检索结果-内蒙古大学图书馆

An efficient sentiment analysis technique based on fine-tuned EdBERT for virtual learning environments

Multimedia Tools and Applications 2024年 1-15页

作者： Srivastav, Gaurav Kant, Shri Srivastava, Durgesh Sharma, Neha Hu, Yu-Chen Department of Computer Science and Engineering Sharda University Gautam Budh Nagar India Department of Computer Science and Engineering Chitkara University Institute of Engineering & ampTechnology Chitkara University Punjab Rajpura India Department of Computer Science Tunghai University No. 1727 Sec. 4 Boulevard Xitun District Taichung City407224 Taiwan

With artificial intelligence propelling rapid technological advances, many tools and frameworks have surfaced to assist virtual learning settings. They all make unique claims about how best to facilitate distance education, particularly in light of the pandemic. This paper presents a new model called "EdBERT," which is created explicitly for sentiment analysis of evaluations written by virtual learners with unmatched categorization accuracy. With Google BERT, EdBERT improves sentiment analysis specifically for educational feedback datasets. Using a comparison analysis and the "fine-tuned Google BERT," taught at several levels to understand language, context, and emotions, the methodology accurately classifies learners' feedback. The discussion includes thorough testing and analysis of the accuracy of the model, as well as information on its effectiveness and operation. The model and its operation are described in the discussion together with reliable evidence from analyses and accuracy tests. EdBERT is a cutting-edge model in AIEd sentiment analysis, boasting the best evaluation matrix to date with accuracy rates of 87.89%, F1-score of 88%, precision of 89%, and recall of 88%. These evaluation matrix values outperform all other current models covered in the article. In an effort to increase the productivity of students, teachers, and the learning environment, academic academics and scientists are delving into the relatively young field of AIEd. Trustworthy sentiment analysis may be produced using three fundamental sentiment classes: deep learning and natural language processing models. Plutchik's wheel of emotion, which will aid in more accurately recording feelings using artificial intelligence and deep learning, can be used to further this study. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A novel brain tumor segmentation and classification model using deep neural network over MRI-flair images

引用

Multimedia Tools and Applications 2024年 1-32页

作者： Rajendirane, Rajmohan Ananth Kumar, T. Sandhya, S.G. Hu, Yu-Chen Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur Campus Tamil Nadu Kattankulathur India Department of Computer Science and Engineering IFET College of Engineering Tamil Nadu Villupuram India Department of Computer Science and Engineering Annamalai University Chidambaram India Department of Computer Science Tunghai University No. 1727 Sec. 4 Boulevard Xitun District Taichung City407224 Taiwan

Brain tumors pose a significant health concern globally, with their detection and diagnosis being crucial for timely intervention and treatment planning. These abnormal growths can develop within the brain or originate from other parts of the body, spreading to the brain. They can be benign or malignant, and their impact on cognitive and physical function can vary widely depending on their location, size, and type. Detecting brain tumors involves a combination of imaging techniques and clinical assessment. Magnetic Resonance Imaging (MRI) is one of the primary imaging modalities used for this purpose due to its ability to provide detailed images of the brain's anatomy and pathology. Advanced image processing techniques and machine learning algorithms play an increasingly important role in enhancing the accuracy and efficiency of brain tumor detection. This study presents a comprehensive approach for enhancing brain tumor detection in MRI images using a combination of advanced techniques. Firstly, an improved K-means clustering algorithm is introduced to segment tumor regions effectively. Following this, Median Filtering is applied to refine image quality and reduce noise interference. Subsequently, a deep neural network architecture is employed for precise tumor classification utilizing the BRATS dataset. The proposed methodology aims to improve the accuracy and efficiency of brain tumor detection, offering potential advancements in medical image analysis and diagnosis. Experimental results demonstrate promising outcomes, indicating the effectiveness of the proposed approach in accurately identifying tumor regions in MRI scans. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

