检索结果-内蒙古大学图书馆

IEEE Networking Letters 2024年第4期6卷 247-251页

作者： Barkatsa, Sofia Diamanti, Maria Charatsaris, Panagiotis Tsiropoulou, Eirini Eleni Papavassiliou, Symeon Institute of Communication and Computer Systems School of Electrical and Computer Engineering National Technical University of Athens Zografou15780 Greece University of New Mexico Department of Electrical and Computer Engineering AlbuquerqueNM87131 United States

Federated Learning (FL), an emerging distributed Artificial Intelligence (AI) technique, is susceptible to jamming attacks during the wireless transmission of trained models. In this letter, we introduce a jamming attack mitigation mechanism for the uplink of wireless FL networks using the power-domain Non-Orthogonal Multiple Access (NOMA) technique. The problem of transmission power allocation for all clients (legitimate and malicious) is formulated and solved distributively as a Bayesian game with incomplete information. The clients aim to successfully transmit their model parameters, minimizing transmission time and consumed power, while having probabilistic knowledge about the malicious behavior of the other clients in the game. © 2019 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Leveraging feature fusion ensemble of VGG16 and ResNet-50 for automated potato leaf abnormality detection in precision agriculture

引用

Soft Computing 2025年第4期29卷 2263-2277页

作者： Trivedi, Amit Kumar Mahajan, Tripti Maheshwari, Tanmay Mehta, Rajesh Tiwari, Shailendra Department of Computer Science and Engineering Thapar Institute of Engineering and Technology Punjab Patiala147001 India

In the era of advancement in technology and modern agriculture, early disease detection of potato leaves will improve crop yield. Various researchers have focussed on disease due to different types of microbial infection in potato leaves using computer vision and machine learning approaches. In this paper, a data science approach for multiclass classification of potato normal and abnormal leaves due to fungal infection like early blight and late blight is performed using the ensembling of deep learning (DL) CNN models. Firstly, the performance of classification on potato disease is verified separately on VGG16 and ResNet-50 CNN models after pre-processing of the leaf dataset. The pre-processing includes noise removal and normalization. Further improvement in classification accuracy is achieved by the ensembling of VGG16 and ResNet-50 CNN models. The ensembling of CNN models is performed on the feature level by fusing features extracted using VGG16 and ResNet-50. From the experimental results, performed on publicly available datasets consisting of 2152 number of normal and abnormal images it is observed that the average classification accuracy of 98.22%, 96.16% and 95.68% is achieved using the proposed ensemble, VGG16 and ResNet-50 models respectively. The efficacy of the proposed approach (ensemble technique at feature level fusion) is verified in comparison with recently reported DL model-based approaches. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Daisy-Chaining Embedded Processors for Enhanced Capacitive Sensor Array Resolution

Daisy-Chaining Embedded Processors for Enhanced Capacitive S...

引用

2024 IEEE Green Technologies Conference, GreenTech 2024

作者： Komanduri, Abhinav Nelson, Alexander University of Arkansas Department of Electrical Engineering and Computer Science United States

ISBN: (纸本)9798350308587

Capacitive sensing technology is widely applied in ubiquitous sensing. Its low-power consumption enables it to be used in a wide variety of Industry 4.0 applications. Capacitive Sensors can be combined into Arrays (CSAs) with mutual capacitive sensing to reduce external wiring requirements. For instance, the Texas Instruments (TI) MSP430FR2676 can capture and process data from 8×8 capacitive sensor grids. However, it is limited to supporting only 64 sensors. We propose a design incorporating daisy-chaining of CSAs via the I2C serial protocol to enable support for 256 sensors. We also demonstrate a rapid prototyping implementation of 128 sensors. The extended work we plan is to implement the prototype on custom Printed Circuit Boards (PCB) and maximize data update frequency. This architecture can find relevance in industries like manufacturing and farming, enhancing precision in the interaction between robots and huma ns/objects. © 2024 IEEE.

关键词： Embedded systems

来源：评论

学校读者我要写书评

暂无评论

ViT-LSTM synergy: a multi-feature approach for speaker identification and mask detection

引用

Neural Computing and Applications 2024年第35期36卷 22569-22586页

作者： Nassif, Ali Bou Shahin, Ismail Bader, Mohamed Ahmed, Abdelfatah Werghi, Naoufel Department of Computer Engineering University of Sharjah Sharjah United Arab Emirates Department of Electrical Engineering University of Sharjah Sharjah United Arab Emirates Department of Electrical Engineering and Computer Sciences Khalifa University Abu Dhabi United Arab Emirates

