On the Use of Unsupervised Techniques for Fraud Detection in VoIP Networks

Rebahi, Yacine; Thanh, Tran Quang; Busse, Roman; Lorenz, Pascal

doi:10.1016/b978-0-12-411474-6.00022-0

Cited by 3 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the inactivity periods (0 call) are not taken into account when computing the long-term signatures. More detail can be found at [16] and our implementions have been partly published as open source at [17]. Moreover, in the framework, we have proposed two approaches that, in our point of view, will bring advantages when adopting in real environments by MNOs as describe in the following:…”

Section: A Mitigating Malicious Activitiesmentioning

confidence: 99%

A DIAMETER based security framework for mobile networks

Thanh

Rebahi

Magedanz

2014

2014 International Conference on Telecommunications and Multimedia (TEMU)

Self Cite

View full text Add to dashboard Cite

After several decades of circuit switched technology, mobile telephony is moving towards all-IP network architecture. The convergence to IP, on a one hand, brings many advantages, but makes mobile networks easier to be attacked. In this paper, a security framework is discussed addressing two security challenges: DIAMETER-related threats and subscriber malicious activities. The former is taken into account as the fast growing of DIAMETER in the evolving 4G mobile networks. The latter can be mitigated by analyzing DIAMETER signaling traffic and applying appropriate techniques to them. The framework being investigated is flexible and some of the developed components are already open source and being used by the DIAMETER community

show abstract

Section: A Mitigating Malicious Activitiesmentioning

confidence: 99%

A DIAMETER based security framework for mobile networks

Thanh

Rebahi

Magedanz

2014

2014 International Conference on Telecommunications and Multimedia (TEMU)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although it is known that fraud is used in many areas such as banking, telecommunications, finance, health, and academic processes, within the scope of this study, the problem of telecommunications fraud will be investigated, and various evaluations and suggestions will be given for Turkey. About 5% of the annual revenue of telecommunications operators is lost due to fraud and this rate is increasing every passing year (Rebahi et al, 2014). In 2019, it was measured that there was approximately $ 28.3 billion in lost revenue due to fraud cases in the telecommunications industry worldwide (Communications Fraud Control Association, 2019).…”

Section: Introductionmentioning

confidence: 99%

Regulatory Recommendations for Fraud Problem in The Turkish Telecommunication Sector

BAYRAM,

ERGÜNER ÖZKOÇ

2023

AJIT-e

View full text Add to dashboard Cite

Fraud has been a persistent issue throughout human history. As technology continues to advance in various fields, fraudulent activities adapt and evolve accordingly. The telecommunication industry, in particular, has undergone significant transformations since the early 2000s with the advent of mobile technologies. It is evident that telecommunication fraud has seen a substantial increase during this time, leading to serious financial and reputational damage. Therefore, combating and preventing fraud has become a crucial task in the telecommunication sector, as it is in all industries. This study delves into the topic of fraud, with a particular emphasis on telecommunication fraud. It investigates the experiences and efforts made to minimize and prevent fraud globally. Additionally, the study includes a focus group analysis involving two mobile operators in Turkey, aiming to understand the current situation and industry expectations concerning telecommunication fraud within the country. After evaluating the information gathered and examining the existing efforts, the study offers a series of regulatory recommendations for reducing and preventing fraud in the Turkish telecommunication sector.

show abstract

Integrating Real-Time Location Systems with Electronic Medical Records: A Machine Learning Approach for In-Hospital Fall Risk Prediction

Kim,

Seo,

Kwon

et al. 2024

Preprint

View full text Add to dashboard Cite

Hospital falls are the most prevalent adverse event in healthcare, posing significant risks to patient health outcomes and institutional care quality. The effectiveness of several fall prediction models currently in use is limited by various clinical factors. This study explored the efficacy of merging real-time location system (RTLS) data with clinical information to enhance the accuracy of in-hospital fall predictions. The model performances were compared based on the clinical data, RTLS data, and a hybrid approach using various evaluation metrics. The RTLS and integrated clinical data were obtained from 22,201 patients between March 2020 and June 2022. From the initial cohort, 118 patients with falls and 443 patients without falls were included. Predictive models were developed using the XGBoost algorithm across three distinct frameworks: clinical model, RTLS model, and clinical + RTLS model. The model performance was evaluated using metrics, such as AUROC, AUPRC, accuracy, PPV, sensitivity, specificity, and F1 score. Shapley additive explanation values were used to enhance the model interpretability. The clinical model yielded an AUROC of 0.813 and AUPRC of 0.407. The RTLS model demonstrated superior fall prediction capabilities, with an AUROC of 0.842 and AUPRC of 0.480. The clinical + RTLS model excelled further, achieving an AUROC of 0.853 and AUPRC of 0.497. Feature importance analysis revealed that movement patterns of patients on the last day of their stay were significantly associated with falls, together with elevated RDW levels, sedative administration, age. This study underscored the advantages of combining RTLS data with clinical information to predict in-hospital falls more accurately. This innovative technology-driven approach may enhance early fall risk detection during hospitalization, potentially preventing falls, improving patient safety, and contributing to more efficient healthcare delivery.

show abstract

On the Use of Unsupervised Techniques for Fraud Detection in VoIP Networks

Cited by 3 publications

References 8 publications

A DIAMETER based security framework for mobile networks

A DIAMETER based security framework for mobile networks

Regulatory Recommendations for Fraud Problem in The Turkish Telecommunication Sector

Integrating Real-Time Location Systems with Electronic Medical Records: A Machine Learning Approach for In-Hospital Fall Risk Prediction

Contact Info

Product

Resources

About