检索结果-内蒙古大学图书馆

TTST: A Top-k Token Selective Transformer for Remote Sensing Image Super-Resolution

IEEE Transactions on Image Processing 2024年 33卷 738-752页

作者： Xiao, Yi Yuan, Qiangqiang Jiang, Kui He, Jiang Lin, Chia-Wen Zhang, Liangpei Wuhan University School of Geodesy and Geomatics Wuhan430079 China Harbin Institute of Technology School of Computer Science and Technology Harbin150001 China National Tsing Hua University Department of Electrical Engineering The Institute of Communications Engineering Hsinchu300 Taiwan Wuhan University State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan430079 China

Transformer-based method has demonstrated promising performance in image super-resolution tasks, due to its long-range and global aggregation capability. However, the existing Transformer brings two critical challenges for applying it in large-area earth observation scenes: (1) redundant token representation due to most irrelevant tokens;(2) single-scale representation which ignores scale correlation modeling of similar ground observation targets. To this end, this paper proposes to adaptively eliminate the interference of irreverent tokens for a more compact self-attention calculation. Specifically, we devise a Residual Token Selective Group (RTSG) to grasp the most crucial token by dynamically selecting the top-k keys in terms of score ranking for each query. For better feature aggregation, a Multi-scale Feed-forward Layer (MFL) is developed to generate an enriched representation of multi-scale feature mixtures during feed-forward process. Moreover, we also proposed a Global Context Attention (GCA) to fully explore the most informative components, thus introducing more inductive bias to the RTSG for an accurate reconstruction. In particular, multiple cascaded RTSGs form our final Top-k Token Selective Transformer (TTST) to achieve progressive representation. Extensive experiments on simulated and real-world remote sensing datasets demonstrate our TTST could perform favorably against state-of-the-art CNN-based and Transformer-based methods, both qualitatively and quantitatively. In brief, TTST outperforms the state-of-the-art approach (HAT-L) in terms of PSNR by 0.14 dB on average, but only accounts for 47.26% and 46.97% of its computational cost and parameters. The code and pre-trained TTST will be available at https://***/XY-boy/TTST for validation. © 1992-2012 IEEE.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Vision transformer-convolution for breast cancer classification using mammography images: A comparative study

引用

International Journal of Hybrid Intelligent Systems 2024年第2期20卷 67-83页

作者： Abimouloud, Mouhamed Laid Bensid, Khaled Elleuch, Mohamed Aiadi, Oussama Kherallah, Monji National Engineering School of Sfax University of Sfax Laboratory of Electrical Engineering (LAGE) University of KASDI Merbah Ouargla National School of Computer Science (ENSI) University of Manouba Artifcial Intelligence and Information Technology Laboratory (LINATI) Kasdi Merbah University Faculty of Sciences University of Sfax Advanced Technologies for Environment and Smart Cities (ATES Unit) University of Sfax

Breast cancer is a significant global health concern, highlighting the critical importance of early detection for effective treatment of women's health. While convolutional networks (CNNs) have been the best for analysing medical images, recent interest has emerged in leveraging vision transformers (ViTs) for medical data analysis. This study aimed to conduct a comprehensive comparison of three systems a self-attention transformer (VIT), a compact convolution transformer (CCT), and a tokenlearner (TVIT) for binary classification of mammography images into benign and cancerous tissue. Thorough experiments were performed using the DDSM dataset, which consists of 5970 benign and 7158 malignant images. The performance accuracy of the proposed models was evaluated, yielding results of 99.81% for VIT, 99.92% for CCT, and 99.05% for TVIT. Additionally, the study compared these results with the current state-of-the-art performance metrics. The findings demonstrate how convolution-attention mechanisms can effectively contribute to the development of robust computer-aided systems for diagnosing breast cancer. Notably, the proposed approach achieves high-performance results while also minimizing the computational resources required and reducing decision time. © 2024 - IOS Press. All rights reserved.

关键词： Breast cancer (BC) computer-aided diagnosis (CAD) convolutional networks (CNN) DDSM mammography vision transformers (VIT)

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial Introduction to the Special Section on Video and Language

引用

IEEE Transactions on Circuits and Systems for Video Technology 2022年第1期32卷 1-4页

作者： Mei, Tao Corso, Jason J. Kim, Gunhee Luo, Jiebo Shen, Chunhua Zhang, Hanwang Computer Vision and Multimedia Laboratory Jd Explore Academy *** Beijing100101 China Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI48109 United States Department of Computer Science and Engineering Seoul National University Gwanak-gu Seoul08826 Korea Republic of Department of Computer Science University of Rochester RochesterNY14627 United States College of Computer Science and Technology Zhejiang University Hangzhou310058 China School of Computer Science and Engineering Nanyang Technological University 639798 Singapore

computer Vision (CV) and Natural Language Processing (NLP) are two most fundamental disciplines under a broad area of artificial intelligence (AI). CV is regarded as a field of research that explores the techniques to teach computers to see and understand digital content such as images and videos. NLP is a branch of linguistics that enables computers to process, interpret, and even generate human language. With the rise and development of deep learning over the past decade, there has been a steady momentum of innovation and breakthroughs that convincingly push the limits and improve the state-of-the-art of both vision and language modeling. An interesting observation is that the research in the two areas starts to interact, with a significant growth in both the volume of publications and extensive applications. Meanwhile, many previous experiences have shown that this can naturally build up the circle of human intelligence.