The global health crisis caused by the COVID-19 pandemic has brought new challenges to speaker identification systems, particularly due to the acoustic alterations caused by the widespread use of face masks. Aiming to mitigate these distortions and improve the accuracy of speaker identification, this study introduces a novel two-level classification system, leveraging a unique integration of Vision Transformers (ViT) and Long Short-Term Memory (LSTM). This ViT-LSTM model was trained and tested on an extensive dataset composed of diverse speakers, both masked and unmasked, allowing a comprehensive evaluation of its capabilities. Our experimental results demonstrate remarkable improvements in speaker identification, with an accuracy score of 95.67%, significantly surpassing traditional and other deep learning-based methods. Moreover, our framework also shows considerable strength in detecting the presence of a mask, achieving an accuracy of 91.15% and outperforming existing state-of-the-art models. This study provides the first-ever benchmark for mask detection in the context of speaker identification, opening new pathways for research in this emerging area and presenting a robust solution for speaker identification in the era of face masks. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Kinmen Wind Lion Face Generation Based on the Deep Convolutional Generative Adversarial Network 13

Kinmen Wind Lion Face Generation Based on the Deep Convoluti...

引用

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

作者： Wu, Chia-Huan Zhao, Yu-Xiang Chou, Cheng-Hou Hsieh, Yi-Zeng National Taiwan University of Science and Technology Department of Electrical and Computer Engineering Taiwan National Quemoy University Department of Computer Science and Information Engineering Taiwan

ISBN: (纸本)9798350355079

Under the advancements of science and technology at present, artificial intelligence has become widely applied in daily life. Hence, deep learning has attracted much attention in recent years and has been widely used in recognition, classification and generation. The results generated by generative adversarial networks have become increasingly realistic and are now being applied to human face generation and reconstruction. Among the various technologies, the deep convolutional generative adversarial network (DCGAN) is more widely used. Based on the trained DCGAN of human and cat faces, this paper collected Kinmen wind lion data by YOLOv3 and crawler technology and transferred the data to the DCGAN of wind lions through network-based transfer learning to generate complete wind lion faces. The experimental process consisted of four parts. The wind lion dataset was directly used to train the DCGAN in the first two parts, and the DCGAN of the human and cat faces was used for transfer learning in the second two parts. According to the results, the training effect of human face-based transfer learning was the best and was the closest to Kinmen's wind lions. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

An Ant-colony Based Model for Load Balancing in Fog Environments

Supercomputing Frontiers and Innovations

引用

Supercomputing Frontiers and Innovations 2023年第1期10卷 4-20页

作者： Mirtaheri, Seyedeh Leili Azari, Mahya Greco, Sergio Arianian, Ehsan Department of Electrical and Computer Engineering Faculty of Engineering Kharazmi University Tehran Iran Faculty of Mathematics and Computer Science Kharazmi University Tehran Iran Department of Computer Engineering Modeling Electronics and Systems University of Calabria Italy Tehran Iran

Delay-sensitive applications are becoming more and more in demand as a result of the development of information systems and the expansion of communication in cloud computing technologies. Some of these requests will be overlooked in cloud environments due to the communication delay between the processing center and the client’s request. The ‘fog-based computing paradigm’, a novel processing model, can be added to cloud computing to help with the aforementioned issues. The performance of computing systems is always influenced by latency. In this paper, we focus on balancing the load on the fog nodes to lower the latency. It is also a crucial component of fog computing devices. It necessitates the use of load-balancing algorithms to select the optimal hosts, resulting in an even distribution of the load on the available *** provide a load-balancing approach based on the Ant-colony optimization algorithm’s latency rate for responding to tasks. A random data set evaluation of this model reveals shorter response times than those of earlier strategies suggested in this field. © The Authors 2023. This paper is published with open access at ***

关键词： Fog

来源：评论

学校读者我要写书评

暂无评论

A BERT-encoded ensembled CNN model for suicide risk identification in social media posts

引用

Neural Computing and Applications 2024年第18期36卷 10955-10970页

作者： Gorai, Joy Shaw, Dilip Kumar Department of Computer Science and Engineering National Institute of Technology Jamshedpur India

Suicide is a significant public health issue that devastates individuals and society. Early warning systems are crucial in preventing suicide. The purpose of this research is to create a deep learning model to identify suicide risk using a combination of bidirectional encoder representations from transformers (BERT) and an ensemble of multiple convolutional neural networks (CNN). BERT is used to encode the text data into numerical representations that capture the context-aware meaning of words and phrases, while ensemble CNN is used to analyze the encoded text data to identify patterns and relationships relevant to suicide risk. The model is trained on a large corpus of text data from social media and suicide notes and evaluated on a validation set of labeled data. The results of the proposed model perform better than the recent approaches in detecting suicide risk and can potentially be a valuable tool for suicide prevention efforts. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Towards Sustainable and Efficient Rapid Prototyping of Capacitive Sensor Arrays

Towards Sustainable and Efficient Rapid Prototyping of Capac...