A parametric rate-distortion model for video transcoding

引用

Multimedia Tools and Applications 2025年 1-35页

作者： Jamali, Maedeh Karimi, Nader Samavi, Shadrokh Shirani, Shahram Department of Electrical and Computer Engineering McMaster University HamiltonL8S 4L8 Canada Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan84156-83111 Iran Computer Science Department Seattle University Seattle98122 United States

Over the past two decades, the rise in video streaming has been driven by internet accessibility and the demand for high-quality video. To meet this demand across varying network speeds and devices, transcoding is essential. This paper introduces a parametric rate-distortion (R-D) transcoding model that predicts transcoding distortion at different bitrates without the need for re-encoding. Experimental results validate the model’s effectiveness in predicting rate-distortion behavior for diverse video content. Using our model, visual quality (measured by PSNR and VMAF) of transcoded video can be improved through trans-sizing. Moreover, our model can identify visually lossless bitrate ranges. This allows service providers to adjust target bitrates with minimal quality loss. Experimental results validate the model’s effectiveness in predicting rate-distortion behavior for diverse video content. By using the VMAF measure, our model achieves a quality improvement of up to 2.55 and bitrate savings of up to 79.10%. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

Two-Dimensional Golay Complementary Array Sets with Arbitrary Lengths for Omnidirectional MIMO Transmission

引用

IEEE Transactions on Communications 2024年第2期72卷 1135-1145页

作者： Zhao, You-Qi Pai, Cheng-Yu Huang, Zhen-Ming Liu, Zilong Chen, Chao-Yu National Cheng Kung University Department of Engineering Science Tainan701 Taiwan National Cheng Kung University Department of Engineering Science and the Institute of Computer and Communication Engineering Tainan701 Taiwan University of Essex School of Computer Science and Electronic Engineering ColchesterCO4 3SQ United Kingdom National Cheng Kung University Department of Electrical Engineering and the Institute of Computer and Communication Engineering Tainan701 Taiwan

This paper presents a coding approach for achieving omnidirectional transmission of certain common signals in massive multi-input multi-output (MIMO) networks such that the received power at any direction in a cell remains constant for any given distance. Specifically, two-dimensional (2D) Golay complementary array set (GCAS) can be used to design the massive MIMO precoding matrix so as to achieve omnidirectional transmission due to its complementary autocorrelation property. In this paper, novel constructions of new 2D GCASs with arbitrary array lengths are proposed. Our key idea is to carefully truncate the columns of certain larger arrays generated by 2D generalized Boolean functions. Finally, the power radiation patterns and numerical results are provided to verify the omnidirectional property of the GCAS-based precoding. The error performances of the proposed precoding scheme are presented to validate its superiority over the existing alternatives. © 1972-2012 IEEE.

关键词： Peak to average power ratio

来源：评论

学校读者我要写书评

暂无评论

An Automated Few-Shot Learning for Time-Series Forecasting in Smart Grid under Data Scarcity

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2482-2492页

作者： Xu, Jiangjiao Li, Ke Li, Dongdong Shanghai University of Electric Power Department of Electrical Engineering Shanghai20090 China University of Exeter Department of Computer Science ExeterEX4 4QF United Kingdom

Microgrid can improve greenhouse gas emissions and reduce operational costs. To forecast both energy generation and load demand, time-series prediction has been a key tool in real-time control and optimization. Developing an adequate predictive model is difficult when there is a lack of historical data. Moreover, hyperparameters have a tangible impact on the performance of machine learning models. Bearing these considerations in mind, this article develops a BiLO-Auto-TSF/ML framework that automates the optimal design of a few-shot learning pipeline from a bilevel programming perspective. Specifically, a lower level metalearner helps mitigate the small data challenge, whereas an upper level optimization optimizes both hyperparameters for lower and upper level learners. Note that the proposed framework is designed to accommodate a wide range of machine learning methods, allowing for easy integration through a plug-in mechanism. Comprehensive experiments demonstrate the effectiveness of our proposed BiLO-Auto-TSF/ML to search for a high-performance few-shot learning pipeline for various energy sources. © 2020 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Self-supervised learning of pseudo classes for generalized zero-shot fine-grained recognition

