检索结果-内蒙古大学图书馆

CIRED 2024 Vienna Workshop

作者： María Carmen Ruiz-Abellón Luis A. Fernández-Jiménez Antonio Guillamón Antonio Gabaldón Department of Applied Mathematics and Statistics Technical University of Cartagena Cartagena Spain Department Of Electrical Engineering University de La Rioja La Rioja Spain Electrical Engineering Area Technical University of Cartagena Cartagena Spain

ISBN: (数字)9781837241224

Load Forecasting usually deals with the point prediction of electricity consumption at different aggregation levels. Although the literature in this field is broad, it is quite small if we refer to the probabilistic prediction of demand, which might be particularly useful in operation and planning. In this paper, authors show some applications of probabilistic prediction in Demand Response. Quantile Regression Forest, a machine learning technique, is applied to obtain the quantiles of the conditional distribution function giving a set of probabilistic forecasts. From these predictions, demand flexibility strategies are proposed to reduce the incertitude of forecasts. Possibilities are analyzed considering Physical-Based Load Model to evaluate the potential of demand flexibility of two end-uses: Water Heating and Electric Heating. The proposal is illustrated with hourly demand data from a small Spanish city (around 5 MW of peak demand), assuming the partial control of both loads.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SSMIF: Enhanced Spatial-Spectral Mamba Interactive Fusion Network for Hyperspectral Change Detection

SSMIF: Enhanced Spatial-Spectral Mamba Interactive Fusion Ne...

引用

Signal, Information and Data Processing (ICSIDP), IEEE International Conference on

作者： Lanxin Wu Jiangtao Peng Bing Yang Weiwei Sun Zhijing Ye Hubei Key Laboratory of Applied Mathematics Faculty of Mathematics and Statistics Hubei University China College of Sciences China Jiliang University China Department of Geography and Spatial Information Techniques Ningbo University China Faculty of Innovation Engineering Macau University of Science and Technology

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Change detection (CD) in remote sensing images is a complex task. Recent advancements in convolutional neural networks (CNNs) and transformer-based methods have significantly improved CD accuracy. However, hyperspectral image (HSI) CD remains particularly challenging, especially in terms of change feature extraction and fusion. In this paper, we present an enhanced spatial-spectral mamba interactive fusion (SSMIF) network specifically designed for HSI CD. This network incorporates the state space model (SSM) and flow alignment techniques to extract and fuse features more effectively. In particular, the spatial and spectral mamba (SASM) model is employed to capture spatial and spectral features from bi-temporal HSIs. Furthermore, we introduce a bi-temporal flow alignment (BFA) method to resample images for improved feature alignment. An additional long short-term memory (LSTM) module is used to filter important features and reduce redundancy. Experimental results on HSI CD datasets show that the proposed SSMIF network consistently outperforms several state-of-the-art approaches. The source code of the proposed SSMIF will be released at https://***/creativeXin/SSMIF.

关键词： Accuracy Source coding Noise Termination of employment Interference Feature extraction Transformers Data models Long short term memory Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

On modeling and forecasting the stock risk using a new statistical distribution and time series models

引用

Alexandria engineering Journal 2025年 122卷 65-76页

作者： Yan, Lelin Zhou, Weihong Odhah, Omalsad Hamood Widyan, Adel M. Khalifa, Hamiden Abd El-Wahed Alqahtani, Haifa College of Information Science and Engineering Qilu Normal University Jinan 250013 Shandong China Master of Social Work Party School of Hunan Provincial Committee of C.P.C Hunan Changsha 410006 China Department of Mathematical Sciences College of Science Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Department of Mathematics College of Science Qassim University Buraydah51452 Saudi Arabia Department of Statistics and Business Analytics United Arab Emirates University Al Ain Abu Dhabi15551 United Arab Emirates

