Abstract: Green microgrids using mostly renewable energy (RE) for generation, are complex systems with inherent nonlinear dynamics. Among a variety of different optimization tools there are only a few ones that adequately consider this complexity. This paper evaluates applicability of two somewhat similar optimization tools tailored for standalone RE microgrids and also assesses a machine learning tool for performance prediction that can enhance the reliability of any chosen optimization tool. It shows that one of these microgrid optimization tools has certain advantages over another and presents a detailed routine of preparing input data to simulate RE microgrid behavior. The paper also shows how neural-network-based predictive modeling can be used to validate and forecast solar power generation based on weather time series data, which improves the overall quality of standalone RE microgrid analysis.
Abstract: Rainfall and runoff phenomenon is a chaotic and complex outcome of nature which requires sophisticated modelling and simulation methods for explanation and use. Time Series modelling allows runoff data analysis and can be used as forecasting tool. In the paper attempt is made to model river runoff data and predict the future behavioural pattern of river based on annual past observations of annual river runoff. The river runoff analysis and predict are done using ARIMA model. For evaluating the efficiency of prediction to hydrological events such as rainfall, runoff and etc., we use the statistical formulae applicable. The good agreement between predicted and observation river runoff coefficient of determination (R2) display that the ARIMA (4,1,1) is the suitable model for predicting Karkheh River runoff at Iran.
Abstract: In this paper, the intelligent algorithm (IA) that is capable of adapting to dynamical tropical weather conditions is proposed based on fuzzy logic techniques. The IA effectively interacts with the quality of service (QoS) criteria irrespective of the dynamic tropical weather to achieve improvement in the satellite links. To achieve this, an adaptive network-based fuzzy inference system (ANFIS) has been adopted. The algorithm is capable of interacting with the weather fluctuation to generate appropriate improvement to the satellite QoS for efficient services to the customers. 5-year (2012-2016) rainfall rate of one-minute integration time series data has been used to derive fading based on ITU-R P. 618-12 propagation models. The data are obtained from the measurement undertaken by the Communication Research Group (CRG), Physics Department, Federal University of Technology, Akure, Nigeria. The rain attenuation and signal-to-noise ratio (SNR) were derived for frequency between Ku and V-band and propagation angle with respect to different transmitting power. The simulated results show a substantial reduction in SNR especially for application in the area of digital video broadcast-second generation coding modulation satellite networks.
Abstract: Empirical deterministic models have been developed to predict roughness progression of heavy duty spray sealed pavements for a dataset representing rural arterial roads. The dataset provides a good representation of the relevant network and covers a wide range of operating and environmental conditions. A sample with a large size of historical time series data for many pavement sections has been collected and prepared for use in multilevel regression analysis. The modelling parameters include road roughness as performance parameter and traffic loading, time, initial pavement strength, reactivity level of subgrade soil, climate condition, and condition of drainage system as predictor parameters. The purpose of this paper is to report the approaches adopted for models development and validation. The study presents multilevel models that can account for the correlation among time series data of the same section and to capture the effect of unobserved variables. Study results show that the models fit the data very well. The contribution and significance of relevant influencing factors in predicting roughness progression are presented and explained. The paper concludes that the analysis approach used for developing the models confirmed their accuracy and reliability by well-fitting to the validation data.
Abstract: Floods have huge environmental and economic impact. Therefore, flood prediction is given a lot of attention due to its importance. This study analysed the annual maximum streamflow (discharge) (AMS or AMD) of Karkheh River in Karkheh River Basin for flood predicting using ARIMA model. For this purpose, we use the Box-Jenkins approach, which contains four-stage method model identification, parameter estimation, diagnostic checking and forecasting (predicting). The main tool used in ARIMA modelling was the SAS and SPSS software. Model identification was done by visual inspection on the ACF and PACF. SAS software computed the model parameters using the ML, CLS and ULS methods. The diagnostic checking tests, AIC criterion, RACF graph and RPACF graphs, were used for selected model verification. In this study, the best ARIMA models for Annual Maximum Discharge (AMD) time series was (4,1,1) with their AIC value of 88.87. The RACF and RPACF showed residuals’ independence. To forecast AMD for 10 future years, this model showed the ability of the model to predict floods of the river under study in the Karkheh River Basin. Model accuracy was checked by comparing the predicted and observation series by using coefficient of determination (R2).
