检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zheng, Shenhai Wen, Sian Li, Congyu Chen, Qing Li, Laquan College of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing China School of Science Chongqing University of Posts and Telecommunications Chongqing China

ISBN: (纸本)9798350368741

Federated Learning (FL) is an advanced technology that tackles the challenge of blocked data arising from privacy concerns, enabling the training of deep learning models without the need for data sharing. However, FL faces difficulties with heterogeneous data and limited annotations in medical image segmentation. Motivated by this discovery, this study proposes a novel hybrid-supervised federated learning method (FedSLAG) that explores various types of annotations in medical imaging. To focus more on weakly-supervised and unsupervised scenarios within hybrid-supervised learning, a federated Gaussian enhancement module was proposed for heterogeneous sparse annotations (points and scribbles). The feature extraction module combines the features of multiple weakly-supervised clients and establishes the correlation of similar pixels, thus making up for the deficiency of scarce annotations and the insufficient feature extraction capability of a single machine. Then, a two-stage broadcast mechanism based on supervision sparsity was proposed to alleviate optimization deviation in local models. Experiments on breast tumor and skin lesion segmentation tasks demonstrate significant efficiency gains as well as highly competitive segmentation accuracy in many hybrid-supervised situations. Our codes are available at: https://***/TrivenDev/FedSLAG. © 2025 IEEE.

关键词： federated learning hybrid-supervised learning medical image segmentation

来源：评论

学校读者我要写书评

暂无评论

Efficiency Boosting of Secure Cross-Platform Recommender Systems Over Sparse data

引用

IEEE Transactions on Dependable and Secure Computing 2025年第3期22卷 2146-2160页

作者： Ren, Hao Xu, Guowen Zhang, Tianwei Ning, Jianting Huang, Xinyi Li, Hongwei Lu, Rongxing School of Cyber Science and Engineering Sichuan University Chengdu610017 China State Key Laboratory of Cryptology Beijing100878 China Key Laboratory of Data Protection and Intelligent Management Sichuan University Ministry of Education Chengdu610017 China Cyber Science Research Institute Sichuan University Chengdu610017 China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore School of Cyber Science and Engineering Wuhan University Wuhan430072 China Faculty of Data Science City University of Macau 999078 China Colledge of Cyber Security Jinan University Guangzhou510632 China School of Computer Science University of New Brunswick New BrunswickE3B 5A3 Canada

Fueled by its successful commercialization, the recommender system (RS) has gained widespread attention. However, as the training data fed into the RS models are often highly sensitive, it ultimately leads to severe privacy concerns, especially when data are shared among different platforms. In this paper, we follow the tune of existing works to investigate the problem of secure sparse matrix multiplication for cross-platform RSs. Two fundamental and critical issues are addressed: preserving the training data privacy and breaking the data silo problem. Specifically, we propose two concrete constructions with significantly boosted efficiency. They are designed for the sparse location insensitive case and location sensitive case, respectively. State-of-the-art cryptography building blocks including homomorphic encryption (HE) and private information retrieval (PIR) are fused into our protocols with non-trivial optimizations. As a result, our schemes can enjoy the HE acceleration technique without privacy trade-offs. We give formal security proofs for the proposed schemes and conduct extensive experiments on both real and large-scale simulated datasets. Compared with state-of-the-art works, our two schemes compress the running time roughly by 10×10× and 2.8×2.8×. They also attain up to 15×15× and 2.3×2.3× communication reduction without accuracy loss. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Wetland Vegetation Species Classification Using Optical and SAR Remote Sensing Images: A Case Study of Chongming Island, Shanghai,china

引用

Chinese Geographical Science 2025年第3期35卷 510-527页

作者： DENG Yaozi SHI Runhe ZHANG Chao WANG Xiaoyang LIU Chaoshun GAO Wei Key Laboratory of Geographic Information Science Ministry of Education East China Normal University School of Geographic Sciences East China Normal University Key Laboratory of Spatial-temporal Big Data Analysis and Application of Natural Resources in Megacities Ministry of Natural Resources Department of Ecosystem Science and Sustainability Colorado State University

