EEG signal classification for epilepsy diagnosis via optimum path forest – A systematic assessment

Machine learning techniques have been extensively researched in the last years, mainly due to their effectiveness when dealing with recognition or classification applications. Typically, one can comprehend using a Machine Learning system to autonomously delegate routines, save human efforts, and produce great insights regarding decision-making tasks. This paper introduces and validates a stacking-based ensemble approach using Optimum-Path Forest classifiers in intrusion detection tasks. Instead of only using the famous NSL-KDD dataset, we propose a new dataset called uneSPY, which we believe will fill the gap concerning new intrusion detection datasets. Both datasets were evaluated under several classifiers, including Logistic Regression, Decision Trees, Support Vector Machines, Optimum-Path Forests, and compared against Optimum-Path Forest stacking-based ensembles. Experimental results showed an Optimum-Path Forest stacking-based ensemble classification suitability, particularly when considering its ability to generalize large volumes of data while sustaining its performance.

Machine learning (ML) and image processing techniques have been applied together to various scenarios for the development of Intelligent Vehicles. Among these scenarios, pedestrian detection has received growing interest in recent years, since high concern for safety applications in traffic has arisen. Several ML methods were successfully applied to solve this problem. However, because pedestrian detection is in general computationally intensive, a good trade off between accuracy and processing time is desirable, particularly if the methods are directed to real-time applications. Optimum Path Forest (OPF) classifier is a recently developed non-parametric classifier method. This work contribution is the performance assessment of a novel OPF application to pedestrian detection. Results have shown that it is fast and competitive against established methods and a viable alternative to be considered for machine learning and pedestrian detection applications.

In this paper, the Optimum-Path Forest (OPF) classifier is applied in the classification of defects in cowhide, a problem of great evaluation complexity. The OPF classifier reduces a pattern classification problem to the problem of partitioning the vertices of a graph induced by its data set. The results revealed a competent performance compared to traditional classifiers, such as Support Vector Machines (SVM), Artificial Neural Networks-Perceptron Multilayer (MLP), Decision Trees (J48) and k-Nearest Neighbor (kNN).

Some pattern recognition techniques may present a high computational cost for learning samples' behaviour. The Optimum-Path Forest (OPF) classifier has been recently developed in order to overcome such drawbacks. Although it can achieve faster training steps when compared to some state-of-art techniques, OPF can be slower for testing in some situations. Therefore, we propose in this paper an implementation in graphics cards of the OPF classification, which showed to be more efficient than traditional OPF with similar accuracies.

Appropriate metrics are paramount for machine learning and pattern recognition. In Content-based Image Retrieval-oriented applications, low-level features and pairwise-distance metrics are usually not capable of representing similarity among the objects as observed by humans. Therefore, metric learning from available data has become crucial in such applications, but just a few related approaches take into account the contextual information inherent from the samples for a better accuracy performance. In this paper, we propose a novel approach which combines an unsupervised manifold learning algorithm with the Optimum-Path Forest (OPF) classifier to obtain more accurate recognition rates, as well as we show it can outperform standard OPF-based classifiers that are trained over the original manifold. Experiments conducted in some public datasets evidenced the validity of metric learning in the context of OPF classifiers.

Known as one of the most significant neurodegenerative diseases of the central nervous system, Parkinson's disease (PD) has a combination of several symptoms, such as tremor, postural instability, loss of movements, depression, anxiety, and dementia, among others. For the medicine, to point an exam that can diagnose a patient with such illness is challenging due to the symptoms that are easily related to other diseases. Therefore, developing computational methods capable of identifying PD in its early stages has been of paramount importance in the scientific community. Thence, this paper proposes to use a deep neural network called ResNet-50 to learn the patterns and extract features from images draw by patients. Afterwards, the Optimum-Path Forest (OPF) classifier is employed to identify Parkinson's disease automatically, being the results compared against two well-known classifiers, i.e., Support Vector Machines and the Bayes, as well as the ones provided by ResNet-50 itself. The experiments showed promising results concerning OPF, reachinz over 96% of identification rate.

Although one can find several pattern recognition techniques out there, there is still room for improvements and new approaches. In this book chapter, we revisited the Optimum-Path Forest (OPF) classifier, which has been evaluated over the last years in a number of applications that consider supervised, semi-supervised and unsupervised learning problems. We also presented a brief compilation of a number of previous works that employed OPF in different research fields, that range from remote sensing image classification to medical data analysis.

The research on multiple classifiers systems includes the creation of an ensemble of classifiers and the proper combination of the decisions. In order to combine the decisions given by classifiers, methods related to fixed rules and decision templates are often used. Therefore, the influence and relationship between classifier decisions are often not considered in the combination schemes. In this paper we propose a framework to combine classifiers using a decision graph under a random field model and a game strategy approach to obtain the final decision. The results of combining Optimum-Path Forest (OPF) classifiers using the proposed model are reported, obtaining good performance in experiments using simulated and real data sets. The results encourage the combination of OPF ensembles and the framework to design multiple classifier systems.

Although hyperspectral images acquired by on-board satellites provide information from a wide range of wavelengths in the spectrum, the obtained information is usually highly correlated. This paper proposes a novel framework to reduce the computation cost for large amounts of data based on the efficiency of the optimum-path forest (OPF) classifier and the power of metaheuristic algorithms to solve combinatorial optimizations. Simulations on two public data sets have shown that the proposed framework can indeed improve the effectiveness of the OPF and considerably reduce data storage costs.

