Abstracts

December 13, 2016

Artificial Neural Networks in Industry  ANNI’17

Dr. Ahmed Hafaifa

University of Djelfa (Algeria)

Dr. Kouzou Abdellah

University of Djelfa (Algeria)

Dr. Guemana Mouloud

University of Medea (Algeria)

Abstract

Technological advances in computer science on data processing, with the major development trends in this area give effective solutions in modeling and control of industrial complex systems. That allowed to the Artificial Neural Networks a capacity sufficient to solve number of existing problems in several industrial applications. Using Artificial Neural Networks, we propose in this special session in the 14th International Work-Conference on Artificial Neural Networks (IWANN 2017), to show the interest of Artificial Neural Networks with different implementation strategies; in modeling, control and diagnostics of nonlinear industrial processes, with the benefits of this approach. Whereas, the main aim of this proposal is to bring together scientists and industrial actors, to generate debate and to exchange ideas and experiences on the progress in Artificial Neural Networks applicative research development on industry tools. The topics of interest include, but are not limited to, the following;

  • Industrial diagnosis based on Artificial Neural Networks
  • Artificial Neural Networks Identification
  • Modeling using Artificial Neural Networks
  • Artificial Neural Networks classification
  • Nonlinear Autoregressive Exogenous Neural Network
  • Adaptive Network Based Fuzzy Inference System (ANFIS)

Computational intelligence tools and techniques for biomedical applications

Dr. Miguel A. Atencia

University of Málaga(Spain)

Dr. Leonardo Franco

University of Málaga (Spain)

Dr. Ruxandra Stoean

University of Craiova (Romania)

Abstract

Biomedical computation is a novel field of research that encompasses such a wide range of techniques, applications and scientific foundations that it challenges definition. In this session we aim at reviewing significant recent developments in all areas, including, but not limited to:

  • Computational intelligence tools for decision support in diagnosis and grading of diseases
  • Bioinformatics
  • Data mining for biomedical records
  • Artificial visual systems and image processing techniques for computer-aided diagnosis
  • Integrated software and hardware frameworks in healthcare applications
  • Future directions and challenges in biomedical computation

Particular emphasis will be placed on contributions that shed light on the complete life cycle of biomedical applications, from fundamental science to software construction, thus striving for a real change in the quality of life for patients.


Machine learning for renewable energy

Dr. Sancho Salcedo Sanz

Universidad de Alcalá (Spain)

Dr. Pedro Antonio Gutiérrez

University of Cordoba (Spain)

Abstract

In the last decade, global energy demand has increased to non in population, fierce urbanization in developed countries and aggressive industrial development all around the world. Conventional fossil-based energy sources have limited reservoirs and a deep environmental impact (contributing to global warming), and therefore they cannot satisfy this global demand for energy in a sustainable way. These issues related to fossil-based sources have led to a very important development of Renewable Energy (RE) sources in the last years, mainly in renewable technologies such as wind, solar, hydro or marine energies among others. In this regard, Machine Learning (ML) techniques have been demonstrated to be excellent tools to cope with difficult problems arisen from new RE sources. There are many RE ap by ML techniques, such as prediction problems (e.g. solar radiation or significant wave height estimation), optimization algorithms (wind farm or RE devices’ design), new control techniques or fault diagnosis in RE systems, all of them with the common objective of improving significantly RE systems.

This special session aims to cover a wide range of works and recent advances on the application of ML techniques to RE problems. We hope that this session can provide a common exchange their ideas and report their latest finding in the area.

In particular we encourage submissions addressing the following issues:

  • Wind speed prediction problems.
  • Solar radiation prediction problems.
  • Wave height estimation problems.
  • RE Power prediction.
  • Fault diagnosis in RE-related systems.
  • Power quality disturbance detection and analysis.
  • Appliance Load Monitoring applications.
  • Any application of ML techniques to RE problems.

