Community Research and Development Information Service - CORDIS

FP7

LASIE Report Summary

Project ID: 607480
Funded under: FP7-SECURITY
Country: Italy

Periodic Report Summary 2 - LASIE (LArge Scale Information Exploitation of Forensic Data)

Project Context and Objectives:
The LASIE project will design and develop a novel framework to assist forensic analysts in their investigations. More specifically, LASIE will provide a set of tools and processes to support law enforcement agents and investigators or analysts in their everyday work. The proposed system will significantly reduce the required investigation time by utilizing automatic processes for analysing multimedia contents, as well as visual analytics from an inference engine able to highlight otherwise hidden information. The main LASIE objectives are summarised below:
- Development of tools for supporting automated processing of very large amounts of data for all content types (text, image, video, audio, social and biometric data); the tools will apply advanced media analysis techniques and will fuse information acquired from different sources. New solutions beyond existing state-of-the-art will be investigated where necessary.
- Built a comprehensive knowledge representation framework for modelling, indexing, classification and retrieval of data for forensic applications. The framework will integrate diverse sources of information including geospatial grid representation, temporal semantics, event representation and object annotation through a multimedia ontology.
- Development of an Intelligent Evidence-based Search Engine that will enable search and retrieval in both the existing forensic databases and the various captured forensic data; the engine will exploit technologies for large-scale indexing and complex query formulation / multimodal search.
- Provision of guidance to analysts through inference and recommendation functionalities. The modules will provide possible investigation directions, perform automated inference based on the provided evidence and will highlight important information, suggest relevant information sources and supply additional information regarding a particular entity, based on its relations to other entities.
- Implementation of an intuitive user interface that will allow analysts to easily visualise and navigate through the retrieved evidence, highlight relevant events and provide feedback to refine their search criteria as well as to create their own cases in a user-friendly graphical way. The UI should integrate the Query Formulator (QF), the Visual Analytics and the Crime Scene Reconstruction.
- Provide continuous integration and testing including as many as possible modules in the LASIE platform.
- Set up appropriate pilot tests and an evaluation framework (through simulated procedures) in order to have quantitative measures of the system results to support the analyst decisions.
- Support of a series of training sessions to make analysts and operators capable of using the framework in an efficient and easy manner.
- Implementation of a Privacy-by-Design approach for privacy protection through built-in, rather than added-up, legal and ethical compliance mechanisms. This approach will ensure that the aforementioned functionalities and the used forensic data strictly obey all legal and ethical restrictions and national laws and that the outcomes of the system will be accepted in European courts of law.
- Disseminate project results to maximise visibility and coordinate the contribution of LASIE partners to standardization, analysing the needs for novel normative activities and technical contributions to existing standards, and defining a common participation strategy.
- Prepare an exploitation plan, including all available tools that will be available by the end of the project.
LASIE will develop appropriate (semi-) automatic tools for facilitating the analysts in their investigation activities. Such added value represents LASIE’s Unique Selling Proposition in the forensic sector. This will satisfy the products and services demand in forensic investigations which is increasing year after year.

