检索结果-内蒙古大学图书馆

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Haodi Lu Haikun Liu Chencheng Ye Xiaofei Liao Fubing Mao Yu Zhang Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computing Science and Technology Huazhong University of Science and Technology China

Modern storage systems typically replicate data on multiple servers to provide high reliability and availability. However, most commercially-deployed datastores often fail to offer low latency, high throughput, and strong consistency at the same time. This paper presents Whale, a Remote Direct Memory Access (RDMA) based primary-backup replication system for in-memory datastores. Whale achieves both low latency and strong consistency by decoupling metadata multicasting from data replication for all backup nodes, and using an optimistic commitment mechanism to respond to client write requests earlier. Whale achieves high throughput by propagating writes from the primary node to backup nodes asynchronously via RDMA-optimized chain replication. To further reduce the cost of data replication, we design a log-structured datastore to fully exploit the advantages of one-sided RDMA and Persistent Memory (PM). We implement Whale on a cluster equipped with PM and InfiniBand RDMA networks. Experimental results show that Whale achieves much higher throughput and lower latency than state-of-the-art replication protocols.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HGFormer: Topology-Aware Vision Transformer with HyperGraph Learning

引用

IEEE Transactions on Multimedia 2025年

作者： Wang, Hao Zhang, Shuo Leng, Biao Beihang University School of Computer Science and Engineering Beijing100191 China Beijing Key Laboratory of Traffic Data Analysis and Mining School of Computer Science & Technology Beijing100044 China

The computer vision community has witnessed an extensive exploration of vision transformers in the past two years. Drawing inspiration from traditional schemes, numerous works focus on introducing vision-specific inductive biases. However, the implicit modeling of permutation invariance and fully-connected interaction with individual tokens disrupts the regional context and spatial topology, further hindering higher-order modeling. This deviates from the principle of perceptual organization that emphasizes the local groups and overall topology of visual elements. Thus, we introduce the concept of hypergraph for perceptual exploration. Specifically, we propose a topology-aware vision transformer called HyperGraph Transformer (HGFormer). Firstly, we present a Center Sampling K-Nearest Neighbors (CS-KNN) algorithm for semantic guidance during hypergraph construction. Secondly, we present a topology-aware HyperGraph Attention (HGA) mechanism that integrates hypergraph topology as perceptual indications to guide the aggregation of global and unbiased information during hypergraph messaging. Using HGFormer as visual backbone, we develop an effective and unitive representation, achieving distinct and detailed scene depictions. Empirical experiments show that the proposed HGFormer achieves competitive performance compared to the recent SoTA counterparts on various visual benchmarks. Extensive ablation and visualization studies provide comprehensive explanations of our ideas and contributions. © 2025 IEEE.

关键词： Hypergraph Learning Image Classification Vision Transformer

来源：评论

学校读者我要写书评

暂无评论

Real-time Hand Gesture Recognition Using Python and Web Application 1

Real-time Hand Gesture Recognition Using Python and Web Appl...

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Patel, Meenu Rao, Saksham Chauhan, Shweta Kumar, Bibek Chandigarh University Apex Institute of Technology CSE Punjab Mohali India University Centre for Research & Development Chandigarh University Apex Institute of Technology CSE Punjab Mohali India Symbiosis University of Applied Sciences School of Data Science Madhya Pradesh Indore India

ISBN: (纸本)9798350356816

The recognition and tracking of hand gestures are essential elements in human-computer interaction systems, providing intuitive control and facilitating interaction with a wide range of devices and applications. We have developed a hand gesture detection system using Python and JavaScript. Our system uses MediaPipe, an open-source framework for machine learning-based perception tasks, to accurately identify and classify hand gestures. MediaPipe handles hand tracking, interpreting the hand curl and movement of hand gestures with high precision. We've built the frontend interface using HTML, CSS, and JavaScript. By combining these technologies, we've created a user-friendly interface where you can interact with the system through hand gestures captured via a webcam. Additionally, we've added our custom machine-learning methods to detect and recognize various hand *** system has numerous potential applications, including hand-sign translation and gesture-based control for smart devices. By offering an efficient and accessible solution, our project advances human-computer interaction paradigms, enabling more natural and intuitive interactions between users and machines. © 2024 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Building the ARIMA Model for Forecasting the Production of Vietnam’s Coffee Export

