The security and well-being of a nation’s citizens, as well as the protection of their lives and properties, are fundamental for prosperity. Unfortunately, in recent years, we have witnessed a surge in various types of crimes such as murder, robbery, terrorism, and kidnapping. This has placed significant pressure on Law Enforcement Agencies (LEAs) to effectively prevent and detect crimes, driving them to adopt various technologies in the criminal investigation process. Among these technologies, surveillance systems have emerged as a valuable tool for monitoring human behaviors and activities, particularly in public and densely populated areas of large cities. However, video analysis in crime investigation poses significant challenges for LEAs, requiring accurate and timely detection, recognition, and tracking of objects and individuals. Addressing this issue, we present CRIMEO, a smart system designed for mining and extracting behavioral patterns from video content. CRIMEO operates in real-time and leverages an ontology-based approach to represent complex semantic events and employ video analytics. This enables LEAs to automatically detect and identify different types of crimes. CRIMEO encompasses four key phases: data collection, analysis, storage, and visualization. In the data collection phase, video data from surveillance systems is gathered and transmitted, via Apache Kafka, to the subsequent phase after the video is split into frames. The data analysis phase applies a range of video analytics techniques, including face detection and recognition, object detection, action recognition, and more, to extract behavioral patterns from the video content. These extracted patterns are then stored in the Neo4j graph database during the data storage phase. Finally, in the visualization phase, inference rules defined by LEA experts are applied to detect and visualize criminal activities. To demonstrate the effectiveness of CRIMEO, we implemented the system across multiple scenarios, showcasing its relevance in aiding LEAs in the detection of various crime types. By utilizing CRIMEO, LEAs can benefit from advanced video analysis capabilities and real-time crime detection, ultimately enhancing their ability to maintain safety and security within their jurisdictions.

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.

Mobile crowdsensing (MCS) has emerged as a new revolutionary paradigm to collect large-scale data by the crowd. However, there is a lack of a holistic system than can provide an integrated design for this large volumes data coming from different sensors, and afford analytics capabilities. This paper provides an envision of a micro-service based architecture for implementing and automating ETL data management pipelines in MCS.

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.

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.

International audience

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.

International audience

This paper presents an approach whose objective is to support Web services substitution. Substitution means replacing a component with another component, as long as the replacing component produces the same output and satisfies the same requirements as the replaced component. Motives for substitution include Web service's non-responsiveness to client requests and better arrangement with another, competitor Web service. To perform Web services substitution with less impact on the ongoing, and sometimes critical, business processes, the approach proposes deploying communities of Web services. A community promotes the dynamic binding of Web services through a common interface, known as open service connectivity. The open service connectivity directs requests to and responses from Web services regardless of how these latter are specified, implemented, and located