RESUMEN

It is becoming increasingly attractive to detect human emotions using electroencephalography (EEG) brain signals. EEG is a reliable and cost-effective technology used to measure brain activities. This paper proposes an original framework for usability testing based on emotion detection using EEG signals, which can significantly affect software production and user satisfaction. This approach can provide an in-depth understanding of user satisfaction accurately and precisely, making it a valuable tool in software development. The proposed framework includes a recurrent neural network algorithm as a classifier, a feature extraction algorithm based on event-related desynchronization and event-related synchronization analysis, and a new method for selecting EEG sources adaptively for emotion recognition. The framework results are promising, achieving 92.13%, 92.67%, and 92.24% for the valence-arousal-dominance dimensions, respectively.

Asunto(s)

RESUMEN

In recent years, human-computer interaction (HCI) systems have become increasingly popular. Some of these systems demand particular approaches for discriminating actual emotions through the use of better multimodal methods. In this work, a deep canonical correlation analysis (DCCA) based multimodal emotion recognition method is presented through the fusion of electroencephalography (EEG) and facial video clips. A two-stage framework is implemented, where the first stage extracts relevant features for emotion recognition using a single modality, while the second stage merges the highly correlated features from the two modalities and performs classification. Convolutional neural network (CNN) based Resnet50 and 1D-CNN (1-Dimensional CNN) have been utilized to extract features from facial video clips and EEG modalities, respectively. A DCCA-based approach was used to fuse highly correlated features, and three basic human emotion categories (happy, neutral, and sad) were classified using the SoftMax classifier. The proposed approach was investigated based on the publicly available datasets called MAHNOB-HCI and DEAP. Experimental results revealed an average accuracy of 93.86% and 91.54% on the MAHNOB-HCI and DEAP datasets, respectively. The competitiveness of the proposed framework and the justification for exclusivity in achieving this accuracy were evaluated by comparison with existing work.

RESUMEN

Acknowledging the importance of the ability to communicate with other people, the researcher community has developed a series of BCI-spellers, with the goal of regaining communication and interaction capabilities with the environment for people with disabilities. In order to bridge the gap in the digital divide between the disabled and the non-disabled people, we believe that the development of efficient signal processing algorithms and strategies will go a long way towards achieving novel assistive technologies using new human-computer interfaces. In this paper, we present various classification strategies that would be adopted by P300 spellers adopting the row/column paradigm. The presented strategies have obtained high accuracy rates compared with existent similar research works.

Asunto(s)

RESUMEN

Over the past decade, emotion detection using rhythmic brain activity has become a critical area of research. The asymmetrical brain activity has garnered the most significant level of research attention due to its implications for the study of emotions, including hemispheric asymmetry or, more generally, asymmetrical brain activity. This study aimed at enhancing the accuracy of emotion detection using Electroencephalography (EEG) brain signals. This happens by identifying electrodes where relevant brain activity changes occur during the emotions and by defining pairs of relevant electrodes having asymmetric brain activities during emotions. Experimental results showed that the proposed method is highly competitive compared with existing studies of multi-class emotion recognition. These results were improved by processing not the whole EEG signals but by focusing on fragments of the signals, called epochs, which represent the instants where the excitation is maximum during emotions. The epochs were extracted using the zero-time windowing method and the numerator group-delay function.

Asunto(s)

RESUMEN

A fingerprint sensor interoperability problem, or a cross-sensor matching problem, occurs when one type of sensor is used for enrolment and a different type for matching. Fingerprints captured for the same person using various sensor technologies have various types of noises and artifacts. This problem motivated us to develop an algorithm that can enhance fingerprints captured using different types of sensors and touch technologies. Inspired by the success of deep learning in various computer vision tasks, we formulate this problem as an image-to-image transformation designed using a deep encoder-decoder model. It is trained using two learning frameworks, i.e., conventional learning and adversarial learning based on a conditional Generative Adversarial Network (cGAN) framework. Since different types of edges form the ridge patterns in fingerprints, we employed edge loss to train the model for effective fingerprint enhancement. The designed method was evaluated on fingerprints from two benchmark cross-sensor fingerprint datasets, i.e., MOLF and FingerPass. To assess the quality of enhanced fingerprints, we employed two standard metrics commonly used: NBIS Fingerprint Image Quality (NFIQ) and Structural Similarity Index Metric (SSIM). In addition, we proposed a metric named Fingerprint Quality Enhancement Index (FQEI) for comprehensive evaluation of fingerprint enhancement algorithms. Effective fingerprint quality enhancement results were achieved regardless of the sensor type used, where this issue was not investigated in the related literature before. The results indicate that the proposed method outperforms the state-of-the-art methods.

