Final Prediction Error Research Articles

Banking Sector Reforms and the Performance of the Nigerian Industrial Sector

The Nigerian economy has been experiencing a lot of reforms in the banking subsector. Despite these reforms that ought to have enhanced the performance of the industrial sector of the economy, the weak performance of the industrial sector has survived unscathed and prolonged. Therefore, the major interest of this paper is to investigate the long and short-run relationships existing between banking sector reforms and the performance of the industrial sector in Nigeria. The study begins with a review of the banking sector reforms and the link to the industrial sector performance. Time series data from 1982-2015 are used to empirically assess the long-run relationship between banking sector reforms-targeted variables and the Nigerian industrial sector. The Modified PANTULA Principle was adopted in the selection of the most suitable variant of the Johansen Cointegration technique and found that model three was only suitable in the determination of the long-run relationship between commercial banks credit to the industrial sector and industrial production, and not manufacturing capacity utilisation.Summary of the variants of the Johansen cointegration equations were provided to facilitate a robust discussion of the long-run relationship between the indicators of banking sector reforms and industrial sector performance. A modified variant of causality test was adopted in the investigation of the direction of causality that exist between the reforms variables and industrial sector performance indicators. Various lag selection techniques were applied and found the Final Prediction Error(FPE) as most suitable. The Vector Auto Regression (VAR) impulse response and variance decomposition were applied to determine the effects of the reforms shocks on the industrial sector performance variables. The results shows amongst other that in the era reforms, the shocks from the banking sector credit to the industrial sector is higher than other reforms indices. This makes credit to the industrial sector a potent force in the enhancement of industrial sector performance in Nigeria. Therefore, banking sector reforms should be designed to enhance the consistent flow of credit to the industrial sector of the economy. Structural breaks were also applied to see the effects of the changes in reforms on the performance of the industrial sector.

Modeling the Vibrational Dynamics of Piezoelectric Actuator by System Identification Technique

Actuators based on smart materials such as piezoelectric actuators (PEAs) are widely used in many applications to transform electrical signal to mechanical signal and vice versa. However, the major drawbacks for these smart actuators are hysteresis nonlinear, creep and residual vibration. In this paper, PEAs are used for active vibration application. Therefore, a model of PEA must be established to control the vibration that occurs in the system. The frequencies of 1 Hz, 20 Hz and 50 Hz were tested on the PEAs. The results obtained from the experimental were used to develop transfer function model by employing system identification technique. Meanwhile, the model validation was based on level of models fitness to estimation data, mean squared error (MSE), final prediction error (FPE) and correlation test. The experimental result showed that the displacement of the actuator is inversely proportional to the frequency. The following consequences caused the time response criteria at 50 Hz achieved smallest overshoot and fastest response of rise time and settling time.

Time synchronization for acceleration measurement data of Jiangyin Bridge subjected to a ship collision

State-space (SS) model is proposed to identify the time lag between the asynchronous accelerations at different locations of the Jiangyin Bridge measured during a ship–bridge collision. One of the accelerations is chosen as the reference signal, and the time axis of the rest of them are shifted relative to that of the reference signal with a series of shifting times. For each pair of reference and time shifted signals, SS models in correspondence to the shifting time series are formulated. Their system matrices are identified with data-driven stochastic subspace identification algorithm, and their model order is determined by Akaike's information theoretic criterion and final prediction error. If the 2 accelerations for model fitting are asynchronous, errors may be introduced into the SS model and its prediction error is expected to be greater than the counterpart obtained with synchronous accelerations. Therefore, the actual time lag between them is identified from the shifting time that corresponds to the minimum of loss function, which is used to map the prediction error vector sequence to a real number. In addition, asynchronous acceleration data measured 2 hr ahead of the ship–bridge collision and synchronous acceleration data measured long after the ship–bridge collision are also analyzed. The former dataset is exploited to evaluate the reproducibility of the SS model for time synchronization, and the latter dataset is utilized to examine its anti-false-identification capability. The results show that the SS model achieves a satisfactory performance in the identification of time lag for both asynchronous and synchronous measurement data.

