Con esta herramienta te facilitamos un acceso a todas las ofertas y demandas de tecnología europeas y a búsquedas de socios para participar en propuestas europeas de I+D publicadas en la red Enterprise Europe Network, pudiendo filtrar los resultados para facilitar las búsquedas más acordes con tus necesidades.

¿Quieres recibir estos listados de oportunidades de colaboración en tu correo de forma periódica y personalizada? Date de alta en nuestro Boletín

Los términos de búsqueda han de ser en inglés.

Paquete a medida para sistemas y aplicaciones inteligentes en sectores muy exigentes

Resumen

Tipo:
Oferta Tecnológica
Referencia:
TOIT20170308001
Publicado:
21/03/2017
Caducidad:
21/03/2018
Resumen:
Una pequeña empresa italiana de ingeniería especializada en sistemas y sensores basados en técnicas avanzadas de TI e Inteligencia Artificial para seguridad, logística y gestión de tierras ha desarrollado un paquete integral eficiente y adaptable con algoritmos computacionales evolutivos para resolver problemas severos de optimización en diversos campos (biología, seguridad, planificación compleja, TI, etc.). La empresa ofrece un paquete a medida, incluyendo el código fuente, a compañías y grupos de investigación interesados en inteligencia artificial, ingeniería avanzada y aplicaciones de TI. El objetivo es establecer acuerdos comerciales con asistencia técnica.

Details

Tittle:
A customisable package for intelligent systems and applications in highly demanding fields
Summary:
A small engineering Italian company has developed a comprehensive, efficient and adaptable package with evolutionary computational algorithms, to be used with hard optimisation problems in various fields (biology, security, complex planning, IT, etc.). The company is ready to provide a customised package, including source code, under a commercial agreement with technical assistance to companies and research groups interested in artificial intelligence, advanced engineering and IT applications.
Description:
A small engineering Italian company, founded in 2008, is specialised in systems and sensors for security, logistics, and land management based on advanced IT and Artificial Intelligence (AI) techniques. Based on such a long and varied experience, the company has developed a comprehensive package with evolutionary computational algorithms that can be used to solve a variety of hard optimisaton problems in varoius fields (biology, security, complex planning, etc.) and a wide range of problem settings.

In general terms, evolutionary computation is a subfield of artificial intelligence, providing an algorithmic tool based on evolution. It is really recommended with problems where other techniques risk to find only local minima / maxima (e.g. the first peak but not the highest peak).

Typical problems where the technique can be used are related, for instance, to computer-automated design: e.g. design of sophisticated trading systems in the financial sector; multi-objective design of automotive components for crashworthiness, weight savings, and other characteristics; water resource systems or anti-terrorism systems.

Another example of application is in silico experimental procedures to study common aspects of general evolutionary processes. The approach is also used for error optimization with training algorithms in neural or similar networks.

The approach is well known and documented in the scientific literature and many variants and extensions of evolutionary algorithms exist, suited to more specific families of problems and data structures. Also, a number of specific implementations are available and can be easily acquired.

Nonetheless, the existing solutions tend to be very data/application dependent so that experimenting with different algorithms requires additional coding to prepare input data and to tailor the algorithm.

Thus, a first key aspect of the package is that it includes a wide set of different algorithms (such as Ant Colony Optimization, Artificial Bee Colony, Particle Swarm Optimization, etc.) that can be easily applied to the same set of data, so that it is possible to compare and verify different approaches for optimising a given complex (mono- or multi-objective) problem. All algorithms implemented in the package have been already widely tested in different applications and are highly reliable.

Another distinctive feature is that the package has been specifically implemented to exploit the power of parallel computing, by using the open source and powerful framework openMP (Open Multi-Processing), running seamlessly on most platforms, processor architectures and operating systems, including Solaris, AIX, HP-UX, Linux, macOS, and Windows.

The third advantage is that the package can be easily customised to treat a peculiar request / problem (data, parameters, etc) and the source code (the package is written in C language) can also be made entirely available.

In conclusion, the package outperforms the other solutions that are freely availble on the Internet, as none of them can provide such a large collection of algorithms to optimise generic problems, with a numeric or analytic formulation, with high performances in terms of computational times and reliabilities of solutions.

The package is a working tool that can be provided, under a commercial agreement with technical assistance, with the necessary customisation and with the integral source code.

The company is looking for partners interested to jointly develop an application. Partners are expected to be:
- research groups interested in advanced processing of scientific data
- companies developing advanced engineering applications in different fields.

Typical fields of application are chemical engineering, circuit design, digital image processesing, cloud and grid computing, malware detection, security, biology and computational chemistry, climat
Advantages and Innovations:
The package offers a few distinctive advantages over existing solutions so that evolutionary computation algorithms (EC) can be more easily deployed:

- A comprehensive set of EC algorithms, sharing the same format for input / output data

- The possibility to compare and verify different approaches for optimising a given complex (mono- or multi-objective) problem

- High efficiency with the possibility to exploit parallel computing because the package is implemented using the open source framework openMP (Open Multi-Processing), transparently running on different machines (Solaris, AIX, HP-UX, Linux, macOS, Windows)

- The source code of the customised package can be made available
Stage of Development:
Already on the market
IPs:
Copyright
CommeR Statunts Regarding IPR Status:
The algorithms are known in the literature. The implementation is protected by copyright but the software (source code) can be transferred to the partner after the customisation is done.

Partner sought

Type and Role of Partner Sought:
The company is looking for partners interested to jointly develop an application. Partners are expected to be:
- research groups interested in advanced processing of scientific data
- companies developing advanced engineering applications in different fields.

Typical fields of application are chemical engineering, circuit design, digital image processesing, cloud and grid computing, malware detection, security, etc.

Client

Type and Size of Client:
Industry SME <= 10
Already Engaged in Trans-National Cooperation:
No
Languages Spoken:
English
Italian

Dissemination

Restrict dissemination to specific countries:
Albania, Argentina, Armenia, Austria, Belarus, Belgium, Bosnia And Herzegovina, Brazil, Bulgaria, Cameroon, Canada, Chile, China, Croatia, Cyprus, Czech_Republic, Denmark, Egypt, Estonia, Finland, France, Georgia, Germany, Greece, Hungary, Iceland, India, Indonesia, Ireland, Israel, Italy, Japan, Jordan, Korea, Republic Of, Latvia, Lithuania, Luxembourg, Macedonia, The Former Yugoslav Republic Of, Malta, Mexico, Moldova, Republic Of, Montenegro, Netherlands, New Zealand, Norway, Paraguay, Peru, Poland, Portugal, Republic of Serbia, Romania, Russian Federation, Singapore, Slovakia, Slovenia, Spain, Sweden, Switzerland, Taiwan, Province Of China, Tunisia, Turkey, Ukraine, United Kingdom, United States, Viet Nam

Keywords

Technology Keywords:
01003003 Artificial Intelligence (AI)
01003009 Data Protection, Storage, Cryptography, Security
01005005 Filtrado de información, semántica, estadística
01003012 Imaging, Image Processing, Pattern Recognition
01003013 Information Technology/Informatics