scholarly journals ANALISIS SPEKTRAL DALAM PENENTUAN PERIODISITAS SIKLUS CURAH HUJAN DI WILAYAH SELATAN JATILUHUR, KABUPATEN SUBANG, JAWA BARAT

2016 ◽  
Vol 36 (01) ◽  
pp. 89
Author(s):  
Dyah Susilokarti ◽  
Sigit Supadmo Arif ◽  
Sahid Susanto ◽  
Lilik Sutiarso
Keyword(s):  
Fourier Transform ◽  
Mean Square Error ◽  
Rainfall Data ◽  
Mean Square ◽  
Ann Model ◽  
Rainfall Prediction ◽  
Fourier Trans ◽  
Fast Fourier Trans ◽  
The Difference ◽  
The Time Domain

Rainfall data was studied to know how rainfall in the region has a span of time to form a repetitive pattern. The cycle is a change or a wave up and down within a period and repeated at other periods. The cycle has a frequency that can be completed in one period of time. Fourier transform is an algorithm to convert the time domain X to the domain or the frequency spectrum Y, by breaking the signal into a sinusoidal component. This study used the Fast Fourier Transform (FFT) to find the nature of the trend recurrence of rainfall in the southern region of Jatiluhur Subang. Simulation model was done using monthly rainfall data 1975 - 2012. The results showed a trend of rainfall in the study area was repeated every 12 months (1 cycle). Rainfall prediction was done by using a 5-year rainfall data and used the data observation of the next 5 years as a comparison result predicted to see the performance. Performance prediction was resulted using the Mean Square Error (MSE) used to obtain the difference between the standard derivation calculation of observed data and data modeling. The results of the analysis at the time of validation of the model was MSE    14.92 with a 95% confidence level. FFT used to calculate the value of the error (the difference between the values calculated by the ANN model and observed data) resulted in the change cycle of rainfall occurs over a period of months or approximately 71.68 months or 5-6 years.Keywords:  Rain!all, prediction, Fast Fourier Trans!orm (FFT), Mean Square Error (MSE), Subang District ABSTRAKData curah hujan dipelajari salah satunya untuk mengetahui bagaimana curah hujan di suatu wilayah mempunyai rentang waktu untuk membentuk suatu pola berulang. Siklus merupakan suatu perubahan atau gelombang naik dan turun dalam suatu periode serta berulang pada periode lain. Siklus mempunyai frekuensi yang dapat diselesaikan dalam 1 periode waktu. Transformasi Fourier merupakan algoritma untuk mengubah domain waktu X menjadi domain atau spectrum frekuensi Y, dengan cara menguraikan sinyal menjadi komponen sinusoidal.  Penelitian ini menggunakan metode Fast Fourier Trans!orm (FFT) untuk mencari sifat berulangnya trend curah hujan di wilayah selatan Jatiluhur Kabupaten Subang. Simulasi model menggunakan data curah hujan bulanan tahun 1975 - 2012. Hasilnya menunjukkan trend curah hujan di lokasi penelitian berulang setiap 12 bulan sekali (1 siklus). Prediksi curah hujan dilakukan dengan menggunakan data curah hujan 5 tahun dan menggunakan observasi data 5 tahun berikutnya sebagai pembanding hasil prediksi untuk melihat performa yang dihasilkan. Performa hasil prediksi menggunakan Mean Square Error (MSE) sebagai standar perhitungan derivasi perbedaaan antara data real dan data pemodelan. Hasil analisis pada saat validasi model didapatkan MSE    14,92 dengan tingkat kepercayaan 95%. Dengan menggunakan analisis FFT untuk menghitung nilai error (perbedaan antara nilai perhitungan model ANN dengan data sebenarnya), diperoleh perubahan siklus curah hujan terjadi dalam kurun waktu 71,68 bulan atau sekitar 5-6 tahun.Kata kunci:  Curah hujan, prediksi, Fast Fourier Trans!orm (FFT), Mean Square Error (MSE), Kabupaten Subang

Time Series Based House Sale Value Market Forecasting Using Genetically Evolved Neural Networks

2010 ◽  
pp. 265-282
Author(s):  
George S. Atsalakis ◽  
Kimon P. Valavanis ◽  
Constantin Zopounidis ◽  
Dimitris Nezis
Keyword(s):  
Neural Networks ◽  
Linear Regression ◽  
Mean Square Error ◽  
Fuzzy Inference ◽  
Housing Prices ◽  
Individual Investors ◽  
Mean Square ◽  
Ann Model ◽  
Neuro Fuzzy ◽  
Proposed Model

Accurate forecasting of the house sale value market is important for individual investors, business investors, banks and mortgage companies. This chapter uses fundamentals of Genetic Algorithms (GAs) and Artificial Neural Networks (ANNs) to derive and implement a hybrid, genetically evolved feedforward ANN model that predicts next month house sale prices. Derived model results are compared with results obtained using a linear regression model and an Adaptive Neuro Fuzzy Inference System (ANFIS). The proposed model returned lower Root Mean Square Error (RMSE), Absolute Mean Error (MAE), Mean Square Error (MSE) and Mean Absolute Percent Error (MAPE) results compared with the linear regression and ANFIS models. For case studies real monthly data of USA housing prices from 1963 to 2007 were used.

