MARC details
| 000 -LEADER |
|---|
| fixed length control field |
07028namaa22004211i 4500 |
| 003 - CONTROL NUMBER IDENTIFIER |
|---|
| control field |
EG-GICUC |
| 005 - أخر تعامل مع التسجيلة |
|---|
| control field |
20260204102824.0 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION |
|---|
| fixed length control field |
260124s2025 ua a|||frm||| 000 0 eng d |
| 040 ## - CATALOGING SOURCE |
|---|
| Original cataloguing agency |
EG-GICUC |
| Language of cataloging |
eng |
| Transcribing agency |
EG-GICUC |
| Modifying agency |
EG-GICUC |
| Description conventions |
rda |
| 041 0# - LANGUAGE CODE |
|---|
| Language code of text/sound track or separate title |
eng |
| Language code of summary or abstract |
eng |
| -- |
ara |
| 049 ## - Acquisition Source |
|---|
| Acquisition Source |
Deposit |
| 082 04 - DEWEY DECIMAL CLASSIFICATION NUMBER |
|---|
| Classification number |
006.31 |
| 092 ## - LOCALLY ASSIGNED DEWEY CALL NUMBER (OCLC) |
|---|
| Classification number |
006.31 |
| Edition number |
21 |
| 097 ## - Degree |
|---|
| Degree |
M.Sc |
| 099 ## - LOCAL FREE-TEXT CALL NUMBER (OCLC) |
|---|
| Local Call Number |
Cai01.18.11.M.Sc.2025.Sa.M |
| 100 0# - MAIN ENTRY--PERSONAL NAME |
|---|
| Authority record control number or standard number |
Samy Elsayed Teleb Hassan, |
| Preparation |
preparation. |
| 245 10 - TITLE STATEMENT |
|---|
| Title |
Machine learning approach for detecting artificial inflation of SMS traffic / |
| Statement of responsibility, etc. |
by Samy Elsayed Teleb Hassan ; Supervision Prof. Dr. Ammar Mohammed Ammar Mohammed. |
| 246 15 - VARYING FORM OF TITLE |
|---|
| Title proper/short title |
نهج تعلم الآلة لاكتشاف التضخم الاصطناعي لحركة الرسائل النصية |
| 264 #0 - PRODUCTION, PUBLICATION, DISTRIBUTION, MANUFACTURE, AND COPYRIGHT NOTICE |
|---|
| Date of production, publication, distribution, manufacture, or copyright notice |
2025. |
| 300 ## - PHYSICAL DESCRIPTION |
|---|
| Extent |
88 Leaves : |
| Other physical details |
illustrations ; |
| Dimensions |
30 cm. + |
| Accompanying material |
CD. |
| 336 ## - CONTENT TYPE |
|---|
| Content type term |
text |
| Source |
rda content |
| 337 ## - MEDIA TYPE |
|---|
| Media type term |
Unmediated |
| Source |
rdamedia |
| 338 ## - CARRIER TYPE |
|---|
| Carrier type term |
volume |
| Source |
rdacarrier |
| 502 ## - DISSERTATION NOTE |
|---|
| Dissertation note |
Thesis (M.Sc)-Cairo University, 2025. |
| 504 ## - BIBLIOGRAPHY, ETC. NOTE |
|---|
| Bibliography, etc. note |
Bibliography: pages 81-88. |
| 520 #3 - SUMMARY, ETC. |
|---|
| Summary, etc. |
Detecting artificially inflated SMS traffic is crucial in telecommunications to <br/>maintain network integrity amid rising fraudulent activities like SMS spamming. <br/>This thesis explores machine learning techniques for identifying such anomalies, <br/>comparing four models: RandomForestClassifier, GradientBoosting, Support <br/>Vector Machine (SVM), and Naive Bayes (GaussianNB). Utilizing a dataset of <br/>12,500 SMS instances 10,000 labeled as artificially inflated and 2,500 as normal. <br/>The study examines features including sender and recipient numbers, mobile country <br/>code (MCC), mobile network code (MNC), country, and network, all preprocessed <br/>for modeling. <br/>The primary goal is to evaluate each model's effectiveness in distinguishing <br/>artificially inflated SMS traffic from normal messages, focusing on metrics like <br/>precision, recall, and F1-scores. RandomForestClassifier achieved high accuracy <br/>with a precision of 0.91 for AIT and 1.00 for normal traffic; however, it had a lower <br/>recall for normal traffic (0.59), indicating challenges in identifying certain normal <br/>instances. The SVM model, despite its proficiency in high-dimensional spaces, <br/>showed lower precision and recall for normal traffic, suggesting difficulties in <br/>classifying non-inflated messages. GaussianNB performed poorly for normal traffic, <br/>with precision, recall, and F1-scores near zero, indicating its limitations with <br/>complex or imbalanced datasets. In contrast, GradientBoostingClassifier delivered <br/>promising results, with performance metrics comparable to RandomForestClassifier, <br/>demonstrating its effectiveness in detecting artificially inflated SMS