检索结果-内蒙古大学图书馆

Networking and Communications (ICNWC), International Conference on

作者： Nareshkumar R R. Shalinikumari S. Sri Nandhini Kowsalya Vijay Anand P Ajmal Mohamed S. Gayathri Department of Networking and Communications School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu India Department of Architecture Bharath Institute of Higher Education and Research Selaiyur Chennai Tamilnadu India Department of Information Technology Veltech Multitech Dr.Rangarajan Dr.Sakunthala Engineering College Chennai Tamilnadu India Department of Artificial Intelligence and Data Science CMR Institute of Technology Bengaluru India Department of Computer Science and Engineering Saveetha School of Engineering Chennai India Department of Computer Science and Engineering K. Ramakrishnan College of Technology Trichy Tamilnadu India

ISBN: (数字)9798350365269

ISBN: (纸本)9798350365276

The air quality index (AQI) is a metric used to report air quality levels. There has been a substantial rise in the level of air pollution in Indian cities. Multiple methodologies exist for formulating a mathematical equation to ascertain the air quality index. Multiple studies have established a correlation between exposure to air pollution and negative health effects in the general population. The objective of this study is to determine the optimal approach for predicting AQI in order to aid in climate regulation. Nine separate Machine learning (ML) algorithms have been employed in the suggested study to ascertain the AQI. The use of the SMOTE algorithm in the datasets in ML resulted in improved accuracy when comparing the outcomes. Furthermore, all of the implementations have been thoroughly documented using graphs and metrics, which clearly illustrate the differences in outcomes and aid in identifying the specific factors that led to the improvement in accuracy.

关键词： Measurement Machine learning algorithms Urban areas Sociology Machine learning Predictive models Air pollution

来源：评论

学校读者我要写书评

暂无评论

Leveraging Machine Learning for Crime Intent Detection in Social Media Posts 1st

Leveraging Machine Learning for Crime Intent Detection in ...

引用

1st International Conference on AI-generated Content, AIGC 2023

作者： Bokolo, Biodoumoye George Onyehanere, Praise Ogegbene-Ise, Ebikela Olufemi, Itunu Tettey, Josiah Nii Armah Department of Computer Science Sam Houston State University HuntsvilleTX77340 United States Department of Architecture Technology and Engineering University of Brighton BrightonBN2 4AT United Kingdom Department of Computer and Software Engineering Kennesaw State University KennesawGA United States Department of Computer Science and Quantitative Methods Austin Peay State University ClarksvilleTN37044 United States Department of Computer Science and Engineering Wright State University DaytonOH45435 United States

ISBN: (纸本)9789819975860

Detecting crime intent from user-generated content on social media platforms has become increasingly important for law enforcement and crime prevention. This paper presents a comprehensive approach for crime intent detection from user tweets using machine learning techniques. The study utilizes a dataset of about 400,000 tweets and applies data preprocessing, feature selection, and model training with logistic regression, ridge regression classifier, Stochastic Gradient Descent (SGD) classifier, Random Forests, and support vector machine models. Evaluation metrics such as accuracy, precision, recall, and F1 score are employed to assess the models’ performance. The results reveal that the logistic regression model achieves the highest accuracy ratio of 0.981 in detecting crime intent from tweets. This research showcases the effectiveness of machine learning and advanced transformer-based models in leveraging social media data for crime analysis. The findings provide valuable insights into the potential for early detection and monitoring of crime intent using online platforms, contributing to the field of crime prevention and law enforcement. The utilization of machine learning techniques offers new avenues for understanding and analyzing crime-related sentiments expressed by social media users. By accurately detecting crime intent from user-generated content, law enforcement agencies can enhance their proactive measures, monitor public sentiment towards crime, and shape policies and interventions to address public concerns effectively. The research highlights the significance of leveraging social media data for crime detection and emphasizes the potential impact of advanced machine learning models in improving public safety and crime prevention efforts. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Random Selection of Parameters in Asynchronous Pool-Based Evolutionary Algorithms

Random Selection of Parameters in Asynchronous Pool-Based Ev...

