Shodhshauryam, International Scientific Refereed Research Journal

Available online at : www.shisrrj.com

© 2024 SHISRRJ | Volume 7 | Issue 2
ISSN : 2581-6306 doi : https://doi.org/10.32628/SHISRRJ

Medilocator
K. Padmanaban1, T. Nandini2
1Assistant Professor, Department of MCA, Annamacharya Institute of Technology & Sciences, Tirupati, Andhra Pradesh,
India
2Post Graduate, Department of MCA, Annamacharya Institute of Technology & Sciences, Tirupati, Andhra Pradesh,

India

Article Info ABSTRACT

Publication Issue : Mobile Cloud Computing (MCC) has emerged as a transformative

March-April-2024 technological convergence, offering unprecedented advantages in terms of
Volume 7, Issue 2 mobility, scalability, and accessibility for mobile applications and services.
However, this integration also introduces critical data security challenges
that necessitate immediate attention and innovative solutions. This project
Page Number : 114-120
endeavors to comprehensively address and mitigate the data security issues
inherent in Mobile Cloud Computing to ensure the confidentiality,
Article History integrity, and availability of sensitive data. The project acknowledges the
Received : 15 March 2024 multifaceted nature of security concerns in MCC, stemming from the
Published : 30 March 2024 dynamic characteristics of mobile devices, untrusted network
environments, and shared cloud resources.

Keywords: Symptom based disease, machine-learning algorithms and Cloud

Computing

I. INTRODUCTION with sensitive information traversing through

multiple channels and residing on remote servers.
Mobile Cloud Computing (MCC) has The risk of unauthorized access, data breaches,
revolutionized the way we interact with and and privacy violations looms large, necessitating
harness the power of digital information. It comprehensive solutions to minimize these issues.
seamlessly integrates mobile devices with the In this era of technological advancements,
limitless capabilities of cloud computing, offering Machine Learning (ML) emerges as a potent ally
users unprecedented convenience and flexibility. in fortifying data security within MCC. By
However, as this symbiotic relationship between leveraging ML algorithms, we can proactively
mobile devices and the cloud flourishes, it also detect and thwart potential security threats, adapt
amplifies the inherent data security challenges. to evolving attack strategies, and enhance user-
Data security in MCC is a paramount concern, centric security measures. This project delves into
the multifaceted realm of MCC data security,

Copyright © 2024 The Author(s): This is an open-access article distributed under the terms of the Creative 114
Commons Attribution 4.0 International License (CC BY-NC 4.0)
 K. Padmanaban et al Sh Int S Ref Res J, March-April-2024, 7 (2) : 114-120

exploring how ML can be harnessed to create Advantages of Proposed System

robust, adaptive, and responsive security By automating security processes with machine
mechanisms. Through innovative research and learning, organizations can potentially reduce the
practical implementation, we aim to pave the way costs associated with manual security monitoring,
for a safer and more secure mobile cloud- incident response, and data breach mitigation.
computing ecosystem, safeguarding the The proposed system is scalable, allowing it to
confidentiality and integrity of user data in an adapt to the evolving security needs of an
increasingly interconnected world. organization as it grows and faces new challenges
in the mobile cloud-computing environment.
II. EXISTING AND PROPOSED SYSTEM Machine learning enables risk-based
authentication, where additional security
A. Existing System measures are applied when a higher risk is
To enhance data security in Mobile Cloud detected, adding an extra layer of protection for
Computing, augment the existing system with sensitive data and transactions.
machine learning algorithms. Implement anomaly
detection models to identify unusual user III. LITERATURE SURVEY
behaviors, strengthening access controls through
adaptive authentication mechanisms. Employ 1. Sun, X., Wang, D., & Li, H. (2016). A Survey of
encryption and tokenization techniques to Mobile Cloud Computing Security Management.
safeguard data in transit and at rest. Regularly Future Generation Computer Systems, 52, 1-10.
update security protocols and conduct The paper, "A Survey of Mobile Cloud Computing
vulnerability assessments. Additionally, employ Security Management" by Sun, Wang, and Li
machine learning for predictive threat analysis, (2016) explores the critical domain of security
enabling proactive security measures. This holistic management within the context of mobile cloud
approach will mitigate data security issues and computing. This comprehensive survey delves into
ensure a robust mobile cloud computing the challenges and solutions in securing mobile
environment. cloud environments. It addresses issues such as
data privacy, authentication, and integrity,
B. Proposed System emphasizing their relevance due to the unique
To enhance data security in Mobile Cloud characteristics of mobile cloud computing.
Computing, we propose a robust solution The authors conduct a detailed analysis of security
leveraging machine learning. Our system employs management strategies and mechanisms, shedding
advanced encryption algorithms, anomaly light on encryption, access control, and
detection, and user behavior analysis to identify authentication techniques tailored for mobile
and mitigate security threats in real-time. cloud scenarios. While not the primary focus, the
Additionally, it incorporates secure authentication paper may briefly mention machine learning's
methods and periodic security updates to ensure potential role in security enhancement.
the utmost protection of sensitive data on mobile This survey contributes by providing an extensive
devices connected to the cloud. overview of security issues in mobile cloud