Mudflat vegetation plays a crucial role in the ecological function of wetland environment, and obtaining its fine spatial distribution is of great significance for wetland protection and management. Remote sensing techniques can realize the rapid extraction of wetland vegetation over a large area. However, the imaging of optical sensors is easily restricted by weather conditions, and the backscattered information reflected by Synthetic Aperture Radar(SAR) images is easily disturbed by many factors. Although both data sources have been applied in wetland vegetation classification, there is a lack of comparative study on how the selection of data sources affects the classification effect. This study takes the vegetation of the tidal flat wetland in Chongming Island, Shanghai, china, in 2019,as the research subject. A total of 22 optical feature parameters and 11 SAR feature parameters were extracted from the optical data source(Sentinel-2) and SAR data source(Sentinel-1), respectively. The performance of optical and SAR data and their feature parameters in wetland vegetation classification was quantitatively compared and analyzed by different feature combinations. Furthermore, by simulating the scenario of missing optical images, the impact of optical image missing on vegetation classification accuracy and the compensatory effect of integrating SAR data were revealed. Results show that: 1) under the same classification algorithm, the Overall Accuracy(OA) of the combined use of optical and SAR images was the highest, reaching 95.50%. The OA of using only optical images was slightly lower, while using only SAR images yields the lowest accuracy, but still achieved 86.48%. 2) Compared to using the spectral reflectance of optical data and the backscattering coefficient of SAR data directly, the constructed optical and SAR feature parameters contributed to improving classification accuracy. The inclusion of optical(vegetation index, spatial texture, and phenology features)a

关键词： Chongming Island, Shanghai, china multi-source remote sensing optical images Synthetic Aperture Radar (SAR) tidal flat wetland vegetation classification

来源：评论

学校读者我要写书评

暂无评论

Dual-Aspect Noise-Based Regularization for Multi-Modal Relation Extraction in Media Posts

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 1324-1336页

作者： Kai Sun Bin Shi Samuel Mensah Wenjian Liu Bo Dong School of Computer Science and Technology and Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi'an China School of Computer Science and Technology The University of Sheffield Sheffield U.K. Faculty of Data Science City University of Macau Macau China School of Continuing Education and Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi'an China

Multi-Modal Relation Extraction (MMRE) plays a key role in various multimedia applications including, recommendation and information retrieval systems. MMRE aims to extract the semantic relation between entities by leveraging context from a text-image pair. By utilizing context from images, the challenge of learning from noisy images in MMRE emerges as a research problem by itself. For instance, subtle variations in similar images can act as noise and potentially impact the predictions made by MMRE models. To tackle this problem, current work utilizes attention mechanisms to fuse relevant text and image features or devise data augmentation techniques (e.g., via generative models) to improve generalization. However, the current performance still remains unsatisfactory. In an effort to improve upon the performance, we propose a Dual-Aspect Noise-based Regularization framework that encompasses two techniques: 1) noise removal through an adaptive gating mechanism, 2) fighting noise with noise to improve feature stability in the learning process. We find that combining these techniques encourages the model to focus on more relevant image features for MMRE. We carry out extensive experiments and demonstrate that our proposed model is further enhanced by exploring data augmentation techniques. This additional improvement leads the model to achieve state-of-the-art performance on the widely-used Multi-modal Neural Relation Extraction (MNRE) dataset, and show its effectiveness and generalizability on the Multi-Modal Named Entity Recognition task.

关键词： Feature extraction Noise data mining Noise measurement Social networking (online) Adaptation models Transformers Training Predictive models data models

来源：评论

学校读者我要写书评

暂无评论

LSDK-LegalSum: improving legal judgment summarization using logical structure and domain knowledge

引用

Journal of King Saud University - Computer and Information Sciences 2025年第1期37卷 1-15页

作者： Gao, Wei Yu, Shuai Qin, Yongbin Yang, Caiwei Huang, Ruizhang Chen, Yanping Lin, Chuan Engineering Research Center of Text Computing & CognitiveIntelligence Ministry of Education Guizhou University Guizhou Huaxi Guiyang 550025 China State Key Laboratory of Public Big Data Guizhou University Guizhou Huaxi Guiyang 550025 China College of Computer Science and Technology Guizhou University Guizhou Huaxi Guiyang 550025 China

Legal judgment summarization enhances the efficiency and accuracy of processing and retrieving similar cases by distilling key information from legal judgment documents. Legal judgments, which record the trial process and outcome, tend to have lengthy texts. However, most existing methods for legal judgment summarization struggle to effectively handle long texts and focus only on the serialized text information, neglecting the auxiliary role of the document’s logical structure in generating summaries. Additionally, legal judgment documents contain extensive domain knowledge formed by professional legal terminology, which is crucial for accurately understanding and analyzing the content of the documents. We propose a method to improve the quality of legal judgment summaries by utilizing logical structures and domain knowledge (LSDK-LegalSum). Specifically, we first use a multi-label document classification approach to divide the legal judgment into four parts: ‘Type’, ‘Claim’, ‘Fact’ and ‘Result’, then generate a summary of the ‘Type’ part, and combine it with the ‘Claim’ part to create a new summary, and so forth until the final summary is produced. Moreover, the case descriptions in legal judgments cause substantial textual noise;therefore, we employ a text-denoising method that integrates domain knowledge to further enhance the performance of the summaries. Extensive experiments on the CAIL2020 legal summarization dataset have shown that our method achieves improvements of 8.37, 16.64, and 13.07 percentage points in Rouge-1, Rouge-2, and Rouge-L scores respectively over the state-of-the-art models. This demonstrates that our method not only produces concise and semantically complete summaries but also ensures that the content is logically rigorous and well-organized, meeting practical needs more effectively. © The Author(s) 2025.

