BrainMap

Denis Stănescu

- Academia Tehnică Militară „FERDINAND I”

Researcher | Teaching staff | PhD student

Curriculum Vitae (05/07/2021)

Expertise & keywords

Building a collection of datasets for use in projects based on artificial intelligence algorithms in the field of national security Call name: P 5.6 - SP 5.6.3 - Toate temele
PN-IV-P6-6.3-SOL-2024-3-0320 2024 - 2026

Role in this project: Key expert

Coordinating institution: UNIVERSITATEA NAȚIONALĂ DE ȘTIINȚĂ ȘI TEHNOLOGIE POLITEHNICA BUCUREȘTI

Project partners: UNIVERSITATEA NAȚIONALĂ DE ȘTIINȚĂ ȘI TEHNOLOGIE POLITEHNICA BUCUREȘTI (RO); Academia Tehnică Militară „FERDINAND I” (RO); SOFTRUST VISION ANALYTICS S.A. (RO)

Affiliation:

Project website: https://deepdataromania.aimultimedialab.ro/

Abstract:

The DeepDataRomania project aims to improve research skills and security software solutions on the local market (made in Romania), responding to the operational requirements related to the development of a set of integrated services for the aggregation, manipulation and pre-processing of data collections, intended for development , evaluating, validating and increasing the performance of products with Artificial Intelligence components, applied in the field of security. This project proposes the research, investigation, development and implementation of data sets in various security and surveillance scenarios, a set of AI algorithms for processing data associated with security scenarios, but also the creation and integration of web services and platforms that help to the development of databases associated with various security scenarios. Also, in addition to the requirements, the project aims to develop a web platform to help measure the performance of AI algorithms under similar conditions, helping system users to understand which AI variation or model performs best and under which conditions . The main components of the system will reach a maturity level of TRL8, and the project team will provide to the beneficiary the source code developed within the project, as well as the web platforms and Artificial Intelligence systems in the form of a Docker container.

Capacity development for the participation in the EU programs for "pooling and sharing" of secure satellite communications Call name: P 5.6 - SP 5.6.3 - Toate temele
PN-IV-P6-6.3-SOL-2024-2-0200 2024 - 2026

Role in this project: Key expert

Coordinating institution: AGENTIA SPATIALA ROMANA

Project partners: AGENTIA SPATIALA ROMANA (RO); UNIVERSITATEA NAȚIONALĂ DE ȘTIINȚĂ ȘI TEHNOLOGIE POLITEHNICA BUCUREȘTI (RO); RARTEL S.A. (RO); INSTITUTUL NATIONAL DE CERCETARE - DEZVOLTARE IN INFORMATICA - ICI BUCURESTI (RO); INSTITUTUL DE STIINTE SPATIALE-FILIALA INFLPR (RO); Academia Tehnică Militară „FERDINAND I” (RO); INSTITUTUL NATIONAL DE CERCETARE - DEZVOLTARE PENTRU FIZICA SI INGINERIE NUCLEARA " HORIA HULUBEI " - IFIN - HH (RO)

Affiliation:

Project website: http://dk-pex.rosa.ro/

Abstract:

The DK-PEX project aims to develop the capacity (DK) of Romania to participate in the European Programs of Secure Satellite Communications (PEX), respectively GOVSATCOM and IRIS2 (formerly Secure Connectivity - which adds to GOVSTACOM additional services such as the distribution of quantum keys from the former EuroQCI and by adding a European mega constellation of communications satellites). The project aims to develop the national APEX system (access to PEX - obligation of the EU member state) in close collaboration with the European Commission - through the management of the two programs) and with the Romanian institutions eligible to be users. The APEX system will be based on existing communication infrastructures to which will be added the hardware and software subsystems located at the national Competent Authority (which is the single point of interface with the European systems) and terminals for the user institutions. The APEX system will be developed and implemented simultaneously with the EU GOVSATCOM/IRIS2 Hub systems. Between the completion of the project (mid-2026) and the commissioning of the initial operational capability (IOC) of the European system (early 2027), there remains a gap of about 6 months at the disposal of the state authorities in which using the APEX system as a basis and the primary regulations European, to develop the national access regulations. Thus, the technical and legislative conditions will be met for Romania to have access to the services provided by GOVSATCOM/IRIS2. The institutions in the composition of the consortium, through diversity and complementarity, cover the entire complex area of competences necessary for the realization of the project, from competences in the field of space, satellite communications, IT&C systems, cyber security, national regulation, European regulation and direct participation in projects related, including both national and EU GOVSATCOM and EuroQCI domains.

