Utilization of Transfer Learning Model in Detecting COVID-19 cases from Chest X-Ray Images

Diagnosis of COVID-19 pneumonia using patients’ chest X-Ray images is new but yet important task in the field of medicine. Researchers from different parts of the globe have developed many deep learning models to classify COVID-19. The performance of feature extraction and classifier plays a vital role in the recognizing the different patterns in the image. The pivotal process is the extraction of optimum features from the chest X-Ray images. The main goal of this study is to design an efficient hybrid algorithm that integrates the robustness of MobileNet (using transfer learning approach) to extract features and Support Vector Machine (SVM) to classify COVID-19. Experiments were conducted to test the proposed algorithm and it was found to have a high classification accuracy of 95%.

Utilization of Transfer Learning Model in Detecting COVID-19 Cases From Chest X-Ray Images

Diagnosis of COVID-19 pneumonia using patients’ chest X-Ray images is new but yet important task in the field of medicine. Researchers from different parts of the globe have developed many deep learning models to classify COVID-19. The performance of feature extraction and classifier plays a vital role in the recognizing the different patterns in the image. The pivotal process is the extraction of optimum features from the chest X-Ray images. The main goal of this study is to design an efficient hybrid algorithm that integrates the robustness of MobileNet (using transfer learning approach) to extract features and Support Vector Machine (SVM) to classify COVID-19. Experiments were conducted to test the proposed algorithm and it was found to have a high classification accuracy of 95%.

Enhanced Recognition of Amputated Wrist and Hand Movements by Deep Learning Method Using Multimodal Fusion of Electromyography and Electroencephalography

Motion classification can be performed using biometric signals recorded by electroencephalography (EEG) or electromyography (EMG) with noninvasive surface electrodes for the control of prosthetic arms. However, current single-modal EEG and EMG based motion classification techniques are limited owing to the complexity and noise of EEG signals, and the electrode placement bias, and low-resolution of EMG signals. We herein propose a novel system of two-dimensional (2D) input image feature multimodal fusion based on an EEG/EMG-signal transfer learning (TL) paradigm for detection of hand movements in transforearm amputees. A feature extraction method in the frequency domain of the EEG and EMG signals was adopted to establish a 2D image. The input images were used for training on a model based on the convolutional neural network algorithm and TL, which requires 2D images as input data. For the purpose of data acquisition, five transforearm amputees and nine healthy controls were recruited. Compared with the conventional single-modal EEG signal trained models, the proposed multimodal fusion method significantly improved classification accuracy in both the control and patient groups. When the two signals were combined and used in the pretrained model for EEG TL, the classification accuracy increased by 4.18–4.35% in the control group, and by 2.51–3.00% in the patient group.

KLASIFIKASI REGRESI LOGISTIK MULTINOMIAL DAN FUZZY K-NEAREST NEIGHBOR (FK-NN) DALAM PEMILIHAN METODE KONTRASEPSI DI KECAMATAN BULAKAMBA, KABUPATEN BREBES, JAWA TENGAH

The characteristics of society in choosing contraceptive methods are also the crucial factors for the government to prepare the family planning services needed at Bulakamba District, Brebes Regency, Central Java. In this case, a classification process needs to be done to assist the process of classifying the characteristics of society in the selection of contraceptive methods. Multinomial Logistic Regression classification is good in exploring data information meanwhile Fuzzy K Nearest Neighbor (FK-NN) classification is good for handling big data and noise. These two methods used in this study because they are relevant to the data applied and will be compared their classification accuracy through APER and Press's Q calculations.The classification accuracy results obtained based on the APER calculation for Multinomial Logistic Regression is 88,25% and Fuzzy K Nearest Neighbor (FK-NN) is 88,92%. Meanwhile, the Press's Q value of both methods are 9600,945 and 9518,014 greater than χ 2𝛼,1 which is 3,841, so that it is statistically accurate. Based on the results obtained, it can be concluded that Multinomial Logistic Regression classification method has a better classification accuracy than Fuzzy K Nearest Neighbor (FK-NN) method.

Riemannian classification of single-trial surface EEG and sources during checkerboard and navigational images in humans

Objective Different visual stimuli are classically used for triggering visual evoked potentials comprising well-defined components linked to the content of the displayed image. These evoked components result from the average of ongoing EEG signals in which additive and oscillatory mechanisms contribute to the component morphology. The evoked related potentials often resulted from a mixed situation (power variation and phase-locking) making basic and clinical interpretations difficult. Besides, the grand average methodology produced artificial constructs that do not reflect individual peculiarities. This motivated new approaches based on single-trial analysis as recently used in the brain-computer interface field. Approach We hypothesize that EEG signals may include specific information about the visual features of the displayed image and that such distinctive traits can be identified by state-of-the-art classification algorithms based on Riemannian geometry. The same classification algorithms are also applied to the dipole sources estimated by sLORETA. Main results and significance We show that our classification pipeline can effectively discriminate between the display of different visual items (Checkerboard versus 3D navigational image) in single EEG trials throughout multiple subjects. The present methodology reaches a single-trial classification accuracy of about 84% and 93% for inter-subject and intra-subject classification respectively using surface EEG. Interestingly, we note that the classification algorithms trained on sLORETA sources estimation fail to generalize among multiple subjects (63%), which may be due to either the average head model used by sLORETA or the subsequent spatial filtering failing to extract discriminative information, but reach an intra-subject classification accuracy of 82%.

