检索结果-内蒙古大学图书馆

Study of the Performance of Adaptive Sensor Networks for Collecting and processing Thermoelectric data 1

7th international Russian Automation conference, RusAutoCon 2024

作者： Surzhik, D. Vasilyev, G. Kuzichkin, O. Belgorod National Research 85 Pobedy Str Belgorod308015 Russia

ISBN: (数字)9783031824944

ISBN: (纸本)9783031824937

To build models of a multi-level process for collecting and processing data from a telecommunication system for distributed data acquisition and thermoelectric control, including separately allocated objects, the most effective is use of wireless sensor ad-hoc networks (Wireless Ubiquitous Sensor Networks, WUSN). A method is proposed to adjust the performance of WUSN with adaptation of the link layer based on neuro-fuzzy approach, which performs estimation of the dynamic behavior of a communication channel, as well as the integrity of the received data, and controls information packets retransmissions. A comparison was made of the performance of the WUSN network based on the well known CSMA/SA link layer protocol, as well as a similar network with link layer adaptation. It has been established that the proposed link layer protocol provides the least quantity of missed packets at a similar transmission speed and average delay. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

Research on the processing algorithm for solar cell characterization data 2

Research on the processing algorithm for solar cell characte...

引用

2nd international conference on Electronic Information Engineering and Computer Communication, EIECC 2022

作者： Gui, Ruoxia Cheng, Jin Li, Junming Zhang, Chunqian Qin, Lei Research Center for Sensor Technology Beijing Key Laboratory for Sensor School of Applied Sciences Beijing Information Science and Technology University Jianxiangqiao Campus Beijing100101 China Beijing Key Laboratory for Optoelectronic Measurement Technology Beijing Information Science & Technology University Beijing100192 China

ISBN: (纸本)9781510663121

The research of solar cells has gone through three generations, silicon solar cells, thin film solar cells and perovskite solar cells. There are a variety of characterization methods used to analyze the factors that affect the performance of solar cells. Thus far, there are some deficiencies in the research of algorithms of the characterization methods themselves. Three types of data: current density-voltage (J-V) curves, X-ray diffraction (XRD) spectrum and absorption spectrum are the most essential characterization methods. Here, the processing algorithms of these three kinds of characterization data are studied, intend to help researchers to solve the practical problems more efficiently, and improve the accuracy of experimental results. In this paper, the process of processing algorithm are summarized in the way of flow chart, and combined with the example to show in turn. © 2023 SPIE.

关键词： Silicon solar cells

来源：评论

学校读者我要写书评

暂无评论

Research on the Stability of Pattern Recognition Collaborative algorithms Based on data Mining

Research on the Stability of Pattern Recognition Collaborati...

引用

Computers, Information processing and Advanced Education (CIPAE), 2020 international conference on

作者： Xue Fan College of Computer Science and Technology Jilin University Changchun China

ISBN: (数字)9798331527662

ISBN: (纸本)9798331527679

The contemporary era and world of big data has seen the stability of advanced pattern recognition and collaborative algorithms that are critical in the practical process ofdata mining. This research study primarily delves into the factors that significantly enhance algorithms' stability and optimized function. This factor is focused on ensuring reliable and consistent recognition models and patterns. Based on this context, this research primarily focuses on including data mining techniques to bolster collaborative algorithms' optimized functions and robustness. Through a comprehensive analysis of a myriad of data sets, factors that significantly influence the stability of these algorithms are underscored. Findings, therefore, indicate that incorporating pattern recognition and collaborative algorithms based on data mining significantly improves the algorithmic stability of a system. Thus, the research findings validate the extensive and empirical simulation and tests that efficiently maintain stability in a pattern recognition model.

关键词： Computers Error analysis Computational modeling Education Collaboration Information processing Big data Stability analysis Robustness data mining

来源：评论

学校读者我要写书评

暂无评论

Research on the relationship between new business talents' ability and its thinking mode in the era of big data

Research on the relationship between new business talents' a...