引用

2024 IEEE Green Technologies Conference, GreenTech 2024

作者： Rathbun, Russell Nelson, Alexander University of Arkansas Department of Electrical Engineering and Computer Science United States

ISBN: (纸本)9798350308587

Capacitive sensors are common ubiquitous sensing devices that permeate through many industries. The overwhelming majority of touchscreens use capacitive sensor arrays for the precise detection of touch. Many MEMS sensors use capacitance as the variable that is manipulated to detect the sensed parameter (e.g. accelerometers). However, the use of non-rigid, ambient, or custom capacitive sensor arrays has not seen the same level of adoption. CSAs (capacative sensor arrays) can be made from a wide array of materials and techniques-including 3d printing and laser ablation-to rapidly create CSAs that can be custom fit to enable proximity, force, and touch detection. This work investigates some of these materials and how they can be fabricated in a laboratory environment with a single robotic arm. © 2024 IEEE.

关键词： Capacitive sensors

来源：评论

学校读者我要写书评

暂无评论

Light People:*** Dai,*** Lo,and *** Su-innovators in silicon photonics

引用

Light(science & Applications) 2024年第12期13卷 2880-2885页

作者： Yating Wan Chenzi Guo Electrical and Computer Engineering the ComputerElectrical and Mathematical Sciences and Engineering DivisionKing Abdullah University of Science and Technology23955-6900 ThuwalSaudi Arabia Changchun Institute of Optics Fine Mechanics and PhysicsChinese Academy of SciencesChangchunChina

In this edition of Light People,we are excited to feature *** Dai(Zhejiang University),*** Su(Shanghai Jiao Tong University),and *** Lo(Advanced Micro Foundry Pte Ltd,Singapore),three prominent researchers shaping the future of silicon *** collaborative work addresses critical issues in silicon photonics,including reducing propagation losses,enlarging the functionalities and enhancing building blocks,integrating efficient laser sources,expanding applications,and pushing the boundaries of optical and electronic *** this interview,we delve into their academic journeys,challenges,and future visions,offering insights into the ongoing evolution of silicon photonics and its potential to transform *** a deeper exploration of their experiences and advice,the full interview is available in the Supplementary material.

关键词： interview offering photonics

来源：评论

学校读者我要写书评

暂无评论

Ephemeris and Timing Error Disambiguation Enabling Precise LEO PNT

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年第3期61卷 6138-6153页

作者： Saroufim, Joe Kassas, Zaher M. The Ohio State University Department of Electrical and Computer Engineering ColumbusOH43210 United States

The ephemeris and timing errors of low Earth orbit (LEO) satellites are modeled, leading to an approach to disambiguate these errors from pseudorange-type measurements. First, a model is derived describing the ephemeris error's impact on ranging measurements from LEO space vehicles (SVs) with imprecise ephemerides. A simulation study is presented comparing the impact of ephemeris error on ranging error for 5 LEO constellations (Statlink, OneWeb, Orbcomm, Iridium, and Globalstar) and 5 medium Earth orbit (MEO) constellations (GPS, GLONASS, Galileo, BeiDou-3, and O3B). Second, it is shown that for a particular SV position, the ephemeris error has no effect on range measurements. Next, the ephemeris and timing errors are parametrized by the three-dimensional (3-D) ephemeris error magnitude and its direction angle from the in-track axis. This parametrization is exploited in a proposed algorithm to disambiguate the ephemeris and timing error from the LEO SVs' pseudorange measurements at a reference receiver. The two parameters can be communicated to any unknown receiver listening to the same LEO SVs to correct for ephemerides ranging error, leading to improved positioning, navigation, and timing (PNT) precision. Monte Carlo simulation results are presented demonstrating the efficacy of the proposed algorithm. The simulations considered a reference receiver tracking via pseudorange measurements 22 Starlink and 4 OneWeb LEO SVs with poorly known ephemerides (obtained from two-line element (TLE) files, propagated with SGP4). The proposed algorithm reduced the 3-D position error of all SVs from a few kilometers to less than 120 m. The parameters were communicated to an unknown receiver to correct the LEO ephemerides, after which the receiver estimated its position by fusing its LEO pseudoranges via an extended Kalman filter (EKF), resulting in a horizontal position error of 0.91 m, as compared to 213 m utilizing TLE+SGP4 ephemerides. Two sets of experimental results are pres

关键词： Extended Kalman filters

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：