检索结果-内蒙古大学图书馆

IEEE International Conference on engineering, Technology and Innovation

作者： Sami Hyrynsalmi Helena Holmström Olsson Jan Bosch Dept. Software Engineering LUT University Lahti Finland Dept. Computer Science and Media Technology Malmö University Malmö Sweden Dept. Computer Science and Engineering Chalmers University of Technology Göteborg Sweden

Data has been quickly becoming as the fuel, the new oil, of growth and prosperity of companies in the modern age. With useful data and suﬃcient tools, companies have the ability to enhance their current products, presents new innovations and services as well as generate new revenue streams with a secondary customer base. While there are ongoing efforts to develop machine learning and data science techniques, little attention has been paid to understanding and characterizing data-related business activities in software-intensive *** multiple-case study examines four large international embedded system companies to explore how they are utilizing data and how they have proceeded in their journey in the data business. This study identifies six distinct stages, each with unique challenges, that seems to be common for embedded system companies in their data business. As the result, this study presents an initial data business maturity model for software-intensive embedded system companies. Additionally, this research provides a foundation for future efforts to support software-intensive embedded system companies in establishing data businesses.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving Gamma Imaging in Proton Therapy by Sanitizing Compton Camera Simulated Patient Data using Neural Networks through the BRIDE Pipeline

Improving Gamma Imaging in Proton Therapy by Sanitizing Comp...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Chen, Michael O. Hodge, Julian Jin, Peter L. Protz, Ella Wong, Elizabeth Obe, Ruth Shakeri, Ehsan Cham, Mostafa Gobbert, Matthias K. Barajas, Carlos A. Sharma, Vijay R. Mossahebi, Sina Ren, Lei Peterson, Stephen W. Polf, Jerimy C. Dartmouth College Departments of Mathematics United States U. of Maryland Dept. of Mathematics and Statistics United States James M. Bennett High School SalisburyMD United States Florida Atlantic University Department of Mathematics and Sciences United States Brookdale Community College Department of Mathematics United States U. of Houston Dept. of Computer Science and of Software Engineering Clear Lake United States U. of Maryland Dept. of Information Systems United States U. of Maryland School of Medicine Dept. of Radiation Oncology United States U. of Cape Town Dept. of Physics South Africa M3D Inc. United States

ISBN: (纸本)9798350362480

Precision medicine in cancer treatment increasingly relies on advanced radiotherapies, such as proton beam radiotherapy, to enhance efficacy of the treatment. When the proton beam in this treatment interacts with patient matter, the excited nuclei may emit prompt gamma ray interactions that can be captured by a Compton camera. The image reconstruction from this captured data faces the issue of mischaracterizing the sequences of incoming scattering events, leading to excessive background noise. To address this problem, several machine learning models such as Feedfoward Neural Networks (FNN) and Recurrent Neural Networks (RNN) were developed in PyTorch to properly characterize the scattering sequences on simulated datasets, including newly-created patient medium data, which were generated by using a pipeline comprised of the GEANT4 and Monte-Carlo Detector Effects (MCDE) softwares. These models were implemented using the novel 'Big-data REU Integrated Development and Experimentation' (BRIDE) platform, a modular pipeline that streamlines preprocessing, feature engineering, and model development and evaluation on parallelized GPU processors. Hyperparameter studies were done on the novel patient data as well as on water phantom datasets used during previous research. Patient data was more difficult than water phantom data to classify for both FNN and RNN models. FNN models had higher accuracy on patient medium data but lower accuracy on water phantom data when compared to RNN models. Previous results on several different datasets were reproduced on BRIDE and multiple new models achieved greater performance than in previous research. © 2024 IEEE.

关键词： Phantoms

来源：评论

学校读者我要写书评

暂无评论

A New Random-Forest-Based Approach for Cyberattack Detection in Digital Substations

A New Random-Forest-Based Approach for Cyberattack Detection...

