检索结果-内蒙古大学图书馆

3rd International Conference on computer science and Artificial Intelligence, CSAI 2019 and its Workshop - The 11th International Conference on Information and Multimedia Technology, ICIMT 2019

作者： Fan, Hongjie Wang, Dongsheng Ye, Songtao School of Electronics Engineering and Computer Science Peking University Beijing China School of Software and Microelectronics Peking University Beijing China College of Information Engineering Xiangtan University Xiangtan China

ISBN: (纸本)9781450376273

Named entity extraction task refers to identifying and extracting proper named entities from natural language texts. It is the key task in knowledge graph construction. Disease, symptom and drug entities are widely distributed in Chinese electronic medical records (EMRs). Extracting high-quality medical entities from EMR plays an important role in building medical knowledge graph, medical question & answer and assistance decision making. For the widely distributed entities, in this paper, we propose an end-to-end named entity extraction framework, which uses popular deep learning based approach, known as conditional random field (CRF), bidirectional-long short-term memory (Bi- LSTM+CRF) and BERT+Bi-LSTM+CRF for training and testing the named entities. These models are tested on real medical records, and the experimental results show that the method can effectively identify the entities, and has certain practical value. © 2019 Association for Computing Machinery.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Dual-domain decoupled fusion network for semantic segmentation of remote sensing images

引用

Information Fusion 2025年 124卷

作者： Xin Li Feng Xu Jue Zhang Anzhu Yu Xin Lyu Hongmin Gao Jun Zhou College of Computer Science and Software Engineering Hohai University Nanjing China Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China School of Engineering and Built Environment Griffith University Nathan Australia School of Surveying and Mapping Information Engineering University Zhengzhou China School of Information and Communication Technology Griffith University Nathan Australia

Semantic segmentation of remote sensing images (RSIs) is a challenging task due to the complexity of spatial structures, diverse object scales, and heterogeneous land-cover patterns. Traditional approaches often struggle to effectively balance fine-grained boundary details and global contextual understanding, especially for high-resolution images. In this paper, we propose DDFNet, a novel dual-domain decoupled fusion network, to address these challenges. DDFNet integrates spatial and frequency domain features through a dynamic decoupling and fusion strategy. Specifically, we introduce a Dual-Domain Decoupled Feature Fusion (DDFF) module that selectively combines high- and low-frequency components from both domains, enabling the model to capture local textures and global semantics. To further enhance segmentation accuracy, we design a High-Order Geometric Prior Generation (HGPG) module, which utilizes gradient and curvature information to improve boundary precision and maintain geometric consistency. Extensive experiments on three benchmark datasets — ISPRS Vaihingen, ISPRS Potsdam, and LoveDA — demonstrate that DDFNet achieves state-of-the-art performance. Ablation studies validate the contributions of the DDFF and HGPG modules, and efficiency analysis shows DDFNet’s strong adaptability to different computational constraints.

关键词： Attention mechanism Feature fusion Remote sensing images Semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Cardiac Motion Tracking in Short-axis MRI using Siamese Convolution Network

Cardiac Motion Tracking in Short-axis MRI using Siamese Conv...

引用

IEEE International Conference on Bioinformatics and Biomedicine

作者： Jiangyue Tang Ziyu Gan Xuan Yang College of Computer Science and Software Engineering Shenzhen University

ISBN: (纸本)9781728118680

Analysis of mechanical properties of left ventricle (LV) myocardium for short-axis MRI is essential to diagnosis and treatment of cardiovascular diseases. However, the LV myocardium appears highly homogeneous, and there are few features inside the myocardium in cine MRI, which makes it difficult to track motion of the myocardium. In this paper, we propose a novel approach for motion tracking of the myocardium in MR image sequences. We constructed a Siamese convolution network with dense connections for feature extraction of points located on the myocardium contour. Based on a L_2 cost function, the matched patch pairs (positive pairs) and unmatched patch pairs (negative pairs) are used to train our network. Next, given a patch centered at the point located on the myocardium contour, the trained network is employed to track corresponding patches in the image at other time points. The robust point matching is performed between the given contour and the tracking contour of the myocardium to ensure the tracking contours smooth. Our proposed approach is evaluated on the public dataset, and evaluation results show that our approach achieves more accurate tracking accuracy compared with the state-of-the-art methods.

