Etienne Côme

Model selection and clustering in stochastic block models based on the exact integrated complete data likelihood

The stochastic block model (SBM) is a mixture model for the clustering of nodes in networks. The SBM has now been employed for more than a decade to analyze very different types of networks in many scientific fields, including biology and the social sciences. Recently, an analytical expression based on the collapsing of the SBM parameters has been proposed, in combination with a sampling procedure that allows the clustering of the vertices and the estimation of the number of clusters to be performed simultaneously. Although the corresponding algorithm can technically accommodate up to 10 000 nodes and millions of edges, the Markov chain, however, tends to exhibit poor mixing properties, that is, low acceptance rates, for large networks. Therefore, the number of clusters tends to be highly overestimated, even for a very large number of samples. In this article, we rely on a similar expression, which we call the integrated complete data log likelihood, and propose a greedy inference algorithm that focuses on maximizing this exact quantity. This algorithm incurs a smaller computational cost than existing inference techniques for the SBM and can be employed to analyze large networks (several tens of thousands of nodes and millions of edges) with no convergence problems. Using toy datasets, the algorithm exhibits improvements over existing strategies, both in terms of clustering and model selection. An application to a network of blogs related to illustrations and comics is also provided.

Aircraft engine health monitoring using self-organizing maps

Aircraft engines are designed to be used during several tens of years. Ensuring a proper operation of engines over their lifetime is therefore an important and difficult task. The maintenance can be improved if efficients procedures for the understanding of data flows produced by sensors for monitoring purposes are implemented. This paper details such a procedure aiming at visualizing in a meaningful way successive data measured on aircraft engines. The core of the procedure is based on Self-Organizing Maps (SOM) which are used to visualize the evolution of the data measured on the engines. Rough measurements can not be directly used as inputs, because they are influenced by external conditions. A preprocessing procedure is set up to extract meaningful information and remove uninteresting variations due to change of environmental conditions. The proposed procedure contains three main modules to tackle these difficulties: environmental conditions normalization (ECN), change detection and adaptive signal modeling (CD) and finally visualization with Self-Organizing Maps (SOM). The architecture of the procedure and of modules are described in details in this paper and results on real data are also supplied.

Mixture Model Estimation with Soft Labels

This paper addresses classification problems in which the class membership of training data is only partially known. Each learning sample is assumed to consist in a feature vector and an imprecise and/or uncertain “soft” label m i defined as a Dempster-Shafer basic belief assignment over the set of classes. This framework thus generalizes many kinds of learning problems including supervised, unsupervised and semi-supervised learning. Here, it is assumed that the feature vectors are generated from a mixture model. Using the General Bayesian Theorem, we derive a criterion generalizing the likelihood function. A variant of the EM algorithm dedicated to the optimization of this criterion is proposed, allowing us to compute estimates of model parameters. Experimental results demonstrate the ability of this approach to exploit partial information about class labels.

Partially supervised Independent Factor Analysis using soft labels elicited from multiple experts: application to railway track circuit diagnosis

Using a statistical model in a diagnosis task generally requires a large amount of labeled data. When ground truth information is not available, too expensive or difficult to collect, one has to rely on expert knowledge. In this paper, it is proposed to use partial information from domain experts expressed as belief functions. Expert opinions are combined in this framework and used with measurement data to estimate the parameters of a statistical model using a variant of the EM algorithm. The particular application investigated here concerns the diagnosis of railway track circuits. A noiseless Independent Factor Analysis model is postulated, assuming the observed variables extracted from railway track inspection signals to be generated by a linear mixture of independent latent variables linked to the system component states. Usually, learning with this statistical model is performed in an unsupervised way using unlabeled examples only. In this paper, it is proposed to handle this learning process in a soft-supervised way using imperfect information on the system component states. Fusing partially reliable information about cluster membership is shown to significantly improve classification results.

Clustering Smart Card Data for Urban Mobility Analysis

Smart card data gathered by automated fare collection (AFC) systems are valuable resources for studying urban mobility. In this paper, we propose two approaches to cluster smart card data, which can be used to extract mobility patterns in a public transportation system. Two complementary standpoints are considered: a station-oriented operational point of view and a passenger-focused one. The first approach clusters stations based on when their activity occurs, i.e., how trips made at the stations are distributed over time. The second approach makes it possible to identify groups of passengers that have similar boarding times aggregated into weekly profiles. By applying our approaches to a real data set issued from the metropolitan area of Rennes, France, we illustrate how they can help reveal valuable insights about urban mobility, such as the presence of different station key roles, including residential stations used mostly in the mornings and work stations used only in the evening and almost exclusively during weekdays, as well as different passenger behaviors ranging from the sporadic and diffuse usage to typical commute practices. By cross comparing passenger clusters with fare types, we also highlight how certain usages are more specific to particular types of passengers.