关键词： Abstractive summarization Domain knowledge Legal judgment summarization Logical structure Low-source summarization

来源：评论

学校读者我要写书评

暂无评论

Contactless Vital Signs Monitoring for Animals

引用

IEEE Internet of Things Journal 2025年第11期12卷 16789-16796页

作者： Pitafi, Zaid Farooq Song, Yingjian Xie, Zaipeng Brainard, Benjamin Song, Wenzhan University of Georgia School of Electrical and Computer Engineering AthensGA30602 United States Hohai University Key Laboratory of Water Big Data Technology of Ministry of Water Resources Nanjing211100 China University of Georgia College of Veterinary Medicine AthensGA30602 United States

Monitoring vital signs such as Heart Rate (HR) and Respiratory Rate (RR) is critical for veterinary medicine. The existing contact based systems are difficult to use on animals for longer periods as they may cause movement restriction. Contactless solutions have recently gained more popularity due to their ease-of-use. However, there are very few validated systems for animals. In this study, we propose a contactless vital signs monitoring system, CageDot for animals. Our system provides continuous real-time monitoring of HR and RR during hospitalization. The CageDot is placed under the animal cage and detects the heart vibrations using a geophone sensor. The CageDot also has a signal quality control algorithm to address the problem of obtaining high-quality cardiac data in real-life noisy environments such as hospitals. Compared to the existing works that use controlled environments, this is especially significant. The algorithm includes several steps that include background noise/movement removal, subject movement detection, heartbeat extraction and vital signs estimation. The experimental results on 16 hospitalized dogs and cats show that this system can achieve high accuracy for vital signs monitoring with a Mean Absolute Error (MAE) of 4.71 for Heart Rate (3.8 percent error rate) and 1.28 (8 percent error rate) for Respiratory Rate. © 2014 IEEE.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

Steel Defect Detection Algorithm Based on Multiobjective ENAS Sharing Strategy 24

Steel Defect Detection Algorithm Based on Multiobjective ENA...

引用

2nd International Conference on Frontiers of Intelligent Manufacturing and Automation, CFIMA 2024

作者： Zhao, Tianchen Dong, Zhiming Wang, Xianpeng National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang China Ministry of Education Shenyang China Liaoning Engineering Laboratory of Data Analytics and Optimization for Smart Industry Northeastern University Shenyang China Liaoning Key Laboratory of Manufacturing System and Logistics Optimization Northeastern University Shenyang China

ISBN: (纸本)9798400710681

When employing the network architecture search approach for designing a steel surface defect detector, there are issues with conflicting evaluation metrics and limited computational resources. To address this challenge, we propose a multiobjective evolutionary sharing strategy-based network architecture search method (MESNAS). MESNAS defines network architecture search as a bi-level multiobjective optimization problem combined with a weight sharing acceleration strategy designed to quickly and simultaneously optimize the accuracy and complexity of classification models. A refined search space suitable for different image classification and detection tasks is designed. Using the MOEA/D algorithm, which incorporates a variable-length encoding scheme, the search space is co-utilized and explored through targeted improvements to the crossover and mutation operators in the offspring generation process. The optimal network architecture obtained from the search is tested on the concrete surface defect classification task, and the steel continuous casting slab surface defect detection task. The experimental results show that the proposed algorithm has good model performance and portability in image classification as well as defect detection tasks with different data complexities and different categories. © 2024 Copyright held by the owner/author(s).

关键词： Continuous casting

来源：评论

学校读者我要写书评

暂无评论

Logit Adjustment for Imbalanced Cognitive Diagnosis

Logit Adjustment for Imbalanced Cognitive Diagnosis

引用

Algorithms, Computing and Machine Learning (CACML), Asia Conference on

作者： Zhengtao Tan Jimin Bao Zhuangzhuang He Dacao Zhang Key Laboratory of Knowledge Engineering With Big Data Hefei University of Technology Hefei China

ISBN: (数字)9798331543143

ISBN: (纸本)9798331543150

Cognitive diagnosis is a critical task in intelligent education, aimed at inferring students’ mastery of knowledge concepts based on their response logs. Although existing cognitive diagnosis models achieve excellent performance, they underestimate the difficulty of easy exercises and overestimate the difficulty of hard exercises. We attribute this to the class imbalance in the response logs of easy and hard exercises. Moreover, the convergence speed varies from exercise to exercise during model training, which further challenges generalization. To address these problems, we propose an exercise’s correct rate-based logit adjustment approach for a wide range of cognitive diagnosis models. Specifically, we enforce logit adjustment in the loss during training to overcome the class imbalance in response logs. Then, we apply group distributionally robust optimization for generalization. Finally, extensive experiments demonstrate the effectiveness of our model, especially on easy and hard exercises.

