检索结果-内蒙古大学图书馆

DFE: Deep Flow Embedding for Robust Network Traffic Classification

学校读者我要写书评

暂无评论

IEEE Transactions on Network science and Engineering 2025年第3期12卷 1597-1612页

作者： Wang, Zhijiong Zhang, Anguo Li, Hung Chun Yin, Yadong Chen, Wei Lam, Chan Tong Mak, Peng Un Vai, Mang I. Gao, Yueming Pun, Sio Hang Zhuhai UM Science and Technology Research Institute Lingyange Semiconductor Incorporated Joint Laboratory Zhuhai519031 China Lingyange Semiconductor Inc. Zhuhai519030 China University of Macau State Key Laboratory of Analog and Mixed-Signal VLSI Institute of Microelectronics 999078 China Fuzhou University School of Physics and Information Engineering Fuzhou350108 China Fudan University Center for Intelligent Medical Electronics School of Information Science and Technology Human Phenome Institute Shanghai200437 China Fudan University Human Phenome Institute Shanghai200437 China Macau Polytechnic University Faculty of Applied Sciences 999078 China University of Macau Department of Electrical and Computer Engineering Faculty of Science and Technology 999078 China Fuzhou University Key Lab of Medical Instrumentation and Pharmaceutical Technology of Fujian Province Fuzhou350108 China

People's increasing demand for high-quality network services has prompted the continuous attention and development of network traffic classification (NTC). In recent years, deep flow inspection (DFI) is considered to be the most effective and promising method to solve the NTC. However, DFI still cannot effectively address the problem of changes in flow characteristics of complex packet flows and the discovery of new traffic categories. In this paper, we propose a metric learning based deep learning solution with feature compressor, named deep flow embedding (DFE). The feature compressor is used to compress the feature information transmitted layer by layer in DL backbone while maintaining the computational accuracy, so that the backbone can remove as much noise, redundancy, and other irrelevant information from the input data as possible, and achieve more robust feature extraction of network traffic flow. The deep learning (DL) backbone generates an embedding vector for each network packet flow. Then the embedding vector is compared with the vector template preset for each traffic type in the template library to determine the category of the packet flow. Experimental results verify that our method is more effective than the traditional DFI methods in overcoming the problems of flow characteristics variation and new category discovery. © 2013 IEEE.

关键词： Network embeddings

Quasi-two-dimensional magnetism and antiferromagnetic ground state in Li2FeSiO4

学校读者我要写书评

暂无评论

Physical Review B 2025年第2期111卷 024414-024414页

作者： W. Hergett N. Bouldi M. Jonak C. Neef C. Ritter M. Abdel-Hafiez F. Seewald H.-H. Klauss M. W. Haverkort Kirchhoff Institute of Physics Heidelberg University INF 227 D-69120 Heidelberg Germany Institute for Theoretical Physics Heidelberg University D-69120 Heidelberg Germany Institut Laue-Langevin 38042 Grenoble France Physics Department Faculty of Science Fayoum University Fayoum 63514 Egypt Department of Applied Physics and Astronomy University of Sharjah P. O. Box 27272 Sharjah United Arab Emirates Institute for Solid State and Materials Physics TU Dresden D-01069 Dresden Germany

Our experimental (neutron diffraction, Mössbauer spectroscopy, magnetic susceptibility, specific heat) and numerical studies on the evolution of short- and long-range magnetic order in γII−Li2FeSiO4 suggest a quasi-two-dimensional (2D) nature of magnetism. The experimental data obtained on single crystals imply long-range antiferromagnetic order below TN=17 K. A broad maximum in magnetic susceptibility χ at Tm≃28 K, observation of magnetic entropy changes up to 100 K, and anisotropy in χ are indicative of low-dimensional magnetism and suggest short-range magnetic correlations up to 200 K. Neutron diffraction shows that long-range antiferromagnetic order is characterized by the propagation vector k=(12,0,12). The ordered moment μ=2.50(2) μB/Fe, at T=1.5 K, is along the crystallographic a axis. This is consistent with the observed static hyperfine field of Bhyp=14.8(3)T by Mössbauer spectroscopy which indicates significant orbital contributions. The temperature dependence of Bhyp yields the critical exponent β=0.116(12) which is in the regime of the 2D Ising behavior. LSDA+U studies exploiting the experimental spin structure suggest dominating magnetic exchange coupling within the ac layers (i.e., J3≃−6 K and J6≃−2 K) while interlayer coupling is much smaller and partly frustrated. This confirms the 2D nature of magnetism and is in full agreement with the experimental findings.

