In this study, an effective approach of spectral images based on environmental sound classification using Convolutional Neural Networks (CNN) with meaningful data augmentation is proposed. The ...feature used in this approach is the Mel spectrogram. Our approach is to define features from audio clips in the form of spectrogram images. The randomly selected CNN models used in this experiment are, a 7-layer or a 9-layer CNN learned from scratch. Also, various well-known deep learning structures with transfer learning and with a concept of freezing initial layers, training model, unfreezing the layers, again training the model with discriminative learning are considered. Three datasets, ESC-10, ESC-50, and Us8k are considered. As for the transfer learning methodology, 11 explicit pre-trained deep learning structures are used. In this study, instead of using those available data augmentation schemes for images, we proposed to have meaningful data augmentation by considering variations applied to the audio clips directly. The results show the effectiveness, robustness, and high accuracy of the proposed approach. The meaningful data augmentation can accomplish the highest accuracy with a lower error rate on all datasets by using transfer learning models. Among those used models, The ResNet-152 attained 99.04% for ESC-10 and 99.49% for Us8k datasets. DenseNet-161 gained 97.57% for ESC-50. From our understanding, they are the best-achieved results on these datasets.
Induction motors are important equipment in modern industry. However, the occurrence of fatigue failure following an extended period of operation invariably results in a catastrophic failure. As a ...result, monitoring and diagnosing induction motors is critical to avoiding unplanned shutdowns caused by premature failures. This article aims to develop an effective method for motor fault detection using time-frequency contents of vibration signals and an attention-based convolutional neural network model. First, the vibration signals are collected and labeled into five different categories: normal condition, outer ring fault, inner ring fault, misalignment condition, and broken rotor bar. Then, using the Morlet function, continuous wavelet transform (CWT) converts the vibratory time-series signals to the scalogram feature images. The time-frequency feature images are created after downsampling and converting the measured vibration signals to the frequency domain. These images are then resized and fed into the proposed convolutional attention neural network (CANN) to identify various induction motor failures. The experimental results demonstrate that the suggested model can provide an excellent diagnosis accuracy of 99.43%, significantly better than the state-of-the-art deep learning approaches for fault diagnosis. Moreover, the developed model's robustness is validated against adversarial attacks based on the fast gradient sign method (FGSM) by including white Gaussian noise.
In this paper, a novel approach of the real-time chatter detection in the milling process is presented based on the scalogram of the continuous wavelet transform (CWT) and the deep convolutional ...neural network (CNN). The cutting force signals measured from the stable and unstable cutting conditions were converted into two-dimensional images using the CWT. When chatter occurs, the amount of energy at the tooth passing frequency and its harmonics are shifted toward the chatter frequency. Hence, the scalogram images can serve as input to the CNN framework to identify the stable, transitive, and unstable cutting states. The proposed method does not require the subjective feature-generation and feature-selection procedures, and its classification accuracy of 99.67% is higher than the conventional machine learning techniques described in the existing literature. The result demonstrates that the proposed method can effectively detect the occurrence of chatter.
Detecting road damage quickly and accurately facilitates the ability of road-maintenance agencies to make timely repairs to road surfaces, maintain optimal road conditions, optimize transportation ...safety, and minimize transportation costs. An extensive evaluation of eight deep-learning-based road-damage detection models was conducted in this study. Each model was trained on 9493 images sourced from multiple databases. The 16165 instances of road damage in these images were categorized into five types of damage, including longitudinal crack, horizontal crack, alligator damage, pothole-related crack, and line blurring. Two experiments were conducted that identified two models, single shot multi-box detector (SSD) Inception V2 and faster region-based convolutional neural networks (R-CNN) Inception V2, as providing the best balance of road-damage-detection accuracy and image processing time. These experiments demonstrated that increasing the diversity of image sources improved road-damage-detection model performance. In addition to combining data images from different sources with consistently relabeled damage instances, this study released road-damage image data from the road maintenance agency in Zhubei, Hsinchu County, Taiwan for research and other uses, increasing the limited amount of published image data sources and positively impacting future scholarly research into road damage detection.