引用

Canadian Conference on Electrical and computer engineering (CCECE)

作者： Kripa M. Jose Walid G. Morsi Computer and Software Engineering Dept. Smart Grid & Electric Vehicles Research Laboratory Electrical Ontario Tech University Oshawa Canada

ISBN: (数字)9798350371628

ISBN: (纸本)9798350371635

Digital substation automation systems rely heavily on information and communication technologies, which are prone to cyberattack threats. Traditionally, the focus has been geared toward the detection and classification of power quality disturbances from the normal operation. This paper presents a novel approach that uses random forests to detect and classify both cyberattacks and power quality disturbances from normal operation. The proposed approach was successful in identifying the salient features that significantly influence the detection of such cyberattacks. In order to demonstrate the effectiveness of the proposed approach, it has been tested on two different publicly available datasets. Unlike in previous work, the results have shown that the uncertainty associated with the choice of the training and testing sets has insignificant effect on the classification accuracies of the proposed approach. Furthermore, the proposed approach was successful in overcoming the issues of data imbalance and overfitting, which are common in cybersecurity problems.

关键词： Training Accuracy Sensitivity Uncertainty Substation automation Power quality Forestry

来源：评论

学校读者我要写书评

暂无评论

An Automated Wavelet Generation Tool for Cyberattack Detection in Substation Automation systems

An Automated Wavelet Generation Tool for Cyberattack Detecti...

引用

Canadian Conference on Electrical and computer engineering (CCECE)

作者： Matthew Oinonen Walid G. Morsi Computer and Software Engineering Dept. Smart Grid & Electric Vehicles Research Laboratory Electrical Ontario Tech University Oshawa Canada

ISBN: (数字)9798350371628

ISBN: (纸本)9798350371635

This paper presents a novel method, the Automated Custom Wavelet Generation-Deep Learning-based classifier (ACWGDL), for cyberattack detection in smart grids. The proposed method generates custom wavelets for enhanced feature extraction of cyberattacks on substation automation systems (SASs). Physical and network data from a substation is converted into time-frequency spectrograms using the Discrete Wavelet Transform (DWT) with the custom generated wavelets. Deep learning is implemented with a convolutional neural network to classify the generated spectrograms as cyberattacks from normal cases and power quality disturbance cases. The proposed method has been tested on two publicly available datasets from two different substation automation systems. The results have shown that the use of the custom wavelets was able to enhance the detection accuracy of the cyberattacks by up to 11% compared to the existing benchmark wavelets. The proposed method is versatile and has demonstrated its effectiveness in enhancing the detection accuracy of the cyberattacks irrespective of the choice of the datasets.

关键词： Training Time-frequency analysis Substation automation Accuracy Benchmark testing Feature extraction Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Spatial Mini Golf: Game-Based Spatial Intelligence Testing and Training Using VR and Non-VR Platforms

Spatial Mini Golf: Game-Based Spatial Intelligence Testing a...

引用

International Conference on Image and Vision Computing New Zealand, IVCNZ

作者： Patrick Oliver Andy Fong Zixuan Wang Burkhard C. Wünsche Dept. of Software Engineering University of Auckland Auckland New Zealand School of Computer Science University of Auckland Auckland New Zealand

ISBN: (数字)9798331518776

ISBN: (纸本)9798331518783

Spatial intelligence is a key determinant of students' motivation and success in pursuing a STEM career. To improve students' participation in STEM subjects it is important to test and train spatial skills in an enjoyable and unobtrusive manner. We present Spatial Mini Golf, a game designed to test and enhance spatial intelligence, targeting four sub-skills: visual perception, mental rotation, spatial visualization, and visuospatial working memory. Two versions-VR and desktop-were compared. While VR increases engagement, it also presents control challenges that raise cognitive load and extend task completion times. Performance correlates with spatial intelligence, particularly in desktop environments, but VR reduces performance gaps among lower-ability participants. Our research suggest that both VR and desktop games are suitable for testing and training spatial reasoning skills. VR tools might be more accessible for users with low spatial skills if intuitive and easy-to-use interfaces are provided, but results might get affected by users' hand-eye coordination.

