Iterative Component Research Articles

Optimal feature selection based speech emotion recognition using two‐stream deep convolutional neural network

Speech signal processing is an active area of research, the most dominant source of exchanging information among human beings, and the best way for human–computer interaction (HCI). Human behavior assessments and emotion recognition from a speech signal, such as speech emotion recognition (SER) is an emerging HCI area of exploration with various real time claims. The performance of an efficient SER system depends on feature learning, which include salient and discriminative information such as high-level deep features. In this paper, we proposed a two-stream deep convolutional neural network with an iterative neighborhood component analysis (INCA) to learn mutually spatial-spectral features and select the most discriminative optimal features for the final prediction. Our model is composed of two channels, and each channel is associated with the convolutional neural network structure to extract cues from the oral signals. The first channel extracts feature from the spectral domain, and the second channel extracts features from the spatial domain, which are then fused and fed to the INCA to remove the severance and select the optimal features for the final model training. The joint refine features are passed from the fully connected network with a softmax classifier to yield the predictions of the different emotions. We trained our proposed system using three benchmarks, which included the EMO-DB, SAVEE, and RAVDESS emotional speech corpora, and we tested the prediction performance to secure 95%, 82%, and 85% recognition rates. The performance of the system shows the effectiveness and significance of the proposed system.

Application of substitution box of present cipher for automated detection of snoring sounds

Background and purposeSnoring is one of the sleep disorders, and snoring sounds have been used to diagnose many sleep-related diseases. However, the snoring sound classification is done manually which is time-consuming and prone to human errors. An automated snoring sound classification model is proposed to overcome these problems. Material and methodThis work proposes an automated snoring sound classification method using three new methods. These methods are maximum absolute pooling (MAP), the nonlinear present pattern, and two-layered neighborhood component analysis, and iterative neighborhood component analysis (NCAINCA) selector. Using these methods, a new snoring sound classification (SSC) model is presented. The MAP decomposition model is applied to snoring sounds to extract both low and high-level features. The presented model aims to attain high performance for SSC problem. The developed present pattern (Present-Pat) uses substitution box (SBox) and statistical feature generator. By deploying these feature generators, both textural and statistical features are generated. NCAINCA chooses the most informative/valuable features, and these selected features are fed to k-nearest neighbor (kNN) classifier with leave-one-out cross-validation (LOOCV). The Present-Pat based SSC system is developed using Munich-Passau Snore Sound Corpus (MPSSC) dataset comprising of four categories. ResultsOur model reached an accuracy and unweighted average recall (UAR) of 97.10 % and 97.60 %, respectively, using LOOCV. Moreover, a nocturnal sound dataset is used to show the universal success of the presented model. Our model attained an accuracy of 98.14 % using the used nocturnal sound dataset. ConclusionsOur developed classification model is ready to be tested with more data and can be used by sleep specialists to diagnose the sleep disorders based on snoring sounds.

A closed-form estimator for the Markov switching in mean model

This paper revisits the Markov switching in mean model which is commonly fitted by maximizing its log-likelihood. To effectively resolve the computational complexity caused by the nolinear nature and iterative components in the log-likelihood, we propose a closed-form solution inspired by moment-based and Yule–Walker methods. Associated asymptotics are discussed with numerical evidence. For practical considerations, we demonstrate the usefulness of the proposed estimates when supplied as initial values to obtain the usual maximum likelihood estimates for reliable statistical inferences.

Biosynthesis of 6‐Hydroxymellein Requires a Collaborating Polyketide Synthase‐like Enzyme

AbstractThe polyketide synthase (PKS)‐like protein TerB, consisting of inactive dehydratase, inactive C‐methyltransferase, and functional ketoreductase domains collaborates with the iterative non reducing PKS TerA to produce 6‐hydroxymellein, a key pathway intermediate during the biosynthesis of various fungal natural products. The catalytically inactive dehydratase domain of TerB appears to mediate productive interactions with TerA, demonstrating a new mode of trans‐interaction between iterative PKS components.