System identification of an airship using trust region reflective least squares algorithm

Lighter than air vehicles present feasible solutions to several problems in aviation industry. Dynamic modeling of airships, however, poses enhanced complexities due to the effects of buoyancy-based static lift and virtual mass and inertia. System identification is an established technique for modeling aerial vehicles, but it generally requires huge amount of flight data, acquired through costly sensors operating at high sampling rates. Earlier airship identification works have used output/filter error methods, evolution strategies and subspace identification methods; all using large sets of estimation data. In this research, the longitudinal dynamics of a 30 ft long unmanned airship have been modeled using very less estimation data. During airship’s flight experiment, flight data was recorded at a minimal sampling frequency of 8 Hz, using low-cost sensors. The less estimation data was compensated by iterative estimation technique, instead of one-step estimation. The flight data was subjected to trust region reflective least squares algorithm that is based on a relatively new and efficient optimization method. The model estimation quality was quantified by residual analysis and Akaike’s criterion of final prediction error. The promising cross-validation results show that the adopted identification approach is suitable and cost-effective for modeling of complex airship dynamics.

ANALISIS PENGARUH INFLASI TERHADAP PERTUMBUHAN EKONOMI DI INDONESIA DENGAN METODE FINAL PREDICTION ERROR

The purpose of the research is to know whether inflation influences economic growth or economic growth influence inflation and to know the final prediction error of long - term equilibrium relationship between inflation and economic growth.The hypothesis presented in this research is that inflation has negative influence on economic growth and economic growth has negative influence on inflation. It is assumed that the final prediction error of long - term equilibrium relationship between inflation and economic growth has negative influence, and the final prediction error of equilibrium relationship between economic growth and inflation has negative influence.The method used in this research is causality analysis of Final Prediction Error (FPE) by using time series data of 1973 through 2002 taken from the Body of Statistic Center (BPS).It is conducted stationerity and causality test of FPE in this research. This research shows that there is one direction causality in which economic growth influences inflation.

ANALISIS KAUSALITAS EKSPOR NON MIGAS DENGAN PERTUMBUHAN EKONOMI MENGGUNAKAN METODE FINAL PREDICTION ERROR

This research titled "Causality analysis non petrol export with economic growth using final error prediction methods". Goal which needs to find the answer in this research is to know that non petrol export variable affecting to economic growth variable and economic growth variable affecting non petrol export variable. And also to know final prediction error with existence of long term equilibrium between non petrol export with economic growth. Hypothesis proposed is non petrol export having positive effect to economic growth and economic growth have positive effect to non petrol export. Final error prediction with existence of relation between long term equilibrium and non petrol export and economic growth have positive effect, and final error prediction with existence of relation between long term equilibrium with economic growth and non petrol export have positive effect.Based on analysis there's only one direction causality relation between economic growth and non petrol export. From facts above can be concluded that economic growth will bring creation process and expanding strong domestic market because export is not a starting point or initial destination of economic growth but export only a economic growth process

HUTANG LUAR NEGERI, PENANAMAN MODAL ASING (PMA), EKSPOR, DAN PERANANNYA TERHADAP PERTUMBUHAN EKONOMI INDONESIA TAHUN 1975 - 2000

The debate about the role of exports in the development of economic theory has emerged since the 1950s. In the macroeconomic theory, the relationships between export and economic growth and / or national income is an identity because export is a part of national income, but in development economics, heavily concern over matters wether export make prosperity (wealth) or suffering to a nation.Jung and Marshall (1985) examine four viewpoints characterize equally plausible hypothesis of relationships between export and economic growth: (1) export-led growth hypothesis, (2) internally generated export hypothesis, (3) export-reducing growth hypothesis and (4) growth-reducing export hypothesis. The empirical result using real national income and real export data over 1969-1997 suggests that error correction causality tests show bidirectional pattern, but according to the value of error correction term, adjustment coefficient reaction. Granger-causality test (1969) and final prediction error (FPE) show unidirectional causality from real national income to real export. Thus, over the period 1969-1997, Indonesia supported internally generated export hypothesis.

ANALISIS KAUSALITAS ANTARA PENDAPATAN NASIONAL DENGAN SUKU BUNGA MENGGUNAKAN METODE FINAL PREDICTION ERROR (FPE) TAHUN 1997.1 - 2003.4

The objective of this research is to verify if the national income variable influences interest rate, or vice versa, the interest rate influences national income. The research is conducted by using causality test of Final Prediction Error which is method for determining the optimal length in the way minimizing FPE.Result of the test by using FPE showed that there is one datum showing GNP stationer variable demonstrating to Mackinnon critical values 5%, the best testing model is model which having the minimum AIC, and also on interest rate of bank of Indonesia (SBI) there is one datum of stationer showing that SBI stationer on Mackinnon critical values 5% demonstrating model 3 stationer which has minimal AIC value. The conclusion acquired from this research is that GNP causes SBI but SBI does not cause GNP because GNP variable is influenced by the previous time.

