Previous research has demonstrated that various properties of infectious diseases can be inferred from online search behaviour. In this work we use time series of online search query frequencies to ...gain insights about the prevalence of COVID-19 in multiple countries. We first develop unsupervised modelling techniques based on associated symptom categories identified by the United Kingdom's National Health Service and Public Health England. We then attempt to minimise an expected bias in these signals caused by public interest-as opposed to infections-using the proportion of news media coverage devoted to COVID-19 as a proxy indicator. Our analysis indicates that models based on online searches precede the reported confirmed cases and deaths by 16.7 (10.2-23.2) and 22.1 (17.4-26.9) days, respectively. We also investigate transfer learning techniques for mapping supervised models from countries where the spread of the disease has progressed extensively to countries that are in earlier phases of their respective epidemic curves. Furthermore, we compare time series of online search activity against confirmed COVID-19 cases or deaths jointly across multiple countries, uncovering interesting querying patterns, including the finding that rarer symptoms are better predictors than common ones. Finally, we show that web searches improve the short-term forecasting accuracy of autoregressive models for COVID-19 deaths. Our work provides evidence that online search data can be used to develop complementary public health surveillance methods to help inform the COVID-19 response in conjunction with more established approaches.
Cette thèse traite du problème de l'apprentissage automatique supervisé dans le cas ou l'on considère plusieurs sorties, potentiellement de différent types. Nous proposons d'explorer trois différents ...axes de recherche en rapport avec ce sujet. Dans un premier temps, nous nous concentrons sur le cas homogène et proposons un cadre théorique pour étudier la consistance des problèmes multi-labels dans le cas de l'utilisation de chaîne de classifieurs. Ensuite, en nous plaçant dans ce cadre, nous proposons une borne de Rademacher sur l'erreur de généralisation pour tous les classifieurs de la chaîne et exposons deux facteurs de dépendance reliant les sorties les unes aux autres. Dans un deuxième temps, nous développons et analysons la performance de modèles en lien avec la théorie proposée. Toujours dans le cadre de l'apprentissage avec plusieurs sorties homogènes, nous proposons un modèle basé sur des réseaux de neurones pour l'analyse de sentiments à grain fin. Enfin, nous proposons un cadre et une étude empirique qui montrent la pertinence de l'apprentissage multi-objectif dans le cas de multiples sorties hétérogènes.
In this thesis, we study the problem of learning with multiple outputs related to different tasks, such as classification and ranking. In this line of research, we explored three different axes. First we proposed a theoretical framework that can be used to show the consistency of multi-label learning in the case of classifier chains, where outputs are homogeneous. Based on this framework, we proposed Rademacher generalization error bound made by any classifier in the chain and exhibit dependency factors relating each output to the others. As a result, we introduced multiple strategies to learn classifier chains and select an order for the chain. Still focusing on the homogeneous multi-output framework, we proposed a neural network based solution for fine-grained sentiment analysis and show the efficiency of the approach. Finally, we proposed a framework and an empirical study showing the interest of learning with multiple tasks, even when the outputs are of different types.
In this paper, we propose a new framework to study the generalization property of classifier chains trained over observations associated with multiple and interdependent class labels. The results are ...based on large deviation inequalities for Lipschitz functions of weakly dependent sequences proposed by Rio in 2000. We believe that the resulting generalization error bound brings many advantages and could be adapted to other frameworks that consider interdependent outputs. First, it explicitly exhibits the dependencies between class labels. Secondly, it provides insights of the effect of the order of the chain on the algorithm generalization performances. Finally, the two dependency coefficients that appear in the bound could also be used to design new strategies to decide the order of the chain.
Traditional sentiment analysis approaches tackle problems like ternary (3-category) and fine-grained (5-category) classification by learning the tasks separately. We argue that such classification ...tasks are correlated and we propose a multitask approach based on a recurrent neural network that benefits by jointly learning them. Our study demonstrates the potential of multitask models on this type of problems and improves the state-of-the-art results in the fine-grained sentiment classification problem.
