检索结果-内蒙古大学图书馆

1st International Conference on computing, Sciences and Communications, ICCSC 2024

作者： Bdair, Mohammad Ruby, E D Kanmani Juyal, Prachi Taseen, Rakheeba Abirami, A. Soujanya, A. School of Architecture Computing & Engineering University of East London London United Kingdom Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Department of ECE Tamil Nadu Chennai India Uttarakhand Dehradun India School of computer science and Engineering Presidency university Bangalore India Sona College of Technology Department of Mathematics Tamil Nadu Salem India Ibrahimpatnam India

ISBN: (纸本)9798350353648

Lung cancer must be detected as early as possible, but it may be difficult with existing methods since they often depend on human judgment and outdated image processing. These techniques take a lot of time and are prone to errors, which produces uneven outcomes. The research provides a unique deep learning-based method for classifying lung nodules from CT images using convolutional neural networks (CNNs). By automating feature extraction and categorization, the suggested technique greatly increases diagnostic precision. The result shows superior performance over existing systems is demonstrated by evaluation measures such as AUC-ROC, accuracy, sensitivity, and specificity. With a training duration of 12 hours, an AUC-ROC of 0.95, accuracy of 92%, sensitivity of 94%, specificity of 90%, and inference speed of 0.5 seconds per scan, the results demonstrate notable improvements in diagnostic efficiency and accuracy. Deep learning has the potential to revolutionize the diagnosis of lung cancer and enhance patient care, as demonstrated by the study. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Approach for Enhancing Motor Imagery EEG Classification in BCI’s 12th

A Comprehensive Approach for Enhancing Motor Imagery EEG Cl...

引用

12th International Conference on Health Information Science, HIS 2023

作者： Sadiq, Muhammad Tariq Siuly, Siuly Li, Yan Wen, Paul Advanced Engineering Center School of Architecture Technology and Engineering University of Brighton BrightonBN2 4AT United Kingdom Institute for Sustainable Industries and Liveable Cities Victoria University MelbourneVIC3011 Australia School of Mathematics Physics and Computing University of Southern Queensland Toowoomba Campus Toowoomba4350 Australia School of Engineering University of Southern Queensland Toowoomba Campus Toowoomba4350 Australia

ISBN: (纸本)9789819971077

Electroencephalography (EEG) based on motor imagery has become a potential modality for brain-computer interface (BCI) systems, allowing users to control external devices by imagining doing particular motor activities. The existence of noise and the complexity of the brain signals, however, make it difficult to classify motor imagery EEG signals. This work suggests a systematic method for classifying motor imagery in the EEG. A technique known as Multiscale Principal Component Analysis (MSPCA) is used for efficient noise removal to improve the signal quality. A unique signal decomposition technique is proposed for modes extraction, allowing the separation of various oscillatory components related to motor imagery tasks. This breakdown makes it easier to isolate important temporal and spectral properties that distinguish various classes of motor imagery. These characteristics capture the dynamism and discriminative patterns present in motor imagery tasks. The motor imagery EEG signals are then classified using various machine learning and deep learning-based models based on the retrieved features. The findings of the classification show how well the suggested strategy works in generating precise and trustworthy classification success for various motor imaging tasks. The proposed method has enormous potential for BCI applications, allowing people with motor limitations to operate extrasensory equipment via brain signals. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Efficient Tree-based Parallel Algorithms for N-Body Simulations Using C++ Standard Parallelism

Efficient Tree-based Parallel Algorithms for N-Body Simulati...

引用

High Performance computing, Networking, Storage and Analysis, SC-W: Workshops of the International Conference for

作者： Thomas Lane Cassell Tom Deakin Aksel Alpay Vincent Heuveline Gonzalo Brito Gadeschi School of Computer Science University of Bristol Bristol UK Engineering Mathematics and Computing Lab Interdisciplinary Center for Scientific Computing Heidelberg University Heidelberg Germany GPU Architecture NVIDIA Munich Germany

ISBN: (数字)9798350355543

ISBN: (纸本)9798350355550

The Barnes-Hut approximation for N-body simulations reduces the time complexity of the naive all-pairs approach from O(N 2 ) to O(N log N) by hierarchically aggregating nearby particles into single entities using a tree data structure. This inherently irregular algorithm poses substantial challenges for performance portable implementations on multi-core CPUs and GPUs. We introduce two portable fully-parallel Barnes-Hut implementation strategies that trade-off different levels of GPU support for performance: an unbalanced concurrent octree, and a balanced bounding volume hierarchy sorted by a Hilbert spacefilling curve. We implement these algorithms in portable ISO C++ using parallel algorithms and concurrency primitives like atomics. The results demonstrate competitive performance on a range of CPUs and GPUs. Additionally, they highlight the effectiveness of the par execution policy for highly concurrent irregular algorithms, outperforming par_unseq on CPUs and GPUs with Independent Thread Scheduling.