Biosynthesis of 6-Hydroxymellein Requires a Collaborating Polyketide Synthase-like Enzyme.

The polyketide synthase (PKS)‐like protein TerB, consisting of inactive dehydratase, inactive C‐methyltransferase, and functional ketoreductase domains collaborates with the iterative non reducing PKS TerA to produce 6‐hydroxymellein, a key pathway intermediate during the biosynthesis of various fungal natural products. The catalytically inactive dehydratase domain of TerB appears to mediate productive interactions with TerA, demonstrating a new mode of trans‐interaction between iterative PKS components.

EEG-based driving fatigue detection using multilevel feature extraction and iterative hybrid feature selection

Brain activities can be evaluated by using Electroencephalogram (EEG) signals. One of the primary reasons for traffic accidents is driver fatigue, which can be identified by using EEG signals. This work aims to achieve a highly accurate and straightforward process to detect driving fatigue by using EEG signals. Two main problems, which are feature generation and feature selection, are defined to achieve this aim. This work solves these problems by using two different approaches. Deep networks are efficient feature generators and extract features in low, medium, and high levels. These features can be generated by using multileveled or multilayered feature extraction. Therefore, we proposed a multileveled feature generator that uses a one-dimensional binary pattern (BP) and statistical features together, and levels are created using a one-dimensional discrete wavelet transform (1D-DWT). A five-level fused feature extractor is presented by using BP, statistical features of 1D-DWT together. Moreover, a 2-layered feature selection method is proposed using ReliefF and iterative neighborhood component analysis (RFINCA) to solve the feature selection problem. The goals of the RFINCA are to choose the optimal number of features automatically and use the effectiveness of ReliefF and neighborhood component analysis (NCA) together. A driving fatigue EEG dataset was used as a testbed to denote the effectiveness of eighteen conventional classifiers. According to the experimental results, a highly accurate EEG classification approach is presented. The proposed method also reached 100.0% classification accuracy by using a k-nearest neighborhood classifier.

Efficient Iterative Dynamic Kernel Principal Component Analysis Monitoring Method for the Batch Process with Super-large-scale Data Sets.

The Internet environment has provided massive data to the actual industrial production process. It not only has large amounts of data but also has a high data dimension, which brings challenges to the traditional statistical process monitoring. Aiming at the nonlinearity and dynamics of industrial large-scale high-dimensional data, an efficient iterative multiple dynamic kernel principal component analysis (IMDKPCA) method is proposed to monitor the complex industrial process with super-large-scale high-dimensional data. In KPCA, a new KKT matrix is first created by using kernel matrix K. According to the properties of the symmetric matrix, the newly constructed matrix has the same eigenvector as the original matrix K; hence, each column of the matrix K can be used as the input sample of the iteration algorithm. After iterative operation, the kernel principal component can be deduced fleetly without the eigen decomposition. Because the kernel matrix is not stored in the algorithm beforehand, it can effectively reduce the computation complexity of the kernel. Especially for a tremendous data scale, the traditional eigen decomposition technology is no longer appropriate, yet the presented method can be solved quickly. The autoregressive moving average (ARMA) time series model and kernel principal component analysis (KPCA) are combined to build the IDKPCA model for dealing with the dynamics and nonlinearity in the industrial process. Eventually, it is applied to monitor faults in the penicillin fermentation process and compared with MKPCA to certify the accuracy and applicability of the proposed method.