When the photovoltaic (PV) system fails, the power generation efficiency is greatly reduced or even leads to incidents, that is why the fault diagnosis of the PV system is very necessary. This paper proposed an optimum-path forest (OPF) photovoltaic arrays fault diagnosis method. According to the characteristics of the photovoltaic panel, seven factors were selected as the characteristic parameters for studying the fault diagnosis of PV system. Then, combined with the actual measurement data and the simulated measurement data, the complete graphs and the minimum spanning trees were obtained in turn, and finally the OPF classifier was obtained which was used for fault diagnosis and classification. At the same time, this paper also compared the OPF algorithm with other algorithms such as Linear SVM, Fine KNN, Linear discriminant and Boosted Trees that showed the OPF algorithm has very high speed and accuracy and is more suitable for fault diagnosis of PV system in practical application. In addition, this paper also optimized the traditional OPF method which improves the speed of classification. Finally, the actual fault detection of PV system was built and achieved good fault diagnosis effect.

Cutting analysis is a important and crucial task task to detect and prevent problems during the petroleum well drilling process. Several studies have been developed for drilling inspection, but none of them takes care about analysing the generated cutting at the vibrating shale shakers. Here we proposed a system to analyse the cutting's concentration at the vibrating shale shakers, which can indicate problems during the petroleum well drilling process, such that the collapse of the well borehole walls. Cutting's images are acquired and sent to the data analysis module, which has as the main goal to extract features and to classify frames according to one of three previously classes of cutting's volume. A collection of supervised classifiers were applied in order to allow comparisons about their accuracy and efficiency. We used the Optimum-Path Forest (OPF), Artificial Neural Network using Multilayer Perceptrons (ANN-MLP), Support Vector Machines (SVM) and a Bayesian Classifier (BC) for this task. The first one outperformed all the remaining classifiers. Recall that we are also the first to introduce the OPF classifier in this field of knowledge. Very good results show the robustness of the proposed system, which can be also integrated with other commonly system (Mud-Logging) in order to improve the last one's efficiency.

This article explores the use of single trial EEG signals to predict the voluntary movements of single hand and two hands. During single-hand movements, three kinds of task, grasping, releasing, and holding were considered. The tasks considered during two-hand movements are left and right grasping, left and right releasing, and holding. The subject performs the tasks spontaneously without waiting for and responding to any external cues. In addition, a neural adaptive noise canceller is developed that accomplishes eye blinks suppression. The neural adaptive filter is here implemented by means of a three-layer feed-forward neural network. The feature vectors are formed from the three channels (Fz, C3, and F3). We employ the multilayer perceptron (MLP) with back-propagation learning algorithm and Radial Basis Function (RBF) network with stochastic gradient learning rule for discriminating different patterns of the EEG signals. In the classical approach to RBF and MLP network implementation, the number of hidden units is predetermined. It, usually, results in too many hidden units. To overcome this drawback, we develop an enhanced resource-allocating network (RAN) for discriminating the EEG patterns. These networks start with no hidden units and grow by allocating new hidden units based on the novelty in the EEG signals, which arrive sequentially. The results of this analysis show that the neural networks would be able to detect the movements of a single hand and two hands with an average classification accuracy of 98.82% and 96.40%, respectively. Moreover, the RAN provides a reduction in the training epochs as compared to the MLP and RBF networks. This work represents a promising approach to control prosthesis device.

Research into the problem of classification of radar returns from the ionosphere has been taken up as a challenging task for the neural networks (NNs). It appears from the literature review that for the Multi layer Perceptron (MLP) NN trained with backpropagation, reported average classification accuracy was about 96% on the test instances. This paper investigates and designs an optimal classifier using a radial basis function (RBF) NN. Authors compare the performance of two NN configurations, namely a well-known MLP NN model and the proposed RBF NN model on the radar dataset collected from the published studies. It is shown that the proposed RBF NN, consistently, has 100% accuracy on bad instances and 99.1935% accuracy on good instances. The results show that the proposed RBF NN classifier clearly outperforms the MLP NN one in various performance measures such as MSE, NMSE, correlation coefficients, area under the ROC curve and classification accuracy on the testing datasets even after attempting different data partitions.

A novel algorithm for feature selection using Harmony Search and its application for non-technical losses detection

We applied multilayer perceptron (MLP) and radial basis function (RBF) neural networks using data from two water quality monitoring stations at the Karaj Dam in Iran. Input data were calcium ions (Ca2+), magnesium ions (Mg2+), sodium ions (Na+), chloride ions (Cl−), sulfate ( SO 42−), and pH, and the output data were total dissolved solids (TDS). An MLP with one hidden layer containing eight neurons was selected for the upstream water quality station using normalized input data. We developed a second MLP neural network for the downstream station with one hidden layer containing 10 neurons in the hidden layer using normalized input data. Considering applying normalized input data and one hidden layer, the coefficient of determination (R2) and index of agreement (IA) between the observed and the predicted data for the upstream and downstream monitoring stations using the MLP neural networks were 0.985, 0.84, 0.99, and 0.92, respectively. The RBF neural network with 100 neurons in its hidden layer reached the minimum errors between the observed and the predicted results in upstream and downstream stations. The R2 between observed and predicted data for upstream and downstream monitoring stations for the RBF was 0.999 and 0.998, respectively. Data normalization improved the performance of the MLP neural networks. Sensitivity analysis indicated that magnesium is the most effective water quality parameter for predicting TDS, and sulfate is the second most effective water quality parameter affecting TDS prediction at the Karaj Dam.