检索结果-内蒙古大学图书馆

Integration of Multi-Source Medical data for Medical Diagnosis Question Answering

IEEE TRANSACTIONS ON MEDICAL IMAGING 2025年第3期44卷 1373-1385页

作者： Peng, Qi Cai, Yi Liu, Jiankun Zou, Quan Chen, Xing Zhong, Zheng Wang, Zefeng Xie, Jiayuan Li, Qing South China Univ Technol Sch Software Engn Minist Educ Guangzhou 510006 Peoples R China South China Univ Technol Minist Educ Key Lab Big Data & Intelligent Robot Guangzhou 510006 Peoples R China Meizhou Peoples Hosp Meizhou 514089 Peoples R China Univ Sydney Fac Engn Sydney NSW 2006 Australia Hong Kong Polytech Univ Dept Comp Hong Kong Peoples R China

Medical question answering aims to enhance diagnostic support, improve patient education, and assist in clinical decision-making by automatically answering medical-related queries, which is an important foundation for realizing intelligent healthcare. Existing methods predominantly focus on extracting key information from a single data source, e.g., CT image, for answering. However, these methods are not enough to promote the development of intelligent healthcare, because they lack comprehensive medical diagnosis capabilities, which usually require the integration of multi-source data (e.g., laboratory tests, radiology images, pathology images, etc.) for processing. To address these limitations, our paper introduces the extended task of medical question answering, named medical diagnosis question answering MedDQA. MedDQA task aims to answer questions related to medical diagnosis based on multi-source data. Specifically, we introduce a corresponding dataset that incorporates multi-source diagnostic information from 250,917 patients in clinical data from hospital records, and utilize a large-scale model for constructing Q&A pairs. We propose a novel system based on large language models, named medical multi-agent (MMA) system, which includes a mechanism of multiple agents to handle different medical tasks. Each agent is specifically tailored to process various modalities of data and provide outputs in a uniform textual modality. Experimental results demonstrate that the MMA system's architecture significantly enhances the handling of multi-source data, thereby improving medical diagnosis, establishing a robust baseline for future research.

关键词： Pathology Hospitals Soft sensors Large language models Decision making Education Radiology Question answering (information retrieval) Medical diagnosis Medical diagnostic imaging Medical question answering medical diagnosis large-scale pre-trained models

来源：评论

学校读者我要写书评

暂无评论

Residential Energy Consumption Forecasting Based on Federated Reinforcement Learning with data Privacy Protection

引用

Computer Modeling in Engineering & Sciences 2023年第10期137卷 717-732页

作者： You Lu Linqian Cui YunzheWang Jiacheng Sun Lanhui Liu School of Electronic and Information Engineering Suzhou University of Science and TechnologySuzhou215009China Jiangsu Province Key Laboratory of Intelligent Building Energy Efficiency Suzhou University of Science and TechnologySuzhou215009China Chongqing Industrial Big Data Innovation Center Co. Ltd.Chongqing400707China

Most studies have conducted experiments on predicting energy consumption by integrating data formodel ***, the process of centralizing data can cause problems of data ***,many laws and regulationson data security and privacy have been enacted, making it difficult to centralize data, which can lead to a datasilo problem. Thus, to train the model while maintaining user privacy, we adopt a federated learning ***, in all classical federated learning frameworks secure aggregation, the Federated Averaging (FedAvg)method is used to directly weight the model parameters on average, which may have an adverse effect on te ***, we propose the Federated Reinforcement Learning (FedRL) model, which consists of multiple userscollaboratively training the model. Each household trains a local model on local data. These local data neverleave the local area, and only the encrypted parameters are uploaded to the central server to participate in thesecure aggregation of the global model. We improve FedAvg by incorporating a Q-learning algorithm to assignweights to each locally uploaded local model. And the model has improved predictive performance. We validatethe performance of the FedRL model by testing it on a real-world dataset and compare the experimental results withother models. The performance of our proposed method in most of the evaluation metrics is improved comparedto both the centralized and distributed models.