Previous research has demonstrated that various properties of infectious diseases can be inferred from online search behaviour. In this work we use time series of online search query frequencies to ...gain insights about the prevalence of COVID-19 in multiple countries. We first develop unsupervised modelling techniques based on associated symptom categories identified by the United Kingdom's National Health Service and Public Health England. We then attempt to minimise an expected bias in these signals caused by public interest -- as opposed to infections -- using the proportion of news media coverage devoted to COVID-19 as a proxy indicator. Our analysis indicates that models based on online searches precede the reported confirmed cases and deaths by 16.7 (10.2 - 23.2) and 22.1 (17.4 - 26.9) days, respectively. We also investigate transfer learning techniques for mapping supervised models from countries where the spread of disease has progressed extensively to countries that are in earlier phases of their respective epidemic curves. Furthermore, we compare time series of online search activity against confirmed COVID-19 cases or deaths jointly across multiple countries, uncovering interesting querying patterns, including the finding that rarer symptoms are better predictors than common ones. Finally, we show that web searches improve the short-term forecasting accuracy of autoregressive models for COVID-19 deaths. Our work provides evidence that online search data can be used to develop complementary public health surveillance methods to help inform the COVID-19 response in conjunction with more established approaches.
Multielement cavity optomechanics constitutes a direction to observe novel effects with mechanical resonators. Several exciting ideas include superradiance, increased optomechanical coupling, and ...quantum effects between distinct mechanical modes among others. Realizing these experiments has so far been difficult, because of the need for extremely precise positioning of the elements relative to one another due to the high-reflectivity required for each element. Here we overcome this challenge and present the fabrication of monolithic arrays of two highly reflective mechanical resonators in a single chip. We characterize the optical spectra and losses of these 200 μm long Fabry-Pérot interferometers, measuring finesse values of up to 220. In addition, we observe an enhancement of the coupling rate between the cavity field and the mechanical center-of-mass mode compared to the single membrane case. Further enhancements in coupling with these devices are predicted, potentially reaching the single-photon strong coupling regime, giving these integrated structures an exciting prospect for future multimode quantum experiments.
We propose a novel approach for an indirect probing of conjugation and hyperconjugation in core-excited molecules using resonant Auger spectroscopy. Our work demonstrates that the changes in the ...electronic structure of thiophene (C
4
H
4
S) and thiazole (C
3
H
3
NS), occurring in the process of resonant sulfur K-shell excitation and Auger decay, affect the stabilisation energy resulting from π-conjugation and hyperconjugation. The variations in the stabilisation energy manifest themselves in the resonant S KL
2,3
L
2,3
Auger spectra of thiophene and thiazole. The comparison of the results obtained for the conjugated molecules and for thiolane (C
4
H
8
S), the saturated analogue of thiophene, has been performed. The experimental observations are interpreted using high-level quantum-mechanical calculations and the natural bond orbital analysis.
Conjugation and hyperconjugation in core-excited states of organosulfur molecules probed by a novel experimental and theoretical approach using resonant Auger spectroscopy.
Demand for lightweight, highly reflective and mechanically compliant mirrors for optics experiments has seen a significant surge. In this aspect, photonic crystal (PhC) membranes are ideal ...alternatives to conventional mirrors, as they provide high reflectivity with only a single suspended layer of patterned dielectric material. However, due to limitations in nanofabrication, these devices are usually not wider than 300 μm. Here we experimentally demonstrate suspended PhC mirrors spanning areas up to 10 × 10 mm
. We overcome limitations imposed by the size of the PhC and measure reflectivities greater than 90 % on 56 nm thick mirrors at a wavelength of 1550 nm-an unrivaled performance compared to PhC mirrors with micro scale diameters. These structures bridge the gap between nano scale technologies and macroscopic optical elements.