ATM SIMULATION SYSTEM

Ms. ARDRA SURESH Ms. LEKSHMI BABU A

Dept of CSE Dept of CSE

Sree Buddha College Of Engineering , Elavumthitta Sree Buddha College Of Engineering,Elavumthitta

Pathanamthitta ,kerala ,India Pathanamthitta,kerala ,India

Mr . ABINE P KOSHY Mr. JOEL JIJI

Dept of CSE Dept of CSE

Sree Buddha College Of Engineering,Elavumthitta Sree Buddha College Of Engineering,Elavumthitta

Pathanamthitta,kerala ,India Pathanamthitta,kerala ,India

Ms. HIMA MOHAN

Asst.Professor, Dept of CSE
Sree Buddha College Of Engineering,Elavumthitta,

Pathanamthitta,kerala ,India

Abstract---- The Automated Teller Machine ATM Banking System is a banking application developed to perform

different banking services through the Automated Teller Machines. The all functions include the regular of the

transactions like cash deposits, cash withdrawals, balance enquiry, balance statements, savings account, and

current account; change PIN Number, Credit card Withdrawals and so on. The application design maintains the

information of the accounts of various customers including the information of the ATM cards, their types Credit

cards, Debit Cards and the transactions done by the customers through the ATM machine centers with co-relation

of the Banking Services. The stored details also include the information of the various centers in and around the

ATM services, which help in the relational maintenance of every transaction in the ATM Machine by the customers

with their concerned branch operations.

Keywords----- Mysql, java swing framework ,Eclipse.

i
 INTRODUCTION

The aim of the ATM Simulation System project is to build a Java based ATM (Automated Teller Machine) Simulation
System. The introduction of ATM’s by various banks have brought about freedom from the interminable queues in front
of withdrawal counters at banks. This ATM Simulation System requires the constant updating of records between the bank
servers and a spread out network of ATM’s.Security is the foundation of a good ATM system. This system will provide
for secure authenticated connections between users and the bank servers. The whole process will be automated right from
PIN (Personal Identification Number) validation to transaction completion. ATM Simulation System will enable two
important features of an ATM, reduction of human error in the banking system and the possibility of 24 hour personal
banking. The card details and PIN database will be a secure module that will not be open to routine maintenance, the only
possibility of access to this database will be through queries raised from an ATM in the presence of a valid bank ATM
card.

I. LITERATURE SURVEY

[1] CONTENT BASED SPAM DETECTION IN EMAIL USING BAYESIANCLASSIFIER

The system proposes a method for detecting and filtering spam emails using a Bayesian classifier algorithm.
The authors explain that email messaging is an essential contribution to data communication, but it is also
frequently used for hacking attacks, phishing attacks, and malicious attacks to attempt fraud and deception.
These attacks use emails to obtain personal credentials of users for financial gain. Emails with genuine content
may include phishing URLs for stealing usefuldata, and such emails are considered spam.

[2] EVALUATION ON THE EFFICIENCY OF HYBRID FEATURE SELECTION IN SPAM

EMAIL CLASSIFICATION
The system discusses a spam filtering technique that combines two types of feature selection methods in its
classification task. The system highlights the issue of spam and the importance of spam filtering systems. The
authors explain that despite the spam filtering system provided by emailservice providers, unwanted messages
still flood our electronic mailboxes. This issue has attracted many researchers to conduct research works on
fighting spam.

[3] INTEGRATED SPAM DETECTION FOR MULTILINGUAL EMAILS

The system proposes an integrated approach to increase the efficiency of detecting and filtering spam emails,
which are often used by cybercriminals to obtain valuable credentials. The approach isbased on a Bayesian
classification problem, where each email can be classified under any of the four scenarios: True Positive
(TP), True Negative (TN), False Positive (FP), and False Negative (FN). The system also reports precision and

ii
 recall as performance measures.

II. SYSTEM MODULES

A .Data Collection

Acquiring a substantial dataset of labelled emails is vital for effectively training and evaluating the machine
learning model. The dataset should encompass a diverse range of spam and non-spam (ham) emails to ensure
the model's robustness and generalization. Creating such a dataset can involve collecting emails from multiple
sources, manually labelling them as spam or ham, or utilizing existing spam filters that have already classified
emails. The dataset serves as the bedrock for training the model, allowing it to learn patterns and features that
differentiate between spam and legitimate emails accurately. The quality and diversity of the dataset greatly
influence the model's performance, ensuring its ability to handle real-world email classification scenarios.

