检索结果-内蒙古大学图书馆

7th International Conference on Digital Medicine and Image Processing, DMIP 2024

作者： Syed Masood, Jafar Ali Ibrahim Vinayagam, Jai Kumar Onteru, Ranjit Kumar Kopparapu, Umamaheswararao Parabathini, Bulah Pushpa Rani Department of IoT School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore632014 India Centre for Big Data Analytics QIS College of Engineering and Technology Andhra Pradesh Ongole India

ISBN: (纸本)9798400709586

The rapid proliferation of medical big data has opened unprecedented opportunities for enhancing patient outcomes through advanced computational analysis. This paper explores the integration of big data analytics with clinical practices to deliver personalized medicine, optimize treatment protocols, and improve patient care. Our findings demonstrate that a synergistic approach between computational insights and clinical decision-making can significantly advance healthcare outcomes. This study provides a comprehensive framework for harnessing medical big data, addressing key challenges, and proposing solutions to integrate these insights into everyday clinical practice. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Personalized medicine

来源：评论

学校读者我要写书评

暂无评论

Distributed Channel Estimation and Optimization for 6D Movable Antenna: Unveiling Directional Sparsity

引用

IEEE Journal on Selected Topics in Signal Processing 2025年第2期19卷 349-365页

作者： Shao, Xiaodan Zhang, Rui Jiang, Qijun Park, Jihong Quek, Tony Q. S. Schober, Robert Friedrich-Alexander-University Erlangen-Nurnberg Institute for Digital Communications Erlangen91054 Germany Shenzhen Research Institute of Big Data The Chinese University of HongKong School of Science and Engineering Shenzhen518172 China National University of Singapore Department of Electrical and Computer Engineering 117583 Singapore The Chinese University of HongKong School of Science and Engineering Shenzhen518172 China Singapore University of Technology and Design 487372 Singapore

Six-dimensional movable antenna (6DMA) is an innovative and transformative technology to improve wireless network capacity by adjusting the 3D positions and rotations of antennas/antenna surfaces based on the channel spatial distribution. To achieve optimal antenna positions and rotations, acquiring statistical channel state information (CSI) is essential for 6DMA systems. However, existing works assume that a central processing unit (CPU) jointly processes the signals of all 6DMA surfaces. This incurs prohibitively high processing cost and latency for channel estimation due to the vast numbers of 6DMA candidate positions/rotations and antenna elements. Therefore, we propose a distributed 6DMA processing architecture to reduce the processing complexity of the CPU by equipping each 6DMA surface with a local processing unit (LPU). Furthermore, we unveil for the first time the directional sparsity property of the 6DMA channels with respect to distributed users, where each user has significant channel gains only for a (small) subset of 6DMA position-rotation pairs. Based on this property, we propose a practical three-stage protocol for the 6DMA system and corresponding algorithms to conduct statistical CSI acquisition for all 6DMA candidate positions/rotations, 6DMA position/rotation optimization based on statistical CSI, and instantaneous CSI estimation for user data transmission with optimized 6DMA positions/rotations. Simulation results show that the proposed channel estimation algorithms achieve higher accuracy than benchmark schemes, while requiring lower pilot overhead. Moreover, the proposed 6DMA system with statistical CSI-based position/rotation optimization achieves a higher ergodic sum rate than fixed-position and fluid antenna systems, even if the latter have perfect instantaneous CSI. © 2025 IEEE.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

SPDGrNet: A Lightweight and Efficient Image Classification Network for Zea mays Diseases

引用

Journal of Crop Health 2025年第3期77卷 1-12页

作者： Xu, Laixiang Cao, Bingxu Su, Jing feng Zhang, Fengyue Song, Hongyun Zhao, Junmin School of Computer and Data Science Research Center of Smart City and Big Data Engineering of Henan Province Henan University of Urban Construction Pingdingshan China School of Information Engineering Luohe Vocational Technology College Luohe China Institute of Technology University of Technology Luohe Luohe China School of Computer and Data Science Innovation Laboratory of Smart Traffic and Big Data Development of Hainan Province Henan University of Urban Construction Pingdingshan China School of Computer and Data Science Henan University of Urban Construction Pingdingshan China School of Computer and Data Science Research Center of Smart City and Big Data Engineering of Henan Province Research Center of Intelligent Campus Application Engineering of Henan Province Innovation Laboratory of Smart Traffic and Big Data Development of Hainan Province Henan University of Urban Construction Pingdingshan China