关键词： Motion tracking Convolution neural network Patch matching Cardiac short-axis MRI Myocardium contour siamese Cine Magnetic Resonance Imaging Convolution tracking

来源：评论

学校读者我要写书评

暂无评论

Robust embedding regression for face recognition 1

引用

2nd Chinese Conference on Pattern Recognition and computer Vision, PRCV 2019

作者： Bao, Jiaqi Lu, Jianglin Lai, Zhihui Liu, Ning Lu, Yuwu College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Institute of Textiles & Clothing Hong Kong Polytechnic University Kowloon Hong Kong

ISBN: (数字)9783030317232

ISBN: (纸本)9783030317225

Classical subspace learning methods such as spectral regression (SR) and its sparse extensions are all two-step ways, which will lead to a suboptimal subspace for feature extraction. Another potential drawback is that these methods are not robust to the outliers and the variations of data because they use Frobenius norm as the basic distance metric. To address these problems, a novel face recognition method called robust embedding regression (RER) is proposed, which performs low-dimensional embedding and jointly sparse regression simultaneously. By this way, the optimal subspace can be obtained. Besides, we not only emphasize L2;1-norm minimization on both loss function and regularization terms, but also use L2;1-norm as the basic distance metric. Therefore, we can obtain jointly sparse projections in the regression process and more stable and robust low-dimensional reconstruction in the embedding process. Moreover, we use a more generalized constraint to improve the generalization of RER. The corresponding optimal solution can be computed by generalized eigen-decomposition via an iterative optimization algorithm. Theoretical analysis and experimental results prove the convergence of RER. Extensive experiments show the proposed RER has a better performance than other related methods on four well-known datasets. © Springer Nature Switzerland AG 2019.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

The Effects of the Property of Access Possibilities and Cybersecurity Awareness on Social Media Application 1st

The Effects of the Property of Access Possibilities and Cybe...

引用

1st International Conference on Intelligent Cloud Computing, ICC 2019

作者： Alrashidi, Bedour F. Almuhana, Aljawharah M. Aljedaie, Alanoud M. Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia College of Computer Science and Software Engineering University of Hail Hail Saudi Arabia

ISBN: (纸本)9783030363642

Cybersecurity became the third war in the world as it affects the privacy, security, availability, and access possibilities of user’s data. Lately, the statistics shows that the users prefer social media application to share their data and updates. Many users believe that only their followers can see their updates while the permissions of access possibilities terms and conditions provided some authority to access the data. To highlight this issue we did a survey in users awareness of accepting access possibility to their data and analyse the risks of allowing/accepting the access possibility of users’ data in social media applications. In this paper we propose a Reconnaissance Penetration Testing Methodology (RPTM) that aims to study the process of reconnaissance and information gathering of specific target to show the user’s data. In result and discussion we have did a statistical study to find out the level of users awareness in cybersecurity and access possibilities. © 2019, Springer Nature Switzerland AG.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Collaborative city digital twin For Covid-19 pandemic: a federated learning solution

arXiv

引用

arXiv 2020年

作者： Pang, Junjie Li, Jianbo Xie, Zhenzhen Huang, Yan Cai, Zhipeng Business School College of Computer Science and Technology Qingdao University QingdaoShandong266000 China College of Computer Science and Technology Qingdao University QingdaoShandong266000 China College of Computer Science and Technology Jilin University ChangchunJilin130012 China College of Computing and Software Engineering at Kennesaw State University AtlantaGA United States Department of Computer Science Georgia State University AtlantaGA United States

The novel coronavirus, COVID-19, is a crisis that affects all segments of the population. As the knowledge and understanding of COVID-19 evolve, an appropriate response plan for this pandemic is regarded as the most effective method to control the spreading. Recent studies indicate that the city digital twin is beneficial to tackle this health crisis since it can construct a virtual replica to simulate factors such as climate conditions, response operations, and people’s trajectory to help plan efficient and inclusive decisions. However, the city digital twin system relies on long-term and high-quality data collection to make appropriate decisions, which limited its advantages when facing urgent crisis like COVID-19. Federated Learning (FL), where all the clients can learn a shared model while keeping all the training data locally, emerges as a promising solution to accumulate the insights from multiple data source efficiently. Furthermore, the enhanced privacy protection settings break the privacy barriers lies in such collaboration. In this work, we propose a collaborative city digital twin based on FL, a novel paradigm that allowing multiple city DT to share the local strategy and status in a timely manner. In particular, an FL central server manages the local updates of multiple collaborators (city DT), provides a global model which is trained in multiple iterations at different city DT systems, until the model gains the correlations between various response plan and infection trend. That means, a collaborative city DT paradigm based on FL techniques can obtain knowledge and patterns from multiple DTs, and eventually establish a ‘global view’ for city crisis management. Meanwhile, it also helps to improve each city digital twin selves by consolidating other DT’s respective data without violating privacy rules. To validate the proposed solution, we take COVID-19 pandemic as a case study. The experimental results on the real dataset with various response plan vali