Multimodal transistors as ReLU activation functions in physical neural network classifiers

Artificial neural networks (ANNs) providing sophisticated, power-efficient classification are finding their way into thin-film electronics. Thin-film technologies require robust, layout-efficient devices with facile manufacturability. Here, we show how the multimodal transistor’s (MMT’s) transfer characteristic, with linear dependence in saturation, replicates the rectified linear unit (ReLU) activation function of convolutional ANNs (CNNs). Using MATLAB, we evaluate CNN performance using systematically distorted ReLU functions, then substitute measured and simulated MMT transfer characteristics as proxies for ReLU. High classification accuracy is maintained, despite large variations in geometrical and electrical parameters, as CNNs use the same activation functions for training and classification.

Analysis of Inducing Factors of Chronic Pulmonary Heart Disease Caused by Chronic Obstructive Pulmonary Disease at High Altitude through Epidemiological Investigation under Intelligent Medicine and Big Data

This study explores the risk factors of chronic pulmonary heart disease (CPHD) induced by plateau chronic obstructive pulmonary disease (COPD) based on intelligent medical treatment and big data of electrocardiogram (ECG) signal. Based on GPU, a wavelet algorithm is introduced to extract features of ECG signal, and it was combined with generalized regression neural network (GRNN) to improve classification accuracy. From June 2018 to December 2020, 10,185 patients diagnosed with COPD in the plateau area by pulmonary function testing, ECG, and chest X-ray at X Hospital are taken as the research objects to evaluate the distribution of CPHD incidence at different ages and altitudes. The running time of GTX780Ti is about 15 times shorter than that of CPU. The accuracy of N detection based on the GPU-accelerated neural network model reached 98.06%. Accuracy (Acc), sensitivity (Se), specificity (Sp), and positive rate (PR) of V were 99.03%, 89.17%, 98.92%, and 93.18%, respectively. The Acc, Se, Sp, and PR of S were 99.54%, 86.22%, 99.74%, and 92.56%, respectively. The GRNN classification accuracy was up to 98%. 19% of COPD patients were diagnosed with CPHD, including 1,409 males (72.82%) and 526 females (36.24%). The highest prevalence of CPHD was 64.60% when the altitude was 1,900–2,499 m, and the prevalence was only 2.43% when the altitude was ≥3,500 m. The highest prevalence of CPHD was 63.77% at the age of 61–70 years, and the lowest prevalence at the age of 15∼20 years was only 0.26%. Therefore, the GPU-based neural network model improved the classification accuracy of ECG signals. Age and altitude were risk factors for CPHD induced by high-altitude COPD, which provided a reference for the prevention, diagnosis, and treatment of CPHD in high-altitude areas.

A Longitudinal Nonparametric Classification Method for Assessing Change in Latent Attributes Over Time

<p>This study proposed a longitudinal Hamming distance discrimination (Long-HDD) method to improve the application of longitudinal cognitive diagnosis in practical teaching by introducing a simple computation and less time-consuming nonparametric classification method—HDD—into longitudinal diagnostic data processing. Compared with the HDD, the proposed method represents correlation or dependence between adjacent time points of the same student using Hamming distance in anticipation of using information from the previous time point to improve the classification accuracy at the current time point. A simulation study was conducted to explore the performance of the proposed method in longitudinal diagnostic data analysis and to compare the performance of the proposed method with the HDD and a parametric longitudinal diagnostic classification model. The findings suggest that (1) the Long-HDD can provide high classification accuracy in longitudinal diagnostic data analysis; (2) compared with the parametric model, the Long-HDD is almost unaffected by sample size and performs better than the parametric model in small sample sizes; and (3) the Long-HDD consumes much less computing time than the parametric model. Overall, the Long-HDD is well suited to analyzing longitudinal diagnostic data and can provide speedy diagnostic feedback due to its convenient computation, which is especially significant in small-scale assessments at the classroom and school levels.</p>

A Longitudinal Nonparametric Classification Method for Assessing Change in Latent Attributes Over Time

<p>This study proposed a longitudinal Hamming distance discrimination (Long-HDD) method to improve the application of longitudinal cognitive diagnosis in practical teaching by introducing a simple computation and less time-consuming nonparametric classification method—HDD—into longitudinal diagnostic data processing. Compared with the HDD, the proposed method represents correlation or dependence between adjacent time points of the same student using Hamming distance in anticipation of using information from the previous time point to improve the classification accuracy at the current time point. A simulation study was conducted to explore the performance of the proposed method in longitudinal diagnostic data analysis and to compare the performance of the proposed method with the HDD and a parametric longitudinal diagnostic classification model. The findings suggest that (1) the Long-HDD can provide high classification accuracy in longitudinal diagnostic data analysis; (2) compared with the parametric model, the Long-HDD is almost unaffected by sample size and performs better than the parametric model in small sample sizes; and (3) the Long-HDD consumes much less computing time than the parametric model. Overall, the Long-HDD is well suited to analyzing longitudinal diagnostic data and can provide speedy diagnostic feedback due to its convenient computation, which is especially significant in small-scale assessments at the classroom and school levels.</p>