Time-Domain Filtering of Two-Dimensional Fluorescence Data

1986 ◽  
Vol 40 (4) ◽  
pp. 542-548 ◽  
Author(s):  
Maria Vicsek ◽  
Sharon L. Neal ◽  
Isiah M. Warner
Keyword(s):  
Error Analysis ◽  
Mean Square Error ◽  
Time Domain ◽  
Moving Average ◽  
Mean Square ◽  
Two Dimensional ◽  
Spline Method ◽  
Dimensional Version ◽  
The Difference ◽  
Polynomial Smoothing

Four time-domain filtering methods are applied to simulated and experimental two-dimensional fluorescence data in order to evaluate their performance. The methods that were evaluated are (1) moving average, (2) Savitsky-Golay polynomial smoothing, (3) Chebyshev filtering, and (4) bicubic spline filtering. The methods are compared with the use of mean square error analysis and the difference in the amplitudes of the filtered noisy and ideal data. The two-dimensional version of the Savitzky-Golay filtering and the spline method produced the best overall results.

Modeling of Phenol Degradation in Spouted Bed Contactor Using Artificial Neural Network (ANN)

2008 ◽  
Vol 3 (2) ◽  
Author(s):  
Madhukar A. Dabhade ◽  
M. B. Saidutta ◽  
D. V. R. Murthy
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Mean Square Error ◽  
Model Prediction ◽  
Phenol Degradation ◽  
Mean Square ◽  
Ann Model ◽  
Spouted Bed ◽  
The Mean ◽  
Artificial Neural Network Ann

Presence of phenol and phenolic compounds in various wastewaters and its harmful effects has led to the use of different treatment methods. Work on biological methods shows the use of different microorganisms and different bioreactors so as to improve the removal efficiency economically. The present work deals with the use of N. hydrocarbonoxydans (NCIM 2386), an actinomycetes, for the degradation of phenol. N. hydrocarbonoxydans was immobilized on GAC and used in a spouted bed contactor for effective contact of microorganisms and the substrate. The contactor performance was studied by varying flow rates, influent concentrations and the solids loading in the contactor. The effect of these variables on phenol degradation was investigated and modeling study was carried out using the artificial neural network (ANN). A feed forward neural network with back propagation was used for the model development. The experiments were planned as per the face centered cube design (FCCD) and used for training of the model, whereas data from four other experimental runs were used for testing and validation of the model. The network was optimized for the number of neurons based on the mean square error. The ANN model with three layers with three input neurons, eight neurons in hidden layers and one output neuron was found to predict effectively the effluent concentration for the given operating conditions in the spouted bed contactor. The mean square error was found to be 9.318e-12 for this ANN model. Also the experimental data was used to develop second order nonlinear empirical model obtained using multiple regression (MR) and the results compared with ANN using correlation coefficient (R2), average absolute error (AAE) and root mean square error (RMSE). Results show that R2, AAE and RMSE values of MR model were 0.9363, 2.085 % and 2.338 % respectively, while in case of ANN model these values were 0.9995, 0.59 % and 1.263 % respectively. This shows that ANN model prediction is better than multiple regression model prediction.

scholarly journals ARTIFICIAL NEURAL NETWORK APPLIED IN FORECASTING THE COMPOSITION OF MUNICIPAL SOLID WASTE IN IASI, ROMANIA

2021 ◽  
Vol 29 (3) ◽  
pp. 368-380
Author(s):  
Cristina Ghinea ◽  
Petronela Cozma ◽  
Maria Gavrilescu
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Artificial Neural Network ◽  
Root Mean Square Error ◽  
Municipal Solid Waste ◽  
Solid Waste ◽  
Mean Square Error ◽  
Coefficient Of Determination ◽  
Mean Square ◽  
Ann Model

