检索结果-内蒙古大学图书馆

2nd Conference on Biomedical Photonics and Cross-Fusion, BPC 2023

作者： Yang, Kun Cai, Yingjie Xu, Zihan Xu, Tiedong Kong, Xiangyan Faculty of Electrical Engineering and Computer Science in Ningbo University Ningbo China Ningbo China

ISBN: (数字)9781510667556

ISBN: (纸本)9781510667549

SERF (Spin-exchange relaxation free) atomic magnetometers have been demonstrated as the ultra-high sensitive, noncryogenic sensor. Single-beam configured sensors often choose VCSEL (Vertical-Cavity Surface-Emitting Laser) as the optical source. The existing commercial VCSELs are often with magnetic package and heater, which will affect the sensitivity of atomic magnetometers. In our work, we presented a novel nonmagnetic VCSEL package and its driver circuit. VCSEL chip, heater, and PT1000 are assembled on FPC (Flexible Printed Circuit), and its driver are optimized in terms of low noise, safe protection and AC temperature control. The result showed that the magnetic field generated by heating current can be ignored based on proposed layout method, and the RMS noise of current and temperature are lower than 0.1 µA and 20 mK, respectively. Our proposed method will expand the possibility for commercialization process of miniature SERF atomic magnetometers. © 2023 SPIE.

关键词： Surface emitting lasers

来源：评论

学校读者我要写书评

暂无评论

Employing Feature engineering for River Stage Forecasting to Improve Hybrid Model Performance 32

Employing Feature Engineering for River Stage Forecasting to...

引用

32nd International Conference on Software, Telecommunications and computer Networks, SoftCOM 2024

作者： Mihel, Anna Maria Pecnik, Spela Vrbancic, Grega Lerga, Jonatan Krvavica, Nino University of Rijeka Faculty of Engineering Department of Computer Engineering Rijeka Croatia University of Maribor Intelligent Systems Laboratory Faculty of Electrical Engineering and Computer Science Maribor Slovenia University of Rijeka Faculty of Civil Engineering Department of Hydrotechnics and Geotechnics Rijeka Croatia

ISBN: (纸本)9789532901382

Establishing early warning systems and efficient management of water resources in tidal reaches is crucial for achieving adequate flood protection. In tidal reaches, the river stage interacts non-linearly with tides (downstream) and discharge (upstream), making the modeling of river processes extremely complex. Data-driven methods have proven helpful for predicting the river stage parameter. This contrasts with existing numerical approaches, which suffer from several limitations. The aim of this study was to predict the river stage of the upstream part of the tidal river, where the influence of salinity is present during the summer months. Using the CNN-LSTM model trained on historical records of the discharge (station of the variable to be predicted), the river stage of three downstream stations, and the point of interest, the prediction was carried out up to 24 hours in advance. By incorporating feature engineering, we achieved an improvement in model results for the longest horizon, confirmed by standard performance metrics, and considered it efficient and effective for risk mitigation. Introducing feature engineering into the data preprocessing resulted in a predictive performance improvement of 0.98% for the Nash-Sutcliffe Efficiency (NSE) metric, 7.0% for the root mean squared error (RMSE) metric, and 7.25% for the mean absolute error (MAE) metric over the second and third-best scenarios using a spectrogram and time-series data. © 2024 University of Split, FESB.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Cultural Heritage Monitoring and Predictive Maintenance using Internet of Things: Assessment and Future Aspects

引用

Journal of Mobile Multimedia 2024年第6期20卷 1211-1250页

作者： Um-E-habiba Shaikh, Faisal Karim Chowdhry, Bhawani Shankar Department of Computer Science Shaheed Zulfikar Ali Bhutto Institute of Science and Technology Hyderabad Pakistan Telecommunication Engineering Department Mehran University of Engineering and Technology Jamshoro Pakistan Faculty of Electrical Electronics and Computer Engineering Mehran University of Engineering and Technology Jamshoro Pakistan

This study presents a detailed survey on the use of the Internet of Things (IoT) for predictive maintenance and monitoring of cultural heritage, focusing on museums and exhibitions. The integration of IoT in these fields offers significant potential for optimizing maintenance and supervision of heritage resources while also enhancing maintenance strategies. This review examines the application of IoT devices, data analysis, and predictive algorithms in monitoring the state of heritage resources to improve tourist experiences and conserve cultural resources. Key enabling technologies can enable adaptive interactions and engagement with enhanced navigation. Visualization technologies are also common, offering hands-on displays. The study also emphasizes the value of accessibility and interactivity, providing personalization and content sharing features. Several initiatives prioritize the delivery of digital content through mobile applications, internet browsers, and downloadable *** study examines how IoT-enabled predictive maintenance systems can recognize potential hazards, like resource decay or environmental dangers, enabling immediate action. This survey also highlights trends, challenges, and future research in IoT and cultural heritage monitoring. © 2025 River Publishers.