On adaptive covariance and spectrum estimation of locally stationary multivariate processes

When estimating the correlation/spectral structure of a locally stationary process, one has to make two important decisions. First, one should choose the so-called estimation bandwidth, inversely proportional to the effective width of the local analysis window, in the way that complies with the degree of signal nonstationarity. Too small bandwidth may result in an excessive estimation bias, while too large bandwidth may cause excessive estimation variance. Second, but equally important, one should choose the appropriate order of the spectral representation of the signal so as to correctly model its resonant structure–when the order is too small, the estimated spectrum may not reveal some important signal components (resonances), and when it is too high, it may indicate the presence of some nonexistent components. When the analyzed signal is not stationary, with a possibly time-varying degree of nonstationarity, both the bandwidth and order parameters should be adjusted in an adaptive fashion. The paper presents and compares three approaches allowing for unified treatment of the problem of adaptive bandwidth and order selection for the purpose of identification of nonstationary vector autoregressive processes: the cross-validation approach, the full cross-validation approach, and the approach that incorporates the multivariate version of the generalized Akaike’s final prediction error criterion. It is shown that the latter solution yields the best results and, at the same time, is very attractive from the computational viewpoint.

Speed Effect to a Quarter Car ARX Model Based on System Identification

This paper presents the effect of car speeds on a quarter car passive suspension system model dynamics. The model is identified using system identification technique, in which the input-output data are collected by running a test car on an artificial road surface with two different speeds i.e., 10 km/h and 20 km/h. The quarter car passive suspension system dynamics is assumed to have an ARX model structure and identified using linear least-square estimation algorithm. The car vertical body acceleration, which is the output variable, is measured by installing an accelerometer sensor on the car body, above the suspension. On the other hand, the car shaft acceleration, which is the input variable, is measured by installing an accelerometer sensor at the lower arm of the car suspension. The best model for the 10 km/h car speed gives the output order () = 4, the input order () = 2, delay (<em>d)</em> = 1, the best fit = 90.65%, and the Akaike’s Final Prediction Error (FPE) = 5.315e-06. In contrast, the 20 km/h speed results in 4^th output order (), 1^stthe input order (), 1^st delay (<em>d)</em>, the best fit of 91.05%, and 7.503e-05Akaike’s FPE. These results show that the higher speed reduces the effect of the road surface to car dynamics, which is indicated by the order of the model

Bootstrap Order Determination for ARMA Models: A Comparison between Different Model Selection Criteria

The present paper deals with the order selection of models of the class for autoregressive moving average. A novel method—previously designed to enhance the selection capabilities of the Akaike Information Criterion and successfully tested—is now extended to the other three popular selectors commonly used by both theoretical statisticians and practitioners. They are the final prediction error, the Bayesian information criterion, and the Hannan-Quinn information criterion which are employed in conjunction with a semiparametric bootstrap scheme of the type sieve.

A pruning approach to optimize synaptic connections and select relevant input parameters for neural network modelling of solar radiation

The accurate modelling of solar radiation is important for many applications including agriculture and energy management. Previous research has widely focused on the development of artificial neural network (ANN) models for this task. Since the inputs to these models include different meteorological parameters, it is usually time consuming and costly to acquire these parameters. Therefore, selection of most relevant input parameters is a key step in the construction of these models. The overall goal of this research is to develop ANN models with less number of parameters and at the same time, high modelling accuracy. To this aim, an algorithm for network pruning, the optimal brain surgeon (OBS), is proposed to achieve two main objectives, selection of most relevant input parameters and optimization of the network structure at synaptic level. Four meteorological parameters, namely: temperature (T), relative humidity (RH), wind speed (WS), and sunshine duration (SSD) are used to model solar radiation, the global horizontal irradiation (GHI), over Abu Dhabi, the United Arab Emirates. The results show that the least relevant input parameter is RH with a contribution of 15.2% in the modelling process as compared to 24.8% for WS, 47.8% for T, and 54.7% for SSD. The parameter selection results coincide with recently used techniques in solar radiation research, J48 technique in Waikato Environment for Knowledge Analysis (WEKA) software and Automatic Relevance Determination (ARD) method. The modelling performance is compared with an all-connected ANN using all the four input parameters and ten hidden layer neurons with a total of 61 synaptic connections including biases. On the one hand, the proposed technique has successfully achieved an ANN with three inputs (T, WS, SSD), seven active hidden layer neuron, and 17 synaptic connections including biases. On the other hand, there are improvements observed in statistical evaluation metrics including mean absolute biased error (MABE), adjusted coefficient of determination (R¯2), Akaike information criterion (AIC), Akaike final prediction error (FPE), Rissanen's minimum description length (MDL), and cross entropy (CE).

