检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Atashgahi, Zahra Liu, Tennison Pechenizkiy, Mykola Veldhuis, Raymond Mocanu, Decebal Constantin van der Schaar, Mihaela Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Netherlands Department of Applied Mathematics and Theoretical Physics University of Cambridge United Kingdom Department of Mathematics and Computer Science Eindhoven University of Technology Netherlands Department of Computer Science University of Luxembourg Luxembourg

Sparse Neural Networks (SNNs) have emerged as powerful tools for efficient feature selection. Leveraging the dynamic sparse training (DST) algorithms within SNNs has demonstrated promising feature selection capabilities while drastically reducing computational overheads. Despite these advancements, several critical aspects remain insufficiently explored for feature selection. Questions persist regarding the choice of the DST algorithm for network training, the choice of metric for ranking features/neurons, and the comparative performance of these methods across diverse datasets when compared to dense networks. This paper addresses these gaps by presenting a comprehensive systematic analysis of feature selection with sparse neural networks. Moreover, we introduce a novel metric considering sparse neural network characteristics, which is designed to quantify feature importance within the context of SNNs. Our findings show that feature selection with SNNs trained with DST algorithms can achieve, on average, more than 50% memory and 55% FLOPs reduction compared to the dense networks, while outperforming them in terms of the quality of the selected features. Our code and the supplementary material are available on GitHub (https://***/zahraatashgahi/Neuron-Attribution). © 2024, CC BY-SA.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Detecting 5G Signal Jammers with Autoencoders Based on Loose Observations

Detecting 5G Signal Jammers with Autoencoders Based on Loose...

引用

2023 IEEE Globecom Workshops, GC Wkshps 2023

作者： Varotto, Matteo Valentin, Stefan Tomasin, Stefano University of Padova Dep. of Information Engineering Padova Italy Darmstadt University of Applied Sciences Dep. of Computer Science Darmstadt Germany University of Padova Dep. of Information Engineering Dep. of Mathematics Padova Italy

ISBN: (纸本)9798350370218

Fifth-generation (5G) networks are prone to jamming attacks, which are particularly dangerous in mission-critical applications such as factory automation. In this paper, we present a simple method to detect jamming attacks with machine learning techniques operating on in-phase and quadrature (IQ) modulated signals. In particular, a convolutional autoencoder (CAE) learns the structure of the clean signal to distinguish it from jammed signals in real time. This approach requires only a loose synchronization to the OFDM symbol, while equalization and decoding are not necessary. Despite its simplicity, our technique has shown high detection rates in experiments on a 5G testbed. © 2023 IEEE.

关键词： 5G Convolutional Autoencoder IQ Signals Jamming Detection New Radio Wireless Intrusion Prevention

来源：评论

学校读者我要写书评

暂无评论

Asset Management Strategies for District Heating Networks

Asset Management Strategies for District Heating Networks

引用

International Conference on System Reliability and science (ICSRS)

作者： Jens Grønberg Maryamsadat Tahavori Peder Bacher DTU Engineering Technology Ballerup Denmark Department of Applied Mathematics and Computer Science DTU Kongens Lyngby Denmark

ISBN: (数字)9798350354508

ISBN: (纸本)9798350354515

District Heating (DH) became widely adopted in European cities during the 20th century to meet demand for heating from a growing urban population. Today, the desire to decarbonize Europe's heat consumption has lead to an renewed interest in increasing the adoption of DH. To meet this end, DH has to be a price competitive alternative to other heating technologies. Over time the underground heat distribution network that DH companies operate suffers from faults that require replacement of pipes. On-demand replacement is more expensive than planned large scale replacement projects. The only question is, when is the optimal time to renew the pipes? In this article this question will be formulated using Reliability Theory. Our approach is to use historical records of time to failure and a bounding result to estimate the optimal time for replacement. The method can be used by DH companies with historical fault records to form an Asset Management strategy on the question of when to renew which pipes.

关键词： Maximum likelihood estimation Costs District heating Urban areas Europe Companies Maintenance Asset management Steel Weibull distribution

来源：评论

学校读者我要写书评

暂无评论

Word2Minecraft: Generating 3D Game Levels through Large Language Models

arXiv

引用

arXiv 2025年

作者： Huang, Shuo Nasir, Muhammad Umair James, Steven Togelius, Julian Department of Computer Science and Engineering Tandon School of Engineering New York University New York10012 United States School of Computer Science and Applied Mathematics University of the Witwatersrand South Africa

We present Word2Minecraft, a system that leverages large language models to generate playable game levels in Minecraft based on structured stories. The system transforms narrative elements—such as protagonist goals, antagonist challenges, and environmental settings—into game levels with both spatial and gameplay constraints. We introduce a flexible framework that allows for the customization of story complexity, enabling dynamic level generation. The system employs a scaling algorithm to maintain spatial consistency while adapting key game elements. We evaluate Word2Minecraft using both metric-based and human-based methods. Our results show that GPT-4Turbo outperforms GPT-4o-Mini in most areas, including story coherence and objective enjoyment, while the latter excels in aesthetic appeal. We also demonstrate the system’s ability to generate levels with high map enjoyment, offering a promising step forward in the intersection of story generation and game design. We open-source the code at https://***/JMZkk/Word2Minecraft/tree/word2mc_v0 Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AHHO: Arithmetic Harris Hawks Optimization algorithm for demand side management in smart grids