引用

Congress on Evolutionary Computation

作者： Mario García-Valdez René Márquez Leonardo Trujillo J.J. Merelo Instituto Tecnológico de Tijuana Computer Architecture and Technology University of Granada Spain

Synchronous operation is not the most natural, as in biologically inspired, mode to run distributed algorithms. In many grid, cloud or volunteer setups nodes are heterogeneous, or simply are not available at the exact same time; this is a challenge for the researcher if their full performance is going to be actually leveraged. Asynchronous distributed evolutionary algorithms try to solve this by dropping the homogeneity, as well as the synchronicity, assumption. These algorithms share the population between distributed workers which execute the actual evolutionary process by taking samples of the population, and replacing them in the population pool by evolved individuals. The performance of these EAs depends in part on the selection of parameters for the EA running in each worker. In this paper we study how randomly varying parameters in distributed evolutionary algorithms affects performance. Experiments were conducted in the AWS cloud using 2, 6 and 12 virtual machine configurations, with both homogeneous and heterogeneous random settings using five test functions for real-valued optimization and the OneMax binary problem. The results suggest that this method can produce a performance that is competitive with instances of the algorithm using workers with parameters specially tuned for the benchmark.

关键词： Cloud computing Sociology Evolutionary computation Benchmark testing Virtual machining Biology Statistics

来源：评论

学校读者我要写书评

暂无评论

Study on ecological impact of Saihanba Forest Farm Based on Evaluation Model

Study on ecological impact of Saihanba Forest Farm Based on ...

引用

作者： Yu Sun Junhan Wu Gengluo Li College of Civil Engineering And Architecture Shandong University of Science and Technology School of Economics and Management Shandong Agricultural University School of Mathematics and Computer Sciences NanChang University

In order to evaluate the impact of Saihanba on the ecological environment,we selecte 11factors from three aspects to build the Ecological Environment Health Index(EEHI) evaluation model;Next,We use a combined weighting method combining Hierarchical Analysis,Entropy Weighting method and Coefficient of Variation method to determine the weights of each *** the EEHI of the Seyhanba area from 1962 to 2020 was calculated using the TOPSIS;Finally,the ecological environment of the Seyhanba area was obtained with a yearly upward trend,and the effect of Seyhanba on the improvement of ecological environment was analyzed in three *** order to evaluate the impact of Saihanba on the anti-dust storm capacity in Beijing,we selected 9indicators from three aspects to build the Sandstorm Resistance Ability(SRA) evaluation model in Beijing;Then,the Main Component Analysis method was used to calculate the SRA in Beijing over the years,and SRA was improved year by *** the same time,we constructed the Sandstorm Index(SI) to indicate the annual severity of dust storms in Beijing;Finally,the relativity between SRA and SI was calculated using the Pearson Correlation Coefficient and find the correlation coefficient between these was-0.833,as a significant *** show that the improvement of Saihanba's resistance to dust storms in Beijing effectively reduces the severity of dust storms in Beijing.

关键词： Seyhanba Ecological Environment Evaluation Model Correlation Analysis

来源：评论

学校读者我要写书评

暂无评论

Exploring the feasibility of Mobility as a Service (MaaS) for integrated passenger and freight transport through a Delphi survey

引用

Transportation Research Procedia 2025年 90卷 559-566页

作者： Michela Le Pira Nadia Giuffrida Rodrigo Tapia Lóránt Tavasszy Gonçalo Correia Francesco Pilla Matteo Ignaccolo Giuseppe Inturri Dept. of Civil Engineering and Architecture University of Catania Via Santa Sofia 64 95123 Catania Italy Dept. of Civil Environmental Land Construction and Chemistry Polytechnic University of Bari Via Edoardo Orabona 4 70125 Bari Italy Dept. of Transport & Planning Faculty of Civil Engineering and Geosciences Delft University of Technology Stevinweg 1 2628 CN Delft the Netherlands Dept. of Political Sciences University of Roma TRE Via Gabriello Chiabrera 199 00145 Roma Italy Faculty of Technology Policy and Management Delft University of Technology Jaffalaan 5 2628 BX Delft the Netherlands School of Architecture Planning and Environmental Policy University College Dublin Richview School of Architecture Belfield Dublin 4 Ireland Dept. of Electrical Electronic and Computer Engineering University of Catania Via Santa Sofia 64 95123 Catania Italy

This paper presents the first results of a Delphi survey aimed at eliciting experts’ opinions on possible scenarios of integration between passenger and freight transport enabled by a Mobility as a Service (MaaS) platform. Combining freight shipments with passenger trips is a promising addition to the MaaS business model that could help to reduce the number of freight vehicles and contribute to a more efficient use of passenger transport services and modes. The research objective of this paper is therefore to explore the feasibility of an extended version of MaaS including freight, called “MaaS for Passenger and Freight” (MaaS4PaF). Passenger and freight transport experts were asked to express their opinions with respect to the potential market penetration, business ecosystem, and implementation of this concept. Results allow to elaborate on opportunities and barriers, especially related to uncertain business models and the multitude of actors involved, and propose a research agenda to further investigate the feasibility and potential of MaaS for passenger and freight transport integration.

