Mikel Salazar

Mechanical properties prediction in high-precision foundry production

Mechanical properties are the attributes of a metal to withstand several forces and tensions. Specifically, ultimate tensile strength is the force a material can resist until it breaks. The only way to examine this mechanical property is the employment of destructive inspections that renders the casting invalid with the subsequent cost increment. In a previous work we showed that modelling the foundry process as a probabilistic constellation of interrelated variables allows Bayesian networks to infer causal relationships. In other words, they may guess the value of a variable (for instance, the value of ultimate tensile strength). Against this background, we present here the first ultimate tensile strength prediction system that, upon the basis of a Bayesian network, is able to foresee the values of this property in order to correct it before the casting is made. Further, we have tested the accuracy and error rate of the system with data of a real foundry.

Procedural approach to volumetric terrain generation

The recent outbreak of indie games has popularized volumetric terrains to a new level, although video games have used them for decades. These terrains contain geological data, such as materials or cave systems. To improve the exploration experience and due to the large amount of data needed to construct volumetric terrains, industry uses procedural methods to generate them. However, they use their own methods, which are focused on their specific problem domains, lacking customization features. Besides, the evaluation of the procedural terrain generators remains an open issue in this field since no standard metrics have been established yet. In this paper, we propose a new approach to procedural volumetric terrains. It generates completely customizable volumetric terrains with layered materials and other features (e.g., mineral veins, underground caves, material mixtures and underground material flow). The method allows the designer to specify the characteristics of the terrain using intuitive parameters. Additionally, it uses a specific representation for the terrain based on stacked material structures, reducing memory requirements. To overcome the problem in the evaluation of the generators, we propose a new set of metrics for the generated content.

Enhancing cybersecurity learning through an augmented reality-based serious game

As social networks and always-connected mobile devices grow in popularity, the control over personal information weakens. This is especially true for teenagers between 15 and 18 years old, one of the population groups that shares more information online, but also the most unaware of the risks associated with this activity. For this reason, many institutions have developed programs to educate the students in the correct use of the new communication mediums. However, the concepts about information security require a lot of expert knowledge and are very difficult to explain appropriately. In this paper, we present a serious game designed to enhance an information security presentation aimed at high school students. This is achieved through the use of augmented reality to give shape and form to the intangible cybersecurity concepts and allow the students to interact with them using the same rule set that was explained during the presentation.

Machine-learning-based surface defect detection and categorisation in high-precision foundry

Foundry is an important industry that supplies key castings to other industries where they are critical. Hence, foundry castings are subject to very strict safety controls to assure the quality of the manufactured castings. One of the type of flaws that may appear in the castings are defects on the surface; in particular, our work focuses in inclusions, cold laps and misruns. We propose a new approach that detects imperfections on the surface using a segmentation method that marks the regions of the casting that may be affected by some of these defects and, then, applies machine-learning techniques to classify the regions in correct or in the different types of faults. We show that this method obtains high precision rates.

Volumetric Virtual Worlds with Layered Terrain Generation

Procedural terrain generators are widely used in computer games, simulators and other virtual environments. Traditionally, these methods have been focused on generating realistic landscapes and their elements, like mountains or rivers. In contrast, there is a movement in the industry which employs virtual worlds using volumetric terrains. This movement uses its owns methods to generate terrains, but they lack of customization features and are completely centered around their specific problem domains. In this paper, we propose an alternative approach to generate procedural volumetric terrains specially suited for shared worlds. Our approach generates completely customizable volumetric terrains with layered materials and other features (such as mineral veins, material mixtures and underground material flow). We enable the designer to specify the characteristics of the terrain and its materials with intuitive parameters. Moreover, our method uses a specific representation for the terrain based on stacked material structures, reducing the memory size and making it easier to share.

Developing Interoperable Experiences with OpenUIX

In this demo, we present a framework that aims to provide UI designers (and end-users) with a simple but powerful language with which easily create, modify and share advanced interaction spaces. A UI description language that takes into consideration the context of the users not only to adapt the contents of the SUI to their real needs and desires, but also to allow them to automatically discover new and meaningful experiences as they go about their daily lives.

Collaborative content creation with the OpenUIX Framework

The OpenUIX framework aims to provide end-users –and developers– with a level playing field where they can not only access 3D user interfaces adapted to their context (location, time of day, hardware platform, disabilities, etc.), but also create and share them with others. To achieve this goal, the framework has a built-in toolset that allows the collaborative edition of the different components of a interaction space; from the threedimensional representations of the different entities (either virtual or real in nature), to the lighting conditions or the logic behaviors that govern the user experience. With this demo, the ISMAR 2016 attendees will be able to test several of the aforementioned collaborative edition tools in different interaction spaces across the entire conference venue (and even outside of it, if the circumstances allow it). Initially, the attendees will have the opportunity to test the different tools at the table provided by the organization of the event (and with mobile platforms provided by the presenters, to ensure the proper execution of the demo). In this way, the presenters will be able to explain and guide them through a series of basic use cases, ranging from virtual painting on 2D surfaces or 3D modeling to how to employ the UI description language the framework employs to modify the lighting conditions of the interaction space (thus allowing a more seamless integration of virtual objects into the physical world). Once the attendees go through the basic use cases and prove their understanding of the interaction techniques, they will receive a code to download a development version of an AR browser created with this framework (available for Android and iOS platforms). With this browser installed in their own devices, the attendees will be able to access other interaction spaces across the venue (that the presenters will prepare beforehand).

[POSTER] A Comprehensive Interaction Model for AR Systems

In this extended poster, we present a model that aims to provide developers with an extensive and extensible set of context-aware interaction techniques, greatly facilitating the creation of meaningful AR-based user experiences. To provide a complete view of the model, we detail the different aspects that form its theoretical foundations, while also discussing several considerations for its correct implementation.

Collective classification for the detection of surface defects in automotive castings

Iron casting production is a very important industry that supplies critical products to other key sectors of the economy. For this reason, these castings are subject to very strict safety controls to ensure their final quality. One of the most common flaws is the appearance of defects on the surface. In particular, our work focuses on three of the most typical defects in iron foundries: inclusions, cold laps and misruns. We propose a new approach that detects these imperfections on the surface by means of a segmentation method that flags the potential defective regions on the casting and, then, applies collective classification techniques to determine whether the regions are defective or not. We show that these classifiers obtain high precision rates whilst decreasing the effort of labelling.

Serious Games, Remote Laboratories and Augmented Reality to Develop and Assess Programming Skills

The project “Serious Games for Education–Programming Skills” presents an innovative technology that integrates serious games techniques with remote laboratories and augmented reality. The flexible and scalable technology is designed with a three layer structure: (1) the physical layer - ROBOT (hardware and communications) remotely manipulated; (2) AR and instruction interface middleware; and (3) end-user game application including game interface. This design enables multiple pedagogical objectives and context of use. In the first prototype we have developed a serious game, the third end-user layer, to develop and assess programming skills, algorithmic thinking and debugging.