关键词： Neutron diffraction

Spin-lattice relaxation of NV centers in nanodiamonds adsorbed on conducting and non-conducting surfaces

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Benedičič, Izidor Tanuma, Yuri Gosar, Žiga Anézo, Bastien Mrózek, Mariusz Wojciechowski, Adam Arčon, Denis Jožef Stefan Institute Jamova c. 39 Ljubljana1000 Slovenia Faculty of Mathematics and Physics University of Ljubljana Jadranska c. 19 Ljubljana1000 Slovenia Nantes University 2 Rue de la Houssinière Nantes France Faculty of Physics Astronomy and Applied Computer Science Jagiellonian University Prof. S. Lojasiewicza 11 Krakow30-348 Poland

The nitrogen-vacancy (NV) centers in nanodiamonds can be utilized as low-cost, highly versatile quantum sensors for studying surface properties in condensed matter physics through the application of relaxometry protocols. For such applications, a detailed knowledge of the intrinsic relaxation processes of NV centers in nanodiamonds is necessary. Here, we study the spin-lattice relaxation rates of NV ensembles in nanodiamonds with average diameters of 40 nm and 3 µm between room temperature and ∼ 6 K. The NV relaxation curves fit to a stretched-exponential form with a stretching exponent α ≈ 0.7, implying the large distribution of relaxation times of individual centers within nanodiamonds. We determine the Orbach-like scattering on phonons as the leading relaxation mechanism. Finally, we discuss the viability of nanodiamonds as surface sensors when deposited on a metallic substrate and emphasize the need for well-controlled surface preparation techniques. © 2025, CC BY.

关键词： Spin-lattice relaxation

Quasi Q-Balls in massless scalar fields

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Romańczukiewicz, Tomasz Shnir, Yakov Faculty of Theoretical Physics Astronomy and Applied Computer Science Jagiellonian University Kraków Poland Instituto de Física de São Carlos IFSC/USP Universidade de São Paulo USP Caixa Postal 369 São Carlos-SPCEP 13560-970 Brazil

We study long-term evolution of radiating quasi-Q-balls in 1+1 dimensional models without mass threshold. Two different models are considered, the model with a rational modification of the usual Q-ball sextic potential and the model of a Q-ball in a box with outgoing boundary conditions. We find that the outgoing boundary conditions modify the angular frequency of quasi-Q-balls which becomes complex-valued. The quasi-Q-balls decay initially very similarly, but in the last stage quasi-Q-balls in a box become linear resonances, whereas in the rationally modified model, they decay according to some power law. © 2025, CC BY.

关键词：

Compressive quantum waveform estimation

学校读者我要写书评

暂无评论

Physical Review A 2025年第2期111卷 022625-022625页

作者： Alex Tritt Joshua Morris Christopher C. Bounds Hamish A. M. Taylor James Saunderson L. D. Turner School of Physics and Astronomy Monash University Victoria 3800 Australia Present address: Vienna Center for Quantum Science and Technology Faculty of Physics University of Vienna 1010 Vienna Austria. Present address: 5 Physikalisches Institut Center for Integrated Quantum Science and Technology Universität Stuttgart Pfaffenwaldring 57 70569 Stuttgart Germany. Department of Electrical and Computer Systems Engineering Monash University Victoria 3800 Australia

Quantum waveform estimation, in which quantum sensors sample entire time series, promises to revolutionize the sensing of weak and stochastic signals, such as the biomagnetic impulses emitted by firing neurons. For long duration waveforms with rapid transients, regular quantum sampling becomes prohibitively resource intensive as it demands many measurements with distinct control and readout. In this paper, we demonstrate how careful choice of quantum measurements, along with the modern mathematics of compressive sensing, achieves quantum waveform estimation of sparse signals in a number of measurements far below the Nyquist requirement. We sense synthesized neural-like magnetic waveforms with radio-frequency-dressed ultracold atoms, retrieving successful waveform estimates with as few measurements as compressive theoretical bounds guarantee.

