Short-term local weather forecast using dense weather station by deep neural network

2018 ◽  
Author(s):  
Kazuo Yonekura ◽  
Hitoshi Hattori ◽  
Taiji Suzuki
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Weather Forecast ◽  
Weather Station ◽  
Short Term ◽  
Local Weather

Wind Power Forecasting Based on the BP Neural Network

2013 ◽  
Vol 341-342 ◽  
pp. 1303-1307 ◽  
Author(s):  
Jian Dong Mao ◽  
Xiao Jing Zhang ◽  
Juan Li
Keyword(s):  
Neural Network ◽  
Wind Power ◽  
Bp Neural Network ◽  
Engineering Application ◽  
Weather Forecast ◽  
Difficult Problem ◽  
Short Term ◽  
Wind Power Forecasting ◽  
Forecasting System ◽  
Power Forecasting

Accurate short-term wind power forecasting has important significance to safety, stability and economy of power system dispatching and also it is a difficult problem in practical engineering application. In this paper, by use of the data of numerical weather forecast, such as wind speed, wind direction, temperature, relative humidity and pressure of atmosphere, a short-term wind power forecasting system based on BP neural network has been developed. For verifying the feasibility of the system, some experiments have been were carried out. The results show that the system is capable of predicting accurately the wind power of future 24 hours and the forecasting accuracy of 85.6% is obtained. The work of this paper has important engineering directive significance to the similar wind power forecasting system.

scholarly journals Sound Levels Forecasting in an Acoustic Sensor Network Using a Deep Neural Network

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 903 ◽  
Author(s):  
Juan M. Navarro ◽  
Raquel Martínez-España ◽  
Andrés Bueno-Crespo ◽  
Ramón Martínez ◽  
José M. Cecilia
Keyword(s):  
Neural Network ◽  
Sensor Network ◽  
Sound Pressure Level ◽  
Deep Neural Network ◽  
Sound Pressure ◽  
Noise Pollution ◽  
Pressure Level ◽  
Acoustic Sensor ◽  
Short Term ◽  
Sound Levels

Wireless acoustic sensor networks are nowadays an essential tool for noise pollution monitoring and managing in cities. The increased computing capacity of the nodes that create the network is allowing the addition of processing algorithms and artificial intelligence that provide more information about the sound sources and environment, e.g., detect sound events or calculate loudness. Several models to predict sound pressure levels in cities are available, mainly road, railway and aerial traffic noise. However, these models are mostly based in auxiliary data, e.g., vehicles flow or street geometry, and predict equivalent levels for a temporal long-term. Therefore, forecasting of temporal short-term sound levels could be a helpful tool for urban planners and managers. In this work, a Long Short-Term Memory (LSTM) deep neural network technique is proposed to model temporal behavior of sound levels at a certain location, both sound pressure level and loudness level, in order to predict near-time future values. The proposed technique can be trained for and integrated in every node of a sensor network to provide novel functionalities, e.g., a method of early warning against noise pollution and of backup in case of node or network malfunction. To validate this approach, one-minute period equivalent sound levels, captured in a two-month measurement campaign by a node of a deployed network of acoustic sensors, have been used to train it and to obtain different forecasting models. Assessments of the developed LSTM models and Auto regressive integrated moving average models were performed to predict sound levels for several time periods, from 1 to 60 min. Comparison of the results show that the LSTM models outperform the statistics-based models. In general, the LSTM models achieve a prediction of values with a mean square error less than 4.3 dB for sound pressure level and less than 2 phons for loudness. Moreover, the goodness of fit of the LSTM models and the behavior pattern of the data in terms of prediction of sound levels are satisfactory.

scholarly journals A Novel Stock Index Intelligent Prediction Algorithm Based on Attention-Guided Deep Neural Network

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Yangzi Zhao
Keyword(s):  
Neural Network ◽  
Stock Market ◽  
Deep Neural Network ◽  
Short Term Memory ◽  
Stock Index ◽  
Prediction Algorithm ◽  
Short Term ◽  
Term Memory ◽  
Model Based