Assistive Rehabilitation Technology

Dr. Oresti Baños

University of Twente (Netherlands)

Dr. Jose A. Moral-Muñoz

University of Cadiz (Spain)

Abstract

The use of devices and software in healthcare disciplines has become more frequent during the last few years. The application in physical therapy or rehabilitation offers many possibilities, such as easily assess several pathologies, keep an adequate follow up or allow users to access remotely and globally to healthcare, improving the service offered. This special session aims at showcasing the latest achievements in the field of telerehabilitation.

We welcome novel, innovative, and exciting contributions in areas including but not limited to:

  • Assistive technology for learning disabilities
  • Virtual reality for rehabilitation
  • Personalized telerehabilitation
  • Bioelectric sensors
  • Wearable computers and devices for telerehabilitation
  • Smart physical training systems

Computational Intelligence methods for Time Series

Dr. Héctor Pomares

University of Granada (Spain)

Dr. Germán Gutierrez

E.P.S. University Carlos III of Madrid (Spain)

Abstract

Within the field of science and engineering, it is very common to have data arranged in the form of time series data which must be subsequently analysed, modelled and classified with the eventual goal of predicting future values. The literature shows that all these tasks related to time series can be undertaken using computational intelligence methods. In fact, new and further computational intelligence approaches, their efficiency and their comparison to statistical methods and other fact-checked computational intelligence methods, is a significant topic in academic and professional projects and works.

Therefore, this special session aims at showing to our research community high quality and state of the art computational intelligence (and statistical) related works, applied to time series data and their tasks: analysis, forecasting, classification and clustering. Furthermore, the experts can, from the starting point that the works shown provide, discuss different solutions and research issues for these topics.

Topics (but not limited to):

  • Computational Intelligence (CI) techniques applied to
    • time series analysis,
    • time series modelling,
    • time series forecasting,
    • time series classification,
    • time series clustering,
  • Statistical and CI techniques for time series, comparative evaluation and/or novel propositions.

Machine Learning applied to Vision and Robotics (MLVR)

Dr. Jose Garcia-Rodriguez

University of Alicante (Spain)

Dr. Enrique Dominguez

University of Málaga (Spain)

M.Sc. Mauricio Zamora

University of Costa Rica (Costa Rica)

Dr. Eldon Caldwel

University of Costa Rica (Costa Rica)

Abstract

Over the last decades there has been an increasing interest in using machine learning methods combined with computer vision techniques to create autonomous systems that solve vision problems in different fields. This special session is designed to serve researchers and developers to publish original, innovative and state-of-the art algorithms and architectures for real time applications in the areas of computer vision, image processing, biometrics, virtual and augmented reality, neural networks, intelligent interfaces and biomimetic object-vision recognition.

This special session provides a platform for academics, developers, and industryrelated researchers belonging to the vast communities of *Neural Networks*, *Computational Intelligence*, *Machine Learning*, *Biometrics*, *Vision systems*, and *Robotics *, to discuss, share experience and explore traditional and new areas of the computer vision and machine learning combined to solve a range of problems. The objective of the workshop is to integrate the growing international community of researchers working on the application of Machine Learning applied to Vision and Robotics to a fruitful discussion on the evolution and the benefits of this technology to the society.

The Special Session topics can be identified by, but are not limited to, the following subjects:

  • Artificial Vision
  • Video tracking
  • Video and Image Processing
  • 3D Scene reconstruction
  • 3D Tracking in Virtual Reality Environments
  • 3D Volume visualization
  • Computational Intelligence
  • Machine Learning
  • Intelligent Interfaces (User-friendly Man Machine Interface)
  • Self-adaptation and self-organisational systems
  • Deep Learning Architectures for vision
  • Multi-camera and RGB-D camera systems
  • Robust computer vision algorithms (operation under variable conditions,
  • object tracking, behaviour analysis and learning, scene segmentation)
  • Multi-modal Human Pose Recovery and Behavior Analysis
  • Gesture and posture analysis and recognition
  • Biometric Identification and Recognition
  • Extraction of Biometric Features (fingerprint, iris, face, voice, palm, gait)
  • Surveillance systems
  • Robotics vision
  • Collaborative Robotics
  • Human Robot Interaction
  • Hardware implementation and algorithms acceleration (GPUs, FPGA,s,…)

https://www.dtic.ua.es/~jgarcia/IWANN2017/


 