关键词： Performance evaluation ISO Standards Software algorithms Octrees Graphics processing units C++ languages Scheduling Hardware Parallel algorithms Standards

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Loan Approval: Harnessing the Power of K-Nearest Neighbors for Predictive Eligibility

Revolutionizing Loan Approval: Harnessing the Power of K-Nea...

引用

International Conference on Innovation and Intelligence for Informatics, computing, and Technologies (3ICT)

作者： Mhd Saeed Sharif Madhav Theeng Tamang Niyas Jaheer Hussain Wael Elmedany Intelligent Technologies Research Group School of Architecture Computing and Engineering UEL London UK College of Information Technology University of Bahrain Kingdom of Bahrain

ISBN: (数字)9798331533137

ISBN: (纸本)9798331533144

A bank has become a basic need of our daily lives. People use banks for several tasks, such as depositing or withdrawing money and borrowing loans. The number of loan applications is rising significantly. It is crucial for the bank and financial sectors to determine loan eligibility and approve loans to suitable applicants only. This study attempts to design a system which can easily predict loan eligibility with the application of several machine learning (ML) algorithms. We employed the five different machine learning algorithms to achieve this research's aim. These algorithms were trained using the pre-processed dataset to create predictive models. F1 score, accuracy, Recall and Precision are used to evaluate the performance of the proposed approaches. The result showed that K-nearest neighbor (KNN) demonstrated outstanding performance, with an accuracy rate of 88.89%. The Random Forest (RF) model had an accuracy of 84.44%, whereas the Support Vector Machine (SVM) and Linear regression (LR) models achieved 82.22% and 80% accuracy, respectively. The Decision Tree (DT) algorithms showed the worst performance among the five algorithms, with an accuracy of 79.88%. The achievement of this research focuses on the possibility of machine learning algorithms as an efficient method for predicting loan eligibility in banks, contributing to the advancement of financial technology by automating and optimizing key banking processes, reducing processing times, and enhancing overall bank efficiency.

关键词： Support vector machines Radio frequency Machine learning algorithms Accuracy Fintech Banking Predictive models Nearest neighbor methods Prediction algorithms Decision trees

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Stressful Commutes Using Physiological Signals and Machine Learning Techniques

Evaluating the Stressful Commutes Using Physiological Signal...

引用

2022 International Conference on Innovation and Intelligence for Informatics, computing, and Technologies, 3ICT 2022

作者： Sharif, Mhd Saeed Tamang, Madhav Raj Theeng Elmedany, Wael Fu, Cynthia H.Y. School of Architecture Computing and Engineering Uel London United Kingdom University of Bahrain College of Information Technology P.O. Box 32038 Bahrain School of Psychology Stratford Campus London United Kingdom

ISBN: (数字)9781665451932

ISBN: (纸本)9781665451932

Stress can be described as an alteration in our body that can cause strain emotionally, physically, or psychologically. It is a reaction from our body to something that demands attention or exertion. It can be caused by various reasons depending on the physical or mental activity of the body. Commuting on a regular basis also acts as a source of stress. This research aims to explore the physiological effects of the commute with an application of a machine-learning algorithm. The data used in this research is collected from 45 healthy participants who commute to work on a regular basis. A multimodal dataset containing medical data like biosignals (heart rate, blood pressure, and EEG signal) plus responses obtained from the questionnaire PANAS. Evaluation is based on the performance metrics that include confusion matrix, ROC/AUC, and classification accuracy of the model. In this research, several machine learning algorithms are applied to design a model which can predict the effect of a commute. The results obtained from this research suggest that whether the interval of commute was small or large, there was a significant rise in stress levels including the bio-signals (electroencephalogram, blood pressure and heart rate) after the commute. The results obtained from the employed machine learning algorithms predict that heart rate difference before and after commute will correlate with EEG signals in participants who have self-reported to be stress after the commute. The random forest algorithm gave a very promising result with an accuracy of 91%, while the KNN and the SVM showed the accuracy of 78% and 80% respectively. © 2022 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

A Thermal Comfort Modelling Framework for Urban Neighbourhoods: Tempo-Spatial Coupling of Building Energy and CFD Models 5th

A Thermal Comfort Modelling Framework for Urban Neighbourhoo...