关键词： Special issues and sections computer vision Question answering (information retrieval) Natural language processing Visual captioning

来源：评论

学校读者我要写书评

暂无评论

A Blockchain-Based Transactive Energy Management Scheme for Nano-Grids using Power Flow Coloring

A Blockchain-Based Transactive Energy Management Scheme for ...

引用

2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023

作者： Masood, Abdullah Bin Javaid, Saher Tan, Yasuo Vassiliou, Vasos Lestas, Marios University of Cyprus Department of Computer Science Nicosia Cyprus Cyens - Centre of Excellence Nicosia Cyprus Japan Advanced Institute of Science and Technology School of Information Science Ishikawa Japan Frederick University Department of Electrical Engineering Nicosia Cyprus

ISBN: (纸本)9798350324174

The proliferation of distributed energy resources (DER) and the widespread adoption of the Internet of Things (IoT) in Prosumer Nano-Grids (P-NGs) pose severe challenges in existing energy management schemes, thus necessitating the need for the development of novel solutions which can guarantee system efficiency and security. To address such challenges, we propose a novel scheme leveraging the benefits of distributed power flow coloring, blockchain technology, and Transactive Energy Management (TEM). The proposed system model offers P-NGs a secure, transparent, trustworthy, and efficient energy management and transactions platform that can: maintain the overall voltage stability and specified power ratios against power fluctuations within the P-NG, offer an increase in energy security, provide real-time monitoring, and reduce energy waste. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Energy Consumption Prediction of a CNC Machining Process With Incomplete Data

引用

IEEE/CAA Journal of Automatica Sinica 2021年第5期8卷 987-1000页

作者： Jian Pan Congbo Li Ying Tang Wei Li Xiaoou Li the State Key Laboratory of Mechanical Transmission Chongqing UniversityChongqing 400044China the Department of Electrical and Computer Engineering Rowan UniversityGlassboroNJ 08028 USA the Computer Science Department The Research and Advanced Studies Centre of the National Polytechnic InstituteMexico City 07360Mexico

Energy consumption prediction of a CNC machining process is important for energy efficiency optimization *** improve the generalization abilities,more and more parameters are acquired for energy prediction *** the data collected from workshops may be incomplete because of misoperation,unstable network connections,and frequent transfers,*** work proposes a framework for energy modeling based on incomplete data to address this ***,some necessary preliminary operations are used for incomplete data ***,missing values are estimated to generate a new complete data set based on generative adversarial imputation nets(GAIN).Next,the gene expression programming(GEP)algorithm is utilized to train the energy model based on the generated data ***,we test the predictive accuracy of the obtained *** experiments are designed to investigate the performance of the proposed framework with different rates of missing *** results demonstrate that even when the missing data rate increases to 30%,the proposed framework can still make efficient predictions,with the corresponding RMSE and MAE 0.903 k J and 0.739 k J,respectively.

关键词： Energy consumption prediction incomplete data generative adversarial imputation nets(GAIN) gene expression programming(GEP)

来源：评论

学校读者我要写书评

暂无评论

A novel method for the detection and classification of multiple diseases using transfer learning-based deep learning techniques with improved performance

引用

Neural Computing and Applications 2024年第30期36卷 18979-18997页

作者： Natarajan, Krishnamoorthy Muthusamy, Suresh Sha, Mizaj Shabil Sadasivuni, Kishor Kumar Sekaran, Sreejith Charles Gnanakkan, Christober Asir Rajan A.Elngar, Ahmed School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore India Tamil Nadu Perundurai Erode India Centre for Advanced Materials Qatar University Doha Qatar Department of Mechanical and Industrial Engineering Qatar University PO Box 2713 Doha Qatar Department of Electrical Engineering National Institute of Technology Assam Silchar India Department of Electrical and Electronics Engineering Puducherry Technological University Puducherry India Faculty of Computers and Artificial Intelligence Beni-Suef University Beni-Suef City62511 Egypt