关键词： mobility on-demand last-mile logistics urban freight transport digital platforms

来源：评论

学校读者我要写书评

暂无评论

Wayfinding design in transportation architecture-are saliency models or designer visual attention a good predictor of passenger visual attention?

引用

Frontiers of Architectural Research 2020年第4期9卷 726-738页

作者： Ran Xu Haishan Xia Mei Tian School of Architecture and Design Beijing Jiaotons UniversityBeijing 100044China School of Computer and Information Technology Beijing Jiaotons UniversityBeijing 100044China

In transportation architecture,wayfinding quality is a crucial factor for determining transfer efficiency and level of *** developing architectural design concepts,designers often employ their visual attention to imagine where passengers will look.A saliency model is a software program that can predict human visual *** research examined whether a saliency model or designer visual attention is a good predictor of passenger visual attention during wayfinding in side transportation *** a remote eye-tracking system,the eye-movements of 29 participants watching 100 still images depicting different indoor seenes of transportation architecture were recorded and transformed into saliency maps to illustrate participants'visual *** were categorized as either"designers"or"laypeople"based on their architectural design *** were compared among the"designers'"visual attention,saliency model predictions,and"laypeople's"visual *** results showed that while the"designers'"visual attention was the best predictor of that of"laypeople",followed by saliency models,a single desig ner's visual attend on was not a good *** divergence in visual attention highlights the limitation of designers in predicting passenger wayfinding behavior and implies that integrating a saliency model in practice can be beneficial for wayfinding design.

关键词： Tran sportation architecture design Passenger wayfinding Path choice Visual attention Eye fixation

来源：评论

学校读者我要写书评

暂无评论

Optimized Model Predictive Control for Unmanned Aerial Vehicles with Sensor Uncertainties

Optimized Model Predictive Control for Unmanned Aerial Vehic...

引用

2022 International Conference on Control, Automation and Diagnosis, ICCAD 2022

作者： Taher Azar, Ahmad Serrano, Fernando E. Ahmad Kamal, Nashwa Qureshi, Basit Al Mhdawi, Ammar K. Humaidi, Amjad J. Kasim Ibraheem, Ibraheem Ben Njima, Chakib Prince Sultan University College of Computer and Information Sciences Riyadh Saudi Arabia Benha University Faculty of Computers and Artificial Intelligence Benha Egypt Faculty of Engineering and Architecture Tegucigalpa Honduras Cairo University Faculty of Engineering Egypt Hill University United Kingdom University of Technology Control and Systems Engineering Department Baghdad Iraq Dijlah University College Department of Computer Techniques Engineering Baghdad10001 Iraq University of Sousse Tunisia

ISBN: (数字)9781665497947

ISBN: (纸本)9781665497947

In this paper, a novel control strategy based on model predictive control is proposed for tracking the trajectory of unmanned aerial vehicles (UAV). First, the dynamic model of an unmanned aerial vehicle UAV is established by considering the linear velocities in terms of the analyzed system's attitude angles. The UAV's dynamic model is suitable for kinematic control by using two attitude angles as control inputs. The controller design is made up of an output feedback controller formed by the error variables, which are the difference between the measured output and the reference variables. Then, a model predictive control is established by considering an optimization problem with a performance index and the corresponding constraints. Furthermore, the stochastic properties of the UAV dynamic model are taken into account in this research study. The measured outputs provided by the sensors are constrained by the topological characteristics of the unmanned aerial vehicle to be analyzed. Finally, a numerical experiment and its conclusions are presented, demonstrating that the proposed control strategy provides optimal trajectory tracking. © 2022 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Inland Waterway Object Detection in Multi-environment: Dataset and Approach

arXiv

引用

arXiv 2025年

作者： Wang, Shanshan Xu, Haixiang Feng, Hui Wang, Xiaoqian Song, Pei Liu, Sijie He, Jianhua Ministry of Education Hubei Wuhan China College of Automobile Technology and Service Wuhan City Polytechnic Hubei Wuhan China School of Naval Architecture Ocean and Energy Power Engineering Wuhan University of Technology Hubei Wuhan China School of Computer Science and Electronic Engineering University of Essex ColchesterCO4 3SQ United Kingdom

