QDA Classifier Research Articles

Decoding covert visual attention to motion direction using graph theory features of EEG signals and quadratic discriminant analysis

Visual attention is a type of selective attention that plays an important role in prioritizing and processing the information received from the visual scenes around us. The brain is an intricate network composed of numerous regions, each with distinct functions. As different tasks are performed, brain regions regularly synchronize and correlate with each other through intricate networks of connections. The aim of this study is to decode two states of attention by examining the interactions and connections between different brain regions using graph theory. This is demonstrated by EEG recordings from 15 participants who performed visual attention task. Pearson's correlation coefficient and coherence have been used to measure the functional connections between brain regions. In fact, each of these two criteria is regarded as an individual feature, and we perform decoding using each criterion separately. With an optimal selection of 40 connectivity features, the QDA classifier attained accuracies of 79.83% and 83.28% using correlation and coherence features, respectively. The results of attention decoding using the coherence criterion are more promising, indicating the superior effectiveness of coherence-based methods. Therefore, this study employed graph theory to analyse a neural network derived from coherence measurements. The study focused on three graph-theoretical metrics: degree centrality, efficiency, and betweenness centrality. The QDA classifier, using an optimal set of 40 features that includes degree, betweenness, and channel efficiency, achieved an accuracy of 86.46%. In comparison, the QDA classifier with 40 features based solely on degree centrality reached an accuracy of 89.96%. Finally, the results of this research indicate that analysing brain connections and brain network graphs can effectively decode different covert visual attention states.

Use Discriminant Analysis to Identify Eroticism-Related Terms in The Lyrics of Dangdut Songs

The song "Dangdut" is one of the most popular songs in Indonesia, having gained popularity from the 1960s until the present. It's even been acknowledged as authentic Indonesian music. There are both positive and negative effects on the pendengarnya of lagu dangdut. Positive dampening can lower stress levels, and negative dampening occurs when emotions are heightened. If this was brought up by a young child who was not yet fully grown, it would give them a hard time and negatively impact their journey. According to this framework, it is recommended that any eroticism in the lyrics of dance music be identified. It is therefore advised to look for signs of sexuality in the lyrics of dangdut songs. The intention is to restrict and filter the music that kids can listen to. Using LDA and QDA classifiers in conjunction with natural language processing is the suggested approach. According to research findings, LDA can identify more than QDA. The LDA examination yielded the following results: recall = 56.522%, accuracy = 56.522%, precision = 79.13%, and F1score = 65.942%. It has been demonstrated that discriminant analysis, particularly LDA, is useful for classification, as QDA has not shown itself to be the most effective method in this instance.

Automated postural asymmetry assessment in infants neurodevelopmental evaluation using novel video-based features

Background and Objective: Neurodevelopmental assessment enables the identification of infant developmental disorders in the first months of life. Thus, the appropriate therapy can be initiated promptly, increasing the chances for correct motor function. Posture asymmetry is one of the crucial aspects evaluated during the diagnosis. Available diagnostic methods are mainly based on qualitative assessment and subjective expert opinion. Current trends in computer-aided diagnosis focus mostly on analyzing infants’ spontaneous movement videos using artificial intelligence methods, based primarily on limbs movement. This study aims to develop an automatic method for determining the infant’s positional asymmetry in a video recording using computer image processing methods. Methods: We made the first attempt to determine positional preferences in a recording automatically. We proposed six quantitative features describing trunk and head position based on pose estimation. As a result of our algorithm, we estimate the percentage of each trunk position in a recording using known machine learning methods. The training and test sets were created from 51 recordings collected during our research and 12 recordings from the benchmark dataset evaluated by five of our experts. The method was assessed using the leave-one-subject-out cross-validation method for ground truth video fragments and different classifiers. Log loss for multiclass classification and ROC AUC were determined to evaluate the results for both our and benchmark datasets. Results: In a classification of the shortened side, the QDA classifier yields the most accurate results, gaining the lowest log loss of 0.552 and AUC of 0.913. The high accuracy (92.03) and sensitivity (93.26) confirm the method’s potential in screening for asymmetry. Conclusions: The method allows obtaining quantitative information about positional preference, a valuable extension of basic diagnostics without additional tools and procedures. In combination with an analysis of limbs movement, it may constitute one of the elements of a novelty computer-aided infants’ diagnosis system in the future.

