者： Tsesses, Shai Dreher, Pascal Janoschka, David Neuhaus, Alexander Cohen, Kobi Meiler, Tim C. Bucher, Tomer Sapir, Shay Frank, Bettina Davis, Timothy J. Meyer Zu Heringdorf, Frank Giessen, Harald Bartal, Guy rew and Erna Viterbi Department of Electrical and Computer Engineering Technion - Israel Institute of Technology Haifa Israel Department of Physics MIT-Harvard Center for Ultracold Atoms and Research Laboratory of Electronics Massachusetts Institute of Technology Cambridge MA United States Faculty of Physics and Center for Nanointegration University of Duisburg-Essen Duisburg-Essen (CENIDE) Duisburg Germany 4th Physics Institute Research Center SCoPE Integrated Quantum Science and Technology Center University of Stuttgart Stuttgart Germany Centre for Disruptive Photonic Technologies and School of Physical and Mathematical Sciences Nanyang Technological University Singapore Faculty of Mathematics and Computer Science Weitzmann Institute of Science Rehovot Israel School of Physics University of Melbourne Parkville VIC Australia

According to Noether's theorem, symmetries in a physical system are intertwined with conserved quantities. These symmetries often determine the system topology, which is made ever more complex with increased dimensionality. Quasicrystals have neither translational nor global rotational symmetry, yet they intrinsically inhabit a higher-dimensional space in which symmetry resurfaces. Here, we discovered topological charge vectors in four dimensions (4D) that govern the real-space topology of 2D quasicrystals and reveal their inherent conservation laws. We demonstrate control over the topology in pentagonal plasmonic quasilattices, mapped by both phase-resolved and time-domain near-field microscopy, showing that their temporal evolution continuously tunes the 2D projections of their distinct 4D topologies. Our work provides a route to experimentally probe the thermodynamic properties of quasicrystals and topological physics in 4D and above.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ultra-Accurate Time Dissemination in a Hybrid Fiber-Optic System with Frequency-Synchronized Lasers and λ-Swapping

Ultra-Accurate Time Dissemination in a Hybrid Fiber-Optic Sy...

引用

IEEE International Frequency Control Symposium

作者： Ł. Śliwczyński P. Krehlik Ł. Buczek Faculty of Computer Science Electronics and Telecommunications AGH University of Science and Technology Kraków Poland

Summary The accuracy of the wavelengths of lasers used in a fiber optic long-distance time transfer systems need to be at the level of some tens of MHz, if the transfer uncertainty at the level of picoseconds is expected at the distances spanning hundreds of kilometers. Such level of accuracy is difficult to obtain using a typical technology exploiting telecom-grade wavelength lockers based on Fabry-Perot etalons. We propose to solve this problem in a hybrid fiber optic transfer system, where the lasers used for time transfer are frequency-locked to a stable optical carrier, which also is simultaneously transmitted in the same fiber. Proposed method makes the time transfer uncertainty practically unaffected by the chromatic dispersion of the fiber link.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Interplay between extended s-wave symmetry of the gap and spin-orbit coupling in the low electron concentration regime of quasi-two-dimensional superconductors

引用

Physical Review B 2022年第18期106卷 184508-184508页

作者： M. Zegrodnik P. Wójcik Academic Centre for Materials and Nanotechnology AGH University of Science and Technology Aleja Mickiewicza 30 30-059 Krakow Poland AGH University of Science and Technology Faculty of Physics and Applied Computer Science al. A. Mickiewicza 30 30-059 Krakow Poland

We analyze the real-space paired state with the k-dependent superconducting gap in the presence of Rashba-type spin-orbit coupling and external magnetic field. We show that the extended s-wave pairing symmetry is the most probable scenario to appear in the low electron concentration regime. According to our study, the van Hove singularity induced by the spin-orbit coupling may lead to a significant enhancement of the superconducting gap, critical temperature, and critical magnetic field. Moreover, the combined effect of the spin-orbit coupling and the external magnetic field results in a nonzero total momentum of the Cooper pairs, which is a characteristic feature of the so-called helical state. In such a situation, due to the C4 symmetry breaking, a small d-wave and p-wave contributions to the pairing appear, which significantly change the character of the helical state. The obtained results are discussed in the context of the experimental data related with the unconventional superconducting features of the transition metal oxide interfaces as well as the recently reported supercurrent diode effect.

