User profiles for S. Aridhi
Sabeur AridhiAssociate Professor (Maître de conférences), University of Lorraine Verified email at loria.fr Cited by 1749 |
Application of artificial intelligence to gastroenterology and hepatology
… A neural network that analyzes morphometric images of early-stage biopsies from patients
with Crohn’s disease identified those with disease progression with approximately 83.3% …
with Crohn’s disease identified those with disease progression with approximately 83.3% …
[HTML][HTML] The CAFA challenge reports improved protein function prediction and new functional annotations for hundreds of genes through experimental screens
Background The Critical Assessment of Functional Annotation (CAFA) is an ongoing, global,
community-driven effort to evaluate and improve the computational annotation of protein …
community-driven effort to evaluate and improve the computational annotation of protein …
Big graph mining: Frameworks and techniques
… if its support is greater than a minimum support threshold: s u p p o r t ( g ) > m i n S u p p . …
11, Hill et al.'s approach generates the set of frequent subgraphs by performing two …
11, Hill et al.'s approach generates the set of frequent subgraphs by performing two …
An experimental survey on big data frameworks
… per second varies between 375 KB/s and 385 KB/s in the case of Flink, and varies between
387 KB/s and 390 KB/s in the case of Storm and about 400 Mb/s in the case of Samza. This …
387 KB/s and 390 KB/s in the case of Storm and about 400 Mb/s in the case of Samza. This …
Preesm: A dataflow-based rapid prototyping framework for simplifying multicore dsp programming
… link for each core at 16 GB/s while the external DDR3 has a unique link to the processor
at 10.6 GB/s. More advanced features are representable in S-LAM such as the delegation of …
at 10.6 GB/s. More advanced features are representable in S-LAM such as the delegation of …
Accuracy and diversity-aware multi-objective approach for random forest construction
… First, a training sample T r i will be generated by using L i , I d S i and I d R i as follows: (1)
A set S i of instance indexes is generated by using the Algorithm 1 and Eq. (3) ( E is an array …
A set S i of instance indexes is generated by using the Algorithm 1 and Eq. (3) ( E is an array …
Pimm: Parameterized and interfaced dataflow meta-model for mpsocs runtime reconfiguration
…, JF Nezan, SS Bhattacharyya, S Aridhi - 2013 International …, 2013 - ieeexplore.ieee.org
Dataflow models of computation are widely used for the specification, analysis, and optimization
of Digital Signal Processing (DSP) applications. In this paper a new meta-model called …
of Digital Signal Processing (DSP) applications. In this paper a new meta-model called …
Improving memory-based user collaborative filtering with evolutionary multi-objective optimization
… subset of profiles P s index i d P s − p 0 , we generate the appropriate P s . Now, an … s , P s
can be generated as follows: First, we generate P s with only the index of p s 0 (ie., P s = { p s 0 …
can be generated as follows: First, we generate P s with only the index of p s 0 (ie., P s = { p s 0 …
[HTML][HTML] The uncertain cloud: State of the art and research challenges
During the last decade, cloud computing became a natural choice to host and provide
various computing resources as on-demand services. The correct characterization and …
various computing resources as on-demand services. The correct characterization and …
Distributed k-core decomposition and maintenance in large dynamic graphs
Distributed processing of large, dynamic graphs has recently received considerable attention,
especially in domains such as the analytics of social networks, web graphs and spatial …
especially in domains such as the analytics of social networks, web graphs and spatial …