Since 1994, Instituto Tecnológico de la Informatica (ITI) has focused on the needs and problems of companies, seeking technological solutions that respond to social and economic challenges that improve industrial competitiveness, fostering a more intelligent and sustainable society.

ITI provides knowledge, infrastructures and technologies to answer technology and business challenges coming from companies, as well as funding assessment to cover their research and digitalization processes.

More than 300 professionals work together in ITI, all of them from different backgrounds, experienced in customer satisfaction, and concern and vocation for research applied to real problems.

In the last year ITI has conducted over 135 R&D projects and around 240 companies have relied on ITI as a “technologic partner”. All this using an open and collaborative model that allows it to generate knowledge and experience for developing innovative and advanced technological solutions and services.

ITI’s research activity is the result of a Technology Monitoring activity via its Technology Observatory, Trend Detection through participating in major national and international technology platforms, and Active Listening to active enterprises needs.

ITI is located in the Polytechnic City of Innovation (CPI) which is the Science Park of the Polytechnic University of Valencia (UPV). The CPI is built on a Open Collaboration Network model, with a flexible configuration, that brings together public and private stakeholders that share their knowledge and resources on a voluntary basis.


ITI is one of the partners of the AIDEAS project where it brings its expertise from two different groups: the Perception, Recognition, and Artificial Intelligence Algorithms (PRAIA) and the Applied Optimization Systems (SOA) groups.


The main activities of the PRAIA group imply research, experimentation, design and implementation of techniques that allow computers to learn through algorithms capable of generalising behaviours, recognising patterns from provided information and improving using interaction and learning techniques. These learning techniques enable the resolution of problems such as quality control in manufacturing or the creation of decision support tools in healthcare.

PRAIA group’s main strategic R&D areas are healthcare data analysis (AI/HEALTH) for diagnosis and early detection of diseases and industrial part analysis (AI/II3D) through image acquisition and 3D processing for sample classification and quality control. Nevertheless, PRAIA also responds to R&D needed in other tasks with a strong AI component (AI/SC), which links with the business environment ITI regularly works.

PRAIA focuses on Artificial Intelligence (AI) which has become part of the popular vocabulary through its constant use in the media and its increased application in all sectors and fields. Much of the expansion of AI is motivated by significant advances in Machine Learning (ML). ML involves using algorithms that allow computers to autonomously learn to perform a given task through analysing examples rather than explicit programming by a person. Despite the promising prospects for this field, there are multiple challenges in applying these techniques in a real-world environment. It is typical for the industry, healthcare, and other domains to work with moderate-sized datasets characterised by few samples. This reality makes it difficult to establish reliable decision boundaries with a small number of observations, which implies a lower accuracy in the models obtained. On the other hand, it is possible that the problem posed is incomplete because it is not possible to be sure to what extent the objective is related to the information available for everyone.

The combination of these challenges and the high degree of specialization needed to offer significant and innovative results concerning state of the art has made PRAIA focus its efforts on two critical domains: Industry and Health. In addition, a more basal and general line of work is maintained to provide an initial response to problems posed by companies and organizations. Thus, PRAIA focuses its work in AI through its experience in pattern recognition and machine learning, along the following lines:

·         AI applied to 3D Industrial Inspection [3DII].

·         AI applied to the field of Health [HEALTH].

·         Research and development for tasks with a strong AI component [SC].

AI covers a significant number of techniques and is of interest in many domains and topics. In this manner, it covers machine learning methods, going through computer vision, natural language processing or data mining. These techniques can be applied in many domains: healthcare, finances, manufacturing, transportation, etc.

The Group expectations

PRAIA group participation in the AIDEAS project falls in the line of 3D Industrial Inspection [3DII]. For this strategic line, the work is focused on applying artificial intelligence in industrial environments, especially for quality control through 3D inspection. It aims to improve industrial processes such as in-line inspection, early detection of defects in the production environment, increasing product quality, and reducing material waste. Machine learning, pattern recognition, and metrology techniques are applied to achieve these objectives, ensuring quality and accuracy standards beyond the reach of traditional industry.

