检索结果-内蒙古大学图书馆

SlowFast Based Real-Time Human Motion Recognition with Action Localization

computer systems science & engineering 2023年第11期47卷 2135-2152页

作者： Gyu-Il Kim Hyun Yoo Kyungyong Chung Department of Computer Science Kyonggi UniversitySuwon16227Korea Contents Convergence Software Research Institute Kyonggi UniversitySuwon16227Korea Division of AI Computer Science and Engineering Kyonggi UniversitySuwon16227Korea

Artificial intelligence is increasingly being applied in the field of video analysis,particularly in the area of public safety where video surveillance equipment such as closed-circuit television(CCTV)is used and automated analysis of video information is ***,various issues such as data size limitations and low processing speeds make real-time extraction of video data *** analysis technology applies object classification,detection,and relationship analysis to continuous 2D frame data,and the various meanings within the video are thus analyzed based on the extracted basic *** recognition is key in this *** recognition is a challenging field that analyzes human body movements,requiring the interpretation of complex movements of human joints and the relationships between various *** deep learning-based human skeleton detection algorithm is a representative motion recognition ***,motion analysis models such as the SlowFast network algorithm,have also been developed with excellent ***,these models do not operate properly in most wide-angle video environments outdoors,displaying low response speed,as expected from motion classification extraction in environments associated with high-resolution *** proposed method achieves high level of extraction and accuracy by improving SlowFast’s input data preprocessing and data structure *** input data are preprocessed through object tracking and background removal using YOLO and DeepSORT.A higher performance than that of a single model is achieved by improving the existing SlowFast’s data structure into a frame unit *** on the confusion matrix,accuracies of 70.16%and 70.74%were obtained for the existing SlowFast and proposed model,respectively,indicating a 0.58%increase in *** detection,based on behavioral classification,the existing SlowFast detected 2,341,164 cases,whereas the proposed model detected 3,11

关键词： Artificial intelligence convolutional neural network video analysis human action recognition skeleton extraction

来源：评论

学校读者我要写书评

暂无评论

Speech Recognition System for Upper-Limb Impairment: A Text Editor for Programming via Voice 2

Speech Recognition System for Upper-Limb Impairment: A Text ...

引用

2nd International Conference on Automation, Computing and Renewable systems, ICACRS 2023

作者： Rampriya, R.S. Dharshan, R. Santhosh, S. School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamilnadu Vellore India Department of Computer Technology Madras Institute of Technology Tamilnadu Chennai India

ISBN: (纸本)9798350340235

Programming is one of the most important skills to learn for the present and future generations. However, those with hand disabilities may find it difficult to program with a traditional keyboard and mouse. Disabled people would greatly benefit from assistive technology that allows them to use their voices to control computers. The existing system recognizes user input as voice and translates it into a program. However, the existing system only recognizes a limited number of keywords in a programming language. It would also be difficult to debug errors if the voice was misinterpreted. Our suggested work in speech recognition using natural language processing (NLP) would perform better than the previously available systems. It is possible to build a foundation for programming without a keyboard by creating tools that use a publicly accessible speech recognition API. Voice control of the user interface for program execution and code debugging would also be quite beneficial. This can be done with the help of modules such as Pynput. Keyboard, PyAutoGUI, which can simulate mouse cursor movements and clicks as well as keyboard button presses. The accuracy of our proposed system is 87%. When converting voice commands to text, the Word Error Rate (WER) is 18%. © 2023 IEEE.

关键词： Python Speech Recognition Speech-to-Text Vocal Programming

来源：评论

学校读者我要写书评

暂无评论

Extending OpenStack Monasca for Predictive Elasticity Control

引用

Big Data Mining and Analytics 2024年第2期7卷 315-339页

作者： Giacomo Lanciano Filippo Galli Tommaso Cucinotta Davide Bacciu Andrea Passarella Scuola Normale Superiore Pisa 56126Italy the Real-Time Systems Laboratory(RETIS) TelecommunicationsComputer Engineeringand Photonics Institute(TeCIP)Scuola Superiore Sant’AnnaPisa 56127Italy Department of Computer Science University of PisaPisa 56127Italy National Research Council Pisa56127Italy

