The paper presents an artificial neural network based approach in support of cash demand forecasting for automatic teller machine (ATM). On the start phase a three layer feed-forward neural network was trained using Levenberg-Marquardt algorithm and historical data sets. Then ANN was retuned every week using the last observations from ATM. The generalization properties of the ANN were improved ...

We propose a new technique for interactive formal verification of temporal properties of UML state machines. We introduce a formal, operational semantics of UML state machines and give an overview of the proof method which is based on symbolic execution with induction. Usefulness of the approach is demonstrated by example of an automatic teller machine. The approach is implemented in the KIV sy...

An Automated Teller Machine (ATM) is a safety-critical and real-time system that is highly complicated in design and implementation. This paper presents the formal design, specification, and modeling of the ATM system using a denotational mathematics known as Real-Time Process Algebra (RTPA). The conceptual model of the ATM system is introduced as the initial requirements for the system. The ar...

Automated teller machines (ATM) have become a part and parcel of supermarkets, convenience stores, travel centers and banking. ATM is a real-time system that is very complex in design and application. This paper presents the formal design, requirement, a distributed approach for the ATM networks, and type of the ATM system. 