Showing papers on "Linear discriminant analysis published in 2020"
TL;DR: Two of the prominent dimensionality reduction techniques, Linear Discriminant Analysis (LDA) and Principal Component Analysis (PCA) are investigated on four popular Machine Learning (ML) algorithms using publicly available Cardiotocography dataset from University of California and Irvine Machine Learning Repository to prove that PCA outperforms LDA in all the measures.
Abstract: Due to digitization, a huge volume of data is being generated across several sectors such as healthcare, production, sales, IoT devices, Web, organizations. Machine learning algorithms are used to uncover patterns among the attributes of this data. Hence, they can be used to make predictions that can be used by medical practitioners and people at managerial level to make executive decisions. Not all the attributes in the datasets generated are important for training the machine learning algorithms. Some attributes might be irrelevant and some might not affect the outcome of the prediction. Ignoring or removing these irrelevant or less important attributes reduces the burden on machine learning algorithms. In this work two of the prominent dimensionality reduction techniques, Linear Discriminant Analysis (LDA) and Principal Component Analysis (PCA) are investigated on four popular Machine Learning (ML) algorithms, Decision Tree Induction, Support Vector Machine (SVM), Naive Bayes Classifier and Random Forest Classifier using publicly available Cardiotocography (CTG) dataset from University of California and Irvine Machine Learning Repository. The experimentation results prove that PCA outperforms LDA in all the measures. Also, the performance of the classifiers, Decision Tree, Random Forest examined is not affected much by using PCA and LDA.To further analyze the performance of PCA and LDA the eperimentation is carried out on Diabetic Retinopathy (DR) and Intrusion Detection System (IDS) datasets. Experimentation results prove that ML algorithms with PCA produce better results when dimensionality of the datasets is high. When dimensionality of datasets is low it is observed that the ML algorithms without dimensionality reduction yields better results.
414 citations
TL;DR: This paper adopts Random Forest to select the important feature in classification and compares the result of the dataset with and without essential features selection by RF methods varImp(), Boruta, and Recursive Feature Elimination to get the best percentage accuracy and kappa.
Abstract: Feature selection becomes prominent, especially in the data sets with many variables and features. It will eliminate unimportant variables and improve the accuracy as well as the performance of classification. Random Forest has emerged as a quite useful algorithm that can handle the feature selection issue even with a higher number of variables. In this paper, we use three popular datasets with a higher number of variables (Bank Marketing, Car Evaluation Database, Human Activity Recognition Using Smartphones) to conduct the experiment. There are four main reasons why feature selection is essential. First, to simplify the model by reducing the number of parameters, next to decrease the training time, to reduce overfilling by enhancing generalization, and to avoid the curse of dimensionality. Besides, we evaluate and compare each accuracy and performance of the classification model, such as Random Forest (RF), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), and Linear Discriminant Analysis (LDA). The highest accuracy of the model is the best classifier. Practically, this paper adopts Random Forest to select the important feature in classification. Our experiments clearly show the comparative study of the RF algorithm from different perspectives. Furthermore, we compare the result of the dataset with and without essential features selection by RF methods varImp(), Boruta, and Recursive Feature Elimination (RFE) to get the best percentage accuracy and kappa. Experimental results demonstrate that Random Forest achieves a better performance in all experiment groups.
271 citations
TL;DR: This investigation of Bitcoin price prediction can be considered a pilot study of the importance of the sample dimension in machine learning techniques, with accuracy reaching 67.2%.
203 citations
TL;DR: A comparative analysis using the Wilcoxon signed-rank tests revealed a significant improvement of landslide prediction using the spatially explicit DL model over the quadratic discriminant analysis, Fisher's linear discriminantAnalysis, and multi-layer perceptron neural network.
