检索结果-内蒙古大学图书馆

Salix-Leaf: Find Main Veins of Signal Clusters for Practical Parallel Decoding

IEEE Transactions on Mobile Computing 2025年

作者： Li, Yajun Zhao, Jumin Li, Dengao Wu, Hejun Xu, Shuang Bai, Ruiqin Taiyuan University of Technology College of Electronic Information and Optical Engineering Taiyuan China Key Laboratory of Big Data Fusion Analysis and Application of Shanxi Province Taiyuan China Intelligent Perception Engineering Technology Center of Shanxi Taiyuan China Taiyuan University of Technology College of Computer Science and Technology College of Data Science Taiyuan China Sun Yat-sen University Department of Computer Science Guangzhou China

Parallel decoding of backscatter improves communication throughput by enabling concurrent transmission of backscatter tags. In practical applications of parallel decoding, it is extremely difficult to distinguish collided signals in superclusters where multiple signal clusters overlap. Existing methods are usually effective for superclusters with uniformly distributed signals. Nevertheless, there are many more scenarios in which signals in superclusters tend to gather unevenly, and existing methods cannot work. Such uneven clustering of signals occurs due to the following two possible causes: (1) signal-strengthdifferences (SSDs) among tags;or (2) cluster drifting (CD) driven by interferences from other objects within communication environments. This paper proposes a novel scheme called SalixLeaf, which aims to identify the main veins of signal clusters to address this problem of superclusters with unevenly distributed signals. Salix-Leaf identifies the main vein of each signal cluster for fine-grained clustering so that the direction of the main veins can be used to verify the accuracy of clustering. In addition, SalixLeaf employs a supercluster decomposer that divides signals into different segments for clustering analysis, enhancing robustness and practicability. Experimental results show that Salix-Leaf achieves a 1.2-fold increase in throughput and a 25% reduction in bit error rate (BER) compared to the state-of-the-art. © 2002-2012 IEEE.

关键词： Backscattering

来源：评论

学校读者我要写书评

暂无评论

Fast extraction of winter wheat planting area in Huang-Huai-Hai Plain using high-resolution satellite imagery on a cloud computing platform

引用

International Journal of Agricultural and Biological Engineering 2022年第1期15卷 241-250页

作者： Dongyan Zhang Mengru Zhang Fenfang Lin Zhenggao Pan Fei Jiang Liang He Hang Yang Ning Jin National Engineering Research Center for Agro-Ecological Big Data Analysis&Application Anhui UniversityHefei 230601China Key Laboratory of Geospatial Technology for Middle and Lower Yellow River Regions(Henan University) Ministry of EducationKaifeng 475004HenanChina School of Informatics and Engineering Suzhou UniversitySuzhou 234000AnhuiChina National Meteorological Center Beijing 100081China Aerospace Information Research Institute Chinese Academy of ScienceBeijing 100101China

To extract regional winter wheat planting area using higher-resolution satellite imagery still faces many challenges due to large data size and long processing time in traditional remote sensing *** Earth Engine(GEE),a cloud computing analysis platform based on global geospatial analysis,provides a new opportunity for rapid analysis of remote sensing *** this study,high-quality Landsat-8 imagery was used to extract the winter wheat planting area from the Huang-Huai-Hai Plain in *** random forest algorithm was used to identify and map the winter wheat sown in 2019 and harvested in 2020,and Sentinel-2 imagery was used to verify the *** spectral indices,texture,and terrain features of the image were derived,and their contribution to the classification accuracy of winter wheat was evaluated by *** the top nine features were selected to form an optimal feature *** the set of thirty-four features and the optimized feature subset as the input variables of the random forest classifier,the results show that the accuracy difference between the two feature classification schemes is small,but the classification effect of all feature sets is slightly better than the optimal feature *** overall classification accuracy of sample plots verification was 86%-95%,the Kappa coefficient was between 0.7 and 0.85,and the percentage error of the total area was 5.42%.The research demonstrates a reliable method for mapping a wide range of winter wheat planting area,and provides a good prospect for exploring the precise mapping of other crops,which is of great significance to crop monitoring and agricultural development.

