Méthode des loci | EPFL Graph Search

vignette|Buste de Cicéron, l'un des plus célèbres utilisateurs de cette technique. La méthode des loci \lɔ.ki\ (« lieux » en latin) , méthode des lieux ou plus récemment palais de la mémoire, ou encore palais mental est une méthode mnémotechnique, ou « art de mémoire », pratiquée depuis l'Antiquité ; le poète Simonide de Céos en serait l'inventeur. Elle sert principalement à mémoriser de longues listes d'éléments ordonnés. Elle est fondée sur le souvenir de lieux déjà bien connus, auxquels on associe par divers moyens les éléments nouveaux que l'on souhaite mémoriser. Art de mémoire, architecture et « palais de la mémoire » On conseillait autrefois d'utiliser des endroits existants pour l'usage de l'art de mémoire, par exemple un marché ou une église. Pour utiliser la méthode, on visitait plusieurs fois l'édifice, en examinant toutes ses parties, toujours dans le même ordre. Après plusieurs visites, on était capable de se remémorer et de visualiser chacune de ses pièces ave

Localizing Polygonal Objects in Man-Made Environments

Xiaolu Sun

Object detection is a significant challenge in Computer Vision and has received a lot of attention in the field. One such challenge addressed in this thesis is the detection of polygonal objects, which are prevalent in man-made environments. Shape analysis is an important cue to detect these objects. We propose a contour-based object detection framework to deal with the related challenges, including how to efficiently detect polygonal shapes and how to exploit them for object detection. First, we propose an efficient component tree segmentation framework for stable region extraction and a multi-resolution line segment detection algorithm, which form the bases of our detection framework. Our component tree segmentation algorithm explores the optimal threshold for each branch of the component tree, and achieves a significant improvement over image thresholding segmentation, and comparable performance to more sophisticated methods but only at a fraction of computation time. Our line segment detector overcomes several inherent limitations of the Hough transform, and achieves a comparable performance to the state-of-the-art line segment detectors. However, our approach can better capture dominant structures and is more stable against low-quality imaging conditions. Second, we propose a global shape analysis measurement for simple polygon detection and use it to develop an approach for real-time landing site detection in unconstrained man-made environments. Since the task of detecting landing sites must be performed in a few seconds or less, existing methods are often limited to simple local intensity and edge variation cues. By contrast, we show how to efficiently take into account the potential sitesâ global shape, which is a critical cue in man-made scenes. Our method relies on component tree segmentation algorithm and a new shape regularity measure to look for polygonal regions in video sequences. In this way we enforce both temporal consistency and geometric regularity, resulting in reliable and consistent detections. Third, we propose a generic contour grouping based object detection approach by exploring promising cycles in a line fragment graph. Previous contour-based methods are limited to use additive scoring functions. In this thesis, we propose an approximate search approach that eliminates this restriction. Given a weighted line fragment graph, we prune its cycle space by removing cycles containing weak nodes or weak edges, until the upper bound of the cycle space is less than the threshold defined by the cyclomatic number. Object contours are then detected as maximally scoring elementary circuits in the pruned cycle space. Furthermore, we propose another more efficient algorithm, which reconstructs the graph by grouping the strongest edges iteratively until the number of the cycles reaches the upper bound. Our approximate search approaches can be used with any cycle scoring function. Moreover, unlike other contour grouping based approaches, our approach does not rely on a greedy strategy for finding multiple candidates and is capable of finding multiple candidates sharing common line fragments. We demonstrate that our approach significantly outperforms the state-of-the-art.

EPFL2015

A New Approach to the On-line Estimation of the Loss of Generation Size in Power Systems

Rasoul Azizipanah-Abarghooee, Mario Paolone

Following an unintended disconnection of a synchronous generator (SG) from the power system, what is also known as a loss of generation (LoG), it is not trivial to precisely estimate the post-event power system's inertia and the LoG size. One of reasons for that is that both of them are a function of the unknown inertia reduction. To solve this challenging problem, this paper presents an analytical method based on the rate-of-change-of-frequency (RoCoF). The method relies on a modified swing equation, allowing a simultaneous estimation of both unknowns. To this end, the values of mechanical starting time, apparent power and loading of lost generator are formulated for the power system under study. In a practical application, the method can use RoCoF measured by phasor measurement units (PMUs). The paper discusses the impact of various frequency estimation approaches to the proposed LoG estimation. Furthermore, a new method for LoG size estimation, based on the interpolated estimated inertial response, is proposed. The efficiency of the proposed approach is validated through extensive simulations with Matlab/Simulink using a simple power system and the IEEE 39-bus test network.

2018

Agile in-litero experiments

Renaud Luc Richardet

In neuroscience, as in many other scientific domains, the primary form of knowledge dissemination is through published articles in peer-reviewed journals. One challenge for modern neuroinformatics is to design methods to make the knowledge from the tremendous backlog of publications accessible for search, analysis and its integration into computational models. In this thesis, we introduce novel natural language processing (NLP) models and systems to mine the neuroscientific literature. In addition to in vivo, in vitro or in silico experiments, we coin the NLP methods developed in this thesis as in litero experiments, aiming at analyzing and making accessible the extended body of neuroscientific literature. In particular, we focus on two important neuroscientific entities: brain regions and neural cells. An integrated NLP model is designed to automatically extract brain region connectivity statements from very large corpora. This system is applied to a large corpus of 25M PubMed abstracts and 600K full-text articles. Central to this system is the creation of a searchable database of brain region connectivity statements, allowing neuroscientists to gain an overview of all brain regions connected to a given region of interest. More importantly, the database enables researcher to provide feedback on connectivity results and links back to the original article sentence to provide the relevant context. The database is evaluated by neuroanatomists on real connectomics tasks (targets of Nucleus Accumbens) and results in significant effort reduction in comparison to previous manual methods (from 1 week to 2h). Subsequently, we introduce neuroNER to identify, normalize and compare instances of identify neuronsneurons in the scientific literature. Our method relies on identifying and analyzing each of the domain features used to annotate a specific neuron mention, like the morphological term 'basket' or brain region 'hippocampus'. We apply our method to the same corpus of 25M PubMed abstracts and 600K full-text articles and find over 500K unique neuron type mentions. To demonstrate the utility of our approach, we also apply our method towards cross-comparing the NeuroLex and Human Brain Project (HBP) cell type ontologies. By decoupling a neuron mention's identity into its specific compositional features, our method can successfully identify specific neuron types even if they are not explicitly listed within a predefined neuron type lexicon, thus greatly facilitating cross-laboratory studies. In order to build such large databases, several tools and infrastructureslarge-scale NLP were developed: a robust pipeline to preprocess full-text PDF articles, as well as bluima, an NLP processing pipeline specialized on neuroscience to perform text-mining at PubMed scale. During the development of those two NLP systems, we acknowledged the need for novel NLP approaches to rapidly develop custom text mining solutions. This led to the formalization of the agile text miningagile text-mining methodology to improve the communication and collaboration between subject matter experts and text miners. Agile text mining is characterized by short development cycles, frequent tasks redefinition and continuous performance monitoring through integration tests. To support our approach, we developed Sherlok, an NLP framework designed for the development of agile text mining applications.

EPFL2016