关键词： FFLO Spin-orbit coupling Superconducting order parameter Superconductivity Superconductors 2-dimensional systems Two-dimensional electron system Unconventional superconductors Lattice models in condensed matter

来源：评论

学校读者我要写书评

暂无评论

Energy Theft Identification Using Adaboost Ensembler in the Smart Grids

引用

computers, Materials & Continua 2022年第7期72卷 2141-2158页

作者： Muhammad Irfan Nasir Ayub Faisal Althobiani Zain Ali Muhammad Idrees Saeed Ullah Saifur Rahman Abdullah Saeed Alwadie Saleh Mohammed Ghonaim Hesham Abdushkour Fahad Salem Alkahtani Samar Alqhtani Piotr Gas Electrical Engineering Department College of EngineeringNajran University Saudi ArabiaNajran61441Saudi Arabia Department of Computer Science Federal Urdu University of Science and TechnologyIslamabad44000Pakistan Faculty of Maritime Studies King Abdulaziz UniversityJeddah21589Saudi Arabia Department of Electrical Engineering HITEC UniversityTaxila47080Pakistan Department of Computer Science and Engineering University of Engineering and TechnologyNarowal CampusLahore54000Pakistan College of Computer Science and Information Systems Najran UniversityNajran61441Saudi Arabia Department of Electrical and Power Engineering AGH University of Science and Technology Mickiewicza 30 AvenueKrakow30-059Poland

One of the major concerns for the utilities in the Smart Grid(SG)is electricity *** the implementation of smart meters,the frequency of energy usage and data collection from smart homes has increased,which makes it possible for advanced data analysis that was not previously *** this purpose,we have taken historical data of energy thieves and normal *** avoid imbalance observation,biased estimates,we applied the interpolation ***,the data unbalancing issue is resolved in this paper by Nearmiss undersampling technique and makes the data suitable for further *** proposing an improved version of Zeiler and Fergus Net(ZFNet)as a feature extraction approach,we had able to reduce the model’s time *** minimize the overfitting issues,increase the training accuracy and reduce the training loss,we have proposed an enhanced method by merging Adaptive Boosting(AdaBoost)classifier with Coronavirus Herd Immunity Optimizer(CHIO)and Forensic based Investigation Optimizer(FBIO).In terms of low computational complexity,minimized over-fitting problems on a large quantity of data,reduced training time and training loss and increased training accuracy,our model outperforms the benchmark *** proposed algorithms Ada-CHIO andAda-FBIO,have the low MeanAverage Percentage Error(MAPE)value of error,i.e.,6.8%and 9.5%,***,due to the stability of our model our proposed algorithms Ada-CHIO and Ada-FBIO have achieved the accuracy of 93%and 90%.Statistical analysis shows that the hypothesis we proved using statistics is authentic for the proposed technique against benchmark algorithms,which also depicts the superiority of our proposed techniques.

关键词： Smart grids and meters electricity theft detection machine learning AdaBoost optimization techniques

来源：评论

学校读者我要写书评

暂无评论

Estimation of River Water Surface Elevation Using UAV Photogrammetry and Machine Learning

arXiv

引用

arXiv 2023年

作者： Szostak, Radoslaw Pietroń, Marcin Wachniew, Przemyslaw Zimnoch, Miroslaw Ćwiąkala, Pawel AGH University of Science and Technology Faculty of Physics and Applied Computer Science ul. Reymonta 19 building D-10 Kraków Poland AGH University of Science and Technology Faculty of Computer Science Electronics and Telecommunications al. Mickiewicza 30 building D-17 Krakow Poland AGH University of Science and Technology Faculty of Geo-Data Science Geodesy and Environmental Engineering al. Mickiewicza 30 building C-4 Krakow Poland

Unmanned aerial vehicle (UAV) photogrammetry allows for the creation of orthophotos and digital surface models (DSMs) of a terrain. However, DSMs of water bodies mapped with this technique reveal water surface distortions, preventing the use of photogrammetric data for accurate determination of water surface elevation (WSE). Firstly, we propose a new solution in which a deep learning (DL) convolutional neural network (CNN) is used as a WSE estimator from photogrammetric DSMs and orthophotos. Second, we improved the previously known "water-edge" method by filtering the outliers using a forward-backwards exponential weighted moving average (FBEWMA). An additional improvement in these two methods was achieved by performing a linear regression of the WSE values against chainage. Furthermore, the solutions estimate the uncertainty of the predictions, which allows the evaluation of the model credibility when the ground-truth values are unknown. To our knowledge, this is the first approach in which DL was used for this task. A brand new machine learning data set has been created for the purpose of this work. It was collected on a small lowland river in winter and summer conditions. It consists of 322 samples, each corresponding to a 10 by 10 meter area of the river channel and adjacent land. Each data set sample contains orthophoto and DSM arrays as input, along with a single ground-truth WSE value as output. The data set was supplemented with data collected by other researchers that compared the state-of-the-art methods for determining WSE using an UAV. This makes these additional data an excellent benchmark to compare the method developed with existing ones. The results of the DL solution were verified using the reliable k-fold cross-validation method, in which samples from a single survey campaign were excluded from training and used as a validation subset. This provided an in-depth examination of the model's ability to perform on previously unseen data. The WSE RMSE va

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Unique Properties of the Electronic Structure of Alluaudite Sodium Iron Sulfate Cathode Material and the Impact on its Electrochemical Performance

