检索结果-内蒙古大学图书馆

FPGA-based acceleration for binary neural networks in edge computing

Journal of electronic science and technology 2023年第2期21卷 65-77页

作者： Jin-Yu Zhan An-Tai Yu Wei Jiang Yong-Jia Yang Xiao-Na Xie Zheng-Wei Chang Jun-Huan Yang School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu610054China School of Automation Chengdu University of Information TechnologyChengdu610225China State Grid Sichuan Electric Power Research Institute Chengdu610095China Department of Information Sciences and Technology George Mason UniversityFairfaxVA22030USA

As a core component in intelligent edge computing,deep neural networks(DNNs)will increasingly play a critically important role in addressing the intelligence-related issues in the industry domain,like smart factories and autonomous *** to the requirement for a large amount of storage space and computing resources,DNNs are unfavorable for resource-constrained edge computing devices,especially for mobile terminals with scarce energy *** of DNN has become a promising technology to achieve a high performance with low resource consumption in edge ***-programmable gate array(FPGA)-based acceleration can further improve the computation efficiency to several times higher compared with the central processing unit(CPU)and graphics processing unit(GPU).This paper gives a brief overview of binary neural networks(BNNs)and the corresponding hardware accelerator designs on edge computing environments,and analyzes some significant studies in *** performances of some methods are evaluated through the experiment results,and the latest binarization technologies and hardware acceleration methods are *** first give the background of designing BNNs and present the typical types of *** FPGA implementation technologies of BNNs are then *** comparison with experimental evaluation on typical BNNs and their FPGA implementation is further ***,certain interesting directions are also illustrated as future work.

关键词： Accelerator Binarization Field-programmable gate array(FPGA) Neural networks Quantification

来源：评论

学校读者我要写书评

暂无评论

Deploying Hybrid Ensemble Machine Learning Techniques for Effective Cross-Site Scripting(XSS)Attack Detection

引用

Computers, Materials & Continua 2024年第10期81卷 707-748页

作者： Noor Ullah Bacha Songfeng Lu Attiq Ur Rehman Muhammad Idrees Yazeed Yasin Ghadi Tahani Jaser Alahmadi School of Cyber Science and Engineering Huazhong University of Science and TechnologyWuhan430073China Department of Computer Science and Engineering University of Engineering and TechnologyLahore54000Pakistan Department of Computer Science and Software Engineering Al Ain UniversityAl Ain12555Abu Dhabi Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh84428Saudi Arabia

Cross-Site Scripting(XSS)remains a significant threat to web application security,exploiting vulnerabilities to hijack user sessions and steal sensitive *** detection methods often fail to keep pace with the evolving sophistication of cyber *** paper introduces a novel hybrid ensemble learning framework that leverages a combination of advanced machine learning algorithms—Logistic Regression(LR),Support Vector Machines(SVM),eXtreme Gradient Boosting(XGBoost),Categorical Boosting(CatBoost),and Deep Neural Networks(DNN).Utilizing the XSS-Attacks-2021 dataset,which comprises 460 instances across various real-world trafficrelated scenarios,this framework significantly enhances XSS attack *** approach,which includes rigorous feature engineering and model tuning,not only optimizes accuracy but also effectively minimizes false positives(FP)(0.13%)and false negatives(FN)(0.19%).This comprehensive methodology has been rigorously validated,achieving an unprecedented accuracy of 99.87%.The proposed system is scalable and efficient,capable of adapting to the increasing number of web applications and user demands without a decline in *** demonstrates exceptional real-time capabilities,with the ability to detect XSS attacks dynamically,maintaining high accuracy and low latency even under significant ***,despite the computational complexity introduced by the hybrid ensemble approach,strategic use of parallel processing and algorithm tuning ensures that the system remains scalable and performs robustly in real-time *** for easy integration with existing web security systems,our framework supports adaptable Application Programming Interfaces(APIs)and a modular design,facilitating seamless augmentation of current *** innovation represents a significant advancement in cybersecurity,offering a scalable and effective solution for securing modern web applications against evolving threats.