Abstract: With the increasing threat of recurring landslides, susceptibility maps are expected to play a bigger role in promoting our understanding of future landslides and their magnitude. This study describes the development and validation of a spatially explicit deep learning (DL) neural network model for the prediction of landslide susceptibility. A geospatial database was generated based on 217 landslide events from the Muong Lay district (Vietnam), for which a suite of nine landslide conditioning factors was derived. The Relief-F feature selection method was employed to quantify the utility of the conditioning factors for developing the landslide predictive model. Several performance metrics demonstrated that the DL model performed well both in terms of the goodness-of-fit with the training dataset (AUC = 0.90; accuracy = 82%; RMSE = 0.36) and the ability to predict future landslides (AUC = 0.89; accuracy = 82%; RMSE = 0.38). The efficiency of the model was compared to the quadratic discriminant analysis, Fisher's linear discriminant analysis, and multi-layer perceptron neural network. A comparative analysis using the Wilcoxon signed-rank tests revealed a significant improvement of landslide prediction using the spatially explicit DL model over these other models. The insights provided from this study will be valuable for further development of landslide predictive models and spatially explicit assessment of landslide-prone regions around the world.
187 citations
TL;DR: It is pointed out that the deep features provided robust and consistent features for pneumonia detection, and minimum redundancy maximum relevance method was found a beneficial tool to reduce the dimension of the feature set.
Abstract: Pneumonia is one of the diseases that people may encounter in any period of their lives. Approximately 18% of infectious diseases are caused by pneumonia. This disease may result in death in the following stages. In order to diagnose pneumonia as a medical condition, lung X-ray images are routinely examined by the field experts in the clinical practice. In this study, lung X-ray images that are available for the diagnosis of pneumonia were used. The convolutional neural network was employed as feature extractor, and some of existing convolutional neural network models that are AlexNet, VGG-16 and VGG-19 were utilized so as to realize this specific task. Then, the number of deep features was reduced from 1000 to 100 by using the minimum redundancy maximum relevance algorithm for each deep model. Accordingly, we achieved 100 deep features from each deep model, and we combined these features so as to provide an efficient feature set consisting of totally 300 deep features. In this step of the experiment, this feature set was given as an input to the decision tree, k-nearest neighbors, linear discriminant analysis, linear regression, and support vector machine learning models. Finally, all models ensured promising results, especially linear discriminant analysis yielded the most efficient results with an accuracy of 99.41%. Consequently, the results point out that the deep features provided robust and consistent features for pneumonia detection, and minimum redundancy maximum relevance method was found a beneficial tool to reduce the dimension of the feature set.
172 citations
TL;DR: This work has shown that it has reached the perfect classification rate by using X-ray image for Covid-19 detection, and SVM classifier achieved 100.0% classification accuracy by using 10-fold cross-validation.
122 citations
TL;DR: It is demonstrated that even though PCA ignores the information regarding the class labels of the samples, this unsupervised tool can be remarkably effective as a feature selector.
Abstract: Partial Least-Squares Discriminant Analysis (PLS-DA) is a popular machine learning tool that is gaining increasing attention as a useful feature selector and classifier. In an effort to understand its strengths and weaknesses, we performed a series of experiments with synthetic data and compared its performance to its close relative from which it was initially invented, namely Principal Component Analysis (PCA). We demonstrate that even though PCA ignores the information regarding the class labels of the samples, this unsupervised tool can be remarkably effective as a feature selector. In some cases, it outperforms PLS-DA, which is made aware of the class labels in its input. Our experiments range from looking at the signal-to-noise ratio in the feature selection task, to considering many practical distributions and models encountered when analyzing bioinformatics and clinical data. Other methods were also evaluated. Finally, we analyzed an interesting data set from 396 vaginal microbiome samples where the ground truth for the feature selection was available. All the 3D figures shown in this paper as well as the supplementary ones can be viewed interactively at http://biorg.cs.fiu.edu/plsda
Our results highlighted the strengths and weaknesses of PLS-DA in comparison with PCA for different underlying data models.
120 citations
TL;DR: A sparse-adaptive hypergraph discriminant analysis (SAHDA) method is proposed to obtain the embedding features of the HSI and achieves better classification accuracies than the traditional graph learning methods.
