检索结果-内蒙古大学图书馆

High precision indoor positioning algorithm of single LED lamp based on A-Bayes

OPTIK 2021年 241卷 167190-167190页

作者： Qin, Ling Niu, Ben Li, Bao-Shan Hu, Xiao-Li Du, Yong-Xing Inner Mongolia Univ Sci & Technol Sch Informat Engn Baotou 014010 Inner Mongolia Peoples R China

With the rapid development of information technology, the application field of city positioning technology is more and more extensive. Traditional indoor positioning technology has shortcomings in positioning accuracy, equipment cost, security and so on. Visible light indoor positioning technology can effectively solve the above problems. This paper presents an Adaptive boosting- Bayes (A-Bayes) localization algorithm. In this algorithm, three tilted photodetectors and one horizontal PD are used as receivers to measure the received optical power of each PD and set up a fingerprint database. The Adaboost strong classifier is used to divide the test space into two regions: the center and the edge. In the online positioning stage, for the measured received optical power, the region to which it belongs is first determined, and then the bayesian matching algorithm is used to match the regions to complete the positioning. The experimental results show that in the test space of, and the overall average positioning error is 9.27 cm. Compared with the traditional indoor positioning algorithm, the positioning error of the proposed algorithm is smaller;Compared with the traditional multi lamp location algorithm, the algorithm proposed in this paper avoids the interference between multi light source symbols, and the equipment is simpler;Compared with the traditional fingerprint matching algorithm, the proposed algorithm has faster positioning speed.

关键词： Visible light indoor positioning Received optical power bayesian algorithm AdaBoost strong classifier

来源：评论

学校读者我要写书评

暂无评论

An Attempt to Analyze a Human Nervous System algorithm for Sensing Earthquake Precursors

引用

Open Journal of Earthquake Research 2023年第1期12卷 1-25页

作者： Da Cao Chinese Geophysical Society Natural Disaster Prediction Committee Fuzhou China

We statistically validate the 2011-2022 earthquake prediction records of Ada, the sixth finalist of the 2nd China AETA in 2021, who made 147 earthquake predictions (including 60% of magnitude 5.5 earthquakes) with a prediction accuracy higher than 70% and a confidence level of 95% over a 12-year period. Since the reliable earthquake precursor signals described by Ada and the characteristics of Alfvén waves match quite well, this paper proposes a hypothesis on how earthquakes are triggered based on the Alfvén (Q G) torsional wave model of Gillette et al. When the plume of the upper mantle column intrudes into the magma and lithosphere of the soft flow layer during the exchange of hot and cold molten material masses deep inside the Earth’s interior during ascent and descent, it is possible to form body and surface plasma sheets under certain conditions to form Alfven nonlinear isolated waves, and Alfven waves often perturb the geomagnetic field, releasing huge heat and kinetic energy thus triggering earthquakes. To explain the complex phenomenon of how Ada senses Alvfen waves and how to locate epicenters, we venture to speculate that special magnetosensory cells in a few human bodies can sense earthquake precursors and attempt to hypothesize an algorithm that analyzes how the human biological nervous system encodes and decodes earthquake precursors and explains how human magnetosensory cells can solve complex problems such as predicting earthquake magnitude and locating epicenters.

关键词： Earthquake Prediction Earthquake Precursors Mantle Column Plume Asthenosphere Alfven Isolated Waves Human Magnetic Induction Cells Neuronal Spikes bayesian algorithm