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

The DUDFTO Attack: Towards Down-to-UP Timeout Probing and Dynamically Flow Table Overflowing in SDN

引用

IEEE Transactions on Network and Service Management 2025年

作者： Li, Jiasong Cui, Yunhe Chen, Yi Shen, Guowei Guo, Chun Qian, Qing Guizhou University State Key Laboratory of Public Big Data Engineering Research Center of Text Computing and Cognitive Intelligence Ministry of Education College of Computer Science and Technology Guizhou Provincial Characteristic Key Laboratory of Software Engineering and Information Security Guiyang550000 China Guizhou University of Finance and Economics School of Information Guiyang550000 China

As a new network structure, the decoupling of the control plane and forwarding plane makes software-Defined Networking (SDN) widely used in large-scale network scenarios. However, the decoupling network architecture also brings new vulnerabilities. The flow table overflow attack is an attack strategy that can overwhelm SDN switches. Nevertheless, the existing flow table overflow attacks may fail in probing timeouts and match fields of flow entries, due to link failure, measurement of the round-trip time (RTT) of different packets, interference of hard-timeout and idle-timeout. Meanwhile, the stealthiness of the existing attacks may also reduce, as these attacks use fixed attack rate. To improve the timeout probing accuracy and the stealthiness of attack, a new flow table overflow attack strategy, DUDFTO, is proposed to accurately probe timeout settings and match fields, then stealthily overflow SDN flow tables. Firstly, it probes the match fields by measuring the one-sided transmission delay of the packets. After that, DUDFTO designs a down-to-up feedback-based timeout probing algorithm to eliminate the issues caused by high RTT, link failure, interference between hard-timeout and idle-timeout. Then, DUDFTO designs a dynamic attack packets sending algorithm to improve its stealthiness. Finally, DUDFTO probes the flow table state to stop sending new attack packets. The evaluation results demonstrate that DUDFTO outperforms the existing attacks in terms of match fields probing ability, timeout probing relative error, number of packet_in and flow_mod messages generated by the attack, rate distribution of packet_in and flow_mod messages generated during the attack, and number of detected attack packets. © 2004-2012 IEEE.

关键词： flow table overflow attack information probing SDN switchs

来源：评论

学校读者我要写书评

暂无评论

Proactive Data Caching and Replacement in the Edge Computing Environment

Proactive Data Caching and Replacement in the Edge Computing...

引用

IEEE International Conference on Cloud Computing, CLOUD

作者： Ying Liu Ao Zhang Xiaoyu Xia Feifei Chen Lei Ye Bin Zhang Qiang He Software College Northeastern University Shenyang China School of Information Technology Deakin University Melbourne Australia College of Computer Science and Technology Zhejiang University of Technology Hangzhou China School of Software Engineering Chengdu University of Information Technology China

ISBN: (数字)9781728187808

ISBN: (纸本)9781728187815

Mobile data traffic is exploding in recent years with the exponential growth of mobile users. In the edge computing environment where edge servers are deployed around mobile users, caching data on edge servers can ensure mobile users' fast access to those data and reduce the data traffic between mobile users and the centralized cloud. Existing studies consider the data cache and replacement problem with the consideration of the reduction of network delay and the improvement of mobile devices' energy efficiency. In this paper, we attack proactive data caching and replacement problem in the edge computing environment from the service providers' perspective, who would like to maximize their venues of caching their data. This problem is complicated because data caching produces benefits at a cost and there usually is a trade-off in-between. In this paper, we formulate the data caching and replacement problem as an integer programming problem, and maximizes the revenue of the service provider while satisfying a constraint for data access latency. We also propose an online algorithm to solve problems in large-scale scenarios. Extensive experiments are conducted on a real-world dataset that contains the locations of edge serPvers and mobile users.

