A Method of Speech Coding for Speech Recognition Using a Convolutional Neural Network

Kubanek, Mariusz; Bobulski, Janusz; Kulawik, Joanna

doi:10.3390/sym11091185

Cited by 31 publications

(14 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…New technologies of data collection and processing force interdisciplinary research and the need to combine existing solutions. Future large IT systems will be based on techniques that use Deep Learning, Computer Vision, Big Data and others [24,25], so new technologies should be developed that can process large amounts of data and extract useful knowledge for medical world.…”

Section: Resultsmentioning

confidence: 99%

Big Data System for Medical Images Analysis

Bobulski¹,

Kubanek²

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Big Data in medicine includes possibly fast processing of large data sets, both current and historical in purpose supporting the diagnosis and therapy of patients' diseases. Support systems for these activities may include pre-programmed rules based on data obtained from the interview medical and automatic analysis of test results diagnostic results will lead to classification of observations to a specific disease entity. The current revolution using Big Data significantly expands the role of computer science in achieving these goals, which is why we propose a Big Data computer data processing system using artificial intelligence to analyze and process medical images.

show abstract

Section: Resultsmentioning

confidence: 99%

Big Data System for Medical Images Analysis

Bobulski¹,

Kubanek²

2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Deep learning algorithms based on Artificial Neural Networks (ANN) have been recommended for processing sequential data or time-series prediction [31][32][33]. Among them, Recurrent Neural Networks (RNN) has been shown to be an effective model for time-series forecasting since this model can "remember" prior information and has been effectively applied for forecasting sequential and time-series data [34].…”

Section: Introductionmentioning

confidence: 99%

Predicting Discharges in Sewer Pipes Using an Integrated Long Short-Term Memory and Entropy A-TOPSIS Modeling Framework

Nguyen

Tornyeviadzi

Bui

et al. 2022

Water

View full text Add to dashboard Cite

Predicting discharges in sewage systems play an essential role in reducing sewer overflows and impacts on the environment and public health. Choosing a suitable model to predict discharges in these systems is essential to realizing these aforementioned goals. Long Short-Term Memory (LSTM) has been proposed as a robust technique for predicting discharges in wastewater networks. This study explored the potential application of an LSTM model to predict discharges using 3-month data set in a sewer network in Ålesund city, Norway. Different sequence-to-sequence LSTMs were investigated using various input and output datasets. The impact of data aggregation (10-min and 30-min intervals) was examined and compared to original sensor data (5-min intervals) to evaluate the performance of the LSTM model. The results show that 50-neuron LSTM architecture performed better (MAPE = 0.09, RMSE = 0.0008, R2 = 0.8) in predicting discharges for the study area. The study indicates that using the same sequence length for the prior and the forecast can improve the effectiveness of the LSTM model. Based on the results, using a 10-min aggregated discharge dataset reduces energy consumption, transmission bandwidth, and storage capacity. Additionally, it improves prediction performance compared to an original 5-min interval data in Ålesund city.

show abstract

“…[10]. Its main working principle is to use the known pixel information around the to-be-recognized area of the digital network image to fill the to-be-recognized area of the digital network image [11]. Network image recognition is different from network image filtering.…”

Section: Introductionmentioning

confidence: 99%

Analysis and Recognition Method of Internet Image Public Opinion Based on Partial Differential Equation

Zhang

2021

Advances in Mathematical Physics

View full text Add to dashboard Cite

This article comprehensively and systematically expounds the development trends and basic theory of partial differential methods, analyzes the characteristics of sampling multiscale transformation in detail, and deeply studies the network image denoising and network image restoration methods that perform partial differential diffusion in the pixel domain and the transform domain. An adaptive diffusion method of partial differential equations is proposed. Among them, the key parameters can be adaptively changed according to the curvature and gradient of the local geometric information of the network image, and the diffusion direction and intensity of the diffusion can be controlled. First, using the principle of variation, we derive the Euler equation corresponding to the diffusion method of partial differential equations and analyze its diffusion ability using the local orthogonal coordinate system of the network image. Based on the theoretical analysis of public opinion, this article applies opinion mining technology to the online public opinion early warning system to achieve the purpose of grasping the opinions of netizens in time and guiding the trend of public opinion. Opinion mining is the use of natural language processing technology to automatically extract the emotional tendencies and evaluation objects contained in the subjective text. In the edge area of the network image, the diffusion along the edge direction should have a large diffusion coefficient, and the diffusion along the vertical edge direction should have a small diffusion coefficient; in the flat area of the network image, it diffuses to the surrounding with equal intensity, and the diffusion intensity value is relatively high. Secondly, based on the analysis of the adaptive partial differential equation diffusion method, using the half-point difference format, a numerical method for network image recognition is designed. Both theoretical analysis and experimental results show that the network image recognition model based on adaptive partial differential equation diffusion is more effective than the model based on partial differential equation recognition; at the same time, experiments show that the network image recognition model based on adaptive partial differential equation diffusion is more effective than the network image recognition model based on ordinary diffusion. The network image recognition model based on constant partial differential equation diffusion is more effective in improving the quality of network image recognition.

show abstract

A Method of Speech Coding for Speech Recognition Using a Convolutional Neural Network

Cited by 31 publications

References 19 publications

Big Data System for Medical Images Analysis

Big Data System for Medical Images Analysis

Predicting Discharges in Sewer Pipes Using an Integrated Long Short-Term Memory and Entropy A-TOPSIS Modeling Framework

Analysis and Recognition Method of Internet Image Public Opinion Based on Partial Differential Equation

Contact Info

Product

Resources

About