Abstract: Hyperspectral image (HSI) contains complex multiple structures. Therefore, the key problem analyzing the intrinsic properties of an HSI is how to represent the structure relationships of the HSI effectively. Hypergraph is very effective to describe the intrinsic relationships of the HSI. In general, Euclidean distance is adopted to construct the hypergraph. However, this method cannot effectively represent the structure properties of high-dimensional data. To address this problem, we propose a sparse-adaptive hypergraph discriminant analysis (SAHDA) method to obtain the embedding features of the HSI in this letter. SAHDA uses the sparse representation to reveal the structure relationships of the HSI adaptively. Then, an adaptive hypergraph is constructed by using the intraclass sparse coefficients. Finally, we develop an adaptive dimensionality reduction mode to calculate the weights of the hyperedges and the projection matrix. SAHDA can adaptively reveal the intrinsic properties of the HSI and enhance the performance of the embedding features. Some experiments on the Washington DC Mall hyperspectral data set demonstrate the effectiveness of the proposed SAHDA method, and SAHDA achieves better classification accuracies than the traditional graph learning methods.
113 citations
TL;DR: A novel intelligent fault identification method based on multiple source domains that describes the discriminant structure of each source domain as a point of Grassmann manifold using local Fisher discriminant analysis to learn effective discriminant directions from multimodal fault data.
Abstract: The data-driven diagnosis methods based on conventional machine-learning techniques have been widely developed in recent years. However, the assumption of conventional methods that the training and test data should be identically distributed is usually unsatisfied in actual diagnosis scenario. While there are several existing works that have been studied to construct diagnosis models by transfer learning methods, most of them are only focused on learning from a single source. Actually, how to discover effective and general diagnosis knowledge from multiple related source domains and further generalize the learned knowledge to new target tasks is crucial to data-driven fault diagnosis. To this end, this paper proposes a novel intelligent fault identification method based on multiple source domains. First, the method describes the discriminant structure of each source domain as a point of Grassmann manifold using local Fisher discriminant analysis. Through preserving the within-class local structure, local Fisher discriminant analysis can learn effective discriminant directions from multimodal fault data. Second, the mean subspace of source domains is computed on the Grassmann manifold through Karcher mean. The mean subspace can be viewed as a representation of the general diagnosis structure that can facilitate the construction of the diagnosis model for the target domain. Experiments on bearing fault diagnosis tasks verify the effectiveness of the proposed method.
109 citations
TL;DR: The toolbox computes various classification and regression metrics and establishes their statistical significance, is modular and easily extendable, and offers interfaces for LIBSVM and LIBLINEAR as well as an integration into the FieldTrip neuroimaging toolbox.
Abstract: MVPA-Light is a MATLAB toolbox for multivariate pattern analysis (MVPA). It provides native implementations of a range of classifiers and regression models, using modern optimization algorithms. High-level functions allow for the multivariate analysis of multi-dimensional data, including generalization (e.g., time x time) and searchlight analysis. The toolbox performs cross-validation, hyperparameter tuning, and nested preprocessing. It computes various classification and regression metrics and establishes their statistical significance, is modular and easily extendable. Furthermore, it offers interfaces for LIBSVM and LIBLINEAR as well as an integration into the FieldTrip neuroimaging toolbox. After introducing MVPA-Light, example analyses of MEG and fMRI datasets, and benchmarking results on the classifiers and regression models are presented.
104 citations
TL;DR: Experimental results show that the strategy and parameter self-adaptive mechanisms can improve the performance of the evolutionary algorithms, and that SPS-PSO can achieve higher classification accuracy and obtain more concise solutions than those of the other algorithms on the large-scale feature problems selected in this research.
TL;DR: The proposed model is consistent diagnosis model for lung cancer detection using chest CT images using LeNet, AlexNet and VGG-16 deep learning models.
TL;DR: This work presents a sustainable deep learning architecture, which utilizes multi-layer deep features fusion and selection, for accurate object classification, and shows significantly more accuracy than existing methods.