关键词： Google Earth Engine regional scale winter wheat rapid mapping

来源：评论

学校读者我要写书评

暂无评论

Graph Structure Prefix Injection Transformer for Multi-Modal Entity Alignment

SSRN

引用

SSRN 2024年

作者： Li, Zhifei Luo, Xiangyu Zhang, Miao Zhang, Yan Xiao, Kui School of Computer Science and Information Engineering Hubei University Wuhan430062 China School of Cyber Science and Technology Hubei University Wuhan430062 China Key Laboratory of Intelligent Sensing System and Security Hubei University Ministry of Education Wuhan430062 China Hubei Key Laboratory of Big Data Intelligent Analysis and Application Hubei University Wuhan430062 China

Multi-modal entity alignment aims to integrate equivalent entities in diverse multi-modal knowledge graphs. However, previous studies have primarily focused on multi-modal fusion methods without considering the impact of graph structure heterogeneity on entity alignment tasks due to the distinct structural features of different knowledge graphs. Moreover, the multi-modal information that enriches entity representations, including image, textual content, and numerical attributes, frequently incorporates noise due to modal discrepancies. To tackle these challenges, we introduce the Graph Structural Prefix Injection transformer (GSIEA) for multi-modal entity alignment. This novel approach minimizes structural heterogeneity’s impact and optimizes structural data utilization by integrating a structural prefix inject interaction module within the multi-head attention mechanism. Then, we adopt a convolutional enhancement module to extract local features of multi-modal information and complete feature fusion by cross-modal weights. Extensive experiments on two datasets demonstrate that GSIEA outperforms previous baseline models, showcasing an average performance improvement of 3.26% on MRR, with a maximum enhancement of 12.5%. Additionally, the average performance improvement on Hits@1 is 4.96%, with a maximum enhancement of 16.92%. Our code is available at https://***/HubuKG/GSIEA. © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Collaborative List-and-Pairwise Filtering from Implicit Feedback : Extended Abstract

Collaborative List-and-Pairwise Filtering from Implicit Feed...

引用

International Conference on data Engineering

作者： Runlong Yu Qi Liu Yuyang Ye Mingyue Cheng Enhong Chen Jianhui Ma Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China Hefei China Management Science and Information Systems Rutgers Business School Rutgers University Newark USA

Collaborative filtering (CF) from implicit datasets has attracted much attention in recent years. The current mainstream pairwise methods optimize the Area Under the Curve (AUC) and are empirically proven to be helpful to exploit implicit feedback, but lead to not addressing the rank-biased scenarios where positive items are supposed to be placed on the top-k positions. Although there exist listwise methods, they have low efficiency and are not particularly adequate for general implicit feedback situations. To that end, in this paper, we propose a new framework, namely Collaborative List-and-Pairwise Filtering (CLAPF), which aims to introduce pairwise thinking into listwise methods. Specifically, we first smooth a well-known rank-biased measure called Mean Average Precision (MAP) as a low-bound version to make it can be optimized. After that, we combined the objective functions of optimizing the MAP with pairwise comparisons. The CLAPF framework is a new hybrid model that provides the idea of utilizing a listwise measure in a pairwise way on implicit feedback.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Sentence Matching via Exploiting List-level Semantics Expansion

Multi-Sentence Matching via Exploiting List-level Semantics ...

引用

IEEE International Conference on Big Knowledge (ICBK)

作者： Ruijun Sun Zhi Li Qi Liu Zhefeng Wang Xinyu Duan Baoxing Huai Nicholas Jing Yuan Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China Shenzhen International Graduate School Tsinghua University Huawei Cloud

Sentence semantic matching plays a fundamental role in natural language understanding and is widely used in various tasks. Previous methods are mainly based on the One-to-One single pair matching process, while in many real application scenarios, such as user query matching in FAQ, we need to match multiple sentences with the specified query sentence. The reality is that the multi-sentence matching problem is largely unexplored. Although to some extent, we can use multiple One-to-One pair matching on the multi-sentence matching problem, the exploitation of list-level candidate semantics is still limited, which leads to inferior performance. To that end, in this paper, we present a focused study on the novel multi-sentence matching problem. To begin with, we propose a Multi-Sentence Matching Network (MSMN) with a meticulously designed Fusion Module and Contrastive Matching Module to deeply exploit the list-level candidate semantics expansion for the multi-sentence matching task. Then, we construct two multi-sentence matching datasets, i.e., mQuora and mReceipt, to bridge the gap of benchmark data in this area. Finally, we conduct extensive experiments on two datasets. The experimental results clearly demonstrate the effectiveness of our method.

