---

Aim: The main aim of this study was to assess the efficacy of two important signal processing approaches i.e., wavelet transform and ensemble empirical mode decomposition (EEMD) on the performance of convolutional neural network (CNN).
Materials & Methods: The study was performed in two watersheds i.e., Kasilian and Bar-Erieh watersheds. In the first step, the CNN based runoff modeling was done in its single form i.e., using the original data as input. In the next step the input data was decomposed into several different sub-components i.e., approximation and details using Wavelet transform and Intrinsic Mode Functions (IMFs) using EEMD. Then the decomposed data were imported to the CNN model as input and combined Wavelet-CNN and EEMD-CNN models were provided.
Findings: The results showed that CNN in its single form could not estimate the one day ahead runoff with an acceptable accuracy. CNN in its original form had a moderate performance (with NRMSE of 83 and 66%). However, application of Wavelet transform and EEMD in combination with CNN produced acceptable results. It was shown that Wavelet transform had a higher impact (with NRMSE of 48 and 26%) on the performance of CNN in comparison to EEMD (with NRMSE of 52 and 61%).
Conclusion: This study showed that signal processing approaches can enhance the ability of deep learning methods such as CNN in predicting runoff values for one day ahead. However, the impact of signal processing methods on the performance of deep learning methods are not equal.
 

---

Ventricular Fibrillation (VF) is the major cause of triggering sudden cardiac death (SCD). Efficient prediction of ventricular fibrillation is very important for clinical purpose, as this is the most serious cardiac rhythm disturbance and can be life threatening. A reliable predictor of an imminent episode of VF, could be incorporated in an implantable cardioverter defibrillator (ICD) would be capable of delivering preventive therapy. The aim of this study is to investigate the possibility of predicting VF from surface electrocardiogram (ECG) signal by beat to beat tracing of the signal and using a dynamic thresholding method. As VF arises from the lower pumping chambers of the heart (ventricles), it is expected to find some changes in the ventricular activity part of the ECG signal before its occurrence. In this paper, we focused on the T-wave of ECG signal which shows the repolarization of ventricles and tried to present an online predictor by finding an entropy-based pattern in T-waves of ECG signal that can effectively maps the irregularity of this wave before VF. We have also used an Empirical Mode Decomposition (EMD) method to reduce the high frequency noises of T-waves before predictive index extraction in each beat. We found that proposed predictive pattern can be considered as a useful index for probability occurrence of VF. It reached the sensitivity of 89% and specificity of 95% in online VF prediction method. Presented method is simple, computationally fast and has high prediction quality and hence is well suited for real time implementation.  

---

In this paper the effect of artificial noise on the performance of nonlinear system identification method in reconstructing the response of a cantilever beam model having a local nonlinearity is investigated. For this purpose, the weak form equation governing the transverse vibration of a linear beam having a strongly nonlinear spring at the end is discretized by using Rayleigh-Ritz approach. Then, the derived equations are solved via Rung-Kutta method and the simulated response of the beam to impulse force is obtained. By contaminating the simulated response to artificial measurement noise, nonparametric nonlinear system identification is applied to reconstruct the response. Accordingly, intrinsic mode functions of the response are obtained by using advanced empirical mode decomposition, and nonlinear interaction model including intrinsic modal oscillators is constructed. Primary results show that the presence of noise in the response highly affects the sifting process which results in extraction of spurious intrinsic mode functions. In order to eradicate the effect of noise on this process, noise signals are used as masking signals in the advanced empirical mode decomposition method and intrinsic mode functions corresponding to the noise are extracted. Based on this approach, the dynamic of the noise in the response is identified and noise reduced signals are reconstructed by the intrinsic modal oscillators with appropriate accuracy.

---

The empirical mode decomposition method is a new technique to obtain constitutive components of a signal. Applicability to all kinds of signals including non-stationary and nonlinear is a main feature of this method. So far, many researches have been done in the literature to eliminate or reduce effects of multiple sources of errors such as stop criteria, end effects and interpolation function. This article focuses on end effects error which many of previous solutions have been proposed based on symmetry or similar methods to decline it. The proposed combined method using auto-regressive (AR) models for short sections of signal edges, forecasts tails of maximum and minimum envelops. Some of first intrinsic mode functions are initially calculated as a result of AR model application. The methods based on symmetry are then used to continue sifting algorithm for remaining signal that has no enough extremums to employ AR model. Finally, by executing some examples, more accurate results obtained from proposed method are compared with those achieved from the mirror method. Noise is also added to signal time history in the last example, to simulate a more realistic situation.

