time series

Neural network models with different input: An application on stock market forecasting

It is no doubt challenging to forecast the stock market accurately in reality due to the ever-changing market.  Ever since Artificial Neural Networks (ANNs) have been recognized as universal approximators, they are extensively used in forecasting albeit not having a systematic approach in identifying optimal input.  The appropriate number of significant lags of a time series corresponds to the optimal input in time series forecasting.  Hence, this study aims to compare the effect of several approaches in determining the input lag for ANNs prior to stock market forecasti

Dynamic learning rate adjustment using volatility in LSTM models for KLCI forecasting

The prediction of financial market behaviour constitutes a multifaceted challenge, attributable to the underlying volatility and non-linear characteristics inherent within market data.  Long Short-Term Memory (LSTM) models have demonstrated efficacy in capturing these complexities.  This study proposes a novel approach to enhance LSTM model performance by modulating the learning rate adaptively based on market volatility.  We apply this method to forecast the Kuala Lumpur Composite Index (KLCI), leveraging volatility as a key input to adapt the learning rate during trai

Impact of information on solar flares and earthquakes on the prediction of the annual dynamics of the infrasound wave envelope

The research results on the effectiveness of using data on solar flares and earthquakes to predict the infrasound wave envelope are presented.  The resulting SARIMAX model, enhanced with the aforementioned external factors, exhibits a 30% reduction in mean squared error and a 29% increase in the coefficient of determination compared to the previously presented ARIMA model.  Additionally, a significant achievement of the new approach, compared to previous ones, is the successful reproduction of the sharp intensity drop in the envelope during the August–September–October

FORECASTING THE ELECTRICITY CONSUMPTION USING AN ENSEMBLE OF MACHINE LEARNING MODELS

The use of machine learning models for electricity consumption prediction for smart grid has been investigated. It was found that data pre-processing can improve the performance of the energy consumption prediction model, while machine learning algorithms can improve model prediction accuracy through the integration of multiple algorithms and hyperparameter optimization. It was found that the ensemble learning method can provide better prediction accuracy than each individual method by combining the strong features of different methods that have different structural characteristics.

Прогнозування багатовимірних нестаціонарних часових рядів на основі адаптивної нео-фаззі-моделі

Введено структуру адаптивного нео-фаззі-предиктора та багатовимірного нео- фаззі-нейрона, а також метод навчання останнього. Запропонований алгоритм навчання має підвищену швидкість збіжності та забезпечує фільтруючі властивості. Завдяки введеній нейромережевій архітектурі, вузлами якої є нео-фаззі-нейрони, можна розв’язувати задачі короткострокового прогнозування у реальному часі за умов короткої навчальної вибірки.

Вплив функції активації RBF нейронної мережі на ефективність прогнозування кількості відмов програмного забезпечення

Досліджено вплив функції активації нейронної мережі типу RBF на ефективність навчання та прогнозування надійності програмного забезпечення у вигляді часових рядів. Показано, що оптимальною функцією активації для цієї задачі є Inverse Multiquadric з 10 нейронами у вхідному шарі та 30 – у прихованому.

Machine Learning Methods to Increase the Energy Efficiency of Buildings

Predicting a building’s energy consumption plays an important role as it can help assess its energy efficiency, identify and diagnose energy system faults, and reduce costs and improve climate impact. An analysis of current research in the field of ensuring the energy efficiency of buildings, in particular, their energy assessment, considering the types of models under consideration, was carried out.

Mathematical modeling and statistical analysis of Moroccan mean annual rainfall using EXPAR processes

In this work, we propose a study of the mean annual rainfall time series in order to evaluate the climate changes pattern over time.  If the analysis of this time series is carried out correctly, it can contribute to improve planning and policy development.  That is why we consider the problem of mathematical modeling and analysis of the mean annual rainfall of Morocco between 1901 and 2020 using descriptive statistics, structure changes analysis, spectral analysis and a nonlinear Exponential Autoregressive (EXPAR) processes to reproduce the behavior of this time series

Development of software and algorithmic security for forecasting the cryptocurrency course using fractal analysis methods

The work created software and algorithmic support for modeling and forecasting the Bitcoin cryptocurrency using the ARFIMA (AutoRegressive Fractionally Integrated Moving Average) fractal model. Time series forecasting models (autoregressive, fractal) were analyzed. The selection of the most appropriate parameters of the selected fractal model was also carried out to maximize accuracy in view of the RMSE metric. The series were analyzed for trend, seasonality, white noise, non-stationarity and long-term memory.

Trends in horizontal and vertical crustal displacements based on international GNSS service data: a case study of New Zealand

The study analyzes the coordinate time series of five permanent International GNSS Service (IGS) stations located in New Zealand. It also considers their annual movement from 2009 to 2018. The raw data in the form of Receiver Independence Exchange (RINEX) files were taken from IGS database and processes by means of online processing service AUSPOS. Using coordinate time series, horizontal and vertical displacement rates were calculated covering the ten-year study period. According to the results, stations located at the North Island of New Zealand revealed an uplift of 31-32 mm/yr.