引用

Journal of Applied Mathematics and Physics 2024年第4期12卷 1237-1246页

作者： Duy Quang Phung Quoc Thang Trinh Quang Truong Do Ngan Giang Nguyen Van Ha Nguyen Gia Khiem Ngo Thi Minh Ngoc Tran Faculty of Technology and Data Science Foreign Trade University Hanoi Vietnam School of Economics and International Business Foreign Trade University Hanoi Vietnam

Coffee is a significant industry, accounting for 3% of Vietnam’s GDP, with annual export turnover consistently exceeding USD 3 billion. Despite global economic challenges affecting purchasing power at various times, Vietnam’s coffee exports in December 2023 continued to surge, reaching the highest level in the past 9 months at 190,000 tons, a 59.3% increase compared to November 2023, but still a slight 3.5% decrease from the same period last year. The export turnover reached USD 538 million, a 51% increase from November 2023 and a 26.4% increase from the same period last year. Therefore, forecasting the coffee export volume holds significant importance for coffee producers nationwide. This research employs the Box-Jenkins method to construct an ARIMA model for forecasting Vietnam’s coffee export volume based on annual data published by the General Statistics Office. Results indicate that among the models considered, the ARIMA(1, 1, 2) model is the most suitable. The study also provides short-term forecasts for Vietnam’s coffee export volume. However, the current model is limited to forecasting and is not yet optimized, as the assumed linearity in the model is a simplification.

关键词： ARIMA Forecasting Coffee Export Volume data science

来源：评论

学校读者我要写书评

暂无评论

ENCODER: Entity Mining and Modification Relation Binding for Composed Image Retrieval 39

ENCODER: Entity Mining and Modification Relation Binding for...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Li, Zixu Chen, Zhiwei Wen, Haokun Fu, Zhiheng Hu, Yupeng Guan, Weili School of Software Shandong University China School of Computer Science and Technology Harbin Institute of Technology Shenzhen China School of Data Science City University of Hong Kong Hong Kong

ISBN: (纸本)157735897X

The objective of Composed Image Retrieval (CIR) is to identify a target image that meets the requirement based on a multimodal query (including the reference image and the modification text) provided by the user. Despite the notable success of existing approaches, they fail to adequately address the modification relation between visual entities and modification actions. This limitation is non-trivial due to three challenges: 1) irrelevant factor perturbation, 2) vague semantic boundaries, and 3) implicit modification relations. To address the above challenges, we propose an Entity miNing and modifiCation relatiOn binDing nEtwoRk (ENCODER), which has been designed to mine visual entities and modification actions, and then bind modification relations. Among the various components of the proposed ENCODER, we have initially designed the Latent Factor Filter (LFF) module to filter visual and textual latent factors related to modification semantics based on a threshold gating mechanism. Secondly, we propose Entity-Action Binding (EAB), which comprises modality-shared Learnable Relation Queries (LRQ) that are capable of mining visual entities and modification actions, as well as learning implicit modification relations for entity-action binding. Finally, the Multi-scale Composition module is introduced to achieve multi-scale feature composition, with guidance provided by entity-action binding. Extensive experiments on four benchmark datasets demonstrate the superiority of our proposed method. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neutrosophic Mean Estimators Using Extreme Indeterminate Observations in Sample Surveys

引用

Neutrosophic Sets and Systems 2025年 80卷 86-117页

作者： Yadav, Vinay Kumar Majhi, Deepak Alkhathami, Alia A. Prasad, Shakti Department of Data Sciences and Analytics School of Social Sciences M S Ramaiah University of Applied Sciences Bengaluru560054 India PG Department of Mathematics Veer Kunwar Singh University Bihar Ara802301 India Department of Basic Science College of Science and Theoretical Studies Saudi Electronic University Riyadh11673 Saudi Arabia Department of Mathematics National Institute of Technology Jamshedpur Jharkhand Jamshedpur831014 India