---

Identification of spin maneuver flight characteristics focused in this paper. To analyses an airplane flying quality, identification of the dynamic modes and extracting their characteristics is essential for assessment of the airplane dynamic stability and response-to-control. The paper aims to present a new method for identification of some flight modes, including natural and nonstandard modes, and extraction of their characteristics the same as instantaneous frequency and instantaneous damping ratio, directly from measurements of flight parameters in the time domain in nonlinear flight regime. Firstly, a conceptual method based on the Empirical Mode Decomposition (EMD) algorithm is proposed. The key issue of the EMD algorithm is to represent the signal as the summation of the pattern and detail parts, besides separating them from each other. by utilize the Empirical Mode Decomposition (EMD) capabilities in real-time, a local-online algorithm is introduced which estimates the signal intrinsic mode functions Secondly, by applying Hilbert- Huang transformation to IMFs obtained by EMD algorithm the flight characteristics the same as instantaneous frequency and instantaneous damping ratio for flight mode has been estimated from spin measured flight data. The results indicate the appropriate performance of the identification method in nonlinear flight regime.

---

In this study, fair comparisons between the empirical mode decomposition, ensemble empirical mode decomposition and discrete wavelet transform with the mother wavelet function of Meyer and Daubechies, were performed for detecting unbalance faults in a rotating machinery. In order to classify the healthy class from the unbalance classes, a support vector machines that was optimized by particle swarm optimization algorithm, was used. A comparison between the performances of optimized and non-optimized of support vector machines were also carried out. In order to obtained the required data, a rotating machinery fault simulator was developed and vibrational signals were acquired at healthy and unbalance fault conditions by accelerometer sensors. By processing the recorded signals and analysing signal to their frequency components, several statistical features were extracted from each frequency component as input support vector machine for the separation of classes. The obtained results indicated that the discrete wavelet transform with the Meyer mother wavelet, higher success rate than other methods for diagnosing unbalance faults.

---

---

According to the vital role that bridges play in transportation system and also communications of a society, monitoring their structural safety and keeping theme in service is crucial. Numerous methods have been proposed for detecting probable damages in bridges. Unfortunately most of them are based on comparison between the response of bridge in an intact and damaged state. Therefore intact state response must be known. However, not always it’s true in practice. So proposing a method which can determine and localize damages without prior knowledge of intact state is necessary. Such a method which was proposed by Sun et al. is studied carefully. Through the aforementioned method, the dynamic displacement response of a simply supported beam was decomposed into a dynamic component and a quasi-static component. Using Maxwell-Betti law of reciprocal deflection, the quasi-static component was attributed to the static deflection of the beam. Later damage which is defined by loss of stiffness, could be localized based on the abrupt changes in the static deflection curvature as it is related to bending moment and flexural stiffness of a beam. It is found out that the decomposition approach proposed by Sun et al. is restricted to fact that only one mode of oscillation must be dominant and also the natural frequency of motion must be determined through experimental measuring. Another limitation is that the abrupt changes in the curvature diagram cannot be related to damage essentially as curvature is also affected by the bending moment. In this study two modifications were proposed to get more accurate results in localizing the imposed damages. The first modification is the use of EMD method in order to decompose the displacement response into its intrinsic mode functions. Hence the aforementioned method could be used in real bridge displacement responses as higher modes corporations can also be determined and extracted through EMD process and finally the quasi-static component is determined as the residue of EMD algorithm. Also the ambient noise may be decomposed from the original signal, improving the method to work in real situations. The second modification is creating an imaginary constant moment length in the beam by the use of super position principle. So sudden increase in the curvature diagram is essentially a damage. Different scenarios of damage were studied and both methods have been used to detect damage in each scenario. Results show a great improvement in detection and localization of damage using the improved algorithm rather than the original proposed method. Eventually a five span real bridge model was taken into study. The improved damaged detection method could clearly determine the longitudinal position of the damage.