检索结果-内蒙古大学图书馆

LOS and NLOS identification in real indoor environment using deep learning approach

Digital Communications and Networks 2024年第5期10卷 1305-1312页

作者： Alicja Olejniczak Olga Blaszkiewicz Krzysztof K.Cwalina Piotr Rajchowski Jaroslaw Sadowski Faculty of Electronics Telecommunications and InformaticsGdansk University of TechnologyGdansk 80-233Poland

Visibility conditions between antennas,***-of-Sight(LOS)and Non-Line-of-Sight(NLOS)can be crucial in the context of indoor localization,for which detecting the NLOS condition and further correcting constant position estimation errors or allocating resources can reduce the negative influence of multipath propagation on wireless communication and *** this paper a Deep Learning(DL)model to classify LOS/NLOS condition while analyzing two Channel Impulse Response(CIR)parameters:Total Power(TP)[dBm]and First Path Power(FP)[dBm]is *** experiments were conducted using DWM1000 DecaWave radio module based on measurements collected in a real indoor environment and the proposed architecture provides LOS/NLOS identification with an accuracy of more than 100%and 95%in static and dynamic senarios,*** proposed model improves the classification rate by 2-5%compared to other Machine Learning(ML)methods proposed in the literature.

关键词： Deep learning Machine learning LOS NLOS UWB

来源：评论

学校读者我要写书评

暂无评论

RELAXED INERTIAL METHOD FOR SOLVING A CLASS OF BILEVEL VARIATIONAL INEQUALITIES

Applied Set-Valued Analysis and Optimization

引用

Applied Set-Valued Analysis and Optimization 2025年第2期7卷 143-163页

作者： Thuy, Nguyen Thi Thu Toan, Tran Sy Anh, Tran Thi Phuong Faculty of Mathematics and Informatics Hanoi University of Science and Technology Hanoi Viet Nam

In this paper, we investigate a problem of monotone variational inequalities over the solution set of a split variational inequality problem in real Hilbert spaces. We propose a new two-step inertial iterative method with self-adaptive step sizes for approximating the solution of the problem. Our proposed algorithm does not require the co-coerciveness of the associated single-valued operators. Moreover, some parameters are relaxed to accommodate a larger range of values for the step sizes. We obtain strong convergence results under some mild conditions on the control parameters and without prior knowledge of the transformation operators and the monotone and Lipschitz continuous constants of the involved operators. Finally, we apply our result to the traffic network models and we present several numerical experiments to demonstrate the implementability of the proposed method. © 2025 Applied Set-Valued Analysis and Optimization.

关键词： Choquet integral

来源：评论

学校读者我要写书评

暂无评论

Survey of Asynchronous Radiolocation Methods

引用

IEEE Access 2025年 13卷 85613-85640页

作者： Stefanski, Jacek Sadowski, Jaroslaw Gdansk University of Technology Faculty of Electronics Telecommunications and Informatics Gdansk80-233 Poland

This paper reviews asynchronous radiolocation methods, emphasizing their analytical descriptions. Radiolocation systems evolve through the integration of advancements from multiple scientific disciplines, including telecommunications, computer science, electronics, and digital signal processing, making them inherently interdisciplinary. Most existing literature focuses on radiolocation systems with synchronized reference stations, supported by theoretical analyses and experimental studies. In contrast, asynchronous systems are less explored. Synchronous systems are preferred for their high measurement accuracy, achieved by providing a common time reference for the main components involved in measuring the radio signal parameters that are related to the position of mobile devices. However, a loss of synchronization or a failure of master reference stations can prevent object localization, underscoring the need for asynchronous methods as standalone or backup solutions. Additionally, asynchronous approaches allow the integration of multiple independent radiolocation networks, enhancing the efficiency of the localization process. To address this gap, the authors systematized the current knowledge on asynchronous radiolocation methods, which can help researchers to understand this topic and choose appropriate position estimation methods for various applications, taking into account the limitations caused by network or mobile device design. The paper also highlights key asynchronous radiolocation solutions that have been practically implemented, demonstrating their potential and effectiveness in real-world scenarios. © 2013 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Comparison of 3D Point Cloud Completion Networks for High Altitude Lidar Scans of Buildings

引用

Photogrammetric Engineering and Remote Sensing 2024年第1期90卷 55-64页

作者： Kulawiak, Marek Department of Geoinformatics Faculty of Electronics Telecommunications and Informatics Gdansk University of Technology Poland

High altitude lidar scans allow for rapid acquisition of big spatial data representing entire city blocks. Unfortunately, the raw point clouds acquired by this method are largely incomplete due to object occlusions and restrictions in scanning angles and sensor resolution, which can negatively affect the obtained results. In recent years, many new solutions for 3D point cloud completion have been created and tested on various objects;however, the application of these methods to high-altitude lidar point clouds of buildings has not been properly investigated yet. In the above context, this paper presents the results of applying several state-of-the-art point cloud completion networks to various building exteriors acquired by simulated airborne laser scanning. Moreover, the output point clouds generated from partial data are compared with complete ground-truth point clouds. The performed tests show that the SeedFormer network trained on the ShapeNet-55 data set provides promising shape completion results. © 2024 American Society for Photogrammetry and Remote Sensing.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