Traditional auto-scaling approaches are conceived as reactive automations,typically triggered when predefined thresholds are breached by resource consumption *** such rules at scale is cumbersome,especially when resources require non-negligible time to be *** paper introduces an architecture for predictive cloud operations,which enables orchestrators to apply time-series forecasting techniques to estimate the evolution of relevant metrics and take decisions based on the predicted state of the *** this way,they can anticipate load peaks and trigger appropriate scaling actions in advance,such that new resources are available when *** proposed architecture is implemented in OpenStack,extending the monitoring capabilities of Monasca by injecting short-term forecasts of standard *** use our architecture to implement predictive scaling policies leveraging on linear regression,autoregressive integrated moving average,feed-forward,and recurrent neural networks(RNN).Then,we evaluate their performance on a synthetic workload,comparing them to those of a traditional *** assess the ability of the different models to generalize to unseen patterns,we also evaluate them on traces from a real content delivery network(CDN)*** particular,the RNN model exhibites the best overall performance in terms of prediction error,observed client-side response latency,and forecasting *** implementation of our architecture is open-source.

关键词： OpenStack monitoring elasticity control auto-scaling predictive operations Monasca

来源：评论

学校读者我要写书评

暂无评论

Agricultural Water Conservation through AI-Enhanced Solar IoT Networks 3

Agricultural Water Conservation through AI-Enhanced Solar Io...

引用

3rd International Conference on Electronics and Renewable systems, ICEARS 2025

作者： Maniraj, S.P. Monisha, J. Amutha, R. Kavitha, R. Shriidhar, P.J. Srinivasan, C. Srm Institute of Science and Technology School of Computing Department of Data Science and Business Systems Kattankulathur Tamilnadu Chennai India Tamil Nadu Chennai India Ultra College of Engineering and Technology Department of Electrical and Electronics Engineering Tamil Nadu Madurai India Chennai Institute of Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Vinayaka Missions Kirupananda Variyar Engineering College Department of Computer Science and Engineering Tamil Nadu Salem India Saveetha Universityi Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331509675

With the increasing water shortage and climatic uncertainty, creative strategies for effective water management in agriculture are necessary. This research investigates the integration of Artificial Intelligence (AI), particularly Artificial Neural Networks (ANN), with solar-powered Internet of Things (IoT) networks to enhance water utilization in agricultural activities. The proposed system facilitates accurate irrigation scheduling using real-time data from soil moisture sensors, meteorological stations, and crop health monitoring devices. The ANN model analyses this data to predict ideal irrigation schedules and volumes, minimizing water waste while improving crop yields. The solar-powered IoT framework provides sustainability and reduces dependence on traditional energy sources. Field trials indicate that the AI-enhanced system may promote water saving by as much as 30% relative to traditional irrigation techniques. Moreover, using AI enables adaptive learning, enabling the system to enhance its irrigation tactics using historical and real-time data. This novel method conserves water resources and fosters sustainable agriculture practices, coinciding with global initiatives to address water shortages and assure food security. The findings underscore the potential of technology-based solutions to revolutionize agricultural water management for a sustainable future. © 2025 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

An Improved Multi-Objective Particle Swarm Optimization Routing on MANET

引用

computer systems science & engineering 2023年第2期44卷 1187-1200页

作者： G.Rajeshkumar M.Vinoth Kumar K.Sailaja Kumar Surbhi Bhatia Arwa Mashat Pankaj Dadheech Department of Computer Science and Engineering Erode Sengunthar Engineering CollegePerunduraiErode638057Tamil NaduIndia Department of Information Science and Engineering Dayananda Sagar Academy of Technology and ManagementBangalore560082India Department of Master of Computer Applications M.S.Ramaiah Institute of TechnologyBangalore560054India Department of Information Systems College of Computer Science and Information TechnologyKing Faisal UniversityRiyadh11533Saudi Arabia Faculty of Computing and Information Technology King Abdulaziz UniversityRabigh21911Saudi Arabia Department of Computer Science and Engineering Swami Keshvanand Institute of TechnologyManagement&GramothanJaipur302017RajasthanIndia