关键词： heritage monitoring IoTs predictive maintenance trends

来源：评论

学校读者我要写书评

暂无评论

Securing MIMO Wiretap Channel With Learning-Based Friendly Jamming Under Imperfect CSI

引用

IEEE Internet of Things Journal 2025年第11期12卷 16009-16022页

作者： Minh Tuan, Bui Nguyen, Diep N. Linh Trung, Nguyen Nguyen, Van-Dinh Van Huynh, Nguyen Thai Hoang, Dinh Krunz, Marwan Dutkiewicz, Eryk University of Technology Sydney School of Electrical and Data Engineering SydneyNSW2007 Australia University of Engineering and Technology Vietnam National University Faculty of Electronics and Telecommunications Hanoi100000 Viet Nam College of Engineering and Computer Science VinUniversity Hanoi100000 Viet Nam University of Liverpool Department of Electrical Engineering and Electronics LiverpoolL69 3GJ United Kingdom The University of Arizona Department of Electrical and Computer Engineering TucsonAZ85721 United States

Wireless communications are particularly vulnerable to eavesdropping attacks due to their broadcast nature. To effectively deal with eavesdroppers, existing security techniques usually require accurate channel state information (CSI), e.g., for friendly jamming (FJ), and/or additional computing resources at transceivers, e.g., cryptography-based solutions, which unfortunately may not be feasible in practice. This challenge is even more acute in low-end IoT devices. We thus introduce a novel deep learning-based FJ framework that can effectively defeat eavesdropping attacks with imperfect CSI and even without CSI of legitimate channels. In particular, we first develop an autoencoder-based communication architecture with FJ, namely, AEFJ, to jointly maximize the secrecy rate and minimize the block error rate (BLER) at the receiver without requiring perfect CSI of the legitimate channels. In addition, to deal with the case without CSI, we leverage the mutual information neural estimation (MINE) concept and design a MINE-based FJ scheme that can achieve comparable security performance to the conventional FJ methods that require perfect CSI. Extensive simulations in a multiple-input-multiple-output (MIMO) system demonstrate that our proposed solution can effectively deal with eavesdropping attacks in various settings. Moreover, the proposed framework can seamlessly integrate MIMO security and detection tasks into a unified end-to-end learning process. This integrated approach can significantly maximize the throughput and minimize the BLER, offering a good solution for enhancing communication security in wireless communication systems. © 2014 IEEE.

关键词： Jamming

来源：评论

学校读者我要写书评

暂无评论

Deep Learning in Medical Image Analysis for Personalized Medicine 65

Deep Learning in Medical Image Analysis for Personalized Med...

引用

65th International Symposium ELMAR, ELMAR 2023

作者： Galic, Irena Habijan, Marija Faculty of Electrical Engineering Computer Science and Information Technology Osijek Osijek31000 Croatia

ISBN: (纸本)9798350325126

Deep learning (DL) has transformed the field of medical image processing, enabling unprecedented accuracy and efficiency in various applications. It has been widely utilized for medical image analysis of different anatomical regions. In this article, we provide an overview of commonly used deep learning methods, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and generative adversarial networks (GANs). We briefly overview their applications in medical image analysis, such as image classification, object detection/localization, segmentation, generation, and registration. We also highlight the strengths and limitations of each method and identify the challenges that still need to be addressed, including the limited availability of annotated data, variability in medical images, and the interpretability issue. Finally, we discuss future research directions, including developing explainable deep learning methods and integrating multi-modal data. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Motor Imagery Classification of Finger Movements based on Position Subtask Network Learning

Motor Imagery Classification of Finger Movements based on Po...

引用

2022 International Conference on Signal Processing and Communication Technology, SPCT 2022

作者： Luo, Huiyan Ye, Qingwei Lu, Zhihua Zhou, Peng Faculty of Electrical Engineering and Computer Science Ningbo University Zhejiang Ningbo315211 China

ISBN: (纸本)9781510664333

The multi-classification of finger movements is a difficult challenge at present. In this paper, a multi-task Siamese network is proposed. Based on the basic Siamese network architecture, this study designs the position relationships between sample pairs and constructs single-sample subtasks for the left and right input samples. The position relationships between samples not only additionally supplement the spatial factors between electroencephalogram (EEG) signals that facilitate the generalization performance of position network learning, but also turn the EEG signals set structured so that the multi-task Siamese network is used to effectively learn multiple relationships between samples. During the model testing phase, a balanced matching algorithm of single test sample VS multi-training sample is used to improve the robustness of the multi-task Siamese network model. The experimental results on the 5F motor imagery data set from The Largest SCP of Motor-Imagery, an EEG data signal repository, and data set4 of the 4th brain-computer interface (BCI) competition show that compared with the single-subtask Siamese network, EEGNet, ResNet-50 and the public experimental results of the original dataset, the multi-task Siamese network in this paper can obtain better multiclass motor imagery (MI) classification accuracy and can better realize the multi-classification of MI-EEG signals. This study could be helpful to promote the development of finger-based MI-BCI system. © 2023 SPIE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Secrecy Rate Threshold VS. An Optimum Power Splitting Factor Using Beamforming Technique in PHY Layer Security for MU-MIMO Systems 3

Secrecy Rate Threshold VS. An Optimum Power Splitting Factor...