关键词： Training Visualization engineering profession Games Cognitive load Testing Visual perception

来源：评论

学校读者我要写书评

暂无评论

FingerNet: EEG Decoding of A Fine Motor Imagery with Finger-tapping Task Based on A Deep Neural Network

arXiv

引用

arXiv 2024年

作者： Go, Young-Min Yu, Seong-Hyun Park, Hyeong-Yeong Lee, Minji Jeong, Ji-Hoon Dept. Computer Science Chungbuk National University Chungbuk28644 Korea Republic of Dept. Biomedical Software Engineering The Catholic University of Korea Gyeonggi14662 Korea Republic of

Brain-computer interface (BCI) technology facilitates communication between the human brain and computers, primarily utilizing electroencephalography (EEG) signals to discern human intentions. Although EEG-based BCI systems have been developed for paralysis individuals, ongoing studies explore systems for speech imagery and motor imagery (MI). This study introduces FingerNet, a specialized network for fine MI classification, departing from conventional gross MI studies. The proposed FingerNet could extract spatial and temporal features from EEG signals, improving classification accuracy within the same hand. The experimental results demonstrated that performance showed significantly higher accuracy in classifying five finger-tapping tasks, encompassing thumb, index, middle, ring, and little finger movements. FingerNet demonstrated dominant performance compared to the conventional baseline models, EEGNet and DeepConvNet. The average accuracy for FingerNet was 0.3049, whereas EEGNet and DeepConvNet exhibited lower accuracies of 0.2196 and 0.2533, respectively. Statistical validation also demonstrates the predominance of FingerNet over baseline networks. For biased predictions, particularly for thumb and index classes, we led to the implementation of weighted cross-entropy and also adapted the weighted cross-entropy, a method conventionally employed to mitigate class imbalance. The proposed FingerNet involves optimizing network structure, improving performance, and exploring applications beyond fine MI. Moreover, the weighted Cross Entropy approach employed to address such biased predictions appears to have broader applicability and relevance across various domains involving multi-class classification tasks. We believe that effective execution of motor imagery can be achieved not only for fine MI, but also for local muscle MI. © 2024, CC BY-NC-ND.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Mitigating Insecure Outputs in Large Language Models(LLMs): A Practical Educational Module

Mitigating Insecure Outputs in Large Language Models(LLMs): ...

引用

IEEE Annual International computer software and Applications Conference (COMPSAC)

作者： MD Abdul Barek Md Mostafizur Rahman Shapna Akter A.B.M Kamrul Islam Riad Md Abdur Rahman Hossain Shahriar Akond Rahman Fan Wu Department of Intelligent Systems and Robotics University of West Florida USA Dept. of Cybersecurity and Information Technology University of West Florida USA Center for Cybersecurity University of West Florida USA Computer Science and Software Engineering Auburn University USA Dept. of Computer Science Tuskegee University USA

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

Large Language Models (LLMs) have extensive ability to produce promising output. Nowadays, people are increasingly relying on them due to easy accessibility, rapid and outstanding outcomes. However, the use of these results without appropriate scrutiny poses serious security risks, particularly when they are integrated with other software, APIs, or plugins. This is because the LLM outputs are highly dependent on the prompts they receive. Therefore, it is essential to carefully clean these outputs before using them in additional software environments. This paper is designed to teach students about the potential dangers of contaminated LLM output within the context of web development through prelab, hands-on, and postlab experiences. Hands-on lab provides practical guidance on how to handle LLM vulnerabilities to make applications safe with some real-world examples in Python. This approach aims to provide students with a deeper understanding of the precautions necessary to ensure software against the vulnerabilities introduced by LLM output.

关键词： Training Navigation Large language models Computational modeling software Security software development management

来源：评论

学校读者我要写书评

暂无评论

A Novel Dual FedAux-based Harvested Energy Prediction for Road Safety systems

A Novel Dual FedAux-based Harvested Energy Prediction for Ro...