Asunto(s)

RESUMEN

There are many applications controlled by the brain signals to bridge the gap in the digital divide between the disabled and the non-disabled people. The deployment of novel assistive technologies using brain-computer interface (BCI) will go a long way toward achieving this lofty goal, especially after the successes demonstrated by these technologies in the daily life of people with severe disabilities. This paper contributes in this direction by proposing an integrated framework to control the operating system functionalities using Electroencephalography signals. Different signal processing algorithms were applied to remove artifacts, extract features, and classify trials. The proposed approach includes different classification algorithms dedicated to detecting the P300 responses efficiently. The predicted commands passed through a socket to the API system, permitting the control of the operating system functionalities. The proposed system outperformed those obtained by the winners of the BCI competition and reached an accuracy average of 94.5% according to the offline approach. The framework was evaluated according to the online process and achieved an excellent accuracy attaining 97% for some users but not less than 90% for others. The suggested framework enhances the information accessibility for people with severe disabilities and helps them perform their daily tasks efficiently. It permits the interaction between the user and personal computers through the brain signals without any muscular efforts.

RESUMEN

Masses are one of the early signs of breast cancer, and the survival rate of women suffering from breast cancer can be improved if masses can be correctly identified as benign or malignant. However, their classification is challenging due to the similarity in texture patterns of both types of mass. The existing methods for this problem have low sensitivity and specificity. Based on the hypothesis that diverse contextual information of a mass region forms a strong indicator for discriminating benign and malignant masses and the idea of the ensemble classifier, we introduce a computer-aided system for this problem. The system uses multiple regions of interest (ROIs) encompassing a mass region for modeling diverse contextual information, a single ResNet-50 model (or its density-specific modification) as a backbone for local decisions, and stacking with SVM as a base model to predict the final decision. A data augmentation technique is introduced for fine-tuning the backbone model. The system was thoroughly evaluated on the benchmark CBIS-DDSM dataset using its provided data split protocol, and it achieved a sensitivity of 98.48% and a specificity of 92.31%. Furthermore, it was found that the system gives higher performance if it is trained and tested using the data from a specific breast density BI-RADS class. The system does not need to fine-tune/train multiple CNN models; it introduces diverse contextual information by multiple ROIs. The comparison shows that the method outperforms the state-of-the-art methods for classifying mass regions into benign and malignant. It will help radiologists reduce their burden and enhance their sensitivity in the prediction of malignant masses.

Asunto(s)

RESUMEN

There is a wide area of application that uses cerebral activity to restore capabilities for people with severe motor disabilities, and actually the number of such systems keeps growing. Most of the current BCI systems are based on a personal computer. However, there is a tremendous interest in the implementation of BCIs on a portable platform, which has a small size, faster to load, much lower price, lower resources, and lower power consumption than those for full PCs. Depending on the complexity of the signal processing algorithms, it may be more suitable to work with slow processors because there is no need to allow excess capacity of more demanding tasks. So, in this review, we provide an overview of the BCIs development and the current available technology before discussing experimental studies of BCIs.

Asunto(s)

RESUMEN

The fingerprint is one of the leading biometric modalities that is used worldwide for authenticating the identity of persons. Over time, a lot of research has been conducted to develop automatic fingerprint verification techniques. However, due to different authentication needs, the use of different sensors and the fingerprint verification systems encounter cross-sensor matching or sensor interoperability challenges, where different sensors are used for the enrollment and query phases. The challenge is to develop an efficient, robust and automatic system for cross-sensor matching. This paper proposes a new cross-matching system (SiameseFinger) using the Siamese network that takes the features extracted using the Gabor-HoG descriptor. The proposed Siamese network is trained using adversarial learning. The SiameseFinger was evaluated on two benchmark public datasets FingerPass and MOLF. The results of the experiments presented in this paper indicate that SiameseFinger achieves a comparable performance with that of the state-of-the-art methods.

