Evaluating and selecting features via information theoretic lower bounds of feature inner correlations for high-dimensional data

Zhang, Yishi; Zhu, Ruilin; Chen, Zhijun; Gao, Jie; Xia, De

doi:10.1016/j.ejor.2020.09.028

Cited by 43 publications

(23 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first part is mainly through the establishment of the consumption-land conversion matrix [20,21]. It is relatively simple to convert the consumption of biological resources into the corresponding land area; only the embedding of the corresponding land area should be considered, that is, how much land area is needed for a given consumption quantity to produce and supply [22].…”

Section: Calculation Methods Of Ecological Footprintmentioning

confidence: 99%

Spatial–temporal calculation simulation of ecological footprint of resource and environmental pollution in green communication

Chen

Zhang

2020

J Wireless Com Network

View full text Add to dashboard Cite

As a quantitative evaluation method, the ecological footprint analysis (EFA) method is a frontier topic in the field of sustainable development. Human production activities will inevitably produce certain consumption, including the occupation of natural resources, resource consumption and waste production, which will have a certain impact on the ecological environment. This paper proposes to use the ecological footprint to inversely analyze the ecological environment and resource consumption, quantitatively convert the material consumption produced by human activities into the area of biological production land and compare it with the supply area of the study area. The EFA is used to reflect the changes in the indicators of regional sustainable development, and the regional sustainable development indicator system and analysis framework based on the ecosystem are constructed. The experimental result shows that the proposed model can effectively divide the resource space and at the same time can measure the degree of resource transfer, which has important guidance for revealing the internal relationship between regional ecological footprint characteristics and regional development and evolution significance.

show abstract

Section: Calculation Methods Of Ecological Footprintmentioning

confidence: 99%

Spatial–temporal calculation simulation of ecological footprint of resource and environmental pollution in green communication

Chen

Zhang

2020

J Wireless Com Network

View full text Add to dashboard Cite

show abstract

“…Among them, the platform basic information maintenance functions include platform initialization, data dictionary recovery, and database backup and restore. Platform initialization includes initialization of platform default settings and creation of some necessary folders [20]; data dictionary recovery is to prevent the platform from running abnormally due to malicious tampering with the original data in the database; the course review function allows the administrator to review the course applied by the teacher. The course review status includes pending review, pass, and fail.…”

Section: Background Functionmentioning

confidence: 99%

Emerging Applications of Blockchain Technology on a Virtual Platform for English Teaching and Learning

Wang

Qiao

2020

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

To extend a broad application of blockchain technology to the fields of online English education, this paper aims to improve a virtual platform for English teaching and learning of landscape design majors, mainly composed of presentation layer, business layer, and data layer by analyzing the performance of the proposed algorithm, and comparing with other existing algorithms. In the platform, through the service layer, the communication between the presentation layer and the data layer is completed, and the data in the data layer is transferred to the presentation layer. The user first establishes a connection with the server in the presentation layer. Using the transmitted data information, the server assigns an identifier to the user and establishes a role model. Users can download the teaching courseware through the server and simulate the real learning scene by controlling the interaction of XAML files. The results show that the virtual teaching platform makes the interconnection of users (students and teachers), machines, and things at any time and any place; realizes information self-verification, transmission, deep unsupervised learning, and management; and gives students a more realistic visual experience in high security.

show abstract

“…When analyzing the impact of investor sentiment on the stock market in the above-mentioned research, the news sources selected can often only represent one party (the investor or the government) and cannot reflect the information interaction between both parties [26,27]. In terms of methods applied, machine learning-based models are more commonly used in the literature [28][29][30]. Although machine learning model-based methods can fuse multiple information sources, the research on the mechanism of mutual influence between information is not sufficient.…”

Section: Related Workmentioning

confidence: 99%

Modeling and Prediction of Stock Price with Convolutional Neural Network Based on Blockchain Interactive Information

Zhang

Tao

et al. 2020

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

The interactive information in blockchain architecture establishes an effective communication channel between users and enterprises, enabling them to communicate in a comprehensive and effective manner. Therefore, taking blockchain interactive information as the research object, this paper explores how the intervention of official information on investors affects the stock price movement and then makes predictions on stock prices according to the emotional tendency of interactive information. With the contextual information fusion, a sentiment computing model based on a convolutional neural network is established to extract and quantify the emotional features of blockchain interactive information. Combined with investors’ emotional features, the stock price prediction model based on long short-term memory is proposed. The experiment results show that the accuracy of the model has been improved by incorporating the intervened emotional features, thereby proving that information clarification can have a positive effect on the stock price.

show abstract

Evaluating and selecting features via information theoretic lower bounds of feature inner correlations for high-dimensional data

Cited by 43 publications

References 46 publications

Spatial–temporal calculation simulation of ecological footprint of resource and environmental pollution in green communication

Spatial–temporal calculation simulation of ecological footprint of resource and environmental pollution in green communication

Emerging Applications of Blockchain Technology on a Virtual Platform for English Teaching and Learning

Modeling and Prediction of Stock Price with Convolutional Neural Network Based on Blockchain Interactive Information

Contact Info

Product

Resources

About