International audience

International audience

Understanding and classifying mobility modes, such as walking, cycling, driving, or public transport, is essential for sustainable urban planning and mobility behavior analysis. Traditional approaches rely on handcrafted features and machine learning models trained on GPS trajectory data. However, these methods require extensive data preparation and model training. In this work, we explore the potential of large language models (LLMs) as zero-shot predictors for transportation mode classification, eliminating the need for training data altogether. We propose a pipeline that transforms enriched trajectory segments into textual prompts, enabling LLMs to perform classification without task-specific pretraining. We benchmark the performance of a locally distilled 32B parameter LLM (DeepSeek Gwen) against standard machine learning baselines on the Geolife dataset. Preliminary results demonstrate that LLMs effectively capture semantic and contextual cues from trajectory-derived features, highlighting their promise for rapid, data-efficient transportation mode classification. Our work provides novel insights into leveraging LLMs in the mobility domain and identifies future opportunities for their integration.

Mobility datasets are crucial for various applications. However, sharing this data raises privacy concerns due to the sensitive nature of geolocation information. Synthetic data generation has recently emerged as a promising solution to protect geo-privacy of trajectory data. Current approaches rely on having a large set of authentic trajectories collected from individual users to train generative networks. However, this assumption proves impractical in many real-world scenarios due to the sensitive personal information typically embedded within trajectories. Our approach leverages federated learning to generate privacy-preserving synthetic trajectories without the need for centralized data collection. Experimental results demonstrate that our distributed framework effectively produces synthetic trajectories with distributions comparable to baseline, offering a privacy-conscious alternative for geo-privacy protection in mobility datasets.

Applications that generate continuous data have proliferated in recent years, and thus the challenge of processing those data streams has emerged. This requires Data Stream Processing frameworks with monitoring capabilities able to detect and react to any non-desired situation. Many streaming use cases deal with distributed sources of data which, for privacy and communication saving purposes, need to be tackled in a distributed manner. Based on the mentioned challenges, this paper presents STREAMER 3.0, an improvement on the former data stream framework with two new modules: (i) a monitoring manager with detection algorithms, alert raising and automatic model updater; and (ii) a distributed learning module relying on federated learning. We showcase these new functionalities with an example of remaining useful life estimation of turbofan engines using an LSTM.

Abstract Traffic forecasting has attracted widespread attention recently. In reality, traffic data usually contains missing values due to sensor or communication errors. The Spatio-temporal feature in traffic data brings more challenges for processing such missing values, for which the classic techniques (e.g., data imputations) are limited: (1) in temporal axis, the values can be randomly or consecutively missing; (2) in spatial axis, the missing values can happen on one single sensor or on multiple sensors simultaneously. Recent models powered by Graph Neural Networks achieved satisfying performance on traffic forecasting tasks. However, few of them are applicable to such a complex missing-value context. To this end, we propose GCN-M, a Graph Convolutional Network model with the ability to handle the complex missing values in the Spatio-temporal context. Particularly, we jointly model the missing value processing and traffic forecasting tasks, considering both local Spatio-temporal features and global historical patterns in an attention-based memory network. We propose as well a dynamic graph learning module based on the learned local-global features. The experimental results on real-life datasets show the reliability of our proposed method.

Learning from Multivariate Time Series (MTS) has attracted widespread attention in recent years. In particular, label shortage is a real challenge for the classification task on MTS, considering its complex dimensional and sequential data structure. Unlike self-training and positive unlabeled learning that rely on distance-based classifiers, in this paper, we propose SMATE, a novel semi-supervised model for learning the interpretable Spatio-Temporal representation from weakly labeled MTS. We validate empirically the learned representation on 30 public datasets from the UEA MTS archive. We compare it with 13 state-of-the-art baseline methods for fully supervised tasks and four baselines for semi-supervised tasks. The results show the reliability and efficiency of our proposed method.

