检索结果-内蒙古大学图书馆

Collaborative Knowledge Infusion for Low-Resource Stance Detection

Big Data Mining and Analytics 2024年第3期7卷 682-698页

作者： Ming Yan Tianyi Zhou Joey W.Tsang Ivor Centre for Frontier AI Research and Institute of High-Performance ComputingAgency for Science Technology and ResearchSingapore 138632Singapore

Stance detection is the view towards a specific target by a given context(***,commercial reviews).Target-related knowledge is often needed to assist stance detection models in understanding the target well and making detection ***,prevailing works for knowledge-infused stance detection predominantly incorporate target knowledge from a singular source that lacks knowledge verification in limited domain *** low-resource training data further increase the challenge for the data-driven large models in this *** address those challenges,we propose a collaborative knowledge infusion approach for low-resource stance detection tasks,employing a combination of aligned knowledge enhancement and efficient parameter learning ***,our stance detection approach leverages target background knowledge collaboratively from different knowledge sources with the help of knowledge ***,we also introduce the parameter-efficient collaborative adaptor with a staged optimization algorithm,which collaboratively addresses the challenges associated with low-resource stance detection tasks from both network structure and learning *** assess the effectiveness of our method,we conduct extensive experiments on three public stance detection datasets,including low-resource and cross-target *** results demonstrate significant performance improvements compared to the existing stance detection approaches.

关键词： parameter-efficient learning low-resource stance detection knowledge infusion

来源：评论

学校读者我要写书评

暂无评论

Multi-view stereo algorithms based on deep learning: a survey

引用

Multimedia Tools and Applications 2025年第6期84卷 2877-2908页

作者： Huang, Hongbo Yan, Xiaoxu Zheng, Yaolin He, Jiayu Xu, Longfei Qin, Dechun Computer School Beijing Information Science & Technology University Beijing China Institute of Computing Intelligence Beijing Information Science & Technology University Beijing China Foreign Languages School Beijing Information Science & Technology University Beijing China

Multi-View Stereo (MVS) is a long-standing and fundamental task in computer vision, which aims to reconstruct the 3D geometry of a scene from a set of overlapping images. With known camera parameters, MVS matches pixels across images to compute dense correspondences and recover 3D points. Traditional MVS methods often encounter difficulties in addressing complex scenes due to limitations in robustness. However, recent advancements in deep-learning-based MVS have demonstrated remarkable performance gains, attributed to their enhanced feature extraction and cost volume processing capabilities. This comprehensive survey delves into deep-learning-based MVS algorithms, highlighting key challenges and avenues for future exploration. Our focus is on studies aimed at mitigating algorithmic memory requirements and elevating processing speeds. To better understand the developments in this field, we propose a new taxonomy. The deep-learning-based MVS algorithms are categorized into two categories: scene-oriented and view-oriented methods. Scene-oriented methods typically employ voxels or neural implicit representations as the representative form of the scene and infer the complete scene directly. View-oriented methods focus on estimating the depth map of a single view. Detailed classifications and reviews have been conducted for each category. Furthermore, we introduce several widely used datasets and metrics and empirical evaluation of representative algorithms across three popular datasets. This article concludes by discussing prevalent challenges in the MVS domain and promising research directions for the future. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Solar Power Output Prediction with AI: Leveraging Meta Learner Ensemble Stacked Regressor

Solar Power Output Prediction with AI: Leveraging Meta Learn...

引用

2024 International Conference on Integration of Emerging Technologies for the Digital World, ICIETDW 2024

作者： Shreeja, G. Kannan, Shruthi Sivakumar, Soubraylu SRM Institute of Science and Technology Computing Technologies School of Computing Chennai India

ISBN: (纸本)9798331541170

As the world shifts from fossil fuels to renewable energy, solar power has become essential in meeting global energy demands. The efficiency of solar energy depends on effectively capturing the environmental and physical factors that impact electricity production by solar panels. This study aims to leverage available data on power output and environmental conditions to build advanced machine learning models for predicting solar power. Models such as KNN, DNN, LGBM, RF, and a Meta Learner will be rigorously trained and fine-tuned using various data subsets and hyperparameter optimization. By employing the stacking regressor module from Scikit-learn, a Python machine-learning library, we successfully combined four distinct models, achieving an R-squared value of 0.68 in predicting solar power. This method not only improves the accuracy of solar power predictions but also enhances our ability to capture the complex data relationships critical for forecasting renewable energy. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Real-Time Multi-Feature Approximation Model-Based Efficient Brain Tumor Classification Using Deep Learning Convolution Neural Network Model

引用

Computer Systems science & Engineering 2023年第9期46卷 3883-3899页

作者： Amarendra Reddy Panyala M.Baskar Department of Computer Science and Engineering School of ComputingSRM Institute of Science and TechnologyKattankulathurChengalpattuChennai603203TamilnaduIndia Department of Information Technology MLR Institute of TechnologyHyderabad500043TelanganaIndia Department of Computing Technologies School of ComputingSRM Institute of Science and TechnologyKattankulathurChengalpattuChennai603203TamilnaduIndia

