PFVAE: A Planar Flow-Based Variational Auto-Encoder Prediction Model for Time Series Data

Jin, Xue-Bo; Gong, Wen-Tao; Kong, Jianlei; Bai, Yuting; Su, Tingli

doi:10.3390/math10040610

Cited by 104 publications

(60 citation statements)

References 90 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The prediction and verification experiment of Beijing air quality data, considering the indicators such as RMSE, MSE, and MAE, shows that the model is superior to other models in terms of prediction accuracy and calculation speed. The proposed prediction approaches of time-series models in the paper can combine other parameter estimation algorithms [52][53][54][55][56][57][58] with studying the parameter identification problems of linear and nonlinear systems with different disturbances [59][60][61][62][63][64] to build soft sensor models and prediction models based on time-series data that can be applied to other fields [65][66][67][68][69][70] such as signal processing and engineering application systems [71][72][73][74][75][76][77][78].…”

Section: Discussionmentioning

confidence: 99%

A Variational Bayesian Deep Network with Data Self-Screening Layer for Massive Time-Series Data Forecasting

Jin

Gong

Kong

et al. 2022

Entropy

Self Cite

View full text Add to dashboard Cite

Compared with mechanism-based modeling methods, data-driven modeling based on big data has become a popular research field in recent years because of its applicability. However, it is not always better to have more data when building a forecasting model in practical areas. Due to the noise and conflict, redundancy, and inconsistency of big time-series data, the forecasting accuracy may reduce on the contrary. This paper proposes a deep network by selecting and understanding data to improve performance. Firstly, a data self-screening layer (DSSL) with a maximal information distance coefficient (MIDC) is designed to filter input data with high correlation and low redundancy; then, a variational Bayesian gated recurrent unit (VBGRU) is used to improve the anti-noise ability and robustness of the model. Beijing’s air quality and meteorological data are conducted in a verification experiment of 24 h PM2.5 concentration forecasting, proving that the proposed model is superior to other models in accuracy.

show abstract

Section: Discussionmentioning

confidence: 99%

A Variational Bayesian Deep Network with Data Self-Screening Layer for Massive Time-Series Data Forecasting

Jin

Gong

Kong

et al. 2022

Entropy

Self Cite

View full text Add to dashboard Cite

show abstract

“…The criteria for the decomposition are effective and practical, which can help the automatic feature extraction of the time series. In the future, we will further investigate non-stationary time series forecasting [40][41][42][43][44], including optimization methods for decomposition models and multi-model fusion methods [45][46][47].…”

Section: Discussionmentioning

confidence: 99%

Deep Prediction Model Based on Dual Decomposition with Entropy and Frequency Statistics for Nonstationary Time Series

Shi

Bai

Wang

et al. 2022

Entropy

Self Cite

View full text Add to dashboard Cite

The prediction of time series is of great significance for rational planning and risk prevention. However, time series data in various natural and artificial systems are nonstationary and complex, which makes them difficult to predict. An improved deep prediction method is proposed herein based on the dual variational mode decomposition of a nonstationary time series. First, criteria were determined based on information entropy and frequency statistics to determine the quantity of components in the variational mode decomposition, including the number of subsequences and the conditions for dual decomposition. Second, a deep prediction model was built for the subsequences obtained after the dual decomposition. Third, a general framework was proposed to integrate the data decomposition and deep prediction models. The method was verified on practical time series data with some contrast methods. The results show that it performed better than single deep network and traditional decomposition methods. The proposed method can effectively extract the characteristics of a nonstationary time series and obtain reliable prediction results.

show abstract

“…Voice Feature Recognition Database. Any artificial intelligence application field [23] requires database support, and the quality of the pathological voice database has a direct impact on the classification effect of experiments. There is no standardized method for recognizing and extracting voice features.…”

Section: Building Amentioning

confidence: 99%

Teacher Voice Feature Extraction and Recognition Based on Health Belief Model

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Teachers are professional voice workers who complete their education and teaching tasks primarily through spoken English. Teachers’ voices are the most important tool for completing their professional tasks, as well as an important part of their public image. This paper proposes innovative design strategies with health management as the core concept, in light of the voice health problems of primary and secondary school teachers in the era of intelligence. For a long time, China has had a high percentage of teachers with voice problems. Teachers’ oral English expression is affected by voice diseases, which reduces teaching efficiency. Teachers’ physical and mental health are also jeopardized, and their professional identities are diminished. It is primarily caused by a lack of health-care awareness, excessive use of voice in daily life, incorrect vocalization techniques, a lack of knowledge and methods for voice protection, and ignorance on the part of education management departments. As a result, we must reduce the frequency with which we use our voices and employ scientific feature recognition methods to protect our voices.

show abstract

PFVAE: A Planar Flow-Based Variational Auto-Encoder Prediction Model for Time Series Data

Cited by 104 publications

References 90 publications

A Variational Bayesian Deep Network with Data Self-Screening Layer for Massive Time-Series Data Forecasting

A Variational Bayesian Deep Network with Data Self-Screening Layer for Massive Time-Series Data Forecasting

Deep Prediction Model Based on Dual Decomposition with Entropy and Frequency Statistics for Nonstationary Time Series

Teacher Voice Feature Extraction and Recognition Based on Health Belief Model

Contact Info

Product

Resources

About