检索结果-内蒙古大学图书馆

Neural Machine Translation by Fusing Key Information of Text

Computers, Materials & Continua 2023年第2期74卷 2803-2815页

作者： Shijie Hu Xiaoyu Li Jiayu Bai Hang Lei Weizhong Qian Sunqiang Hu Cong Zhang Akpatsa Samuel Kofi Qian Qiu Yong Zhou Shan Yang School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu610054China Science and Technology on Altitude Simulation Laboratory Sichuan Gas Turbine Establishment Aero Engine Corporation of ChinaMianyang621000China School of Power and Energy Northwestern Polytechnical UniversityXi’an710072China School of Computer Science Southwest Petroleum UniversityChengdu610500China Department of Chemistry Physics and Atmospheric SciencesJackson State UniversityJacksonMS 39217USA

When the Transformer proposed by Google in 2017,it was first used for machine translation tasks and achieved the state of the art at that *** the current neural machine translation model can generate high quality translation results,there are still mistranslations and omissions in the translation of key information of long *** the other hand,the most important part in traditional translation tasks is the translation of key *** the translation results,as long as the key information is translated accurately and completely,even if other parts of the results are translated incorrect,the final translation results’quality can still be *** order to solve the problem of mistranslation and missed translation effectively,and improve the accuracy and completeness of long sentence translation in machine translation,this paper proposes a key information fused neural machine translation model based on *** model proposed in this paper extracts the keywords of the source language text separately as the input of the *** the same encoding as the source language text,it is fused with the output of the source language text encoded by the encoder,then the key information is processed and input into the *** incorporating keyword information from the source language sentence,the model’s performance in the task of translating long sentences is very *** order to verify the effectiveness of the method of fusion of key information proposed in this paper,a series of experiments were carried out on the verification *** experimental results show that the Bilingual Evaluation Understudy(BLEU)score of the model proposed in this paper on theWorkshop on Machine Translation(WMT)2017 test dataset is higher than the BLEU score of Transformer proposed by Google on the WMT2017 test *** experimental results show the advantages of the model proposed in this paper.

关键词： Key information transformer fusion neural machine translation

来源：评论

学校读者我要写书评

暂无评论

SWT-UNet: Medical Image Segmentation Based on Multi-modality UNet with Sliding Window Transformer Block

SWT-UNet: Medical Image Segmentation Based on Multi-modality...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Zhang, Yangqianhui Han, Dong Gang, Xiaoming Ma, Jiajun Yuan, Xu Zhejiang University School of Mechanical Engineering Hangzhou China Zhejiang University State Key Laboratory of Fluid Power and Mechatronic Systems Hangzhou China Anshan Municipal Central Hospital Anshan China Shenhua Hollysys Information Technology Co. Ltd Beijing China Dalian University of Technology School of Software Technology Dalian China

ISBN: (纸本)9798350337488

Medical images are information carriers that visually reflect and record the anatomical structure of the human body, and play an important role in clinical diagnosis, teaching and research, etc. Modern medicine has become increasingly inseparable from the intelligent processing of medical images. In recent years, there have been more and more attempts to apply deep learning theory to medical image segmentation tasks, and it is imperative to explore a simple and efficient deep learning algorithm for medical image segmentation. In this paper, we conduct research on multi-modal medical image segmentation algorithms with a hybrid architecture of Convolutional Neural Networks and Vision Transformer. This paper proposes a multi-modal medical image segmentation model SWT-UNet based on the CNN-ViT hybrid framework. The self-attention mechanism and sliding window design of the visual Transformer are used to capture the global feature association and break the limitation of the receptive field caused by the inductive bias of the convolution operation. At the same time, a widened self-attentive vector is used to streamline the number of modules and compress the model size, so as to fit the characteristics of a small amount of medical data, which makes the model easy to be overfitted. Experiments on two multi-modal medical image datasets validate that the algorithm can achieve efficient medical image segmentation at a lightweight scale. © 2023 IEEE.

