检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Dai, RuiTing Luo, Jiayi Luo, Xucheng Mo, Lisi Ma, Wanlun Zhou, Fan School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu610054 China Swinburne University of Technology Australia

Inferring geographic locations via social posts is essential for many practical location-based applications such as product marketing, point-of-interest recommendation, and infector tracking for COVID-19. Unlike image-based location retrieval or social-post text embedding-based location inference, the combined effect of multi-modal information (i.e., post images, text, and hashtags) for social post positioning receives less attention. In this work, we collect real datasets of social posts with images, texts, and hashtags from Instagram and propose a novel Multi-modal Representation Learning Framework (MRLF) capable of fusing different modalities of social posts for location inference. MRLF integrates a multi-head attention mechanism to enhance location-salient information extraction while significantly improving location inference compared with single domain-based methods. To overcome the noisy user-generated textual content, we introduce a novel attention-based character-aware module that considers the relative dependencies between characters of social post texts and hashtags for flexible multimodel information fusion. The experimental results show that MRLF can make accurate location predictions and open a new door to understanding the multi-modal data of social posts for online inference tasks. © 2023, CC BY-NC-ND.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Joint QoS Prediction for Web Services based on Deep Fusion of Features

引用

IEEE Transactions on Network and Service Management 2023年 1-1页

作者： Ding, Linghang Liu, Jianxun Kang, Guosheng Xiao, Yong Cao, Buqing Hunan Provincial Key Lab. for Services Computing and Novel Software Technology and School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China

In order to solve the problem of insufficient accuracy of Web service QoS prediction, a joint QoS prediction method for Web services based on the deep fusion of features was proposed by considering the hidden environmental preference information in QoS and the common characteristics of multi-class QoS. QoS data was modeled as user-service bipartite graph at first, then, multi-component graph convolution neural network was used for feature extraction and mapping, and weighted fusion method was used for the same dimensional mapping of multi-class of QoS features. Subsequently, the attention factor decomposition machine was used to extract the first-order features, second-order interactive features and high-order interactive features of the mapped feature vector. Finally, the results of each part were combined to achieve the joint QoS prediction. The experimental results show that the proposed method is superior to the existing QoS prediction methods in terms of root mean square error (RMSE) and average absolute error (MAE). IEEE

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Temporal-Assisted Dynamic Beampattern Optimization in Integrated Sensing and Communication Systems

arXiv

引用

arXiv 2024年

作者： Zhou, Shengcai Xiang, Luping Yang, Kun University of Electronic Science and Technology of China Quzhou324003 China School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu611731 China State Key Laboratory of Novel Software Technology Nanjing University Nanjing210008 China School of Intelligent Software and Engineering Nanjing University Suzhou Campus Suzhou215163 China

In this paper, an integrated sensing and communication (ISAC) system is investigated. Initially, we introduce a design criterion wherein sensing data acquired from the preceding time slot is employed for instantaneous optimal beamforming in the succeeding time slot, aiming to enhance the communication rate. Subsequently, the development of optimal beamforming is addressed, and a high-caliber suboptimal resolution is derived utilizing successive convex approximation (SCA) techniques combined with the iterative rank minimization (IRM) methodology. Our evaluations, grounded on numerical analyses, reveal that the communication rate of the introduced beamforming strategy surpasses that of conventional omnidirectional sensing and pilot based approaches. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Remote Consultation System for Oral Prevention in Children: A Case Study in Mongolia 15

An Intelligent Remote Consultation System for Oral Preventio...

引用

15th International Conference on software, Knowledge, Information Management and Applications, SKIMA 2023

作者： Ren, Lijuan Bendjeddou, Randa Cheima Kahn, Giacomo Seklouli, Aicha Sekhari Myagmar, Bat-Erdene Garidkhuu, Ariuntuul School of Software Engineering Chengdu University of Information Technology Chengdu China Lyon France School of Dentistry Mongolian National University of Medical Sciences Department of Dental Technology and Dental Hygiene Ulaanbaatar Mongolia School of Dentistry Mongolian National University of Medical Sciences Department of Prosthodontics Ulaanbaatar Mongolia

ISBN: (纸本)9798350316551

Children's dental caries is a common oral health issue, causing pain and discomfort. Therefore, oral health plays a crucial role in children's growth and development. However, regular dental check-ups and consultations are burdensome and expensive for parents, especially for Mongolian children with uneven access to healthcare. To address this issue, we developed an intelligent remote consultation system for children's dental prevention, which utilizes advanced technologies like risk assessment and image recognition for automated oral risk analysis and cavity localization. Subsequently, we conducted experiments and analyses based on data collected from the initial phase in Mongolia, showing the potential of the system to improve children's oral health. However, the system's precision is restricted by the small amount of data. Expanding data collection will be the focus of future efforts to improve system performance and further improve this creative solution. © 2023 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Model for software Defect Prediction 2

An Ensemble Model for Software Defect Prediction

引用

2nd International Conference on Digital Futures and Transformative Technologies, ICoDT2 2022

