Wyniki wyszukiwania - Biblioteka Nauki

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Multi-factor signcryption scheme for secure authentication using hyper elliptic curve cryptography and bio-hash function

100%

Rajasekar V. , Premalatha J. , Sathya K.

Bulletin of the Polish Academy of Sciences. Technical Sciences

2020

tom Vol. 68, nr 4

923--935

Among rapid development of wireless communication, technology cryptography plays a major role in securing the personal information of the user. As such, many authentication schemes have been proposed to ensure secrecy of wireless communication but they fail to meet all the required security goals. The proposed signcryption scheme uses multi-factor authentication techniques such as user biometrics, smart card and passwords to provide utmost security of personal information. In general, wireless devices are susceptible to various attacks and resource constraint by their very nature. To overcome these challenges a lightweight cryptographic scheme called signcryption has evolved. Signcryption is a logical combination of encryption and digital signature in a single step. Thereby it provides necessary security features in less computational and communication time. The proposed research work outlines the weaknesses of the already existing Cao et al.’s authentication scheme, which is prone to biometric recognition error, offline password guessing attack, impersonation attack and replay attack. Furthermore, the proposed study provides an enhanced multi-factor authentication scheme using signcryption based on hyper elliptic curve cryptography and bio-hash function. Security of the proposed scheme is analyzed using Burrows-Abadi-Needham logic. This analysis reveals that the proposed scheme is computational and communication-efficient and satisfies all the needed security goals. Finally, an analysis of the study results has revealed that the proposed scheme protects against biometric recognition error, password guessing attack, impersonation attack, DoS attack and dictionary attack.

Ensemble machine learning methods to predict the balancing of ayurvedic constituents in the human body

75%

Rajasekar V. , Krishnamoorthi S. , Saracevic M. , Pepic D. , Zajmovic M. , Zogic H.

Computer Science

2022

tom T. 23 (1)

117--132

In this paper, we demonstrate the result of certain machine-learning methods like support vector machine (SVM), naive Bayes (NB), decision tree (DT), k-nearest neighbor (KNN), artificial neural network (ANN), and AdaBoost algorithms for various performance characteristics to predict human body constituencies. Ayurveda-dosha studies have been used for a long time, but the quantitative reliability measurement of these diagnostic methods still lags. The careful and appropriate analysis leads to an effective treatment to predict human body constituencies. From an observation of the results, it is shown that the AdaBoost algorithm with hyperparameter tuning provides enhanced accuracy and recall (0.97), precision and F-score (0.96), and lower RSME values (0.64). The experimental results reveal that the improved model (which is based on ensemble-learning methods) significantly outperforms traditional methods. According to the findings, advancements in the proposed algorithms could give machine learning a promising future.