The deep learning models are identified as having a significant impact on various *** same can be adapted to the problem of brain tumor ***,several deep learning models are presented earlier,but they need better classification *** efficient Multi-Feature Approximation Based Convolution Neural Network(CNN)model(MFACNN)is proposed to handle this *** method reads the input 3D Magnetic Resonance Imaging(MRI)images and applies Gabor filters at multiple *** noise-removed image has been equalized for its quality by using histogram ***,the features like white mass,grey mass,texture,and shape are extracted from the *** features are trained with deep learning Convolution Neural Network(CNN).The network has been designed with a single convolution layer towards dimensionality *** texture features obtained from the brain image have been transformed into a multi-dimensional feature matrix,which has been transformed into a single-dimensional feature vector at the convolution *** neurons of the intermediate layer are designed to measure White Mass Texture Support(WMTS),GrayMass Texture Support(GMTS),WhiteMass Covariance Support(WMCS),GrayMass Covariance Support(GMCS),and Class Texture Adhesive Support(CTAS).In the test phase,the neurons at the intermediate layer compute the support as mentioned above values towards various classes of *** on that,the method adds a Multi-Variate Feature Similarity Measure(MVFSM).Based on the importance ofMVFSM,the process finds the class of brain image given and produces an efficient result.

关键词： CNN deep learning brain tumor classification MFA-CNN MVFSM 3D MRI texture Gabor

来源：评论

学校读者我要写书评

暂无评论

Knowledge Discovery of the Internet of Things (IoT) Using Large Language Model

引用

International Journal of Advanced Computer science and Applications 2025年第4期16卷 993-998页

作者： Alsulami, Bassma Saleh Department of Computer Science Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia

Internet of Things (IoT) technology quickly transformed traditional management and engagement techniques in several sectors. This work explores the trends and applications of the Internet of Things in industries, including agriculture, education, transportation, water management, air quality monitoring, underground mining, smart retail, smart home systems, and weather forecasting. The methodology involves a comprehensive review of the literature, followed by data extraction and analysis using BERT to identify key insights and patterns in IoT applications. The findings show that IoT significantly impacts the improvement of real-time monitoring, increasing efficiency, and encouraging innovative solutions in various sectors. Despite its transformative potential, cybersecurity threats, data privacy concerns, and the need for strong policy frameworks persist. The study emphasizes the necessity of multidisciplinary approaches to address these difficulties and optimize IoT implementation. Future research should focus on establishing secure IoT systems, maintaining data integrity, and encouraging collaboration between disciplines to realise the benefits of IoT technology. © (2025), (science and Information Organization). All rights reserved.

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

IoT-CDS:Internet of Things Cyberattack Detecting System Based on Deep Learning Models

引用

Computers, Materials & Continua 2024年第12期81卷 4265-4283页

作者： Monir Abdullah Department of Computer Science and Artificial Intelligence College of Computing and Information TechnologyUniversity of BishaBisha61922Saudi Arabia

The rapid growth and pervasive presence of the Internet of Things(IoT)have led to an unparalleled increase in IoT devices,thereby intensifying worries over IoT *** learning(DL)-based intrusion detection(ID)has emerged as a vital method for protecting IoT *** rectify the deficiencies of current detection methodologies,we proposed and developed an IoT cyberattacks detection system(IoT-CDS)based on DL models for detecting bot attacks in IoT *** DL models—long short-term memory(LSTM),gated recurrent units(GRUs),and convolutional neural network-LSTM(CNN-LSTM)were suggested to detect and classify IoT *** BoT-IoT dataset was used to examine the proposed IoT-CDS system,and the dataset includes six attacks with normal *** experiments conducted on the BoT-IoT network dataset reveal that the LSTM model attained an impressive accuracy rate of 99.99%.Compared with other internal and external methods using the same dataset,it is observed that the LSTM model achieved higher accuracy *** are more efficient than GRUs and CNN-LSTMs in real-time performance and resource efficiency for cyberattack *** method,without feature selection,demonstrates advantages in training time and detection ***,the proposed approach can be extended to improve the security of various IoT applications,representing a significant contribution to IoT security.

关键词： Cyberattacks intrusion detection system deep learning internet of things

来源：评论

学校读者我要写书评

暂无评论

Real Time Road Lane Detection and Vehicle Detection on YOLOv8 with Interactive Deployment 16

Real Time Road Lane Detection and Vehicle Detection on YOLOv...

引用

16th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2024

作者： Segu, Girish Sai Pavan Kumar Sivannarayana, Annam Devi Satya Naga Ramesh, S. School of Computing College of Engineering and Technology Srm Institute of Science and Technology Department of Computing Technologies India

