No abstract

AbstractÐThis paper describes a hidden Markov model-based approach designed to recognize off-line unconstrained handwritten words for large vocabularies. After preprocessing, a word image is segmented into letters or pseudoletters and represented by two feature sequences of equal length, each consisting of an alternating sequence of shape-symbols and segmentationsymbols, which are both explicitly modeled. The word model is made up of the concatenation of appropriate letter models consisting of elementary HMMs and an HMM-based interpolation technique is used to optimally combine the two feature sets. Two rejection mechanisms are considered depending on whether or not the word image is guaranteed to belong to the lexicon. Experiments carried out on real-life data show that the proposed approach can be successfully used for handwritten word recognition.

Fast urbanization generates increasing amounts of travel flows, urging the need for efficient transport planning policies. In parallel, mobile phone data have emerged as the largest mobility data source, but are not yet integrated to transport planning models. Currently, transport authorities are lacking a global picture of daily passenger flows on multimodal transport networks. In this work, we propose the first methodology to infer dynamic Origin-Destination flows by transport modes using mobile network data e.g., Call Detail Records. For this study, we pre-process 360 million trajectories for more than 2 million devices from the Greater Paris as our case study region. The model combines mobile network geolocation with transport network geospatial data, travel survey, census and travel card data. The transport modes of mobile network trajectories are identified through a two-steps semi-supervised learning algorithm. The later involves clustering of mobile network areas and Bayesian inference to generate transport probabilities for trajectories. After attributing the mode with highest probability to each trajectory, we construct Origin-Destination matrices by transport mode. Flows are up-scaled to the total population using state-of-the-art expansion factors. The model generates time variant road and rail passenger flows for the complete region. From our results, we observe different mobility patterns for road and rail modes and between Paris and its suburbs. The resulting transport flows are extensively validated against the travel survey and the travel card data for different spatial scales.

No abstract

Communication-enabled devices routinely carried by individuals have become pervasive, opening unprecedented opportunities for collecting digital metadata about the mobility of large populations. In this paper, we propose a novel methodology for the estimation of people density at metropolitan scales, using subscriber presence metadata collected by a mobile operator. Our approach suits the estimation of static population densities, i.e., of the distribution of dwelling units per urban area contained in traditional censuses. More importantly, it enables the estimation of dynamic population densities, i.e., the time-varying distributions of people in a conurbation. By leveraging substantial real-world mobile network metadata and ground-truth information, we demonstrate that the accuracy of our solution is superior to that granted by state-of-the-art methods in practical heterogeneous urban scenarios.

Research in diabetes, especially when it comes to building data-driven models to forecast future glucose values, is hindered by the sensitive nature of the data. Because researchers do not share the same data between studies, progress is hard to assess. This paper aims at comparing the most promising algorithms in the field, namely Feedforward Neural Networks (FFNN), Long Short-Term Memory (LSTM) Recurrent Neural Networks, Extreme Learning Machines (ELM), Support Vector Regression (SVR) and Gaussian Processes (GP). They are personalized and trained on a population of 10 virtual children from the Type 1 Diabetes Metabolic Simulator software to predict future glucose values at a prediction horizon of 30 minutes. The performances of the models are evaluated using the Root Mean Squared Error (RMSE) and the Continuous Glucose-Error Grid Analysis (CG-EGA). While most of the models end up having low RMSE, the GP model with a Dot-Product kernel (GP-DP), a novel usage in the context of glucose prediction, has the lowest. Despite having good RMSE values, we show that the models do not necessarily exhibit a good clinical acceptability, measured by the CG-EGA. Only the LSTM, SVR and GP-DP models have overall acceptable results, each of them performing best in one of the glycemia regions.

No abstract

Smartphones and other mobile devices are today pervasive across the globe. As an interesting side effect of the surge in mobile communications, mobile network operators can now easily collect a wealth of high-resolution data on the habits of large user populations. The information extracted from mobile network traffic data is very relevant in the context of population mapping: it provides a tool for the automatic and live estimation of population densities, overcoming the limitations of traditional data sources such as censuses and surveys. In this paper, we propose a new approach to infer population densities at urban scales, based on aggregated mobile network traffic metadata. Our approach allows estimating both static and dynamic populations, achieves a significant improvement in terms of accuracy with respect to state-of-the-art solutions in the literature, and is validated on different city scenarios.Comment: in proc of the 17th International Symposium on A World of Wireless, Mobile and Multimedia Networks (WoWMoM), 201