检索结果-内蒙古大学图书馆

MedBLIP: A Multimodal Method of Medical Question-Answering Based on Fine-Tuning Large Language Model

computerized Medical Imaging and Graphics 2025年

作者： Lejun Gong Jiaming Yang Shengyuan Han Yimu Ji Jiangsu Key Lab of Big Data Security & Intelligent Processing School of computer science Nanjing University of Posts and Telecommunications Nanjing210023 China Institute of High Performance Computing and Bigdata Nanjing University of Posts and Telecommunications Nanjing 210023 China

Medical visual question answering is crucial for effectively interpreting medical images containing clinically relevant information. This study proposes a method called MedBLIP (Medical Treatment Bootstrapping Language-Image Pretraining) to tackle visual language generation tasks related to chest X-rays in the medical field. The method combine an image encoder with a large-scale language model, and effectively generates medical question-answering text through a strategy of freezing the image encoder based on the BLIP-2 model. Firstly, chest X-ray images are preprocessed, and an image sample generation algorithm is used to enhance the text data of doctor-patient question-answering, thereby increasing data diversity. Then, a multi-layer convolutional image feature extractor is introduced to better capture the feature representation of medical images. During the fine-tuning process of the large language generation model, a new unfreezing strategy is proposed, which is to unfreeze different proportions of the weights of the fully connected layer to adapt to the data in the medical field. The image feature extractor is responsible for extracting key features from images, providing the model with rich visual information, while the text feature extractor accurately captures the essential requirements of the user's question. Through their synergistic interaction, the model can more effectively integrate medical images and user inquiries, thereby generating more accurate and relevant output content. The experimental results show that unfreezing 31.25% of the weights of the fully connected layer can significantly improve the performance of the model, with ROUGE-L reaching 66.12%, and providing a more accurate and efficient answer generation solution for the medical field. The method of this study has potential applications in the field of medical language generation tasks. Although the proposed model cannot yet fully replace human radiologists, it plays an indispensable role

关键词：

来源：评论

学校读者我要写书评

暂无评论

HeRB: Heterophily-Resolved Structure Balancer for Graph Neural Networks

arXiv

引用

arXiv 2025年

作者： Chen, Ke-Jia Mu, Wenhui ZhengLiu Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Jiangsu Nanjing210023 China School of Computer Science Nanjing University of Posts and Telecommunications Jiangsu Nanjing210023 China State Key Laboratory of Novel Software Technology Nanjing University Jiangsu Nanjing210093 China

—Recent research has witnessed the remarkable progress of Graph Neural Networks (GNNs) in the realm of graph data representation. However, GNNs still encounter the challenge of structural imbalance. Prior solutions to this problem did not take graph heterophily into account, namely that connected nodes process distinct labels or features, thus resulting in a deficiency in effectiveness. Upon verifying the impact of heterophily on solving the structural imbalance problem, we propose to rectify the heterophily first and then transfer homophilic knowledge. To the end, we devise a method named HeRB (Heterophily-Resolved Structure Balancer) for GNNs. HeRB consists of two innovative components: 1) A heterophily-lessening augmentation module which serves to reduce inter-class edges and increase intra-class edges;2) A homophilic knowledge transfer mechanism to convey homophilic information from head nodes to tail nodes. Experimental results demonstrate that HeRB achieves superior performance on two homophilic and six heterophilic benchmark datasets, and the ablation studies further validate the efficacy of two proposed components. Copyright © 2025, The Authors. All rights reserved.

关键词： Network theory (graphs)

来源：评论

学校读者我要写书评

暂无评论

Congestion Relief in Downlink OFDMA Cellular System Using Inter-Cell Relay

引用

China Communications 2019年第4期16卷 35-46页

作者： Weifeng Lu Mingqi Zhu Jia Xu Siguang Chen Lijun Yang Jian Xu School of Computer Science Nanjing University of Posts and Telecommunications Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications College of Internet of Things Nanjing University of Posts and Telecommunications School of Computer Science and Engineering Nanjing University of Science and Technology

This paper proposes the concept of inter-cell relay for downlink orthogonal frequency division multiple access(OFDMA) cellular systems, which uses multi-hop to relay calls from overloaded cells to light-load neighboring cells. It is shown that when using inter-cell relay, the number of calls in the congestion cell can be significantly increased. The congestion cell is divided into two parts. One is called non-relay area(NRA), in which a call directly communicates with the base station(BS) of a congested cell. The other is called relay area(RA), in which a call communicates with the BS of a neighboring cell through a relay station(RS). The two parts have different user-call densities. By adjusting the densities of two parts, we will maximize the number of supported calls inside a congested cell. The results show the benefits gained from inter-cell relay in congestion relief, which can reduce cell congestion by fully utilizing the available resources in the neighboring cells.