关键词： Learning systems Semantics Benchmark testing Natural language processing Task analysis

来源：评论

学校读者我要写书评

暂无评论

Backdoor Defense via Deconfounded Representation Learning

Backdoor Defense via Deconfounded Representation Learning

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zaixi Zhang Qi Liu Zhicai Wang Zepu Lu Qingyong Hu Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei Anhui China University of Science and Technology of China Hong Kong University of Science and Technology

Deep neural networks (DNNs) are recently shown to be vulnerable to backdoor attacks, where attackers embed hidden backdoors in the DNN model by injecting a few poisoned examples into the training dataset. While extensive efforts have been made to detect and remove backdoors from backdoored DNNs, it is still not clear whether a backdoor-free clean model can be directly obtained from poisoned datasets. In this paper, we first construct a causal graph to model the generation process of poisoned data and find that the backdoor attack acts as the confounder, which brings spurious associations between the input images and target labels, making the model predictions less reliable. Inspired by the causal understanding, we propose the Causality-inspired Backdoor Defense (CBD), to learn deconfounded representations for reliable classification. Specifically, a backdoored model is intentionally trained to capture the confounding effects. The other clean model dedicates to capturing the desired causal effects by minimizing the mutual information with the confounding representations from the backdoored model and employing a sample-wise re-weighting scheme. Extensive experiments on multiple benchmark datasets against 6 state-of-the-art attacks verify that our proposed defense method is effective in reducing backdoor threats while maintaining high accuracy in predicting benign samples. Further analysis shows that CBD can also resist potential adaptive attacks. The code is available at https://***/zaixizhang/CBD.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Coordinate Attention Based 3D-CNN Using Ghost Multi-Scale for Diagnosing Alzheimer’s Disease

Coordinate Attention Based 3D-CNN Using Ghost Multi-Scale fo...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xiaolu Lin Pinya Lu Jie Pan Hongqin Yang Xuemei Ding Fujian Provincial Engineering Research Center for Public Service Big Data Mining and Application Fujian Provincial University Engineering Research Center for Big Data Analysis and Application Fujian Normal University Fuzhou China Xiamen Jingyi Zhikang Technology Co. Ltd Xiamen China Fujian Provincial Key Laboratory for Photonics Technology Key Laboratory of OptoElectronic Science and Technology for Medicine of Ministry of Education Fujian Normal University Fuzhou China School of Computing Engineering and Intelligent Systems Ulster University Derry-Londonderry NI UK

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Alzheimer's disease (AD) is a neurodegenerative disease and mild cognitive impairment (MCI) is the early stage of AD. Previous studies have predominantly focused on binary classification using 3 dimensional - convolutional neural network (3D-CNN) for AD diagnosis, with limited progress in multi-classification. Moreover, the current 3D-CNNs often adopt a single-scale architecture with massive parameters growth. Additionally, obtaining precise location information of brain imaging data is crucial for improving the classification accuracy with 3D-CNN. Hence, we propose a multi-scale 3D-CNN based on coordinate attention mechanism to marvelously capture and integrate 3D features with fewer parameters, improving the accuracy of AD diagnosis. A total of 447 cognitively normal (CN), 512 MCI, and 358 AD sMRI images from the Alzheimer's Disease Neuroimaging Initiative datasets are used for multi-class classification task, yielding a classification accuracy of 92.8%. The model merely involves 2.41 M parameters and achieves the best classification results with the least number of parameters when compared to other representative CNN architectures including ResNet 18, ResNet 34, ConvNeXt tiny, and VGG 11. Through the ablation experiment, the addition of attention mechanism and the multi-scale classification enhances the classification performance by 4.5% and 1.5%, respectively. Furthermore, our model outperforms the other six existing studies in terms of accuracy for classifying AD vs. MCI vs. CN. Overall, this study underscores the efficacy of our approach for AD diagnosis, showcasing its utility in diagnosing AD patients and providing novel insights for diagnosing other neurological disorder diseases.

关键词： Neuroimaging Accuracy Attention mechanisms Three-dimensional displays Resonance Convolutional neural networks Alzheimer's disease

来源：评论

学校读者我要写书评

暂无评论

A Revised Model for Sea-Surface Wind Inversion data with Joint Interpolation Optimization and Residual Network

A Revised Model for Sea-Surface Wind Inversion Data with Joi...