关键词： Cross-site scripting machine learning XSS detection stacking ensemble learning hybrid learning

来源：评论

学校读者我要写书评

暂无评论

FeBT: A Feature Balancing Transformer for Corporate ESG Forecasting

引用

IEEE Transactions on Knowledge and Data engineering 2025年第7期37卷 4063-4074页

作者： Li, Yawen Zhuang, Mengyu Ye, Guanhua Li, Yan Wang, Junheng Zhou, Jinyi Zhang, Pengfei Beijing University of Posts and Telecommunications School of Economics and Management Beijing China Beijing University of Posts and Telecommunications School of Computer Science National Pilot School of Software Engineering Beijing China University of Electronic Science and Technology of China School of Management and Economics Chengdu China University of Science and Technology Beijing School of Economics and Management Beijing China The University of Queensland School of Electrical Engineering and Computer Science Brisbane Australia

Environmental, social, and governance (ESG) serves as a crucial indicator for evaluating firms in terms of sustainable development. However, the existing ESG evaluation systems suffer from limitations, such as narrow coverage, subjective bias, and lack of timeliness. Therefore, there is a pressing need to leverage machine learning methods to predict the ESG performance of firms using their publicly available data. Traditional machine learning models encounter the feature imbalance problem due to the heterogeneity in ESG-related features. Common approaches typically involve unfolding all features, thereby granting highdimensional folding features greater exposure and accessibility to downstream models, which results in the neglect of lowdimensional features. To fill the research gap regarding fully using the heterogeneous features of enterprises to enhance AIbased ESG prediction performance, we propose the Feature Balancing Transformer (FeBT), a model based on autoencoders and Transformer blocks. FeBT incorporates a novel feature balancing technique that compresses and enhances high-dimensional features from imbalanced data into low-dimensional representations, thereby ensuring a more balanced impact of high-dimensional and low-dimensional features on the model's performance in the downstream ESG forecasting module. Extensive experiments verified the superior performance of FeBT compared with stateof-the-art methods in real-world ESG-related datasets and evidenced that our feature balancing module provides significant insights from high-dimensional folding features. © 1989-2012 IEEE.

关键词： Predictive Models Transformers Data Models Forecasting Accuracy Biological System Modeling Training Time Series Analysis Support Vector Machines Vectors ESG Forecasting Data Masking Time Series Forecasting Machine Learning Models Autoencoder High Dimensional Feature Transformer Block Time Series Support Vector Machine Time Series Data Linear Discriminant Analysis Air Quality Long Short Term Memory Recurrent Neural Network Attention Mechanism Final Prediction Transformer Model Word Embedding XG Boost Gated Recurrent Unit Linear Probe Air Quality Index Positional Encoding Multi Head Attention Mechanism Light GBM Traditional Transformation Compressed Representation Time Series Prediction Attention Heads Prediction Model K Nearest Neighbor Imbalance In Levels Latent Representation

来源：评论

学校读者我要写书评

暂无评论

HUID:DBN-Based Fingerprint Localization and Tracking System with Hybrid UWB and IMU

引用

China Communications 2023年第2期20卷 139-154页

作者： Junchang Sun Rongyan Gu Shiyin Li Shuai Ma Hongmei Wang Zongyan Li Weizhou Feng School of Information and Control Engineering China University of Mining and TechnologyXuzhou 221116China Peng Cheng Laboratory Shenzhen 518055China School of Information and Communications Engineering University of Electronic Science and Technology of ChinaChengdu 611731China

High-precision localization technology is attracting widespread attention in harsh indoor *** this paper,we present a fingerprint localization and tracking system to estimate the locations of the tag based on a deep belief network(DBN).In this system,we propose using coefficients as fingerprints to combine the ultra-wideband(UWB)and inertial measurement unit(IMU)estimation linearly,termed as a HUID *** particular,the fingerprints are trained by a DBN and estimated by a radial basis function(RBF).However,UWB-based estimation via a trilateral method is severely affected by the non-line-of-sight(NLoS)problem,which limits the localization *** tackle this problem,we adopt the random forest classifier to identify line-of-sight(LoS)and NLoS ***,we adopt the random forest regressor to mitigate ranging errors based on the identification results for improving UWB localization *** experimental results show that the mean square error(MSE)of the localization error for the proposed HUID system reduces by 12.96%,50.16%,and 64.92%compared with that of the existing extended Kalman filter(EKF),single UWB,and single IMU estimation methods,respectively.