Controlling diseases on the foliage of cultivated plants has a major impact on crop yield and quality. Leaf symptoms and environmental information are the basis of crop disease and pest identification. Due to the complexity and diversity of disease leaf symptoms and environmental information, the accuracy of crop disease detection methods has decreased. Aiming at low disease identification efficiency and difficult feature modeling, we propose a new deep learning algorithm and obtain ideal results. We used improved convolutional neural networks (CNNs) SPDNet and GrNet (SPDGrNet) to perform Zea mays disease identification. The proposed research and analysis focus on four categories of Zea mays symptoms: healthy, leaf blight, southern leaf blight and grey spot. The experimental results and analysis confirm that the proposed approach outperforms other excellent plant disease recognition algorithms and achieves an overall classification accuracy of 98.96%. When compared to AlexNet, VGG-16, Inception-V4, ShuffleNet-V3, and Efficient-B7, the proposed model achieves accuracy improvements of 27.78%, 19.05%, 14.59%, 10.28%, and 7.06%, respectively, with corresponding accuracies of 71.18%, 79.91%, 84.37%, 88.68%, and 91.9%. The proposed model has outstanding generalization ability in open-source databases, such as the PlantifyDr, Plant Pathology, and New Plant Diseases dataset. The suggested strategy can provide ideas for transplanting models into mobile disease detection equipment. This is very helpful in the intelligent development of agricultural systems and crop leaf disease analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A data Watermark Scheme Base on data Converted Bitmap for data Trading 24th

A Data Watermark Scheme Base on Data Converted Bitmap for ...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Liu, Xinyu Ren, Wei Liu, Wenmao Zheng, Xianghan School of Computer Science China University of Geosciences Wuhan430078 China NSFOCUS Technologies Group Company Ltd. Beijing China College of Computer and Big Data Fuzhou University Fujian Fuzhou350000 China School of Information and Intelligent Engineering Sanya College Hainan China

ISBN: (纸本)9789819615445

data watermark is of the surmount importance for data trading. Most of the data in the current data trading market is stored in the form of spreadsheets, yet there are few watermarking schemes specifically designed for tables. We propose a bitmap-based watermark scheme for table data. Our approach involves converting the table into a bitmap representation and utilizing classical image processing algorithms to embed a watermark that incorporates error correction codes. The watermarked data is then returned to its corresponding positions in the table. During the table conversion process, we apply the principle of minimal modification to minimize the impact of watermark embedding on the table data. Experimental evaluations demonstrate the effectiveness of the proposed scheme in preserving data integrity and accurately extracting watermarks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： data integrity

来源：评论

学校读者我要写书评

暂无评论

Nonparametric Modal Identification of Time-varying Dynamic Systems with Sliding-window Method

引用

Journal of Vibration Engineering and Technologies 2025年第5期13卷 1-12页

作者： Guan, Wei Xu, Wen-Jie Wang, Ze-Kun Wang, Cheng Ji, Sheng-Jie School of Computer Science and Artificial Intelligence & Aliyun School of Big Data Changzhou University Changzhou 213164 China Digital Fujian Ocean Monitoring IoT Laboratory Huaqiao University Xiamen 361021 China Jiangsu Branch of China Academy of Machinery Science and Technology Group Co. Ltd Changzhou 213164 China

Purpose: Modal identification of time-varying structures is a fundamental aspect in the field of structural dynamics, from which the identified modal parameters are considered as important indicators for damage identification and structural condition assessment in structural health monitoring. Therefor a nonparametric modal identification approach for time-varying structures from a data-driven perspective is investigated. Methods: The inherent connection between dynamic mode decomposition and operational modal identification is revealed, where the modal identification is converted to solve the eigenvalues of dynamic matrix in dynamic mode decomposition. Furthermore, the full implementation procedures of the method for time-varying modal parameters extraction are provided, where the dynamic mode decomposition and sliding-window technique is effectively combined. Finally, a series of numerical examples are performed to validate the effectiveness and practicability of the method, where the dynamic modelling of simply supported beam with moving mass is derived and the classical methods based on signal decomposition for time-varying modal identification are used for comparison. Results: The results from studied cases show that the proposed method has the capability for accurately identifying the instantaneous modal frequencies with good efficiency when the external excitation is unknown, showing promising prospects for engineering applications. Conclusion: An online modal identification method for time-varying structures based on dynamic mode decomposition and sliding-window technique is presented without requiring establishing an accurate parameterized mathematical model. The proposed method can well identify instantaneous modal frequencies, and provides a more easily implementable framework with few adjustable parameters and lower computational resources and better identification performance compared with the VMD-HT and STMVMD method. © Springer Nature Singapore Pte Lt