Within the AIDEAS project, PRAIA will play a major role creating an AI-supported 3D analysis and comparison tool that will detect differences between an expected/ideal 3D product model and the one captured by the produced object.


The Applied Optimization Systems (SOA) group is formed by professors with expertise in statistics and operations research and professionals with expertise in various branches of computer science.

This group conducts research in both general and specific optimization problems of relevance to different sectors at local, national or international level. The main motivation of the SOA group is the transfer of knowledge to the productive and commercial sectors. To this end, they have focused on the development and application of optimization techniques for solving real problems of great complexity. This type of solutions incorporates intelligent systems capable of analysing and processing an immense number of variables and data, in minimum time achieving optimized solutions.

The SOA group focuses on production, logistics, routing and inventory problems, among many others. They provide solutions to problems for which existing procedures have not been able to provide satisfactory answers. To this end, they use and develop the most advanced optimization techniques from operations research, decision sciences, computer science, artificial intelligence and industrial engineering.

Another important branch is the creation of tools oriented to the design, development, testing and implementation of optimization algorithms. With the intention of facilitating the implementation and development of optimization algorithms, they have been working for several years on the creation and improvement of a framework called FACOP (Framework for Applied Computational Optimization Problems). They have also developed some tools that accelerate the design, testing and deployment of optimization algorithms through FACOP.

Through the years they have acquired the ability to solve different problems applied to industry and businesses. Some of the optimization problems that have been explored both in the form of basic research and in the development of applied algorithms are:

·         Scheduling: It refers to finding a program or production plan in an industrial environment where there are machines capable of carrying out operations to obtain a certain product or batch of product. Finding a solution to these problems means determining the production order of the batches and assigning each operation of each batch to a machine at a point in time.

·         Routing: These are problems where the best possible route must be found for one or more vehicles. These routes may involve unloading and/or loading of products or passengers.

·         Decision problems at ports: Modern ports concentrate a specific yet large set of decision problems.

·         Fleet location problems: These problems focus on selecting the best locations for vehicle parking with the objective of covering as much area as possible.

·         SOA have also worked on operational research such as time series forecasting and the creation of optimized MRP (material requirements plan).

The Group expectations

SOA have laid out several objectives for their team to achieve. Their aim is to improve our technologies surrounding optimization algorithms, which will enhance their ability to create and execute them. Additionally, they plan to increase the Technology Readiness Level of the FACOP framework.

They aim to expand their knowledge and find solutions to decision problems faced by international companies. To accomplish this, they will create new optimization algorithms specifically designed to solve pilot optimization problems.

They also plan to improve their understanding of technologies provided by partner organizations. Furthermore, they would like to increase connectivity between their tools and other AI systems, robotics, and augmented reality, which will be used throughout the project. Publishing scientific research regarding the optimization problems they aim to solve is also one of their goals.

Contributions to the AIDEAS project:

The main contributions to the projects from ITI are the following:

·         Contribution in the project vision and AIDEAS Framework definition.

·         Lead the requirements identification and specification definition of AIDEAS project.

·         Lead the development of MRP AI applications based on FACOP for optimizing materials and components procurement.

·         Develop an AI application for fast-response rescheduling using model-driven methods for rapid response reprogramming, allowing production replanification and changes.

·         Develop an AI-supported 3D analysis and comparison tool (ZG3D) for detecting differences between an expected/ideal product model and the produced one.

·         Contribute to the integration, training and validation of the industrial Use Cases selected.

·         Contribute to the dissemination and communication strategy in addition to the exploitation and standardisation actions of the project.

·         Lead the generation of the Knowledge and Data Management Plan (KDMP).

·         Provide the ITI DataHub to host the AIDEAS cloud platform services.