关键词： OFDMA cellular system congestion relief optimization problem inter-cell relay

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

A New Semi-supervised Approach for Network Encrypted Traffic Clustering and Classification 25

A New Semi-supervised Approach for Network Encrypted Traffic...

引用

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

作者： Lin, Kunda Xu, Xiaolong Jiang, Yu School of Computer Science Nanjing University of Posts and Telecommunications Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing China

ISBN: (纸本)9781665405270

Encrypted network traffic classification is an essential task in modern communications, which is used in a wide range of applications, such as network resource allocation, QoS (Quality of Service), malicious detection, etc. With the continuous evolution of network technology, approaches used to classify network encrypted traffic have become increasingly complex, and model training relies heavily on a large amount of labeled data. However, the acquisition of correct and massive labeled data of network traffic in the real environment remains a major challenge in this field. On the opposite, unlabeled traffic is extremely easy to obtain in a network. Therefore, the effective use of unlabeled data is of great significance to the development of modern communications. In this paper, we propose the Sauce model, which can effectively use unlabeled information to obtain high-quality clustering space. It is composed of Aux (auxiliary network) and AE (auto encoder), where Aux is designed for collaborative training with AE, affecting the distribution of samples in the latent space generated by AE. Sauce uses t-SNE (t- distributed stochastic neighbor embedding) to perform secondary dimensionality reduction on the latent code, and then uses a clustering algorithm for cluster analysis. Besides, sauce applies the self-training technique, replacing the real labeled data with pseudo-labeled data to reduce the reliance on labeled data and improve the utilization of unannotated data. We conduct experiments on two real network datasets. The experiments show that Sauce can achieve clustering accuracies of 98.4% (VPN dataset) and 98.0% (TOR dataset), outperforming other unsupervised or semi-supervised learning methods. © 2022 IEEE.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Raft Consensus Algorithm Based on Credit Model in Consortium Blockchain

引用

Wuhan University Journal of Natural sciences 2020年第2期25卷 146-154页

作者： CHEN Yunfang LIU Ping ZHANG Wei School of Computer Science Nanjing University of Posts and TelecommunicationsNanjing 210023JiangsuChina Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and TelecommunicationsNanjing 210023JiangsuChina

As one of the underlying technologies of the blockchain,the consensus algorithm plays a vital role in ensuring security and *** a consensus algorithm for the private blockchain,Raft has better performance than the rest of the consensus algorithms,and it does not cause problems such as the concentrated hashing power,resource waste and ***,Raft can only be used in a non-byzantine environment with a small network *** order to enable Raft to be used in a large-scale network with a certain number of byzantine nodes,this paper combines Raft and credit model to propose a Raft blockchain consensus algorithm based on credit model *** the node credit evaluation phase,RBF-based support vector machine is used as the anomaly detection method,and the node credit evaluation model is *** the Trust Nodes List(TNL)mechanism is introduced to make the consensus phase in a creditable network ***,the common node is synchronized to the consensus node to update the blockchain of the entire *** show that CRaft has better throughput and lower latency than the commonly used consortium blockchain consensus algorithm PBFT(Practical Byzantine Fault Tolerance).

关键词： credit model consensus algorithm consortium blockchain P2P network

来源：评论

学校读者我要写书评

暂无评论

MTSS: multi-path traffic scheduling mechanism based on SDN

引用

Journal of Systems Engineering and Electronics 2019年第5期30卷 974-984页

作者： XU Xiaolong CHEN Yun HU Liuyun KUMAR Anup Jiangsu Key Laboratory of Big Data Security&Intelligent Processing Nanjing University of Posts and TelecommunicationsNanjing 210023China Institute of Big Data Research at Yancheng Nanjing University of Posts and TelecommunicationsYancheng 224000China School of Computer Science Nanjing University of Posts and TelecommunicationsNanjing 210023China Department of Computer Engineering and Computer Science University of LouisvilleLouisville KY40292USA

Large-scale and diverse businesses based on the cloud computing platform bring the heavy network traffic to cloud data ***,the unbalanced workload of cloud data center network easily leads to the network congestion,the low resource utilization rate,the long delay,the low reliability,and the low *** order to improve the utilization efficiency and the quality of services(QoS)of cloud system,especially to solve the problem of network congestion,we propose MTSS,a multi-path traffic scheduling mechanism based on software defined networking(SDN).MTSS utilizes the data flow scheduling flexibility of SDN and the multi-path feature of the fat-tree structure to improve the traffic balance of the cloud data center network.A heuristic traffic balancing algorithm is presented for MTSS,which periodically monitors the network link and dynamically adjusts the traffic on the heavy link to achieve programmable data forwarding and load *** experimental results show that MTSS outperforms equal-cost multi-path protocol(ECMP),by effectively reducing the packet loss rate and *** addition,MTSS improves the utilization efficiency,the reliability and the throughput rate of the cloud data center network.