Human activity recognition for health and well-being applications

Dr. Daniel Rodríguez-Martín

Politechnical University of Catalunya (Spain)

Dr. Albert Samà

Politechnical University of Catalunya (Spain)

Abstract

Human activity recognition (HAR) has become a field of great interest in the latter years. Especially in the field of health, HAR is used in the study of falls in the elderly people, evaluation of motor disorders such as Parkinson’s disease and to quantify and analyse movement in patients with Alzheimer’s Disease. In rehabilitation, HAR might assess on the one hand the disease evolution of people with stroke or amyotrophic lateral sclerosis. On the other hand, HAR can be applied in well-being applications such as in the sports field in order to keep an optimal injury recovery or to correct the way an athlete is performing a movement with the aim of preventing an injury.

In this special session, we propose a meeting point where researchers can discuss signal processing methods, machine learning algorithms, bio-mechanical models, statistical approaches and novel sensors in order to perform HAR applications, such as the recognition of symptoms, interpret patterns with relation to disease evolution or stages, as well as to recognize human activity with the aim of contributing in the health field.

The main topics for this special session are the following:

  • Machine learning techniques for human activity recognition
  • ICT for symptomatology diagnosis
  • ICT for rehabilitation purposes
  • Novel sensors and devices for HAR in health
  • Falls, frailty and energy expenditure monitoring in elderly people based on ICT

Software Testing and Intelligent Systems

Dr. Manuel Núñez

Universidad Complutense of Madrid (Spain)

M.Sc. Pablo Cerro Cañizares

Universidad Complutense of Madrid (Spain)

Abstract

Current software systems are increasingly complex and, therefore, it is more difficult and costly to ensure that they do what they are supposed to do. Software testing plays a key role to increase the confidence on the correctness of systems. Despite the huge amount of resources devoted to testing (up to 60% of the budget), testing is still mainly a manual and prone to errors process. Therefore, there is a need to improve testing so that costs can be cut, by automating most of the tasks, and the amount of detected errors can be increased, by using better techniques.

Intelligent systems are ubiquitous in our daily routine: smartphones, navigation systems, smartwatches, etc. In addition to be the basis of (more or less) sophisticated gadgets, these systems are fundamental in areas such as healthcare diagnostics and medical devices, traffic estimation, weather forecast, and many others. They are a clear case of complex systems. As a consequence, these systems are difficult to design, implement, and test. In the case of testing, classical techniques cannot be used because intelligent systems have some peculiarities. On the one hand, they are usually governed by non-deterministic algorithms using advance AI techniques where classical testing will struggle. On the other hand, they have to analyze huge amounts of data in real-time, so that it is extremely important that the solutions scale. Therefore, it is important that testing methodologies adapt to deal with these challenging systems, so that the number of errors can be reduced, avoiding recalls derived from wrong implementations.

During the last years we are contemplating the emergence of new testing techniques based on the application of AI techniques such as evolutionary computation, artificial life, neural computation and swarm intelligence. Therefore, there is a feedback process between the fields: the reliability of intelligent systems is improved thanks to good software testing methodologies and software testing is improved thanks to knowledge obtained from the techniques used to develop intelligent systems. The main aim of this special session is to contribute to the progress in the improvement and appropriate use of software testing and intelligent systems. We are interested in the adaption of existing testing approaches, as well as new ones, to test intelligent systems. In addition, we look forward to novel testing techniques based on computational intelligence paradigms. We are sure that the collaboration of researchers from different areas will result in benefits that can be applied in some of the research lines that are under the umbrella of the IWANN conference.