来源：评论

学校读者我要写书评

暂无评论

Improved matrix model of sequence grid partition based on vector space sampling

引用

PHYSICAL COMMUNICATION 2024年 64卷

作者： Cui, Lina Yingkou Inst Technol Yingkou 115002 Liaoning Peoples R China

In information technology and data science predictive analysis work, the goal is to infer guess values as accurately as possible. A more densely spaced grid of points should be set as a tool for operating measurement models. It has a wide range of applications in psychology, education and other social science research fields. Although the grid seems to meet the requirements of further improving the accuracy of reasoning and guessing from a certain point of view, it also means complex calculations. When multiple false values fall between another grid point, the traditional Data Oriented Architecture fails. To guarantee the accuracy and efficiency of the calculation, it is necessary to solve the problem of excessive noise in the prediction of samples in meta-learning to solve the uncertainty caused by the noise database data or the assumption of the matrix model. This paper proposes a grid partition movable inference least squares method, that is, the sparse bayesian least squares method based on the grid minimum matrix. The method is used for solving the problem that the prediction noise of the sample in the meta-learning is too large, to solve the uncertainty brought by the generated noise database data or the array matrix model assumption. According to the Symplectic bayesian learning of the sequence matrix model, the basic parameters for processing the input sample database data are determined. The sparse bayesian algorithm solution is used on the grid, combined with the off-grid inference guess of the sequence matrix model and the grid division. We set a coarse grid of points around the grid of false values. The rough point grid division is set, and the grid division around the false value is divided in detail. Then select more appropriate meta-learning parameters to clean up data. In the experiment analysis, we take the small sample study as the scene and carry on the concrete analysis to the experiment. The test proof in the fitting degree of the algorithm adop

关键词： Inference prediction Data evaluation Data matrix Noise interference bayesian algorithm Sparse grid

来源：评论

学校读者我要写书评

暂无评论

Multiple-signal defect identification of hydraulic pump using an adaptive normalized model and S transform

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2023年第1期124卷

作者： Zhu, Yong Tang, Shengnan Yuan, Shouqi Jiangsu Univ Natl Res Ctr Pumps Zhenjiang 212013 Peoples R China Int Shipping Res Inst GongQing Inst Sci & Technol Jiujiang 332020 Peoples R China Jiangsu Univ Inst Adv Mfg & Modern Equipment Technol Zhenjiang 212013 Peoples R China LEO Grp Co Ltd Wenling 317500 Peoples R China Saurer Changzhou Text Machinery Co Ltd Changzhou 213200 Peoples R China Jiangsu Univ Wenling Fluid Machinery Technol Inst Wenling 317525 Peoples R China

Axial piston pump plays a pivotal role in a hydraulic transmission system since it can supply the core power source. The complexity of structure and the invisibility of failure feature bring more difficulties and challenges to fault identification of an axial piston pump. It is of great meaning to exploit an effective and feasible fault identification method for the safe and stable system operation. An improved convolutional neural network (CNN) is constructed by mining and utilizing the interdisciplinary advantages of artificial intelligence and machinery engineering. First, the modeling takes the batch normalization strategy into account due to its capability of decreasing the data distribution differences. Second, bayesian algorithm is used for intelligent tuning of hyperparameters. Third, the improved CNN is applied to fault identification based on the S transform of multiple source signals. The performance of the proposed method is demonstrated by the experiments on an axial piston pump. The identification accuracies based on three signals reach 88.17%, 95.94%, and 99.44%. Results show that it can automatically recognize typical faults of the axial piston pump, and present the superiority to common CNNs.

关键词： Axial piston pump Intelligent defect identification CNN bayesian algorithm S transform

来源：评论

学校读者我要写书评

暂无评论

Modeling of microbial fuel cell power generation using machine learning-based super learner algorithms

引用

FUEL 2023年第1期349卷

作者： Hossain, S. M. Zakir Sultana, Nahid Haji, Shaker Mufeez, Shaikha Talal Janahi, Sara Esam Ahmed, Noof Adel Univ Bahrain Coll Engn Dept Chem Engn Zallaq Bahrain Imam Abdulrahman Bin Faisal Univ Coll Comp Sci & Informat Technol Dept Comp Sci Dammam Saudi Arabia

Electricity generation from microbial fuel cells (MFCs) is a potential environment-friendly technology. This study provides bayesian algorithm (BA) based Support Vector Regression (SVR) and Boosted Regression Tree (BRT) as prospective super learner modeling tools (BA-SVR, BA-BRT) for predictions of electricity production from MFCs. The membrane thickness, external resistance, and anode area were considered independent variables, while power generation was taken as a response variable. The key novelties of this study include (i) hybridization of BA with SVR and BRT (separately) for forecasting power generation from fuel cells for the first time, (ii) performance comparison of the developed models (BA-SVR and BA-BRT) with the existing Response Surface Methodology (RSM) based on the coefficient of determination (R2), relative error (RE), mean absolute error (MAE), mean absolute percentage error (MAPE), root mean square error (RMSE), and computing efficiency, and the (iii) analysis of the models' robustness by utilizing Gaussian white noise. Based on the performance indicators, the proposed super leaner models showed excellent performance compared to the existing M.J. Salar-Garcia et al. RSM model. The BA-SVR model provided the lowest errors (MAE of 2.94, RSME of 7.2926, MAPE of 13.8341) with the highest R2 of 0.9981, compared to the BA-BRT and RSM models. The proposed BA-SVR model showed superior performance to the RSM and BA-BRT models in predicting the MFCs' power generation, with a per-formance improvement of more than 90% regarding MAPE, as an example. The future prediction and high robustness of the proposed super learner model would ensure quick estimation for maximization of electricity generation that may lead to reducing massive lab trials and saving resources.

