Mahendiran, N. Deepa, C.
Published in
SN Computer Science
The explosive generation of data in the digital era directs to the requirements of effective approaches to transmit and store the data. The necessities of security and limited resources have led to the development of image encryption and compression approaches, respectively. The digital contents are transmitted over the internet which may subject t...
Berthelier, Anthony Yan, Yongzhe Chateau, Thierry Blanc, Christophe Duffner, Stefan Garcia, Christophe
While deep neural networks (DNNs) have proven to be efficient for numerous tasks, they come at a high memory and computation cost, thus making them impractical on resource-limited devices. However, these networks are known to contain a large number of parameters. Recent research has shown that their structure can be more compact without compromisin...
Hokke, Olivier (author)
Many games played on the mobile phone have become large in download size. A significant portion thereof is due to the many textures that are involved. However, many games have art styles that include clean drawings with gradients, solid colors, and hard lines. We observe that these images’ areas may be more efficiently described by interpolating co...
Zeegers, M.T. (Mathé) Pelt, D.M. (Daniël) Leeuwen, T. (Tristan) van Liere, R. (Robert) van Batenburg, K.J. (Joost)
An important challenge in hyperspectral imaging tasks is to cope with the large number of spectral bins. Common spectral data reduction methods do not take prior knowledge about the task into account. Consequently, sparsely occurring features that may be essential for the imaging task may not be preserved in the data reduction step. Convolutional n...
Kim, Yeon-Jin Zou, Yang Kim, Young-Eun Chung, Jin-Gyun
Published in
International Journal of Automotive Technology
Controller area network (CAN) has become the most widely used protocol in automotive networks due to its efficiency and robustness. The number of electronic control units (ECUs) in modern vehicles continually increases as more control functions are needed. CAN buses with limited bandwidths may be overloaded due to increases in bus load. Therefore, ...
Tawitian, Anthony
La maladie veineuse chronique est considérée comme la maladie vasculaire la plus fréquente dans notre pays. Elle englobe un très large spectre de présentations cliniques. Parmi celles-ci, nous allons nous pencher sur les affections veineuses chroniques du membre inférieur et plus précisément l’insuffisance veineuse chronique. Cette dernière touche ...
Maalej, Asma Ben-Romdhane, Manel Tlili, Mariam Rivet, François Dallet, Dominique Rebai, Chiheb
Published in
Measurement
This paper presents a compression study of electrocardiogram (ECG) signals for e-Health cardiac online diagnostic systems. The study uses 75 real electrocardiogram records sampled with continuous-time level-crossing (LC) analog-to-digital converter (ADC). This signal-dependent LC-ADC compresses signals compared to conventional ADC but further compr...
Berthelier, Anthony Chateau, Thierry Duffner, Stefan Garcia, Christophe Blanc, Christophe
Over the past, deep neural networks have proved to be an essential element for developing intelligent solutions. They have achieved remarkable performances at a cost of deeper layers and millions of parameters. Therefore utilising these networks on limited resource platforms for smart cameras is a challenging task. In this context, models need to b...
Myrtja, Erisa
Le travail de cette thèse concerne la durabilité d’un point de vue mécanique des mortiers haute performance. De nombreuses structures sont soumises à des efforts de fatigue au cours de leur durée de vie comme des structures offshore, joints de chaussée, pistes d’aéroport ou planchers industriels.Bien que ce phénomène soit assez connu pour les const...
Mercier, C Rousseau, S Gori, P Bloch, I Boubekeur, T
Published in
Neuroinformatics
Diffusion MRI fiber tracking datasets can contain millions of 3D streamlines, and their representation can weight tens of gigabytes of memory. These sets of streamlines are called tractograms and are often used for clinical operations or research. Their size makes them difficult to store, visualize, process or exchange over the network. We propose ...