ISBN: (纸本)9798331505264

Modern strides in autonomous vehicles and embedded advanced driver assistant part systems(ADAS) have forced the need of an efficient in addition to accurate system intended for clear road lane as in addition to vehicle detection. For road lane detection, this study introduces a new proposal through the combination of YOLOv8 (You Only Look Once), and YOLO for vehicle detection, creating a complete package for road understanding and navigation. To achieve accurate road lane detection, YOLOv8, which is the fastest and most accurate model to date, is used to ensure that it can keep track of these lanes in real-time with consistent accuracy whenever the camera is placed under various scenarios with insufficient lighting and occlusions as well. At the same time it uses YOLO for vehicle detection, which improves the recognition and interpretation of the presence and motion of vehicles in real time. The system uses Streamlit, which is an open-source app framework for Machine Learning and Data science projects to provide an intuitive user experience. Finally, we build an interface to provide results of lane and vehicle detection in realtime manner to allow ease of monitoring and evaluation on the overall system. The combination of YOLOv8 and YOLO with Streamlit provides a powerful, scalable, and deployable solution for practical computer vision applications. Combining well established object detection algorithms with a simplified deployment platform, the proposed system tackles some of the hardest and time consuming areas of autonomous driving. The goal is to make significant contributions to both the safety and efficiency of autonomous vehicles and pave the way for further inevitable advances in ADAS. © 2024 IEEE.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

Spontaneous Infection and Periodic Evolving of Domain in a Diffusive SIS Epidemic Model

引用

Acta Mathematicae Applicatae Sinica 2024年第1期40卷 164-191页

作者： Qiang Wen Guo-qiang Ren Bin Liu School of Mathematics and Statistics Huazhong University of Science and TechnologyWuhan430074China Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Science and TechnologyWuhan430074China

In this paper, we consider a susceptible-infective-susceptible(SIS) reaction-diffusion epidemic model with spontaneous infection and logistic source in a periodically evolving domain. Using the iterative technique,the uniform boundedness of solution is established. In addition, the spatial-temporal risk index R0(ρ) depending on the domain evolution rate ρ(t) as well as its analytical properties are discussed. The monotonicity of R0(ρ)with respect to the diffusion coefficients of the infected dI, the spontaneous infection rate η(ρ(t)y) and interval length L is investigated under appropriate conditions. Further, the existence and asymptotic behavior of periodic endemic equilibria are explored by upper and lower solution method. Finally, some numerical simulations are presented to illustrate our analytical results. Our results provide valuable information for disease control and prevention.

关键词： diffusive SIS model spontaneous infection periodically evolving domain periodic endemic equilibrium

来源：评论

学校读者我要写书评

暂无评论

Effortless learning: leveraging summarization and tabulation for automated note making

引用

Multimedia Tools and Applications 2024年 1-26页

作者： Arivarasi, A. Srinivasan, R. Rajeswari, D. Govindasamy, Alagiri School of Electronics Engineering Vellore Institute of Technology Tamil Nadu Chennai600127 India Department of Computing Technologies School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur603203 India Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur603203 India Future Connect Technologies Pvt. Ltd Tamil Nadu Kanchipuram600034 India

In this fast-paced Digital Age, Natural Language Processing (NLP) can prove beneficial in consuming quality information efficiently. With the ever-growing number of learning resources, it is becoming onerous for students to choose the best-suited learning resource. Furthermore, many students find it difficult to understand and retain highly factual information. To overcome these issues, this paper proposes a novel Automated TExt Summarization of scholastic text in Table format (Auto-TEST) to provide information at a glance by mimicking the student’s style of note-making. The Auto-TEST framework is achieved through two steps which is Summarization and Tabulation. Initially, the Extractive Single Document Text Summarization (ESDTS) method is adopted to identify the salient information from the non-fictional (scholastic) text which is extracted and grouped together to form a concise summary. A Named Entity Recognition (NER) method is implemented to extract noun chunks and then arrange them in a tabulation format that aids in memorizing essential facts and figures by enabling effortless retrieval. The performance of the Auto-TEST framework is gauged by using scholastic domain-specific dataset using ROUGE as an evaluation metric. The extracted entities gives an average Recall of 71.40%, an average Precision score of 75.80% and an average F-score of 73.54% for the dataset respectively. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

CALTM:A Context-Aware Long-Term Time-Series Forecasting Model

引用

Computer Modeling in Engineering & sciences 2024年第4期139卷 873-891页

作者： Canghong Jin Jiapeng Chen Shuyu Wu Hao Wu Shuoping Wang Jing Ying School of Computer and Computing Science Hangzhou City UniversityHangzhou310015China School of Computer Science and Engineering Macao University of Science and TechnologyMacao999078China College of Computer Science and Technology Zhejiang UniversityHangzhou310058China

Time series data plays a crucial role in intelligent transportation *** flow forecasting represents a precise estimation of future traffic flow within a specific region and time *** approaches,including sequence periodic,regression,and deep learning models,have shown promising results in short-term series ***,forecasting scenarios specifically focused on holiday traffic flow present unique challenges,such as distinct traffic patterns during vacations and the increased demand for long-term ***,the effectiveness of existing methods diminishes in such ***,we propose a novel longterm forecasting model based on scene matching and embedding fusion representation to forecast long-term holiday traffic *** model comprises three components:the similar scene matching module,responsible for extracting Similar Scene Features;the long-short term representation fusion module,which integrates scenario embeddings;and a simple fully connected layer at the head for making the final *** results on real datasets demonstrate that our model outperforms other methods,particularly in medium and long-term forecasting scenarios.

关键词： Traffic volume forecasting scene matching multi module fusion

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：