检索结果-内蒙古大学图书馆

UAV-Aided Data Acquisition Using Gaining-Sharing Knowledge Optimization Algorithm

computers, Materials & Continua 2022年第9期72卷 5999-6013页

作者： Rania M Tawfik Hazem A.A.Nomer M.Saeed Darweesh Ali Wagdy Mohamed Hassan Mostafa Wireless Intelligent Networks Center(WINC) School of Engineering and Applied SciencesNile UniversityGiza12677Egypt School of Information Technology and Computer Science(ITCS) Nile UniversityGiza12677Egypt Operations Research Department Faculty of Graduate Studies for Statistical ResearchCairo UniversityGiza12613Egypt Department of Mathematics and Actuarial Science School of Science and EngineeringThe American University in CairoEgypt Electronics and Communications Engineering Department Cairo UniversityEgypt University of Science and Technology Nanotechnology and Nanoelectronics ProgramZewal City of Science and TechnologyOctober Gardens6th of OctoberGiza12578Egypt

Unmanned Aerial Vehicles(UAVs)provide a reliable and energyefficient solution for data collection from the Narrowband Internet of Things(NB-IoT)***,the UAV’s deployment optimization,including locations of the UAV’s stop points,is a necessity to minimize the energy consumption of the UAV and the NB-IoT devices and also to conduct the data collection *** this regard,this paper proposes GainingSharing Knowledge(GSK)algorithm for optimizing the UAV’s *** GSK,the number of UAV’s stop points in the three-dimensional space is encapsulated into a single individual with a fixed length representing an entire *** superiority of using GSK in the tackled problem is verified by simulation in seven *** provides significant results in all seven scenarios compared with other four optimization algorithms used before with the same ***,the NB-IoT is proposed as the wireless communication technology between the UAV and IoT devices.

关键词： NB-IoT UAV GSK stop points optimization

来源：评论

学校读者我要写书评

暂无评论

Pantypes: Diverse Representatives for Self-Explainable Models

arXiv

引用

arXiv 2024年

作者： Kjærsgaard, Rune Boubekki, Ahcène Clemmensen, Line Department of Applied Mathematics and Computer Science Technical University of Denmark Denmark Machine Learning and Uncertainty Physikalisch-Technische Bundesanstalt Germany

Prototypical self-explainable classifiers have emerged to meet the growing demand for interpretable AI systems. These classifiers are designed to incorporate high transparency in their decisions by basing inference on similarity with learned prototypical objects. While these models are designed with diversity in mind, the learned prototypes often do not sufficiently represent all aspects of the input distribution, particularly those in low density regions. Such lack of sufficient data representation, known as representation bias, has been associated with various detrimental properties related to machine learning diversity and fairness. In light of this, we introduce pantypes, a new family of prototypical objects designed to capture the full diversity of the input distribution through a sparse set of objects. We show that pantypes can empower prototypical self-explainable models by occupying divergent regions of the latent space and thus fostering high diversity, interpretability and fairness. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

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

A High-order Spectral Element based Time-Domain Simulation of a Model-Scale Floating Offshore Wind Turbine 33rd

A High-order Spectral Element based Time-Domain Simulation o...

引用

33rd International Ocean and Polar Engineering Conference, ISOPE 2023

作者： Visbech, Jens Bingham, Harry B. Eskilsson, Claes Palm, Johannes Engsig-Karup, Allan P. Department of Applied Mathematics and Computer Science Kgs. Lyngby Denmark Kgs. Lyngby Denmark Department of Civil and Mechanical Engineering Kgs. Lyngby Denmark Department of the Built Environment Aalborg East Denmark Sigma Energy & Marine AB Gothenburg Sweden

ISBN: (纸本)9781880653807

This paper describes a new high-order composite numerical model designed for the efficient arbitrary-scale simulation of moored floating offshore bodies. The study focuses on static equilibrium and free decay of such structures, particularly a floating offshore wind turbine. The composite scheme models the linear or weakly-nonlinear motion in the time domain by solving the Cummins equations derived from Newton’s 2nd law of motion. The mooring forces are acquired from a discontinuous Galerkin spectral element solver. The linear pseudo-impulsive radiation problems are modeled via a three-dimensional spectral element-based solver on an unstructured hybrid-configured mesh, ultimately providing accurate frequency-dependent added mass and damping coefficients. In this work, a numerical simulation of a moored model-scale floating offshore wind turbine is performed and compared with experimental measurements. The numerical experiments agree with the measurements and demonstrate that the model can be used for full-scale computations relevant to offshore engineering applications. © 2023 by the International Society of Offshore and Polar Engineers (ISOPE).