引用

Multimedia Tools and Applications 2025年第10期84卷 7915-7930页

作者： Chen, Yan-He Yeh, Mei-Chen Department of Computer Science and Information Engineering National Taiwan Normal University No. 88 Sec. 4 Tingzhou Rd. Taipei Taiwan

Generalized zero-shot learning (GZSL) attempts to recognize visual instances from both seen and unseen classes by transferring knowledge from seen classes to unseen classes through semantic information (e.g., attributes). Generative methods are commonly employed to alleviate the issue of extreme data imbalance in which visual samples from unseen classes are not available during training, by synthesizing training samples for unseen classes from class prototypes. However, in the context of GZSL applied to fine-grained recognition, a notable complication arises. Similar class prototypes among different categories lead to ambiguity when generating synthetic data for classification. In response, we present a novel solution: a self-supervised pseudo-labeling (SSPL) module designed to enhance the generation of discerning synthetic data. This enhancement is achieved through an unsupervised grouping of fake and real samples using pseudo classes. By doing so, the SSPL module addresses the challenge of generating discriminative fake data, ultimately improving the overall quality of synthesized samples for classification. Our experimental results, conducted on three widely recognized GZSL datasets, demonstrate the effectiveness of the proposed method. Notably, the SSPL module not only produces well-distributed synthetic samples, but also enhances the discriminative and generalizable visual features derived from both real and synthetic samples within the GZSL framework. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

SFI-Swin: symmetric face inpainting with swin transformer by distinctly learning face components distributions

引用

Multimedia Tools and Applications 2024年 1-15页

作者： Givkashi, MohammadHossein Naderi, MohammadReza Karimi, Nader Shirani, Shahram Samavi, Shadrokh Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan84156-83111 Iran Department of Electrical and Computer Engineering McMaster University HamiltonL8S 4L8 Canada Computer Science Department Seattle University Seattle98122 United States

Image inpainting consists of filling holes or missing parts of an image. Inpainting face images with symmetric characteristics is more challenging than inpainting a natural scene. None of the powerful existing models can fill out the missing parts of an image while considering the symmetry and homogeneity of the picture. Moreover, the metrics that assess a repaired face image quality cannot measure the preservation of symmetry between the rebuilt and existing parts of a face. In this paper, we intend to solve the symmetry problem in the face inpainting task by using multiple discriminators that check each face organ’s reality separately and a transformer-based network. We also propose "symmetry concentration score" as a new metric for measuring the symmetry of a repaired face image. The quantitative and qualitative results show the superiority of our proposed method compared to some of the recently proposed algorithms in terms of the reality, symmetry, and homogeneity of the inpainted parts. The code for the proposed method is available at https://***/mohammadrezanaderi4/SFI-Swin. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Modeling the effects of salt concentration on aqueous and organic electrolytes

引用

npj Computational Materials 2023年第1期9卷 546-552页

作者： Stephanie C.C.van der Lubbe Pieremanuele Canepa Department of Materials Science and Engineering National University of Singapore9 Engineering Drive 1117575 SingaporeSingapore Department of Chemical and Biomolecular Engineering National University of Singapore4 Engineering Drive 4117585 SingaporeSingapore Department of Electrical and Computer Engineering and Texas Center for Superconductivity University of HoustonHoustonTX 77204USA

Understanding the thermodynamic properties of electrolyte solutions is of vital importance for a myriad of physiological and technological *** mean activity coefficientγ±is associated with the deviation of an electrolyte solution from its ideal behavior and may be obtained by combining the Debye-Hückel(DH)and Born(B)***,the DH and B equations depend on the concentration and temperature-dependent static permittivity of the solutionεr(c,T)and the size of the solvated ions ri,whose experimental data is often not ***,we use a combination of molecular dynamics and density functional theory to predictεr(c,T)and ri,which enables us to apply the DH and B equations to any technologically relevant aqueous and nonaqueous electrolyte at any concentration and temperature of interest.