The success of deep learning in the field of intelligent ship visual perception largely relies on information-rich image data. However, the dedicated datasets for inland waterway vessel objects remain scarce, failing to meet the adaptability requirements of visual perception systems in complex and dynamic environments. Particularly in inland waterway scenarios, due to narrow waterways, variable weather conditions, and interference from urban structures and lighting along the riverbanks, object detection systems based on existing inland waterway datasets exhibit significant limitations in robustness. To address these issues, this paper constructs a new vessel detection dataset named Multi-environment Inland Waterway Vessel Dataset (MEIWVD). The MEIWVD comprises 32,478 high-quality images from various inland waterway scenarios, covering complex environmental conditions such as sunny, rainy, foggy, and artificial lighting, etc. These images comprehensively encompass common vessel types in the Yangtze River Basin, while considering image diversity, sample independence, environmental complexity, and multi-scale characteristics, making MEIWVD a benchmark dataset with exceptional properties for vessel object detection. To leverage the characteristics of the MEIWVD, this paper proposes a scene-guided image enhancement module for multi-environment scenarios, which adaptively enhances water surface images based on environmental conditions to improve detector performance in complex scenarios. Additionally, a parameter-limited dilated convolution is introduced to enhance the representation of salient features of inland waterway vessels by leveraging their geometric characteristics. Finally, a multi-scale dilated residual fusion method is proposed to effectively integrate multi-scale features and improve the detection of multi-scale objects. Experimental results demonstrate that the MEIWVD dataset, constructed in this study, provides a more rigorous benchmark for object detectio

关键词： Canals

来源：评论

学校读者我要写书评

暂无评论

Diffusion Unit: Interpretable Edge Enhancement and Suppression Learning for 3D Point Cloud Segmentation

SSRN

引用

SSRN 2023年

作者： Xiu, Haoyi Liu, Xin Wang, Weimin Kim, Kyoung-Sook Shinohara, Takayuki Chang, Qiong Matsuoka, Masashi Department of Architecture and Building Engineering Tokyo Institute of Technology Tokyo Japan Artificial Intelligence Research Center AIST Tokyo Japan DUT-RU International School of Information Science and Engineering Dalian University of Technology Dalian China Innovation Technology Office Research Center PASCO Corporation Tokyo Japan Department of Computer Science Tokyo Institute of Technology Tokyo Japan

3D point clouds are discrete samples of continuous surfaces which can be used for various applications. However, the lack of true connectivity information, i.e., edge information, makes point cloud recognition challenging. Recent edge-aware methods incorporate edge modeling into network designs to better describe local structures. Although these methods show that incorporating edge information is beneficial, how edge information helps remains unclear, making it difficult for users to analyze its usefulness. To shed light on this issue, in this study, we propose a new algorithm called Diffusion Unit (DU) that handles edge information in a principled and interpretable manner while providing decent improvement. First, we theoretically show that DU learns to perform task-beneficial edge enhancement and suppression. Second, we experimentally observe and verify the edge enhancement and suppression behavior. Third, we empirically demonstrate that this behavior contributes to performance improvement. Extensive experiments and analyses performed on challenging benchmarks verify the effectiveness of DU. Specifically, our method achieves state-of-the-art performance in object part segmentation using ShapeNet part and scene segmentation using S3DIS. Our source code is available at https://***/martianxiu/DiffusionUnit. © 2023, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Reduced graphene oxide-based composites for wearable strain-sensing applications

引用

Sensors and Actuators A: Physical 2022年 345卷

作者： Hu, Qinhua Nag, Anindya Zhang, Lijuan Wang, Kuaishe School of Mechanical and Electrical Engineering Xi'an University of Architecture and Technology Xi'an710055 China School of Chemical Engineering and Energy Technology Dongguan University of Technology Dongguan523808 China Faculty of Electrical and Computer Engineering Technische Universität Dresden Dresden01062 Germany Technische Universität Dresden Dresden01069 Germany DGUT-CNAM Institute Dongguan University of Technology Dongguan523106 China College of Metallurgical Engineering Xi'an University of Architecture and Technology Xi'an710055 China

The exceptional electromechanical attributes of graphene have led to its usage in pure and composite forms for different kinds of biomedical and industrial applications. Among the various physiochemical allotropes of graphene employed to form flexible sensors, reduced graphene oxide (rGO) has been preferred due to the easier process of fabrication and an ability to disperse uniformly in water and other organic solvents. This paper reports some of the significant work done on the use of rGO/polymer-based composites for strain-sensing applications. A classification has been implemented in terms of nature, the polymers being integrated with rGO to form the resultant sensors. The use of two types of polymers, including polydimethylsiloxane (PDMS) and thermoplastic polyurethane (TPU), have been shown in this paper. PDMS and TPU have been largely employed to form wearable sensors due to the mechanical advantages imparted by them. These polymers have either been used as substrates or as polymer matrices to mix with rGO and other nanomaterials at optimized ratios. Some of the existing challenges and the possible remedial solutions of the current rGO/PDMS-based strain sensors have been showcased here. © 2022 Elsevier B.V.

关键词： Polydimethylsiloxane

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：