A study of neural-network-based classifiers for material classification

Abstract

In this paper, the performance of the commonly used neural-network-based classifiers is investigated on solving a classification problem which aims to identify the object nature based on surface features of the object.When the surface data is obtained, a proposed feature extraction method is used to extract the surface feature of the object. The extracted features are then used as the inputs for the classifier. This research studies eighteen household objects which are requisite to our daily life. Six commonly used neural-network-based classifiers, namely one-against-all, weighted one-against-all, binary coded, parallel-structured, weighted parallel structured and tree-structured, are investigated. The performance for the six neural-network-based classifiers is evaluated based on recognition accuracy for individual object. Also, two traditional classifiers, namely k-nearest neighbor classifier and naive Bayes classifier, are employed for the comparison purposes. To evaluate robustness property of the classifiers, the original clean data is contaminated with Gaussian white noise. Experimental results show that the parallel-structured, tree-structured and the naive Bayes classifiers outperform the others under the noise-free data. The tree-structured classifier demonstrates the best robustness property under the noisy data.

Compensating Uncertainties in Force Sensing for Robotic-Assisted Palpation

“…By considering the mapping from the input to the output, it is natural to adopt the supervised learning method [38]. It is worth mentioning that the artificial neural-network-based approaches are reported in [37,39], in which the ANN-based methods are used to successfully classify the materials by the force sensor. In this paper, we propose the neural-network-based approach to model the force sensor in a supervised learning manner.…”

Genre Classification for Brazilian Music using Independent and Discriminant Features

“…SLFN are widely applied for classification problems (see for example [26], [27], [4]) and in this work, two different neural network architectures were used for the SLFN classifiers: (i) one comprises in the output layer one neuron associated to each musical genre (in this case, 12 neurons); and (ii) other uses one SLFN classifier specialized for each class of interest, in an one-against-all (OAA) approach. For both cases, the number of neurons in the hidden layer is chosen using a network growing procedure (starting from a small number of hidden neurons and adding hidden units until the desired discrimination performance is achieved).…”

Classification of epilepsy seizure phase using interval type-2 fuzzy support vector machines

“…After feature extraction has been implemented to the raw data, the extracted features are then used and applied to the pre-determined classification technique. There are a wide range of classification techniques for EEG classification in the literature, examples of these include the artificial neural network [42], [43] and also the neuro-fuzzy systems [44]- [46]. There are 3 sets of EEG signals which are extracted from the 3 seizure phases (seizure-free, preseizure and seizure) to obtain 112 2-second 19-channel EEG epochs from 10 patients for each dataset.…”