作者： Ali, Amad Rizwan Ur Rehman, Attique Nawaz, Ali Ali, Tahir Muhammad Abbas, Muhammad UserMaven Inc United States University of Sialkot Department of Software Engineering Sialkot Pakistan College of Electrical and Mechanical Engineering National University of Science and Technology Rawapindi Pakistan Gulf University for Science and Technology Department of Computer Science College of Science and Arts Kuwait

ISBN: (纸本)9781665498197

software testing is one of the important ways to ensure the quality of software. It is found that testing cost more than 50% of overall project cost. Effective and efficient software testing utilizes the minimum resources of software. Therefore, it is important to construct the procedure which is not only able to perform the efficient testing but also minimizes the utilization of project resources. The goal of software testing is to find maximum defects in the software system. As world is continuously moving toward data driven approach for making important decision. Therefore, in this research paper we performed the machine learning analysis on the publicly available datasets and tried to achieve the maximum accuracy. The major focus of the paper is to apply different machine learning techniques on the datasets and find out which technique produce efficient result. Particularly, we proposed an ensemble learning models and perform comparative analysis among KNN, Decision tree, SVM and Naïve Bayes on different datasets and it is demonstrated that performance of Ensemble method is more than other methods in term of accuracy, precision, recall and F1-score. The classification accuracy of ensemble model trained on CM1 is 98.56%, classification accuracy of ensemble model trained on KM2 is 98.18% similarly, the classification accuracy of ensemble learning model trained on PC1 is 99.27%. This reveals that ensemble learning is more efficient method for making the defect prediction as compared other techniques. © 2022 IEEE.

关键词： software testing

来源：评论

学校读者我要写书评

暂无评论

A Fine-Grained Emotion Prediction Method Based on Large Language Models

A Fine-Grained Emotion Prediction Method Based on Large Lang...

引用

IEEE International Conference on software Quality, Reliability and Security Companion (QRS-C)

作者： Fang Li Yubin Qu Chao Feng Xianzhen Dou Long Li Jiangsu College of Engineering and Technology Nantong Jiangsu China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin Guangxi China Army Engineering University of PLA Nanjing Jiangsu China

ISBN: (数字)9798350365658

ISBN: (纸本)9798350365665

Every day, much multimodal data emerges on social media. Previous studies have focused on the problem of fine-grained sentiment analysis in multimodal data. However, many multimodal data must be annotated for specific emotions to train fine-grained emotion prediction models. To efficiently train fine-grained emotion risk prediction models for multimodal data, we propose a few-shot learning-based method for multimodal fine-grained sentiment analysis. This model captures sentiment polarity in text using a pre-trained large language model, annotates a small amount of data, and generates a training dataset. Then, utilizing an intermediate layer fusion strategy, it combines representation vectors of text, images, videos, and audio to ultimately create a fine-grained emotion prediction model based on multimodal data. Exper-imental work on a real multimodal dataset, compared with random fine-grained sentiment analysis methods, shows that our proposed method has significant advantages in handling multimodal fine-grained sentiment analysis tasks and practical value.

关键词： Training Sentiment analysis Social networking (online) Large language models software quality Predictive models Data models Vectors software reliability Videos

来源：评论

学校读者我要写书评

暂无评论

Veinseg-Net: A Novel Finger Vein Segmentation Algorithm Based on Deep Learning 23

Veinseg-Net: A Novel Finger Vein Segmentation Algorithm Base...

引用

3rd International Conference on Bioinformatics and Intelligent Computing, BIC 2023

作者： Xu, Hong Wang, Peng Sun, Yewei Ye, Caizeng School of Software Shandong University Jinan250101 China Jinan Engineering Polytechnic Jinan250200 China Hazen and Sawyer 4035 Ridge Top Rd Suite 500 FairfaxVA22030 United States Shandong Institute of Commerce and Technology Jinan250103 China National Agricultural Products Modern Logistics Engineering Technology Research Center Jinan250103 China

ISBN: (纸本)9798400700200

On the basis of the original U-Net and ResNet finger vein segmentation methods, this paper proposes a new finger vein segmentation method based on the combination of the above two methods. This method completes feature extraction by using depth residual network instead of U-Net. Using extended convolution instead of traditional convolution solves the risk of loss of finger vein information extracted by pooling layer, so that the method can extract finger vein veins more accurately without pooling. The algorithm uses the Mish constructor to replace the ReLU constructor to strengthen the anti-compression ability of the model and make vein image more continuous. From the comparison of experimental results, it is not difficult to see that the segmentation accuracy of the newly proposed Veinseg-Net network on multiple finger vein databases are better than those of other depth learning segmentation methods. The good segmentation accuracy of finger vein image can help the finger vein recognition process in the subsequent environment intelligence. © 2023 ACM.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Towards Automated Support for the Co-Evolution of Meta-Models and Grammars

arXiv

引用

arXiv 2023年

作者： Zhang, Weixing Department of Computer Science & Engineering Division of Interaction Design & Software Engineering Chalmers University of Technology University of Gothenburg Gothenburg Sweden