Unraveling the Development of an Algorithm for Recognizing Primary Emotions Through Electroencephalography.

The large range of potential applications, not only for patients but also for healthy people, that could be achieved by affective brain-computer interface (aBCI) makes more latent the necessity of finding a commonly accepted protocol for real-time EEG-based emotion recognition. Based on wavelet package for spectral feature extraction, attending to the nature of the EEG signal, we have specified some of the main parameters needed for the implementation of robust positive and negative emotion classification. Twelve seconds has resulted as the most appropriate sliding window size; from that, a set of 20 target frequency-location variables have been proposed as the most relevant features that carry the emotional information. Lastly, QDA and KNN classifiers and population rating criterion for stimuli labeling have been suggested as the most suitable approaches for EEG-based emotion recognition. The proposed model reached a mean accuracy of 98% (s.d. 1.4) and 98.96% (s.d. 1.28) in a subject-dependent (SD) approach for QDA and KNN classifier, respectively. This new model represents a step forward towards real-time classification. Moreover, new insights regarding subject-independent (SI) approximation have been discussed, although the results were not conclusive.

Applying antagonistic activation pattern to the single-trial classification of mental arithmetic

BackgroundAt present, the application of fNIRS in the field of brain-computer interface (BCI) is being a hot topic. By fNIRS-BCI, the brain realizes the control of external devices. A state-of-the-art BCI system has five steps which are cerebral cortex signal acquisition, data pre-processing, feature selection and extraction, feature classification and application interface. Proper feature selection and extraction are crucial to the final fNIRS-BCI effect. This paper proposes a feature selection and extraction method for the mental arithmetic task. Specifically, we modified the antagonistic activation pattern approach and used the combination of antagonistic activation patterns to extract features for enhancement of the classification accuracy with low calculation costs. MethodsExperiments are conducted on an open-acquisition dataset including fNIRS signals of eight healthy subjects of mental arithmetic (MA) tasks and rest tasks. First, the signals are filtered using band-pass filters to remove noise. Second, channels are selected by prior knowledge about antagonistic activation patterns. We used cerebral blood volume (CBV) and cerebral oxygen exchange (COE) of selected each channel to build novel attributes. Finally, we proposed three groups of attributes which are CBV, COE and CBV + COE. Based on attributes generated by the proposed method, we calculated temporal statistical measures (average, variance, maximum, minimum and slope). Any two of five statistical measures were combined as feature sets. Main resultsWith the LDA, QDA, and SVM classifiers, the proposed method obtained higher classification accuracies the basic control method. The maximum classification accuracies achieved by the proposed method are 67.45 ± 14.56% with LDA classifier, 89.73 ± 5.71% with QDA classifier, and 87.04 ± 6.88% with SVM classifier. The novel method reduced the running time by 3.75 times compared with the method incorporating all channels into the feature set. Therefore, the novel method reduces the computational costs while maintaining high classification accuracy. The results are validated by another open-access dataset including MA and rest tasks of 29 healthy subjects.

On-board Training Strategy for IMU-Based Real-Time Locomotion Recognition of Transtibial Amputees With Robotic Prostheses.