Clustering the Vélib' Dynamic Origin/Destination flows using a family of Poisson Mixture Models

Studies on human mobility, including Bike Sharing System Analysis, have expanded over the past few years. They aim to give insight into the underlying urban phenomena linked to city dynamics and generally rely on data-mining tools to extract meaningful patterns from the huge volume of data recorded by such complex systems. This paper presents one such tool through the introduction of a family of generative models based on Poisson mixtures to automatically analyse and find temporal-based clusters in Origin/Destination flow-data. Such an approach may provide latent factors that reveal how regions of different usage interact over time. More generally, the proposed methodology can be used to cluster edges of temporal valued-graphs with respect to their temporal profiles and is thus particularly suited to mine patterns in dynamic Origin/Destination matrices commonly encountered in the field of transport. An in-depth analysis of the results of the proposed models was carried out on two months of trips data recorded on the Velib׳ Bike-Sharing System of Paris to validate the approach.

Temporal association rule mining for the preventive diagnosis of onboard subsystems within floating train data framework

The increasing interest in preventive maintenance strategies for railway transportation systems and the emergence of telecommunication technologies have both led to the development of floating train data (FTD) systems. Commercial trains are being equipped with both positioning and communications systems as well as onboard intelligent sensors monitoring various subsystems all over the train. The sizable collected amounts of real-time spatio-temporal data can be used to leverage the development of innovative diagnosis methodologies based on temporal and sequential data mining. This paper presents a temporal association rule mining approach named T-patterns, applied on highly challenging floating train data. The aim is to discover temporal associations between pairs of timestamped alarms, called events, that can predict the occurrence of severe failures within a complex bursty environment. Experiments carried out on Alstoms TrainTracer™ data show promising results.

Aircraft engine fleet monitoring using self-organizing maps and edit distance

Aircraft engines are designed to be used during several tens of years. Ensuring a proper operation of engines over their lifetime is therefore an important and difficult task. The maintenance can be improved if efficient procedures for the understanding of data flows produced by sensors for monitoring purposes are implemented. This paper details such a procedure aiming at visualizing in a meaningful way successive data measured on aircraft engines and finding for every possible request sequence of data measurement similar behaviour already observed in the past which may help to anticipate failures. The core of the procedure is based on Self-Organizing Maps (SOM) which are used to visualize the evolution of the data measured on the engines. Rough measurements can not be directly used as inputs, because they are influenced by external conditions. A preprocessing procedure is set up to extract meaningful information and remove uninteresting variations due to change of environmental conditions. The proposed procedure contains four main modules to tackle these difficulties: environmental conditions normalization (ECN), change detection and adaptive signal modeling (CD), visualization with Self-Organizing Maps (SOM) and finally minimal Edit Distance search (SEARCH). The architecture of the procedure and of its modules is described in this paper and results on real data are also supplied.

Noiseless Independent Factor Analysis with Mixing Constraints in a Semi-supervised Framework. Application to Railway Device Fault Diagnosis

In Independent Factor Analysis (IFA), latent components (or sources) are recovered from only their linear observed mixtures. Both the mixing process and the source densities (that are assumed to be generated according to mixtures of Gaussians) are learned from observed data. This paper investigates the possibility of estimating the IFA model in its noiseless setting when two kinds of prior information are incorporated: constraints on the mixing process and partial knowledge on the cluster membership of some examples. Semi-supervised or partially supervised learning frameworks can thus be handled. These two proposals have been initially motivated by a real-world application that concerns fault diagnosis of a railway device. Results from this application are provided to demonstrate the ability of our approach to enhance estimation accuracy and remove indeterminacy commonly encountered in unsupervised IFA such as source permutations.

A mixture model clustering approach for temporal passenger pattern characterization in public transport

Smartcard data provide a great number of information that are increasingly used nowadays. In the field of transport, they offer the opportunity to study passenger behavior, leading to a better knowledge of public transit demand and thereby granting the transport operators the ability to adapt their transport offer and services accordingly, both in space and in time. In particular, an accurate characterization of mobility patterns using data mining approaches has a very strong interest for transport planning purposes. This paper aims to propose a two-level generative mixture model that partitions passengers according to their temporal profiles. Using the timestamps of the passengers’ transactions in the public transport network, the first level models the passengers partitioning into a reduced set of clusters, whereas the second level captures how the trips made by each cluster of passengers are distributed over time. The proposed approach is applied on real ticketing data collected from the urban transport network of Rennes Métropole (France). The obtained results show that different passenger profiles can be discovered, thus highlighting several patterns of transport demand. The crossing of the clustering results with smartcard fare types as well as city characteristics such as academic centralities is also conducted in order to identify the close link between urban mobility and the socioeconomic characteristics of the city.