关键词： Electricity generation Fuel cell bayesian algorithm Response surface methodology Support vector regression Boosted regression tree

来源：评论

学校读者我要写书评

暂无评论

Micromechanical model of nanoparticle compaction and shock waves in metal powders

引用

INTERNATIONAL JOURNAL OF PLASTICITY 2021年 147卷 103102-103102页

作者： Mayer, Alexander E. Chelyabinsk State Univ Bratiev Kashirinykh St 129 Chelyabinsk 454001 Russia South Ural State Univ Lenin Prospect 76 Chelyabinsk 454080 Russia

A micromechanical model of metal powder compaction is developed as a generalization of the previous model proposed by Mayer et al. (2020). The model is applicable for an arbitrary axisymmetric deformed state including the uniaxial compression and the uniform tri-axial one. It describes the stage of compression of initially spherical particles, the percolation transition to the system of isolated pores and the stage of the collapse of pores. At the first stage, the metal particles are approximated by spheres with indented sectors with two independent indentation depths: One along the dedicated axis and another one along the perpendicular directions. The model of porous medium is formulated in finite deformations and the dislocation-driven plasticity model (Krasnikov and Mayer, 2015) is used to describe the pore collapse at the last stage. MD simulations of uniform tri-axial and uniaxial compression of iron, copper and magnesium nanoparticles of 6, 12 and 18 nanometers in diameter are performed for a number of temperatures. Activity of dislocations, which form dense structures, is the main driver of the plastic deformation of nanoparticles during compaction, while the presence of twins is revealed for copper and magnesium. MD data is used for identification of the model parameters and verification of the model. bayesian algorithm is implemented for parameter identification, which reveals itself as an efficient tool and allows us to fit the model with the same set of parameters to MD data for all investigated temperatures, particle diameters and modes of compression. The developed and parameterized micromechanical model is embedded into the continuum model of shock wave propagation in metal powder as a constitutive model of the substance. Both partial and complete compaction by the shock wave is investigated by an example of iron. The presence of elastic precursor is revealed for the case of nanopowders because of high yield strength of nanoparticle material achieved d

关键词： Nanoparticles Metal powder Compaction Micromechanical model Molecular dynamics bayesian algorithm Shock waves Plate impact Elastic precursor

来源：评论

学校读者我要写书评

暂无评论

Scalable Indoor Localization via Mobile Crowdsourcing and Gaussian Process

引用

SENSORS 2016年第3期16卷 381-381页

作者： Chang, Qiang Li, Qun Shi, Zesen Chen, Wei Wang, Weiping Natl Univ Def Technol Coll Informat Syst & Management Changsha 410073 Hunan Peoples R China

Indoor localization using Received Signal Strength Indication (RSSI) fingerprinting has been extensively studied for decades. The positioning accuracy is highly dependent on the density of the signal database. In areas without calibration data, however, this algorithm breaks down. Building and updating a dense signal database is labor intensive, expensive, and even impossible in some areas. Researchers are continually searching for better algorithms to create and update dense databases more efficiently. In this paper, we propose a scalable indoor positioning algorithm that works both in surveyed and unsurveyed areas. We first propose Minimum Inverse Distance (MID) algorithm to build a virtual database with uniformly distributed virtual Reference Points (RP). The area covered by the virtual RPs can be larger than the surveyed area. A Local Gaussian Process (LGP) is then applied to estimate the virtual RPs' RSSI values based on the crowdsourced training data. Finally, we improve the bayesian algorithm to estimate the user's location using the virtual database. All the parameters are optimized by simulations, and the new algorithm is tested on real-case scenarios. The results show that the new algorithm improves the accuracy by 25.5% in the surveyed area, with an average positioning error below 2.2 m for 80% of the cases. Moreover, the proposed algorithm can localize the users in the neighboring unsurveyed area.