关键词： Energy consumption forecasting federated learning data privacy protection Q-learning

来源：评论

学校读者我要写书评

暂无评论

User-Level Large Scale Load Forecasting Based on GPU 9

User-Level Large Scale Load Forecasting Based on GPU

引用

9th Annual International Conference on Network and Information Systems for Computers, ICNISC 2023

作者： Qi, Jinshan Wang, Jiangtao Liang, Xun Xu, Zhiming Huaiyin Normal University Huai'an Key Laboratory of Big Data Intelligent Computing and Analysis School of Computer Science and Technology Huai'an China Renmin University of China School of Information Beijing China

ISBN: (纸本)9798350306682

Load forecasting is an essential part in power system management and planning. In recent years, more and more researchers started to focus on the behavior of terminal customers, trying to improve the accuracy of load forecasting. This paper proposes to use the neuron network model to predict each user's load first, and then aggregate all the forecasting results to get higher-level prediction. In order to speed up the process, we also design a model based on CUDA. We conducted several experiments on real-world data (160 thousand consumers' load profiles) and the results confirm the effectiveness and efficiency of our method. © 2023 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Tri-Training with Granular-Ball in Weighted Fuzzy Rough Sets 11th

Tri-Training with Granular-Ball in Weighted Fuzzy Rough Se...

引用

11th International Joint Conference on Rough Sets, IJCRS 2025

作者： Xu, Gaojie Lian, Xiaoyu Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Chongqing China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Posts and Telecommunications Chongqing China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing China

ISBN: (纸本)9783031927461

This paper proposes a Tri-Training framework based on the Weighted Fuzzy Rough Sets and integrates the Granular-Ball method to enhance semi-supervised learning through multi-view granulation. Traditional Tri-Training methods, while effective in leveraging unlabeled data, often suffer from label propagation inaccuracies. Moreover, despite their strengths in handling high-dimensional and uncertain data, Weighted Fuzzy Rough Sets face challenges in robustness and feature selection. To address these limitations, we introduce Granular-Ball computing to generate multi-level granular representations, promoting classifier diversity and reducing redundancy. Additionally, we employ the Weighted Fuzzy Lower Approximation classifier to improve robustness in uncertain environments. Experimental results on multiple benchmark datasets demonstrate that our approach consistently outperforms traditional semi-supervised learning methods, particularly in handling noisy data. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Granular-Ball Computing Semi-Supervised Learning Weighted Fuzzy Rough Sets

来源：评论

学校读者我要写书评

暂无评论

ANALYSIS OF TRIPARTITE GAME IN POWER SYSTEMS BASED ON UNCERTAIN NASH EQUILIBRIUM THEORY

引用

UPB Scientific Bulletin, Series A: Applied Mathematics and Physics 2025年第1期87卷 117-128页

作者： Wu, Liang Yan, Xiaolin Yao, Zhangsong Zhao, Teng School of Management and Ningxia Key Laboratory of intelligent information and Big Data Processing North Minzu University Ningxia Yinchuan750021 China School of Mathematical Sciences Tiangong University Tianjin300387 China School of Information Engineering Nanjing Xiaozhuang University Nanjing211171 China School of Mathematics and Information Science North Minzu University Ningxia Yinchuan750021 China

Power systems serve as the fundamental infrastructure for the socioeconomic development of modern societies. Researching power systems can stimulate the growth of the power industry and contribute to the sustainable development of society. This paper aims to address uncertainties prevalent in power systems, including extreme weather events, disruptions in renewable energy supply, and adjustments in economic policies. To achieve this objective, an uncertain Nash equilibrium model is established. Subsequently, a game theoretic analysis is conducted to maximize the interests of users, grid companies, and proxy purchasers. Under the condition of not necessarily continuous differentiability, the Riemann-Stieltjes discrete approximation method has been proposed. The difficulty of calculating the expectation of the optimal revenue function has been resolved. Weak first-order equilibrium condition based on Clarke’s generalized gradient, the convergence and convergence rate of uncertain Nash equilibrium solutions are proved. © 2025, Politechnica University of Bucharest. All rights reserved.

关键词： power system tripartite game uncertain Nash equilibrium uncertainty theory

来源：评论

学校读者我要写书评

暂无评论

Toward Damage-Less robotic Fragile Fruit Grasping: A Closed-Loop Force Control Method for Pneumatic-Driven Soft Gripper

引用

SOFT robotICS 2024年 2024 Dec 9页

作者： Wang, Qingyu Zhang, Youchao Liu, Wei Li, Qiang Zhang, Jianwei Knoll, Alois Zhou, Mingchuan Jiang, Huanyu Ying, Yibin Zhejiang Univ Coll Biosyst Engn & Food Sci Hangzhou Peoples R China Zhejiang Univ Zhejiang Key Lab Intelligent Sensing & Robot Agr Hangzhou Peoples R China Minist Agr & Rural Affairs Key Lab Site Proc Equipment Agr Prod Hangzhou Peoples R China Shenzhen Technol Univ Coll Big Data & Internet Shenzhen 518118 Guangdong Peoples R China Tech Univ Munich Dept Comp Sci Munich Germany

