Search results for " Computer"
showing 10 items of 6910 documents
Étude d'un système de stéréo-vision hybride
2013
National audience; On considère dans ce travail un système de vision hybride fixe composé d'une caméra fisheye et d'une caméra PTZ dans un environnement rigide. Nous souhaitons être en mesure d'orienter la caméra mécanisée sur une cible visible depuis l'image omnidirectionnelle de manière à obtenir une image de bonne définition de l'objet d'intérêt à partir de la caméra PTZ. Nous proposons dans cet article d'utiliser la modélisation sphérique des images ainsi que les propriétés de la géométrie épipolaire afin d'initialiser la localisation de la cible dans la caméra PTZ.
Surrogate Modelling for Oxygen Uptake Prediction Using LSTM Neural Network
2023
Oxygen uptake (V˙O2) is an important metric in any exercise test including walking and running. It can be measured using portable spirometers or metabolic analyzers. Those devices are, however, not suitable for constant use by consumers due to their costs, difficulty of operation and their intervening in the physical integrity of their users. Therefore, it is important to develop approaches for the indirect estimation of V˙O2-based measurements of motion parameters, heart rate data and application-specific measurements from consumer-grade sensors. Typically, these approaches are based on linear regression models or neural networks. This study investigates how motion data contribute to V˙O2 …
Automatic surrogate modelling technique selection based on features of optimization problems
2019
A typical scenario when solving industrial single or multiobjective optimization problems is that no explicit formulation of the problem is available. Instead, a dataset containing vectors of decision variables together with their objective function value(s) is given and a surrogate model (or metamodel) is build from the data and used for optimization and decision-making. This data-driven optimization process strongly depends on the ability of the surrogate model to predict the objective value of decision variables not present in the original dataset. Therefore, the choice of surrogate modelling technique is crucial. While many surrogate modelling techniques have been discussed in the liter…
MUV: A Game to Encourage Sustainable Mobility Habits
2019
This working paper investigates the question of changing people mobility towards more sustainable habits involving them in an engaging gameplay. The work is performed within MUV H2020 research and innovation action. The game design, definition and features have been co-created through the involvement of different citizens and stakeholders in six European neighbourhoods. The paper discusses the game design as resulting from co-creation and co-design experiences with each neighbourhood communities involved in initial phases. The paper argues that the local co-design activities have influenced the game definition, together with the community engagement approach. The MUV gameplay approach resul…
Improving Energy Expenditure Estimation in Wrist-Worn Wearables by Augmenting Heart Rate Data With Heat Flux Measurement
2021
Wearable electronics are often used for estimating the energy expenditure of the user based on heart rate measurement. While heart rate is a good predictor of calorie consumption at high intensities, it is less precise at low intensity levels, which translates into inaccurate results when estimating daily net energy expenditure. In this study, heart rate measurement was augmented with heat flux (HF) measurement, a form of direct calorimetry. A physical exercise test on a group of 15 people showed that HF measurement can improve the accuracy of calorie consumption estimates especially during rest and low-intensity activity when used in conjunction with heart rate information and vital backgr…
A Self-Contained Biometric Sensor for Ubiquitous Authentication
2007
This paper describes a real-life behavior framework in simulation game based on Probabilistic State Machine (PSM) with Gaussian random distribution. According to the dynamic environment information, NPC can generate behavior planning autonomously associated with defined FSM. After planning process, we illuminate Gaussian probabilistic function for real-life action simulation in time and spatial domains. The expected value of distribution is estimated during behavior planning process and variance is determined by NPC personality in order to realize real life behavior simulation. We experiment the framework and Gaussian PSM on a restaurant simulation game. Furthermore we give some suggestions…
Moving beyond the Turing test
2012
Computers interacting with, not imitating, humans is the way forward.
How to Improve the Reliability of Chord?
2008
In this paper we focus on Chord P2P protocol and we study the process of unexpected departures of nodes from this system. Each of such departures may effect in losing any information and in classical versions of this protocol the probability of losing some information is proportional to the quantity of information put into this system. This effect can be partially solved by gathering in the protocol multiple copies (replicas) of information. The replication mechanism was proposed by many authors. We present a detailed analysis of one variant of blind replication and show that this solution only partially solves the problem. Next we propose two less obvious modifications of the Chord protoco…
The Impact of Financial Development and Macroeconomic Fundamentals on Nonperforming Loans among Emerging Countries: An Assessment Using the NARDL App…
2022
The relationship between financial development indicators and non-performing loans (NPLs) has garnered significant attention, especially in emerging countries. The puzzle of whether financial sector development increases or decreases Non-performing Loans (NPL)s has not been resolved to the satisfaction of the curious mind. This research attempts to answer the above question by studying the asymmetric and symmetric association between financial sector development and NPLs, by utilizing the novel non-linear autoregressive distribution lag (NARDL) and the linear autoregressive distribution lag (ARDL) approach. Moreover, to make the study inclusive, we have added a series of proxies to measure …
Une nouvelle approche de classification de personnes à partir d'une plate-forme multi-kinect
2015
International audience; Dans ce papier nous présentons un descripteur 3D original pour la classification de personnes. Nous avons réalisé une plate-forme multi-kinect qui fait l'acquisition de nuages de points complets (c'est à dire selon une vue à 360°). Un post-traitement (suppression d'arrière-plan) isole les éléments qui sont candidats à représenter une personne. Notre descripteur exploite ces données et permet, au travers d'un classifieur SVM (Support Vector Machine), de classifier les personnes et de déterminer l'orientation du plan frontal de la personne. Il utilise la répartition spatiale et l'orientation des normales aux surfaces dans un procédé dérivé de celui des HOG (Histogram o…