B . Data Preprocessing

Data preprocessing involves preparing the collected email data for further analysis. Tokenization is performed
to break down the emails into individual words or tokens. Stop word removal eliminates common words (e.g.,
"and," "the," "is") that do not contribute significantly to the classification task.Stemming reduces words to
their root form (e.g., "running" becomes "run") to handle variations in word endings. Additionally, special
symbols, punctuation, and unwanted characters are removed to ensure cleaner and standardized text.
C . Feature Extraction and Selection

Feature extraction involves identifying and extracting relevant information from the email messages. This
includes considering features like the subject lines, body text, attachments, and links. In the case of Naive
Bayes, the model assumes the probability of a word appearing in a spam message is independent of other
words appearing in the same message. Therefore, each word becomes a feature, and its frequency or
presence in an email is used for classification.
D. Model Training and Evaluation

During this step, the Naive Bayes model is trained using the labelled dataset of spam and non-spam emails.
The training process entails inputting the extracted features and their respective labels into the model. By doing
so, the model learns the statistical patterns and relationships between the features and their corresponding
labels. After training, the model's performance is evaluated using aseparate test dataset. Evaluation metrics
like accuracy, precision, recall, and F1 score are computed to gauge the model's effectiveness in accurately
classifying emails. These metrics provide valuable insights into the model's performance and guide further
improvements, ensuring its reliability in distinguishing between spam and legitimate emails.

iii
 E . Model Deployment

After training and evaluating the model, it can be deployed for practical use, allowing users to access it through a user-
friendly interface. The Streamlit framework is often employed for creating interactive web applications, making it an
ideal choice for deploying the model. Through the deployed model, users can input new email messages, and the model
will predict whether they are spam or ham. This enables users to quickly and conveniently classify incoming emails,
ensuring that spam emails are filtered out and only legitimate emails reach their inbox.

VI. EXPERIMENTAL RESULT AND DISCUSSION

• Create Account Class: Define a class to represent an account. Each account will have attributes like name, pin
and balance. Methods will include checking balance, depositing funds, withdrawing funds, and transferring funds to
another account.
• Implement ATM Class: This class will handle user interactions like authentication, menu display, and executing
transactions.
• Authenticate User: The ATM class will authenticate users by matching the provided name and pin with the stored
account details.
• Display Menu: After successful authentication, display a menu with options like checking balance, depositing,
withdrawing, transferring, and exiting
• Error Handling: Implement error handling for invalid inputs and insufficient funds.

• Handle User Input: Based on the user’s choice, execute the corresponding action(checking balance, depositing,

withdrawing, transferring or exiting).

iv
v
V. SYSTEM ARCHITECTURE

vi
 VI. CONCLUSION
We can hereby conclude that:

1. The system effectively automated the functions involved in the processes being handled
manually before.

2. The cost & benefit analysis shows that the system was quite successful in saving costs for the
bank & generate equivalently huge benefits

3. The system is secure & scalable. The system design has been done keeping user-friendliness
and efficiency in mind.

VII.. REFERENCES

[1] J. Bowen. (2010). How ATMs Work. [Online].Available:

http://money.howstuffworks.com/atm3.htm,.
[2] M. Badmus. (2011). Nigerian Students and the ATM (Automated Teller
Machines).[Online].Available:http://www.upiu.com/other/2011/06/15/Nigerian-
students-and-theATMAutomated-Teller-Machines/UPIU-3801308194612/
[3] C. Robat. (2006). ATM Automatic Teller Machine. [Online]. Available:
http://www.thocp.net/hardware/atm.htm
[4] Wikipedia the Free Encyclopedia. (2010). Automated Teller Machine. [Online].
Available: http//:en.wikipedia.org,.
[5] R Hossain, et al., Designing an Atm Network Based on Distributed Database
Systems", no date.
[6] A. R. Rai, "Customer relationship management: Concepts and cases " New Delhi,
2008, pp. 97-98
[7] E. W. Croft and B. J. Spencer, "Fees and surcharging in automatic teller machine
networks: non-bank atm providers versus large banks", 2003
[8] R. Rajesh and T. Sivagnanasithi, "Banking theory: LAW & Practice,” New Delhi,
2009, pp 313-314.
[9] V. Skorpil “Simulation of ATM communication system”, 1-2 Oct. 2003,IEEE/Siberian Conference
on Control

and Communications (IEEE Cat. No.03EX687) 10.1109/SIBCON.2003.1335723

vii
[10] Guoming Sung, Wen Duon Chou, Xingxi Chen. “Packet Process with Deficit Round Robin ASIC
for
ATM/Ethernet Bridge.” Proceedings of the Tenth International Conference on Information and
Communication
Technologies and Development,4-January-2019 Published by : IEEE
[11] Peng, Tao, Lianying Sun, and Hong Bao. "Design and implementation of ATM simulation system
based on
MVC pattern." 2010 International Conference on Educational and Information Technology. Vol. 1.
IEEE, 201[4] Xu, Xiaoru, Zhihao Yang, and Yunting Xian. "ATM: Attribute-Based Privacy-Preserving
Task Assignment
and Incentive Mechanism for Crowdsensing." IEEE Access 9 (2021): 60923-60933
[12] Hudgell, Alison J., and R. M. Gingell. "Assessing the capacity of novel ATM systems." In 4th
USA/Europe Air
Traffic Management R&D Seminar. 2001
[13] Kreuz, Michael, Tanja Luchkova, and Michael Schultz. "Effect of restricted airspace on the ATM
system."
In WCTR Conference. 2016
[14] Bilimoria, Karl D., Banavar Sridhar, Shon R. Grabbe, Gano B. Chatterji, and Kapil S. Sheth.
"FACET: Future
ATM concepts evaluation tool." Air Traffic Control Quarterly 9, no. 1 (2001)

viii