Wide spread use of sensors and mobile devices along with the new paradigm of Mobile Crowd-Sensing (MCS), allows monitoring air pollution in urban areas. Several measurements are collected, such as Particulate Matters, Nitrogen dioxide, and others. Mining the context of MCS data in such domains is a key factor for identifying the individuals’ exposure to air pollution, but it is challenging due to the lack or the weakness of predictors. We have previously developed a multi-view learning approach which learns the context solely from the sensor measurements. In this demonstration, we propose a visualization tool (COMIC) showing the different recognized contexts using an improved version of our algorithm. We also demonstrate the change points detected by a multi-dimensional CPD model. We leverage real data from a MCS campaign, and compare different methods.

The ubiquity of GPS-enabled smartphones and automotive navigation systems allows to monitor and collect massive streams of trajectory data in real-time. This enables real-time analyses on mobility data in urban settings, which in turn have the potential to substantially improve traffic conditions, analyze congested areas, detect events in (quasi) real-time, and so on. While many existing approaches characterize past movements of moving objects from historical trajectory data, or address the problem of finding out clusters of moving objects from data streams, such approaches fail to capture how movement behaviors unravel over time - for instance, they fail to capture typically trafficked routes or traffic jams. In this work we propose NET-CUTiS, a novel approach that addresses the problem of discovering and monitor the evolution of clusters of trajectories over road networks from trajectory data streams. We conduct several experiments that demonstrate the validity of our proposal in terms of clustering quality and run-time performance.

Over past years, various attempts have been made at analysing Time Series (TS) which has been raising great interest of Data Mining community due to its special data format and broad application scenarios. An important aspect in TS analysis is Time Series Classification (TSC), which has been applied in medical diagnosis, human activity recognition, industrial troubleshooting, etc. Typically, all TSC work trains a stable model from an off-line TS dataset, without considering potential Concept Drift in streaming context. Domains like healthcare look to enrich the database gradually with more medical cases, or in astronomy, with human's growing knowledge about the universe, the theoretical basis for labelling data will change. The techniques applied in a stable TS dataset are then not adaptable in such dynamic scenarios (i.e. streaming context). Classical data stream analysis are biased towards vector or row data, where each attribute is independent to train an adaptive learning model, but rarely considers Time Series as a stream instance. Processing such type of data requires combining techniques in both communities of Time Series (TS) and Data Streams. To this end, by adopting the concepts of Shapelet and Matrix Profile, we conduct the first attempt to extract the adaptive features from Time Series Stream based on the Test-then-Train strategy, which is applicable in both contexts: a) under stable concept, learning model will be updated incrementally; b) for data source with Concept Drift, previous concepts that do not represent the current stream behavior will be discarded from the model.

In this paper, we predict the movement of objects under the circumstance where external sensors placed on the road-sides (e.g., traffic surveillance cameras) capture their trajectories. This type of trajectories may have very different mobility patterns since they are not restricted to a fleet or a community of users. However, their reported positions are sparse due to the sparsity of the sensor distribution, and incomplete, since the sensors may fail to register the passage of objects. In this paper, we first analyze such external sensor trajectories based on a real dataset, which evidenced the problems of their sparsity and their incompleteness, and hinders the location prediction. In this context, we proposed an approach for coping with the missing data problem. We discussed how to apply this approach in conjunction with the predictors based on Recurrent Neural Networks. In particular, we adjusted the accuracy metrics to account for missing values in the test set, by introducing the distance between the predicted location and the registered next location. We evaluate our approach compared to the baselines, showing an improvement of about 23% in the prediction accuracy while reducing the overall distances. In spite of the contribution of many works in location prediction, at the best of our knowledge, none of those works have studied location prediction for trajectories based on external (road-side) sensors data.