关键词： Dynamic mode decomposition Online modal identification Sliding-window Structural health monitoring Time-varying system

来源：评论

学校读者我要写书评

暂无评论

MLPFormer: MLP-integrated transformer for colorectal histopathology whole slide image segmentation

引用

Neural Computing and Applications 2025年第6期37卷 4651-4661页

作者： Wang, Yuxuan Li, Dan Li, Xuechen Guo, Yan Zuo, Yanfei Shen, Linlin Department of Computer Science Wenzhou-Kean University Wenzhou China School of Electronics and Information Engineering Wuyi University Jiangmen China Department of Histo Pathology Shanghai Histo Pathology Diagnostic Center Shanghai China College of Computer Sicence and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

Colorectal intraepithelial neoplasia is a precancerous lesion of colorectal cancer, which is mainly diagnosed using pathological images. According to the characteristics of lesions, precancerous lesions can be classified into four different grades, i.e., background, normal, low and high level. However, due to the continuity of lesion development, tissue in different stages has high similarity. Recently, visual transformers have achieved impressive results in different visual tasks, due to their capacity of capturing long-range dependencies. However, due to computational cost, transformer cannot well extract detailed feature, which is important for lesion grading. To accurately segment pathological tissues with high similarity, in this work, we embed the multi-head MLP mixer module in the transformer network to extract cell and edge information. Furthermore, we propose a hierarchical MLP decoder to facilitate multi-scale feature fusion. The proposed transformer, namely MLPFormer, achieves remarkable results against competitive baselines on the Histo-CRC Biopsy dataset. The experimental results demonstrate that MLPFormer significantly outperforms the competitive baselines, i.e., a 3% dice improvement is achieved over the SegFormer series. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Make an Image Move: Few-Shot Based Video Generation Guided by CLIP 27th

Make an Image Move: Few-Shot Based Video Generation Guided b...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Huang, Yonglong Yu, Cheng Li, Nannan Deng, Fuqin Ge, Ruiquan Wang, Changmiao School of Computer Science and Engineering Macau University of Science and Technology Macau China Chongqing University of Technology Chongqing China Wuyi University Jiangmen China Hangzhou Dianzi University Hangzhou China Shenzhen Research Institute of Big Data Shenzhen China

ISBN: (纸本)9783031781711

The recent surge in interest surrounding text-to-video diffusion models highlights their capability to generate videos with both consistency and diversity. Current methods focus on leveraging large-scale datasets to align with training videos, while certain approaches explore the potential of zero-shot generation. Few-shot generative models adapt text-to-image model with temporal layers. They can capture the temporal motion and appearance with acceptable computational resources. However, the prevalent few-shot based approaches, which employ a singular prompt for training videos, typically result in inadequate control over complex backgrounds and multiple objects. To overcome this limitation, we introduce a novel component: the dual cross-attention layer. This component leverages CLIP for image feature extraction. The image feature and text feature will be processed independently in dual cross-attention layer, aiming to achieve image reference and enrich the training videos with additional information. This dual cross-attention mechanism empowers the diffusion model to learn both image and text information effectively, facilitating the generation of higher quality videos. Furthermore, we propose an innovative sampling method to enhance temporal consistency and stability of generative videos. Compared to other text-to-video generative models, our framework demonstrates superior efficiency in generating high quality videos with diverse styles. The code is available at https://***/FatLong666/MAIM. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in Multi-Level Model Space

引用

IEEE Transactions on big data 2025年

作者： Chen, Ao Zhou, Xiren Fan, Yizhan Chen, Huanhuan University of Science and Technology of China School of Computer Science and Technology Hefei230027 China University of Science and Technology of China School of Big Data Hefei230027 China