The stock market is affected by economic market, policy, and other factors, and its internal change law is extremely complex. With the rapid development of the stock market and the expansion of the scale of investors, the stock market has produced a large number of transaction data, which makes it more difficult to obtain valuable information. Because deep neural network is good at dealing with the prediction problems with large amount of data and complex nonlinear mapping relationship, this paper proposes an attention-guided deep neural network stock prediction algorithm. This paper synthesizes the daily stock social media text emotion index and stock technology index as the data source and applies them to the long-term and short-term memory neural network (LSTM) model to predict the stock market. The stock emotion index is extracted by constructing a social text classification emotion model of bidirectional long-term and short-term memory neural network (Bi-LSTM) based on attention mechanism and glove word vector representation algorithm. In addition, a dimensionality reduction model based on decision tree (DT) and principal component analysis (PCA) is constructed to reduce the dimensionality of stock technical indicators and extract the main data information. Furthermore, this paper proposes a model based on nasNet for pattern recognition. The recognition results can be used to automatically identify short-term K-line patterns, predict reliable trading signals, and help investors customize short-term high-efficiency investment strategies. The experimental results show that the prediction accuracy of the proposed algorithm can reach 98.6%, which has high application value.

scholarly journals Separating overlapping bat calls with a bi-directional long short-term memory network

2019 ◽  
Author(s):  
Kangkang Zhang ◽  
Tong Liu ◽  
Shengjing Song ◽  
Xin Zhao ◽  
Shijun Sun ◽  
...  
Keyword(s):  
Neural Network ◽  
Clustering Analysis ◽  
Deep Neural Network ◽  
Short Term Memory ◽  
Short Term ◽  
Term Memory ◽  
Echolocation Calls ◽  
Significant Difference ◽  
Long Short Term Memory ◽  
Sound Data

AbstractAcquiring clear and usable audio recordings is critical for acoustic analysis of animal vocalizations. Bioacoustics studies commonly face the problem of overlapping signals, but the issue is often ignored, as there is currently no satisfactory solution. This study presents a bi-directional long short-term memory (BLSTM) network to separate overlapping bat calls and reconstruct waveform audio sounds. The separation quality was evaluated using seven temporal-spectrum parameters. The applicability of this method for bat calls was assessed using six different species. In addition, clustering analysis was conducted with separated echolocation calls from each population. Results showed that all syllables in the overlapping calls were separated with high robustness across species. A comparison between the seven temporal-spectrum parameters showed no significant difference and negligible deviation between the extracted and original calls, indicating high separation quality. Clustering analysis of the separated echolocation calls also produced an accuracy of 93.8%, suggesting the reconstructed waveform sounds could be reliably used. These results suggest the proposed technique is a convenient and automated approach for separating overlapping calls using a BLSTM network. This powerful deep neural network approach has the potential to solve complex problems in bioacoustics.Author summaryIn recent years, the development of recording techniques and devices in animal acoustic experiment and population monitoring has led to a sharp increase in the volume of sound data. However, the collected sound would be overlapped because of the existence of multiple individuals, which laid restrictions on taking full advantage of experiment data. Besides, more convenient and automatic methods are needed to cope with the large datasets in animal acoustics. The echolocation calls and communication calls of bats are variable and often overlapped with each other both in the recordings from field and laboratory, which provides an excellent template for research on animal sound separation. Here, we firstly solved the problem of overlapping calls in bats successfully based on deep neural network. We built a network to separate the overlapping calls of six bat species. All the syllables in overlapping calls were separated and we found no significant difference between the separated syllables with non-overlapping syllables. We also demonstrated an instance of applying our method on species classification. Our study provides a useful and efficient model for sound data processing in acoustic research and the proposed method has the potential to be generalized to other animal species.

Sign in / Sign up

Export Citation Format

Share Document