Fragile fruit uploading and packaging are labor-intensive and time-consuming steps in postharvest industry. With the aging of the global population, it is supposed to develop robotic grasping systems to replace manual labor. However, damage-less grasping of fragile fruit is the key problem in robotization. Inappropriate grasping force will result in damage, early-stage bruise, or slip. Benefits from the advantages of softness and compliance of a pneumatic-driven soft gripper have been widely adopted for agricultural product and food manipulation. Nevertheless, pneumatic gripper is a complex, multivariable, nonlinear, and long time-delay control system, which is difficult to achieve robust closed-loop grasping force control. In this study, we aim to solve this problem and developed a robotic grasping force control system with pneumatic gripper and matrix force sensor. The force distribution condition was explored to tackle the problem in changing of the main contact point. A double closed-loop control method was proposed based on Kalman filter (KF) and proportion integration differentiation controller with dead band. The external and internal control loops were force controller and air pressure of the pump controller, respectively. The double closed-loop controller with dead band achieved robust grasping force control through air pressure. The experimental results validated the effectiveness of the KF method for denoising and the matrix force visualization method for exploring grasping mechanism. Ablation studies were carried out to demonstrate the effectiveness of the multiple grasping force sensing units in matrix form and the dead band in the controller. The maximum steady-state error was 0.07 N. In addition, the generalization performance and the antidisturbance ability of the grasping force control system was also validated. In summary, the problem in closed-loop control of the grasping force for pneumatic gripper has been solved in our study, and the method in

关键词： robotic fragile fruit grasping grasping force control pneumatic-driven soft gripper double closed-loop control

来源：评论

学校读者我要写书评

暂无评论

Rethinking Two-Stage Referring Expression Comprehension: A Novel Grounding and Segmentation Method Modulated by Point 38

Rethinking Two-Stage Referring Expression Comprehension: A N...

引用

38th AAAI Conference on Artificial Intelligence (AAAI) / 36th Conference on Innovative Applications of Artificial Intelligence / 14th Symposium on Educational Advances in Artificial Intelligence

作者： Zhao, Peizhi Zheng, Shiyi Zhao, Wenye Xu, Dongsheng Li, Pijian Cai, Yi Huang, Qingbao Guangxi Univ Sch Elect Engn Nanning Peoples R China Guangxi Key Lab Multimedia Commun & Network Techn Nanning Guangxi Peoples R China South China Univ Technol Sch Software Engn Guangzhou Peoples R China MOE China Key Lab Big Data & Intelligent Robot SCUT Guangzhou Peoples R China

ISBN: (纸本)1577358872

As a fundamental and challenging task in the vision and language domain, Referring Expression Comprehension (REC) has shown impressive improvements recently. However, for a complex task that couples the comprehension of abstract concepts and the localization of concrete instances, one-stage approaches are bottlenecked by computing and data resources. To obtain a low-cost solution, the prevailing two-stage approaches decouple REC into localization (region proposal) and comprehension (region-expression matching) at regionlevel, but the solution based on isolated regions cannot sufficiently utilize the context and is usually limited by the quality of proposals. Therefore, it is necessary to rebuild an efficient two-stage solution system. In this paper, we propose a point-based two-stage framework for REC, in which the two stages are redefined as point-based cross-modal comprehension and point-based instance localization. Specifically, we reconstruct the raw bounding box and segmentation mask into center and mass scores as soft ground-truth for measuring point-level cross-modal correlations. With the soft groundtruth, REC can be approximated as a binary classification problem, which fundamentally avoids the impact of isolated regions on the optimization process. Remarkably, the consistent metrics between center and mass scores allow our system to directly optimize grounding and segmentation by utilizing the same architecture. Experiments on multiple benchmarks show the feasibility and potential of our point-based paradigm. Our code available at https://***/VILANLab/PBREC-MT.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

An Adaptive DoH Encrypted Tunnel Detection Method Based on Contrastive Learning

引用

IEEE Internet of Things Journal 2025年

作者： Tong, Jiacheng Zhao, Yilin Jin, Chongju Chen, Wei Zhang, Yiting Wu, Lifa Nanjing University of Posts and Telecommunications School of Computer Science Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing210003 China