The value of probability distributions in reflecting practical events, especially in financial risk, is significant. The flexible Weibull extension distribution, recognized as a significant modification of the Weibull distribution, serves as a foundational distribution in our study. Thus, we present a new distribution known as the sine cosine flexible Weibull extension (SCFWE) distribution. We conduct a detailed study of the mathematical properties associated with the SCFWE distribution. We also detail the methodology for parameter estimation and present simulation studies that explore various combinations of parameter values. Furthermore, we analyze a practical data set that highlights the volatility of the financial market, thereby demonstrating the relevance of the SCFWE distribution within the financial sector. Furthermore, we use the traditional time series models such as the autoregressive (AR), autoregressive integrated moving average (ARIMA), and random walk for forecasting the stock volatility. Our findings show that ARIMA is the most accurate model having the lowest root mean squared error and mean absolute error, the AR performed poorly with the highest errors, while, the random walk showed moderate performance, but ARIMA emerged as the most reliable model for precise predictions. © 2025 The Authors

关键词： Flexible Weibull extension Sine function Cosine function Volatility Financial risk Time series models Statistical analysis Data set

来源：评论

学校读者我要写书评

暂无评论

Emergence of elastic chiral Landau levels and snake states

引用

Physical Review B 2024年第18期109卷 184109-184109页

作者： Shuaifeng Li Panayotis G. Kevrekidis Jinkyu Yang Department of Aeronautics and Astronautics University of Washington Seattle Washington 98105 USA Department of Physics University of Michigan Ann Arbor Michigan 48109 USA Department of Mathematics and Statistics University of Massachusetts Amherst Massachusetts 01003 USA Department of Mechanical Engineering Seoul National University Seoul 08826 Republic of Korea

In this paper, we present a method for generating a synthetic gauge field in the vertical direction by linearly modulating the mass term in a Dirac equation model. This allows for the quantization of Landau levels through the generated pseudomagnetic field, with the chiral zeroth Landau level being topologically protected. An elastic snake state is realized using the coupling between the zeroth and the first Landau levels. For demonstration, our theoretical predictions are realized numerically in an elastic medium of truss structures arranged in a honeycomb lattice. Our results, supported by theory and simulations, establish a framework for generating pseudomagnetic fields in elastic systems with potential applications in waveguides and cloaking.

关键词： Landau levels Origami & Kirigami Metamaterials Bloch wave theory k dot p method

来源：评论

学校读者我要写书评

暂无评论

A radial basis scale conjugate gradient neural network process for the Zika model with human movement and reservoirs

引用

Chaos, Solitons and Fractals 2025年 199卷

作者： Sabir, Zulqurnain Souayeh, Basma Umar, Muhammad Salahshour, Soheil Alfannakh, Huda Suresh Kumar Raju, S. Department of Computer Science and Mathematics Lebanese American University Lebanon Department of Physics College of Science King Faisal University PO Box 400 Al-Ahsa31982 Saudi Arabia Faculty of Engineering and Natural Sciences Istanbul Okan University Istanbul Turkey Faculty of Engineering and Natural Sciences Bahcesehir University Istanbul Turkey Department of Mathematics and Statistics College of Science King Faisal University Al-Ahsa31982 Saudi Arabia

The purpose of current research is to find the numerical solutions of the nonlinear Zika model with human movement and reservoirs (ZMHMR) by designing a novel radial basis scale conjugate gradient neural network (RB-SCGNN). This nonlinear model contains ten different groups, and the numerical solutions are presented by the stochastic RB-SCGNN process. A design of dataset is presented through the Runge-Kutta scheme to lessen the values of the mean square error by splitting the data into training as 72 %, while 14 %, 14 % for both verification and testing. Fifteen neurons in the hidden layers, single input, and radial basis activation function are used to solve the ZMHMR. The accuracy of the proposed scheme is judged through the overlapping of the outputs, whereas smaller values of the absolute error indicate the exactness of the RB-SCGNN. Additionally, the statistical representations using different operators validate the approach's trustworthiness. © 2025 Elsevier Ltd

关键词： Runge Kutta methods

来源：评论

学校读者我要写书评

暂无评论

Leveraging Large Language Models for Dynamic Scenario Building targeting Enhanced Cyber-threat Detection and Security Training