An automated COVID-19 detection based on fused dynamic exemplar pyramid feature extraction and hybrid feature selection using deep learning

The new coronavirus disease known as COVID-19 is currently a pandemic that is spread out the whole world. Several methods have been presented to detect COVID-19 disease. Computer vision methods have been widely utilized to detect COVID-19 by using chest X-ray and computed tomography (CT) images. This work introduces a model for the automatic detection of COVID-19 using CT images. A novel handcrafted feature generation technique and a hybrid feature selector are used together to achieve better performance. The primary goal of the proposed framework is to achieve a higher classification accuracy than convolutional neural networks (CNN) using handcrafted features of the CT images. In the proposed framework, there are four fundamental phases, which are preprocessing, fused dynamic sized exemplars based pyramid feature generation, ReliefF, and iterative neighborhood component analysis based feature selection and deep neural network classifier. In the preprocessing phase, CT images are converted into 2D matrices and resized to 256 × 256 sized images. The proposed feature generation network uses dynamic-sized exemplars and pyramid structures together. Two basic feature generation functions are used to extract statistical and textural features. The selected most informative features are forwarded to artificial neural networks (ANN) and deep neural network (DNN) for classification. ANN and DNN models achieved 94.10% and 95.84% classification accuracies respectively. The proposed fused feature generator and iterative hybrid feature selector achieved the best success rate, according to the results obtained by using CT images.

A modified ISAR cross‐range scaling method based on iterative principle component analysis

High-resolution inverse synthetic aperture radar (ISAR) imaging can produce electromagnetic images of a target in the range and cross-range domain. However, to make full use of an ISAR image in target detection and recognition, we need to rescale the image in a homogeneous range and cross-range domain, and further, to estimate the effective rotational velocity (RV) of the target. A precise ISAR image cross-range scaling method is proposed. A candidate RV is obtained based on the bisection method. Then, the effective rotation angle (RA) between two sequential rescaled images is characterised by the RA between the major axes of the images. These axes are extracted by principle component analysis (PCA). A precise estimation of the RV is obtained through iterative PCA and bisection. Simulated and real data experimental results validate the effectiveness of the proposed method.

EPICS application for ITER RH supervisory control system

The purpose of the Remote Handling System is to carry-out remote maintenance of the ITER machine and components where the environment radiation levels are greater than 100 μSv/hr. The general approach to the remote maintenance operations is to remove components from the ITER machine and to replace with new or refurbished components. The refurbishment and waste processing operations take place in the Hot-Cell, also using the RH System. Remote maintenance operations are man-in-the-loop. Trained RH operators, using specialized interfaces to remotely operated RH equipment, carry-out a maintenance activity in the hazardous location. A dedicated suite of control rooms, located in the Personnel Access Control Building (B24), is used to control the RH operations in the Tokamak and Hot-Cell.The Remote Handling (RH) Supervisory Control System provides the basic control infrastructure to integrate the RH equipment systems into a single ITER Plant System operating from the RH control room(s) under the authority of the ITER central control system. The RH Supervisory Control System (RHSCS) has six relatively independent sub-systems fulfilling three major functions: a) to provide basic control infrastructure of the RH maintenance system; b) to support central monitoring and coordination of RH maintenance activities; c) to support management of RH maintenance campaigns.The RHSCS, currently in Final Design phase, comprehends the RH Plant Controller System (RHPC), responsible to provide the functionalities to control RH plant activities at a level suitable for coordination with other ITER activities. This sub-system, developed using the EPICS framework, will allow the connection between the main control room (MCR) and the RH Plant Controller.The system implements the EPICS Channel Access Protocol and it uses a set of process variable to communicate RH Plant System operating states and ITER rooms states between MCR and RH System via CODAC interface. Behind the simple approach based on the HMI created in BOY, the sub-system implements a mechanism to allow the flow-down and application of MCR work program to the RH System.