引用

2020 international conference on data processing algorithms and models, icdpam 2020

作者： Qu, Ying An, Ruoyu Hebei University of Science and Technology School of Economics and Management Data Science and Intelligent Computing Research Center Shijiazhuang City Hebei Province China

In the era of big data, the development of "new business"really needs talents who use new ways of thinking to solve economic management ***, it is very important to comprehensively analyze the relationship between the ability of new business talents and the way of thinking in the era of big *** combing the literature, we have collected and sorted out the thinking mode in the era of big data and the ability requirements of new business for talents. This article selects 9 ability elements, including 4 ways of thinking and 5 talent abilities, to present the structural model of the relationship between the ability of new business talents and their thinking mode in the era of big data. Analyzing the relationship between talent abilities and thinking styles from a new perspective of big data, supplementing and expanding the existing research on new business talent's abilities, is conducive to the update of training programs, and has certain significance for integrating teaching resources and optimizing curriculum structure. © Published under licence by IOP Publishing Ltd.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Advanced ML Techniques for Real-Time Air Quality Prediction in Megacities: A Comparative Study 2

Advanced ML Techniques for Real-Time Air Quality Prediction ...

引用

2nd international conference on Automation, Computing and Renewable Systems, ICACRS 2023

作者： Vignesh, U. Elakya, R. Selvi, R. Thanga Shanthana, S. School of Computer Science and Engineering Vellore Institute of Technology VIT- Kelambakkam - Vandalur Road Tamil Nadu Chennai India Information Technology Sri Venkateswara College of Engineering Sriperumbudur Chennai India Computer Science and Engineering Vel Tech Rangarajan Dr Sagunthala R & D Institute of Science and Technology Avadi Chennai India Rajalakshmi Institute of Technology Chennai India

ISBN: (纸本)9798350340235

It is impossible to imagine humans surviving without oxygen. Due to the recent developments in almost all aspects of civilization, air quality has continually decreased. The day-to-day industrial, transportation, and home activities produce harmful pollutants into our surroundings. Monitori ng and forecasting air quality have become crucial in the modern era, particularly in the developing countries like India. In comparison to more traditional methodologies, new prediction technologies based on machine learning have emerged as the most useful tools for analyzing those unique threats. The current study analyses air quality data from 23 Indian cities over a period of six years in order to make air quality projections. Correlation analysis is used to identify the most significant aspects of the dataset and to complete the preprocessing. Pollutants with a direct impact on the air quality index are identified using exploratory data analysis, which is used to identify hidden patterns in the dataset. Due to pandemic situation, almost all pollutants were greatly reduced in the year 2020. After addressing the data imbalance issue with a resampling method, five machine learning models are employed to predict air quality. There are comparisons between these models and the gold standard metrics. The Gaussi an Naive Bayes model has the highest accuracy, while the S upport Vector Machine model has the lowest. When compared to other existing models, XGBoost has the maximum linearity between the predicted and actual data. © 2023 IEEE.

关键词： Air quality prediction comparative analysis Environmental data Machine learning Real- time processing Regression algorithms Sensor data Time-series data

来源：评论

学校读者我要写书评

暂无评论

2nd international conference on Machine Learning, Image processing, Network Security and data Sciences, MIND 2020

2nd International Conference on Machine Learning, Image Proc...

引用

2nd international conference on Machine Learning, Image processing, Network Security and data Sciences, MIND 2020