In this paper, an adaptive chattering free neural network‐based sliding mode control (ACFN‐SMC) method is proposed for tracking trajectories of redundant parallel manipulators. ACFN‐SMC combines ...adaptive chattering free radial basis function neural networks (RBFN), sliding mode control with online updating the robust term parameters, and a nonlinear compensation item for reducing tracking errors. The stability of the closed‐loop system with modeling uncertainties, frictional uncertainties, and external disturbances is ensured by using the Lyapunov method. The proposed controller has a simple structure and little computation time while securing dynamic performance with expected quality in tracking trajectories of redundant parallel manipulators. In addition, the ACFN‐SMC strategy does not need to know the upper bound of any uncertainties. From the simulation results, it is evident that the proposed control strategy not only has significantly higher robustness capability for uncertainties but also can achieve better chattering elimination when compared with those using existing intelligent control schemes.
Abstract
Coronary artery disease is caused primarily by vessel narrowing. Extraction of the coronary artery area from images is the preferred procedure for diagnosing coronary diseases. In this ...study, a U-Net-based network architecture, 3D Dense-U-Net, was adopted to perform fully automatic segmentation of the coronary artery. The network was applied to 474 coronary computed tomography (CT) angiography scans performed at Wanfang Hospital, Taiwan. Of these, 10% were used for testing. The CT scans were divided into patches of 16 original high-resolution slices. The slices were overlapped between patches to take advantage of surrounding imaging information. However, an imbalance between the foreground and background presents a challenge in smaller-object segmentation such as with coronary arteries. The network was optimized and achieved a promising result when the focal loss concept was adopted. To evaluate the accuracy of the automatic segmentation approach, the dice similarity coefficient (DSC) was calculated, and an existing clinical tool was used. The subjective ratings of three experienced radiologists were used to compare the two ratings. The results show that the proposed approach can achieve a DSC of 0.9691, which is significantly higher than other studies using a deep learning approach. In the main trunk, the results of automatic segmentation agree with those of the clinical tool; they were significantly better in some small branches. In our study, automatic segmentation tool shows high-performance detection in coronary lumen vessels, thereby providing potential power in assisting clinical diagnosis.
This paper introduces a two-element antenna array with dual-sense circular polarization, wideband operation, and high isolation characteristics. The antenna consists of two conventional truncated ...corner patches and an extra layer of metasurface (MS) located above the radiating patches. The overall dimensions of the proposed antenna are 0.92 lambda.sub.0 x 0.73 lambda.sub.0 x 0.05 lambda.sub.0 and the element spacings are 0.02 lambda.sub.0 and 0.39 lambda.sub.0 with respect to edge-to-edge and center-to-center spacings. For validation, measurements on a fabricated antenna prototype are carried out. The measured data demonstrate that the presented MS-based antenna has a wide operating bandwidth of 14.5% with high isolation of better than 26 dB. The excellent performance could be concluded from the results of the investigation, which indicates that the proposed MS-based antenna could be a good candidate for multiple-input multiple-output (MIMO) and full-duplex applications.
Variations of water discharge and sediment load in the Red River basin have received considerable attention due to its drastic reduction during the past several decades. This paper presents a more ...specifically investigating of the seasonal variations in water discharge and sediment load from 1958 to 2021, both before and after the impoundment of all large dam‐reservoirs, using daily observations from the Son Tay hydrological gauging station, the outlet of the Red River system and entry to the delta. Sediment loads have decreased progressively since the early 1990s due to sediment yield reduction and dams in the upper basin, with a reduction of about 91% (from 116 × 106 to 11 × 106 t/year) over the 64‐year observation period. Prior to the impoundment of the Hoa Binh dam‐reservoir in 1988, the hydrological processes in the Red River system exhibited seasonal anomalies (clockwise mode on the hysteresis of rating curve), which implies that sediment load is highly proportional to water discharge and precipitation. The hysteresis loops between mean monthly water discharge and suspended sediment concentration after 1988 were altered by tributary dam‐reservoirs and a phenomenon known as ‘temporal monsoon moving’, which shifted the rating curve from clockwise to counterclockwise mode. Our long‐term analysis indicates that approximately 57.5% and 79% of sediments were trapped during the periods 1989–2008 (after Hoa Binh dam‐reservoir impoundment) and 2009–2021 (a series of new dam‐reservoirs went into operation), respectively, primarily during the high‐discharge months (June–October). Additionally, we concluded that the contribution of climate components (e.g., rainfall) to the dramatic decline in sediment load of the Red River system was less than the human impact.