In classical statistics, research typically relies on precise data to estimate the population mean, especially when auxiliary information is available. However, in the presence of outliers, conventional statistical approaches that depend on accurate data and auxiliary information encounter challenges. The primary objective is to attain the most accurate population mean estimates while minimizing the mean square error. Neutrosophic statistics, a more attractive framework than classical statistics, deals with data characterized by imprecision and uncertainty. In this current article, we adapt Särndal’s strategy and introduce neutrosophic mean estimators, applying them to meteorological data, specifically stratified dew point data. In these proposed estimators, the incorporation of auxiliary information and the application of robust techniques address issues that arise due to outliers and imprecise observations. These factors can otherwise undermine the effectiveness of neutrosophic estimation methods. The article also suggests combining auxiliary information with extremely indeterminate neutrosophic observations, utilizing robust regression methods (Huber-M, Hampel-M, and Tukey-M), as well as the quantile regression technique. These approaches enhance the neutrosophic mean estimation process. The outcomes, which include the utilization of dew point data, showcase the superior performance of the proposed estimators compared to adapted estimators in a neutrosophic context. Ultimately, this study provides valuable insights by taking an initial step in defining and utilizing the concept of neutrosophic indeterminate extreme observations. © 2025, University of New Mexico. All rights reserved.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

SP-DSTS-MIMO Scheme-Aided H.266 for Reliable High data Rate Mobile Video Communication

引用

Computers, Materials & Continua 2023年第1期74卷 995-1010页

作者： Khadem Ullah Nasru Minallah Durre Nayab Ishtiaque Ahmed Jaroslav Frnda Jan Nedoma Department of Computer Systems Engineering University of Engineering and Technology PeshawarPeshawar25000Pakistan National Centre in Big Data and Cloud Computing University of Engineering and Technology Peshawar(NCBC-UETP)Peshawar25000Pakistan Department of Quantitative Methods and Economic Informatics Faculty of Operation and Economics of Transport and CommunicationsUniversity of Zilina01026ZilinaSlovakia Department of Telecommunications Faculty of Electrical Engineering and Computer ScienceVSB-Technical University of OstravaOstrava-PorubaCzech Republic

With the ever growth of Internet users,video applications,and massive data traffic across the network,there is a higher need for reliable bandwidth-efficient multimedia *** Video Coding(VVC/H.266)is finalized in September 2020 providing significantly greater compression efficiency compared to Highest Efficient Video Coding(HEVC)while providing versatile effective use for Ultra-High Definition(HD)*** article analyzes the quality performance of convolutional codes,turbo codes and self-concatenated convolutional(SCC)codes based on performance metrics for reliable future video *** advent of turbo codes was a significant achievement ever in the era of wireless communication approaching nearly the Shannon *** codes are operated by the deployment of an interleaver between two Recursive Systematic Convolutional(RSC)encoders in a parallel *** RSC encoders may be operating on the same or different architectures and code *** proposed work utilizes the latest source compression standards H.266 and H.265 encoded standards and Sphere Packing modulation aided differential Space Time Spreading(SP-DSTS)for video transmission in order to provide bandwidth-efficient wireless video ***,simulation results show that turbo codes defeat convolutional codes with an averaged E_(b)/N_(0) gain of 1.5 dB while convolutional codes outperformcompared to SCC codes with an E_(b)/N_(0) gain of 3.5 dBatBit ErrorRate(BER)of 10−*** Peak Signal to Noise Ratio(PSNR)results of convolutional codes with the latest source coding standard of H.266 is plotted against convolutional codes with H.265 and it was concluded H.266 outperform with about 6 dB PSNR gain at E_(b)/N_(0) value of 4.5 dB.

关键词： H.265 RSC turbo codes SCC SP-DSTS BP-CNN BER PSNR

来源：评论

学校读者我要写书评

暂无评论

Enhancing Breeding Control: The IoT-Driven Automated System for Budgie Farming 11

Enhancing Breeding Control: The IoT-Driven Automated System ...