Platform specialized in identifying and evaluating early warning indices for crisis management Call name: P 2 - SP 2.1 - Soluţii - 2021
PN-III-P2-2.1-SOL-2021-0063 2021 - 2023

Role in this project: Key expert

Coordinating institution: Academia Tehnică Militară „FERDINAND I”

Project partners: Academia Tehnică Militară „FERDINAND I” (RO); UNIVERSITATEA NAŢIONALĂ DE ŞTIINŢĂ ŞI TEHNOLOGIE POLITEHNICA BUCUREŞTI (RO); SOFT GALAXY INTERNATIONAL S.R.L. (RO); MARCTEL - S.I.T. S.R.L. (RO)

Affiliation: Academia Tehnică Militară „FERDINAND I” (RO)

Project website: https://www.27sol.ro/

Abstract:

The project aims to develop a Platform specialized in identifying and evaluating early warning indices for crisis management - PIMS-IAT, which combines multidisciplinary scientific knowledge about web crawling, machine learning, crisis management, early warning and knowledge of communications. Within the platform, a mobile solution pilot center will be designed, developed, approved and operationalized. The mobile solution is a portable version of the platform, which allows the analysis of information flows in mobility conditions and will be installed on a dedicated server that will communicate in the network with a smart board with touch screen. The versatility and scalability of PIMS-IAT lies in the fact that it will achieve the integration of several communication technologies and software, and the systems can also work independently or integrated separately in other systems in SNAOPSN. A testing-evaluation platform will be developed that will contain databases and software applications to provide a software functionality testing solution as a whole, as PIMS-IAT will integrate multiple complex technologies. The platform will capture from multi-source streams, analyze and identify possible risks, using search algorithms that will be able to extract information based on hierarchies, synonyms, relationships, native language, fuzzy searches, proximity and Boolean operators. The use of the risk score methodology allows the sorting and differentiation of false content by applying relevance markers extracted from the Bayesian neural network on any data set generated by the system.

Identifying the unusual behavior of people in video streams Call name: P 2 - SP 2.1 - Soluţii - 2021
PN-III-P2-2.1-SOL-2021-0024 2021 - 2023

Role in this project: Key expert

Coordinating institution: UNIVERSITATEA OVIDIUS

Project partners: UNIVERSITATEA OVIDIUS (RO); SOFTRUST VISION ANALYTICS S.A. (RO); UNIVERSITATEA POLITEHNICA DIN BUCURESTI (RO); Academia Tehnică Militară „FERDINAND I” (RO)

Affiliation: UNIVERSITATEA OVIDIUS (RO)

Project website: https://ideneo.univ-ovidius.ro/

Abstract:

The IDENEO project "Identifying the unusual behavior of people in video streams" aims to raise the current level of knowledge and methods in the field of detecting suspicious behavior of people and crowds and to combat violent or terrorist actions, in certain circumstances. This will allow law enforcement to act preventively and not reactively.

To achieve this goal, the focus will be on three main aspects: (i) the development of state-of-the-art algorithms, such as AI (Artificial Intelligence), which will be able to detect humans positions in the environment, actions and behavior of people, and crowd behavior; (ii) adapting the algorithms to run on both airborne and classic cameras is yet another very important aspect of the project which will allow major flexibility by allowing a processed video stream to be obtained from any location; (iii) the integration of all developed modules in a VMS capable of rendering all relevant information to the operator, including GIS (Geographic Information System) information, in an easy and intuitive way. All the processed information (saved and displayed to the operator) will be in full compliance with GDPR laws; this will be achieved by a dedicated module that will hide sensitive data to the operators without access.

Finally, the proposed solution will allow law enforcement to detect individuals or groups and crowds of suspects, in varied and dynamic scenarios, such as public protests or within monitored areas of interest. This will allow the user to understand the entire operational scenario, by combining information from airborne cameras, classic cameras, image analysis and displaying them on the GIS map.

FILE DESCRIPTION	DOCUMENT
List of research grants as project coordinator or partner team leader
Significant R&D projects for enterprises, as project manager
R&D activities in enterprises
Peer-review activity for international programs/projects