Search In this Thesis
   Search In this Thesis  
العنوان
Performance Enhancement and Security of Body Area Sensor Network Using Artificial Intelligence /
المؤلف
El-Banaa, Alaa Mohamed Ali.
هيئة الاعداد
باحث / آلاء محمد علي البنا
مشرف / محمد السعيد نصر
مشرف / رؤيات اسماعيل عبد الفتاح الصعيدي
مناقش / مجدي زكريا رشاد
مناقش / سامح عاطف نابليون
الموضوع
Electronics. Electrical Communications Engineering.
تاريخ النشر
2024.
عدد الصفحات
70 p. :
اللغة
الإنجليزية
الدرجة
ماجستير
التخصص
الهندسة الكهربائية والالكترونية
تاريخ الإجازة
10/9/2024
مكان الإجازة
جامعة طنطا - كلية الهندسه - هندسة الالكترونيات والاتصالات الكهربية
الفهرس
Only 14 pages are availabe for public view

from 95

from 95

Abstract

Mobile Ad hoc Networks (MANETs) face standardization issues such as incorrect transmission and vulnerability to unauthorized node access, raising significant security concerns, particularly regarding authentication procedures. To address these challenges, researchers explore innovative methods to enhance authentication mechanisms within MANETs. In this research, we present a novel solution that integrates the Body Area Network (BAN) system for capturing medical data from sensors such as ECG and EEG, facilitating data transmission across MANETs. Additionally, we utilize the hybrid Elgamal algorithm for encrypting medical data, enhanced with fingerprint biometrics to reinforce the encryption process and enhance network security. Furthermore, we conduct comparative analyses by exploring different key sizes and generation techniques, evaluating system performance through the calculation of False Acceptance Rate (FAR), False Rejection Rate (FRR), and Equal Error Rate (ERR) across varying threshold values for patient authentication. Additionally, we evaluate the Genuine Acceptance Rate (GAR) specifically for genuine patients within the system to highlight the effectiveness of authentication in the system. Our results reveal an optimal ERR of 0.375 with a threshold of 0.24, achieving a balance between error acceptance and rejection rates. Moreover, the GAR, representing the authentication rate, is determined to be 96.3%, confirming the effectiveness of the proposed secure system. Through practical testing and analysis, our study demonstrates the flexibility and strength of the proposed multimodal biometric authentication system, offering a promising solution for secure communication in dynamic MANET environments with limited resources. Another proposed solution combines multimodal biometric authentication with RSA and AES encryption, offering robust security for user authentication and data protection in MANETs. This comprehensive approach effectively mitigates risks such as unauthorized access and data tampering, making it essential for secure communication in dynamic MANET environments with limited resources. Our system incorporates face and fingerprint biometrics for encryption, significantly enhancing network security. Practical testing demonstrates a high authentication rate of 92.42%, accompanied by minimal processing times: 0.042 ms for key generation, 0.019 ms for encryption, and 0.032 ms for decryption, utilizing a 1024-bit key size. These results highlight the resilience and efficiency of our secure system.