检索结果-内蒙古大学图书馆

3rd International Conference on Data Science and Information technology, DSIT 2020

作者： Wang, Xinyun Ning, Hongyun Tianjin Key Laboratory of Intelligence Computing and New Software Technology Tianjin University of Technology Tianjin China

ISBN: (纸本)9781450376044

keyword extraction plays the same role as the cornerstone in the field of natural language processing. Text classification, information retrieval, abstract generation and text clustering are all based on keyword extraction. This article takes the research of keyword extraction model as the subject. First, it analyzes the principle and limitations of the traditional keyword extraction model TF-IDF when extracting keywords. Secondly, it focuses on the problem of ignoring context and word polysemy in the keyword extraction model. To improve, introduce the concept of context vector, construct a chain-extensible structure for polysemous words, and propose a new keyword extraction method of TF-IDF that combines context and semantic classification. The specific research contents are as follows: TF-IDF extracts keywords based on multiple texts. The target keywords are words that appear frequently in the current text, but appear in other articles that are significantly lower in frequency than the current article. This method takes into account the characteristic content of the article and makes the article distinct. However, this method ignores the influence of the context of the article and the problem of word polysemy. Obviously, the expression of the thought of the article will not only be affected by the context of the words, but also by the semantics of the words. In order to solve the above problems, this paper proposes a TF-IDF keyword extraction method that combines context and semantic classification. First, the text constructs a linked list expandable structure to solve the problem of polysemy;then, the influence of context is introduced. Before inserting a new word into the extended structure, the semantic similarity is calculated through the context vector. Finally, iterate over the entire expandable structure, sum the word frequency with semantic similarity under each semantic, and then sort the results to obtain TopN words as the text keywords of the correspond

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Chinese keyword extraction method based on context and word classification

Chinese keyword extraction method based on context and word ...

引用

2020 International Conference on Computer Information and Big Data Applications, CIBDA 2020

作者： Wang, Xinyun Ning, Hongyun Tianjin Key Laboratory of Intelligence Computing &new Software Technology Tianjin University of Technology Tianjin China

ISBN: (纸本)9781728198378

The traditional keyword extraction algorithm TextRank increases the weight of the central word through the correlation between the words and the central word in the co-occurrence window, but the number of words in the co-occurrence window is limited, which will cause the poor expression of the semantic information of the word, and then affect accuracy of the keyword extraction results. In order to solve the limitation of word information in traditional keyword extraction methods and the problem of ignoring polysemy, this paper proposes a Chinese keyword extraction method based on context and semantic classification. © 2020 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

INNSE: Invertible neural network-based DNA image storage with self-correction encoding

引用

Computational and Structural Biotechnology Journal 2025年 27卷 2492-2502页

作者： Yanfen Zheng Xiaokang Zhang Lijun Sun Ben Cao Bin Wang Qiang Zhang Pan Zheng School of Computer Science and Technology Dalian University of Technology Dalian Liaoning 116024 China The Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian University Dalian Liaoning 116622 China Department of Accounting and Information Systems University of Canterbury Upper Riccarton Christchurch 8140 New Zealand

DNA storage has become an alternative to silicon-based storage of media. However, when used to store multimodal data such as images, it fails to take full advantage of the characteristics of high correlation and variability present in such data, and currently remains inferior in terms of encoding density and time complexity. It also has the shortcoming of weak performance in terms of error correction methods to address insertion and deletion errors caused by error crosstalk. Therefore, we proposed an invertible neural network-based DNA image storage self-correction encoding method (INNSE) that uses the invertibility of network to perform up-down sampling processing on image and video data, thereby greatly reducing the number of DNA sequences required for data storage. A codebook generator was then designed to encode low-dimensional vectors into DNA sequences that meet various constraints. Finally, a self-correction method was constructed to achieve DNA sequence error correction at the base level without adding any redundant information. Our experimental results showed that, compared to the Yin-Yang algorithm, the encoding density of INNSE was increased by 3×, encoding time complexity was reduced by 95.26%. Under a simulated error rate of 2%, PSNR and SSIM were raised by 80.88% and 63.82%, respectively, proving that INNSE has significant advantages in encoding performance and error correction ability.

关键词： Codebook generator DNA storage Invertible neural network Self-correction

来源：评论

学校读者我要写书评

暂无评论

Talking Head Generation for Media Interaction System with Feature Disentanglement

Talking Head Generation for Media Interaction System with Fe...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Lei Zhang Qingyang Chen Zhilei Liu College of Intelligence and Computing School of New Media and Communication Tianjin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun P.R. China State Key Laboratory for Novel Software Technology Nanjing University P.R. China School of New Media and Communication Tianjin University Tianjin China College of Intelligence and Computing Tianjin University Tianjin China

The task of talking head generation for the media interaction system is to take images and audio clips of the target face as input, and generate a realistic video of the target synchronized with the audio. Most of the existing works directly take all the information in the image as input, which causes the problem of feature information redundancy. At the same time, in the stage of feature fusion, the image and audio information is directly spliced, and the relationship between the two modal information is ignored. To solve the problems, we initially implement the disentanglement of image by introducing a loss function to separate the image into identity features and content-related features. Besides, we introduce a multi-head selfattention mechanism to learn the relationship between the two modal information of image and audio, and implement the full fusion of multi-modal information. In addition, we validate the effectiveness of our model through extensive quantitative and qualitative analysis of two datasets. Extensive experiments show the superiority of the proposed model in all aspects.