Optimization of spaceflight millimeter-wave impedance matching networks using laser trimming

AbstractRealizing packaged state-of-the-art performance of monolithic microwave integrated circuits (MMICs) operating at millimeter wavelengths presents significant challenges in terms of electrical interface circuitry and physical construction. For instance, even with the aid of modern electromagnetic simulation tools, modeling the interaction between the MMIC and its package embedding circuit can lack the necessary precision to achieve optimum device performance. Physical implementation also introduces inaccuracies and requires iterative interface component substitution that can produce variable results, is invasive and risks damaging the MMIC. This paper describes a novel method for in situ optimization of packaged millimeter-wave devices using a pulsed ultraviolet laser to remove pre-selected areas of interface circuit metallization. The method was successfully demonstrated through the optimization of a 183 GHz low noise amplifier destined for use on the MetOp-SG meteorological satellite series. An improvement in amplifier output return loss from an average of 12.9 dB to 22.7 dB was achieved across an operational frequency range of 175–191 GHz and the improved circuit reproduced. We believe that our in situ tuning technique can be applied more widely to planar millimeter-wave interface circuits that are critical in achieving optimum device performance.

Design And Optimization Of Floating Point Division And Square Root Using Minimal Device Latency

New microprocessors have become a compulsory feature of floating-point support. In recent years, multiple generations of floating-point units (FPU’s) have been seen by leading architectures. Although the introduction of addition and multiplication has been increasingly effective, the support of division as well as square root will have remained uneven. The types of algorithms employed, as well as the quality and efficiency of the implementations, are drastically different. Here a floating-point division and square root unit is provided that implements a radix-64 floating-point division and a radix-16 floating-point squareroot. Here a floating-point division and square root unit is provided that implements a radix-64 floating-point division and aradix-16 floating-point squareroot. Speculation between successive radix-4 incarnations is used to achieve a reduced timing. In digit-recurrence implementations, there are three separate components: initialization, digital repeats, and rounding. The repetition of the digit is the iterative component and for multiple loops it follows the same logic. The initialization and rounding steps are partly shared by the division and square root, although each has a separate logic for digital iterations. The result is a floating-point divider and square root with low latency, requiring double, single S and half-precision division of standardized operandsand 11, 6, and 4 result cycles, and 15, 8, and 5 cycles of square root cycles. One or two additional cycles are required in the case S of subnormal operand(s) or result

Application of Petersen graph pattern technique for automated detection of heart valve diseases with PCG signals

This work aimed to use machine learning to diagnose four heart valve disease conditions and normal heart sounds. This paper proposed the automated classification of normal, aortic stenosis, mitral valve prolapse, mitral stenosis, and mitral regurgitation using phonocardiogram (PCG) signals.This work proposed a novel graph-based feature generator developed using a graph-based technique called Petersen graph pattern (PGP). In addition, a new decomposition model was proposed using variable-sized overlapping blocks, namely tent pooling (TEP) decomposition. By combining TEP and PGP, a novel multilevel feature generation network was developed. Iterative neighborhood component analysis (INCA) was used to select the features. The selected features were fed to decision tree (DT), linear discriminant (LD), bagged tree (BT), and support vector machine (SVM) classifiers for automated classification into five classes.The proposed method's results yielded 100.0% classification accuracy using the k nearest neighbor (kNN) classifier with a ten-fold cross-validation strategy in classifying the five classes. DT, LD, BT, SVM classifiers yielded an accuracy of 95.10%, 98.30%, 98.60%, and 99.90%, respectively.Our attained high classification accuracy suggests that the proposed PGP and TEP based model can be used for heart sound classification using PCG signals.

A novel Covid-19 and pneumonia classification method based on F-transform

Nowadays, Covid-19 is the most important disease that affects daily life globally. Therefore, many methods are offered to fight against Covid-19. In this paper, a novel fuzzy tree classification approach was introduced for Covid-19 detection. Since Covid-19 disease is similar to pneumonia, three classes of data sets such as Covid-19, pneumonia, and normal chest x-ray images were employed in this study. A novel machine learning model, which is called the exemplar model, is presented by using this dataset. Firstly, fuzzy tree transformation is applied to each used chest image, and 15 images (3-level F-tree is constructed in this work) are obtained from a chest image. Then exemplar division is applied to these images. A multi-kernel local binary pattern (MKLBP) is applied to each exemplar and image to generate features. Most valuable features are selected using the iterative neighborhood component (INCA) feature selector. INCA selects the most distinctive 616 features, and these features are forwarded to 16 conventional classifiers in five groups. These groups are decision tree (DT), linear discriminant (LD), support vector machine (SVM), ensemble, and k-nearest neighbor (k-NN). The best-resulted classifier is Cubic SVM, and it achieved 97.01% classification accuracy for this dataset.