关键词： cloud data center software defined networking(SDN) load balancing multi-path transmission OpenFlow

来源：评论

学校读者我要写书评

暂无评论

Topic modeling for noisy short texts with multiple relations 30

Topic modeling for noisy short texts with multiple relations

引用

30th International Conference on Software Engineering and Knowledge Engineering, SEKE 2018

作者： Liu, Chiyu Liu, Zheng Li, Tao Xia, Bin Jiangsu Key Laboratory of Big Data Security and Intelligent Processing School of Computer Science Nanjing University of Posts and Telecommunications Nanjing210023 China

ISBN: (纸本)1891706446

Understanding contents in social networks by inferring high-quality latent topics from short texts is a significant task in social analysis, which is challenging because social network contents are usually extremely short, noisy and full of informal vocabularies. Due to the lack of sufficient word co-occurrence instances, well-known topic modeling methods such as LDA and LSA cannot uncover high-quality topic structures. Existing research works seek to pool short texts from social networks into pseudo documents or utilize the explicit relations among these short texts such as hashtags in tweets to make classic topic modeling methods work. In this paper, we explore this problem by proposing a topic model for noisy short texts with multiple relations called MRTM (Multiple Relational Topic Modeling). MRTM exploits both explicit and implicit relations by introducing a document-Attribute distribution and a two-step random sampling strategy. Extensive experiments, compared with stateof-the-Art topic modeling approaches, demonstrate that MRTM can alleviate the word co-occurrence sparsity and uncover highquality latent topics from noisy short texts. © 2018 Universitat zu Koln. All rights reserved.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

Sharing of Encrypted Lock keys in the Blockchain-Based Renting House System from Time- and Identity-Based Proxy Reencryption

引用

China Communications 2022年第5期19卷 164-177页

作者： Zhiwei Wang Liping Qian Danwei Chen Guozi sun School of Computer Nanjing University of Posts and TelecommunicationsNanjing 210023China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing 210023China Guangxi Key Laboratory of Cryptography and Information Security Department of Computer SciencesGuilin University of Electronic TechnologyGuilin 541004China

To design an efficient protocol for sharing the encrypted lock keys in the renting house system,we introduce a new notion called time-and identitybased proxy reencryption(TIPRE)and the blockchain *** CPA secure TIPRE scheme is constructed from Green et al.’s identity-based proxy reencryption scheme by adding the time *** every time period,a time stamp authority generates a public key embedded with the current time stamp for each *** our protocol for the renting house system,the TIPRE scheme is the primary building block,and the blockchain platform serves instead of a trusted third party,such as a real estate agency between landlords and *** TIPRE scheme allows the landlord to change the lock key at each time period for *** blockchain platform allows the landlords and tenants to directly interact,and all of the interactions are recorded in the blockchain database to provide the desired security requirements,such as nonrepudiation and ***,we provide the secure analysis of our protocol and test its performance by implementing it in the MacBook Pro and the Intel Edison development platforms.

关键词： identity-based proxy reencryption time stamp renting houses system blockchain

来源：评论

学校读者我要写书评

暂无评论

Predicting Genotype Information Related to COVID-19 for Molecular Mechanism Based on Computational Methods

引用

computer Modeling in Engineering & sciences 2021年第10期129卷 31-45页

作者： Lejun Gong Xingxing Zhang Li Zhang Zhihong Gao Jiangsu Key Laboratory of Big Data Security&Intelligent Processing School of Computer Science Nanjing University of Posts and TelecommunicationsNanjing210046China Smart Health Big Data Analysis and Location Services Engineering Laboratory of Jiangsu Province Nanjing210046China College of Computer Science and Technology Nanjing Forestry UniversityNanjing210037China Zhejiang Engineering Research Center of Intelligent Medicine Wenzhou325035China

Novel coronavirus disease 2019(COVID-19)is an ongoing health *** studies are related to ***,its molecular mechanism remains *** rapid publication of COVID-19 provides a new way to elucidate its mechanism through computational *** paper proposes a prediction method for mining genotype information related to COVID-19 from the perspective of molecular mechanisms based on machine *** method obtains seed genes based on prior *** genes are mined from biomedical *** candidate genes are scored by machine learning based on the similarities measured between the seed and candidate ***,the results of the scores are used to perform functional enrichment analyses,including KEGG,interaction network,and Gene Ontology,for exploring the molecular mechanism of *** results show that the method is promising for mining genotype information to explore the molecular mechanism related to COVID-19.

关键词： COVID-19 SARS-CoV-2 computational method bioinformatics genotype machine 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：