Factor Modelling for High‐Dimensional Time Series: Inference and Model Selection

Analysis of high‐dimensional time series data is of increasing interest among different fields. This article studies high‐dimensional time series from a dimension reduction perspective using factor modelling. Statistical inference is conducted using eigen‐analysis of a certain non‐negative definite matrix related to autocovariance matrices of the time series, which is applicable to fixed or increasing dimension. When the dimension goes to infinity, the rate of convergence and limiting distributions of estimated factors are established. Using the limiting distributions of estimated factors, a high‐dimensional final prediction error criterion is proposed to select the number of factors. Asymptotic properties of the criterion are illustrated by simulation studies and real applications.

Mixture of autoregressive modeling orders and its implication on single trial EEG classification

Autoregressive (AR) models are of commonly utilized feature types in Electroencephalogram (EEG) studies due to offering better resolution, smoother spectra and being applicable to short segments of data. Identifying correct AR’s modeling order is an open challenge. Lower model orders poorly represent the signal while higher orders increase noise. Conventional methods for estimating modeling order include Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC) and Final Prediction Error (FPE). This article assesses the hypothesis that appropriate mixture of multiple AR orders is likely to better represent the true signal compared to any single order. Better spectral representation of underlying EEG patterns can increase utility of AR features in Brain Computer Interface (BCI) systems by increasing timely & correctly responsiveness of such systems to operator’s thoughts. Two mechanisms of Evolutionary-based fusion and Ensemble-based mixture are utilized for identifying such appropriate mixture of modeling orders. The classification performance of the resultant AR-mixtures are assessed against several conventional methods utilized by the community including (1) A well-known set of commonly used orders suggested by the literature, (2) conventional order estimation approaches (e.g., AIC, BIC and FPE), (3) blind mixture of AR features originated from a range of well-known orders. Five datasets from BCI competition III that contain 2, 3 and 4 motor imagery tasks are considered for the assessment. The results indicate superiority of Ensemble-based modeling order mixture and evolutionary-based order fusion methods within all datasets.

Modelling and Control of Polymer Electrolyte Membrane Fuel Cell

Objective: Development of Mathematical model and implementation of PID control scheme for 500Watt Polymer Electrolyte Membrane (PEMFC) Fuel Cell system. Methods: Model is developed in the MATLAB/Simulink platform by using Box Jenkins, Output Error method, Polynomial State space method and Subspace method. Findings: Subspace method of identification provides good results with acceptable Final Prediction Error (FPE) and this model is considered for implementing PID control scheme. Tuning of PID parameters is carried out by Cuckoo Search (CS) algorithm which yields most challenging results. Applications/Improvements: Residential power generation, Recreation vehicles, Light weight vehicles, Portable computers, Transportation.

Detection of low-velocity impact-induced delaminations in composite laminates using Auto-Regressive models

In this paper, the detection of delaminations in carbon-fiber-reinforced-plastic (CFRP) laminate plates induced by low-velocity impacts (LVI) is investigated by means of Auto-Regressive (AR) models obtained from the time histories of the acquired responses of the composite specimens. A couple of piezoelectric patches for actuation and sensing purposes are employed. The proposed structural health monitoring (SHM) routine begins with the selection of the suitable locations of the piezoelectric transducers via the numerical analysis of the curvature mode shapes of the CFRP plates. The normalized data recorded for the undamaged plate configuration are then analyzed to obtain the most suitable AR model using five techniques based on the Akaike Information Criterion (AIC), the Akaike Final Prediction Error (FPE), the Partial Autocorrelation Function (PAF), the Root Mean Squared (RMS) of the AR residuals for different order p, and the Singular Value Decomposition (SVD). Linear Discriminant Analysis (LDA) is then applied on the AR model parameters to enhance the performance of the proposed delamination identification routine. Results show the effectiveness of the developed procedure when a reduced number of sensors is available.