引用

Public Safety Technology (WFPST), IEEE World Forum on

作者： Papa Sidy Mactar Traoré Wael Jaafar Fatoumata Baldé Dept. Computer Science Université Alioune Diop Bambey Sénégal Dept. Software and IT Engineering École de Technologie Supérieure (ÉTS) Montreal Canada

ISBN: (数字)9798350329148

ISBN: (纸本)9798350329155

In the evolving landscape of road safety, the role of solar-powered Internet-of-Things (IoT) devices, crucial for supporting connected and autonomous vehicles (CAVs) with enhanced computing and storage capabilities, is increasingly significant These devices, often deployed in remote areas such as transcontinental highways, rely heavily on their energy harvesting capabilities for optimal operation. Given their expected widespread deployment, this paper explores the challenge of accurately predicting harvested energy in such IoT devices. To do so, we introduce "Dual FedAux", a novel approach that blends Federated Learning with a dual-model architecture, integrating long short-term memory (LSTM) and Transformer models. This combination, which is enhanced with meta-learning, i.e., stacking ensemble learning, is particularly adapted for time series analysis, such as for energy prediction. Through experiments, we demonstrate that the proposed Dual FedAux significantly outperforms benchmark models in terms of root-mean-square error (RMSE) and convergence, thus underscoring its potential to enhance the efficiency and reliability of large-scale road safety IoT-based systems.

关键词： Computational modeling Time series analysis Solar energy computer architecture Predictive models Transformers Road safety

来源：评论

学校读者我要写书评

暂无评论

Physics-Based Spatio-Temporal Modeling With Machine Learning for the Prediction of Oceanic Internal Waves 19

Physics-Based Spatio-Temporal Modeling With Machine Learning...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and Computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable Computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy Computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Wu, Song Zhang, Xiaojiang Dong, Wei Wang, Senzhang Li, Xiaoyong Bao, SenLiang Li, Kai National University of Defense Technology Dept. College of Computer Science and Technology Changsha China National University of Defense Technology Dept. College of Meteorology and Oceanography Changsha China Central South University School of Computer Science and Engineering Changsha China National University of Defense Technology Dept. College of Systems Engineering Changsha China

ISBN: (纸本)9798350346558

Accurately predicting the occurrence of oceanic internal waves in the northeastern South China Sea is of great importance to marine ecosystems, and economy. The traditional physics-based models for monitoring the occurrence of internal waves require complex parameterization, and the partial differential equations (PDEs) are relatively difficult to solve. The emergence of integrating physical knowledge and data-driven models brings light to solving the problem, which improves interpretability and meets the physical consistency. It not only inherits the advantages of machine learning in massive data processing but also makes up for the 'black box' characteristics. In this paper, we propose a physics-based spatio-temporal data analysis model based on the widely used LSTM framework to achieve oceanic internal wave prediction. The results show higher prediction accuracy compared with the traditional LSTM model, and the introduction of physical laws can improve data utilization while enhancing interpretability. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Comparative Reliability Analysis of a Microgrid versus Zonal Nanogrids

Comparative Reliability Analysis of a Microgrid versus Zonal...

引用

IEEE Energy Conversion Congress and Exposition, ECCE

作者： Gabrielle Smith Douglas L. Van Bossuyt Giovanna Oriti Mark Vygoder Richard Alves Systems Engineering Dept. Naval Postgraduate School Monterey CA USA Electrical and Computer Engineering Dept. Naval Postgraduate School Monterey CA USA Electrical Engineering Dept. University of Wisconsin Milwaukee Milwaukee WI USA

ISBN: (数字)9798350376067

ISBN: (纸本)9798350376074

Nanogrids are small-scale power distribution systems that can operate independently or integrated with the grid like microgrids. These nanogrids can interconnect in a network and have built-in redundancy. This paper investigates the potential of bringing zonal shipboard power ashore with zonal nanogrids to enhance energy reliability at industrial facilities which addresses the limitations of current microgrid systems and emergency backup generators. A reliability analysis is conducted by using the reliability block diagram method to compare microgrid and zonal nanogrid configurations with various control architectures to identify the most reliable solution. The two common types of control strategies are centralized and decentralized. The results indicate that decentralized zonal nanogrids offer higher reliability over a 14-day grid power outage. Furthermore, a sensitivity analysis is conducted to identify the most impactful component in the reliability of zonal nanogrids which is the power transmission lines and fiber optic cables.

关键词： Optical fibers Power transmission lines Sensitivity analysis Redundancy Power distribution Microgrids Reliability engineering Industrial facilities Generators Power system reliability

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：