In this demonstration, we present a framework to predict the movement of moving objects under the circumstance where external sensors placed on the road-sides (e.g., traffic surveillance cameras) capture their trajectories. The reported positions in such trajectories are sparse due to the sparsity of the sensor distribution, and incomplete, since the sensors may fail to register the passage of objects. In our framework, we cope with the missing data coming from the external sensor trajectories, which improves the quality of predictions in terms of accuracy and closeness in the road network.

International audience

Sky surveys represent a fundamental data source in astronomy. Today, these surveys are moving into a petascale regime produced by modern telescopes. Due to the exponential growth of astronomical data, there is a pressing need to provide efficient astronomical query processing. Our goal is to bridge the gap between existing distributed systems and high-level languages for astronomers. In this paper, we present efficient techniques for query processing of astronomical data using ASTROIDE. Our framework helps astronomers to take advantage of the richness of the astronomical data. The proposed model supports complex astronomical operators expressed using ADQL (Astronomical Data Query Language), an extension of SQL commonly used by astronomers. ASTROIDE proposes spatial indexing and partitioning techniques to better filter the data access. It also implements a query optimizer that injects spatial-aware optimization rules and strategies. Experimental evaluation based on real datasets demonstrates that the present framework is scalable and efficient.

Ridesharing services are getting a lot of attention in the recent years as they are beneficial for both travelers and drivers, and friendly to the environment. The problem is that these services are isolated from existing public transportation networks. They are proposed as alternative plans and not as part of a trip plan. Integrating these services may vastly improve the trips quality and serve as a backup plan in case delays or unexpected events happen. The main challenge facing the integration is limiting the search space and coping with the specific characteristics of ridesharing. This paper introduces RETRy, a system that enables the integration of ridesharing services with existing trip planners to provide real multi-modal trip planning solutions in near-real time.

Integrating transportation data is a key issue to provide passengers with optimized and more suitable trips that combines multiple transportation modes. Current integration solutions in the transportation domain mostly rely on experts knowledge and manual matching tasks. Besides, existing automatic matching solutions do not exploit the geospatial features of the data. This demo introduces an instance based system to identify geospatial properties and match transportation points of transfers using geocoding services as mediators.

Recent research initiatives in the domain of business process management such as process intelligence, monitoring, and mining have shown significant results in automated process environments. However, such techniques fall short to provide efficient solutions and support for non-fully automated business processes i.e., processes embodying dynamic, continuous, and manual activities such as in logistics. More precisely, things turn to be very challenging when it comes to consider the monitoring and violation predictions through-out context-dependent and manual processes. Unlike current initiatives that mainly focus on the model of the process as a whole, we shift in this work towards instance-based and specific processing for each activity. We showcase a contextualized template-driven framework called the buttery, along side its architecture that could address the needs of continuous monitoring and prediction. Satisfactory results from evaluations on real data demonstrate the effectiveness of our framework.

Recent approaches for online clustering of moving objects location are restricted to instantaneous positions. Subse-quently, they fail to capture the behavior of moving objects over time. By continuously tracking sub-trajectories of moving object at each time window, it becomes possible to gain insight on the current behavior and potentially detect mobility patterns in real time. In our previous work [1], we proposed CUTiS, an incremental algorithm for discovering and maintaining the density-based clusters in trajectory data streams, while tracking the evolution of the clusters. This paper extends [1] to CUTiS* by proposing an indexing structure for sub-trajectory data based on a space-filling curve. The proposed index improves the performance of our approach without losing quality in the clusters results as we show in our experiments conducted on a real dataset.

Movement tracking becomes ubiquitous in many applications, which raises great interests in trajectory data analysis and mining. Most existing approaches cluster the whole trajectories offline. This allows characterizing the past movements of the objects but not current patterns. Recent approaches for online clustering of moving objects location are restricted to instantaneous positions. Subsequently, they fail to capture moving objects' behavior over time. By continuously tracking moving objects' sub-trajectories at each time window, rather than just the last position, it becomes possible to gain insight on the current behavior, and potentially detect mobility patterns in real time. In this work, we tackle the problem of discovering and maintaining the density based clusters in trajectory data streams, despite the fact that most moving objects change their position over time. We propose CUTiS, an incremental algorithm to solve this problem, while tracking the evolution of the clusters as well as the membership of the moving objects to the clusters. Our experiments were conducted on real data sets, and it shows the efficiency and the effectiveness of our method.