ISBN: (纸本)9789811563140

The proceedings contain 83 papers. The special focus in this conference is on Machine Learning, Image processing, Network Security and data Sciences. The topics include: Distance Invariant RGB-D Object Recognition Using DSMS System;Single Look SAR Image Segmentation Using Local Entropy, Median Low-Pass Filter and Fuzzy Inference System;An Edge Detection and Sliding Window Based Approach to Improve Object Localization in YOLOv3;automatic Detection of Pneumonia from Chest X-Rays Using Deep Learning;an Improved Accuracy Rate in Microaneurysms Detection in Retinal Fundus Images Using Non-local Mean Filter;emotion Recognition from Periocular Features;a Comparative Study of Computational Intelligence for Identification of Breast Cancer;segmentation of Blood Vessels from Fundus Image Using Scaled Grid;head Pose Estimation of Face: Angle of Roll, Yaw, and Pitch of the Face Image;identifying Fake Profile in Online Social Network: An Overview and Survey;enhancing and Classifying Traffic Signs Using Computer Vision and Deep Convolutional Neural Network;diabetic Retinopathy Detection on Retinal Fundus Images Using Convolutional Neural Network;medical Image Fusion Based on Deep Decomposition and Sparse Representation;rice Plant Disease Detection and Classification Using Deep Residual Learning;Flood Detection Using Multispectral Images and SAR data;Handwritten Character Recognition Using KNN and SVM Based Classifier over Feature Vector from Autoencoder;a ConvNet Based Procedure for Image Copy-Move Forgery Detection;a Novel Invisible Watermarking Approach for Double Authentication of Image Content;remote Sensing Signature Classification of Agriculture Detection Using Deep Convolution Network models;buddhist Hasta Mudra Recognition Using Morphological Features.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Local Attention: Enhancing the Transformer Architecture for Efficient Time Series Forecasting

Local Attention: Enhancing the Transformer Architecture for ...

引用

international Joint conference on Neural Networks (IJCNN)

作者： Aguilera-Martos, Ignacio Herrera-Poyatos, Andres Luengo, Julian Herrera, Francisco Univ Granada Andalusian Inst Data Sci & Computat Intelligence Dept Comp Sci & Artificial Intelligence Granada Spain

ISBN: (纸本)9798350359329;9798350359312

Transformers have emerged as a highly effective architecture for natural language processing and computer vision. Of late, there has been a surge in initiatives aimed at refining this architecture to enhance its applicability to long sequence time-series forecasting, yielding promising outcomes. This paper introduces Local Attention, an efficient attention mechanism tailored for time series data. This mechanism exploits the continuity properties of time series and the principle of locality in order to compute less attention scores. We provide an T(n log n) algorithm to implement Local Attention based on tensor algebra results, which contrasts to the theta(n(2)) time and memory complexity of the original attention mechanism. Our experimental analysis shows that the vanilla transformer with Local Attention outperforms state of the art models based on probabilistic attention mechanisms. These findings affirm the effectiveness of our approach and outline a spectrum of future challenges in long sequence time series forecasting.

关键词： time series transformer attention mechanism deep learning

来源：评论

学校读者我要写书评

暂无评论

Selection of audio materials in college music education courses based on hybrid recommendation algorithm and big data

Selection of audio materials in college music education cour...

引用

2020 international conference on data processing algorithms and models, icdpam 2020

作者： Li, Tianjiao Shandong Management University Jinan City Shandong Province China

Aiming at the problem of audio material selection in college music education courses and to solve the problem of students' low enthusiasm caused by improper selection of audio materials, this paper adopts the hybrid recommendation algorithm combining big data, personalized recommendation algorithm based on Collaborative Filtering Recommendation Algorithm (CF). Big data is used to obtain user evaluation matrix, and Pearson correlation coefficient is used to calculate the similarity between users, so as to form the nearest neighbor set, obtain the nearest neighbor set of target users, and generate the user-based recommendation set. At the same time, a questionnaire is set up to obtain the real evaluation scores of each user on the audio materials. 20% of the questionnaire data are used for model testing and 80% for model training. The accuracy of the square root error is measured, and the prediction score obtained by the model is compared with the real score. It is found that the mean RMSE value of the model adopted in this paper is 0.3813, which is at least 2.564% higher than that of similar models, and has a higher accuracy. Meanwhile, the algorithm is relatively simple, providing a reference for audio selection of college students in courses. © Published under licence by IOP Publishing Ltd.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

The evolution of IB research: a topic model analysis of EIBA conference papers (1975-2020)