关键词： Waveform analysis

Classification of pair symmetries in superconductors with unconventional magnetism

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Maeda, Kazuki Fukaya, Yuri Yada, Keiji Lu, Bo Tanaka, Yukio Cayao, Jorge Department of Applied Physics Nagoya University Nagoya464-8603 Japan Faculty of Environmental Life Natural Science and Technology Okayama University Okayama700-8530 Japan Department of Physics Tianjin University Tianjin300354 China Department of Physics and Astronomy Uppsala University Box 516 UppsalaS-751 20 Sweden

We consider superconductors with unconventional magnetism and investigate the emergence of superconducting correlations by carrying out a full classification of allowed Cooper pair symmetries. In particular, we focus on spin-singlet and spin-triplet superconductors under the influence of dwave altermagnets and p-wave magnets. Under generic conditions, we find that unconventional magnets not only drive a spin-singlet to spin-triplet conversion but also they transfer their parity symmetry that induces superconducting correlations with higher angular momentum. For instance, a conventional spin-singlet s-wave superconductor with d-wave altermagnetism is able to host odd-frequency mixed spin-triplet d-wave superconducting pair amplitudes, while when combining with pwave magnetism the emerging superconducting pairing acquires an even-frequency mixed spin-triplet p-wave symmetry. We further demonstrate that unconventional magnetism produces even more exotic superconducting correlations in spin-singlet d-wave superconductors, where odd-frequency mixed spin-triplet g-wave and even-frequency mixed spin-triplet f-wave pair symmetries are possible in altermagnets and p-wave magnets, respectively. We also discuss how these ideas generalize to spin-triplet p-wave superconductors and also show how our results can be applied to unconventional magnets with higher angular momentum, such as f-, g-, and i-wave. Our results can help understand the emergent superconducting correlations due to the interplay of unconventional magnetism and superconductivity. © 2025, CC BY-NC-SA.

关键词： Shear waves

Explainable Machine Learning for Radio Environment Mapping: An Intelligent System for Electric Field Strength Monitoring

学校读者我要写书评

暂无评论

IEEE Access 2025年 13卷 75100-75118页

作者： Kiouvrekis, Yiannis Panagiotakopoulos, Theodor Nousi, Efthymia Filippopoulos, Ioannis Ploussi, Agapi Spyratou, Ellas Efstathopoulos, Efstathios P. University of Thessaly Mathematics Computer Science and Artificial Intelligence Laboratory Faculty of Public and One Health Karditsa43100 Greece University of Limassol Department of Information Technologies Limassol3020 Cyprus University of Nicosia Business School Nicosia2417 Cyprus University of Patras Department of Management Science and Technology Patras26334 Greece Infralabs Ltd. Nicosia1107 Cyprus University of Limassol Technology And Innovation School Limassol3020 Cyprus National and Kapodistrian University of Athens Medical School Department of Applied Medical Physics Athens11527 Greece

