No abstract

No abstract

While mobile hosts are evolving into full-IP enabled devices, there is a greater demand to provide a more flexible, reconfigurable, and scalable security mechanism in mobile communication systems beyond 3G (B3G). Work has already begun on such an “all-IP” end-to-end solution, commonly referred to as 4G systems. Fully fledged integration between heterogeneous networks, such as 2.5G, UMTS, WLAN, Bluetooth, and the Internet, demands fully compatible, time-tested, and reliable mechanisms to depend on. SSL protocol has proved its effectiveness in the wired Internet and it will probably be the most promising candidate for future wireless environments. In this paper, we discuss existing problems related to authentication and key agreement (AKA) procedures, such as compromised authentication vectors attacks, as they appear in current 2/2.5G/3G mobile communication systems, and propose how SSL, combined with public key infrastructure (PKI) elements, can be used to overcome these vulnerabilities. In this B3G environment, we perceive authentication as a service, which has to be performed at the higher protocol layers irrespective of the underlying network technology. Furthermore, we analyze the effectiveness of such a solution, based on measurements of a “prototype” implementation. Performance measurements indicate that SSL-based authentication can be possible in terms of service time in future wireless systems, while it can simultaneously provide both the necessary flexibility to network operators and a high level of confidence to end users.

No abstract

No abstract

No abstract

This study addresses the breast cancer diagnosis and prognosis problem by employing two neural network architectures with the Wisconsin diagnostic and prognostic breast cancer (WDBC/WPBC) datasets. A probabilistic approach is dedicated to solve the diagnosis problem, detecting malignancy among cases (instances) as derived from fine needle aspirate (FNA) tests, while the second architecture estimates the time interval that possibly contains the right endpoint of disease-free survival (DFS) of the patient. The accuracy of the neural classifiers reaches nearly 98% for the diagnosis and 93% for the prognosis problem, while the prognostic recurrence predictions were evaluated using survival analysis through the Kaplan-Meier approximation method. Both architectures were compared with other similar approaches. The robustness and real-time response of the proposed classifiers were further tested over the web as a potential integrated web-based decision support system.

No abstract