引用

COMPETITIVENESS REVIEW 2025年第1期35卷 1-31页

作者： Corado Simoes, Vitor Rocha, Joao Pedro Piepenbrink, Anke Cantwell, John Gugler, Philippe Univ Lisbon Lisbon Sch Econ & Management ISEG ADVANCECSG Lisbon Portugal Univ Lisbon Lisbon Sch Econ & Management ISEG Lisbon Portugal Rennes Sch Business Dept Strategy & Innovat Rennes France Rutgers State Univ Rutgers Business Sch Piscataway NJ USA Univ Fribourg Fac Management Econ & Social Sci Fribourg Switzerland

PurposeThis paper comes in the context of the European international Business Academy (EIBA) History project, and the long period analysed was broken down in six time windows (1975-1981, 1982-1988, 1989-1995, 1996-2002, 2003-2012;and 2013-2020), in line with the periodisation followed in writing such history. The main purpose was to identify the key themes of the papers presented at EIBA conferences between 1975 and ***/methodology/approachThe analysis was carried out drawing on topic modelling, a machine-learning statistical solution that is capable of processing large volumes of text *** set of 5,296 Competitive and Workshop papers was processed with the use of topic modelling. The method enabled to identify 24 underlying research topics. These were then grouped into nine higher-level categories. The results show a consistent growth in the number of papers presented, especially in the periods going from 1989-2012. This is a sign of an increasing attractiveness, openness and attendance in EIBA's annual conferences. Overall, the topics with the highest probabilities were topic 22 (Measuring and Assessing IB performance), followed ex-aequo by topics 13 (Evolutionary Approaches, Matrix Structures and Managerial Challenges) and 20 (Comparative Management Education and Behaviour) and then by topic 4 (Born Globals and international New Ventures). A key finding was the change in methodological approaches over time, with a significant increase in the use of sound quantitative and qualitative methods, instead of broad narratives mostly based on descriptive *** limitations/implicationsLatent Dirichlet Allocation (LDA), as a quantitative approach to analyse text data, has some limitations. LDA, along with other distributional models, may identify degrees of semantic relations between words, but is not able by itself to specify the kind of relation, entailing a possible loss of contextual information which might have been able to further assi

关键词： international Business EIBA conference Papers Research method Content Analysis Topic Modelling Machine Learning C10 F20 M16 O19 O30

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal Modeling Encounters 3D Medical Image Analysis: Slice-Shift UNet with Multi-View Fusion 7

Spatiotemporal Modeling Encounters 3D Medical Image Analysis...

引用

7th international conference on Machine Vision and Applications (ICMVA)

作者： Ugwu, Cynthia I. Casarin, Sofia Lanz, Oswald Free Univ Bozen Bolzano Bolzano Italy

ISBN: (纸本)9798400716553

As a fundamental part of computational healthcare, Computer Tomography (CT) and Magnetic Resonance Imaging (MRI) provide volumetric data, making the development of algorithms for 3D image analysis a necessity. Despite being computationally cheap, 2D Convolutional Neural Networks can only extract spatial information. In contrast, 3D CNNs can extract three-dimensional features, but they have higher computational costs and latency, which is a limitation for clinical practice that requires fast and efficient models. Inspired by the field of video action recognition we propose a new 2D-based model dubbed Slice SHift UNet (SSH-UNet) which encodes three-dimensional features at 2D CNN's complexity. More precisely multi-view features are collaboratively learned by performing 2D convolutions along the three orthogonal planes of a volume and imposing a weights-sharing mechanism. The third dimension, which is neglected by the 2D convolution, is reincorporated by shifting a portion of the feature maps along the slices' axis. The effectiveness of our approach is validated in Multi-Modality Abdominal Multi-Organ Segmentation (AMOS) and Multi-Atlas Labeling Beyond the Cranial Vault (BTCV) datasets, showing that SSH-UNet is more efficient while on par in performance with state-of-the-art architectures.

关键词： healthcare volumetric data neural networks segmentation

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：