CERIST DIGITAL LIBRARY
http://www.cerist.dz:80
Le système de dépôt numérique DL collecte, emmagasine, indexe, archive, et diffuse du matériel de recherche en format numérique.2018-09-18T14:43:36ZLeveraging Learners' Activity Logs for Course Reading Analytics Using Session-Based Indicators
http://dl.cerist.dz/handle/CERIST/927
Leveraging Learners' Activity Logs for Course Reading Analytics Using Session-Based Indicators
Sadallah, Madjid; Encelle, Benoît; Maredj, Azze-Eddine; Prié, Yannick
A challenge that course authors face when reviewing their contents is to detect how to improve their courses in order to meet the expectations of their learners.
In this paper, we propose an analytical approach that exploits learners' logs of reading to provide authors with insightful data about the consumption of their courses.
We first model reading activity using the concept of reading-session and propose a new and efficient session identification. We then elaborate a list of indicators computed using learners' reading sessions that allow to represent their behaviour and to infer their needs. We evaluate our proposals with course authors and learners using logs from a major e-learning platform. Interesting results were found. This demonstrates the effectiveness of the approach in identifying aspects and parts of a course that may prevent it from being easily read and understood, and for guiding the authors through the analysis and review tasks.
2018-01-01T00:00:00ZVisual Data Mining by Virtual Reality for Protein-Protein Interaction Networks
http://dl.cerist.dz/handle/CERIST/926
Visual Data Mining by Virtual Reality for Protein-Protein Interaction Networks
Aouaa Noureddine;; Gherbi Rachid; Meziane Abdelkrim; Hayat Hadjar; Insaf Setitra
Currently, visualization techniques in the genetic field require a very important modeling phase in terms of resources. Traditional modeling techniques (in two dimensions) are rarely adapted to manage and process this mass of information. To overcome this kind of problem, we propose to use a new graph modeling technique that, used in conjunction with the concept of virtual reality, allows biologists to have a wide visibility through several points of view, thus facilitating them the exploration of massive data.
The general principle of our approach is to build a biological network model in the form of a graph with a spatial representation adapted to the visualization of biological networks in a virtual environment. The results show that the improvement of the node distribution algorithm allows a better and more intuitive visualization, compared to the equivalent two-dimensional representations.
2018-03-28T00:00:00ZRandom input helps searching predecessors
http://dl.cerist.dz/handle/CERIST/924
Random input helps searching predecessors
Belazzougui, Djamal; Kaporis, Alexis C.; Spirakis, Paul G.
A data structure problem consists of the finite sets: D of data, Q of
queries, A of query answers, associated with a function f : D ×Q → A.
The data structure of file X is “static” (“dynamic”) if we “do not”
(“do”) require quick updates as X changes. An important goal is to
compactly encode a file X ∈ D, such that for each query y ∈ Q, function
f(X, y) requires the minimum time to compute an answer in A. This
goal is trivial if the size of D is large, since for each query y ∈ Q,
it was shown that f(X, y) requires O(1) time for the most important
queries in the literature. Hence, this goal becomes interesting to study
as a trade off between the “storage space” and the “query time”, both
measured as functions of the file size n = |X|. The ideal solution would
be to use linear O(n) = O(|X|) space, while retaining a constant O(1)
query time. However, if f(X, y) computes the static predecessor search
(find largest x ∈ X : x ≤ y), then Ajtai [Ajt88] proved a negative
result. By using just n
O(1) = |X|
O(1) data space, then it is not possible
to evaluate f(X, y) in O(1) time ∀y ∈ Q. The proof exhibited a bad
distribution of data D, such that ∃y
∗ ∈ Q (a “difficult” query y
∗
), that
f(X, y∗
) requires ω(1) time. Essentially [Ajt88] is an existential result,
resolving the worst case scenario. But, [Ajt88] left open the question:
do we typically, that is, with high probability (w.h.p.) 1
encounter
such “difficult” queries y ∈ Q, when assuming reasonable distributions
with respect to (w.r.t.) queries and data? Below we make reasonable
assumptions w.r.t. the distribution of the queries y ∈ Q, as well as
w.r.t. the distribution of data X ∈ D. In two interesting scenarios
studied in the literature, we resolve the typical (w.h.p.) query time.
2018-06-17T00:00:00ZAngle Minimization and Graph Analysis for text line segmentation in handwritten documents
http://dl.cerist.dz/handle/CERIST/923
Angle Minimization and Graph Analysis for text line segmentation in handwritten documents
Setitra, Insaf; Meziane, Abdelkrim
We propose in this paper a novel approach for text
line segmentation in handwritten documents. The approach is
based on angle minimization and graph analysis for text lines
extraction. We apply our approach on images of ICDAR 2013
Handwriting Segmentation Contest, and give details about its
robustness against skew and text orientation. We compare the
approach to relevant text line segmentation state of art methods,
apply it to Algerian manuscripts and report relevant results
2018-07-08T00:00:00Z