关键词： attention mechanism medical image segmentation multi-modality Vision Transformer

来源：评论

学校读者我要写书评

暂无评论

Adaptive Scheme for Crowd Counting Using off-the-Shelf Wireless Routers

引用

Computer Systems Science & engineering 2022年第4期41卷 255-269页

作者： Wei Zhuang Yixian Shen Chunming Gao Lu Li Haoran Sang Fei Qian School of Computer and Software Nanjing University of Information Science&TechnologyNanjing210044China Engineering Research Center of Digital Forensics Ministry of EducationNanjing University of Information Science and TechnologyNanjing210044China School of Engineering&Technology University of WashingtonTacomaWA 98402USA China General Nuclear Power Group Nanjing210028China Jiangsu Province Hospital of Chinese Medicine Affiliated Hospital of Nanjing University of Chinese MedicineNanjing210029China

Since the outbreak of the world-wide novel coronavirus pandemic,crowd counting in public areas,such as in shopping centers and in commercial streets,has gained popularity among public health administrations for preventing the crowds from *** this paper,we propose a novel adaptive method for crowd counting based on Wi-Fi channel state information(CSI)by using common commercial wireless *** with previous researches on device-free crowd counting,our proposed method is more adaptive to the change of environ-ment and can achieve high accuracy of crowd count *** the dis-tance between access point(AP)and monitor point(MP)is typically non-ﬁxed in real-world applications,the strength of received signals varies and makes the tra-ditional amplitude-related models to perform poorly in different *** order to achieve adaptivity of the crowd count estimation model,we used convo-lutional neural network(ConvNet)to extract features from correlation coefﬁcient matrix of subcarriers which are insensitive to the change of received signal *** conducted experiments in university classroom settings and our model achieved an overall accuracy of 97.79%in estimating a variable number of participants.

关键词： CSI device-free deep learning crowd counting Wi-Fi wireless sensing

来源：评论

学校读者我要写书评

暂无评论

Attack against UAV Infrared Object Detection Based on Gradient Descent Method 7

Attack against UAV Infrared Object Detection Based on Gradie...

引用

7th IEEE International Conference on Information Systems and Computer Aided Education, ICISCAE 2024

作者： Xu, Mingkang Chen, Keyu Xu, Haoli Yang, Xing Lu, Jun Qu, Bin Gao, Haoqi Hu, Zhiyang Wu, Mengjiang Chen, Jun State Key Laboratory of Pulsed Power Laser College of Electronic Engineering National University of Defense Technology Hefei230037 China National University of Defense Technology Hefei China Jianghuai Advance Technology Center Hefei230000 China Key Laboratory of Electronic Restriction of Anhui Province Hefei230037 China College of Computer Science and Software Enginering Hohai University Nanjing211100 China

ISBN: (纸本)9798350350760

At present, infrared intelligent detection technology has been widely used in various fields. Due to the development of its technology, how to interfere with important targets such as intelligent recognition of vehicles has become a hot issue in the current technical field. Therefore, this study is based on the near-infrared band. We generate vehicle target confrontation samples to interfere with infrared detector devices. This paper proposes to first collect the single-band image of the protection target through the infrared UAV, and aligns it to align the position of the protection target in the single-band image to obtain the salient features of the protection target. Then, based on the loss function calculated by machine learning method, the adversarial samples of single-band images are generated by using the basic iterative method. The constraint function is used to jointly optimize the loss function, so that the attack of the adversarial samples on the single-band detection system of the infrared UAV can reach the target value, and the adversarial samples of the infrared image in this state are obtained. Then, it is arranged in multiple positions on the target vehicle to complete the interference to the infrared detection system. We first need to complete the simulation attack experiment in the digital domain, and then complete the confrontation with the infrared detector by using a special material that meets the requirements in the physical domain. The experimental results show that the attack success rate of this method has a certain effect. This paper has a certain reference for the future research of vehicle infrared reconnaissance and anti-reconnaissance. ©2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Enhancing software Defect Prediction Accuracy using Stacking Ensemble Model

Enhancing Software Defect Prediction Accuracy using Stacking...