Abstract: With an overwhelming increase in the demand of autonomous systems, especially in the applications related to intelligent robotics and visual surveillance, come stringent accuracy requirements for complex object recognition. A system that maintains its performance against a change in the object’s nature is said to be sustainable and it has become a major area of research for the computer vision research community in the past few years. In this work, we present a sustainable deep learning architecture, which utilizes multi-layer deep features fusion and selection, for accurate object classification. The proposed approach comprises three steps: (1) By utilizing two deep learning architectures, Very Deep Convolutional Networks for Large-Scale Image Recognition and Inception V3, it extracts features based on transfer learning, (2) Fusion of all the extracted feature vectors is performed by means of a parallel maximum covariance approach, and (3) The best features are selected using Multi Logistic Regression controlled Entropy-Variances method. For verification of the robust selected features, the Ensemble Learning method named Subspace Discriminant Analysis is utilized as a fitness function. The experimental process is conducted using four publicly available datasets, including Caltech-101, Birds database, Butterflies database and CIFAR-100, and a ten-fold validation process which yields the best accuracies of 95.5%, 100%, 98%, and 68.80% for the datasets respectively. Based on the detailed statistical analysis and comparison with the existing methods, the proposed selection method gives significantly more accuracy. Moreover, the computational time of the proposed selection method is better for real-time implementation.
01 Jun 2020
TL;DR: By combining streaming linear discriminant analysis with deep learning, this work is able to outperform both incremental batch learning and streaming learning algorithms on both Ima- geNet ILSVRC-2012 and CORe50, a dataset that involves learning to classify from temporally ordered samples.
Abstract: When an agent acquires new information, ideally it would immediately be capable of using that information to understand its environment. This is not possible using conventional deep neural networks, which suffer from catastrophic forgetting when they are incrementally updated, with new knowledge overwriting established representations. A variety of approaches have been developed that attempt to mitigate catastrophic forgetting in the incremental batch learning scenario, where a model learns from a series of large collections of labeled samples. However, in this setting, inference is only possible after a batch has been accumulated, which prohibits many applications. An alternative paradigm is online learning in a single pass through the training dataset on a resource constrained budget, which is known as streaming learning. Streaming learning has been much less studied in the deep learning community. In streaming learning, an agent learns instances one-by-one and can be tested at any time, rather than only after learning a large batch. Here, we revisit streaming linear discriminant analysis, which has been widely used in the data mining research community. By combining streaming linear discriminant analysis with deep learning, we are able to outperform both incremental batch learning and streaming learning algorithms on both ImageNet ILSVRC-2012 and CORe50, a dataset that involves learning to classify from temporally ordered samples.
01 Jan 2020
TL;DR: The strategy of combining the generic models with online training is easily accepted and achieves higher levels of user satisfaction (as measured by subjective reports), which provides a valuable new strategy for improving the performance of P300-based BCI.
Abstract: P300-based brain-computer interfaces (BCIs) provide an additional communication channel for individuals with communication disabilities. In general, P300-based BCIs need to be trained, offline, for a considerable period of time, which causes users to become fatigued. This reduces the efficiency and performance of the system. In order to shorten calibration time and improve system performance, we introduce the concept of a generic model set. We used ERP data from 116 participants to train the generic model set. The resulting set consists of ten models, which are trained by weighted linear discriminant analysis (WLDA). Twelve new participants were then invited to test the validity of the generic model set. The results demonstrated that all new participants matched the best generic model. The resulting mean classification accuracy equaled 80% after online training, an accuracy that was broadly equivalent to the typical training model method. Moreover, the calibration time was shortened by 70.7% of the calibration time of the typical model method. In other words, the best matching model method only took 81s to calibrate, while the typical model method took 276s. There were also significant differences in both accuracy and raw bit rate between the best and the worst matching model methods. We conclude that the strategy of combining the generic models with online training is easily accepted and achieves higher levels of user satisfaction (as measured by subjective reports). Thus, we provide a valuable new strategy for improving the performance of P300-based BCI.