A Mobile Ad hoc Network(MANET)is a group of low-power con-sumption of wireless mobile nodes that conﬁgure a wireless network without the assistance of any existing infrastructure/centralized *** primary aim of MANETs is to extendﬂexibility into the self-directed,mobile,and wireless domain,in which a cluster of autonomous nodes forms a MANET routing *** Intrusion Detection System(IDS)is a tool that examines a network for mal-icious behavior/policy violations.A network monitoring system is often used to report/gather any suspicious attacks/*** IDS is a software program or hardware system that monitors network/security trafﬁc for malicious attacks,sending out alerts whenever it detects malicious *** impact of Dynamic Source Routing(DSR)in MANETs challenging blackhole attack is investigated in this research *** Cluster Trust Adaptive Acknowledgement(CTAA)method is used to identify unauthorised and malfunctioning nodes in a MANET *** system is active and provides successful delivery of a data packet,which implements Kalman Filters(KF)to anticipate node ***,KF is used to eliminate synchronisation errors that arise during the sending and receiving *** order to provide an energy-efﬁcient solution and to minimize network trafﬁc,route optimization in MANET by using Multi-Objective Particle Swarm Optimization(MOPSO)technique to determine the optimal num-ber of clustered MANET along with energy dissipation in *** to the researchﬁndings,the proposed CTAA-MPSO achieves a Packet Delivery Ratio(PDR)of 3.3%.In MANET,the PDR of CTAA-MPSO improves CTAA-PSO by 3.5%at 30%malware.

关键词： MANET intrusion detection system cluster kalmanﬁlter dynamic source routing multi-objective particle swarm optimization packet delivery ratio

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Hashtag Topic Classification with Multimodal Features and VLMs

A Novel Approach for Hashtag Topic Classification with Multi...

引用

2024 International Conference on Horizons of Information Technology and engineering, HITE 2024

作者： Zafar, Hafiza Tayyaba Tahir, Bilal Mehmood, Muhammad Amir University of Engineering and Technology Al-Khawarizmi Institute of Computer Science Lahore54890 Pakistan Islamic University of Madinah Associated with Faculty of Computer and Information Systems Madinah42351 Saudi Arabia

ISBN: (纸本)9798331516055

The rapid expansion of Instagram content marked by a large volume of photos and comments demands effective methods for discovering topics. While hashtags facilitate the grouping of posts, categorizing these hashtags into specific topics is challenging task due to the multimodal and noisy nature of content on the platform. In this paper, we introduce a novel approach that leverages multimodal features and Vision-Language Models (VLMs) for the topic classification of hashtags. To achieve this, we develop a dataset InstaHash which includes 464 hashtags and 12,345 posts spanning five topic categories: army, politics, sports, judiciary, and religion. We extract text features using the TF-IDF algorithm and visual features using HSV, SIFT, ResNet50, and VGG16 algorithms. Additionally, we introduce 34 binary features derived from the VLM of LLAVA through prompt engineering. These prompt engineering features examine the six aspects of images such as people, symbols and objects, buildings, events, uniforms, and embedded text. We train four classifiers of Support Vector Machine (SVM), Logistic Regression (LR), Decision Tree (DT), and Convolutional Neural Network (CNN) for topic classification of hashtags. Our analysis reveals that combining text and visual features yields an accuracy of 0.89 for topic classification with the CNN classifier. However, by incorporating additional prompt features into the model, we achieve the highest accuracy of 0.96. Moreover, we notice that prompt features related to aspects of people and symbols are the most important features for the topic classification of hashtags. © 2024 IEEE.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Semi-analytical finite element method applied for characterizing micropolar fibrous composites

引用

Applied Mathematics and Mechanics(English Edition) 2024年第12期45卷 2147-2164页

作者： J.A.OTERO Y.ESPINOSA-ALMEYDA R.RODRIGUEZ-RAMOS J.MERODIO School of Engineering and Sciences Monterrey Institute of TechnologyEstado de Mexico 52926Mexico Institute of Engineering and Technology Autonomous University of Ciudad JuarezCiudad JuarezChihuahua 32310Mexico Postgraduate Program in Computational Modeling in Science and Technology Federal Fluminense UniversityRıo de Janeiro 27255-125Brazil Faculty of Mathematics and Computer Science University of HavanaLa Habana 10400Cuba Department of Mathematics Applied to ICT School of Informatics Systems EngineeringTechnical University of MadridMadrid 28031Spain

A semi-analytical finite element method(SAFEM),based on the two-scale asymptotic homogenization method(AHM)and the finite element method(FEM),is implemented to obtain the effective properties of two-phase fiber-reinforced composites(FRCs).The fibers are periodically distributed and unidirectionally aligned in a homogeneous *** framework addresses the static linear elastic micropolar problem through partial differential equations,subject to boundary conditions and perfect interface contact *** mathematical formulation of the local problems and the effective coefficients are presented by the *** local problems obtained from the AHM are solved by the FEM,which is denoted as the *** numerical results are provided,and the accuracy of the solutions is analyzed,indicating that the formulas and results obtained with the SAFEM may serve as the reference points for validating the outcomes of experimental and numerical computations.

