AGATHA Project

The AGATHA consortium aims to develop a system for assisting criminal investigation police and intelligence services to facilitate the compilation of evidence of criminal practices by using the information available in open sources, analyzing them automatically.

Partner:
This project has the participation of the Judiciary Police, through its PJ-UTI-AESE unit, as a user and receiver of its results. The system is managed by employees of PJ-UTI-AESE, whom we thank for all their effort, help and constant dedication throughout the development phase of this platform.

Description:
Platform aimed at criminal investigation police and intelligence services, facilitating the collection of evidence of criminal practices by using the information available in open sources, analyzing them automatically. The following are considered sources of information: social networks, forums, images, information from the blogosphere and other sources of information present on the web, including audio and video sources.

SYSTEM MODULES
Data acquisition: collection of information from open sources, through crawling algorithms, data mining and ETL tools Video and image analysis: feature extraction from video files, automatic delimitation of moments and scenes, pattern detection and respective segmentation Audio and voice analysis: development of technologies capable of automatically obtaining information from audio data sources collected by the data acquisition module Biometric analysis: development of technologies for facial recognition with a special focus for forensic use. Voice biometrics will also be explored. By combining the 2 classifiers (face and voice identification) the error inherent to each of the identification techniques is minimized; Data management, organization and visualization: define rules for processing user information requests, for retrieving information from the system's database, using semantic search methodologies, implemented through a Visual Analytics (VA) component that will allow visual analysis of large amounts of data User interface: develop the user interface that guarantees all security measures that prevent access to users who are not properly accredited

INNOVATIVE SOLUTION
The AGATHA project will present to the market an innovative product both in technological and functional terms, being an unquestionably disruptive solution, both nationally and internationally. The system will be able to analyze large amounts of information and extract from it implicit relationships, patterns and actors, among others, through modules dedicated to the analysis of video and image, audio and text in several languages, composed of crawling and data mining algorithms. , for the collection of content in a selective and targeted manner.

IN CONSTANT EVOLUTION
Based on the editing data obtained by the researchers, the system has pre-integrated a set of self-learning tools that allow a constant improvement of the automatic results through corrections introduced by the users. Thus, this makes the platform, over time, improve its ability to make more correct transcripts, increasing the success rate and reducing the correction time spent by researchers.

CONFIDENTIALITY
The entire management of the platform is local to the security forces' facilities, safeguarding the danger of sensitive data being viewed by individuals not duly accredited. All access to the system is therefore controlled and, depending on the permissions of each user, only certain intercepts can be consulted. Thus, we intend to fulfill all the security and confidentiality requirements that a task of this nature requires.




Grants:
Project designation: AGATHA – Intelligent analysis system in open sources of information for surveillance/crime control

Project code: POCI-01-0247-FEDER-018022 and LISBON-01-0247-FEDER-018022

Main purpose: Reinforce Research, technological development and innovation

Intervention region: North, Lisbon, Alentejo

Beneficiary entity: COMPTA - Business Solutions, S.A
C.C.G./ZGDV Association, University of Évora, VOICEINTERACTION

Approval date: 2016-09-23

Start date: 2016-10-01

Completion date: 09-30-2019

Total eligible cost: €2.354.805,42
VOICE INTERACTION: €777.466,61

European Union financial support | FEDER: €1.386.907,35
VOICE INTERACTION: €310.986,65
Call us today at +1 646 504 7906 or Email us at info@voiceinteraction.tv
Stay in touch
Request a demo and experience what our Speech Processing platforms can offer you.
Call us today at
+1 646 504 7906
or Email us at info@voiceinteraction.tv
Request a demo and experience what our Speech Processing platforms can offer you.
Stay in touch