引用

Discover Internet of Things 2023年第1期3卷 3页

作者： Manzoor, Awais Judge, Malik Ali Islam, Saif ul Neggaz, Nabil Abulaigh, Laith Ahmad, Ishfaq Department of Computer Science COMSATS University Islamabad Islamabad44550 Pakistan Department of Computer Sciences Institute of Space Technology Islamabad Pakistan Faculty of Mathematics and Computers University of Sciences and Technologies-USTO-MB Oran Algeria Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan Faculty of Information Technology Middle East University Amman11831 Jordan Department of Computer Science and Engineering The University of Texas at Arlington Arlington United States

Energy management strategies are crucial to efficiently scheduling appliances and preventing peak generation due to increased energy demand. It is essential to manage the demand and supply of energy based on the consumer’s consumption patterns using various heuristic optimization techniques. Additionally, the end-user is more concerned with minimizing electricity costs and reducing peak-to-average ratios (PARs). This work proposes an arithmetic Harris hawks optimization (AHHO) as a new approach for improving the Harris hawks algorithm to optimize residential demand response (DR) load management in a smart grid. Our method employs arithmetic and lightweight flight operators based on the Lévy flight distribution to generate diverse design solutions and improve the HHO’s exploration capabilities. We consider 15 smart appliances and categorize them based on how much energy they use, computing the electricity price using real-time pricing (RTP) and critical peak pricing (CPP). While maintaining user satisfaction within operational and power limits, the objective is to decrease energy costs and PAR. We evaluate the effectiveness of our proposed AHHO approach against nine cutting-edge algorithms using both RTP and CPP schemes. The findings demonstrate that our suggested approach performs better than the other algorithms because it achieved cost savings of 42.10% and 30% under RTP and CPP schemes, respectively. Meanwhile, it also reduced PAR by 55.17% and 50% under RTP and CPP schemes, respectively. © The Author(s) 2023.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Automatic Identification of Table Contents in Electronic Component Specifications of EDA 28th

Automatic Identification of Table Contents in Electronic Com...

引用

28th International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2023

作者： Hong, Tzung-Pei Xu, Yi-Zhen Huang, Shi-Feng Chen, Yi-Ting Lee, Ming-Han Department of Computer Science and Information Engineering National University of Kaohsiung Kaohsiung Taiwan Graduate Institute of Statistics National Central University Taoyuan Taiwan Footprintku Inc. Kaohsiung Taiwan Department of Applied Mathematics National University of Kaohsiung Kaohsiung Taiwan

ISBN: (纸本)9789819717132

With the rapid advancement of technology, the electronics industry has flourished in recent decades. Electronic products such as computers, mobile phones, and smart televisions are ubiquitous in our daily lives. In the design, manufacturing, and maintenance processes of electronic products, a large number of electronic components are required. The relevant information of these components is usually recorded in the tables of electronic component specifications. In this paper, we design methods to recognize and extract contents from tables, which typically contain vital information about electronic components, such as their characteristics and packaging methods. Our approach utilizes text processing techniques to structurally process and analyze the extracted table content, enabling us to obtain the specific information we need. We categorize tables in PDFs into different types and explore relevant information from them using the procedure of each type. The experimental results demonstrate that our method can achieve a high accuracy rate of over 90% in recognizing table contents. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Specifications

来源：评论

学校读者我要写书评

暂无评论

Improving Performance and Explainability of Sensor-Based Human Activity Recognition 9

Improving Performance and Explainability of Sensor-Based Hum...

引用

Joint 9th International Conference on Digital Arts, Media and Technology with 7th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering, ECTI DAMT and NCON 2024

作者： Mekruksavanich, Sakorn Jantawong, Ponnipa Jitpattanakul, Anuchit University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (纸本)9798350318241

Significant progress has been made in developing systems that can automatically recognize human activities, largely thanks to deep learning models and sensor data. However, high performance and comprehensibility are often at odds in these systems. The aim of this research is to enhance both the accuracy and understandability of models that use sensors for human activity recognition (HAR). We present a new convolutional neural network design which takes input from accelerometers and gyroscopes across multiple data streams. This allows efficient capture of time and frequency characteristics. Additionally, we put forward an attention module that identifies informative patterns in the sensor signals to shed light on the model's predictions. Experiments were conducted on a benchmark dataset of common daily movements gathered from ubiquitous sensors. Our model achieves state-of-the-art accuracy exceeding prior deep learning techniques. The attention visuals provide transparency into which sensor segments are most relevant for accurate activity classification. This validates improved model interpretability. Our multi-channel architecture pushes sensor-based HAR forward through heightened predictive performance. We offer original perspectives to create reliable, precise systems for HAR. © 2024 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Optimized Runge-Kutta Methods with Automatic Step Size Control for Compressible Computational Fluid Dynamics