Neural network time series (NNTS) tool was used to predict municipal solid waste composition in Iasi, Romania. The nonlinear input output (NIO) time series model and nonlinear autoregressive model with external (exogenous) input (NARX) included in this tool were selected. The coefficient of determination (R2) and root mean square error (RMSE) were chosen for evaluation. By applying NIO, the optimum model is 4-11-6 artificial neural network (ANN, R2 = 0.929) in the case of testing as for the validation, with all 0.849 and 0.885, respectively. Applying NARX, the suitable model became 4-13-6 ANN model, with R2 = 0.999 for training, 0.879 for testing, and 0.931, respectively 0.944 for validation and all. The resulted RMSE is zero for training and 0.0109 for validation in the case of this model which had 4 inputs, 13 neurons and 6 outputs. The four input variables were: number of residents, population aged 15–59 years, urban life expectancy, total municipal solid waste (ton/year). The suitable ANN model revealed the lowest root mean square error and the highest coefficient of determination. Results indicate that NNTS tool is a complex instrument, NARX is more accurate than NIO model, and can be used and applied easily.

scholarly journals Enhanced CORDIC Based Rotator Design for Sinusoidal Transforms

2020 ◽  
Vol 9 (3) ◽  
pp. 1001-1004
Keyword(s):  
Fourier Transform ◽  
Frequency Domain ◽  
Discrete Fourier Transform ◽  
Mean Square Error ◽  
Time Domain ◽  
Basis Function ◽  
The Other ◽  
Mean Square ◽  
Circular Rotation ◽  
The Mean

Transforms play an important role in conversion of information from one domain to the other. To be more specific transforms like Discrete Fourier transform (DFT) and Discrete Cosine transform (DCT) helps us to migrate from one time domain to frequency domain based on the basis function selected. The basis function of the every sinusoidal transform carries out a circular rotation to convert information from one domain to the other. There are applications related to communication which requires this rotation into the hyperbolic trajectory as well. Multiplierless algorithm like CORDIC improves the latency of the transforms by eliminating the number of multipliers in the basis function. In this paper we have designed and implemented enhanced version of CORDIC based Rotator design. The Enhanced version is simulated for order 1 to order 36 to emphasize on the results of the proposed algorithm. Results shows that the enhanced CORDIC rotator design surpasses the Mean square error after the order 18 compared to standard CORDIC. Unified CORDIC also can be implemented using the said algorithm to implement different three trajectories.

The Cramer–Rao lower bound in a non-AWGN model for the affine phase retrieval

2021 ◽  
pp. 2050089
Author(s):  
Zhitao Zhuang ◽  
Kaixin Wang
Keyword(s):  
Lower Bound ◽  
Mean Square Error ◽  
Gaussian Noise ◽  
Phase Retrieval ◽  
Additive White Gaussian Noise ◽  
White Gaussian Noise ◽  
Mean Square ◽  
Cramer Rao Lower Bound ◽  
The Difference

In this paper, we derive the Cramer–Rao lower bound (CRLB) in a non-additive white Gaussian noise (AWGN) model for the affine phase retrieval (APR) and simulate the difference of CRLB and mean square error produced by PhaseLift of phase retrieval and APR in AWGN and non-AWGN cases.

scholarly journals Using Mixed Probability Distribution Functions for Modelling Non-Zero Sub-Daily Rainfall in Australia

Geosciences ◽  
2020 ◽  
Vol 10 (2) ◽  
pp. 43
Author(s):  
Md Masud Hasan ◽  
Barry F. W. Croke ◽  
Shuangzhe Liu ◽  
Kunio Shimizu ◽  
Fazlul Karim
Keyword(s):  
Probability Distribution ◽  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Daily Rainfall ◽  
Rainfall Data ◽  
Mean Square ◽  
Weibull Distributions ◽  
Rainfall Events ◽  
High Rainfall

Probabilistic models for sub-daily rainfall predictions are important tools for understanding catchment hydrology and estimating essential rainfall inputs for agricultural and ecological studies. This research aimed at achieving theoretical probability distribution to non-zero, sub-daily rainfall using data from 1467 rain gauges across the Australian continent. A framework was developed for estimating rainfall data at ungauged locations using the fitted model parameters from neighbouring gauges. The Lognormal, Gamma and Weibull distributions, as well as their mixed distributions were fitted to non-zero six-minutes rainfall data. The root mean square error was used to evaluate the goodness of fit for each of these distributions. To generate data at ungauged locations, parameters of well-fit models were interpolated from the four closest neighbours using inverse weighting distance method. Results show that the Gamma and Weibull distributions underestimate and lognormal distributions overestimate the high rainfall events. In general, a mixed model of two distributions was found better compared to the results of an individual model. Among the five models studied, the mixed Gamma and Lognormal (G-L) distribution produced the minimum root mean square error. The G-L model produced the best match to observed data for high rainfall events (e.g., 90th, 95th, 99th, 99.9th and 99.99th percentiles).