Leveraging Large Language Models for Dynamic Scenario Buildi...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Marantos, Charalampos Evangelatos, Spyridon Veroni, Eleni Lalas, George Chasapas, Konstantinos Christou, Ioannis T. Lappas, Pantelis Netcompany-Intrasoft S.A. Research & Innovation Development Department Luxembourg Luxembourg Hellenic Mediterranean University Dept. of Electronic Engineering Crete Greece The American College of Greece School of Liberal Arts & Sciences Dept. of Information Technology Athens Greece University of the Aegean Dept. of Statistics and Actuarial-Financial Mathematics Samos Greece

ISBN: (纸本)9798350362480

As cybercrime is becoming increasingly sophisticated, effective cybersecurity is crucial to safeguard digital assets and protect critical infrastructures from emerging threats. Several security applications exploit recent advances in (Big) data analysis and Artificial Intelligence (AI) to prevent and respond to malicious activities. Towards this direction, supervised and unsupervised Machine Learning (ML) methods are used to detect anomalies or reveal patterns that may indicate potential threats. However, the successful implementation of these technologies requires security practitioners to undergo specialized training to fully understand and use AI-driven tools and data analytics. On the other hand, AI models themselves are vulnerable to a variety of cyber threats, which can compromise their training data and learning processes. To ensure the safe operation of these systems, especially when deployed in adversarial environments, it is crucial to create novel AI adversarial algorithms and models that are resilient against diverse security threats. This work presents a conceptual framework based on Large Language Models (LLMs) supported by a Multi-Agent layer for training of security practitioners in various advanced technologies and enhance ML models ability to detect and respond to emerging cyber threats effectively. © 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

On the Dominant Local Metric Dimension of Corona Product Graphs

引用

IAENG International Journal of Applied mathematics 2022年第4期52卷 1页

作者： Umilasari, Reni Susilowati, Liliek Slamin Prabhu, Savari Mathematics Department Airlangga University Indonesia Study Program of Informatics Jember University Indonesia Mathematics Department Rajalakshmi Engineering College Tamil Nadu Chennai602105 India

A nontrivial connected graph T which one of the vertex is v, v is said to distinguish two vertex u;t if the distance between v and u is different from v to t, where u,t (Formula Presented) V (T). Metric dimension is one topic in graph theory that uses the concept of distance. Combining the definition of the local metric dimension and dominating set, there is a new term, we called it dominant local metric dimension and symbolized as Ddiml(T). An ordered subset Wl = {w1,w2,…,wn}(Formula Presented)V (T) is called a dominant local resolving set of T if Wl is a local resolving set as well as a dominating set of T. The goal of this paper’s research is to determine precise values of dominant local metric dimension for the corona product graphs. n copies of the graphs P1,P2,…,Pn of P are made to constructed the corona of any two graph T and P. After that, we link the i-th vertex of T to the vertices of Pi, where n is an order of graph T. T corona P is symbolized by T(Formula Presented)P. © 2022,IAENG International Journal of Applied mathematics. All Rights Reserved.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Click-Through Rate Prediction Models based on Interest Modeling 5

Click-Through Rate Prediction Models based on Interest Model...

引用

5th International Conference on Big Data engineering, BDE 2023

作者： Luo, Zhen Zhang, Yingfang Hu, Chengxuan Xia, Yuxuan Zhu, Shengxin Department of Statistical Science University College London United Kingdom Department of Statistics and Actuarial Science University of Hong Kong Hong Kong Hong Kong Department of Industrial and Systems Engineering Polytechnic University of Hong Kong Hong Kong Hong Kong School of Mathematics University of Southampton United Kingdom Research Center for Mathematics Advanced Institute of Natural Science Beijing Normal University Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science BNU-HKBU United International College China

