ANNIIP 2015 Abstracts
Short Papers
| Paper Nr: | 1 |
| Title: | Exploring Machine Learning Techniques for Identification of Cues for Robot Navigation with a LIDAR Scanner |
| Authors: | Aj Bieszczad |
| Abstract: | In this paper, we report on our explorations of machine learning techniques based on backpropagation neural networks and support vector machines in building a cue identifier for mobile robot navigation using a LIDAR scanner. We use synthetic 2D laser data to identify a technique that is most promising for actual implementation in a robot, and then validate the model using realistic data. While we explore data preprocessing applicable to machine learning, we do not apply any specific extraction of features from the raw data; instead, our feature vectors are the raw data. Each LIDAR scan represents a sequence of values for measurements taken from progressive scans (with angles vary from 0° to 180°); i.e., a curve plotting distances as a functions of angles. Such curves are different for each cue, and so can be the basis for identification. We apply varied grades of noise to the ideal scanner measurement to test the capability of the generated models to accommodate for both laser inaccuracy and robot motion. Our results indicate that good models can be built with both back-propagation neural network applying Broyden–Fletcher–Goldfarb–Shannon (BFGS) optimization, and with Support Vector Machines (SVM) assuming that data shaping took place with a [-0.5, 0.5] normalization followed by a principal component analysis (PCA). Furthermore, we show that SVM can create models much faster and more resilient to noise, so that is what we will be using in our further research and can recommend for similar applications. |
| Paper Nr: | 4 |
| Title: | Grey Relational Analysis based Artificial Neural Networks for Product Design: A Comparative Study |
| Authors: | Yang-Cheng Lin and Chung-Hsing Yeh |
| Abstract: | Artificial neural networks (ANNs) have been applied successfully in a wide range of fields due to its effective learning ability. In this paper, we propose a grey relational analysis (GRA) based ANN model that can be used to build a design decision support database for facilitating the product design process and matching specific consumers’ preferences. The result of an empirical application and a comparative study on fragrance bottle form design shows that the ANN models outperform the grey prediction models, indicating that the ANN technique is promising to help product designers design a new product that best meets consumers’ needs. |
| Paper Nr: | 5 |
| Title: | An Experimentation Line for Underlying Graphemic Properties - Acquiring Knowledge from Text Data with Self Organizing Maps |
| Authors: | Gilles Bernard, Nourredine Aliane and Otman Manad |
| Abstract: | We present an experimentation line that encompasses various stages for research on graphemes distribution and unsupervised classification. We aim to help close the gap between recent research results showing the abilities of unsupervised learning and clustering algorithms to detect underlying properties of phonemes and the present possibilities of Unicode textual representation. Our procedures need to ensure repeatability and guarantee that no information is implicitely present in the preprocessing of data. Our approach is able to categorize potential graphemes correctly, thus showing that not only phonemic properties are indeed present in textual data, but that they can be automatically retrieved from raw-unicode text data and translated into phonemic representations. By the way, we observe that SOM algorithm copes well with very sparse vectors. |
| Paper Nr: | 6 |
| Title: | Evaluation of Processor Health within Hierarchical Condition Monitoring System |
| Authors: | Lenka Pavelková and Ladislav Jirsa |
| Abstract: | This paper proposes an intelligible method for the evaluation of a condition of the central processing unit (CPU). Proposed method monitors CPU utilisation with respect to user given bounds and provides result in the form of binomial opinion that serves subsequently for the condition monitoring of an industrial system. The system in question is described by a hierarchical structure and the examined CPU belongs to the set of its basic building blocks. |