关键词： Analytical models Redundancy Media Synchronization Task analysis Faces

来源：评论

学校读者我要写书评

暂无评论

Family of Mutually Uncorrelated Codes for DNA Storage Address Design

IEEE Transactions on Nanobioscience

引用

IEEE Transactions on Nanobioscience 2025年 PP卷 PP页

作者： Liu, Zhenlu Cao, Ben Shao, Qi Zheng, Yanfen Wang, Bin Zhou, Shihua Zheng, Pan Dalian University Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian116622 China Dalian University of Technology School of Computer Science and Technology Dalian116024 China University of Canterbury Upper Riccarton Department of Accounting and Information Systems Christchurch8140 New Zealand

Deoxyribonucleic acid (DNA) has become an ideal medium for long-term storage and retrieval due to its extremely high storage density and long-term stability. But access efficiency is an existing bottleneck in DNA storage, especially the lack of high-quality random access address sequences. Therefore, in this paper, we report a series of approaches based on k-weakly mutually uncorrelated (k-WMU) codes to design the address sequence to improve the access efficiency of DNA storage. To address the problem of DNA sequences that are poorly scalable at the base level, we propose a 0-m-ruling coding scheme combined with k-WMU codes that can make address sequences avoid generating secondary structure with stem lengths ranging from 3 to 9. Based on the decoupled structure, We further extend the k-WMU codes with error correction function while satisfying combinatorial biological constraints. In order to investigate the performance of the designed address sequences for real-world applications, we perform simulation experiments based on thermodynamic properties and error correction capability as well as compared the minimum free energy (MFE), melting temperature (TM), and average decoding success rate (ADSR) with previous work. The results show that designed address sequences have a high MFE value and ADSR and a substantial reduction in TM-variance while satisfying the combinatorial biological constraints. As the quality of address sequences improves, this will help to achieve accurate random access as well as enhance the robustness of the DNA storage system. © 2002-2011 IEEE.

关键词： DNA sequences

来源：评论

学校读者我要写书评

暂无评论

new Method of Traffic Flow Forecasting Based on QPSO Strategy for Internet of Vehicles 4

New Method of Traffic Flow Forecasting Based on QPSO Strateg...

引用

4th IEEE International Conference on Smart Internet of Things, SmartIoT 2020

作者： Zhang, De-Gan Du, Jing-Yu Zhang, Ting Fan, Hong-Rui Tianjin University of Technology Tianjin Key Lab of Intelligent Computing Novel Software Technology Tianjin300384 China Tianjin University of Technology Ministry of Education Key Laboratory of Computer Vision and System Tianjin China

ISBN: (纸本)9781728165141

We propose a new method of traffic flow forecasting based on quantum particle swarm optimization strategy (QPSO) for Internet of Vehicles (IOV). Establish a corresponding model based on the characteristics of the traffic flow data. The genetic simulated annealing method is applied to the quantum particle swarm method to obtain the optimized initial cluster center, and is applied to the parameter optimization of the radial basis neural network prediction model. The function approximation of radial basis neural network can be used to obtain the required data. In addition, in order to compare the performance of the methods, a comparison study with other related methods such as QPSO-RBF is also performed. Our method can reduce prediction errors and get better and more stable prediction results. © 2020 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

LarTap: A Luminance-aware Framework with Text-correlation Priors for Multi-Exposure Image Fusion

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Wang, Enlong Li, Jiawei Yan, Tiantian Lei, Jia Zhou, Shihua Wang, Bin Liu, Jinyuan Kasabov, Nikola K. Dalian University Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian116622 China University of the Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China Xi’an Jiaotong University School of Software Engineering Shaanxi Xi’an710049 China Dalian Univer sity of Technology School of Mechanical Engineering Dalian116024 China Auckland University of Technology Knowledge Engineering and Discovery Research Institute Auckland1061 New Zealand

Conventional imaging devices often struggle to produce high-dynamic-range (HDR) images that accurately represent natural scenes. To overcome this limitation, multi-exposure image fusion (MEF) techniques have been introduced as a viable solution. Existing MEF approaches aim to enhance performance by optimizing or searching architectures. However, they face challenges in precise feature extraction and scene reconstruction, leading to distortion in the fused images. Additionally, most methods do not adequately address luminance variations across different image regions, which may result in the loss of essential details. To address these challenges, we present a novel luminance-aware MEF framework that integrates text-correlation priors (LarTap). By embedding textual information into fusion process, the proposed framework enhances content extraction and comprehension. Specifically, it consist of two key components: the text-image correlation network (N1) and the multi-exposure fusion network (N2). First, N1 performs correlation training to achieve a holistic alignment between text and image pairs. Its iterative vision encoders (VEs) generate text-correlated prior knowledge to facilitate the fusion process in N2. Second, N2 leverages these priors for scene reconstruction and dynamically adjusts luminance based on comparative perception. Extensive experiments on multiple datasets demonstrate that LarTap outperforms state-of-the-art methods. © 1991-2012 IEEE.