关键词： Training Machine learning algorithms Accuracy Computational modeling Asia Machine learning Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

Surface-enhanced Raman scattering on nanomaterials for cancer and pathogens diagnosis

引用

Nano Research 2025年第2期18卷 650-674页

作者： Jingjing Wu Baohong Zhang Lei Xu Yanyu Zhao Tao Chen Jie Lin Anran Li School of Engineering Medicine Beihang UniversityBeijing 100191China Key Laboratory of Big Data-Based Precision Medicine Ministry of Industry and Information Technology of the People’s Republic of ChinaBeihang UniversityBeijing 100191China School of Optics and Photonics Beijing Institute of TechnologyBeijing 100089China Shanxi Lu'an Taihang Lubricant Technology Co. Ltd.Changzhi 046204China Cixi Institute of Biomedical Engineering Ningbo Institute of Materials Technology and EngineeringChinese Academy of SciencesNingbo 315201China

Surface-enhanced Raman scattering(SERS)is a non-invasive spectroscopic technique that provides specific chemical fingerprint information for biomarkers in cancer and pathogen ***,the SERS strategies are limited by the non-specific interactions between substrates and co-existing substances in biological matrices and the challenges of obtaining molecular fingerprint information from the complex vibrational *** recent years,the rapid development of novel substrates with high SERS activity has opened up new opportunities for their applications in cancer and pathogen *** aim of this review is to present the recent progress and perspectives of novel SERS-based substrates for cancer and pathogen diagnostic ***,we will introduce recently developed SERS-active nanomaterials and discuss the influencing factors of the SERS ***,the advantages of SERS in the diagnosis of cancer and pathogens will be ***,we will review the latest breakthroughs in cancer and pathogen detection research with SERS technology,as well as the new opportunities for SERS applications brought about by artificial intelligence(Al)*** addition,the novel microfluidic-SERS platforms for cancer and pathogens diagnosis will also be ***,we will summarize the challenges and future perspectives of SERS technology in the field of early cancer diagnosis and rapid pathogen *** is highly expected that this review could benefit a comprehensive understanding of the research status of the SERS-active nanomaterials and arouse the research enthusiasm for them,leading to accelerated clinical translation of SERS technology in cancer and pathogen diagnosis.

关键词： surface-enhanced Raman scattering(SERS) SERS-active nanomaterials cancer and pathogen diagnosis artificial intelligence(Al)technology

来源：评论

学校读者我要写书评

暂无评论

MSPL: Multi-modal Statistical Prompt Learning for New Energy Equipment Defect Recognition

引用

IEEE Internet of Things Journal 2025年第11期12卷 16438-16450页

作者： Wang, Zhenwei Wang, Pengfei Han, Guangjie Zhou, Chengjie Lin, Qing Zhang, Jianxin Fan, Guangjie Zhang, Qiang Dalian University of Technology School of Computer Science and Technology Dalian116024 China Dalian116024 China Shenyang Huayan Electric Technology Co Ltd Shenyang110180 China Hohai University Key Laboratory of Maritime Intelligent Network Information Technology Ministry of Education China Deputy Director of the Yantai Big Data Center and Senior Engineer Yantai264003 China Dalian Minzu University School of Computer Science and Engineering Dalian116600 China

Monitoring renewable energy devices is crucial for the timely detection of faults and the improvement of system stability, making it a key component of the Internet of Things (IoT) ecosystem. However, existing intelligent algorithms and IoT methods rely on edge devices with limited computational capacity, which requires balancing real-time performance and accuracy. Additionally, most methods require initial training on large-scale data using cloud platforms or high-performance servers, leading to high initial costs. To address these challenges, we propose Multi-modal Statistical Prompt Learning (MSPL) for new energy equipment defect recognition on IoT edge devices. This method enables rapid learning with only a few samples, avoiding the need for large-scale centralized training. Specifically, MSPL uses the pre-trained Contrastive Language-Image Pre-training model as its backbone, leveraging text-based conceptual information to enhance the understanding of visual inputs. A Statistical Query (SQ) module is implemented at the end of the backbone to extract distinctive features from the outputs, integrating these features with soft prompts to customize them for the defect recognition task. Since the learnable parameters are limited to soft prompts added at the end of the backbone, MSPL restricts gradient backpropagation to this point. This improves parameter and memory efficiency, making it more suitable for scenarios with limited computational capacity on IoT edge devices. Experimental results of MSPL on two renewable energy equipment defect datasets and edge devices indicate that it meets real-time processing requirements while maintaining high accuracy, outperforming other methods. © 2025 IEEE.

关键词： Zero-shot learning

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：