SSRN

引用

SSRN 2025年

作者： Molenda, Janina Tobola, Janusz Milewska, Anna Budziak, Andrzej Zając, Wojciech Wolczko, Marta Dziedzic-Kocurek, Katarzyna Nowak, Mikolaj Kalahurska, Katarzyna Imam, Neama Henkel, Karsten Flege, Jan Ingo Zschech, Ehrenfried Dresden University of Technology Germany AGH University of Krakow Faculty of Energy and Fuels Al. Mickiewicza 30 Krakow30-059 Poland AGH University of Krakow Faculty of Physics and Applied Computer Science Al. Mickiewicza 30 Krakow30-059 Poland Jagiellonian University Faculty of Physics Astronomy and Applied Computer Science ul. S. Lojasiewicza 11 Krakow30-348 Poland Brandenburg University of Technology Cottbus-Senftenberg Institute of Physics Konrad-Zuse-Str. 1 Cottbus03046 Germany

This work explores the unique properties of the electronic structure of alluaudite-type Na2.5Fe1.75(SO4)3, which impacts its electrochemical properties as a cathode for sodium-ion batteries (SIBs). Density functional theory calculations using the implemented KKR-CPA package (Korringa-Kohn-Rostoker method combined with the coherent potential approximation) showed the diverse electrochemical activity of sodium at different sites within the alluaudite structure. This revealed unprecedented contributions of the Na atoms to the overall electronic density of states near the Fermi energy (dominated by d-Fe and p-O states), undetected before in the group of layered transition oxide cathode materials. A high-purity Na2.5Fe1.75(SO4)3 cathode material was synthesized by optimizing the solid-state synthesis route. Based on a multi-technique approach including: X-ray diffraction, scanning electron microscopy, Mössbauer, X-ray photoelectron, Fourier Transform Infrared, and Raman spectroscopy studies, the electronic structure and electrochemical properties of the cathode material and its evolution during the sodium deintercalation/intercalation processes have been characterized, providing a comprehensive understanding of the sodium storage mechanism. Operando and in-situ X-ray diffraction studies monitored changes in the crystal structure of the cathode material during charge/discharge cycles showing that the system exhibits a reversible tendency to amorphize at deep sodium deintercalation. The electrochemical analysis showed reversible cycling with minimal capacity loss (only 2.5% after 300 cycles at discharge at C/5 current loading), demonstrating high structural stability of this optimized cathode material. © 2025, The Authors. All rights reserved.

关键词： Sodium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

Influence of structural defects on charge density waves in 1T-TaS_(2)

引用

Nano Research 2023年第8期16卷 11528-11539页

作者： Iaroslav Lutsyk Karol Szalowski Pawel Krukowski Pawel Dabrowski Maciej Rogala Witold Kozlowski Maxime Le Ster Michal Piskorski Dorota A.Kowalczyk Wojciech Rys Rafal Dunal Aleksandra Nadolska Klaudia Toczek Przemyslaw Przybysz Ewa Lacinska Johannes Binder Andrzej Wysmolek Natalia Olszowska Jacek J.Kolodziej Martin Gmitra Takuma Hattori Yuji Kuwahara Guang Bian Tai-Chang Chiang Pawel J.Kowalczyk Faculty of Physics and Applied Informatics University of LodzPomorska 149/15390-236 LodzPoland Faculty of Physics University of WarsawPasteura 502-093 WarsawPoland Faculty of Physics Astronomyand Applied Computer ScienceJagiellonian UniversityLojasiewicza 1130-348 KrakowPoland National Synchrotron Radiation Centre SOLARIS Jagiellonian UniversityCzerwone Maki 9830-392 KrakówPoland Institute of Physics Faculty of SciencePavol JozefŠafárik University in KošicePark Angelinum 904001 KošiceSlovakia Institute of Experimental Physics Slovak Academy of SciencesWatsonova 4704001 KošiceSlovakia Department of Precision Engineering Graduate School of EngineeringOsaka University2-1 Yamada-okaSuita 565-0871Japan Department of Physics and Astronomy University of MissouriColumbiaMissouri 65211USA Department of Physics and Frederick Seitz Materials Research Laboratory University of Illinois at Urbana-ChampaignUrbanaIllinois 61801-3080USA

The influence of intrinsic defects of 1T-TaS_(2)on charge density waves(CDWs)is studied using scanning tunneling microscopy and spectroscopy(STM,STS),angle-resolved photoelectron spectroscopy(ARPES),and density functional theory(DFT).We identify several types of structural defects and find that most have a local character limited to a single CDW site,with a single exception which effectively behaves as a dopant,leading to band-bending and affecting multiple neighboring *** only one type of defect can be observed by STM topographic imaging,all defects are easily resolved in STS *** results indicate modulation of the Mott band gap commensurate with the CDW and breaking of the three-fold symmetry of electronic *** calculations(with included Coulomb interactions)are used to investigate the electronic structure,focusing on both sulfur vacancy and oxygen-sulfur *** sulfur vacancy system,characterized with a metallic behavior,is identified as the origin of one of the experimentally observed ***,the effect of oxidation of 1T-TaS_(2)depends on the substitution site,leading to the heterogeneity of electronic properties.

关键词： structural charge sulfur

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：