The paper puts forward an on-board strategy for a training model and develops a real-time human locomotion mode recognition study based on a trained model utilizing two inertial measurement units (IMUs) of robotic transtibial prosthesis. Three transtibial amputees were recruited as subjects in this study to finish five locomotion modes (level ground walking, stair ascending, stair descending, ramp ascending, and ramp descending) with robotic prostheses. An interaction interface was designed to collect sensors' data and instruct to train model and recognition. In this study, the analysis of variance ratio (no more than 0.05) reflects the good repeatability of gait. The on-board training time for SVM (Support Vector Machines), QDA (Quadratic Discriminant Analysis), and LDA (Linear discriminant analysis) are 89, 25, and 10 s based on a 10,000 × 80 training data set, respectively. It costs about 13.4, 5.36, and 0.067 ms for SVM, QDA, and LDA for each recognition process. Taking the recognition accuracy of some previous studies and time consumption into consideration, we choose QDA for real-time recognition study. The real-time recognition accuracies are 97.19 ± 0.36% based on QDA, and we can achieve more than 95% recognition accuracy for each locomotion mode. The receiver operating characteristic also shows the good quality of QDA classifiers. This study provides a preliminary interaction design for human–machine prosthetics in future clinical application. This study just adopts two IMUs not multi-type sensors fusion to improve the integration and wearing convenience, and it maintains comparable recognition accuracy with multi-type sensors fusion at the same time.

BRAIN SIGNATURES PERSPECTIVE FOR HIGH-SECURITY AUTHENTICATION

In the recent past, the web (internet) has emerged as the most interactive authentication system for all of us (i.e. Internet banking passwords, system or building access, and e-payment platforms, etc.) and as a result, traditional authentication systems (like passwords or token-based) are never again more secure i.e. they are vulnerable to attacks. As a result, the security of individual information and safe access to a system winds up prime necessities. Therefore, the EEG-based authentication system has recently become a reasonable key for high-level security. This study centers upon P300 evoked potential-based authentication system designing. In this paper, a new visual stimulus paradigm (i.e. [Formula: see text] P300 speller) using pictures of different objects as stimuli for a person authentication system is designed instead of the conventional character-based paradigm (i.e. [Formula: see text] speller) for increasing the classification accuracy and Information Transfer Rate (ITR). The trial begins by exhibiting a collection of pictures of various objects on four corners of the PC screen comprising of random object pictures (non-target) alongside password pictures (target) that trigger P300 reactions. The P300 reaction’s rightness then checks the identity of the subject concerning the focused pictures (Target). The proposed investigation model achieves higher classification accuracy of 96.78%, along with 0.03075 False Rejection Rate (FRR), 0.03297 False Acceptation Rate (FAR), and ITR of [Formula: see text]. This study has shown that P300-based authentication system has an advantage over conventional methods (Password, Token, etc.) as EEG-based systems cannot be mimicked or forged (like Shoulder surfing in case of password) and can still be used for disabled users with a brain in good running condition. The classification results revealed that the performance of the QDA classifier outperformed other classifiers based on accuracy and ITR.

Maturity detection and volume estimation of apricot using image processing technique

Physical and imaging properties of apricot fruits are the main factors considered in the design and development of sorting mechanisms. Classification of apricots based on visual appearance was performed using image processing technique. The apricots were classified into three maturity stages (i.e. unripe, ripe, and overripe) and the volume was estimated. The captured images of fruits were processed using a previously developed automatic algorithm. The images were cropped, filtered, and segmented upon which imaging features of apricots including relative R, G, B channels, gray-scale, L*, a*, and b* were extracted. The volumes of apricots were estimated using the stripping method and multiplying the value by an oval factor. The result of statistical analysis indicated that there was significant difference among the maturity stages with respect to G, gray-scale, L* and b* features. The LDA and QDA classifiers could categorize the apricots with the accuracy of 0.904 and 0.923, respectively based on color features. Results showed that the algorithm can properly classify the fruits using the image properties of apricots.

Merging of Classifiers for Enhancing Viable vs Non-Viable Tissue Discrimination on Human Injuries.