TL;DR: In this paper, a large set of descriptors and neural networks are employed to compress the information in a lower-dimensional space, using Fisher's linear discriminant as an objective function to maximize the discriminative power.
Abstract: Designing an appropriate set of collective variables is crucial to the success of several enhanced sampling methods. Here we focus on how to obtain such variables from information limited to the metastable states. We characterize these states by a large set of descriptors and employ neural networks to compress this information in a lower-dimensional space, using Fisher's linear discriminant as an objective function to maximize the discriminative power of the network. We test this method on alanine dipeptide, using the nonlinearly separable data set composed by atomic distances. We then study an intermolecular aldol reaction characterized by a concerted mechanism. The resulting variables are able to promote sampling by drawing nonlinear paths in the physical space connecting the fluctuations between metastable basins. Lastly, we interpret the behavior of the neural network by studying its relation to the physical variables. Through the identification of its most relevant features, we are able to gain chemical insight into the process.
TL;DR: This work contributes to successfully implement spatial PCA to reduce signal dimensionality and to select the suitable features based on the t-statistical inferences among the classes to achieve a highly efficient brain-computer interface (BCI) system regarding emotion recognition from electroencephalogram signal.
TL;DR: The results demonstrate the MRCP and ERD features of pre-movements contain significantly discriminative information, which are complementary to each other, and thereby could be well recognized by the proposed combination method of DCPM and CSP.
Abstract: OBJECTIVE In recent years, brain-computer interface (BCI) systems based on electroencephalography (EEG) have developed rapidly. However, the decoding of voluntary finger pre-movements from EEG is still a challenge for BCIs. This study aimed to analyze the pre-movement EEG features in time and frequency domains and design an efficient method to decode the movement-related patterns. APPROACH In this study, we first investigated the EEG features induced by the intention of left and right finger movements. Specifically, the movement-related cortical potential (MRCP) and event-related desynchronization (ERD) features were extracted using discriminative canonical pattern matching (DCPM) and common spatial patterns (CSP), respectively. Then, the two types of features were classified by two fisher discriminant analysis (FDA) classifiers, respectively. Their decision values were further assembled to facilitate the classification. To verify the validity of the proposed method, a private dataset containing 12 subjects and a public dataset from BCI competition II were used for estimating the classification accuracy. MAIN RESULTS As a result, for the private dataset, the combination of DCPM and CSP achieved an average accuracy of 80.96%, which was 5.08% higher than the single DCPM method (p < 0.01) and 10.23% higher than the single CSP method (p < 0.01). Notably, the highest accuracy could achieve 91.5% for the combination method. The test accuracy of dataset IV of BCI competition II was 90%, which was equal to the best result in the existing literature. SIGNIFICANCE The results demonstrate the MRCP and ERD features of pre-movements contain significantly discriminative information, which are complementary to each other, and thereby could be well recognized by the proposed combination method of DCPM and CSP. Therefore, this study provides a promising approach for the decoding of pre-movement EEG patterns, which is significant for the development of BCIs.
TL;DR: In this paper, the sum of ranking difference (SRD) algorithm was applied to create a nonparametric Partial least squares-discriminant analysis (PLS-DA) model.
Abstract: Identifying tea grades is crucial to providing consumers with tea and ensuring consumer rights. Partial least squares–discriminant analysis (PLS-DA) is a simple and traditional classification algorithm in analyzing e-tongue data. However, the number of latent variables (LVs) in a PLS-DA model needs to be determined, and cross-validation is the most common way to identify the optimal latent variables. To overcome this obstacle, sum of ranking difference (SRD) algorithm was applied to create a non-parametric PLS-DA-SRD model. The performance of PLS-DA and PLS-DA-SRD models were then compared, and significant improvement in term of accuracy, sensitivity, and specificity was obtained when SRD was combined with PLS-DA algorithm. Moreover, no training phase was needed to identify the optimal LVs for PLS-DA, making the calculation of classification rapid and concise. The PLS-DA-SRD method demonstrated its efficiency and capability by successfully identifying the tea sample grade.