RESUMEN

Recognizing emotions using biological brain signals requires accurate and efficient signal processing and feature extraction methods. Existing methods use several techniques to extract useful features from a fixed number of electroencephalography (EEG) channels. The primary objective of this study was to improve the performance of emotion recognition using brain signals by applying a novel and adaptive channel selection method that acknowledges that brain activity has a unique behavior that differs from one person to another and one emotional state to another. Moreover, we propose identifying epochs, which are the instants at which excitation is maximum, during the emotion to improve the system's accuracy. We used the zero-time windowing method to extract instantaneous spectral information using the numerator group-delay function to accurately detect the epochs in each emotional state. Different classification scheme were defined using QDC and RNN and evaluated using the DEAP database. The experimental results showed that the proposed method is highly competitive compared with existing studies of multi-class emotion recognition. The average accuracy rate exceeded 89%. Compared with existing algorithms dealing with 9 emotions, the proposed method enhanced the accuracy rate by 8%. Moreover, experiment shows that the proposed system outperforms similar approaches discriminating between 3 and 4 emotions only. We also found that the proposed method works well, even when applying conventional classification algorithms.

Asunto(s)

RESUMEN

The advancement of assistive technologies toward the restoration of the mobility of paralyzed and/or amputated limbs will go a long way. Herein, we propose a system that adopts the brain-computer interface technology to control prosthetic fingers with the use of brain signals. To predict the movements of each finger, complex electroencephalogram (EEG) signal processing algorithms should be applied to remove the outliers, extract features, and be able to handle separately the five human fingers. The proposed method deals with a multi-class classification problem. Our machine learning strategy to solve this problem is built on an ensemble of one-class classifiers, each of which is dedicated to the prediction of the intention to move a specific finger. Regions of the brain that are sensitive to the movements of the fingers are identified and located. The average accuracy of the proposed EEG signal processing chain reached 81% for five subjects. Unlike the majority of existing prototypes that allow only one single finger to be controlled and only one movement to be performed at a time, the system proposed will enable multiple fingers to perform movements simultaneously. Although the proposed system classifies five tasks, the obtained accuracy is too high compared with a binary classification system. The proposed system contributes to the advancement of a novel prosthetic solution that allows people with severe disabilities to perform daily tasks in an easy manner.

RESUMEN

BACKGROUND: Brain-computer interface (BCI) is a communication pathway applied for pathological analysis or functional substitution. BCI based on functional substitution enables the recognition of a subject's intention to control devices such as prosthesis and wheelchairs. Discrimination of electroencephalography (EEG) trials related to left- and right-hand movements requires complex EEG signal processing to achieve good system performance. NEW METHOD: In this study, a novel dynamic and self-adaptive algorithm (DSAA) based on the least-squares method is proposed to select the most appropriate feature extraction and classification algorithms couple for each subject. Specifically, the best couple identified during the training of the system is updated during online testing in order to check the stability of the selected couple and maintain high system accuracy. RESULTS: Extensive and systematic experiments were conducted on public datasets of 17 subjects in the BCI-competition and the results show an improved performance for DSAA over other selected state-of-the-art methods. COMPARISON WITH EXISTING METHODS: The results show that the proposed system enhanced the classification accuracy for the three chosen public datasets by 8% compared to other approaches. Moreover, the proposed system was successful in selecting the best path despite the unavailability of reference labels. CONCLUSIONS: Performing dynamic and self-adaptive selection for the best feature extraction and classification algorithm couple increases the recognition rate of trials despite the unavailability of reference trial labels. This approach allows the development of a complete BCI system with excellent accuracy.

Asunto(s)

RESUMEN

The fingerprint is a commonly used biometric modality that is widely employed for authentication by law enforcement agencies and commercial applications. The designs of existing fingerprint matching methods are based on the hypothesis that the same sensor is used to capture fingerprints during enrollment and verification. Advances in fingerprint sensor technology have raised the question about the usability of current methods when different sensors are employed for enrollment and verification; this is a fingerprint sensor interoperability problem. To provide insight into this problem and assess the status of state-of-the-art matching methods to tackle this problem, we first analyze the characteristics of fingerprints captured with different sensors, which makes cross-sensor matching a challenging problem. We demonstrate the importance of fingerprint enhancement methods for cross-sensor matching. Finally, we conduct a comparative study of state-of-the-art fingerprint recognition methods and provide insight into their abilities to address this problem. We performed experiments using a public database (FingerPass) that contains nine datasets captured with different sensors. We analyzed the effects of different sensors and found that cross-sensor matching performance deteriorates when different sensors are used for enrollment and verification. In view of our analysis, we propose future research directions for this problem.