Non-invasive optical imaging techniques have been recently proposed for distinguishing between different types of tissue in burns generated in porcine models. These techniques are designed to assist surgeons during the process of burn debridement, to identify regions requiring excision and their appropriate excision depth. This paper presents a machine learning tool for discriminating between Viable and Non- Viable tissues in human injuries. This tool merges a supervised (QDA) with an unsupervised (k-means clustering) classification algorithms. This combination improves the Non-Viable tissue detection in 23.7% with respect to a simple QDA classifier.

Integrated One-Against-One Classifiers as Tools for Virtual Screening of Compound Databases: A Case Study with CNS Inhibitors.

A total of 21 833 inhibitors of the central nervous system (CNS) were collected from Binding-database and analyzed using discriminant analysis (DA) techniques. A combination of genetic algorithm and quadratic discriminant analysis (GA-QDA) was proposed as a tool for the classification of molecules based on their therapeutic targets and activities. The results indicated that the one-against-one (OAO) QDA classifiers correctly separate the molecules based on their therapeutic targets and are comparable with support vector machines. These classifiers help in charting the chemical space of the CNS inhibitors and finding specific subspaces occupied by particular classes of molecules. As a next step, the classification models were used as virtual filters for screening of random subsets of PUBCHEM and ZINC databases. The calculated enrichment factors together with the area under curve values of receiver operating characteristic curves showed that these classifiers are good candidates to speed up the early stages of drug discovery projects. The "relative distances" of the center of active classes of biosimilar molecules calculated by OAO classifiers were used as indices for sorting the compound databases. The results revealed that, the multiclass classification models in this work circumvent the definition inactive sets for virtual screening and are useful for compound retrieval analysis in Chemoinformatics.

Using Multiscale Spectra in Regularizing Covariance Matrices for Hyperspectral Image Classification

An important component in many supervised classifiers is the estimation of one or more covariance matrices, and the often low training-sample count in supervised hyperspectral image classification yields the need for strong regularization when estimating such matrices. Often, this regularization is accomplished through adding some kind of scaled regularization matrix, e.g., the identity matrix, to the sample covariance matrix. We introduce a framework for specifying and interpreting a broad range of such regularization matrices in the linear and quadratic discriminant analysis (LDA and QDA, respectively) classifier settings. A key component in the proposed framework is the relationship between regularization and linear dimensionality reduction. We show that the equivalent of the LDA or the QDA classifier in any linearly reduced subspace can be reached by using an appropriate regularization matrix. Furthermore, several such regularization matrices can be added together forming more complex regularizers. We utilize this framework to build regularization matrices that incorporate multiscale spectral representations. Several realizations of such regularization matrices are discussed, and their performances when applied to QDA classifiers are tested on four hyperspectral data sets. Often, the classifiers benefit from using the proposed regularization matrices.

Disjoint hard models for classification

AbstractThe paper describes a new approach for disjoint hard modelling of classes. This involves developing independent PC models for each group in the class, and calculating both the Q statistic (square prediction error) for each sample to the class model and a separate statistic about how well samples are classified within the projected PC space. The latter statistic can be applied to different types of classifiers, in this paper we choose to illustrate by Quadratic Discriminant Analysis (D statistic) and one class Support Vector Domain Description (SVDD) (f‐value). The two measures (Q and the classifier dependent statistic) are combined into a joint decision function which uniquely classifies each sample. The disjoint hard models are contrasted to conjoint models where PCA is performed on the entire dataset using both QDA and Support Vector Machines (SVMs) classifiers. The optimum number of PCs for each model is determined using the bootstrap, and model performance assessed on 100 test sets obtained using different iterative splits, using %PA (Predictive Ability) and %CR (Classification Rate). The method is illustrated using a dataset consisting of 293 samples from nine groups of polymers obtained using thermal profiling. The approach described, in this paper, has many of the advantages of one class disjoint models (e.g. SIMCA) and of conventional hard models, and is useful if it is known that all samples must belong to one of a series of known groups but each group has a very different structure. Copyright © 2010 John Wiley & Sons, Ltd.