关键词： Numerical models

来源：评论

学校读者我要写书评

暂无评论

Efficient Recognition of Complex Human Activities Based on Smartwatch Sensors Using Deep Pyramidal Residual Network 15

Efficient Recognition of Complex Human Activities Based on S...

引用

15th International Conference on Information Technology and Electrical Engineering, ICITEE 2023

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

ISBN: (纸本)9798350304466

Human activity recognition (HAR) has become a hot topic in artificial intelligence research due to the rapid development of smart wearable technologies. The goal of HAR is to accurately identify human actions using various data sources, such as video, images, and sensor data from wearable devices. Recent research in HAR has achieved promising results using learning-based methods, especially deep learning techniques. However, achieving state-of-the-art results remains a challenge for researchers. This study proposes a new approach to HAR that uses deep learning to classify human activities from smartwatch sensor data. We propose the use of a one-dimensional deep pyramidal residual network (1D-PyramidNet) for accurate human action identification. We evaluate the performance of our model against baseline models using the DHA dataset, a benchmark dataset for HAR that includes wristwatch sensor data for 11 complex human activities. The experimental results show that our 1D-PyramidNet model outperforms the baseline models, including CNN, LSTM, BiLSTM, GRU, and BiGRU. This confirms that the use of 1D-PyramidNet can improve the identification capabilities of HAR systems, achieving a maximum accuracy of 96.64%. © 2023 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Deep Residual Network for Recognizing Activities in Daily Living Using Channel State Information 14

A Lightweight Deep Residual Network for Recognizing Activiti...

引用

14th IEEE International Conference on Software Engineering and Service science, ICSESS 2023

作者： Mekruksavanich, Sakorn Jitpattanakul, Anuchit School of Information and Communication Technology University of Phayao 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)9798350336269

The field of human activity recognition (HAR) focuses on predicting human motion and actions by analyzing data from various sensors. HAR tasks can benefit from vision-based and sensor-based approaches, which offer high data quality. However, it's essential to recognize that these methods have drawbacks, such as intrusiveness and privacy concerns. With the increasing prevalence of Wi-Fi devices, Wi-Fi technology has gained popularity for tracking everyday activities, particularly among senior individuals, making it an appealing choice in healthcare applications. Channel State Information (CSI), a crucial attribute of Wi-Fi signals, can be leveraged to recognize different human actions. This study introduces CSI-ResNeXt, a lightweight deep residual network designed to classify human actions using CSI data from daily living scenarios. A series of tests were conducted to evaluate the network's performance, using a standard CSI-HA dataset. The results of the experiments demonstrated that the proposed lightweight deep residual network achieved an impressive accuracy of 99.17% and an F1-score of 99.10%, surpassing the performance of previous deep learning models. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Extracting structural motifs from pair distribution function data of nanostructures using explainable machine learning

引用

npj Computational Materials 2022年第1期8卷 2053-2063页

作者： Andy S.Anker Emil T.S.Kjær Mikkel Juelsholt Troels Lindahl Christiansen Susanne Linn Skjærvø Mads Ry Vogel Jørgensen Innokenty Kantor Daniel Risskov Sørensen Simon J.L.Billinge Raghavendra Selvan Kirsten M.Ø.Jensen Department of Chemistry and Nano-Science Center University of Copenhagen2100CopenhagenDenmark Department of Materials University of OxfordParks RoadOxfordUK Department of Chemistry&iNANO Aarhus University8000AarhusDenmark MAX IV Laboratory Lund University22484LundSweden Department of Physics Technical University of Denmark2880LyngbyDenmark Department of Applied Physics and Applied Mathematics Columbia UniversityNew YorkNY10027USA Condensed Matter Physics and Materials Science Department Brookhaven National LaboratoryUptonNY11973USA Department of Computer Science University of Copenhagen2100CopenhagenDenmark Department of Neuroscience University of Copenhagen2200CopenhagenDenmark

Characterization of material structure with X-ray or neutron scattering using *** Distribution Function(PDF)analysis most often rely on refining a structure model against an experimental ***,identifying a suitable model is often a ***,automated approaches have made it possible to test thousands of models for each dataset,but these methods are computationally expensive and analysing the output,*** structural information from the resulting fits in a meaningful way,is *** Machine Learning based Motif Extractor(ML-MotEx)trains an ML algorithm on thousands of fits,and uses SHAP(SHapley Additive exPlanation)values to identify which model features are important for the fit *** use the method for 4 different chemical systems,including disordered nanomaterials and ***-MotEx opens for a type of modelling where each feature in a model is assigned an importance value for the fit quality based on explainable ML.

