scholarly journals Combination of SOM-RBF for drought code prediction using rainfall and air temperature data

2019 ◽  
Vol 8 (1) ◽  
pp. 64-68
Author(s):  
Dwi Marisa Midyanti
Keyword(s):  
Air Temperature ◽  
Temperature Data ◽  
Detection Accuracy ◽  
Rbf Network ◽  
Network Training ◽  
Learning Rates ◽  
Weight Value ◽  
Final Weight ◽  
Hidden Layer ◽  
Number Of Iterations

This study aims to predict Drought Code (DC) in Kabupaten Kubu Raya using a combination of SOM-RBF. The final weight value of SOM was used as a center on the RBF network. The input data variables are rainfall data and air temperature data for three days with three binary outputs to predict DC values. This study also observed the effect of the number of neurons, learning rates, and the number of iterations on the results of the SOM-RBF network training. The smallest MSE of training result from the SOM-RBF network was 0.159933 using 65 neurons in the hidden layer, learning rate 0.007, and epoch 45000. The detection accuracy of SOM-RBF was 91.34 % from 245 test data.

An Effective Solution to Regression Problem by RBF Neuron Network

2015 ◽  
Vol 6 (4) ◽  
pp. 57-74 ◽  
Author(s):  
Dang Thi Thu Hien ◽  
Hoang Xuan Huan ◽  
Le Xuan Minh Hoang
Keyword(s):  
Regression Function ◽  
Training Data ◽  
Neuron Network ◽  
Open Problems ◽  
Regression Problem ◽  
Rbf Network ◽  
Network Training ◽  
Hidden Layer ◽  
Definition Of ◽  
Selection Of

Radial Basis Function (RBF) neuron network is being applied widely in multivariate function regression. However, selection of neuron number for hidden layer and definition of suitable centre in order to produce a good regression network are still open problems which have been researched by many people. This article proposes to apply grid equally space nodes as the centre of hidden layer. Then, the authors use k-nearest neighbour method to define the value of regression function at the center and an interpolation RBF network training algorithm with equally spaced nodes to train the network. The experiments show the outstanding efficiency of regression function when the training data has Gauss white noise.

scholarly journals Hardware implementation of radial-basis neural networks with Gaussian activation functions on FPGA

2021 ◽  
Author(s):  
Volodymyr Shymkovych ◽  
Sergii Telenyk ◽  
Petro Kravets
Keyword(s):  
Neural Networks ◽  
Hardware Implementation ◽  
Gaussian Function ◽  
Activation Function ◽  
Rbf Neural Networks ◽  
Activation Functions ◽  
Rbf Network ◽  
Combination Scheme ◽  
Radial Basis ◽  
Hidden Layer

AbstractThis article introduces a method for realizing the Gaussian activation function of radial-basis (RBF) neural networks with their hardware implementation on field-programmable gaits area (FPGAs). The results of modeling of the Gaussian function on FPGA chips of different families have been presented. RBF neural networks of various topologies have been synthesized and investigated. The hardware component implemented by this algorithm is an RBF neural network with four neurons of the latent layer and one neuron with a sigmoid activation function on an FPGA using 16-bit numbers with a fixed point, which took 1193 logic matrix gate (LUTs—LookUpTable). Each hidden layer neuron of the RBF network is designed on an FPGA as a separate computing unit. The speed as a total delay of the combination scheme of the block RBF network was 101.579 ns. The implementation of the Gaussian activation functions of the hidden layer of the RBF network occupies 106 LUTs, and the speed of the Gaussian activation functions is 29.33 ns. The absolute error is ± 0.005. The Spartan 3 family of chips for modeling has been used to get these results. Modeling on chips of other series has been also introduced in the article. RBF neural networks of various topologies have been synthesized and investigated. Hardware implementation of RBF neural networks with such speed allows them to be used in real-time control systems for high-speed objects.

scholarly journals On the Spatial Patterns of Urban Thermal Conditions Using Indoor and Outdoor Temperatures