GAD-7, GAD-2, and GAD-mini: Psychometric properties and norms of university students in the United States

ObjectiveThe Generalized Anxiety Disorder (GAD-7 & GAD-2) scales are reliable and valid instruments for assessing generalized anxiety symptoms in the general and clinical populations. However, little attention has been given to the psychometric qualities of GAD-7 and reduced length versions in a diverse sample of young adult college students stratified by sex. Thus, the aims for this study are to test psychometric properties and normative values of GAD-7, GAD-2, and GAD-Mini scales. MethodU.S university students (N = 4128; females n = 2527, males n = 1601) ages 18–26 years completed an online survey composed of the GAD-7, Patient Health Questionnaire (PHQ-2), and demographic questions. ResultsExploratory principal components analysis yielded a one factor solution for GAD-7 across sexes. In reducing scale length, iterative confirmatory principal components analyses stratified by sex revealed a two-item scale (GAD-Mini) with high factor loading items, internal consistency (α ≥ 0.85), and construct validity with PHQ-2 (r ≥ 0.55). Normative data indicate that regardless of whether GAD-7, GAD-2, or GAD-Mini scores were considered, about three-quarters of men and two-thirds of women scored below the reasonable cut-points in screening for GAD. ConclusionFindings from this study may help health care providers and researchers better understand the interpretation of these scales among university students when screening for GAD.

A local knit pattern-based automated fault classification method for the cooling system of the data center

Many automated sound-based fault diagnosis or classification methods have been presented in the literature. A novel automatic fault diagnosis method is presented by using sounds for the cooling system of the data center. A novel feature generator and an iterative feature selector are used together to present an automated data center cooling system (DCCS) fault diagnosing method. A new feature generator is proposed inspired by knitting hence, it is called a local knit pattern (LKP). A multiple pooling based decomposition method is presented as a preprocessor. The LKP generates features from each signal. Iterative neighborhood component analysis (INCA) feature selector selects the most discriminative. Twelve classifiers are calculated in the classification phase. The selected classifiers were achieved greater than 90.0% classification accuracies, and the best-resulted classifier is Quadratic SVM. It reached 96.40% classification accuracy. Results show that new generation automated sound fault diagnosis applications can also be developed as novel sound-based fault detection applications.

A Synchrophasor Data Compression Technique With Iteration-Enhanced Phasor Principal Component Analysis

The phasor data were compressed as separated amplitudes and phases in previous synchrophasor data compression techniques. To utilize the spatial correlation and temporal continuity of synchrophasors for data compression, a phasor principal component analysis (PPCA) in the field of complex numbers is proposed to compress synchrophasors as a whole in this article. Then, an iterative phasor principal components selection method is proposed to achieve PPCA and ensure the accuracy of reconstructed data since the existing eigenvalue-based criteria are not suitable for data compressions. Moreover, the proposed PPCA is enhanced by an iteration-based process to reduce the computation of PPCA. Actual PMU data measured under both a low-frequency oscillation incident and a two-phase short circuit incident conditions are used to verify the performance of PPCA compared with a recent PCA-based compression method. The results demonstrate that PPCA achieves higher compression ratios with better accuracy of reconstructed data, significantly reduced computation, and better real-time performance under both conditions.

