Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Annals of Computer Science and Information Systems

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Clustering Corticosteroids Responsiveness in Sepsis Patients using Game-Theoretic Rough Sets

Hellali Rahma, Dagdia Zaineb Chelly, Zeitouni Karine

Annals of Computer Science and Information Systems

2023

Vol. 35

545--556

Performing data mining tasks in the medical domain poses a significant challenge, mainly due to the uncertainty present in patients' data, such as incompleteness or missingness. In this paper, we focus on the data mining task of clustering corticosteroid (CS) responsiveness in sepsis patients. We address the issue and challenge of missing data by applying Game-Theoretic Rough Sets (GTRS) as a three-way decision approach. Our study considers the APROCCHS cohort, comprising 1240 sepsis patients, provided by the Assistance Publique--Hôpitaux de Paris (AP-HP), France. Our experimental results on the APROCCHS cohort indicate that GTRS maintains the trade-off between accuracy and generality, demonstrating its effectiveness even when increasing the number of missing values.

Towards a granular computing framework for multiple aspect trajectory representation and privacy preservation: research challenges and opportunities

Dagdia Zaineb Chelly, Bogorny Vania

Annals of Computer Science and Information Systems

2022

Vol. 32

65--72

In recent years, there has been a lot of research on trajectory data analysis and mining. Despite the fact that trajectories are multidimensional data characterized by the spatial, the temporal, as well as the semantic aspect, few are the studies that have taken into account all of these three dimensions. Apart from these dimensions that should be considered all together for an efficient trajectory data analysis and mining, it should be also made feasible to represent trajectories from several points of view, which is called multiple aspect representation. State-of-the-art works are typically restricted to a single trajectory representation, which limits the identification of a variety of key patterns. These multiple aspect trajectories are quite rich that they reveal sensitive information, making the user's privacy vulnerable; hence, raising several challenges when it comes to privacy preservation. In this paper, we show that there is a need to consider granular computing for multiple aspect trajectory representation and privacy preservation, and present new research challenges and opportunities in this concern.