TL;DR: The proposed WHITE STAG model and kernel sliding perceptron outperformed the existing well known statistical state-of-the-art methods by achieving a weighted average recognition rate of 87.48% over UT-interaction, 87.5% over BIT-Interaction and 85.7% over IM-IntensityInteractive7 datasets.
Abstract: To understand human to human dealing accurately, human interaction recognition (HIR) systems require robust feature extraction and selection methods based on vision sensors. In this paper, we have proposed WHITE STAG model to wisely track human interactions using space time methods as well as shape based angular-geometric sequential approaches over full-body silhouettes and skeleton joints, respectively. After feature extraction, feature space is reduced by employing codebook generation and linear discriminant analysis (LDA). Finally, kernel sliding perceptron is used to recognize multiple classes of human interactions. The proposed WHITE STAG model is validated using two publicly available RGB datasets and one self-annotated intensity interactive dataset as novelty. For evaluation, four experiments are performed using leave-one-out and cross validation testing schemes. Our WHITE STAG model and kernel sliding perceptron outperformed the existing well known statistical state-of-the-art methods by achieving a weighted average recognition rate of 87.48% over UT-Interaction, 87.5% over BIT-Interaction and 85.7% over proposed IM-IntensityInteractive7 datasets. The proposed system should be applicable to various multimedia contents and security applications such as surveillance systems, video based learning, medical futurists, service cobots, and interactive gaming.
TL;DR: Experimental results under seven UCI datasets and eight gene expression datasets illustrate that the proposed NMRS-based attribute reduction method using Lebesgue and entropy measures in incomplete neighborhood decision systems is effective to select most relevant attributes with higher classification accuracy, as compared with representative algorithms.
Abstract: For incomplete data with mixed numerical and symbolic attributes, attribute reduction based on neighborhood multi-granulation rough sets (NMRS) is an important method to improve the classification performance. However, most classical attribute reduction methods can only handle finite sets as to produce more attributes and lower classification accuracy. This paper proposes a novel NMRS-based attribute reduction method using Lebesgue and entropy measures in incomplete neighborhood decision systems. First, some concepts of optimistic and pessimistic NMRS models in incomplete neighborhood decision systems are given, respectively. Then, a Lebesgue measure is combined with NMRS to study neighborhood tolerance class-based uncertainty measures. To analyze the uncertainty, noise and redundancy of incomplete neighborhood decision systems in detail, some neighborhood multi-granulation entropy-based uncertainty measures are developed by integrating Lebesgue and entropy measures. Inspired by both algebraic view with information view in NMRS, the pessimistic neighborhood multi-granulation dependency joint entropy is proposed. What is more, the corresponding properties are further deduced and the relationships among these measures are discussed, which can help to investigate the uncertainty of incomplete neighborhood decision systems. Finally, the Fisher linear discriminant method is used to eliminate irrelevant attributes to significantly reduce computational complexity for high-dimensional datasets, and a heuristic attribute reduction algorithm with complexity analysis is designed to improve classification performance of incomplete and mixed datasets. Experimental results under seven UCI datasets and eight gene expression datasets illustrate that the proposed method is effective to select most relevant attributes with higher classification accuracy, as compared with representative algorithms.
TL;DR: The results prove that different classification models must be used to identify different emotional states.
Abstract: Emotion recognition using brain signals has the potential to change the way we identify and treat some health conditions. Difficulties and limitations may arise in general emotion recognition software due to the restricted number of facial expression triggers, dissembling of emotions, or among people with alexithymia. Such triggers are identified by studying the continuous brainwaves generated by human brain. Electroencephalogram (EEG) signals from the brain give us a more diverse insight on emotional states that one may not be able to express. Brainwave EEG signals can reflect the changes in electrical potential resulting from communications networks between neurons. This research involves analyzing the epoch data from EEG sensor channels and performing comparative analysis of multiple machine learning techniques [namely Support Vector Machine (SVM), K-nearest neighbor, Linear Discriminant Analysis, Logistic Regression and Decision Trees each of these models] were tested with and without principal component analysis (PCA) for dimensionality reduction. Grid search was also utilized for hyper-parameter tuning for each of the tested machine learning models over Spark cluster for lowered execution time. The DEAP Dataset was used in this study, which is a multimodal dataset for the analysis of human affective states. The predictions were based on the labels given by the participants for each of the 40 1-min long excerpts of music. music. Participants rated each video in terms of the level of arousal, valence, like/dislike, dominance and familiarity. The binary class classifiers were trained on the time segmented, 15 s intervals of epoch data, individually for each of the 4 classes. PCA with SVM performed the best and produced an F1-score of 84.73% with 98.01% recall in the 30th to 45th interval of segmentation. For each of the time segments and “a binary training class” a different classification model converges to a better accuracy and recall than others. The results prove that different classification models must be used to identify different emotional states.