关键词： Integer programming Cloud computing Mobile handsets Energy efficiency Delays Servers Edge computing

来源：评论

学校读者我要写书评

暂无评论

FlashRegex: Deducing Anti-ReDoS Regexes from Examples

FlashRegex: Deducing Anti-ReDoS Regexes from Examples

引用

IEEE International Conference on Automated software engineering (ASE)

作者： Yeting Li Zhiwu Xu Jialun Cao Haiming Chen Tingjian Ge Shing-Chi Cheung Haoren Zhao State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China College of Computer Science and Software Engineering Shenzhen University Shenzhen China The Hong Kong University of Science and Technology Hong Kong China State Key Laboratory of Computer Science Institute of Software Beijing China University of Massachusetts Lowell United States Shaanxi Normal University Xi'an China

ISBN: (数字)9781450367684

ISBN: (纸本)9781728172811

Regular expressions (regexes) are widely used in different fields of computer science such as programming languages, string processing and databases. However, existing tools for synthesizing or repairing regexes were not designed to be resilient to Regex Denial of Service (ReDoS) attacks. Specifically, if a regex has super-linear (SL) worst-case complexity, an attacker could provide carefully-crafted inputs to launch ReDoS attacks. Therefore, in this paper, we propose a programming-by-example framework, FlashRegex, for generating anti-ReDoS regexes by either synthesizing or repairing from given examples. It is the first framework that integrates regex synthesis and repair with the awareness of ReDoS-vulnerabilities. We present novel algorithms to deduce anti-ReDoS regexes by reducing the ambiguity of these regexes and by using Boolean Satisfiability (SAT) or Neighborhood Search (NS) techniques. We evaluate FlashRegex with five related state-of-the-art tools. The evaluation results show that our work can effectively and efficiently generate anti-ReDoS regexes from given examples, and also reveal that existing synthesis and repair tools have neglected ReDoS-vulnerabilities of regexes. Specifically, the existing synthesis and repair tools generated up to 394 ReDoS-vulnerable regex within few seconds to more than onehour, while FlashRegex generated no SL regex within around five seconds. Furthermore, the evaluation results on ReDoS-vulnerable regex repair also show that FlashRegex has better capability than existing repair tools and even human experts, achieving 4 more ReDoS-invulnerable regex after repair without trimming and resorting, highlighting the usefulness of FlashRegex in terms of the generality, automation and user-friendliness.

关键词： computer science computer languages Databases Maintenance engineering Tools Security software engineering

来源：评论

学校读者我要写书评

暂无评论

Integration of Deep Learning and Machine Learning Techniques for Advancing the Detection of Plant Diseases

Engineering Reports

引用

engineering Reports 2025年第6期7卷

作者： Abdul Karim Touqeer Ahmed Jumani Muhammad Amir Raza Shadi Khan Baloch Nouman Qadeer Soomro Muhammad Masud Muhammad Salman Saeed Mouaaz Nahas Aamir Ali Patoli Department of Electrical Engineering Mehran University of Engineering and Technology Khairpur Mirs' Sindh Pakistan Department of Electrical Engineering and Computer Science College of Engineering A'Sharqiyah University Ibra Oman Department of Mechatronics Engineering Mehran University of Engineering and Technology Jamshoro Pakistan Department of Software Engineering Mehran University of Engineering and Technology Khairpur Mirs' Sindh Pakistan Department of Electrical Engineering College of Engineering University of Business and Technology Jeddah Saudi Arabia Multan Electric Power Company Multan Pakistan Department of Electrical Engineering Umm Al-Qura University Makkah Saudi Arabia Department of Electronics Engineering Mehran University of Engineering and Technology Jamshoro Pakistan

This research proposed a new hybrid system for the detection of diseases in Pepper, Tomatoes, and Potatoes vegetable crops. Vegetable plant disease poses a significant threat to both the quality and quantity of crop yields, leading to enormous economic losses in the agricultural industry. Early detection and prompt measures are essential for the effective control of plant diseases. Extreme Gradient Boosting (XGBoost) and Convolutional Neural Network (CNN) algorithm were employed to detect diseases precisely. CNN derived intricate patterns from images, whereas the XGBoost algorithm is employed for precise categorization. The model is built for Pepper, Tomatoes, and Potatoes diseases and also for plant type classification using the dataset which was captured by mobile phone camera from Kotri and Unerpur, Sindh, Pakistan with accuracy of 93%, 92%, 99%, and 98%, respectively. Detection of new diseases which were not detected earlier is another primary aim of this research. For the detection of the unknown kind of diseases in plants, the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm was utilized for clustering the similar captured images and for disease classification; then CNN XGBoost was applied on the newly developed dataset. This study employed a new automated hybrid framework that combines the strengths of CNN and XGBoost to identify familiar and unfamiliar diseases in vegetable crops.

关键词： deep learning machine learning plant disease detection vegetables

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：