引用

3rd IEEE International Maghreb Meeting of the Conference on sciences and Techniques of Automatic Control and computer engineering, MI-STA 2023

作者： Elhoula, Abeer A S Abousetta, Marai M. Ghmati, Tarek Saleh M. Libyan Academy School of Applied Science and Engineering Department of Electrical and Computer Engineering Libya Elemrgib University Al-Graboulli Faculty of Engineering Department of Electrical and Computer Engineering Libya

ISBN: (纸本)9798350319897

This paper describes a new approach to the problem of interception of wireless communication channels between the legitimate users. Physical PHY Layer Security (PLS) is new topic enhancing the secrecy performance of a Multi-User Multiple-Input-Multiple-Output (MU-MIMO) system for wireless communication from a single base-station to many users. Beamforming techniques such as "Pre-Maximum Ratio Combining (P-MRC) and Pre-Equal Gain Combining (P-EGC)"with assumption of perfect Channel State Information CSI is considered in order to achieve the perfect secure transmission between legitimate users. Along with beamforming, Artificial Noise (AN) is a technology that is being studied. The plotted achievable worst-case of secrecy rate down to the best secrecy rate value (threshold of secrecy rate) versus the power allocation fractions (The power splitting factor). The achieved threshold of secrecy rates for the implemented MU-MIMO were used by Matched Filter (MF) beamforming schemes (P-MRC) and (P-EGC) and suggested that the (P-MRC) is considered as an optimal beamforming technique in order to achieve a best secrecy rate or best threshold of secrecy rate for a nearest Information User (IU) to the Eavesdropper Eve. © 2023 IEEE.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

HTc Scanning SQUID Microscope with High Spatial Resolution for OLED Detection

HTc Scanning SQUID Microscope with High Spatial Resolution f...

引用

2023 IEEE International Conference on Applied Superconductivity and Electromagnetic Devices, ASEMD 2023

作者： Yang, Aoyue Wang, Hai Zhang, Zhidan He, Anran Kong, Xiangyan Ningbo China Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo China

ISBN: (纸本)9798350301571

Organic Light Emitting Diode (OLED) screens have advantages such as high brightness, self-illumination, wide color gamut, and have excellent market prospects. However, current optoelectronic testing methods are insufficient for OLED analysis after module packaging. This paper proposes a detection method using sensitive Superconducting QUantum Interference Device (SQUID) for packaged OLED screens with pixel sizes of one hundred micrometers and current changes of microamperes. An OLED simulation model is designed to verify the feasibility of magnetic detection, in which a magnetic flux guide probe is adopted to obtain high spatial resolution. We demonstrated the feasibility of magnetic detection and simulates the impact of probe parameters on system performance, and found that the smaller the angle, diameter, and total length of the probe, the better its performance is. © 2023 IEEE.

关键词： flux guide magnetic detection OLED SQUID

来源：评论

学校读者我要写书评

暂无评论

Optimization and evaluation of a mobile IMU-based ballistocardiography system

Optimization and evaluation of a mobile IMU-based ballistoca...

引用

作者： Klauth, Lucas Mühlen, Andreas Kitzig, Andreas Naroska, Edwin Stockmanns, Gudrun Faculty of Electrical Engineering and Computer Science Niederrhein University of Applied Sciences Krefeld Germany

In recent decades ballistocardiography (BCG) has regained popularity as a way to measure the mechanical activ- ity of the heart. In this paper we present and evaluate a new iteration of our mobile BCG measurement system. The pro- posed system uses an inertial measurement unit (IMU) placed on the carotid artery to derive the BCG. We conducted a mea- surement series to evaluate the system and to do an initial in- vestigation into whether more complex heart parameters can be derived from BCG data. The evaluation shows that heart rate (HR) and heart rate variability (HRV) calculated using BCG data, agrees well with the reference measurement and amplitudes calculated are mostly comparable in range to other papers. In conclusion, the system can reliably derive features from BCG data that can be used in further research. © 2023 the author(s), published by Walter de Gruyter Berlin/Boston.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

Portable Automatic System for Data Acquisition of Noise Pollution 2

Portable Automatic System for Data Acquisition of Noise Poll...

引用

2nd International Conference on Electronics and Renewable Systems, ICEARS 2023

作者： Ciufudean, Calin Buzduga, Corneliu Stefan Cel Mare University Faculty of Electrical Engineering and Computer Science Suceava Romania

ISBN: (纸本)9798350346640

Noise pollution, often referred to as forgotten pollution, has begun to be recognized as a problem for the environment and human health. This paper presents a new ultraportable system, AM-01, to perform data acquisition of noise pollution. The system is tested in various places from public institutions and companies to personal domicile. The AM-01 system is very useful for real time monitoring noise pollution on a map displayed a central dispatcher which monitories a large area considering its ease of handling, increased fidelity and outstanding mobility. Experimental results are shown as well as further development of the AM-01 system. © 2023 IEEE.

关键词： Data acquisition

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：