引用

5th International Conference on Building Energy and Environment, COBEE 2022

作者： Aghamolaei, Reihaneh Fallahpour, Marzieh Zhang, Ruijun Mirzaei, Parham A. School of Mechanical and Manufacturing Engineering Faculty of Engineering and Computing Dublin City University Whitehall Dublin 9 Ireland College of Fine Arts University of Tehran Tehran Iran Architecture and Built Environment Department University of Nottingham University Park NottinghamNG2RD United Kingdom

ISBN: (纸本)9789811998218

More accurate tools are required to replicate urban climates to achieve healthy and comfortable urban environments. To this end, this study implements a novel high-resolution simulation framework to improve the OTC modelling by dynamic coupling of convective fluxes calculated by computational fluid dynamic (CFD) model, and dynamic building energy simulation (BES) for analyzing outdoor surface temperature of buildings. In addition, radiative fluxes emitted from building surfaces are coupled with latter models. The workflow is applied at the Grasshopper platform based on the results of ANSYS Fluent as the CFD and EnergyPlus as the BES tools. This framework is tested within a generic case study representing an urban neighbourhood. As a result of this framework, tempo-spatial values for OTC are achieved at each time-step of simulation and then compared with the OTC values from the traditional OTC modelling approach. Statistical analysis of results shows that the OTC valued predicted using the coupled method can change considerably compared to OTC results from traditional methods at the neighbourhood scale. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Computational fluid dynamics

来源：评论

学校读者我要写书评

暂无评论

Mechanistic investigation of highly bendable magnesium alloy sheet fabricated by short-process manufacturing

引用

Journal of Magnesium and Alloys 2024年第10期12卷 4289-4310页

作者： Shiwei Xu Peijie Xiao Xiaofan Wu John Holmes Frédéric Mompiou Zhenyu Xiao Chen Jin Tianjiao Li Kuaishe Wang Zhuoran Zeng College of Mechanical and Vehicle Engineering Hunan UniversityChangsha 410082China State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle Hunan UniversityChangsha 410082China Suzhou Research Institute of Hunan University Suzhou 215131China College of Engineering Computing and CyberneticAustralian National UniversityACT 2601Australia CEMES-CNRS Universitéde Toulouse29 rue J.MarvigToulouse 31055France Qinghai Salt Lake Teli Magnesium Co. Ltd.Xining 810000China International Joint Laboratory for Light Alloys(Ministry of Education) College of Materials Science and EngineeringChongqing UniversityChongqing 400044China School of Metallurgical Engineering Xi’an University of Architecture&TechnologyXi’an 710055China College of Materials Science and Engineering Hunan UniversityChangsha 410082China

In this study,a commercial magnesium alloy AZ31(Mg-3Al-1Zn-0.3Mn)sheet through a short manufacturing process was found to be ductile and highly formable in *** possessing a strong basal texture,the short-processed sheet without any annealing can be bent at a small radius,only 0.2 times its thickness in the 90°bending ***,it could withstand direct deformation by repeated *** in-situ microstructural characterization reveals that extension twin bands with strain localization appear in the bending *** subsequent flattening,these twin bands underwent detwinning,reducing local strain concentrations and enabling further bending *** outstanding bend formability originated from the significant-type dislocation loops slipping on the prismatic crystal planes within dynamic-recrystallized *** grains underwent a uniform refinement to several microns in the short manufacturing process and exhibited low residual *** active prismatic dislocation slip within refined grains was due to its much lower relative activation stress to basal slip(CRSSprism/CRSSbasal of only∼1.6)owing to the effective grain boundary ***,the prismatic dislocation activity was further enhanced when bypassing Al-Mn nano-particles during motion,leaving debris and loops that facilitated easy multiplication.

关键词： Magnesium Deformation Texture In-situ characterization Dislocation slip.

