i DECLARATION No portion of the work referred to in this dissertation has been submitted in support of an application for another degree or qualification of this or any other university or other institution of learning. ii ABSTRACT Real world problems are described by non-linear and chaotic processes which makes them hard to model and predict. The aim of this dissertation is to determine the st...

The treatment of manufacturing problems, whether in process control, process optimization, or system design and planning, can be helped by input-output models, namely, relationships between input and output variables. Artificial neural networks present an opportunity to "learn" empirically established relationships and apply them subsequently in order to solve a particular problem. In light of ...

Ensuring the best possible stability of UTC(k) (local time scale) and its compliance with UTC scale (Universal Coordinated Time) forces predicting [UTC-UTC(k)] deviations, article presents results work on two methods constructing series (TS) for a neural network (NN), increasing accuracy prediction. In first method, prepared TSs are based deviations determined according to 5-day interval. order...

The effective thermal conductivity (ETC) of soil is an essential parameter for the design and unhindered operation underground energy transportation storage systems. Various experimental, empirical, semi-empirical, mathematical, numerical methods have been tried in past, but lack either accuracy or are computationally cumbersome. recent developments computer science provided a new computational...

Among the foremost frequent and vital tasks for hydrologist is to deliver a high accuracy estimation on hydrological variable, which reliable. It essential flood risk evaluation project, hydropower development developing efficient water resource management. Presently, approach of Group Method Data Handling (GMDH) has been widely applied in modelling sector. Yet, comparatively, same tool not vas...

Abstract The study aims at forecasting the return volatility of cryptocurrencies using several machine learning algorithms, like neural network autoregressive (NNETAR), cubic smoothing spline (CSS), and group method data handling (GMDH-NN) algorithm. used in this is spanning from April 14, 2017, to October 30, 2020, covering 1296 observations. We predict four cryptocurrencies, namely Bitcoin, E...

With the increasing level of intelligence marine engines, there is an demand for online monitoring and NOx emissions have been great concern. In this paper, a simulation model developed based on virtual measurement technology, which can calculate predict current operating state parameters low-speed two-stroke diesel engines. First, calibrated 3D used to design experiments obtain experimental sa...