关键词： radio map bayesian algorithm gaussian process indoor localization mobile crowdsourcing WLAN

来源：评论

学校读者我要写书评

暂无评论

Application Research in Internet information retrieval of Data Mining Technology

Application Research in Internet information retrieval of Da...

引用

2nd International Symposium on Instrumentation and Measurement, Sensor Network and Automation (IMSNA)

作者： Li Jie-yi Beijing Univ Posts & Telecommun Dept Econ & Management Beijing 100088 Peoples R China

ISBN: (纸本)9781479927166

According to the problem of the constant increase of internet data and the current Internet information retrieval system has been unable to meet the needs of data and information retrieval, this paper puts forward the data mining based Internet information retrieval system. The paper first uses data mining to excavate association rules, and evaluates the entire behavior simulation of users resources need according to a certain factor of user's retrieval resources, and then uses bayesian network algorithm to correlate the mining data. Experimental simulation results show that the application of bayesian network algorithm into Internet information retrieval has implemented intelligence and personalization of information retrieval to a certain extent, which has certain research value.

关键词： resource retrieval behavior pattern discrimination bayesian algorithm association rules mining

来源：评论

学校读者我要写书评

暂无评论

A Study on Sentiment Analysis Techniques of Twitter Data

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2019年第2期10卷 361-374页

作者： Alsaeedi, Abdullah Khan, Mohammad Zubair Taibah Univ Dept Comp Sci Coll Comp Sci & Engn Madinah Saudi Arabia

The entire world is transforming quickly under the present innovations. The Internet has become a basic requirement for everybody with the Web being utilized in every field. With the rapid increase in social network applications, people are using these platforms to voice them their opinions with regard to daily issues. Gathering and analyzing peoples' reactions toward buying a product, public services, and so on are vital. Sentiment analysis (or opinion mining) is a common dialogue preparing task that aims to discover the sentiments behind opinions in texts on varying subjects. In recent years, researchers in the field of sentiment analysis have been concerned with analyzing opinions on different topics such as movies, commercial products, and daily societal issues. Twitter is an enormously popular microblog on which clients may voice their opinions. Opinion investigation of Twitter data is a field that has been given much attention over the last decade and involves dissecting "tweets" (comments) and the content of these expressions. As such, this paper explores the various sentiment analysis applied to Twitter data and their outcomes.

关键词： Twitter sentiment Web data text mining SVM bayesian algorithm hybrid ensembles

来源：评论

学校读者我要写书评

暂无评论

Research on Air Quality Index Prediction Based on Neural Network Taking Beijing as an Example

Research on Air Quality Index Prediction Based on Neural Net...

引用

作者： Cong Zhao Xuemei Li School of Economics and Management Beijing Jiaotong University

With the continuous improvement of the level of industrialization, the air pollution situation in China has become more and more serious. In many places, extreme weather such as haze has appeared, which seriously threatens people's health. Therefore, it is necessary to establish a scientific and reasonable air quality index prediction model. However, there are significant differences in air quality indices in different quarters, that is, the AQI values are significantly seasonal. Therefore, in order to improve the prediction accuracy, the data of different quarters are distinguished, and models of different quarters are established. In this paper, the principal component analysis method is used to analyze the correlation between API value and various meteorological factors, and the correlation factor is used as the input variable of neural network. The number of neurons in different quarters is determined according to the mean square error, and bayesian normalization is established. The neural network is a model of the algorithm. Finally, the corresponding model was used to predict the air quality index of the corresponding quarter in 2018 based on the winter, spring, summer and autumn air conditions of Beijing from 2014 to 2017. The results show that the forecasting accuracy of each quarter is 88.27%, 92.28%, 94.04%, and 91.01%, respectively. The prediction accuracy of most studies is 70%～90%, and the prediction accuracy is high, which has certain reference value.

关键词： neural network air quality index linear regression principal component analysis bayesian algorithm

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：