RESUMEN

BACKGROUND: Screening of atrial fibrillation (AF) for high-risk patients including all patients aged 65 years and older is important for prevention of risk of stroke. Different technologies such as modified blood pressure monitor, single lead ECG-based finger-probe, and smart phone using plethysmogram signal have been emerging for this purpose. All these technologies use irregularity of heartbeat duration as a feature for AF detection. We have investigated a normalization method of heartbeat duration for improved AF detection. METHOD: AF is an arrhythmia in which heartbeat duration generally becomes irregularly irregular. From a window of heartbeat duration, we estimate the possible rhythm of the majority of heartbeats and normalize duration of all heartbeats in the window based on the rhythm so that we can measure the irregularity of heartbeats for both AF and non-AF rhythms in the same scale. Irregularity is measured by the entropy of distribution of the normalized duration. Then we classify a window of heartbeats as AF or non-AF by thresholding the measured irregularity. The effect of this normalization is evaluated by comparing AF detection performances using duration with the normalization, without normalization, and with other existing normalizations. RESULTS: Sensitivity and specificity of AF detection using normalized heartbeat duration were tested on two landmark databases available online and compared with results of other methods (with/without normalization) by receiver operating characteristic (ROC) curves. ROC analysis showed that the normalization was able to improve the performance of AF detection and it was consistent for a wide range of sensitivity and specificity for use of different thresholds. Detection accuracy was also computed for equal rates of sensitivity and specificity for different methods. Using normalized heartbeat duration, we obtained 96.38% accuracy which is more than 4% improvement compared to AF detection without normalization. CONCLUSIONS: The proposed normalization method was found useful for improving performance and robustness of AF detection. Incorporation of this method in a screening device could be crucial to reduce the risk of AF-related stroke. In general, the incorporation of the rhythm-based normalization in an AF detection method seems important for developing a robust AF screening device.

Asunto(s)

RESUMEN

We studied the impact of 2D and 3D educational contents on learning and memory recall using electroencephalography (EEG) brain signals. For this purpose, we adopted a classification approach that predicts true and false memories in case of both short term memory (STM) and long term memory (LTM) and helps to decide whether there is a difference between the impact of 2D and 3D educational contents. In this approach, EEG brain signals are converted into topomaps and then discriminative features are extracted from them and finally support vector machine (SVM) which is employed to predict brain states. For data collection, half of sixty-eight healthy individuals watched the learning material in 2D format whereas the rest watched the same material in 3D format. After learning task, memory recall tasks were performed after 30 minutes (STM) and two months (LTM), and EEG signals were recorded. In case of STM, 97.5% prediction accuracy was achieved for 3D and 96.6% for 2D and, in case of LTM, it was 100% for both 2D and 3D. The statistical analysis of the results suggested that for learning and memory recall both 2D and 3D materials do not have much difference in case of STM and LTM.

Asunto(s)

RESUMEN

Assessing a person's intelligence level is required in many situations, such as career counseling and clinical applications. EEG evoked potentials in oddball task and fluid intelligence score are correlated because both reflect the cognitive processing and attention. A system for prediction of an individual's fluid intelligence level using single trial Electroencephalography (EEG) signals has been proposed. For this purpose, we employed 2D and 3D contents and 34 subjects each for 2D and 3D, which were divided into low-ability (LA) and high-ability (HA) groups using Raven's Advanced Progressive Matrices (RAPM) test. Using visual oddball cognitive task, neural activity of each group was measured and analyzed over three midline electrodes (Fz, Cz, and Pz). To predict whether an individual belongs to LA or HA group, features were extracted using wavelet decomposition of EEG signals recorded in visual oddball task and support vector machine (SVM) was used as a classifier. Two different types of Haar wavelet transform based features have been extracted from the band (0.3 to 30 Hz) of EEG signals. Statistical wavelet features and wavelet coefficient features from the frequency bands 0.0-1.875 Hz (delta low) and 1.875-3.75 Hz (delta high), resulted in the 100 and 98% prediction accuracies, respectively, both for 2D and 3D contents. The analysis of these frequency bands showed clear difference between LA and HA groups. Further, discriminative values of the features have been validated using statistical significance tests and inter-class and intra-class variation analysis. Also, statistical test showed that there was no effect of 2D and 3D content on the assessment of fluid intelligence level. Comparisons with state-of-the-art techniques showed the superiority of the proposed system.