Emotional states recognition, implementing a low computational complexity strategy

2016 ◽  
Vol 24 (2) ◽  
pp. 146-170 ◽  
Author(s):  
Adrian Rodriguez Aguiñaga ◽  
Miguel Angel Lopez Ramirez
Keyword(s):  
Neural Networks ◽  
Computational Complexity ◽  
Recognition Rate ◽  
Relevant Information ◽  
Support Vector ◽  
Emotional States ◽  
Computational Burden ◽  
Low Computational Complexity ◽  
Identification Process ◽  
Vector Machines

This article describes a methodology to recognize emotional states through an electroencephalography signals analysis, developed with the premise of reducing the computational burden that is associated with it, implementing a strategy that reduces the amount of data that must be processed by establishing a relationship between electrodes and Brodmann regions, so as to discard electrodes that do not provide relevant information to the identification process. Also some design suggestions to carry out a pattern recognition process by low computational complexity neural networks and support vector machines are presented, which obtain up to a 90.2% mean recognition rate.

scholarly journals Automatic Artifact Recognition and Correction for Electrodermal Activity in Uncontrolled Environments

2021 ◽  
Author(s):  
Jose Llanes-Jurado ◽  
Lucía Amalia Carrasco-Ribelles ◽  
Mariano Alcañiz ◽  
Javier Marín-Morales
Keyword(s):  
Neural Networks ◽  
Intelligent Systems ◽  
Electrodermal Activity ◽  
Time Windows ◽  
Ground Truth ◽  
Linear Interpolation ◽  
Support Vector ◽  
Emotional States ◽  
Vector Machines ◽  
High Degree

Abstract Scholars are increasingly using electrodermal activity (EDA) to assess cognitive-emotional states in laboratory environments, while recent applications have recorded EDA in uncontrolled settings, such as daily-life and virtual reality (VR) contexts, in which users can freely walk and move their hands. However, these records can be affected by major artifacts stemming from movements that can obscure valuable information. Previous work has analyzed signal correction methods to improve the quality of the signal or proposed artifact recognition models based on time windows. Despite these efforts, the correction of EDA signals in uncontrolled environments is still limited, and no existing research has used a signal manually corrected by an expert as a benchmark. This work investigates different machine learning and deep learning architectures, including support vector machines, recurrent neural networks (RNNs), and convolutional neural networks, for the automatic artifact recognition of EDA signals. The data from 44 subjects during an immersive VR task were collected and cleaned by two experts as ground truth. The best model, which used an RNN fed with the raw signal, recognized 72% of the artifacts and had an accuracy of 87%. An automatic correction was performed on the detected artifacts through a combination of linear interpolation and a high degree polynomial. The evaluation of this correction showed that the automatically and manually corrected signals did not present differences in terms of phasic components, while both showed differences to the raw signal. This work provides a tool to automatically correct artifacts of EDA signals which can be used in uncontrolled conditions, allowing for the development of intelligent systems based on EDA monitoring without human intervention.

Persian Handwritten Number Recognition Using Adapted Framing Feature and Support Vector Machines

2016 ◽  
Vol 15 (01) ◽  
pp. 1650004 ◽  
Author(s):  
Hedieh Sajedi ◽  
Mehran Bahador
Keyword(s):  
Support Vector Machines ◽  
Recognition Rate ◽  
Nearest Neighbors ◽  
Polynomial Kernel ◽  
Support Vector ◽  
K Nearest Neighbors ◽  
New Approach ◽  
Number Recognition ◽  
Vector Machines

In this paper, a new approach for segmentation and recognition of Persian handwritten numbers is presented. This method utilizes the framing feature technique in combination with outer profile feature that we named this the adapted framing feature. In our proposed approach, segmentation of the numbers into digits has been carried out automatically. In the classification stage of the proposed method, Support Vector Machines (SVM) and k-Nearest Neighbors (k-NN) are used. Experimentations are conducted on the IFHCDB database consisting 17,740 numeral images and HODA database consisting 102,352 numeral images. In isolated digit level on IFHCDB, the recognition rate of 99.27%, is achieved by using SVM with polynomial kernel. Furthermore, in isolated digit level on HODA, the recognition rate of 99.07% is achieved by using SVM with polynomial kernel. The experiments illustrate that applying our proposed method resulted higher accuracy compared to previous researches.