引用

International Conference on Computer and Information technology (ICCIT)

作者： Md. Tanziar Rahman Sarhan Wasif Md. Abu Ismail Siddique Saifur Rahman Department of Software Engineering Nuclear Power Plant Company Bangladesh Limited Dhaka Bangladesh Department of Computer Science and Engineering Rajshahi University of Engineering and Technology Rajshahi Bangladesh Department of Electronics and Telecommunication Engineering Rajshahi University of Engineering and Technology Rajshahi Bangladesh

ISBN: (数字)9798331519094

ISBN: (纸本)9798331519100

software defect prediction is the culmination process in software development industries. software defect prediction using machine learning (ML) is an increasingly vital approach for improving software quality and reducing development costs by anticipating potential defects before they impact the final product. Machine learning models offer a powerful means to predict software defects by analyzing historical data and identifying patterns that indicate defect-prone areas. Different supervised and unsupervised classification models are used to predict software defect at early stage of development life cycle. But they face some challenges due to data quality and model adaptability. Recent advancements address these challenges through techniques such as ensemble learning, which combines predictions from multiple models to enhance accuracy and robustness. In our research, we have compared the predicted results using Support Vector Classifier (SVC), Extreme Gradient Boosting (XGB), Random Forest (RF) and Voting Classifier with our proposed stacking classifier designed with SVC, RF and XGB. In our experimental study, it shows that proposed stacking model outperforms in more accurate detection of software defects for multiple datasets. This research findings can greatly advance the effectiveness of defect prediction, contributing to the development of higher-quality software systems.

关键词： Analytical models Adaptation models Accuracy Computational modeling Stacking Static VAr compensators software quality Predictive models software Vectors

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of PV Integrated NPC Multilevel Inverter-Based Unified power Quality conditioners

Performance Analysis of PV Integrated NPC Multilevel Inverte...

引用

Renewable Energy and Hydrogen Technologies (GlobConHT), IEEE IAS Global Conference on

作者： Anisha Heenkenda Ahmed Elsanabary Mehdi Seyedmahmoudian Saad Mekhilef Alex Stojcevski Nur Fadilah Ab Aziz Department of Software and Electrical Engineering Swinburne Univeristy of Technology Melbourne Australia Institute of Power Engineering Universiti Tenaga Nasional Kajang Malaysia

Unified power Quality Conditioners are used frequently in modern distribution networks to eliminate power quality issues. Furthermore, compared to other existing power quality enhancement devices, UPQCs can concurrently improve both voltage and current profiles. To enhance their power quality issue compensation capability, multilevel inverters can replace the traditional two-level inverters in UPQCs. This study aims to investigate the behavior of diode-clamped multilevel inverters based UPQC when integrated with a Photovoltaic system in the presence of non-linear loads. Finally, a MATLAB/Simulink simulation was conducted to observe the performance of the proposed UPQC configuration by utilizing synchronous reference frame (SRF) and hysteresis control methods. The simulation results when obtained from both control strategies were compared to identify which method can improve the operating capability of the proposed UPQC configuration.

关键词： Photovoltaic systems Renewable energy sources Simulation power quality Hydrogen Multilevel inverters Performance analysis

来源：评论

学校读者我要写书评

暂无评论

QoS Prediction Model of Cloud Services Based on Deep Learning

引用

IEEE/CAA Journal of Automatica Sinica 2022年第3期9卷 564-566页

作者： WenJun Huang PeiYun Zhang YuTong Chen MengChu Zhou Yusuf Al-Turki Abdullah Abusorrah Nanjing University of Information Science&Technology School of Computer and SoftwareNanjingChina IEEE New Jersey Institute of Technology Helen and John C.Hartmann Department of Electrical and Computer EngineeringNewarkUSA Center of Research Excellence in Renewable Energy and Power Systems Department of Electrical and Computer EngineeringFaculty of Engineeringand K.A.CARE Energy Research and Innovation CenterKing Abdulaziz UniversityJeddah 21589Saudi Arabia

Dear editor,This letter presents a deep learning-based prediction model for the quality-of-service(QoS)of cloud ***,to improve the QoS prediction accuracy of cloud services,a new QoS prediction model is proposed,which is based on multi-staged multi-metric feature fusion with individual *** multi-metric features include global,local,and individual *** results show that the proposed model can provide more accurate QoS prediction results of cloud services than several state-of-the-art methods.

关键词： services Services individual

来源：评论

学校读者我要写书评

暂无评论

A Deployment Scheme of YOLOv5 with Inference Optimizations Based on the Triton Inference Server 6

A Deployment Scheme of YOLOv5 with Inference Optimizations B...