A disease is a distinct abnormal state that significantly affects the functioning of all or part of an individual and is not caused by external harm. Diseases are frequently understood as medical conditions connected with distinct indications and symptoms. According to a fairly wide categorization, diseases can also be categorized as mental disorders, deficient diseases, genetic diseases, degenerative diseases, self-inflicted diseases, infectious diseases, non-infectious diseases, social diseases, and physical diseases. Prevention of the diseases is of multiple instances. Primary prevention seeks to prevent illness or harm before it ever happens. Secondary prevention tries to lessen the effect of an illness or damage that has already happened. This is done through diagnosing and treating illness or injury as soon as feasible to stop or delay its course, supporting personal ways to avoid recurrence or reinjury, and implementing programs to restore individuals to their previous health and function to prevent long-term difficulties. Tertiary prevention tries to lessen the impact of a continuing sickness or injury that has enduring repercussions. Diagnosis of the disease at an earlier stage is important for the treatment of the disease. Hence, in this study, deep learning algorithms, such as VGG16, EfficientNetB4, and ResNet, are utilized to diagnose various diseases, such as Alzheimer's, brain tumors, skin diseases, and lung diseases. Chest X-rays, MRI scans, CT scans, and skin lesions are used to diagnose the mentioned diseases. Transfer learning algorithms, such as VGG16, VGG19, ResNet, InceptionV3, and EfficientNetB4, are utilized to categorize various diseases. EfficientNetB4 with the learning rate annealing, having obtained an accuracy of 94.04% on the test dataset, is observed. As a consequence, we observed that every network has unique particular skills on the multi-disease dataset, which includes chest X-rays, MRI scans, etc., © The Author(s) 2024.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Assessing a BERT-based model for analyzing subjectivity and classifying academic articles

引用

Multimedia Tools and Applications 2024年第42期83卷 90511-90532页

作者： Mehmood, Atif Shahid, Farah Khan, Rizwan Ahmed, Shahzad Ibrahim, Mostafa M. Zheng, Zhonglong School of Computer Science and Technology Zhejiang Normal University Jinhua321002 China Zhejiang Institute of Photoelectronics & Zhejiang Institute for Advanced Light Source Zhejiang Normal University Zhejiang Jinhua321004 China Faculty of Information Technology Beijing University of Technology Beijing100024 China Department of Electrical Engineering Faculty of Engineering Minia University Minia61519 Egypt

The metaverse concept extends beyond virtual worlds and can be applied to collaborative analysis environments. Data analysts worldwide may read academic article extracts in real-time in a shared digital workplace to mine and analyze data using the metaverse. Furthermore, a semantic metaverse in natural language processing might also involve creating a digital environment with linguistic and semantic connections. Many dedicated researchers navigating the complexities of natural language processing in the metaverse era have spent considerable time searching for relevant papers. However, online reviews and evaluations of articles are helpful for their assistance and may save the researcher time. In this work, human specialists manually produced a dataset from four conferences and evaluated subjectively using rule-based techniques. Subsequently, we aim to evaluate the effectiveness of pre-trained word embeddings and pre-trained BERT models seamlessly integrated with convolutional neural networks. This endeavor focuses on the subjective analysis and classification of contributions and previous work sentences extracted from academic literature. For comparison, various deep learning architectures were systematically employed, including long short-term memory-GloVe and bi-directional long short-term memory-GloVe, alongside classical machine learning methods. Our findings show that the proposed BERT model achieved state-of-the-art performance in classification and subjective analysis tasks with an accuracy of 91.50% and F1 score of 91.00%. Finally, we plan to utilize sentence similarity to identify contributions within abstracts, thus outlining potential avenues for future research. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

HLSDataset: Open-Source Dataset for ML-Assisted FPGA Design using High Level Synthesis

arXiv

引用

arXiv 2023年

作者： Wei, Zhigang Arora, Aman Li, Ruihao John, Lizy The Laboratory for Computer Architecture Department of Electrical and Computer Engineering The University of Texas at Austin Austin United States

Machine Learning (ML) has been widely adopted in design exploration using high level synthesis (HLS) for faster resource, timing and power estimation at very early stages for FPGA-based design. To perform prediction accurately, high-quality and large-volume datasets are required for training ML models. However, the current datasets used in this domain are proprietary or limited in use, and practitioners have to generate their own dataset to train HLS-related ML models. This paper presents a dataset for ML-assisted FPGA design using HLS, called HLSDataset. The dataset is generated from widely used HLS C benchmarks including Polybench, Machsuite, CHStone and Rossetta. The Verilog samples are generated with a variety of directives including loop unroll, loop pipeline, and array partition to make sure optimized and realistic designs are covered. The total number of generated Verilog samples is nearly 9,000 per FPGA type. The dataset repository includes CSV (comma separated values) files containing both HLS and implementation metrics which can be easily consumed by ML model. We also include original C source code with directives, Verilog designs, post-HLS reports, post-implementation reports for each sample in the dataset, so that any metrics not present in the CSV can be easily extracted. In order to extend the dataset for future benchmarks, generation and extraction scripts are also provided. To demonstrate the effectiveness of our dataset, we undertake case studies to perform power estimation and resource usage estimation with ML models trained with our dataset. All the code and dataset are public at our github page1. We believe that HLSDataset can save valuable time for researchers by avoiding the tedious process of running tools, scripting and parsing files to generate the dataset, and enable them to spend more time where it counts, that is, in training ML models. © 2023, CC BY-NC-ND.