traffic. <br/>The thesis analyzes each model's strengths and weaknesses, identifying contexts <br/>where one may be more suitable than others. RandomForestClassifier and <br/>GradientBoostingClassifier emerged as the most reliable for detecting artificial <br/>inflation, with GradientBoosting showing greater resilience with imbalanced <br/>datasets. SVM's performance was hindered by its inability to effectively identify <br/><br/><br/>v <br/><br/>normal traffic in this scenario, while GaussianNB's simplifying assumptions limited <br/>its utility. <br/>This comprehensive evaluation underscores the importance of selecting appropriate <br/>machine learning models based on data characteristics and task requirements. While <br/>advanced models like RandomForest and GradientBoosting offer superior <br/>performance in this domain, simpler models such as Naive Bayes or SVM may still <br/>be applicable in specific scenarios with proper data preparation. Future research <br/>could explore other algorithms, hyperparameter optimization, and incorporation of <br/>domain-specific features to enhance detection accuracy. <br/>In conclusion, the study confirms that machine learning effectively identifies <br/>artificially inflated SMS traffic, providing telecom operators and fraud detection <br/>systems with viable solutions to mitigate SMS-based fraud risks. Comparative <br/>analysis offers valuable insights for selecting suitable techniques based on data <br/>availability, computational resources, and specific detection system objectives. . |
| 520 #3 - SUMMARY, ETC. |
|---|
| Summary, etc. |
يُعد تضخم حركة الرسائل النصية القصيرة (SMS) بشكلٍ اصطناعي من أخطر التحديات التي تواجه شركات الاتصالات، لما له من آثار مالية وتشغيلية سلبية. تهدف هذه الدراسة إلى تطوير نموذج تنبؤي يعتمد على تقنيات تعلم الآلة لاكتشاف الرسائل النصية المصطنعة التي تُستخدم غالبًا في هجمات احتيالية مثل إساءة استخدام رموز التحقق (OTP).<br/>تركز الدراسة على تحليل بيانات حقيقية مكونة من 12,500 رسالة قصيرة، منها 10,000 تم تصنيفها كحركة مضخّمة اصطناعيًا و2,500 رسالة طبيعية. شملت الدراسة استخراج وتحليل عدد من الخصائص (features) المرتبطة بالمرسل، المستلم، ومعلومات الشبكة مثل رمز الدولة (MCC) ومُشغّل الشبكة (MNC)، وتمت معالجة البيانات باستخدام تقنيات مناسبة للتشفير والتنظيف.<br/>تم بناء وتقييم أربعة نماذج تصنيف باستخدام خوارزميات تعلم الآلة: Random Forest، Gradient Boosting، Support Vector Machine (SVM)، وGaussian Naive Bayes. وأظهرت النتائج أن نماذج Random Forest وGradient Boosting حققت أعلى أداء، حيث تفوقت في الكشف عن الرسائل الاصطناعية بدقة عالية، بينما أظهرت خوارزميات SVM وNaive Bayes أداءً أقل خاصة في التعامل مع البيانات غير المتوازنة.<br/>تقدم هذه الدراسة مساهمة عملية في تعزيز أمان شبكات الاتصالات، من خلال تقديم إطار عمل قابل للتطبيق يُمكّن مزودي الخدمة من التعرف المبكر على التضخم الاصطناعي للرسائل، مما يدعم تحسين الكفاءة التشغيلية وتقليل الفاقد المالي. |
| 530 ## - ADDITIONAL PHYSICAL FORM AVAILABLE NOTE |
|---|
| Issues CD |
Issues also as CD. |
| 546 ## - LANGUAGE NOTE |
|---|
| Text Language |
Text in English and abstract in Arabic & English. |
| 650 #0 - SUBJECT ADDED ENTRY--TOPICAL TERM |
|---|
| Topical term or geographic name entry element |
Machine learning |
| 650 #0 - SUBJECT ADDED ENTRY--TOPICAL TERM |
|---|
| Topical term or geographic name entry element |
تعلم الآلة |
| 653 #1 - INDEX TERM--UNCONTROLLED |
|---|
| Uncontrolled term |
Machine Learning |
| -- |
Fraud Detection |
| -- |
SMS |
| -- |
Artificial Inflation |
| -- |
Data Classification |
| -- |
Pattern Recognition |
| -- |
Mobile Networks |
| -- |
التعلم الآلي |
| -- |
كشف الاحتيال |
| 700 0# - ADDED ENTRY--PERSONAL NAME |
|---|
| Personal name |
Ammar Mohammed Ammar Mohammed |
| Relator term |
thesis advisor. |
| 900 ## - Thesis Information |
|---|
| Grant date |
01-01-2025 |
| Supervisory body |
Ammar Mohammed Ammar Mohammed |
| Universities |
Cairo University |
| Faculties |
Faculty of Graduate Studies for Statistical Research |
| Department |
Department of Data Science |
| 905 ## - Cataloger and Reviser Names |
|---|
| Cataloger Name |
Shimaa |
| Reviser Names |
Eman Ghareb |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) |
|---|
| Source of classification or shelving scheme |
Dewey Decimal Classification |
| Koha item type |
Thesis |
| Edition |
21 |
| Suppress in OPAC |
No |