Trajectory pattern mining allows characterizing movement behavior, which leverages new applications and services. Most existing approaches analyse the whole object trajectory rather that the current movement. Besides existing approaches for online pattern discovery are restricted to instantaneous positions. Subsequently, they fail to capture the movement behaviour along time. By continuously tracking moving objects sub-trajectories at each time window, rather than just the last position, it becomes feasible to gain insight on the current behaviour, and potentially detect mobility patterns in real time. This demonstration presents a novel framework for online mobility pattern discovery in sub-trajectory data streams. Key innovations include: (i) Online discovery of mobility patterns and pattern evolution by tracking the sub-trajectories of moving objects, (ii) A novel structure, called micro-group, to represent the relationship among moving objects, and (iii) An incremental algorithm to maintain micro-groups and to capture their evolution on highly dynamic sub-trajectory data. We present various demonstration scenarios using a real data set.

Mobile participatory sensing could be used in many applications such as vehicular traffic monitoring, pollution tracking, or even health surveying. However, its success depends on finding a solution for querying large numbers of users which protects user location privacy and works in real-time. This paper presents PAMPAS, a privacy-aware mobile distributed system for efficient data aggregation in mobile participatory sensing. In PAMPAS, mobile devices enhanced with secure hardware, called secure probes (SPs), perform distributed query processing, while preventing users from accessing other users' data. A supporting server infrastructure (SSI) coordinates the inter-SP communication and the computation tasks executed on SPs. PAMPAS ensures that SSI cannot link the location reported by SPs to the user identities even if SSI has additional background information. In addition to its novel system architecture, PAMPAS also proposes two new protocols for privacy-aware location-based aggregation and adaptive spatial partitioning of SPs that work efficiently on resource-constrained SPs. Our experimental results and security analysis demonstrate that these protocols are able to collect the data, aggregate them, and share statistics or derived models in real-time, without any location privacy leakage.

Privacy became one of the main concerns in location-based services in general and in community-based traffic monitoring in particular. This demonstration presents a new approach for privacy preserving online traffic monitoring using mobile probes. It combines hardware and software solutions, and a secure protocol to collect, aggregate and share the traffic information.

Skyline queries were introduced to formulate multi-criteria searches. Such a query tries to select in a relation the tuples that optimize all the criteria, called dominant tuples. There rarely exists a single dominant tuple, but usually a set of incomparable ones, the skyline set. Unfortunately, the deterioration of the query (the size of its answer) increases proportionally with the number of criteria. To address this limitation, we propose a flexible approach to categorize and refine the skyline set by applying successive relaxations of the dominance conditions with respect to user's preferences. Our approach, called θ-skyline, is based on decision theory which deals with decision-making in the presence of conflicting choices. We also define global ranking method over the skyline set.

In this paper we propose PARINET, a new access method to efficiently retrieve the trajectories of objects moving in networks. The structure of PARINET is based on a combination of graph partitioning and a set of composite B+-tree local indexes. PARINET is designed for historical data and relies on the distribution of the data over the network as for historical data, the data distribution is known in advance. Because the network can be modeled using graphs, the partitioning of the trajectory data is based on graph partitioning theory and can be tuned for a given query load. The data in each partition is indexed on the time component using B+-trees. We study different types of queries, and provide an optimal configuration for several scenarios. PARINET can easily be integrated into any RDBMS, which is an essential asset particularly for industrial or commercial applications. The experimental evaluation under an off-the-shelf DBMS shows that PARINET is robust. It also significantly outperforms both MON-tree and another R-tree based access method which are the reference indexing techniques for in-network trajectory databases.