引用

6th IEEE International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2021

作者： Fang, Jiacong Liu, Qiong Li, Jingzheng School of Software Engineering South China University of Technology Guangzhou China Zhuhai Unitech Power Technology Company Ltd China

ISBN: (纸本)9780738105338

Object detection constitutes a large part of computer vision applications. You Only Look Once (YOLO) v5 is a salient object detection algorithm that provides high accuracy and real-time performance. This paper illustrates a deployment scheme of YOLOv5 with inference optimizations on Nvidia graphics cards using an open-source deep-learning deployment framework named Triton Inference Server. Moreover, we developed a non-maximum suppression (NMS) operator with dynamic-batch-size support in TensorRT to accelerate inference. The experimental results show that both throughput and latency are improved significantly through our deployment scheme. © 2021 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

FedIERF: Federated Incremental Extremely Random Forest for Wearable Health Monitoring

引用

Journal of Computer Science & technology 2023年第5期38卷 970-984页

作者：胡春雨忽丽莎袁林陆佃杰吕蕾陈益强 Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science Center(National Supercomputer Center in Jinan)Qilu University of Technology(Shandong Academy of Sciences)Jinan 250353China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer ScienceJinan 250000China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan 25000China Institute of Information Technology Hebei University of Economics and BusinessShijiazhuang 050061China School of Information Science and Engineering Shandong Normal UniversityJinan 250358China Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China

Wearable health monitoring is a crucial technical tool that offers early warning for chronic diseases due to its superior portability and low power ***,most wearable health data is distributed across dfferent organizations,such as hospitals,research institutes,and companies,and can only be accessed by the owners of the data in compliance with data privacy *** first challenge addressed in this paper is communicating in a privacy-preserving manner among different *** second technical challenge is handling the dynamic expansion of the federation without model *** address the first challenge,we propose a horizontal federated learning method called Federated Extremely Random Forest(FedERF).Its contribution-based splitting score computing mechanism significantly mitigates the impact of privacy protection constraints on model *** on FedERF,we present a federated incremental learning method called Federated Incremental Extremely Random Forest(FedIERF)to address the second technical *** introduces a hardness-driven weighting mechanism and an importance-based updating scheme to update the existing federated model *** experiments show that FedERF achieves comparable performance with non-federated methods,and FedIERF effectively addresses the dynamic expansion of the *** opens up opportunities for cooperation between different organizations in wearable health monitoring.

关键词： federated learning incremental learning random forest wearable health monitoring

来源：评论

学校读者我要写书评

暂无评论

Efficient Scheduling Mapping Algorithm for Row Parallel Coarse-Grained Reconfigurable Architecture

引用

Tsinghua Science and technology 2021年第5期26卷 724-735页

作者： Naijin Chen Zhen Wang Ruixiang He Jianhui Jiang Fei Cheng Chenghao Han School of Computer and Information Science Anhui Polytechnic UniversityWuhu 241000China School of Computer Science and Technology Shanghai University of Electric PowerShanghai 200090China School of Software Engineering Tongji UniversityShanghai 201804China

Row Parallel Coarse-Grained Reconfigurable Architecture(RPCGRA)has the advantages of maximum parallelism and programmable *** an efficient algorithm to map the diverse applications onto RPCGRA is difficult due to a number of RPCGRA hardware *** solve this problem,the nodes of the data flow graph must be partitioned and scheduled onto the *** this paper,we present a Depth-First Greedy Mapping(DFGM)algorithm that simultaneously considers the communication costs and the use times of the Reconfigurable Cell Array(RCA).Compared with level breadth mapping,the performance of DFGM is *** percentage of maximum improvement in the use times of RCA is 33%and the percentage of maximum improvement in non-original input and output times is 64.4%(Given Discrete Cosine Transfor 8(DCT8),and the area of reconfigurable processing unit is 56).Compared with level-based depth mapping,DFGM also obtains the lowest averages of use times of RCA,non-original input and output times,and the reconfigurable time.

关键词： temporal mapping Reconfigurable Cell Array(RCA) listed scheduling communication costs

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：