关键词： explain structural meaningful

来源：评论

学校读者我要写书评

暂无评论

Recognizing and Understanding Sport Activities based on Wearable Sensor Signals using Deep Residual Network 4

Recognizing and Understanding Sport Activities based on Wear...

引用

4th Research, Invention, and Innovation Congress: Innovative Electricals and Electronics, RI2C 2023

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

ISBN: (纸本)9798350330618

The prevalence of intelligent wearable devices has significantly increased, offering advantages to individuals of all age groups. In the field of human activity recognition (HAR) research, wearable sensor data plays a crucial role in classifying various human actions. Sensor-based assessments are commonly employed in hazard analysis and risk assessments. However, traditional machine learning (ML) algorithms have faced challenges when applied to sports activities due to their unpredictable nature. These challenges have prompted the need for manual feature extraction, limiting the efficacy of ML methodologies in data categorization. To address this, our study introduces ResNet, a deep residual network, for effectively categorizing sports activities using wearable sensor data. To evaluate our proposed approach, we utilized a publicly available benchmark dataset consisting of sensor data collected from the dominant wrist, neck, and thigh of each study participant. The experimental results demonstrated the exceptional performance of the ResNet model, achieving an impressive accuracy rate of 99.83% in recognizing sport activities. Additionally, we compared the efficacy of our suggested model with five fundamental deep learning models, namely CNN, LSTM, BiLSTM, GRU, and BiGRU. The comparative analysis revealed that the ResNet model outperformed the other deep learning models, demonstrating superior performance in sport activity recognition. ©2023 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Lane Detection using Kalman Filtering

引用

Procedia computer science 2023年 230卷 598-607页

作者： R Subramani K Suresh Donald Cecil C Vijayalakshmi Department of Mathematics CHRIST (Deemed to be University) Bengaluru India Department of Computer Science CHRIST (Deemed to be University) Bengaluru India Department of Statistics and Applied Mathematics Central University of Tamil Nadu Thiruvarur India

Autonomous vehicles are the future of transportation. Modern high-tech vehicles use a sequence of cameras and sensors and in order to assess their atmosphere and aid to the driver by generating various alerts. While driving, it is always a challenging task for drivers to notice lane lines on the road, especially at night time, it becomes more difficult. This research proposes a novel way to recognize lanes in a variety of environments, including day and night. First various pre-processing techniques are used to improve and filter out the noise present in the video frames. Then, a sequence of procedure with respect to lane detection is performed. This stable lane detection is achieved by Kalman filter, by removing offset errors and predict future lane lines.

关键词： Kalman Filter Autonomous Driving Lane Detection Driverless

来源：评论

学校读者我要写书评

暂无评论

Errors-In-Variables Model Fitting for Partially Unpaired Data Utilizing Mixture Models

arXiv

引用

arXiv 2024年

作者： Hoegele, Wolfgang Brockhaus, Sarah Munich University of Applied Sciences HM Department of Computer Science and Mathematics Lothstraße 64 München80335 Germany

We introduce a general framework for regression in the errors-in-variables regime, allowing for full flexibility about the dimensionality of the data, observational error probability density types, the (nonlinear) model type and the avoidance of ad-hoc definitions of loss functions. In this framework, we introduce model fitting for partially unpaired data, i.e. for given data groups the pairing information of input and output is lost (semi-supervised). This is achieved by constructing mixture model densities, which directly model the loss of pairing information allowing inference. In a numerical simulation study linear and nonlinear model fits are illustrated as well as a real data study is presented based on life expectancy data from the world bank utilizing a multiple linear regression model. These results show that high quality model fitting is possible with partially unpaired data, which opens the possibility for new applications with unfortunate or deliberate loss of pairing information in data. Copyright © 2024, The Authors. All rights reserved.

关键词： Multiple linear regression

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：