Audio-Based Condition Monitoring in Milling of the Workpiece Material With the Hardness Variation Using Support Vector Machines and Convolutional Neural Networks

2018 ◽  
Author(s):  
Achyuth Kothuru ◽  
Sai Prasad Nooka ◽  
Rui Liu
Keyword(s):  
Neural Networks ◽  
Support Vector Machines ◽  
Tool Wear ◽  
Support Vector ◽  
Workpiece Material ◽  
Artificial Intelligent ◽  
Tool Condition ◽  
Hardness Variation ◽  
Vector Machines ◽  
Audible Sound

Machining industry has been evolving towards implementation of automation into the process for higher productivity and efficiency. Although many studies have been conducted in the past to develop intelligent monitoring systems in various application scenarios of machining processes, most of them just focused on cutting tools without considering the influence due to the non-uniform hardness of workpiece material. This study develops a compact, reliable, and cost-effective intelligent Tool Condition Monitoring (TCM) model to detect the cutting tool wear in machining of the workpiece material with hardness variation. The generated audible sound signals during the machining process will be analyzed by state of the art artificial intelligent techniques, Support Vector Machines (SVMs) and Convolutional Neural Networks (CNNs), to predict the tool condition and the hardness variation of the workpiece. A four-level classification model is developed for the system to detect the tool wear condition based on the width of the flank wear land and hardness variation of the workpiece. The study also involves comparative analysis between two employed artificial intelligent techniques to evaluate the performance of models in predicting the tool wear level condition and workpiece hardness variation. The proposed intelligent models have shown a significant prediction accuracy in detecting the tool wear and from the audible sound into the proposed multi-classification wear class in the end-milling process of non-uniform hardened workpiece.

scholarly journals Inspeção Automática de Defeitos em Madeiras de Pinus usando Visão Computacional

2008 ◽  
Vol 15 (2) ◽  
pp. 203-218
Author(s):  
Luiz E. S. Oliveira ◽  
Paulo R. Cavalin ◽  
Alceu S. Britto Jr ◽  
Alessandro L. Koerich
Keyword(s):  
Neural Networks ◽  
Genetic Algorithms ◽  
Feature Selection ◽  
Defect Detection ◽  
Color Image ◽  
Support Vector ◽  
Grayscale Image ◽  
Selection Algorithm ◽  
Feature Selection Algorithm ◽  
Vector Machines

This paper addresses the issue of detecting defects in Pine wood using features extracted from grayscale images. The feature set proposed here is based on the concept of texture and it is computed from the co-occurrence matrices. The features provide measures of properties such as smoothness, coarseness, and regularity. Comparative experiments using a color image based feature set extracted from percentile histograms are carried to demonstrate the efficiency of the proposed feature set. Two different learning paradigms, neural networks and support vector machines, and a feature selection algorithm based on multi-objective genetic algorithms were considered in our experiments. The experimental results show that after feature selection, the grayscale image based feature set achieves very competitive performance for the problem of wood defect detection relative to the color image based features.

scholarly journals Impacts of multicollinearity on CAPT modalities: An heterogeneous machine learning framework for computer-assisted French phoneme pronunciation training

PLoS ONE ◽  
2021 ◽  
Vol 16 (10) ◽  
pp. e0257901
Author(s):  
Yanjing Bi ◽  
Chao Li ◽  
Yannick Benezeth ◽  
Fan Yang
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Support Vector Machines ◽  
Partial Least Square ◽  
Least Square ◽  
Support Vector ◽  
Computer Assisted ◽  
Long Distance ◽  
Relationship Analysis ◽  
Vector Machines

Phoneme pronunciations are usually considered as basic skills for learning a foreign language. Practicing the pronunciations in a computer-assisted way is helpful in a self-directed or long-distance learning environment. Recent researches indicate that machine learning is a promising method to build high-performance computer-assisted pronunciation training modalities. Many data-driven classifying models, such as support vector machines, back-propagation networks, deep neural networks and convolutional neural networks, are increasingly widely used for it. Yet, the acoustic waveforms of phoneme are essentially modulated from the base vibrations of vocal cords, and this fact somehow makes the predictors collinear, distorting the classifying models. A commonly-used solution to address this issue is to suppressing the collinearity of predictors via partial least square regressing algorithm. It allows to obtain high-quality predictor weighting results via predictor relationship analysis. However, as a linear regressor, the classifiers of this type possess very simple topology structures, constraining the universality of the regressors. For this issue, this paper presents an heterogeneous phoneme recognition framework which can further benefit the phoneme pronunciation diagnostic tasks by combining the partial least square with support vector machines. A French phoneme data set containing 4830 samples is established for the evaluation experiments. The experiments of this paper demonstrates that the new method improves the accuracy performance of the phoneme classifiers by 0.21 − 8.47% comparing to state-of-the-arts with different data training data density.

Sign in / Sign up

Export Citation Format

Share Document