2021 ◽  
Vol 13 (4) ◽  
pp. 640
Author(s):  
Sadroddin Alavipanah ◽  
Dagmar Haase ◽  
Mohsen Makki ◽  
Mir Muhammad Nizamani ◽  
Salman Qureshi
Keyword(s):  
Heat Stress ◽  
Air Temperature ◽  
Temperature Data ◽  
Cold Spot ◽  
Temperature Pattern ◽  
Outdoor Temperature ◽  
Residential Units ◽  
Urban Settlements ◽  
The Impact ◽  
Indoor And Outdoor

The changing climate has introduced new and unique challenges and threats to humans and their environment. Urban dwellers in particular have suffered from increased levels of heat stress, and the situation is predicted to continue to worsen in the future. Attention toward urban climate change adaptation has increased more than ever before, but previous studies have focused on indoor and outdoor temperature patterns separately. The objective of this research is to assess the indoor and outdoor temperature patterns of different urban settlements. Remote sensing data, together with air temperature data collected with temperature data loggers, were used to analyze land surface temperature (outdoor temperature) and air temperature (indoor temperature). A hot and cold spot analysis was performed to identify the statistically significant clusters of high and low temperature data. The results showed a distinct temperature pattern across different residential units. Districts with dense urban settlements show a warmer outdoor temperature than do more sparsely developed districts. Dense urban settlements show cooler indoor temperatures during the day and night, while newly built districts show cooler outdoor temperatures during the warm season. Understanding indoor and outdoor temperature patterns simultaneously could help to better identify districts that are vulnerable to heat stress in each city. Recognizing vulnerable districts could minimize the impact of heat stress on inhabitants.

scholarly journals A Geometric Perspective on Information Plane Analysis

Entropy ◽  
2021 ◽  
Vol 23 (6) ◽  
pp. 711
Author(s):  
Mina Basirat ◽  
Bernhard C. Geiger ◽  
Peter M. Roth
Keyword(s):  
Neural Network ◽  
Mutual Information ◽  
Geometric Interpretation ◽  
Neural Network Training ◽  
Neural Network Learning ◽  
Network Learning ◽  
Plane Analysis ◽  
Network Training ◽  
Hidden Layer ◽  
The Impact

Information plane analysis, describing the mutual information between the input and a hidden layer and between a hidden layer and the target over time, has recently been proposed to analyze the training of neural networks. Since the activations of a hidden layer are typically continuous-valued, this mutual information cannot be computed analytically and must thus be estimated, resulting in apparently inconsistent or even contradicting results in the literature. The goal of this paper is to demonstrate how information plane analysis can still be a valuable tool for analyzing neural network training. To this end, we complement the prevailing binning estimator for mutual information with a geometric interpretation. With this geometric interpretation in mind, we evaluate the impact of regularization and interpret phenomena such as underfitting and overfitting. In addition, we investigate neural network learning in the presence of noisy data and noisy labels.

scholarly journals <i>Brief communication</i> "A statistical validation for the cycles found in air temperature data using a Morlet wavelet-based method"

2010 ◽  
Vol 17 (3) ◽  
pp. 269-272 ◽  
Author(s):  
S. Nicolay ◽  
G. Mabille ◽  
X. Fettweis ◽  
M. Erpicum
Keyword(s):  
Air Temperature ◽  
Climate Model ◽  
Surface Air Temperature ◽  
Weather Forecast ◽  
Temperature Data ◽  
Temperature Time Series ◽  
Climatic Data ◽  
Statistical Validation ◽  
Confidence Levels ◽  
Temperature Time

Abstract. Recently, new cycles, associated with periods of 30 and 43 months, respectively, have been observed by the authors in surface air temperature time series, using a wavelet-based methodology. Although many evidences attest the validity of this method applied to climatic data, no systematic study of its efficiency has been carried out. Here, we estimate confidence levels for this approach and show that the observed cycles are significant. Taking these cycles into consideration should prove helpful in increasing the accuracy of the climate model projections of climate change and weather forecast.

scholarly journals Historical and future temporal trends in the summer Urban Heat Island of Athens (Greece) 