Volume 7, Issue 2, March-April-2024 | www.shisrrj.com 115

 K. Padmanaban et al Sh Int S Ref Res J, March-April-2024, 7 (2) : 114-120

computing, offering insights for researchers, Inventive Communication and Computational

practitioners, and decision-makers. It serves as a Technologies (ICICCT) (pp. 1859-1863).
valuable resource, summarizing the state of the art The paper "Mobile Cloud Computing: A Review
and guiding future research in this vital on Data Security" by Kumar, N., Jain, N., and
intersection of mobile and cloud technologies. Tiwari, P., presented at the International
2. Zhang, L., & Zhang, Z. (2016). Mobile Cloud Conference on Inventive Communication and
Computing Security: A Survey. IEEE Access, 4, Computational Technologies (ICICCT) in 2019,
5395-5406. focuses on examining the critical aspect of data
The paper titled "Mobile Cloud Computing security within the realm of mobile cloud
Security: A Survey" by Zhang and Zhang, computing.
published in IEEE Access in 2016, presents a In this paper, the authors conduct a
comprehensive overview of security issues in the comprehensive review of data security concerns,
context of Mobile Cloud Computing (MCC). The strategies, and technologies in the context of
authors conduct a survey to examine the existing mobile cloud computing. They likely explore
challenges, solutions, and research trends in MCC various aspects of data security, including
security. encryption methods, access control,
They explore various security aspects, including authentication, and privacy preservation
data privacy, authentication, authorization, and techniques specific to mobile cloud environments.
data integrity, and provide insights into how these The significance of this paper lies in its
concerns are unique in the MCC environment. contribution to understanding the state-of-the-art
The paper also discusses the role of encryption, practices and challenges in securing data within
access control, and authentication mechanisms in mobile cloud computing. It likely highlights the
addressing these security challenges. importance of safeguarding sensitive data as
Furthermore, the authors offer a valuable mobile devices increasingly rely on cloud
perspective on emerging security threats and resources for storage and processing. By
potential countermeasures. While not exclusively summarizing existing research and strategies, this
focused on machine learning, the paper may touch paper likely offers v
upon the use of machine learning for security
enhancement in MCC. IV. METHODOLOGY
In summary, "Mobile Cloud Computing Security:
A Survey" is a comprehensive resource that Data Collection:
outlines the key security issues in MCC, making it Gather data from diverse sources, including
a valuable reference for researchers, practitioners, healthcare institutions, to acquire information
and policymakers working in this rapidly evolving such as medical service ratings, user comments,
field. and facility details. Structure the data,
3. Kumar, N., Jain, N., & Tiwari, P. (2019). Mobile incorporating attributes like facility ID, user
Cloud Computing: A Review on Data Security. In reviews, service ratings, and geographic location.
Proceedings of the International Conference on

Volume 7, Issue 2, March-April-2024 | www.shisrrj.com 116

 K. Padmanaban et al Sh Int S Ref Res J, March-April-2024, 7 (2) : 114-120

Data Loading and Initial Exploration: They can specify their preferred date and time for
Load the collected dataset into the project the appointment.
environment. Perform initial data exploration to 5. Search Blood Group and View Data: The
identify unique values, assess data quality, and patients have a feature to get a data from each
detect any anomalies or missing values. Prepare hospital by searching blood group.
the dataset for further analysis by addressing data 5. View Reports: Patients can access their medical
preprocessing tasks such as data cleaning and reports and test results through this module. It
normalization. allows them to review their health information
Data Visualization: conveniently.
Utilize data visualization techniques to gain 6. Download Report: Patients can download and
insights into the dataset. Create visualizations such save their medical reports or test results for their
as bar plots, histograms, and geographical maps to records or to share with other healthcare
visualize the distribution of medical services, user providers.
ratings, and geographical coverage. Explore 7. View Maps: Patients access a feature to view
correlations between different attributes to doctors' locations on maps for better navigation
understand relationships within the dataset. and appointment planning. Patients can utilize the
User Interface Design: User Location API to see the locations of doctors.
Design an intuitive and user-friendly interface for For GPS location, we utilize an API to fetch and
the MediLocator platform, enabling users to easily display data such as latitude and longitude.
search for and access healthcare services. 8. Logout: Patients can log out of their accounts to
Incorporate features such as search filters, ensure the privacy and security of their health
location-based services, and user reviews to information.
enhance the user experience. Conduct usability
testing and gather feedback from users to refine V. EXPERIMENTAL SETUP
the platform's interface and functionality.
IMPLEMENATION Define the objectives clearly, focusing on
1. Registration: Patients register in the system by developing a system for tracking and locating
providing their personal details, contact medical equipment within a hospital setting.
information, and health history if required. Conduct thorough research on indoor tracking
2. Login: Registered patients can log in to their and localization systems to inform your planning.
accounts securely to access the system's Select appropriate hardware components like
functionalities and their health records. RFID tags, sensors, and beacons based on research
3. Provide Symptom: Patients use this module to and project requirements. Develop necessary
describe their symptoms and health concerns. This software components including data collection
information is crucial for doctors to understand modules, processing algorithms, and visualization
the patient's condition. interfaces.
4. Raise Appointment: Patients can request Build a prototype of the MediLocator system
appointments with doctors through this module. integrating chosen hardware and software
components. Identify and prepare a suitable test