The accurate characterization of signal propagation is critical for optimizing wireless network performance and supporting applications such as electromagnetic field (EMF) exposure assessment and the development of Radio Environmental Maps (REMs). This study proposes a novel, explainable machine learning system to predict electric field strength across diverse urban, semi urban, and rural environments in Cyprus. The system is trained on a rich dataset comprising 6,543 EMF measurements collected in 2023 at mobile phone and digital TV stations, following CEPT/ECC/REC/(02)04 recommendations. The dataset includes geospatial and environmental features such as antenna distance, population density, urbanization level, and detailed built environment characteristics (e.g., volume, surface, and height). We evaluate multiple machine learning models—kNN, neural networks, decision trees, random forests, XGBoost, and LightGBM—using a two-semester split for training and assessment. Best performance was achieved with the Random Forest model, which yielded the lowest RMSE among all models. Gradient boosting models (XGBoost and LightGBM) also performed well, with RMSE values slightly higher than RF while offering flexible and scalable configurations. In contrast, k-NN and neural networks showed higher RMSE values, indicating they were less effective for this specific task. Across all models, confidence intervals were narrow, demonstrating stable and reliable predictions. Explainable AI techniques revealed that antenna distance, building volume, and population density are the most influential predictors of EMF intensity. Our approach outperforms traditional signal models by incorporating urban morphology and demographic context. As part of this system, we also create a Geographic Information System (GIS) that displays electromagnetic field strength maps derived from our explainable machine learning models. This contributes a scalable, interpretable framework for EMF exposure mapping t

关键词： Machine learning Predictive models Radio frequency Accuracy Electric fields Random forests Population density Explainable AI Estimation Buildings

Lattice Protein Folding with Variational Annealing

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Khandoker, Shoummo A. Inack, Estelle M. Hibat-Allah, Mohamed Department of Computer Science Indiana University-Bloomington BloomingtonIN47405 United States Perimeter Institute for Theoretical Physics WaterlooON Canada yiyaniQ TorontoON Canada Department of Physics and Astronomy University of Waterloo WaterlooON Canada Department of Applied Mathematics University of Waterloo WaterlooON Canada Vector Institute TorontoON Canada

Understanding the principles of protein folding is a cornerstone of computational biology, with implications for drug design, bioengineering, and the understanding of fundamental biological processes. Lattice protein folding models offer a simplified yet powerful framework for studying the complexities of protein folding, enabling the exploration of energetically optimal folds under constrained conditions. However, finding these optimal folds is a computationally challenging combinatorial optimization problem. In this work, we introduce a novel upper-bound training scheme that employs masking to identify the lowest-energy folds in two-dimensional Hydrophobic-Polar (HP) lattice protein folding. By leveraging Dilated Recurrent Neural Networks (RNNs) integrated with an annealing process driven by temperature-like fluctuations, our method accurately predicts optimal folds for benchmark systems of up to 60 beads. Our approach also effectively masks invalid folds from being sampled without compromising the autoregressive sampling properties of RNNs. This scheme is generalizable to three spatial dimensions and can be extended to lattice protein models with larger alphabets. Our findings emphasize the potential of advanced machine learning techniques in tackling complex protein folding problems and a broader class of constrained combinatorial optimization challenges. Copyright © 2025, The Authors. All rights reserved.

关键词： Protein folding

Performance Comparison of Various Dual-Band AMC Structures Using Textile Materials

学校读者我要写书评

暂无评论

Performance Comparison of Various Dual-Band AMC Structures U...

International Electrical Engineering Congress (iEECON)

作者： Yotrawee Hengroemyat Wanwisa Thaiwirot Prayoot Akkaraekthalin Nonchanutt Chudpooti Department of Electrical and Computer Engineering Faculty of Engineering King Mongkut’s University of Technology North Bangkok Bangkok Thailand Department of Industrial Physics and Medical Instrumentation Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798331543952

ISBN: (纸本)9798331543969

This paper presents the performance comparison of various dual-band AMC structures using textile materials. The textile AMC structure includes of the inner patch and outer loop to achieve dual-band operation. The felt is used as substrate of AMC unit cell while the copper-nickel plated polyester fabric is used as conductive parts. The various geometries of AMC unit cell based on square, circle, hexagon, octagon shapes are designed to operate at 2.4/5.5 GHz for WBAN and Wi-Fi applications. Moreover, the performance of AMC unit cell structures is compared in term of size and bandwidth. It is found from simulation results that the inner square patch and outer square loop can provide compact size and wider bandwidth. The hexagon shape can achieve compact size when it is arranged in form of array.

关键词： Geometry Wireless communication Shape Simulation Dual band Bandwidth Reflector antennas Substrates Wireless fidelity Textiles