The percentage of encrypted network traffic has constantly increased as network security has been continuously improved. Attackers can, however, utilize encrypted DNS over HTTPS (DoH) to conceal their malicious traffic, which makes it more difficult to identify malicious tunnels. To address this issue, we first examine the encryption features of DoH tunnel traffic. Due to the incapability of current detection techniques to properly fuse traffic attributes, a fusion learning-based method is proposed to detect DoH encrypted tunnel traffic. At the same time, we discover that the DoH traffic samples may exhibit concept drift. As a result, we present a concept drift detection approach based on a contrastive sparse autoencoder. In addition to the above method, a model retraining strategy is also suggested to improve the model’s capacity to identify new DoH encrypted tunnel traffic while reducing its reliance on expert label data. This strategy involves incrementally training the model using as few samples as possible. Experiments demonstrate that the proposed method can significantly enhance detection performance. When 7% of drift samples are used during incremental training, the detection accuracy of the model recovers from 74.02% to 99.96%. © 2014 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Generative data Free Model Quantization With Knowledge Matching for Classification

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2023年第12期33卷 7296-7309页

作者： Xu, Shoukai Zhang, Shuhai Liu, Jing Zhuang, Bohan Wang, Yaowei Tan, Mingkui South China Univ Technol Sch Software Engn Guangzhou 510006 Peoples R China Peng Cheng Lab Shenzhen 518055 Peoples R China Monash Univ Fac Informat Technol Clayton Vic 3800 Australia South China Univ Technol Key Lab Big Data & Intelligent Robot Minist Educ Guangzhou 510006 Peoples R China

Neural network quantization aims to reduce the model size, computational complexity, and memory consumption by mapping weights and activations from full-precision to low-precision. However, many existing quantization methods, either post-training with calibration or quantization-aware training with fine-tuning, require original data for better performance, which may not be available due to confidentiality or privacy constraints. This lack of data can lead to a significant decline in performance. In this paper, we propose a universal and effective method called Generative data Free Model Quantization with Knowledge Matching for Classification(KMDFQ) that removes the dependence on data for neural network quantization. To achieve this, we propose a knowledge matching generator that produces meaningful fake data based on the latent knowledge in the pre-trained model, including classification boundary knowledge and data distribution information. Based on this generator, we propose a fake-data driven data free quantization method that uses the generated data to take advantage of the latent knowledge for quantization. Furthermore, we introduce Mean Square Error alignment during the fine-tuning of the quantized model to more strictly and directly learn knowledge, making it more suitable for data free quantization. Extensive experiments on image classification demonstrate the effectiveness of our method, achieving higher accuracy than existing data free quantization methods, particularly as the quantization bit decreases. For example, on ImageNet, the 4-bit data free quantized ResNet-18 has less than a 1.2% accuracy decline compared to quantization with real data. The source code is available at https://***/ZSHsh98/KMDFQ.

关键词： data privacy and security model compression data free quantization data generation

来源：评论

学校读者我要写书评

暂无评论

ALEDAR: An Attentions-based Encoder-Decoder and Autoregressive model for workload Forecasting of Cloud data Center 25

ALEDAR: An Attentions-based Encoder-Decoder and Autoregressi...

引用

25th IEEE International Conference on Computer Supported Cooperative Work in Design, CSCWD 2022

作者： Sun, Wei Xu, Xiaolong Nanjing University of Posts and Telecommunications Jiangsu Key Laboratory of Big Data Security and Intelligent Processing School of Computer Science Nanjing China

ISBN: (纸本)9781665405270

Effective workload forecasting can provide a reference for resource scheduling in cloud data centers. Compared with the normal single data center, the multi-data center has a more complicated architecture design and provides more diverse computing services. The traditional load forecasting models need too much manual intervention to set up the parameters, meanwhile, the emerging neural network methods are not sensitive to the prediction scale and cannot capture the long-term associations between input features. To address these challenges, we propose a hybrid model named Attentions-based LSTM Encoder-Decoder network and Autoregressive model (ALEDAR), which combines neural network and statistical learning methods, to analyze the linear and nonlinear characteristics of the load sequence over time in a multi-cloud data center environment. ALEDAR uses a dual attention-based Encoder-Decoder architecture to extract the relationships between historical workload data, the design can also avoid the deterioration of prediction effect caused by long-range data scale, the output layer is composed of a three-layer perceptron. Moreover, ALEDAR employs an autoregressive module to capture the linear trend of the load sequence and eliminate scale insensitivity of input and output data. The experimental results show that our approach is adaptive and can improve the performance of host workload prediction in both single cloud data center and multi-cloud data center environments. We evaluate the performance of the proposed algorithm on real-world data sets and observe consistent improvement of 9.7% - 34.2% over the state-of-the-art baselines. © 2022 IEEE.

关键词： Forecasting

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：