Название: Digital Economy, Business Analytics, and Big Data Analytics Applications
Автор: Saad G. Yaseen
Издательство: Springer
Серия: Studies in Computational Intelligence
Год: 2022
Страниц: 723
Язык: английский
Формат: pdf (true)
Размер: 18.9 MB

As the digital economy infiltrates almost every aspect of our lives and is moving at a breakneck speed, smart technologies including computational intelligence systems are changing our global business world. The added value of smart technologies is only realized when businesses apply big data analytics to uncover insights that can improve business optimization, competitiveness, and innovation performance. A thorough examination of the antecedents, consequences, and diffusion of the business analytics and big data analytics application shows that computational intelligence systems play a crucial role in business. Thus, the current book highlights cutting-edge applied research in the fields of business analytics, big data analytics, and business intelligence paradigms, models, techniques, tools, and applications.

In the chapter "User Interface Development Tools and Software for Arduino “A Comparative Study”" we have introduced some of the most interesting user interface software for developing applications with Arduino modules. A brief comparison of the most used Graphical interfaces is done based on student’s feedback and experiment. The first scenario was a questionnaire presented to License L3 students and Master students in their final project work. The second scenario is taken from research’s documentation from the web. We concluded that students like to have GUI in their applications however they prefer simplicity, clearness in the GUI and real-time interaction.

In the chapter "Deep Neural Network to Forecast Stock Market Price", the forecasting of futurity open and close asking price of Dow Jones Industrial Average (DJIV) has been performed utilization deep neural network (DNN). The Long short term memory (LSTM) network was used to predict values of futurity time steps of a sequence of opening and closing into Dow Jones Industrial Average stock market. The LSTM network learns to forecast the value of the next step. By train the LSTM network, we have expect the value of future time steps of open and close of the stock market. The performance of the proposed technique is promising for DJIV stock market expectation. Artificial neural networks (ANN) have been used for years as a means to expect stock exchange prices. While it is difficult to expect with classical statistical and econometric procedures because of nonlinear connections and the ability of neural networks to model nonlinear relations without a priori presumptions. The neural networks used in time series forecasting have enhanced because of the rising of Deep Learning (DL). Deep neural network has been used to train a complex nonlinear relationship. Deep Learning schemes have promising achievements in many research areas such as stock price expectation.