The topics of interest for this special sessions include, but not are limited to, the following:

  1. Heuristic techniques in software testing.
  2. Formal approaches in intelligent systems.
  3. Risk analysis of intelligent systems.
  4. Swarm intelligence in software testing.
  5. Monitoring of intelligent systems.
  6. Case studies and applications.

http://antares.sip.ucm.es/stis2017/index.html


Real World applications of BCI systems

Dr. Ricardo Ron Angevín

University of Malaga (Spain)

Dr. Ivan Volosyak

Rhine-Waal University of Applied Sciences of Kleve (Germany)

Abstract

A Brain-computer Interfaces (BCI) is based on the analysis of brain activity to provide a non – muscular channel for sending messages and commands to the external world. A BCI emerged few decades ago as a new communication procedure allowing subjects with severe neuromuscular disorders, who may be completely paralyzed or locked-in, to communicate and to interact with the outer world. However, recently BCI applications have been also used in totally different areas (e. g. entertainment). In the future, a qualitative improvement in performance is expected, in terms of information transfer rate and reliability with potential uses in emerging areas of interest.

The main goal of this special session is to show the last research advances in neurotechnologies, BCIs and applications, as well as innovative signal processing algorithms, training techniques or paradigms that make them possible.

The organizers have successfully organized four special sessions about BCIs technologies in last IWANN conferences: IWANN09 (Salamanca), IWANN11 (Málaga), IWANN13 (Tenerife) and IWANN15 (Palma de Mallorca).


Machine learning in imbalanced domains

Dr. Jaime S. Cardoso

University of Porto (Portugal)

Dr. María Pérez Ortiz

Universidad Loyola Andalucía (Spain)

Abstract

Machine learning techniques are usually based on the assumption that the target classes of the problem similar prior probabilities. However, this is often not the case in many real medical diagnosis, information retrieval, fraud detection, fault monitoring, etc. The classification paradigm when one or several classes have a much lower prior probability is known as imbalanced classification and it poses a real challenge for machine learning researchers. Because of that, imbalanced classification is currently receiving a lot of attention from the pattern recognition and  machine learning communities. Often, the minority class happens to be more important than the majority one, but it may also be much more difficult to model and identify complex underlying behaviour patterns due to the low number of available minority samples. Since most traditional learning systems have been designed to work on balanced data, they will usually be focused on improving overall performance and be biased towards the majority class, consequently harming the minority one. Although, from a formal perspective, an imbalanced dataset is any set of labelled data exhibiting an unequal distribution between classes, it has been shown that this is not the only factor involved in hindering the learning in this context. The nature of the class imbalance problem can be also attributed to other factors, such as the complexity of the data (existence of noisy and non-representative samples or class overlapping) or the size of the training set (high dimensional data or small sample size).

This special session aims to cover a wide range of works and recent advances on the application of specific techniques to deal with data imbalance. We hope that this session can provide a common forum for researchers and practitioners to exchange their ideas and report their latest finding in the area

In particular, we encourage submissions addressing the following issues:

  • Learning in the context of imbalanced datasets
  • Sampling approaches (synthetic over
  • Characterization of imbalanced datasets
  • New classification models for imbalanced data
  • New metrics for addressing and measuring data imbalance
  • Applications with presence of data imbalance

 

Surveillance and Rescue Systems and Algorithms for Unmanned Aerial Vehicles

Dr. Wilbert G. Aguilar

Universidad de las Fuerzas Armadas ESPE (Ecuador)

Abstract

This is a special session related to contributions in the emerging branch of Unmanned Aerial Vehicles, which have attracted a great interest for their navigation capabilities. Several contributions on UAV are related to bio-inspired systems, computational intelligence methods, artificial neural networks, and others. These contributions are focused on flight controllers, navigation algorithms, and vision systems with application on Surveillance and Rescue. The vehicles must be able to flight through narrow landscapes but present problems of stability and limited computational power. Hence, new algorithms and systems for control, navigation and vision are necessary and although our primary interest are perception systems for micro aerial vehicles, the problems of control and machine learning have a close relation with these systems. Each contribution, application or innovation for any of these fields is welcome in this special session. Topics of interest include, but are not limited to:

