Search results for "Engineering sciences"
showing 10 items of 2347 documents
Machine Learning VS Transfer Learning - Smart Camera Implementation for Face Authentication
2018
The aim of this paper is to highlight differences between classical machine learning and transfer learning applied to low cost real-time face authentication. Furthermore, in an access control context, the size of biometric data should be minimized so it can be stored on a remote personal media. These constraints have led us to compare only lightest versions of these algorithms. Transfer learning applied on Mobilenet v1 raises to 85% of accuracy, for a 457Ko model, with 3680s and 1.43s for training and prediction tasks. In comparison, the fastest integrated method (Random Forest) shows accuracy up to 90% for a 7,9Ko model, with a fifth of a second to be trained and a hundred of microseconds …
Testing odor memory : incidental versus intentional learning, implicit versus explicit memory
2002
International audience
Automatic cell nuclei counting: a protocol to acquire images and to compare results between color and multispectral images
2013
International audience; High-throughput screening in histology and analysis need a necessary automatic cell or nucleus counting. Current methods and systems based on grayscale or color images give results with counting errors. We suggest to use multispectral imaging (with more than three bands) rather than color one for nucleus counting. A traditional acquisition chains uses a source of white light and a CCD camera in addition to the optical microscope. To pass to a multispectral acquisition, we use a Programmable Light Source (PLS) in the place of the white light source. This PLS is capable of generating different wavelengths in the visible spectrum. So, one color image and four multispect…
Development of fluorescent platforms for the design of multifunctional compounds for in vitro and in vivo applications in molecular imaging
2018
The objective of this thesis was the development and evaluation of new molecular platformsfor optical fluorescence imaging applications. This work sought to develop new tools that caneasily be modified and adapted to the specific needs of the intended use. This is required asthe fluorophore will influence the final properties and should thus be incorporated beforestructural optimization of the selected agent rather than at the very end. Two main axes wereexplored; the use of BODIPYs for the development of trackable therapeutic agents that areprimarily intended for in vitro applications and the use of azaBODIPYs for the design of an invivo compatible fluorescent platform.In the first part tw…
Intégration d'une bouche artificielle dans un système de prélèvement Gilson
2007
Background subtraction for aerial surveillance conditions
2014
International audience; The first step in a surveillance system is to create a representation of the environment. Background subtraction is widely used algorithm to define a part of an image that most time remains stationary in a video. In surveillance tasks, this model helps to recognize those outlier objects in an area under monitoring. Set up a background model on moving platforms (intelligent cars, UAVs, etc.) is a challenging task due camera motion when images are acquired. In this paper, we propose a method to support instabilities caused by aerial images fusing spatial and temporal information about image motion. We used frame difference as first approximation, then age of pixels is …
Influence of the filling factor on the spectral properties of plasmonic crystals
2006
Plasmonics crystals (PCs) comprised of finite-size triangular lattices of gold bumps deposited on a gold thin film are studied by means of a near-field optical microscope. The plasmonic crystals fabricated by electron-beam lithography are illuminated by an incident surface plasmon polariton excited in the Kretschmann-Raether configuration at the gold/air thin-film interface for incident free-space wavelengths in the range $740--820\phantom{\rule{0.3em}{0ex}}\mathrm{nm}$. Based on the measurement of the surface plasmon polariton (SPP) damping distance in the crystals, the existence of a band gap for an incident SPP traveling along the two symmetry axes $\ensuremath{\Gamma}M$ and $\ensuremath…
Simulation analysis of fuel cell integration in a hybrid car
2019
Abstract Fuel cell is one of the green technologies that can help reduce toxic gas and decreasing effect of greenhouse gases in the world. This paper attempts to improve simulation model of fuel cell system that is easy to use and at the same time have an acceptable accuracy. The simulation model is developed through Matlab/Simulink software using Energetic Macroscopic Representation method which accuracy is compared with an established model. Simulation analysis of fuel cell integration is conducted by using experimental data from a real hybrid car. There are two potential types of system that were considered for the hybrid car in term of electricity generation and power produced to move t…
Experimental Study of Lithium-Ion Battery Thermal Behaviour for Electric and Hybrid Electric Vehicles
2014
An experimental study of lithium-ion battery thermal behaviour for automotive applications is presented. Experiments are conducted for a pack of three battery cells which encounter a series of different discharge and cooling conditions. Results show the different temperature distribution on different locations of the battery cell surface with the highest temperature increase near the positive and negative electrode. The temperature increases sharply if the state of charge (SOC) is too small (less then 20%). Higher discharge rate contributes to higher temperature increase and bigger maximum and minimum temperature difference. Higher cooling air velocity helps to decrease the overall temperat…
Modeling and experimenting the thermal behavior of a lithium-ion battery on a electric vehicle
2018
This paper deals with an electro thermal model of a lithium-ion battery for hybrid and electric vehicles. It was developed to study the behavior of lithium-ion battery key parameters. The thermal model, under Matlab/Simulink, is capable of predicting the voltage, current, State of Charge and temperature of the battery. Thereafter, the thermal behavior of the battery was studied under different operating conditions. The results of the simulation were compared with experimental measurements carried out by thermocouples and thermal camera on a test bench. Finally, the model has been validated on the NOAO electric vehicle.