关键词： Ultra-wideband(UWB) inertial measurement unit(IMU) fingerprints positioning NLoS identification estimated errors mitigation deep belief network(DBN) radial basis function(RBF)

来源：评论

学校读者我要写书评

暂无评论

ViF-SD2E: a robust weakly-supervised framework for neural decoding

引用

Neural Computing and Applications 2025年第9期37卷 6645-6661页

作者： Feng, Jingyi Luo, Yong Song, Shuang Hu, Han National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China School of Information and Electronics Beijing Institute of Technology Beijing100081 China

Neural decoding plays a vital role in the interaction between the brain and the outside world. Our task in this paper is to decode the movement track of a finger directly based on the neural data. Existing neural decoding solutions primarily perform some preprocessing operations on neural data before feeding them into existing models (such as LSTM) for decoding. However, these solutions either are prone to overfitting or cannot well exploit the spatial and temporal information. In our previous observations, there is a symmetrical phenomenon between the unsupervised decoded trajectory and the ground truth trajectory within the activity space. This precisely motivates us to propose (or derive) a robust weakly-supervised framework (or model structure), called ViF-SD2E, for neural decoding. In particular, it consists of a space-division (SD) module and an exploration–exploitation (2E) strategy, to effectively exploit both the spatial information of the outside world and the temporal information of neural activity, where the SD2E output is analogized with the weak 0/1 vision feedback (ViF) label for training. Extensive experiments demonstrate the effectiveness of our method, which can sometimes be comparable to supervised counterparts. Therefore, we redirect our attention to the information (hidden in data) ViF-SD2E conveys to us. In other words, we believe that the advantage of ViF-SD2E lies in the fact that its processing steps are objectively determined by the inherent attributes (i.e., symmetry) of the neural data, or rather, the model structure is fixed. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Space division multiple access

来源：评论

学校读者我要写书评

暂无评论

Design of a Miniaturized Low Sidelobe Slot Antenna Based on Dielectric Waveguide in X-band

Design of a Miniaturized Low Sidelobe Slot Antenna Based on ...

引用

2024 Photonics and Electromagnetics Research Symposium, PIERS 2024

作者： Ke, Huaijie Cao, Xin Cai, Qiangming Zhou, Longjian Zhu, Yuyu Yang, Wei Southwest University of Science and Technology School of Information Engineering Mianyang China South China University of Technology School of Electronic and Information Engineering Guangzhou China

ISBN: (纸本)9798350375909

In this paper, a miniaturized low sidelobe slot antenna based on dielectric waveguide in X-band is proposed. The proposed structure is based on multi-slot standing wave array with the Taylor synthesis method at the operating frequency around 9 GHz. The waveguide is filled with non-uniform substrate materials instead of air, which can miniaturize the size of the antenna structure. The proposed structure is full-wave simulated and optimized. It is shown from the simulated results that the size of the antenna has been reduced without significant attenuation of the antenna performance. At the same time, according to the influence of different dielectric filling materials on the electric field distribution of the waveguide antenna, the aspect ratio of the waveguide is designed and optimized by using the change rule of the antenna cutoff wavelength, and the optimal ratio is given. The results show that the volume of the slot array antenna can be reduced by about 2/3 after adding dielectric materials. The maximum gain of the antenna is greater than 13 dBi with the main lobe offset is about 7°. In addition, to further reduce the sidelobe level, a composite element surface is also proposed. The simulation results show that the antenna sidelobe has been reduced by 3.57 dB and 4.04 dB, respectively. The structure can be used in modern wireless communication circuit and radar system. © 2024 IEEE.