ISBN: (纸本)9798400708695

Deep learning frameworks have achieved extraordinary results in popular technological frontiers, which also greatly inspires considerable researchers in recommender system. As one of the mainstream research frontiers, click-through rate (CTR) predictions have received increasing attention from both industrial and academic circles. Recently, Alibaba group has come up with novel idea of interest modeling that can effectively overcome the limitations brought by previous deep learning CTR prediction models, which is also the key to improve performance. For the past few years, more and more relevant works begin to explore approaches taking advantage of the learning, representation, and interpretation ability from neural networks. However, there are few comprehensive surveys targeted at this topic. In this paper, we systematically review and summarize recent CTR prediction models based on interest modeling. First, we elaborate their different design ideas and pay additional attention to their intrinsic relationship including improvements and extensions, similarities and differences, advantages and disadvantages and so on. Next, we deploy them separately according to official open-source code and compare their performance assessment in terms of accuracy and speed, looking for best optimizers and other hyperparameters. Furthermore, we briefly discuss some possible refinement directions and future research trends. © 2023 ACM.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Lower General Position Sets in Graphs

arXiv

引用

arXiv 2023年

作者： Stefano, Gabriele Di Klavžar, Sandi Krishnakumar, Aditi Tuite, James Yero, Ismael Department of Information Engineering Computer Science and Mathematics University of L’Aquila Italy Faculty of Mathematics and Physics University of Ljubljana Slovenia Institute of Mathematics Physics and Mechanics Ljubljana Slovenia Faculty of Natural Sciences and Mathematics University of Maribor Slovenia Department of Mathematics and Statistics Open University Milton Keynes United Kingdom Departamento de Matemáticas Universidad de Cádiz Algeciras Spain

A subset S of vertices of a graph G is a general position set if no shortest path in G contains three or more vertices of S. In this paper, we generalise a problem of M. Gardner to graph theory by introducing the lower general position number gp−(G) of G, which is the number of vertices in a smallest maximal general position set of G. We show that gp−(G) = 2 if and only if G contains a universal line and determine this number for several classes of graphs, including Kneser graphs K(n,2), line graphs of complete graphs, and Cartesian and direct products of two complete graphs. We also prove several realisation results involving the lower general position number, the general position number and the geodetic number, and compare it with the lower version of the monophonic position number. We provide a sharp upper bound on the size of graphs with given lower general position number. Finally we demonstrate that the decision version of the lower general position problem is *** Codes 05C12, 05C69, 68Q25 © 2023, CC BY.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Revisiting Fuel Subsidies in Indonesia using K-Means, PAM, and CLARA

IAENG International Journal of Computer Science

引用

IAENG International Journal of Computer Science 2023年第3期50卷 858页

作者： Prasetyo, Fajar Agung Caraka, Rezzy Eko Kim, Yunho Goldameir, Noor Ell Sulistyowati Tyasti, Avia Enggar Gio, Prana Ugiana Anggoro, Faisal Ramadhani, Muthia Pardamean, Bens Faculty of Economics and Business Universitas Indonesia Indonesia Indonesia Department of Mathematics Ulsan National Institute of Science and Technology Korea Republic of Department of Mathematics Statistics Study Program Riau University Riau Pekanbaru Indonesia Institut Teknologi Adhi Tama Surabaya East Java Indonesia International Trade of ASEAN and RRT Region Polytechnic of APP DKI Jakarta Indonesia Department of Mathematics Universitas Sumatera Utara Medan20155 Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta Indonesia

Indonesia is one of the countries in the world that still applies subsidies for fuel oil. By the law, the Indonesian government must ensure the supply and distribution of fuel for all Indonesian people. To implement this policy properly, understanding the pattern of fuel consumption is fundamental. In this study, clustering will be used to determine the categories of districts and cities based on subsidized fuel consumption patterns. Our research used several methods to compare which cluster method is the most optimal;the methods include k-means, Partitioning Around Medoids (PAM), and Clustering Large Applications (CLARA). The results show that k-means is the best clustering method with the highest Dunn index and Silhouette coefficient compared to others. The optimum cluster number we get is two and represents fuel consumption from several districts and cities. Some districts and cities had under-average consumption and needed to be monitored. © (2023), (International Association of Engineers). All Rights Reserved.

关键词： K-means clustering

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：