Transforming Internal Auditing: Harnessing Retrieval-Augmented Generation technology

引用

International Journal of Advanced Computer Science and Applications 2025年第4期16卷 785-790页

作者： Stumke, Olive Ndlovu, Fanie Faculty of Accounting and Informatics Department of Auditing and Taxation Durban University of Technology Durban South Africa

The advent of cloud-based Generative AI models, such as ChatGPT, Google Gemini, and Claude, has created new opportunities for improving education through real-time, adaptive learning experiences. Despite their widespread use globally, their application in South African higher education remains limited and underexplored, resulting in an application gap. This paper, as Phase 1 of a larger project, addresses this gap by focusing on the development of a Retrieval-Augmented Generation (RAG) web application designed to enhance Internal Auditing education at the Durban University of technology. This is achieved by integrating three powerful Generative AI models—OpenAI GPT-4o-mini, Google Gemini-1.5-flash, and Anthropic Claude-3-haiku—into a single educational platform that will enable lecturers to manage and augment lecture materials while allowing students to access personalized, AI-generated content. This paper presents the design considerations, architecture, and integration techniques employed in the development of the RAG web application, offering insights into the potential of adaptive learning, personalized learning, and AI-driven tutoring in South Africa’s educational landscape. This paper demonstrates how a RAG web application can provide the building blocks for future Generative AI applications that could enhance teaching and learning with minimal effort from lecturers and learners in the South African context. © (2025), (Science and Information Organization). All rights reserved.

关键词： Teaching

来源：评论

学校读者我要写书评

暂无评论

SOME PROPERTIES OF MINIMAL AND MAXIMAL OPERATORS IN AN ABSTRACT FRAMEWORK

引用

UPB Scientific Bulletin, Series A: Applied Mathematics and Physics 2025年第1期87卷 29-40页

作者： Catană, Viorel Georgescu, Horia-George Department of Mathematics-Informatics Faculty of Applied Sciences National University of Science and Technology POLITEHNICA Bucharest Romania

The main goal of this paper is to give a two-parameter abstract framework in which we build a theory of minimal and maximal operators associated to a linear operator A: D(A) ⊂ X → X, with dense domain D(A), where X is a complex Banach space. We prove an analogue of the Agmon-Douglis-Nirenberg inequality for pseudodifferential operators in our abstract setting. Using this inequality, we show that the minimal and maximal operators of the operator A are equal under suitable hypotheses on the complex Banach space X and on the operator A. As an application, we study the existence and regularity of weak solutions of the linear equations Au = f on the reflexive complex Banach space X. Further, we prove a perturbation result regarding the Agmon-Douglis-Nirenberg estimate when the operator A is perturbed by a potential operator with some suitable properties. Moreover, an application to strongly continuous semigroups of contractions generated by the operator A is given. Finally, we prove that the minimal operator of the operator A is Fredholm under suitable hypotheses. © 2025, Politechnica University of Bucharest. All rights reserved.

关键词： Banach spaces

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network for Cataract Clasification Using Primary Dataset 9

Convolutional Neural Network for Cataract Clasification Usin...

引用

9th International Conference on Business and Industrial Research, ICBIR 2024

作者： Totok Suryawan, I Gede Putra, I Wayan Murmayasa Adi Informatics Engineering Study Program Faculty of Technology and Informatics Denpasar Indonesia

ISBN: (纸本)9798350383010

Cataracts are the main factor causing blindness in Indonesia. Traditional diagnostic methods involving clinical examination by an ophthalmologist using a slit-lamp and visual tests have many challenges such as limited resources, time, and medical expertise may not be available in all locations, especially in less developed areas. Utilizing medical image technology is a wise choice because it allows early detection and monitoring of the development of this cataract disease technology is needed to identify medical images that have valuable information so that early detection or monitoring of cataract development can be carried out. CNN as a part of deep learning has the ability to perform automatic feature extraction so that it can identify eye images. A CNN model for recognizing cataracts in eye images taken directly from Bhayangkara Hospital in Denpasar Bali has been developed in this research. The model developed is equipped with a dropout layer technique to prevent overfitting. The test results show that the CNN developed in this research produces very good performance with an average accuracy level of 92% on public dataset images, and 94% on primary dataset images. Tested using the primary dataset and public dataset, this CNN model shows very good performance because it can correctly identify an average of 94% of eye images in the primary dataset, and 92% of eye images in the public dataset.. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Analysis of Centrality Metrics for Geographical Road Networks under Topological Representation

引用

Transactions of the Japanese Society for Artificial Intelligence 2025年第1期40卷 1-11页