TL;DR: An interpretable CNN model with a global average pooling layer is presented for Raman and mid-infrared spectral data analysis and a class activation mapping (CAM)-based approach is leveraged to visualize the active variables in the whole spectrum.
TL;DR: This study compared a recently developed algorithm, i.e., discriminative canonical pattern matching (DCPM), with seven ERP-BCI classification methods for the single-trial classification of two private EEG datasets and three public EEG datasets with small training sets and showed that the DCPM outperformed other classifiers for all of the tested datasets, suggesting theDCPM is a robust classification algorithm for assessing a wide range of ERP components.
Abstract: Event-related potentials (ERPs) are one of the most popular control signals for brain–computer interfaces (BCIs). However, they are very weak and sensitive to the experimental settings including paradigms, stimulation parameters and even surrounding environments, resulting in a diversity of ERP patterns across different BCI experiments. It's still a challenge to develop a general decoding algorithm that can adapt to the ERP diversities of different BCI datasets with small training sets. This study compared a recently developed algorithm, i.e., discriminative canonical pattern matching (DCPM), with seven ERP-BCI classification methods, i.e., linear discriminant analysis (LDA), stepwise LDA, bayesian LDA, shrinkage LDA, spatial-temporal discriminant analysis (STDA), xDAWN and EEGNet for the single-trial classification of two private EEG datasets and three public EEG datasets with small training sets. The feature ERPs of the five datasets included P300, motion visual evoked potential (mVEP), and miniature asymmetric visual evoked potential (aVEP). Study results showed that the DCPM outperformed other classifiers for all of the tested datasets, suggesting the DCPM is a robust classification algorithm for assessing a wide range of ERP components.
TL;DR: A new pretrained Convolutional Neural Network (CNN) model is proposed for the extraction of deep features and provided the best accuracy score when compared to other existing methods using the same dataset, improving the classification accuracy by 5.75%.
Abstract: The recognition of various lung sounds recorded using electronic stethoscopes plays a significant role in the early diagnoses of respiratory diseases. To increase the accuracy of specialist evaluations, machine learning techniques have been intensely employed during the past 30 years. In the current study, a new pretrained Convolutional Neural Network (CNN) model is proposed for the extraction of deep features. In the CNN architecture, an average-pooling layer and a max-pooling layer are connected in parallel in order to boost classification performance. The deep features are utilized as the input of the Linear Discriminant Analysis (LDA) classifier using the Random Subspace Ensembles (RSE) method. The proposed method was evaluated against a challenge dataset known as ICBHI 2017. The deep features and the LDA with RSE method provided the best accuracy score when compared to other existing methods using the same dataset, improving the classification accuracy by 5.75%.
TL;DR: Both RLDA and RSLDA can extract unbounded numbers of features and avoid the small sample size (SSS) problem, and an alternating direction method of multipliers (ADMM) is used to cope with the nonconvexity in the proposed formulations.