2021 ◽  
Author(s):  
Tim van der Schriek ◽  
Konstantinos V. Varotsos ◽  
Dimitra Founda ◽  
Christos Giannakopoulos
Keyword(s):  
Climate Change ◽  
Air Pollution ◽  
Air Temperature ◽  
Temporal Trends ◽  
Temperature Data ◽  
Climate Change Scenarios ◽  
Heat Island ◽  
Hot Days ◽  
The Future ◽  
Urban Heat

&lt;p&gt;Historical changes, spanning 1971&amp;#8211;2016, in the Athens Urban Heat Island (UHI) over summer were assessed by contrasting two air temperature records from established meteorological stations in urban and rural settings. When contrasting two 20-year historical periods (1976&amp;#8211;1995 and 1996&amp;#8211;2015), there is a significant difference in summer UHI regimes. The stronger UHI-intensity of the second period (1996&amp;#8211;2015) is likely linked to increased pollution and heat input. Observations suggest that the Athens summer UHI characteristics even fluctuate on multi-annual basis. Specifically, the reduction in air pollution during the Greek Economic Recession (2008-2016) probable subtly changed the UHI regime, through lowering the frequencies of extremely hot days (T&lt;sub&gt;max&lt;/sub&gt; &gt; 37 &amp;#176;C) and nights (T&lt;sub&gt;min&lt;/sub&gt; &gt; 26 &amp;#176;C).&lt;/p&gt;&lt;p&gt;Subsequently, we examined the future temporal trends of two different UHIs in Athens (Greece) under three climate change scenarios. A five-member regional climate model (RCM) sub-ensemble from EURO-CORDEX with a horizontal resolution of 0.11&amp;#176; (~12 &amp;#215; 12 km) simulated air temperature data, spanning the period 1976&amp;#8211;2100, for the two station sites. Three future emissions scenarios (RCP2.6, RCP4.5 and RCP8.5) were implanted in the simulations after 2005. The observed daily maximum and minimum air temperature data (T&lt;sub&gt;max&lt;/sub&gt; and T&lt;sub&gt;min&lt;/sub&gt;) from two historical UHI regimes (1976&amp;#8211;1995 and 1996&amp;#8211;2015, respectively) were used, separately, to bias-adjust the model simulations thus creating two sets of results.&lt;/p&gt;&lt;p&gt;This novel approach allowed us to assess future temperature developments in Athens under two different UHI intensity regimes. We found that the future frequency of days with T&lt;sub&gt;max&lt;/sub&gt; &gt; 37 &amp;#176;C in Athens was only different from rural background values under the intense UHI regime. There is a large increase in the future frequency of nights with T&lt;sub&gt;min&lt;/sub&gt; &gt; 26 &amp;#176;C in Athens under all UHI regimes and climate scenarios; these events remain comparatively rare at the rural site.&lt;/p&gt;&lt;p&gt;This study shows a large urban amplification of the frequency of extremely hot days and nights which is likely forced by increasing air pollution and heat input. Consequently, local mitigation policies aimed at decreasing urban atmospheric pollution are expected to be also effective in reducing urban temperatures during extreme heat events in Athens under all future climate change scenarios. Such policies therefore have multiple benefits, including: reducing electricity (energy) needs, improving living quality and decreasing heat- and pollution related illnesses/deaths.&lt;/p&gt;&lt;p&gt;&amp;#160;&lt;/p&gt;

scholarly journals Increase in Air Temperature in The Region of South Sumatra Province as the Indicator of Global Warming and the Effect on Transpiration of Lansium domesticum Corr.