Anomaly detection (AD) is gaining prominence, especially in situations with limited labeled data or unknown anomalies, demanding an efficient approach with minimal reliance on labeled data or prior knowledge. Building upon the framework of Learning in the Model Space (LMS), this paper proposes conducting AD through Learning in the Multi-Level Model Spaces (MLMS). LMS transforms the data from the data space to the model space by representing each data instance with a fitted model. In MLMS, to fully capture the dynamic characteristics within the data, multi-level details of the original data instance are decomposed. These details are individually fitted, resulting in a set of fitted models that capture the multi-level dynamic characteristics of the original instance. Representing each data instance with a set of fitted models, rather than a single one, transforms it from the data space into the multi-level model spaces. The pairwise difference measurement between model sets is introduced, fully considering the distance between fitted models and the intra-class aggregation of similar models at each level of detail. Subsequently, effective AD can be implemented in the multi-level model spaces, with or without sufficient multi-class labeled data. Experiments on multiple AD datasets demonstrate the effectiveness of the proposed method. © 2015 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

AccelES: Accelerating Top-K SpMV for Embedding Similarity via Low-bit Pruning 31

AccelES: Accelerating Top-K SpMV for Embedding Similarity vi...

引用

31st IEEE International Symposium on High Performance computer Architecture, HPCA 2025

作者： Zhai, Jiaqi Shi, Xuanhua Huang, Kaiyi Ye, Chencheng Hu, Weifang He, Bingsheng Jin, Hai Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Wuhan430074 China National University of Singapore School of Computing 119077 Singapore

ISBN: (纸本)9798331506476

In the realm of recommendation systems, achieving real-time performance in embedding similarity tasks is often hindered by the limitations of traditional Top-K sparse matrix-vector multiplication (SpMV) methods, which suffer from high latency due to inefficient memory access patterns. This paper identifies these critical gaps and introduces AccelES, a novel approach that significantly enhances the efficiency of Top-K SpMV. Our method employs a two-stage calculation scheme: the first stage utilizes a compact, low-bit dataset to quickly identify the most relevant entries, while the second stage performs full-precision calculations solely on this pruned subset, thereby minimizing computational overhead. Furthermore, AccelES incorporates innovative matrix representations, Ultra-CSR and Random-CSR, which optimize memory bandwidth utilization. Experimental results demonstrate that AccelES accelerates performance, surpassing state-of-the-art FPGA, GPU, and CPU solutions by factors of 3.4×, 2.5×, and 153.3×, respectively, under controlled conditions. These advancements not only enhance processing speed but also significantly improve real-time performance in recommendation systems, establishing AccelES as a pivotal contribution to the field of Top-K sparse matrix-vector multiplication. © 2025 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Enhancing graph representation learning via type-aware decoupling and node influence allocation

引用

Applied Intelligence 2025年第6期55卷 1-14页

作者： Zhu, Guochang Hu, Jun Liu, Li Zhang, Qinghua Wang, Guoyin School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongwen Road Chongqing Chongqing400065 China Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Chongwen Road Chongqing Chongqing400065 China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing400065 China

The traditional graph representation methods can fit the information of graph with low-dimensional vectors, but they cannot interpret their composition, resulting in insufficient security. Graph decoupling, as a method of graph representation, can analyze the latent factors composing the graph representation vectors. However, in current graph decoupling methods, the number of factors is a hyperparameter, and enforce uniform decoupling vector dimensions which leads to information loss or redundancy. To address these issues, we propose a type-aware graph decoupling based on influence called Variational Graph Decoupling Auto-Encoder (VGDAE). It uses node labels as interpretable and objectively existing natural semantics for decoupling and allocates embedding space based on node influence, addressing the issues of manually setting the number of factors in traditional graph decoupling and the mismatch between node information size and embedding space. On the Cora, Citeseer, and fb-CMU datasets, VGDAE shows the impact of different node classes as decoupling targets on classification tasks. Furthermore, we perform visualization of the representations, VGDAE exhibits performance improvements of 2% in classification tasks and 12% in clustering tasks when compared with baseline models. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Graph embeddings

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：