Abstract: The aim of this paper is the comparison of three different methods, in order to produce fuzzy tolerance relations for rainfall data classification. More specifically, the three methods are correlation coefficient, cosine amplitude and max-min method. The data were obtained from seven rainfall stations in the region of central Greece and refers to 20-year time series of monthly rainfall height average. Three methods were used to express these data as a fuzzy relation. This specific fuzzy tolerance relation is reformed into an equivalence relation with max-min composition for all three methods. From the equivalence relation, the rainfall stations were categorized and classified according to the degree of confidence. The classification shows the similarities among the rainfall stations. Stations with high similarity can be utilized in water resource management scenarios interchangeably or to augment data from one to another. Due to the complexity of calculations, it is important to find out which of the methods is computationally simpler and needs fewer compositions in order to give reliable results.
Abstract: This paper presents an automatic normal and abnormal heart sound classification model developed based on deep learning algorithm. MITHSDB heart sounds datasets obtained from the 2016 PhysioNet/Computing in Cardiology Challenge database were used in this research with the assumption that the electrocardiograms (ECG) were recorded simultaneously with the heart sounds (phonocardiogram, PCG). The PCG time series are segmented per heart beat, and each sub-segment is converted to form a square intensity matrix, and classified using convolutional neural network (CNN) models. This approach removes the need to provide classification features for the supervised machine learning algorithm. Instead, the features are determined automatically through training, from the time series provided. The result proves that the prediction model is able to provide reasonable and comparable classification accuracy despite simple implementation. This approach can be used for real-time classification of heart sounds in Internet of Medical Things (IoMT), e.g. remote monitoring applications of PCG signal.
Abstract: In order to study the impact of various factors on the housing price, we propose to build different prediction models based on deep learning to determine the existing data of the real estate in order to more accurately predict the housing price or its changing trend in the future. Considering that the factors which affect the housing price vary widely, the proposed prediction models include two categories. The first one is based on multiple characteristic factors of the real estate. We built Convolution Neural Network (CNN) prediction model and Long Short-Term Memory (LSTM) neural network prediction model based on deep learning, and logical regression model was implemented to make a comparison between these three models. Another prediction model is time series model. Based on deep learning, we proposed an LSTM-1 model purely regard to time series, then implementing and comparing the LSTM model and the Auto-Regressive and Moving Average (ARMA) model. In this paper, comprehensive study of the second-hand housing price in Beijing has been conducted from three aspects: crawling and analyzing, housing price predicting, and the result comparing. Ultimately the best model program was produced, which is of great significance to evaluation and prediction of the housing price in the real estate industry.
Abstract: This paper presents a method for identification
of a linear time invariant (LTI) autonomous all pole system
using singular value decomposition. The novelty of this paper
is two fold: First, MUSIC algorithm for estimating complex
frequencies from real measurements is proposed. Secondly,
using the proposed algorithm, we can identify the coefficients
of differential equation that determines the LTI system by
switching off our input signal. For this purpose, we need only
to switch off the input, apply our complex MUSIC algorithm
and determine the coefficients as symmetric polynomials in the
complex frequencies. This method can be applied to unstable
system and has higher resolution as compared to time series
solution when, noisy data are used. The classical performance
bound, Cramer Rao bound (CRB), has been used as a basis for
performance comparison of the proposed method for multiple
poles estimation in noisy exponential signal.
Abstract: Traditional techniques for analyzing time series are based on the notion of stationarity of phenomena under study, but in reality most economic and financial series do not verify this hypothesis, which implies the implementation of specific tools for the detection of such behavior. In this paper, we study nonstationary non-seasonal time series tests in a non-exhaustive manner. We formalize the problem of nonstationary processes with numerical simulations and take stock of their statistical characteristics. The theoretical aspects of some of the most common unit root tests will be discussed. We detail the specification of the tests, showing the advantages and disadvantages of each. The empirical study focuses on the application of these tests to the exchange rate (USD/TND) and the Consumer Price Index (CPI) in Tunisia, in order to compare the Power of these tests with the characteristics of the series.
