Using improved gradient-boosted decision tree algorithm based on Kalman filter (GBDT-KF) in time series prediction

Li, Ling; Dai, Shuiping; Cao, Zhiwei; Hong, Jinghui; Jiang, Shu; Yang, Kunmeng

doi:10.1007/s11227-019-03130-y

Cited by 45 publications

(19 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is an algorithm commonly used in prediction models. It finds some valuable and potential information by purposefully classifying a large number of data [23,24]. ere are two common decision tree methods.…”

Section: Data Mining Technologymentioning

confidence: 99%

Design of Higher Education System Based on Artificial Intelligence Technology

Li¹,

Yang

et al. 2021

Discrete Dynamics in Nature and Society

View full text Add to dashboard Cite

In order to solve the problems of low security and response efficiency and slow running speed of the current designed higher education system, a higher education system based on artificial intelligence technology is designed. Firstly, according to the characteristics of artificial intelligence technology, intelligent teaching system, agent technology, and data mining technology are introduced in detail. Then it analyzes the overall and detailed functional requirements of the system and adaptively generates knowledge content and teaching mode suitable for students’ ability and personality by using intelligent reasoning ability and the collection and analysis of students’ personality characteristics. Through data mining of intelligent teaching system, the decision tree about curriculum is obtained, and the students’ cognitive ability is calculated. Based on the theory of cognitive science, using the “double master” teaching mode, combined with agent technology and intelligent teaching system, the system function is divided into six modules. Through the design of database structure and data table, the design of higher education system based on artificial intelligence technology is realized. The experimental results show that the proposed method has high security and response efficiency, fast running speed, and good teaching effect.

show abstract

Section: Data Mining Technologymentioning

confidence: 99%

Design of Higher Education System Based on Artificial Intelligence Technology

Li¹,

Yang

et al. 2021

Discrete Dynamics in Nature and Society

View full text Add to dashboard Cite

show abstract

“…[ 31 ] combined AdaBoost with LSTM for sea surface temperature forecasting. A gradient-boosted decision tree algorithm, based on Kalman Filter, was introduced by Li et al [ 32 ]. Boosted LSTMs were used for Internet Traffic Forecasting by Bian et al.…”

Section: Related Workmentioning

confidence: 99%

A machine learning-based model to estimate PM2.5 concentration levels in Delhi's atmosphere

Kumar

Mishra

Singh

2020

Heliyon

View full text Add to dashboard Cite

During the last many years, the air quality of the capital city of India, Delhi had been hazardous. A large number of people have been diagnosed with Asthma and other breathing-related problems. The basic reason behind this has been the high concentration of life-threatening PM2.5 particles dissolved in its atmosphere. A good model, to forecast the concentration level of these dissolved particles, may help to prepare the residents with better prevention and safety strategies in order to save them from many health-related diseases. This work aims to forecast the PM2.5 concentration levels in various regions of Delhi on an hourly basis, by applying time series analysis and regression, based on various atmospheric and surface factors such as wind speed, atmospheric temperature, pressure, etc. The data for the analysis is obtained from various weather monitoring sites, set-up in the city, by the Indian Meteorological Department (IMD). A regression model is proposed, which uses Extra-Trees regression and AdaBoost, for further boosting. Experimentation for comparative study with the recent works is done and results indicate the efficacy of the proposed model.

show abstract

“…erefore, this paper proposes a printmaking art color language analysis technology based on GP-BP neural network aesthetic paradigm, which aims to provide some help for the viewers to understand the printmaking art language. Among them, the gradient boosting (GP) algorithm is a reinforcement learning algorithm, which combines several weak learning models in the form of iterating to minimize the loss function and then forms a strong learning model, which can improve the learning accuracy [4]. BP neural network belongs to error back propagation neural network, which is composed of input layer, hidden layer, and output layer, and is widely used [5].…”

Section: Introductionmentioning

confidence: 99%

[Retracted] Analysis of Color Language and Aesthetic Paradigm of Print Art Based on GB‐BP Neural Network

Chen

Tan

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Color is the basic element of printmaking art creation and also an important medium for artists to express their emotions. In order to improve the understanding of the print by tourists, the research first carries out image analysis of different colors, summarizes the common color image adjectives in the art of publishing and painting, then optimizes BP neural network algorithm by gradient promotion (GP) algorithm, and constructs a color language analysis technology based on GP-BP neural network review paradigm. Through this technology, the content of color expression of different types of print art works is analyzed. Then, the subjective evaluation of these print art works is carried out by questionnaire adjustment method. Finally, the subjective evaluation and network evaluation results are compared. On the three materials, the expression effect of color image adjectives such as “heavy light fast,” “modern classical,” “lively steady,” and “soft Yang Gang” is consistent ( P value is greater than 0.05). The first set of print works mainly reflects the artist’s “affinity cold” emotion. The MSE values of the evaluation results are less than 0.01. That is, the color language analysis technology of print art based on GP-BP neural network can reflect the artist’s emotion to a certain extent when analyzing the color language of the print.

show abstract

Using improved gradient-boosted decision tree algorithm based on Kalman filter (GBDT-KF) in time series prediction

Cited by 45 publications

References 13 publications

Design of Higher Education System Based on Artificial Intelligence Technology

Design of Higher Education System Based on Artificial Intelligence Technology

A machine learning-based model to estimate PM2.5 concentration levels in Delhi's atmosphere

[Retracted] Analysis of Color Language and Aesthetic Paradigm of Print Art Based on GB‐BP Neural Network

Contact Info

Product

Resources

About