关键词： equations electrolyte apply

来源：评论

学校读者我要写书评

暂无评论

A combinatorial algorithm for finding straight skeleton of a digital object

引用

Multimedia Tools and Applications 2025年 1-21页

作者： Maity, Anukul Dutt, Mousumi Biswas, Arindam Department of Computer Science and Engineering Narula Institute of Technology 81 Nilgunj Road Agarpara West Bengal Kolkata700109 India Department of Computer Science and Engineering St. Thomas’ College of Engineering and Technology 4 Diamond Harbour Road Kidderpore West Bengal Kolkata700023 India Department of Information Technology Indian Institute of Engineering Science and Technology Botanical Garden Road Shibpur West Bengal Howrah711103 India

The paper presents a combinatorial algorithm to find the straight skeleton of the inner isothetic cover of a digital object imposed on a uniform background grid. The isothetic polygon (orthogonal polygon) tightly inscribes the given digital object. The algorithm stated here finds the straight skeleton of any isothetic polygon (simple or non-simple) in O(nglogng) time in a single traversal by applying combinatorial rules, where n is the number of pixels on the boundary of the digital object and g is the grid size on which the digital object is imposed. To find the straight skeleton of non-simple orthogonal polygon, the polygon is divided into sub-parts which are a set of simple orthogonal polygons. The straight skeleton is generated for each of the sub-parts and the corresponding results are merged. The orthogonal polygon containing holes is cut at each holes and the polygon becomes hole-free. The algorithm to obtain the straight skeleton is applied on it. The disconnected hole parts are rejoined and the result is merged. The straight skeleton is useful shape descriptor of digital object. This algorithm stated here has applications in shape analysis. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

Matching 5G Connected Vehicles to Sensed Vehicles for Safe Cooperative Autonomous Driving

引用

IEEE Network 2024年第3期38卷 227-235页

作者： Tang, Zuoyin He, Jianhua Yang, Kun Chen, Hsiao-Hwa Aston University School of Computer Science and Digital Technologies BirminghamB4 7ET United Kingdom Essex University School of Computer Science and Electronic Engineering ColchesterCO4 3SQ United Kingdom National Cheng Kung University Department of Engineering Science Tainan70101 Taiwan

5G connected autonomous vehicles (CAVs) help enhance perception of driving environment and cooperation among vehicles by sharing sensing and driving information, which is a promising technology to avoid accidents and improve road-use efficiency. A key issue for cooperation among CAVs is matching communicating vehicles to those captured in sensors such as cameras, LiDAR, etc.. Incorrect vehicle matching may cause serious accidents. While centimeter level positioning is now available for autonomous vehicles, matching connected vehicles to sensed vehicles (MCSV) is still challenging and has rarely been studied. In this paper, we are motivated to investigate the MCSV problem for 5G CAVs, propose and assess solutions for the problem to bridge the research gap. We formulate the MCSV problem and propose two MCSV approaches to support cooperative driving. The first approach is based on vehicle registration number (VRN), which is unique to identify a vehicle and can be shared among CAVs for MCSV. VRN is hashed before sharing to protect privacy, and will be compared to the shared one for vehicle matching. The second MCSV approach is based on visual features of vehicle's external views, which are shared with other CAVs and compared to those obtained from visual sensors to match the vehicles of interest. A new MCSV dataset is developed to assess the effectiveness of the proposed approaches. Experiment results show that both approaches are feasible and useful, and they achieve a very low false positive rate, which is critical for cooperative driving safety. © 1986-2012 IEEE.

关键词： Autonomous vehicles

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：