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Physics-Informed Neural Network Approach for Mean Radiant Temperature Modeling

arXiv

引用

arXiv 2025年

作者： Shaeri, Pouya AlKhaled, Saud Middel, Ariane School of Computing and Augmented Intelligence Arizona State University United States College of Architecture Kuwait University Kuwait School of Arts Media and Engineering Arizona State University United States

Outdoor thermal comfort is a critical determinant of urban livability, particularly in hot desert climates where extreme heat poses challenges to public health, energy consumption, and urban planning. Mean Radiant Temperature (Tmrt) is a key parameter for evaluating outdoor thermal comfort, especially in urban environments where radiation dynamics significantly impact human thermal exposure. Traditional methods of estimating Tmrt rely on field measurements and computational simulations, both of which are resource intensive. This study introduces a Physics-Informed Neural Network (PINN) approach that integrates shortwave and longwave radiation modeling with deep learning techniques. By leveraging a multimodal dataset that includes meteorological data, built environment characteristics, and fisheye image-derived shading information, our model enhances predictive accuracy while maintaining physical consistency. Our experimental results demonstrate that the proposed PINN framework outperforms conventional deep learning models, with the best-performing configurations achieving an RMSE of 3.50 and an R2 of 0.88. This approach highlights the potential of physics-informed machine learning in bridging the gap between computational modeling and real-world applications, offering a scalable and interpretable solution for urban thermal comfort assessments. Copyright © 2025, The Authors. All rights reserved.

关键词： Thermal comfort

来源：评论

学校读者我要写书评

暂无评论

Digital Data Extraction for Vehicles Forensic Investigation

Digital Data Extraction for Vehicles Forensic Investigation

引用

2022 International Conference on Innovation and Intelligence for Informatics, computing, and Technologies, 3ICT 2022

作者： Stathers, Corey Muhammad, Musa Fasanmade, Adebamigbe Al-Bayatti, Ali Morden, Jarrad Sharif, Mhd Saeed De Montfort University Cyber Technology Institute Leicester United Kingdom Uel School of Architecture Computing and Engineering LondonE16 2RD United Kingdom

ISBN: (数字)9781665451932

ISBN: (纸本)9781665451932

In a criminal investigation, vehicles are quickly becoming another crucial source of digital evidence. When a car is involved in a criminal offensive such as road traffic accidents, drunk driving even a robbery or a terrorist attack, investigators typically focus on the capture of DNA, fingerprints, and other non-digital identifying materials. (e.g. calls, contacts, messages, pictures, videos and even web history). This paper is to present our findings undertaken on a 2008 Mitsubishi colt with non-factory fitted equipment which in the 2000s many drivers wanted extra comfort while driving to their own music and even connect the mobile device to their vehicles to call others. By using Mobile forensic techniques and On-board Diagnostics (OBD) software to read the vehicles engine status we can show what data is stored within a vehicle and if there is enough to support a case. This Investigation involves a Maxtek Dashboard camera, Ankeway Head unit, the ECU within the vehicle, a Samsung galaxy Android tablet and it's our goal to show the techniques used to show the different types off data receivable from the vehicle mentioned. © 2022 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

SLSNet: Weakly-Supervised Skin Lesion Segmentation Network with Self-attentions 20th

SLSNet: Weakly-Supervised Skin Lesion Segmentation Network w...

引用

20th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2023

作者： Pei, Songwen Huang, Junjie School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Engineering Research Center of Software/Hardware Co-design Technology and Application Ministry of Education East China Normal University Shanghai200062 China

ISBN: (纸本)9789819970247

Computer-aided skin lesion segmentation with high precision is crucial to diagnose skin cancers in the early stage. However, the lack of pixel-level labels makes the skin lesion segmentation tasks challenging. To tackle this problem, a new weakly-supervised skin lesion segmentation network with self-attentions named SLSNet is proposed. SLSNet contains two modules and uses image-level labels as supervision information. One module named Intra-image Self-attention Seed Expansion (ISE) digs intra-image self-attentions with an expansion loss and a confidence loss to expand seed areas. The other module named Inter-image Affinity-based Noise Suppression (IAS) suppresses the noise pixels in attention maps via inter-image correlations. Extensive experiments conducted on ISIC-2017 dataset show that SLSNet achieves relatively high performance while reducing human labeling efforts. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Expansion

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：