关键词： High level synthesis

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Images-Based Crop Classification Scheme for Agricultural Remote Sensing

引用

computer Systems science & engineering 2023年第7期46卷 303-319页

作者： Imran Ali Zohaib Mushtaq Saad Arif Abeer D.Algarni Naglaa F.Soliman Walid El-Shafai Department of Mechanical Engineering National Taiwan University of Science and TechnologyTaipei City106335TaiwanChina Department of Electrical Engineering Riphah International UniversityIslamabad44000Pakistan Department of Mechanical Engineering HITEC University TaxilaTaxila Cantt.47080Pakistan Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Electronics and Electrical Communications Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Security Engineering Laboratory Department of Computer SciencePrince Sultan UniversityRiyadh11586Saudi Arabia

Hyperspectral imaging is gaining a significant role in agricultural remote sensing *** data unit is the hyperspectral cube which holds spatial information in two dimensions while spectral band information of each pixel in the third *** classification accuracy of hyperspectral images(HSI)increases significantly by employing both spatial and spectral *** this work,the data was acquired using an airborne hyperspectral imager system which collected HSI in the visible and near-infrared(VNIR)range of 400 to 1000 nm wavelength within 180 spectral *** dataset is collected for nine different crops on agricultural land with a spectral resolution of 3.3 nm wavelength for each *** data was cleaned from geometric distortions and stored with the class labels and annotations of global localization using the inertial navigation *** this study,a unique pixel-based approach was designed to improve the crops'classification accuracy by using the edge-preserving features(EPF)and principal component analysis(PCA)in *** preliminary processing generated the high-dimensional EPF stack by applying the edge-preserving filters on acquired *** the second step,this high dimensional stack was treated with the PCA for dimensionality reduction without losing significant spectral *** resultant feature space(PCA-EPF)demonstrated enhanced class separability for improved crop classification with reduced dimensionality and computational *** support vector machines classifier was employed for multiclass classification of target crops using *** classification performance evaluation was measured in terms of individual class accuracy,overall accuracy,average accuracy,and Cohen kappa *** proposed scheme achieved greater than 90%results for all the performance evaluation *** PCA-EPF proved to be an effective attribute for crop classification using hyperspectral imaging in the VNIR *** proposed scheme

关键词： Hyperspectral imaging visible and near-infrared edge preserving feature dimensionality reduction crop classification

来源：评论

学校读者我要写书评

暂无评论

HLSDataset: Open-Source Dataset for ML-Assisted FPGA Design using High Level Synthesis

HLSDataset: Open-Source Dataset for ML-Assisted FPGA Design ...

引用

International Conference on Application Specific Systems (ASAP), architectures and Processors

作者： Zhigang Wei Aman Arora Ruihao Li Lizy John Department of Electrical and Computer Engineering The Laboratory for Computer Architecture The University of Texas at Austin Austin United States

Machine Learning (ML) has been widely adopted in design exploration using high level synthesis (HLS) for faster resource, timing and power estimation at very early stages for FPGA-based design. To perform prediction accurately, high-quality and large-volume datasets are required for training ML models. However, the current datasets used in this domain are proprietary or limited in use, and practitioners have to generate their own dataset to train HLS-related ML models. This paper presents a dataset for ML-assisted FPGA design using HLS, called HLSDataset. The dataset is generated from widely used HLS C benchmarks including Polybench, Machsuite, CHStone and Rossetta. The Verilog samples are generated with a variety of directives including loop unroll, loop pipeline, and array partition to make sure optimized and realistic designs are covered. The total number of generated Verilog samples is nearly 9,000 per FPGA type. The dataset repository includes CSV (comma separated values) files containing both HLS and implementation metrics which can be easily consumed by ML model. We also include original C source code with directives, Verilog designs, post-HLS reports, post-implementation reports for each sample in the dataset, so that any metrics not present in the CSV can be easily extracted. In order to extend the dataset for future benchmarks, generation and extraction scripts are also provided. To demonstrate the effectiveness of our dataset, we undertake case studies to perform power estimation and resource usage estimation with ML models trained with our dataset. All the code and dataset are public at our github page 1 1 https://***/UT-LCAIML4Accel-Dataset/tree/main/fpga_ml_dataset. We believe that HLSDataset can save valuable time for researchers by avoiding the tedious process of running tools, scripting and parsing files to generate the dataset, and enable them to spend more time where it counts, that is, in training ML models.

关键词：

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：