引用

11th International Conference on Cyber and IT Service Management, CITSM 2023

作者： Nooyimsai, Saranpong Thaloy, Jarinya Jansengrat, Parinya Janratchakool, Weena Krohkaew, Jaturapith Crisnapati, Padma Nyoman Thwe, Yamin Rajamangala University of Technology Srivijaya Department of Information Technology Nakhon Si Thammarat Thailand Rajamagala University of Technology Department of Big Data Management and Analytics Thanyaburi Pathum Thani Thailand Rajamagala University of Technology Department of Computer Science Thanyaburi Pathum Thani Thailand Institute of Technology and Business Stikom Bali Department of Information System Bali Indonesia

ISBN: (纸本)9798350305968

In Thailand's Pak Phanang Nok Hong Yok Farm, where budgies are raised, it emphasizes the value of proper care and surroundings. The primary problem this research addresses is the need for efficient and automated management of budgie farms, encompassing aspects such as feeding, watering, and temperature control and overcoming language barriers for Thailand's budgie farmers. An innovative Internet of Things (IoT) solution is suggested, departing from conventional approaches to handle challenges connected to manual care and environmental management for farmers. This system provides solutions for these challenges while enhancing monitoring and facilitating automated control. Through this IoT-based solution, the research intends to increase productivity, save time, and decrease bird mortality while enabling users to manage their farms remotely. Comprehensive methodologies involving breeding, environmental considerations, and hardware and software design are outlined, resulting in significant advancement in budgie farming practices and showcasing IoT's potential in agriculture. © 2023 IEEE.

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

Visual autoregressive modeling: scalable image generation via next-scale prediction 24

Visual autoregressive modeling: scalable image generation vi...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Keyu Tian Yi Jiang Zehuan Yuan Bingyue Peng Liwei Wang Center for Data Science Peking University and Bytedance Inc. Bytedance Inc. Center for Data Science Peking University and State Key Lab of General Artificial Intelligence School of Intelligence Science and Technology Peking University

ISBN: (纸本)9798331314385

We present Visual AutoRegressive modeling (VAR), a new generation paradigm that redefines the autoregressive learning on images as coarse-to-fine "next-scale prediction" or "next-resolution prediction", diverging from the standard raster-scan "next-token prediction". This simple, intuitive methodology allows autoregressive (AR) transformers to learn visual distributions fast and can generalize well: VAR, for the first time, makes GPT-style AR models surpass diffusion transformers in image generation. On ImageNet 256×256 benchmark, VAR significantly improve AR baseline by improving Fréchet inception distance (FID) from 18.65 to 1.73, inception score (IS) from 80.4 to 350.2, with 20× faster inference speed. It is also empirically verified that VAR outperforms the Diffusion Transformer (DiT) in multiple dimensions including image quality, inference speed, data efficiency, and scalability. Scaling up VAR models exhibits clear power-law scaling laws similar to those observed in LLMs, with linear correlation coefficients near -0.998 as solid evidence. VAR further showcases zero-shot generalization ability in downstream tasks including image in-painting, out-painting, and editing. These results suggest VAR has initially emulated the two important properties of LLMs: Scaling Laws and zero-shot generalization. We have released all models and codes to promote the exploration of AR/VAR models for visual generation and unified learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Water Quality Monitoring System and Classification Model Based on Internet of Things 5

Research on Water Quality Monitoring System and Classificati...

引用

5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022

作者： Zeng, Ji Luo, Xue Gang Wang, YueKun Liu, Yong Zhang, ZhiSen Panzhihua University Electrical and Information Engineering School Panzhihua China Panzhihua University School of Mathematics and Computers Big Date Science Panzhihua China Chengdu Aerospace Science and Industry Big Data Research Institute Co. Ltd. Chengdu China Panzhihua University School of Intelligent Manufacturing Panzhihua China

ISBN: (数字)9781665499163

ISBN: (纸本)9781665499163

Aiming at the problems of small coverage, high power consumption, low degree of automation and low accuracy of water quality classification prediction model of traditional wireless water quality monitoring system in industrial cities, a river water quality monitoring system based on Internet of things and neural network was proposed. Using low-power wide area network Lo technology to build low-power, long-distance, wide coverage of water quality monitoring information transmission channel, collect PH value, dissolved oxygen, potassium permanganate index, ammonia nitrogen and other water quality information, through the Internet of things to transmit the data to the cloud monitoring platform to achieve remote access to environmental information. At the same time, quantum genetic algorithm was used to optimize the initial weight and threshold, build G-BPNN water quality classification model, and improve the model. The accuracy and real-time performance of the system for water quality information collection and the effectiveness of the water quality classification model were verified by experiments. Compared with the traditional BP neural network model, the water quality classification prediction MSE was reduced from 0.793 to 0.069, which showed that the system constructed in this study can play the role of factory sewage discharge monitoring. © 2022 IEEE.

关键词： Water quality

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：