Blended modeling is an emerging paradigm involving seamless interaction between multiple notations for the same underlying modeling language. We focus on a model-driven engineering (MDE) approach based on meta-models to develop textual languages to improve the blended modeling capabilities of modeling tools. In this thesis, we propose an approach that can support the co-evolution of meta-models and grammars as language engineers develop textual languages in a meta-model-based MDE setting. Firstly, we comprehensively report on the challenges and limitations of modeling tools that support blended modeling, as well as opportunities to improve them. Second, we demonstrate how language engineers can extend Xtext’s generator capabilities according to their needs. Third, we propose a semi-automatic method to transform a language with a generated grammar into a Python-style language. Finally, we provide a solution (i.e., GrammarOptimizer) that can support rapid prototyping of languages in different styles and the co-evolution of meta-models and grammars of evolving languages. © 2023, CC BY-NC-ND.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Numerical Simulation of Full-Scale Square Concrete Filled Steel Tubular (CFST) Columns Under Seismic Loading

Numerical Simulation of Full-Scale Square Concrete Filled St...

引用

International Conference on Modern Mechanics and Applications, ICOMMA 2020

作者： Phan, Hao D. Lin, Ker-Chun Phan, Hieu T. Faculty of Civil Engineering The University of Danang – University of Science and Technology Danang Viet Nam Department of Civil and Construction Engineering National Taiwan University of Science and Technology Taipei Taiwan National Center for Research on Earthquake Engineering Taipei Taiwan Department of Computer Science and Software Engineering Miami University OxfordOH United States

ISBN: (纸本)9789811632389

This paper presents numerical investigations on the seismic behavior of full-scale square concrete filled steel tubular (CFST) columns. The main objective is to understand the seismic behavior and evaluate the seismic performance of these composite columns under high levels of axial compression. Finite element analysis (FEA) models in ABAQUS software were used to simulate a series of columns subjected to axial compression and cyclic lateral loading. The CFST columns were modeled using eight-node reduced integration brick elements (C3D8R) for the infilled concrete with confinement effect, and four-node reduced integration shell elements (S4R) for the steel tube with consideration of steel-concrete interaction and steel wall’s buckling. The feasibility of the FEA models has been validated by published experimental results. The validated FEA model was further extended to conduct parametric studies with various parameters including width-to-thickness ratio (B/t), concrete strength, and axial compression level. The numerical analysis results reveal that with the same B/t and constituent materials, the higher the axial compression was, the lower the shear strength and the deformation capacity were. Also, the higher axial compression led to earlier local buckling of the steel tube, especially, in the case of the thinner steel wall (B/t of 41.7). The thicker steel wall (B/t of 20.8) resulted in higher strength and larger deformation capacity of the column. Increasing concrete material strength significantly improved the column’s shear strength for both thinner and thicker steel walls, but it led to significant development in deformation for the column having thicker steel walls. This study also reveals that only the square CFST columns with B/t of 20.8 using medium material strengths satisfy the seismic performance demand for the building columns in high seismic zones (ultimate interstory drift ratio (IDRu) not less than 3% radian) under high axial compression (up to 55% of

关键词： Concrete confinement effect Finite element analysis (FEA) model High axial compression Local buckling Seismic performance Square CFST columns Width-to-thickness ratio (B/t)

来源：评论

学校读者我要写书评

暂无评论

Intelligent Prediction Approach for Diabetic Retinopathy Using Deep Learning Based Convolutional Neural Networks Algorithm by Means of Retina Photographs

引用

Computers, Materials & Continua 2021年第2期66卷 1613-1629页

作者： G.Arun Sampaul Thomas Y.Harold Robinson E.Golden Julie Vimal Shanmuganathan Seungmin Rho Yunyoung Nam CSE Department J.B.Institute of Engineering and TechnologyHyderabad500075India School of Information Technology and Engineering Vellore Institute of TechnologyVellore632014India Department of Computer Science and Engineering Anna University Regional CampusTirunelveli627007India Department of Information Technology National Engineering CollegeKovilpatti628503India Department of Software Sejong University209 Neungdong-roGwangjin-guSeoul05006Korea Department of Computer Science and Engineering Soonchunhyang UniversityAsan31538Korea

Retinopathy is a human eye disease that causes changes in retinal blood vessels that leads to bleed,leak fluid and vision *** of retinopathy are blurred vision,changes in color perception,red spots,and eye pain and it cannot be detected with a naked *** this paper,a new methodology based on Convolutional Neural Networks(CNN)is developed and proposed to intelligent retinopathy prediction and give a decision about the presence of retinopathy with automatic diabetic retinopathy screening with accurate *** CNN model is trained by different images of eyes that have retinopathy and those which do not have *** fully connected layers perform the classification process of the images from the dataset with the pooling layers minimize the coherence among the adjacent *** feature loss factor increases the label value to identify the patterns with the kernel-based *** performance of the proposed model is compared with the related methods of DREAM,KNN,GD-CNN and *** results show that the proposed CNN performs better.

关键词： Convolutional neural networks dental diagnosis image recognition diabetic retinopathy detection

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：