2019 ◽  
Author(s):  
Ari Sugiarto ◽  
Hanifa Marisa ◽  
Sarno
Keyword(s):  
Global Warming ◽  
Air Temperature ◽  
Transpiration Rate ◽  
Temperature Increase ◽  
Secondary Data ◽  
Temperature Data ◽  
Randomized Design ◽  
Maximum Air Temperature ◽  
Lansium Domesticum ◽  
Minimum Air Temperature

Abstract Global warming is one of biggest problems faced in the 21st century. One of the impacts of global warming is that it can affect the transpiration rate of plants that °Ccur. This study purpose to see how much increase in air temperature that occurred in the region of South Sumatra Province and to know the effect of increase in ari temperature in the region of South Sumatra Province on transpiration rate of Lansium domesticum Corr. This study used a complete randomized design with 9 treatments (22.9 °C, 23.6 °C, 24.6 °C, 26.3 °C, 27 °C, 27.8 °C, 31.7 °C, 32.5 °C, and 32.9 °C) and 3 replications. Air temperature data as secondary data obtained from the Meteorology, Climatology and Geophysics Agency (MCGA) Palembang Climatology Station in South Sumatra Province. The measurement of transpiration rate is done by modified potometer method with additional glass box. The data obtained are presented in the form of tables and graphs. Transpiration rate (mm3/g plant/hour) at temperture 22.9 °C = 4.37, 23.6 °C = 7.03, 24.6 °C = 8.03, 26.3 °C = 10.11, 27 °C = 13.13, 27.8 °C = 17.87, 31.7 °C = 23.21, 32.5 °C= 25.45 and 32.9 °C= 27.24. At the minimum air temperature in the region of South Sumatra Province there is increase in air temperature of 1.5 °C, average daily air temperature increase 1.3 °C and maximum air temperature increase 1.2 °C.

scholarly journals Financial Time Series Image Algorithm Based on Wavelet Analysis and Data Fusion

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Wuwei Liu ◽  
Jingdong Yan
Keyword(s):  
Time Series ◽  
Wavelet Transform ◽  
Mean Square Error ◽  
Financial Time Series ◽  
Prediction Method ◽  
Mean Square ◽  
Rbf Network ◽  
Network Prediction ◽  
The Mean ◽  
Hidden Layer

In recent years, people are more and more interested in time series modeling and its application in prediction. This paper mainly discusses a financial time series image algorithm based on wavelet analysis and data fusion. In this research, we conducted an in-depth study on the scale decomposition sequence and wavelet transform sequence in different scale domains of wavelet transform according to the scale change rule based on wavelet transform. We use wavelet neural network with different input neurons and hidden neurons to predict, respectively. Finally, the prediction results are integrated into the final prediction results based on the original time series by using wavelet reconstruction technology. Using RBF algorithm in neural network and SPSS Clementine, the wavelet transform sequences on five scales are modeled. Each network model has three layers: one input layer, one hidden layer, and one output layer, and each output layer has only one output element. In order to compare the prediction effect of the model proposed in this study, the ordinary RBF network is used to model and predict the log yield itself. When the input sample is 5, the minimum mean square error is obtained when the hidden layer is 6, and the mean square error is 1.6349. The mean square error of the training phase is 0.0209, and the validation error is 1.6141. The results show that the prediction results of the wavelet prediction method combined with the RBF network prediction method are better than those of wavelet prediction or RBF network prediction.

Fault Diagnosis Analysis of Rotor System Based on RBF Neural Network and Dynamic Systems

2012 ◽  
Vol 460 ◽  
pp. 127-130
Author(s):  
Song He Zhang ◽  
Yue Gang Luo ◽  
Bin Wu ◽  
Bing Cheng Wang
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Rbf Neural Network ◽  
Amplitude Spectrum ◽  
Rates Of Convergence ◽  
Rotor System ◽  
Rbf Network ◽  
Characteristic Quantity ◽  
Learning Rates ◽  
Fault Characteristic

The RBF network was applied in the rotor system to realize the fault diagnosis aiming the mapping complexity between fault symptoms and fault patterns. It can overcome the problems of low learning rates of convergence and falling easily into part minimums in BP algorithm, and improve the precision of diagnosis. The normalized values of seven frequency ranges in amplitude spectrum were used as the fault characteristic quantity, the RBF network was trained to diagnose the faults of rotor system. The results show that RBF neural network is a valid method of diagnosis of mechanical failure.

Sign in / Sign up

Export Citation Format

Share Document