引用

International Conference on Intelligent System and Knowledge Engineering, ISKE

作者： Weihong Lin Lijun You Tianqiang Huang Liqing Huang Haifeng Luo Chao Xu College of Computer and Cyber Security Fujian Normal University Fujian Provincal Engineering Research Center of Big Data Analysis and Application Digital Fujian Institute of Big Data Security Technology Fuzhou China Fujian Meteorological Information Center Fujian Key Laboratory of Severe Weather Fuzhou China

The sea-surface wind fields are pivotal for studies in both oceanography and meteorology. However, the acquisition of ocean wind data is often challenged by practical constraints, especially near coasts, leading to significant data gaps. This paper introduces a two-stage approach that combines interpolation optimization with a residual network to improve satellite-derived sea-surface wind fields data. Initially, the Kriging interpolation method is employed to fill missing regions. Subsequently, a network structure similar to ResNet-18 is tailored to revise the interpolated data using buoy anemometer observations. By establishing a correlation model between the interpolated results and ground truth through supervised training, the approach ensures the interpolated results gravitate towards the actual measurements. The efficacy of the proposed model is corroborated through experimental visual analysis and error cure assessments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Zenith Tropospheric Delay Model Based on TCN Improving HGPT2 Model

Research on Zenith Tropospheric Delay Model Based on TCN Imp...

引用

第十四届中国卫星导航年会

作者： Dengao Li Danyang Shi Jumin Zhao Fanming Wu Liangquan Yan Ran Feng Xinfang Zhang Jinhua Zhao College of Data Science Taiyuan University of Technology Key Laboratory of Big Data Fusion Analysis and Application of Shanxi Province Intelligent Perception Engineering Technology Center of Shanxi Shanxi Province Engineering Technology Research Center of Spatial Information Network College of Information and Computer Taiyuan University of Technology

The zenith tropospheric delay（ZTD） obtained by global navigation satellite system（GNSS） atmospheric sounding is a pivotal data source for water vapor monitoring. Meteorological changes in Antarctica play an important role in analysis of the global climate, but factors such as complex climatic conditions can limit the collection of meteorological data needed for ZTD retrieval. Therefore, it is necessary to establish high-precision ZTD models that do not rely on measured meteorological data. The existing global pressure and temperature 3（GPT3） model has limited ability to capture complex weather variations and cannot obtain high-precision GPT3TD. To address the above issues, this research proposes a high-precision ZTD model through using temporal convolutional network（TCN） for improving the hourly global pressure and temperature 2（HGPT2） model. The HGTP2 model based on Fourier analysis and the time-segmentation concept can consider the linear trend of climate variations, simultaneously the TCN is introduced to simulate the long-term temporal dependence of HGPT2TD, so as to achieve the goal of obtaining high-precision ZTD without relying on measured meteorological data. The experimental results show that the precision of TCNTD obtained from the proposed model is higher than GPT3TD and HGPT2TD when using the GNSSTD observations obtained from 35 stations in Antarctica as a reference, and the improvement of the model is obvious.

关键词： GNSS ZTD GPT3 HGPT2 TCN

来源：评论

学校读者我要写书评

暂无评论

Full-atom protein pocket design via iterative refinement 23

Full-atom protein pocket design via iterative refinement

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Zaixi Zhang Zepu Lu Zhongkai Hao Marinka Zitnik Qi Liu Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence Hefei Anhui China and Harvard University Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence Hefei Anhui China Dept. of Comp. Sci. and Tech. Institute for AI THBI Lab BNRist Center Tsinghua-Bosch Joint ML Center Tsinghua Harvard University

The design and optimization of functional proteins that bind specific ligand molecules is paramount in therapeutics and bio-engineering. A critical yet formidable task in this endeavor is the design of the protein pocket, which is the cavity region of the protein where the ligand binds. Current methods are plagued by inefficient generation, inadequate context modeling of the ligand molecule, and the inability to generate side-chain atoms. Here, we present the Full-Atom Iterative Refinement (FAIR) method, designed to address these challenges by facilitating the co-design of protein pocket sequences, specifically residue types, and their corresponding 3D structures. FAIR operates in two steps, proceeding in a coarse-to-fine manner (transitioning from protein backbone to atoms, including side chains) for a full-atom generation. In each iteration, all residue types and structures are simultaneously updated, a process termed full-shot refinement. In the initial stage, the residue types and backbone coordinates are refined using a hierarchical context encoder, complemented by two structure refinement modules that capture both inter-residue and pocket-ligand interactions. The subsequent stage delves deeper, modeling the side-chain atoms of the pockets and updating residue types to ensure sequence-structure congruence. Concurrently, the structure of the binding ligand is refined across iterations to accommodate its inherent flexibility. Comprehensive experiments show that FAIR surpasses existing methods in designing superior pocket sequences and structures, producing average improvement exceeding 10% in AAR and RMSD metrics.

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：