Hydrogen permeation and retention in deuterium plasma exposed 316L ITER steel

Abstract Fuel permeation and retention in fusion reactor wall materials are important issues for plasma operation and safety reasons in ITER. The austenitic stainless steel 316L(N)-IG will be used as structural material in the first wall components in ITER. The impact of deuterium plasma exposure on the deuterium permeation and retention was studied. Polished 316L(N)-IG steel samples were deuterium plasma exposed with an ion energy of 200 eV and at two different fluences. Deuterium gas-driven permeation and thermal desorption spectroscopy measurements were performed afterwards. By comparison of the exposed samples to an unexposed sample, it is concluded that the surface roughness due to plasma exposure has no significant influence on the deuterium permeation through the samples. The first results of thermal desorption spectroscopy analysis show that the main release of retained deuterium is between 600 ∘ C and 900 ∘ C and the release temperature increases by increasing the plasma fluence.

Exploring systematic biases, rooting methods and morphological evidence to unravel the evolutionary history of the genus Ficus (Moraceae).

Despite many attempts in the Sanger sequencing era, the phylogeny of fig trees remains unresolved, which limits our ability to analyze the evolution of key traits that may have contributed to their evolutionary and ecological success. We used restriction-site-associated DNA sequencing (c. 420kb) and 102 morphological characters to elucidate the relationships between 70 species of Ficus. To increase phylogenetic information for higher-level relationships, we targeted conserved regions and assembled paired reads into long loci to enable the retrieval of homologous loci in outgroup genomes. We compared morphological and molecular results to highlight discrepancies and reveal possible inference bias. For the first time, we recovered a monophyletic subgenus Urostigma (stranglers) and a clade with all gynodioecious Ficus. However, we show, with a new approach based on iterative principal component analysis, that it is not (and will probably never be) possible to homogenize evolutionary rates and GC content for all taxa before phylogenetic inference. Four competing positions for the root of the molecular tree are possible. The placement of section Pharmacosycea as sister to other fig trees is not supported by morphological data and considered a result of a long-branch attraction artefact to the outgroups. Regarding morphological features and indirect evidence from the pollinator tree of life, the topology that divides Ficus into monoecious versus gynodioecious species appears most plausible. It seems most likely that the ancestor of fig trees was a freestanding tree and active pollination is inferred as the ancestral state, contrary to previous hypotheses. However, ambiguity remains on the ancestral breeding system. Despite morphological plasticity, we advocate restoring a central role to morphology in our understanding of the evolution of Ficus, as it can help detect systematic errors that appear more pronounced with larger molecular datasets.

Automated accurate speech emotion recognition system using twine shuffle pattern and iterative neighborhood component analysis techniques

Speech emotion recognition is one of the challenging research issues in the knowledge-based system and various methods have been recommended to reach high classification capability. In order to achieve high classification performance in speech emotion recognition, a nonlinear multi-level feature generation model is presented by using cryptographic structure. The novelty of this work is the use of cryptographic structure called shuffle box for feature generation and iterative neighborhood component analysis to select the features. The proposed method has three main stages: (i) multi-level feature generation using Tunable Q wavelet transform (TQWT), (ii) twine shuffle pattern (twine-shuf-pat) for feature generation, and (iii) discriminative features are selected using iterative neighborhood component analysis (INCA) and classified. The TQWT is a multi-level wavelet transformation method used to generate high-level, medium-level, and low-level wavelet coefficients. The proposed twine-shuf-pat technique is used to extract the features from the decomposed wavelet coefficients. INCA feature selector is employed to select the clinically significant features. The performance of the obtained model is validated using four speech emotion public databases (RAVDESS Speech, Emo-DB (Berlin), SAVEE, and EMOVO). Our developed twine-shuf-pat and INCA based method yielded 87.43%, 90.09%, 84.79%, and 79.08% classification accuracies using RAVDESS, Emo-DB (Berlin), SAVEE and EMOVO corpora respectively with 10-fold cross-validation strategy. A mixed database is created from four public speech emotion databases which yielded 80.05% classification accuracy. Our obtained speech emotion model is ready to be tested with huge database and can be used in healthcare applications.