Search results for "neural"
showing 10 items of 2783 documents
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 …
Load-dependent alpha suppression is related to working memory capacity for numbers
2022
Alpha suppression is proposed to reflect a surge in cortical excitability to enhance stimulus processing in working memory. The attenuated state of alpha might reflect the prioritisation of behaviourally relevant information, making it a proxy for working memory functioning. Despite the growing interest in utilising the advancement of brain-based measures to evaluate individuals’ cognitive processes, there was a lack of consistent evidence on the relationship between alpha suppression and working memory performance. To investigate whether interindividual differences in alpha suppression might be related to variability in working memory capacity, we recorded participants’ electroencephalogra…
Proximity Effect in Superconducting Heterostructures with Strong Spin-Orbit Coupling and Spin Splitting
2019
It has been shown that singlet Cooper pairs can be converted into triplet ones and diffuse into a ferromagnet over a long distance in a phenomenon known as the long-range proximity effect (LRPE). This happens in materials with inhomogeneous magnetism or spin-orbit coupling (SOC). Most of the previous studies focus on the cases with small SOC and exchange field. However, the physics was not clear when SOC and exchange field strength are both much greater than the disorder strength. In this work, we consider a two dimensional system with a large Rashba-type SOC and exchange field in the case where only one band is partially occupied. We develop a generalized quasiclassical theory by projectin…
MUP-CITY© Multi-Skalare Planung als nachhaltiges Verflechtungsprinzip von bebauten Zonen und Freiraum
2011
ACL; National audience
Un observatoire du sport départemental partagé sur l'internet : attendus et expérience
2006
ACL; National audience
Quenched and annealed free energies
1984
This paper gives a simple exposition of the Nishimori method to solve certain quenched, random bond spin-glass models. It allows a transparent physical interpretation in terms of annealed systems. As an application a special solution of the Sherrington-Kirkpatrick model with a discrete probability distribution is obtained and shown to agree with the solution for the Gaussian case. This substantiates the claim that the averaged free energy does not depend on the details of the probability distribution Expose simple de la methode de Nishimori pour resoudre certains modeles de verres de spin avec interactions aleatoires. Interpretation transparente en termes de systemes recuits. Presentation d…
Linear fusion of interrupted reports in cooperative spectrum sensing for cognitive radio networks
2015
Interrupted reporting has recently been introduced as an effective method to increase the energy efficiency of cooperative spectrum sensing schemes in cognitive radio networks. In this paper, joint optimization of the reporting and fusion phases in a cooperative sensing with interrupted reporting is considered. This optimization aims at finding the best weights used at the fusion center to construct a linear fusion of the received interrupted reports, jointly with Bernoulli distributions governing the statistical behavior of the interruptions. The problem is formulated by using the deflection criterion and as a nonconvex quadratic program which is then solved for a suboptimal solution, in a…
Genetic programming through bi-objective genetic algorithms with a study of a simulated moving bed process involving multiple objectives
2013
A new bi-objective genetic programming (BioGP) technique has been developed for meta-modeling and applied in a chromatographic separation process using a simulated moving bed (SMB) process. The BioGP technique initially minimizes training error through a single objective optimization procedure and then a trade-off between complexity and accuracy is worked out through a genetic algorithm based bi-objective optimization strategy. A benefit of the BioGP approach is that an expert user or a decision maker (DM) can flexibly select the mathematical operations involved to construct a meta-model of desired complexity or accuracy. It is also designed to combat bloat - a perennial problem in genetic …
Evaluating the performance of artificial neural networks for the classification of freshwater benthic macroinvertebrates
2014
Abstract Macroinvertebrates form an important functional component of aquatic ecosystems. Their ability to indicate various types of anthropogenic stressors is widely recognized which has made them an integral component of freshwater biomonitoring. The use of macroinvertebrates in biomonitoring is dependent on manual taxa identification which is currently a time-consuming and cost-intensive process conducted by highly trained taxonomical experts. Automated taxa identification of macroinvertebrates is a relatively recent research development. Previous studies have displayed great potential for solutions to this demanding data mining application. In this research we have a collection of 1350 …
Convolutional neural networks in skin cancer detection using spatial and spectral domain
2019
Skin cancers are world wide deathly health problem, where significant life and cost savings could be achieved if detection of cancer can be done in early phase. Hypespectral imaging is prominent tool for non-invasive screening. In this study we compare how use of both spectral and spatial domain increase classification performance of convolutional neural networks. We compare five different neural network architectures for real patient data. Our models gain same or slightly better positive predictive value as clinicians. Towards more general and reliable model more data is needed and collection of training data should be systematic. peerReviewed