The Loss of Dexterity in the Bilateral Lower Extremities in Patients With Stroke

2011 ◽  
Vol 27 (2) ◽  
pp. 122-129 ◽  
Author(s):  
Ryoji Kiyama ◽  
Kiyohiro Fukudome ◽  
Toshiki Hiyoshi ◽  
Akihide Umemoto ◽  
Yoichi Yoshimoto ◽  
...  
Keyword(s):  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Knee Extensor ◽  
Lower Extremities ◽  
Response Force ◽  
Mean Square ◽  
Control Subjects ◽  
The Difference ◽  
Mean Square Errors

The aim of this study was to examine the dexterity of both lower extremities in patients with stroke. Twenty patients with stroke and 20 age-matched control subjects participated in this study. To determine the dexterity of the lower extremities, we examined the ability to control muscle force during submaximal contractions in the knee extensor muscles using a force tracking task. The root mean square errors were calculated from the difference between the target and response force. The root mean square error was significantly greater in the affected limb of patients with stroke compared with those of the unaffected limb and the control subjects, and in the unaffected limb compared with that of the control subjects. Furthermore, the root mean square error of the affected limb was related significantly to motor function as determined by Fugl-Myer assessment. These results demonstrate impairment of the dexterity of both the affected and the unaffected lower extremities in patients with stroke.

scholarly journals An Artificial Neural Network Model for Highway Accident Prediction: A Case Study of Erzurum, Turkey

2015 ◽  
Vol 27 (3) ◽  
pp. 217-225 ◽  
Author(s):  
Muhammed Yasin Çodur ◽  
Ahmet Tortum
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Mean Square Error ◽  
Traffic Accidents ◽  
Model Parameters ◽  
Mean Square ◽  
Ann Model ◽  
Accident Prediction ◽  
Marquardt Algorithm ◽  
Artificial Neural

This study presents an accident prediction model of Erzurum’s Highways in Turkey using artificial neural network (ANN) approaches. There are many ANN models for predicting the number of accidents on highways that were developed using 8 years with 7,780 complete accident reports of historical data (2005-2012). The best ANN model was chosen for this task and the model parameters included years, highway sections, section length (km), annual average daily traffic (AADT), the degree of horizontal curvature, the degree of vertical curvature, traffic accidents with heavy vehicles (percentage), and traffic accidents that occurred in summer (percentage). In the ANN model development, the sigmoid activation function was employed with Levenberg-Marquardt algorithm. The performance of the developed ANN model was evaluated by mean square error (MSE), the root mean square error (RMSE), and the coefficient of determination (R2). The model results indicate that the degree of vertical curvature is the most important parameter that affects the number of accidents on highways.

scholarly journals Development of calibration models for rapid determination of moisture content in rubber sheets using portable near-infrared spectrometers

2020 ◽  
Vol 13 (02) ◽  
pp. 2050009
Author(s):  
Amorndej Puttipipatkajorn ◽  
Amornrit Puttipipatkajorn
Keyword(s):  
Moisture Content ◽  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Near Infrared ◽  
Least Square ◽  
Mean Square ◽  
Ann Model ◽  
Rubber Sheet ◽  
Calibration Models

Rubber sheets are one of the primary products of natural rubber and are the main raw material in various rubber industries. The quality of a rubber sheet can be visually examined by holding it against clear light to inspect for any specks and impurities inside, but its moisture content is difficult to evaluate based on a visual inspection and this might lead to unfair trading. Herein, we developed a rapid, robust and nondestructive near-infrared spectroscopy (NIRS)-based method for moisture content determination in rubber sheets. A set of 300 rubber sheets were divided into a calibration (200 samples) and prediction groups (100 samples). The calibration set was used to develop NIRS calibration equation using different calibration models, Partial Least Square Regression (PLSR), Least Square Support Vector Machine (LS-SVM) and Artificial Neural Network (ANN). Among the models investigated, the ANN model with the first derivative of spectral preprocessing presented the best prediction with a coefficient of determination ([Formula: see text] of 0.993, root mean square error of calibration (RMSEC) of 0.126% and root mean square error of prediction (RMSEP) of 0.179%. The results indicated that the proposed NIRS-ANN model will be able to reduce human error and provide a highly accurate estimate of the moisture content in a rubber sheet compared to traditional wet chemistry estimation methods according to AOAC standards.

Sign in / Sign up

Export Citation Format

Share Document