Since the early 1990s, sediment loads in the Red River system (Vietnam) have steadily reduced by approximately 91%. The Hoa Binh dam's impoundment in 1988 altered hydrological processes, changing their seasonality from clockwise to counterclockwise mode. This shift led to adjustments in rating curves. Notably, the dam effectively trapped 57.5% of sediments from 1989 to 2008 and 79% from 2009 to 2021, showcasing its success in sediment retention during these periods.
Vaginal candidiasis is frequent in women of reproductive age. Accurate identification Candida provides helpful information for successful therapy and epidemiology study; however, there are very ...limited data from the Vietnam have been reported. This study was performed to determine the prevalence, species distribution of yeast causing vaginal discharge and antifungal susceptibility patterns of Candida albicans among symptomatic non-pregnant women of reproductive age. Vaginal discharge samples were collected from 462 women of reproductive age in Hanoi, Vietnam between Sep 2019 and Oct 2020. Vaginal swabs from these patients were examined by direct microscopic examination (10% KOH). CHROMagarTM Candida medium and Sabouraud dextrose agar supplemented with chloramphenicol (0.5 g/l) were used to isolate yeast, and species identification was performed using morphological tests and molecular tools (PCR and sequencing). Antifungal susceptibility testing was determined according to the Clinical and Laboratory Standards Institute guidelines (M27-A3 and M27-S4). The prevalence of vaginal yeast colonization in non-pregnant women was 51.3% of 462 participants. Nine different yeast species were identified. Among these isolates, C. albicans (51.37%) was the most frequent, followed by C. parapsilosis (25.88%), C. glabrata (11.37%), C. tropicalis (4.31%), C. krusei (3.92%), C. africana (1.57%), Saccharomyces cerevisiae (0.78%), C. nivariensis (1 isolates, 0.39%), and C. lusitaniae (1 isolates, 0.39%), respectively. Among C. albicans, all 46 isolates were 100% susceptible to micafungin, caspofungin, and miconazole. The susceptibility rates to amphotericine B, 5-flucytosine, fluconazole, itraconazole and voriconazole were 95.65, 91.30, 91.30, 82.61 and 86.95%, respectively. The prevalence of VVC among symptomatic non-pregnant women of reproductive age in Vietnam was higher than many parts of the world. The high frequency of non-albicans Candida species, which were often more resistant to antifungal agents, was a notable feature. Resistance rates of vaginal C. albicans isolates to antifungal agents was low. Our findings suggest that continued surveillance of changes in species distribution and susceptibility to antifungals should be routinely screened and treated.
IL(interleukin)-6 is a multifunctional cytokine crucial for immunological, hematopoiesis, inflammation, and bone metabolism. Strikingly, IL-6 has been shown to significantly contribute to the ...initiation of cytokine storm—an acute systemic inflammatory syndrome in Covid-19 patients. Recent study has showed that blocking the IL-6 signaling pathway with an anti-IL-6 receptor monoclonal antibody (mAb) can reduce the severity of COVID-19 symptoms and enhance patient survival. However, the mAb has several drawbacks, such as high cost, potential immunogenicity, and invasive administration due to the large-molecule protein product. Instead, these issues could be mitigated using small molecule IL-6 inhibitors, but none are currently available. This study aimed to discover IL-6 inhibitors based on the PPI with a novel camelid Fab fragment, namely 68F2, in a crystal protein complex structure (PDB ID: 4ZS7). The pharmacophore models and molecular docking were used to screen compounds from DrugBank databases. The oral bioavailability of the top 24 ligands from the screening was predicted by the SwissAMDE tool. Subsequently, the selected molecules from docking and MD simulation illustrated a promising binding affinity in the formation of stable complexes at the active binding pocket of IL-6. Binding energies using the MM-PBSA technique were applied to the top 4 hit compounds. The result indicated that DB08402 and DB12903 could form strong interactions and build stable protein–ligand complexes with IL-6. These potential compounds may serve as a basis for further developing small molecule IL-6 inhibitors in the future.
Graphical abstract