Volume 7, Issue 2, March-April-2024 | www.shisrrj.com 117

 K. Padmanaban et al Sh Int S Ref Res J, March-April-2024, 7 (2) : 114-120

environment mirroring real-world conditions

where the system will operate, such as a hospital
ward. Conduct experiments to collect data on
tracking accuracy, response times, reliability, and
other relevant metrics. Analyze collected data
using statistical methods, machine learning
algorithms, or other analytical techniques.
Validate results obtained from experiments and
make necessary optimizations to hardware,
software, or system configuration. Adhere to
ethical guidelines, obtain approvals, and consider Here, the doctor will go for signup page he will
privacy when dealing with sensitive data or sigin the page.
human subjects. Document all aspects of the
experimental setup, including methodologies, B. Fig2
results, challenges, and lessons learned. Gather
feedback from stakeholders and potential users to Here the patient will go for register by entering
iterate and improve upon the experimental setup username, user email, enter password and then
and prototype. they will go for confirming the password

C. fig 3

Here first the admin will reach the website and

check for the available doctors, patients and will
go for checking the appointments and then they
logout

A. fig 1

Volume 7, Issue 2, March-April-2024 | www.shisrrj.com 118

 K. Padmanaban et al Sh Int S Ref Res J, March-April-2024, 7 (2) : 114-120

analysis to preemptively identify and mitigate

threats. It also enhances access control, enables
threat prediction, and reinforces authentication
methods. Secure data sharing and automated
updates further fortify the system. This proactive
approach, grounded in ML, ensures that sensitive
data remains safeguarded in the ever-evolving
landscape of mobile cloud computing, allowing
organizations to harness its advantages with
confidence in data security.

VII. FUTURE ENCHAMENT

Minimizing data security issues in Mobile Cloud

Computing (MCC) while leveraging machine
learning for future enhancement is crucial for
ensuring the privacy and integrity of sensitive
information in an increasingly connected world.
To address current security concerns, MCC
systems can employ advanced encryption
Analyzing datasets of these symptoms can enhance
techniques, secure authentication protocols, and
medical diagnosis and treatment strategies,
robust access controls. Machine learning plays a
improving healthcare outcomes.
pivotal role in threat detection and mitigation by
continuously analyzing data patterns to identify
D. fig 4
anomalies and potential breaches in real-time.
Future enhancements can focus on developing
adaptive machine learning models that evolve
with emerging threats, leveraging federated
learning to maintain data privacy, and integrating
A database schema for doctor appointments, technology for transparent and tamper-proof data
storing patient information, appointment dates, management. Additionally, collaborations
and symptoms, with a separate table for symptom between industry, academia, and policymakers are
reporting. vital to establish standardized security frameworks
VI. CONCLUSION that foster trust and confidence in MCC systems,
ultimately ensuring a safer and more resilient
In conclusion, integrating machine learning into mobile computing environment.
mobile cloud computing is a pivotal strategy for
bolstering data security. ML enables dynamic
encryption, anomaly detection, and behavioral

Volume 7, Issue 2, March-April-2024 | www.shisrrj.com 119

 K. Padmanaban et al Sh Int S Ref Res J, March-April-2024, 7 (2) : 114-120

VIII. REFERENCES

[1]. Sun, X., Wang, D., & Li, H. (2016). A Survey

of Mobile Cloud Computing Security
Management. Future Generation Computer
Systems, 52, 1-10.
[2]. Kumar, N., Jain, N., & Tiwari, P. (2019).
Mobile Cloud Computing: A Review on
Data Security. In Proceedings of the
International Conference on Inventive
Communication and Computational
Technologies (ICICCT) (pp. 1859-1863).
[3]. Zhang, H., & Cai, Z. (2019). A Lightweight
Security Framework for Mobile Cloud
Computing Based on Machine Learning.
IEEE Access, 7, 26433-26444.
[4]. Fernández-Caramés, T. M., & Fraga-Lamas,
P. (2018). A Review on the Use of
Blockchain for the Internet of Things. IEEE
Access, 6, 32979-33001.
[5]. Puthal, D., Malik, N., Mohanty, S. P., &
Kougianos, E. (2019). Everything You
Wanted to Know About Smart Cities: The
Internet of Things Is the Backbone. IEEE
Consumer Electronics Magazine, 8(2), 20-
32.
[6]. Rahman, M. S., Islam, S. H., & Kwak, D.
(2018). A Comprehensive Study on Internet
of Things. In Proceedings of the 8th
International Conference on Computer and
Automation Engineering (ICCAE) (pp. 20-
24).

Volume 7, Issue 2, March-April-2024 | www.shisrrj.com 120