  • Video stabilization for micro aerial vehicles;
  • Vision-based state estimation;
  • Visual odometry;
  • Visual pose estimation;
  • Target Relative Navigation;
  • Bio-Inspired Optic Flow Navigation;
  • Vision-based perception;
  • Visual simultaneous mapping and localization;
  • Vision-based target detection and tracking;
  • Vision-based mapping;
  • Mission-oriented perception;
  • Mapless-based obstacle detection;
  • Visual-inertial systems;
  • Embedded vision systems;
  • LIDAR-based perception;
  • LIDAR-based Simultaneous Localization And Mapping;
  • LIDAR-based Simultaneous Mapping And Planning;
  • LIDAR-based Safe Landing Area Detection;
  • State estimation using range sensors;
  • State estimation using IMU/GPS systems;
  • Navigation, path planning and trajectory optimization;
  • Learning-based flight control systems;
  • Linear flight control systems;
  • Model-based nonlinear flight control system;
  • RGB-D sensors;
  • Real-time and hardware implementations of image processing methods;
  • Sensor design and integration.

 


End-user development for social robotics

M.Sc.Igor Zubrycki

Lodz University of Technology (Poland)

M.Sc.Hoang-Long Cao

Vrije Universiteit Brussel (Belgium)

Dr.Emilia I. Barakova

Eindhoven University of Technology (Netherland)

Abstract

This special session focuses on end-user development for social robotics. So far, social robots are developed for a wide range of applications. Consequently, researchers are interested in providing the end-users with intuitive, natural and enjoyable interaction experiences with the social robots. Also, as artificial intelligence becomes more and more capable, end-user development can enable users to profit from these intelligence gains.

Different end-user groups are now more involved throughout different stages of the life-cycle of robotic systems development, through creating interaction scenarios and robot behaviors, designing and personalizing the robots, promoting robot’s learning. The end-user development allows social robotic systems to be more acceptable and adaptable to different scenarios, but it also presents major challenges including improving the ease of use, modularity and reusability as well as evaluating results of introducing end-user development tools.

The special session welcomes papers describing tools and methods (interfaces, frameworks, algorithms, activities) that deal with the challenges of the end-user development with the goal of improving the experience of interacting with social robots.

We encourage authors to submit original work in the following topics (but are not limited to):

●      Methodologies to involve end-user in the design process of social robotic system

●      End-user programming environments to generate social interaction scenarios and behaviors

●      Social robots learning by demonstration

●      Evaluation methods for end-user developments for social robotics

●      New end-user development frameworks, interfaces, and tools.

https://eudiwann2017.wordpress.com/

 


Artificial Intelligence and Games

Dr. Antonio J. Fernández-Leiva

University of Málaga (Spain)

Dr. Antonio M. Mora García

University of Granada (Spain)

Dr. Pablo García Sánchez

University of Cádiz (Spain)

 

Abstract

Artificial intelligence (AI) comprises a wide set of techniques with an enormous range of practical applications. Problems arising in this area are typically hard and complex to solve to solve, and the associated search spaces are huge. One of the areas that has recently emerged as an exciting field to do research and that provides a high number of interesting problems is the game domain.

Games represent fun but also are interesting to study, and provide competitive and dynamic environments that model many real-world problems. On the other hand, AI has been demonstrated to be a powerful tool to be applied in the game domain, including board games, videogames and mathematical games.

In addition, AI can make a game more attractive from many points of views, and moreover, games can be used to prove the effectiveness of AI techniques.

This session is aimed to bring together leading researchers and practitioners from academia and industry to discuss recent advances and explore future directions in the synergy between AI and games domains, including the application of AI methods to game domain, or the use of games as platform to value the quality of AI techniques for instance.

The topics of interest include, but are not limited to:

  • Bioinspired techniques applied to games (Neural-based systems, Evolutionary algorithms, Ant colony optimization, among others)
  • Learning in games
  • Coevolution in games
  • Fuzzy-based approaches for games
  • Artificial intelligent modelling or improvement in games
  • Theoretical or empirical analysis of CI techniques for games
  • Game theory
  • Content generation
  • Affective Computing in games
  • Player satisfaction and experience in games
  • Game-based benchmarking
  • Serious games
  • Games competitions
  • Computational and artificial intelligence in:
    • Videogames
    • Board and card games
    • Economic or mathematical games
    • Serious games
    • Augmented and mixed-reality games
    • Games for mobile platforms