作者： Kumano, Masahito Saito, Masaki Kimura, Masahiro Faculty of Advanced Science and Technology Ryukoku University Japan Division of Electronics and Informatics Graduate School of Science and Technology Ryukoku University Japan

Aiming at enhancing geographical road network analysis from a network science perspective, we introduce a novel problem of analyzing the road network in a city, and consider providing a new network centrality metric that could be useful for that problem. The problem addresses vehicular evacuation in urban settings. During emergency and disaster scenarios of vehicular evacuation, the shortest distance routes might not always be the most optimal. Instead, routes that are easier to traverse can be more crucial, even if they involve detours. Also, destinations for evacuation do not necessarily have to be restricted to traditional facilities;broad and well-maintained streets might also serve as suitable alternatives. We focus on the streets as the basic units of the road network to be investigated, and consider a scenario in which people efficiently move from starting intersections around their current places to designated goal streets, following the routes of easiest traversal. For the road network, we employ its topological representation, where vertices and edges correspond to streets and intersections between them, respectively. We thus represent the road network as a vertex-weighted graph, where the weight of each vertex reflects its ease of traversal. By appropriately extending the recently developed edge-centrality metric, "salience", to this vertex-weighted graph, we construct a new network centrality metric to detect critical streets for the newly introduced problem. Using a toy model of road network and real-world urban road networks obtained from OpenStreetMap, we experimentally reveal its distinctive characteristics by comparing it with several baselines. Moreover, we demonstrate that the proposed network centrality metric can successfully find critical streets for vehicular evacuation, which are difficult to detect using baseline methods. © 2025, Japanese Society for Artificial Intelligence. All rights reserved.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

Improved Prediction Of Global Temperature Via LSTM Using ReLU Activation And Hyperparameter Optimization

Improved Prediction Of Global Temperature Via LSTM Using ReL...

引用

2024 International Conference on Information technology Research and Innovation, ICITRI 2024

作者： Alamsyah, Nur Budiman Hendra, Acep Setiana, Elia Yoga, Titan Parama Danestiara, Venia Restreva Faculty of Technology and Informatics UNIBI Bandung Indonesia

ISBN: (纸本)9798350376210

Global temperature prediction is a crucial aspect of climate research, supporting applications such as disaster management and environmental planning. Nonetheless, precise prediction remains a challenge due to the complexity of the climate system. In this study, we address this challenge by proposing an enhanced approach using Long Short-Term Memory (LSTM) networks with Rectified Linear Unit (ReLU) activation functions and hyperparameter tuning. Our approach aims to improve the accuracy and reliability of global temperature prediction by leveraging the capabilities of deep learning models and optimizing the configuration. Through a series of experiments and comprehensive evaluation of a large dataset, we successfully demonstrated the effectiveness of our method in forecasting global temperature. The experimental results show that the LSTM with ReLU activation and hyperparameter tuning yields a Root Mean Squared Error (RMSE) of 0.046, indicating a significant improvement in accuracy compared to the model without ReLU activation and hyperparameter tuning, which yields an RMSE of 0.14. We also emphasize the importance of applying advanced machine learning techniques in climate forecasting and underline the potential of LSTM models in contributing to the advancement of climate science. Overall, our research contributes to efforts to improve the accuracy of temperature predictions, which in turn can facilitate better decision-making and more effective resource management in the face of global climate change. Thus, this study confirms that the use of LSTM with ReLU activation and hyperparameter tuning can be a highly effective approach in improving global temperature prediction. © 2024 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Driven Multivariate Regression - Feature Engineering with Random Forest and XGBoost for Accurate Weather Prediction 6

Driven Multivariate Regression - Feature Engineering with Ra...

引用

6th International Conference on Cybernetics and Intelligent System, ICORIS 2024

作者： Alamsyah, Nur Budiman Danestiara, Venia Restreva Akbar, Imannudin Sinaga, Arnold Ropen Nursyanti, Reni Faculty of Technology and Informatics UNIBI Bandung Indonesia

ISBN: (纸本)9798331539603

Fluctuations in weather conditions present a significant challenge for accurate prediction, particularly when considering multiple interdependent variables such as temperature and precipitation. To address this issue, this study proposes a multivariate regression approach driven by advanced feature engineering techniques. Specifically, we employed Random Forest and XGBoost models, leveraging temporal, interaction, and lag features to enhance the predictive accuracy. The proposed method was evaluated using a real-world weather dataset, where both models demonstrated substantial improvements in prediction per-formance. The Random Forest model achieved a Mean Squared Error (MSE) of 0.059 for temperature and 0.019 for precipitation, with an R-squared (R2) of 0.995 and 0.999, respectively. Similarly, the XGBoost model yielded an MSE of 0.043 for temperature and 1.826 for precipitation, with an R2 of 0.996 and 0.983. These results underscore the effectiveness of the feature engineering process combined with robust multivariate regression models, offering a promising approach for accurate weather prediction. © 2024 IEEE.

关键词： Prediction models

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：