关键词： Image correlation

来源：评论

学校读者我要写书评

暂无评论

Learning a Coordinated Network for Detail-Refinement Multiexposure Image Fusion

引用

IEEE Transactions on Circuits and Systems for Video technology 2023年第2期33卷 713-727页

作者： Li, Jiawei Liu, Jinyuan Zhou, Shihua Zhang, Qiang Kasabov, Nikola K. Ministry of Education School of Software Engineering Dalian University Key Laboratory of Advanced Design and Intelligent Computing Dalian116622 China Dalian University of Technology School of Software Technology Dalian116024 China Auckland University of Technology Knowledge Engineering and Discovery Research Institute Auckland1010 New Zealand Ulster University Intelligent Systems Research Center LondonderryBT52 1SA United Kingdom

Nowadays, deep learning has made rapid progress in the field of multi-exposure image fusion. However, it is still challenging to extract available features while retaining texture details and color. To address this difficult issue, in this paper, we propose a coordinated learning network for detail-refinement in an end-to-end manner. Firstly, we obtain shallow feature maps from extreme over/under-exposed source images by a collaborative extraction module. Secondly, smooth attention weight maps are generated under the guidance of a self-attention module, which can draw a global connection to correlate patches in different locations. With the cooperation of the two aforementioned used modules, our proposed network can obtain a coarse fused image. Moreover, by assisting with an edge revision module, edge details of fused results are refined and noise is suppressed effectively. We conduct subjective qualitative and objective quantitative comparisons between the proposed method and twelve state-of-the-art methods on two available public datasets, respectively. The results show that our fused images significantly outperform others in visual effects and evaluation metrics. In addition, we also perform ablation experiments to verify the function and effectiveness of each module in our proposed method. The source code can be achieved at https://***/lok-18/LCNDR. © 1991-2012 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

A new Approach on Task Offloading Scheduling for Application of Mobile Edge computing

A New Approach on Task Offloading Scheduling for Application...

引用

IEEE Conference on Wireless Communications and Networking

作者： Yuya Cui Degan Zhang Ting Zhang Peng Yang Haoli Zhu Tianjin Key Lab of Intelligent Computing and Novel Software Technology Tianjin University of Technology Tianjin Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin China

In mobile edge computing(MEC), application partitioning can split the executions into local and edge server parts. Optimal partitioning will allow mobile devices to obtain the highest benefit from Mobile Edge computing (MEC). In this paper, a new approach on task offloading scheduling for application of mobile edge computing is proposed. We divide the computing task into several subtasks. Then, we analyze the overhead of the system, and propose a fine-grained strategy for task scheduling and offloading in a multi-user MEC system. For reducing the energy consumption and delay, the computation offloading is considered as a constrained multi-objective optimization problem (CMOP), which can be solved by an improved NSGA-II algorithm. The experimental results show that the proposed algorithm can find a large number of optimal solutions to adjust the corresponding offloading decision according to the real-world situation.

关键词： Energy consumption Processor scheduling Parallel processing Scheduling Mobile handsets Delays Servers

来源：评论

学校读者我要写书评

暂无评论

An adaptive POI recommendation algorithm by integrating user's temporal and spatial features in LBSNs 2020

An adaptive POI recommendation algorithm by integrating user...

引用

3rd International Conference on Data Science and Information technology, DSIT 2020

作者： Li, Miao Zheng, Wenguang Xiao, Yingyuan Jiao, Xu Tianjin Key Laboratory of Intelligence Computing and New Software Technology Tianjin University of Technology Tianjin China Department of Liberal Education Tianjin Foreign Studies University Tianjin China

ISBN: (纸本)9781450376044

With the rapid development of Internet technology and global positioning technology, location-based social networks (LBSNs) have emerged. Massive check-in data generated by LBSNs can be employed to explore users' behavior preferences, and enable a wide range of location-based social services. The most straightforward service is Point of Interest (POI) recommendation, which help users to discover their desired places. In order to achieve effective and precise POI recommendation, complicated high-dimensional data need to be handled, i.e., user-geographical position-visiting time-category of the visiting place. Besides, such data usually suffer from a data sparsity problem. To this end, this paper proposes a novel POI recommendation model that incorporates spatial and temporal preferences of the users. We propose a tensor factorization-based approach and a Voronoi diagram-based approach to model the impact of temporal and spatial features on users' preference, respectively. Then, a fusion framework is proposed to calculate similarities between different uses by combining both temporal and spatial preferences of the users. Finally, an adaptive collaborative filtering approach is applied to generate recommendation list. The experiments results on the Foursquare and the Gowalla datasets shows that our model has higher recommendation performance than other comparison models. © 2020 ACM.

关键词： Collaborative filtering

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：