引用

Communications on applied mathematics and Computation 2022年第4期4卷 1191-1228页

作者： Hendrik Ranocha Lisandro Dalcin Matteo Parsani David I.Ketcheson Applied Mathematics Münster University of MünsterMunsterGermany Computer Electrical and Mathematical Science and Engineering Division(CEMSE) Extreme Computing Research Center(ECRC)King Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Saudi Arabia Computer Electrical and Mathematical Science and Engineering Division(CEMSE) King Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Saudi Arabia

We develop error-control based time integration algorithms for compressible fluid dynam-ics(CFD)applications and show that they are efficient and robust in both the accuracy-limited and stability-limited *** on discontinuous spectral element semidis-cretizations,we design new controllers for existing methods and for some new embedded Runge-Kutta *** demonstrate the importance of choosing adequate controller parameters and provide a means to obtain these in *** compare a wide range of error-control-based methods,along with the common approach in which step size con-trol is based on the Courant-Friedrichs-Lewy(CFL)*** optimized methods give improved performance and naturally adopt a step size close to the maximum stable CFL number at loose tolerances,while additionally providing control of the temporal error at tighter *** numerical examples include challenging industrial CFD applications.

关键词： Explicit Runge-Kutta methods Step size control Compressible Euler equations Compressible Navier-Stokes equations hp-adaptive spatial discretizations

来源：评论

学校读者我要写书评

暂无评论

Thermally stratified flow of hybrid nanofluids with radiative heat transport and slip mechanism: multiple solutions

引用

Communications in Theoretical Physics 2022年第1期74卷 142-151页

作者： Rai Sajjad Saif Hashim Maria Zaman Muhammad Ayaz Department of Humanities and Sciences School of Electrical Engineering and Computer Science(SEECS)National University of Sciences and Technology(NUST)IslamabadPakistan Department of Pure&Applied Mathematics University of Haripur22620HaripurPakistan Department of Mathematics&Statistics Riphah International University IslamabadPakistan Department of Mathematics Abdul Wali Khan UniversityMardan23200Pakistan

Research on flow and heat transfer of hybrid nanofluids has gained great significance due to their efficient heat transfer *** fact,hybrid nanofluids are a novel type of fluid designed to enhance heat transfer rate and have a wide range of engineering and industrial *** by this evolution,a theoretical analysis is performed to explore the flow and heat transport characteristics of Cu/Al_(2)O_(3) hybrid nanofluids driven by a stretching/shrinking ***,this work focuses on the physical impacts of thermal stratification as well as thermal radiation during hybrid nanofluid flow in the presence of a velocity slip *** mathematical modelling incorporates the basic conservation laws and Boussinesq *** formulation gives a system of governing partial differential equations which are later reduced into ordinary differential equations via dimensionless *** efficient numerical solver,known as bvp4c in MATLAB,is utilized to acquire multiple(upper and lower)numerical solutions in the case of shrinking *** computed results are presented in the form of flow and temperature *** most significant findings acquired from the current study suggest that multiple solutions exist only in the case of a shrinking surface until a critical/turning ***,solutions are unavailable beyond this turning point,indicating flow *** is found that the fluid temperature has been impressively enhanced by a higher nanoparticle volume fraction for both *** the other hand,the outcomes disclose that the wall shear stress is reduced with higher magnetic field in the case of the second *** simulation outcomes are in excellent agreement with earlier research,with a relative error of less than 1%.

关键词： multiple numerical solutions hybrid nanofluids thermal radiation thermal stratification slip conditions heat transfer

来源：评论

学校读者我要写书评

暂无评论

Hybrid Attention with CNN-BiLSTM and CBAM for Efficient Wearable Activity Recognition 9

Hybrid Attention with CNN-BiLSTM and CBAM for Efficient Wear...

引用

作者： Mekruksavanich, Sakorn Jantawong, Ponnipa Phaphan, Wikanda Jitpattanakul, Anuchit University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand King Mongkut's University of Technology North Bangkok Research Group in Statistical Learning and Inference Department of Applied Statistics Faculty of Applied Science Bangkok Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (纸本)9798350318241

The use of widespread sensors for automatic activity recognition has become a dynamic area of research due to its broad applications in healthcare, fitness monitoring, and assisted living. To efficiently identify daily and sports activities from sensor data, this study suggests a hybrid deep learning model that integrates convolutional neural networks (CNN), bidirectional long short-term memory (BiLSTM) networks, and convolutional block attention modules (CBAM). The model starts by extracting spatial features from the sensor data using CNN layers. These spatial features are then employed to offer temporal context information to the BiLSTM network. To conclude, the CBAM attention mechanism is applied to guide the model's focus to the most informative segments of the BiLSTM feature maps. This approach enables the accurate recognition of patterns in both complex and daily sports activities. The effectiveness of the proposed hybrid model is evaluated using the UCI-DSA, a publicly available benchmark dataset that includes sports and daily activities collected through wearable motion sensors. In contrast to existing approaches, the outcomes reveal that a unified framework involving CNN, BiLSTM, and CBAM achieves outstanding performance in activity recognition, exceeding 99 % in both accuracy and F1-score while maintaining computational efficiency. © 2024 IEEE.

关键词： Wearable sensors

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：