Performance of Mathematical System Identification in Modeling of Hybrid Evaporative Cooling System

The major aim of this study is to model the effect of outside temperature, watering, and airing on the inside temperature of a hybrid evaporative cooling system (HECS). There is great interest in evaporative cooling systems as a new storage system for fruit and vegetables for the purpose of energy saving. The heat transfer process of the HECS has not yet been well analyzed, so system identification based model was used to identify such an unknown process. Four system identification methods were used to train a three input-one output based system. After comparing the performance of the four system identification methods, continuous-time identified transfer function model was selected based on final prediction error (FPE), mean squared error (MSE), and regression of the input-output responses.

Chlorine modeling in water distribution networks using ARX and ARMAX model structures

Chlorination is still the main method of disinfection worldwide. Utilization of chlorine modeling enhances the management of water supply systems toward the reduction of the risks of waterborne diseases and cancer from disinfection byproducts formation. In this paper, the results of chlorine modeling efforts were presented as an extension of a project for Konyaalti Water Distribution Network (KWDN) of Antalya City, in the south of Turkey, using autoregressive with exogenous input (ARX) and autoregressive moving average with exogenous input (ARMAX) model structures. The required data-sets were obtained from the existing online monitoring stations. The ARX and ARMAX model structures modified for time series applications were utilized to predict chlorine concentrations at the critical point of KWDN. Non-representative data-sets were initially identified and excluded from the database. Best fit and Akaike’s Final Prediction Error techniques were used as model selection criteria. ARX4-5-3 and ARMAX2-3-3-4 were identified to be the best ARX and ARMAX model structures among several structures tested to predict chlorine concentrations at the critical point of KWDN. This study shows that ARX and ARMAX model structures can be considered as potential for managing chlorine levels in water distribution networks especially when the properties of the components and hydraulics of water distribution network are unknown.

Jackknife model averaging for quantile regressions

In this paper we consider model averaging for quantile regressions (QR) when all models under investigation are potentially misspecified and the number of parameters is diverging with the sample size. To allow for the dependence between the error terms and regressors in the QR models, we propose a jackknife model averaging (JMA) estimator which selects the weights by minimizing a leave-one-out cross-validation criterion function and demonstrate its asymptotic optimality in terms of minimizing the out-of-sample final prediction error. We conduct simulations to demonstrate the finite-sample performance of our estimator and compare it with other model selection and averaging methods. We apply our JMA method to forecast quantiles of excess stock returns and wages.

Robust Design Space Modeling

Architectural design spaces of microprocessors are often exponentially large with respect to the pending processor parameters. To avoid simulating all configurations in the design space, machine learning and statistical techniques have been utilized to build regression models for characterizing the relationship between architectural configurations and responses (e.g., performance or power consumption). However, this article shows that the accuracy variability of many learning techniques over different design spaces and benchmarks can be significant enough to mislead the decision-making. This clearly indicates a high risk of applying techniques that work well on previous modeling tasks (each involving a design space, benchmark, and design objective) to a new task, due to which the powerful tools might be impractical. Inspired by ensemble learning in the machine learning domain, we propose a robust framework called ELSE to reduce the accuracy variability of design space modeling. Rather than employing a single learning technique as in previous investigations, ELSE employs distinct learning techniques to build multiple base regression models for each modeling task. This is not a trivial combination of different techniques (e.g., always trusting the regression model with the smallest error). Instead, ELSE carefully maintains the diversity of base regression models and constructs a metamodel from the base models that can provide accurate predictions even when the base models are far from accurate. Consequently, we are able to reduce the number of cases in which the final prediction errors are unacceptably large. Experimental results validate the robustness of ELSE: compared with the widely used artificial neural network over 52 distinct modeling tasks, ELSE reduces the accuracy variability by about 62%. Moreover, ELSE reduces the average prediction error by 27% and 85% for the investigated MIPS and POWER design spaces, respectively.