Nikolaos Doulamis

Personalized View Selection of 3D Molecular Proteins

A non-linear classifier is adopted in this chapter to represent the best view for 3D molecule of a protein onto the 2D screen plane. The classifier receives as inputs visual as well as semantic features and actually model the entropy needed to display with high performance the protein. The visual descriptors have been extracted in our case using the OpenCV tookit of the Intel Corporation, while the semantic information includes additional knowledge for the protein. Finally, an XML –based middleware is used to embed complex computer vision algorithms into the contemporary protein viewers which allow only limited transformations on the protein data structure. Experimental results on real-life protein molecules are presented to demonstrate the outperformance of the proposed algorithm.

Transforming Intangible Folkloric Performing Arts into Tangible Choreographic Digital Objects: The Terpsichore Approach.

Intangible Cultural Heritage is a mainspring of cultural diversity and as such it should be a focal point in cultural heritage preservation and safeguarding endeavours. Nevertheless, although significant progress has been made in digitization technology as regards tangible cultural assets and especially in the area of 3D reconstruction, the e-documentation of intangible cultural heritage has not seen comparable progress. One of the main reasons associated lies in the significant challenges involved in the systematic e-digitisation of intangible cultural assets, such as performing arts. In this paper, we present at a high-level an approach for transforming intangible cultural assets, namely folk dances, into tangible choreographic digital objects. The approach is being implemented in the context of the H2020 European project “Terpsichore”.

Machine Learning and Pattern Analysis Methods for Profiling in a Declarative Collaorative Framework

One important issue for a collaborative design framework is the intuitive manner designers describe scenes. To address the humans’ subjective description of a scene, personalization mechanisms are incorporated in the proposed architecture. In this paper, we examine different pattern analysis and machine intelligence algorithms for profiling in such framework. Two main approaches are described; the single (independent) profile estimation and the collaborative (dependent) case. Experimental results are presented to illustrate the efficiency of the proposal user’ profile methodologies.

Hybrid Meta-Filtering System for Cultural Monument Related Recommendations.

A two-phase monument recommendation concept is presented. The system ranks the alternative destinations by using the point and click technique during the process. The core of the system is a hybrid image filtering mechanism, which utilize both collaborative and content-based filtering. At first, the user profile is modelled in the form of a distance matrix, exploiting the user’s annotations over a small set of descriptive images. At the same time, user’s profile is compared to other profiles; the closest profiles are utilized to refine the distance matrix. Then, the system provides relevant images to the user asking him/her to select few. The selected images are used in order to rank the alternative monuments.

Deep Convolutional Neural Networks for Modeling Patterns of Spaceborne Interferometric SAR Systems Signals

Spaceborne radar systems (SAR) are nowadays considered as very beneficial schemes towards a successful implementation of many engineering applications such as surveillance, maritime traffic management, reconnaissance, etc. Among others, modeling and prediction of ionospheric disturbances are considered as crucial towards successful SAR-based engineering applications. However, modeling ionospheric disturbances behavior is a very challenging research task due to high non-linearities involved in the mature of the data and their dynamics. For this reason, previous research efforts have been concentrated on the use of adaptable neural networks models and echo state machines that enable the effective modeling and prediction of the ionospheric disturbances. In this paper, we investigate the use of deep machine learning algorithms and particularly of Deep Convolutional Neural Networks (CNNs). Deep machine learning paradigm has been introduced in the last decade as a new advanced tool for modeling complex dynamic processes. Deep learning better emulates human brain operation, and makes effective processing of large amounts of unlabeled training data for extracting structures and internal representations from the raw sensory inputs. In this paper, CNNs are used to identify patterns in Spaceborne Interferometric SAR (InSAR) systems signals. CNNs can be controlled by varying their depth and breadth, and they also make strong and mostly correct assumptions about the nature of data taking into account local dependencies and varying statistics. SAR systems signals derived from real interferograms produced by earthquakes occurred in Greece the last fifteen years from the Dionysos Satellite Observatory of the National Technical University of Athens (NTUA) in Greece and objective criteria, such as false positives and negatives, are used to evaluate the efficiency of the proposed schemes.