Abstract: The stock market can provide huge profits in a relatively short time in financial sector; however, it also has a high risk for investors and traders if they are not careful to look the factors that affect the stock market. Therefore, they should give attention to the dynamic fluctuations and movements of the stock market to optimize profits from their investment. In this paper, we present a nonlinear autoregressive exogenous model (NARX) to predict the movements of stock market; especially, the movements of the closing price index. As case study, we consider to predict the movement of the closing price in Indonesia composite index (IHSG) and choose the best structures of NARX for IHSG’s prediction.
Abstract: Climate change has become a major concern across the world as the intensity along with quantity of the rainfall, mean surface temperature and other climatic parameters have been changed not only in Bangladesh but also in the entire globe. Bangladesh has already experienced many natural hazards. Among them changing of rainfall pattern, erratic and heavy rainfalls are very common. But changes of rainfall pattern and its amount is still in question to some extent. This study aimed to unfold how the historical rainfalls varied over time and how would be their future trends. In this context, historical rainfall data (1975-2014) were collected from Bangladesh Metrological Department (BMD) and then a time series model was developed using Box-Jenkins algorithm in IBM SPSS to forecast the future rainfall. From the historical data analysis, this study revealed that the amount of rainfall decreased over the time and shifted to the post monsoons. Forecasted rainfall shows that the pre-monsoon and early monsoon will get drier in future whereas late monsoon and post monsoon will show huge fluctuations in rainfall magnitudes with temporal variations which means Bangladesh will get comparatively drier seasons in future which may be a serious problem for the country as it depends on agriculture.
Abstract: This paper examines the forecasting performance of Autoregressive Integrated Moving Average (ARIMA) and Artificial Neural Networks (ANN) models with the published exchange rate obtained from South African Reserve Bank (SARB). ARIMA is one of the popular linear models in time series forecasting for the past decades. ARIMA and ANN models are often compared and literature revealed mixed results in terms of forecasting performance. The study used the MSE and MAE to measure the forecasting performance of the models. The empirical results obtained reveal the superiority of ARIMA model over ANN model. The findings further resolve and clarify the contradiction reported in literature over the superiority of ARIMA and ANN models.
Abstract: This work is devoted to the study of modeling
geophysical time series. A stochastic technique with time-varying
parameters is used to forecast the volatility of data arising in
geophysics. In this study, the volatility is defined as a logarithmic
first-order autoregressive process. We observe that the inclusion of
log-volatility into the time-varying parameter estimation significantly
improves forecasting which is facilitated via maximum likelihood
estimation. This allows us to conclude that the estimation algorithm
for the corresponding one-step-ahead suggested volatility (with ±2
standard prediction errors) is very feasible since it possesses good
convergence properties.
Abstract: Financial derivatives are considered to be risky investment instruments which could possibly bring another financial crisis. As prevention, European Union and its member states have released new legal acts adjusting this area of law in recent years. There have been several cases in history of capital markets worldwide where it was shown that legislature may affect behavior of subjects on capital markets. In our paper we analyze main events on selected European stock exchanges in order to apply them on three chosen markets - Czech capital market represented by Prague Stock Exchange, German capital market represented by Deutsche Börse and Polish capital market represented by Warsaw Stock Exchange. We follow time series of development of the sum of listed derivatives on these three stock exchanges in order to evaluate popularity of those exchanges. Afterwards we compare newly listed derivatives in relation to the speed of development of these exchanges. We also make a comparison between trends in derivatives and shares development. We explain how a legal regulation may affect situation on capital markets. If the regulation is too strict, potential investors or traders are not willing to undertake it and move to other markets. On the other hand, if the regulation is too vague, trading scandals occur and the market is not reliable from the prospect of potential investors or issuers. We see that making the regulation stricter usually discourages subjects to stay on the market immediately although making the regulation vaguer to interest more subjects is usually much slower process.