关键词： Antenna lobes

来源：评论

学校读者我要写书评

暂无评论

Optical Coupling in Atomic Waveguide for Vertically Integrated Photonics

引用

Research 2025年第1期2024卷 15-22页

作者： Yue Wang Junzhuan Wang Ruijuan Tian Jiapeng Zheng Lei Shao Bo Liu Fengqiu Wang Xuetao Gan Yi Shi Xiaomu Wang School of Electronic Science and Engineering Nanjing UniversityNanjing 210093China Key Laboratory of Light Field Manipulation and Information Acquisition Ministry of Industry and Information Technologyand Shaanxi Key Laboratory of Optical Information TechnologySchool of Physical Science and TechnologyNorthwestern Polytechnical UniversityXi'an 710129China Department of Physics The Chinese University of Hong KongHong Kong SARChina State Key Laboratory of Optoelectronic Materials and Technologies Guangdong Province Key Laboratory of Display Material and TechnologySchool of Electronics and Information TechnologySun Yat-sen UniversityGuangzhou 510275China Institute of Optics and Electronics Nanjing University of Information Science and TechnologyNanjing 210044China

Integrated 2-dimensional(2D)photonic devices such as monolayer waveguide has generated exceptional interest because of their ultimate *** particular,they potentially permit stereo photonic architecture through bond-free van der Waals ***,little is known about the coupling and controlling of the single-atom guided wave to its photonic environment,which governs the design and application of integrated ***,we report the optical coupling of atomically guided waves to other photonic *** directly probe the mode beating between evanescent waves in a monolayer 2D waveguide and a silicon photonic waveguide,which constitutes a vertically integrated *** mode-coupling measures the dispersion relation of the guided wave inside the atomic waveguide and unveils it strongly modifies matter's electronic states,manifesting by the formation of a propagating *** also demonstrated light modulating and spectral detecting in this compact nonplanar *** findings provide a generalizable and versatile platform toward monolithic 3-dimensional integrated photonics.

关键词： integrated systemherewe stereo photonic architecture photonic modes mode beating vertically integrated photonics atomically guided waves optical coupling atomic waveguide

来源：评论

学校读者我要写书评

暂无评论

A Neural Computing-Based Access Control Protocol for AI-Driven Intelligent Flying Vehicles in Industry 5.0-Assisted Consumer electronics

引用

IEEE Transactions on Consumer electronics 2024年第1期70卷 3573-3581页

作者： Mahmood, Khalid Tariq, Tayyaba Sangaiah, Arun Kumar Ghaffar, Zahid Saleem, Muhammad Asad Shamshad, Salman National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Douliu64002 Taiwan National Yunlin University of Science and Technology Department of Computer Science and Information Engineering Douliu64002 Taiwan National Yunlin University of Science and Technology International Graduate School of AI Douliu64002 Taiwan Lebanese American University Department of Electrical and Computer Engineering Byblos1102 2801 Lebanon University of Electronic Science and Technology of China School of Computer Science and Engineering Sichuan Chengdu611731 China The University of Lahore Department of Software Engineering Lahore54590 Pakistan

The continuous revolution in Artificial Intelligence (AI) has played a significant role in the development of key consumer applications, including Industry 5.0, autonomous decision-making, fault diagnosis, etc. In practice, autonomous and intelligent robots and flying vehicles (i.e., drones) are also becoming the integral part of Industry 5.0. These vehicles are attaining significant importance nowadays because of their applications in consumer electronics. However, there may be numerous privacy issues in such an infrastructure. Nevertheless, neural computing-driven security solutions have played a significant role in overcoming the security and privacy issues of AI-driven intelligent flying vehicles. Motivated by these facts, this article presents a neural computing-based access control protocol for AI-driven flying vehicles to prevent all possible security threats. A detailed security evaluation of the devised protocol is done formally using the extensively recognized Real-Or-Random (ROR) oracle model. Similarly, the informal security analysis ensures the resistance of our scheme against various potential attacks under the assumptions of CK and DY adversarial models. Moreover, detailed performance scrutiny of the devised protocol with various existing schemes shows the robustness and supremacy of our scheme in terms of computation, communication overhead, and security attributes. © 1975-2011 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Factors affecting forensic electric network frequency matching-A comprehensive study