Project Results:
A summary of the work and main results achieved during the first reporting period are summarised below:
- All societal challenges posed by the LASIE prototype have been discussed and steps have been undertaken to tackle these challenges. Privacy monitoring included report of broad recommendations on how to take into consideration the societal issues raised by LASIE (D2.4, D2.2).
- Use cases and scenarios have been updated as well as the system-level requirements and design of the LASIE architecture (D3.1, D3.3 and D3.5).
- New methods and new algorithms for supporting automated processing of very large amounts of data came up, either by development of existing state-of-the-art or by introducing novel solutions, in all supported modalities, namely text, image, video, audio, social and biometric data (D4.2, D4.3, D4.4, D4.5, D4.6).
- Advanced version of the Knowledge Representation Repository and LASIE knowledge model has been implemented and integrated within the system using Elastic search, hypergraphDB and mongoDB technologies. Knowledge Acquisition modules have been advanced with focus on keywords extraction, semantic analysis and named-entity detection. The first version of the Knowledge visualization toolkit has been realized to allow chronical/casual analysis of processed events in investigation reports.
- Improvement of methods for indexing and search as well as support of complex query formulation in LASIE evidence-based search engine (D6.2). A crowd-sourcing tool specifically designed and developed to support the assessment of super recognisers.
- Finalisation of Evidence Graph and integration to LASIE framework, which describes relations between suspects and objects. Finalisation of LASIE recommendation module and LASIE inference module that provide guidance to analysts, exploit information from previous cases, filter results and remove inconsistencies (D7.1, D7.3).
- A first working version of the user interface has been implemented integrating QF, Visual Analytics and Crime Scene Reconstruction (D8.2). This first working version was presented in 2nd LASIE workshop, during the training sessions, where users had the opportunity to test the platform.
- The integration framework was early defined and guidelines were provided to all technical partners (D9.1). More than 20 LASIE modules have been successfully integrated in the first integrated version of the platform.
- Pilot planning was successfully fulfilled during the 2nd reporting period. Initial scenarios for the pilots have been defined and relevant datasets have been prepared (D10.1).
- Successful collaboration with LASIE External User Advisory Board (EUAB). The LASIE website has been constantly updated, while LASIE newsletters have been published. LASIE project was disseminated through involvement of the consortium in several public events, international fairs, workshops and conferences.
- A market analysis and initial exploitation plans have been performed during the 2nd reporting period and reported in the relevant Deliverable D11.5 (M24). D11.5 defines the preliminary starting points in terms of market analysis and exploitable assets, partner exploitation opportunities (individual exploitation plans) as well as available options for the joint Exploitation Plan of the LASIE project.
- An approach for contribution to standards was introduced (Media Orchestration in the Security Domain, contribution to MPEG).
- The 1st LASIE workshop (London, July 2015) and the 2nd LASIE workshop (London, June 2016) were successfully fulfilled.

Potential Impact:
The LASIE project is expected to have significant economical and social impact in European Union Member states. More specifically:
1) LASIE is expected to provide a set of tools for automated initial analysis of the vast amounts of heterogeneous forensic data, guiding the investigation procedure through the incorporation of a recommendation functionality. This will significantly facilitate the investigation process of the analysts. The proposed approach will not only increase the number of resolved cases, but will also lower the cost of investigation. Thus, LASIE is expected to have significant impact on the “cost of the crime” and resolution of crimes.
2) LASIE will carefully consider the Legal, Ethical and Privacy issues. These issues will be studied by experts within the project and collaboration with projects specifically dedicated to such issues will be sought. Moreover, the LASIE framework will respect privacy and ethical issues by design. Such a result will increase public acceptance of next generation security system.
3) By applying LASIE as an investigation system, an increased effectiveness of the investigation processes will be achieved. This is expected to have a positive impact not only in the actual level of security but also in the psychological feeling of security, resulting in a positive effect in the every-day quality of life especially in the social environment.
3) With respect to the impact on economic growth, LASIE will develop original state of the art know-how (and later on skills) in a specific area of investigation devoted to security systems applications. This area has significant economic potential itself. Yet, the LASIE results will be achieved in the broader area of security and data analysis processing, which is a powerful driver of economic growth (and employment) in today knowledge-based economy. In short, LASIE will help creation of opportunities in the specific area of investigation systems but a larger fallout of some of its results can be envisaged in all areas where data processing can be harnessed to support security and innovation.
4) The market sector related to LASIE is the one related to forensic sector, in particular law enforcement investigators/analysts dealing with the analysis of different source of forensic data coming from surveillance systems, voice recording devices, computer/mobile-phone network monitoring platforms, the networked social services. Such market is growing at a very high pace in recent years. In case of crimes, it is the responsibility of forensic sector to manage the investigation process in order to save lives and restore a sense of order. One of the constant challenges encountered by forensic data is the search in extremely large collections of heterogeneous forensic data, i.e. the information that is required for making high-quality decisions under pressure. Without accurate analysis, analysts/investigators find it hard to make fast and correct decisions. In fact, the absence of reliable evidences (combined with the flood of unsubstantiated reports and rumours) could jeopardise a fast resolution of the crimes.
5) To solve such problems, LASIE will develop appropriate (semi-) automatic tools for facilitating the analysts in their investigation activities. Such added value of LASIE will represent is Unique Selling Proposition in the forensic sectors. LASIE will provide its unique platform towards a market that is expected to increase its spending constantly, in an overall trend that is making Security one of the fastest growing and challenging emerging business environments.

List of Websites:
http://www.lasie-project.eu/

Contact

Maria Silvia Boi, (Senior Project manager)
Tel.: +39 3408100593
E-mail

Subjects

Safety
Record Number: 196989 / Last updated on: 2017-04-13
Follow us on: RSS Facebook Twitter YouTube Managed by the EU Publications Office Top