Abstract: In this paper, we propose a robust linear discriminant analysis (RLDA) through Bhattacharyya error bound optimization. RLDA considers a nonconvex problem with the $L_{1}$ -norm operation that makes it less sensitive to outliers and noise than the $L_{2}$ -norm linear discriminant analysis (LDA). In addition, we extend our RLDA to a sparse model (RSLDA). Both RLDA and RSLDA can extract unbounded numbers of features and avoid the small sample size (SSS) problem, and an alternating direction method of multipliers (ADMM) is used to cope with the nonconvexity in the proposed formulations. Compared with the traditional LDA, our RLDA and RSLDA are more robust to outliers and noise, and RSLDA can obtain sparse discriminant directions. These findings are supported by experiments on artificial data sets as well as human face databases.
TL;DR: This study classification of invasive ductal carcinoma breast cancer is performed by using deep learning models, which is the sub-branch of artificial intelligence, and the proposed approach can be admitted as a successful model in the classification.
01 Feb 2020
TL;DR: Experimental results show that the proposed technique is reliable and applicable in health exercise systems, smart surveillance, e-learning, abnormal behavioral detection, protection for child abuse, care of the elderly people, virtual reality, intelligent image retrieval and human computer interaction.
Abstract: Human body action recognition has drawn a good deal of interest in the community of computer vision, owing to its wide range of applications. Recently, the video / image sequence base action recognition techniques are believed to be ideal for its efficiency and lower cost compared to other techniques such as the ambient sensor and the wearable sensor. However, given to a large amount of variation in human pose and image quality, reliable detection of human action is still a very challenging job for scientists. In this document, we used linear discriminant analysis for the generation of features from the body parts detected. The primary goal of this study is to combine linear discriminant analysis with an artificial neural network for precise human action detection and recognition. Our proposed mechanism detects complicated human actions in two state-of-the-art datasets, i.e. KTH-dataset and Weizmann Human Action. We obtained multidimensional features from twelve body parts, which are estimated from body models. These multidimensional characteristics are used as inputs for the artificial neural network. To access the efficiency of our suggested method, we compared the outcomes with other state-of-the-art classifiers. Experimental results show that our proposed technique is reliable and applicable in health exercise systems, smart surveillance, e-learning, abnormal behavioral detection, protection for child abuse, care of the elderly people, virtual reality, intelligent image retrieval and human computer interaction.
TL;DR: In this article, the authors proposed an intelligent model for automatic detection and classification of the matrix cracking in composites using the guided wave propagation and artificial intelligence (AI) approaches, which achieved the highest classification accuracy (91.7%) followed by linear vector quantization (LVQ) neural network and multilayer perceptron (MLP) NN.
TL;DR: A single system is developed to diagnose one or two neurological diseases at the same time (two-class mode and three- class mode) to aid in the accurate diagnosis of neurological brain disorders: epilepsy and autism spectrum disorder (ASD).
Abstract: Analysis of electroencephalogram (EEG) signals is essential because it is an efficient method to diagnose neurological brain disorders. In this work, a single system is developed to diagnose one or two neurological diseases at the same time (two-class mode and three-class mode). For this purpose, different EEG feature-extraction and classification techniques are investigated to aid in the accurate diagnosis of neurological brain disorders: epilepsy and autism spectrum disorder (ASD). Two different modes, single-channel and multi-channel, of EEG signals are analyzed for epilepsy and ASD. The independent components analysis (ICA) technique is used to remove the artifacts from EEG dataset. Then, the EEG dataset is segmented and filtered to remove noise and interference using an elliptic band-pass filter. Next, the EEG signal features are extracted from the filtered signal using a discrete wavelet transform (DWT) to decompose the filtered signal to its sub-bands delta, theta, alpha, beta and gamma. Subsequently, five statistical methods are used to extract features from the EEG sub-bands: the logarithmic band power (LBP), standard deviation, variance, kurtosis, and Shannon entropy (SE). Further, the features are fed into four different classifiers, linear discriminant analysis (LDA), support vector machine (SVM), k-nearest neighbor (KNN), and artificial neural networks (ANNs), to classify the features corresponding to their classes. The combination of DWT with SE and LBP produces the highest accuracy among all the classifiers. The overall classification accuracy approaches 99.9% using SVM and 97% using ANN for the three-class single-channel and multi-channel modes, respectively.