引用

Digital Communications and Networks 2024年第4期10卷 1121-1130页

作者： Guang Hua Qingyi Wang Dengpan Ye Haijian Zhang Guoyin Wang Shuyin Xia School of Electronic Information Wuhan UniversityWuhan430072China Institute for Infocomm Research(I2R) Agency for ScienceTechnology and Research(A*STAR)Singapore138632Singapore School of Cyber Science and Engineering Wuhan UniversityWuhan430072China School of Computer Science and Technology Chongqing University of Posts and TelecommunicationsChongqing400065China

The power system frequency fluctuations could be captured by digital recordings and extracted to compare with a reference database for forensic timestamp *** is known as the Electric Network Frequency(ENF)criterion,enabled by the properties of random fluctuations and intra-grid *** essence,this is a task of matching a short random sequence within a long reference,whose accuracy is mainly concerned with whether this match could be uniquely *** this paper,we comprehensively analyze the factors affecting the reliability of ENF matching,including the length of test recording,length of reference,temporal resolution,and Signal-to-Noise Ratio(SNR).For synthetic analysis,we incorporate the first-order AutoRegressive(AR)ENF model and propose an efficient Time-Frequency Domain noisy ENF synthesis ***,the reliability analysis schemes for both synthetic and real-world data are respectively *** a comprehensive study,we quantitatively reveal that while the SNR is an important external factor to determine whether timestamp verification is viable,the length of test recording is the most important inherent factor,followed by the length of ***,the temporal resolution has little impact on ***,a practical workflow of the ENF-based audio timestamp verification system is proposed,incorporating the discovered results.

关键词： Digital forensics Audio forensics Data authentication Timestamp verification Electric network frequency criterion

来源：评论

学校读者我要写书评

暂无评论

BCS-YOLOv8s: A Detecting Method for Dense Small Targets in Remote Sensing Images Based on Improved YOLOv8s

IAENG International Journal of Computer Science

引用

IAENG International Journal of Computer science 2025年第2期52卷 417-426页

作者： Du, Wutao Ouyang, Xinyu Zhao, Nannan Ouyang, Yifan School of Electronic and Information Engineering University of Science and Technology Liaoning Liaoning Anshan114051 China School of Electrical Engineering and Artificial Intelligence Xiamen University Malaysia Selangor Darul Ehsan Sepang43900 Malaysia

The remote sensing image contains a lot of dense small targets, which increases the difficulty of object detection. The loss of small target feature information in feature fusion is rarely taken into account by the target detection algorithms used in remote sensing images today. A dense small object detection method based on improved YOLOv8s, namely BCSYOLOv8s, is proposed to address this issue. The innovation of the proposed method is mainly reflected in three aspects. First, the backbone network was modified to incorporate Bi-Level Routing Attention (BRA), a dynamic sparse attention mechanism, which increased the model’s concentration on tiny targets without appreciably changing its parameters. Second, CSNeck is employed as the neck of the model. Content-Aware ReAssembly of Features (CARAFE) is implemented as the upsampling module to minimize information loss of tiny targets in the feature combination. To enhance the model’s capacity to identify tiny targets, a detection head and small target detection layer are also incorporated. Thirdly, pre-selected frame regression may be made faster and more accurate by employing structured IoU (SIoU). The ultimate experimental findings demonstrate that BCS-YOLOv8s lowers the missed rate of tiny targets and enhances the model’s detection ability. The average detection accuracy (mAP) of this model on the DIOR dataset is 89.5%, which is 3.2% higher than the base model. Compared with other mainstream models such as YOLOv5 and YOLOv7, this model has better performance in all aspects. By using this strategy, the model’s capacity to recognize dense and tiny targets is successfully improved. © (2025), (International Association of Engineers). All rights reserved.

关键词： Proximity sensors

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：