Abstract: The effectiveness of energy demand policy depends on identifying the key drivers of energy demand both in the short-run and the long-run. This paper examines the influence of regional differences on the link between energy demand and other explanatory variables for Nigeria, China and USA using the Vector Error Correction Model (VECM) approach. This study employed annual time series data on energy consumption (ED), real gross domestic product (GDP) per capita (RGDP), real energy prices (P) and urbanization (N) for a thirty-six-year sample period. The utilized time-series data are sourced from World Bank’s World Development Indicators (WDI, 2016) and US Energy Information Administration (EIA). Results from the study, shows that all the independent variables (income, urbanization, and price) substantially affect the long-run energy consumption in Nigeria, USA and China, whereas, income has no significant effect on short-run energy demand in USA and Nigeria. In addition, the long-run effect of urbanization is relatively stronger in China. Urbanization is a key factor in energy demand, it therefore recommended that more attention should be given to the development of rural communities to reduce the inflow of migrants into urban communities which causes the increase in energy demand and energy excesses should be penalized while energy management should be incentivized.
Abstract: This paper presents two of the most knowing kernel
adaptive filtering (KAF) approaches, the kernel least mean squares
and the kernel recursive least squares, in order to predict a new output
of nonlinear signal processing. Both of these methods implement a
nonlinear transfer function using kernel methods in a particular space
named reproducing kernel Hilbert space (RKHS) where the model is
a linear combination of kernel functions applied to transform the
observed data from the input space to a high dimensional feature
space of vectors, this idea known as the kernel trick. Then KAF is the
developing filters in RKHS. We use two nonlinear signal processing
problems, Mackey Glass chaotic time series prediction and nonlinear
channel equalization to figure the performance of the approaches
presented and finally to result which of them is the adapted one.
Abstract: Foreign direct investment is a driving force in the development of the interdependent national economies, and the study and analysis of investments is an urgent problem. It is particularly important for transitional economies, such as Georgia, and the study and analysis of investments is an urgent problem. Consequently, the goal of the research is the study and analysis of direct foreign investments in Georgia, and identification and forecasting of modern trends, and covers the period of 2006-2015. The study uses the methods of statistical observation, grouping and analysis, the methods of analytical indicators of time series, trend identification and the predicted values are calculated, as well as various literary and Internet sources relevant to the research. The findings showed that modern investment policy In Georgia is favorable for domestic as well as foreign investors. Georgia is still a net importer of investments. In 2015, the top 10 investing countries was led by Azerbaijan, United Kingdom and Netherlands, and the largest share of FDIs were allocated in the transport and communication sector; the financial sector was the second, followed by the health and social work sector, and the same trend will continue in the future.
Abstract: Empirical mode decomposition (EMD), a new
data-driven of time-series decomposition, has the advantage of
supposing that a time series is non-linear or non-stationary, as
is implicitly achieved in Fourier decomposition. However, the
EMD suffers of mode mixing problem in some cases. The aim of
this paper is to present a solution for a common type of signals
causing of EMD mode mixing problem, in case a signal suffers
of an intermittency. By an artificial example, the solution shows
superior performance in terms of cope EMD mode mixing problem
comparing with the conventional EMD and Ensemble Empirical
Mode decomposition (EEMD). Furthermore, the over-sifting problem
is also completely avoided; and computation load is reduced roughly
six times compared with EEMD, an ensemble number of 50.
Abstract: Traditionally in sensor networks and recently in the
Internet of Things, numerous heterogeneous sensors are deployed
in distributed manner to monitor a phenomenon that often can be
model by an underlying stochastic process. The big time-series
data collected by the sensors must be analyzed to detect change
in the stochastic process as quickly as possible with tolerable
false alarm rate. However, sensors may have different accuracy
and sensitivity range, and they decay along time. As a result,
the big time-series data collected by the sensors will contain
uncertainties and sometimes they are conflicting. In this study, we
present a framework to take advantage of Evidence Theory (a.k.a.
Dempster-Shafer and Dezert-Smarandache Theories) capabilities of
representing and managing uncertainty and conflict to fast change
detection and effectively deal with complementary hypotheses.
Specifically, Kullback-Leibler divergence is used as the similarity
metric to calculate the distances between the estimated current
distribution with the pre- and post-change distributions. Then mass
functions are calculated and related combination rules are applied to
combine the mass values among all sensors. Furthermore, we applied
the method to estimate the minimum number of sensors needed to
combine, so computational efficiency could be improved. Cumulative
sum test is then applied on the ratio of pignistic probability to detect
and declare the change for decision making purpose. Simulation
results using both synthetic data and real data from experimental
setup demonstrate the effectiveness of the presented schemes.