关键词： semi-analytical approach fiber-reinforced composite(FRC) effective property finite element method(FEM) asymptotic homogenization method(AHM) micropolar elasticity

来源：评论

学校读者我要写书评

暂无评论

Prediction of Autoimmune Disease using Ensemble Machine Learning Approaches 2

Prediction of Autoimmune Disease using Ensemble Machine Lear...

引用

2nd International Conference on Augmented Intelligence and Sustainable systems, ICAISS 2023

作者： Khandhan, C. Rukumani Sailogaprakash, S. Sakthivel, K. Seenivasan, D. Mekala, R. Kongu Engineering College Computer Technology-PG Erode India K.S.Rangasamy College of Technology Computer Science and Bussiness Systems Tiruchengode India M.Kumarasamy College of Engineering Computer Science and Bussiness Systems Karur India Bannari Amman Institute of Technology Information Science and Engineering Sathyamangalam India

ISBN: (纸本)9798350325799

The term "autoimmune diseases"refers to a class of illnesses where the immune system attacks the body's own healthy cells. Effective treatment and management of many disorders depend on early detection and precise diagnosis. In this research, Using the clinical and laboratory data were it had been imported from the UCI data repository to develop an ensemble model for the prediction of autoimmune disorders. To create a reliable predictive model, the ensemble model incorporates many machine learning approaches like the Gradient boost classifier, SVC and RF, and the KNN. The suggested model was trained and assessed using a sizable dataset of individuals with autoimmune disorders. When the model's performance was compared to that of individual machine learning methods, it was exposed that the ensemble model gives out them all in terms of accuracy, and sensitivity, and set out with the help of hyper-parameter Tuning. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Less Labeling Burden: A SAR Ship Detection Data Selection Method Based on K-means 2

Less Labeling Burden: A SAR Ship Detection Data Selection Me...

引用

2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024

作者： Yang, Yimin Yin, Junjun Lang, Ping Yang, Jian He, Yaomin Tsinghua University Department of Electronic Engineering Beijing China University of Science and Technology School of Computer and Communication Engineering Beijing China Academy of Military Sciences Institute of Systems Engineering Beijing China

ISBN: (纸本)9798331515669

In deep learning-based object detection, labeled data is crucial. However, annotating ship targets in Synthetic Aperture Radar (SAR) images is challenging because of the distinct characteristics of SAR images, especially when employing Oriented Bounding Boxes (OBB). These challenges arise from factors such as varying ship orientations, complex backgrounds, and the presence of noise, making accurate annotation more difficult. To reduce the labeling burden while minimizing its impact on ship detection performance, we propose a SAR data selection method. This method ensures that, despite limited quantities, the data contains a more representative range of scenarios when constructing a new dataset. By selecting 10 features of SAR images and performing K-means clustering based on these features, we choose the samples closest to the cluster centers as the selected data. We have validated the effectiveness of the proposed method by applying two typical object detection models to both randomly selected and clustering-selected datasets, thereby demonstrating the efficacy of proposed approach. © 2024 IEEE.

关键词： Radar imaging

来源：评论

学校读者我要写书评

暂无评论

Research on Polarization Theory Based on Target Polarization Projection 2

Research on Polarization Theory Based on Target Polarization...

引用

2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024

作者： He, Yaomin Yang, Jian Yang, Yimin Yin, Junjun Liu, Chao Academy of Military Sciences Institute of Systems Engineering Beijing China Tsinghua University Department of Electronic Engineering Beijing China University of Science and Technology School of Computer and Communication Engineering Beijing China

ISBN: (纸本)9798331515669

Aiming at the information processing in classical polarization theory, such as polarization decomposition, optimal polarization, polarization filtering, polarization detection, and polarization classification, et al, they are of great significance which supported a large number of polarization applications. Although the theory is relatively rich, there are also some deficiencies, i.e., overlapping theories and inconsistent concepts, which have inconvenient effects on the systematic research of polarization theory. In this regard, this paper proposes the concept and mathematical model of "target polarization projection", in order to form two polarization basic theories with target polarization decomposition. It can achieve a series of polarization information processing such as polarization filtering, polarization detection, and polarization classification, thus providing a clear polarization theory framework and laying a theoretical foundation for the application of polarimetric SAR. © 2024 IEEE.

关键词： Wiener 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：