Online Data Augmentation Research Articles

A High Accuracy and Real-Time sEMG-Based Hand Gesture Classifier Using LDA-Based Template Matching With Adaptive Majority Vote and Online Data Augmentation

A High Accuracy and Real-Time sEMG-Based Hand Gesture Classifier Using LDA-Based Template Matching With Adaptive Majority Vote and Online Data Augmentation

Multimodal Co-Attention Fusion Network With Online Data Augmentation for Cancer Subtype Classification.

It is an essential task to accurately diagnose cancer subtypes in computational pathology for personalized cancer treatment. Recent studies have indicated that the combination of multimodal data, such as whole slide images (WSIs) and multi-omics data, could achieve more accurate diagnosis. However, robust cancer diagnosis remains challenging due to the heterogeneity among multimodal data, as well as the performance degradation caused by insufficient multimodal patient data. In this work, we propose a novel multimodal co-attention fusion network (MCFN) with online data augmentation (ODA) for cancer subtype classification. Specifically, a multimodal mutual-guided co-attention (MMC) module is proposed to effectively perform dense multimodal interactions. It enables multimodal data to mutually guide and calibrate each other during the integration process to alleviate inter- and intra-modal heterogeneities. Subsequently, a self-normalizing network (SNN)-Mixer is developed to allow information communication among different omics data and alleviate the high-dimensional small-sample size problem in multi-omics data. Most importantly, to compensate for insufficient multimodal samples for model training, we propose an ODA module in MCFN. The ODA module leverages the multimodal knowledge to guide the data augmentations of WSIs and maximize the data diversity during model training. Extensive experiments are conducted on the public TCGA dataset. The experimental results demonstrate that the proposed MCFN outperforms all the compared algorithms, suggesting its effectiveness.

Ultrasonic Weld Quality Inspection Involving Strength Prediction and Defect Detection in Data-Constrained Training Environments.

Welding is an extensively used technique in manufacturing, and as for every other process, there is the potential for defects in the weld joint that could be catastrophic to the manufactured products. Different welding processes use different parameter settings, which greatly impact the quality of the final welded products. The focus of research in weld defect detection is to develop a non-destructive testing method for weld quality assessment based on observing the weld with an RGB camera. Deep learning techniques have been widely used in the domain of weld defect detection in recent times, but the majority of them use, for example, X-ray images. An RGB image-based solution is attractive, as RGB cameras are comparatively inexpensive compared to X-ray image solutions. However, the number of publicly available RGB image datasets for weld defect detection is comparatively lower than that of X-ray image datasets. This work achieves a complete weld quality assessment involving lap shear strength prediction and visual weld defect detection from an extremely limited dataset. First, a multimodal dataset is generated by the fusion of image data features extracted using a convolutional autoencoder (CAE) designed in this experiment and input parameter settings data. The fusion of the dataset reduced lap shear strength (LSS) prediction errors by 34% compared to prediction errors using only input parameter settings data. This is a promising result, considering the extremely small dataset size. This work also achieves visual weld defect detection on the same limited dataset with the help of an ultrasonic weld defect dataset generated using offline and online data augmentation. The weld defect detection achieves an accuracy of 74%, again a promising result that meets standard requirements. The combination of lap shear strength prediction and visual defect detection leads to a complete inspection to avoid premature failure of the ultrasonic weld joints. The weld defect detection was compared against the publicly available image dataset for surface defect detection.

Diseño de una aplicación para detectar covid-19 mediante redes neuronales convolucionales e imágenes de rayos X

This research presents the design of an application to detect covid-19 using convolutional neural networks and X-ray images in two scenarios (covid/Non-covid and covid/Normal/Pneumonia). To avoid overfitting online data augmentation, dropout, batch normalization, and Adam optimizer was used. The three-class network was used as a pre-trained model, tuning only the dense and output layers to obtain the binary model. Additionally, hyper-parameter optimization was used to get dropout probabilities, activation functions, and neurons. The learning rate was adjusted using callbacks to avoid local optimums. Networks were converted to TensorFlow.js format and embedded locally in a hybrid application using Ionic and Capacitor and were deployed through Firebase to help provide diagnostics. The application obtained an accuracy of 98.61% and 96.48% for two and three classes, respectively, achieving higher performance when compared to other proposals (offline models) in the literature and using fewer training parameters.

AraSpot: Arabic Spoken Command Spotting

Spoken keyword spotting (KWS) is the task of identifying a keyword in an audio stream and is widely used in smart devices at the edge in order to activate voice assistants and perform hands-free tasks. The task is daunting as there is a need, on the one hand, to achieve high accuracy while at the same time ensuring that such systems continue to run efficiently on low power and possibly limited computational capabilities devices. This work presents AraSpot for Arabic keyword spotting trained on 40 Arabic keywords, using different online data augmentation, and introducing ConformerGRU model architecture. Finally, we further improve the performance of the model by training a text-to-speech model for synthetic data generation. AraSpot achieved a State-of-the-Art SOTA 99.59% result outperforming previous approaches.

Enhanced image steganalysis through reinforcement learning and generative adversarial networks

With the surging prominence of digital communication platforms, there has been an intensified emphasis on ensuring robust security and privacy measures. Against this backdrop, image steganalysis has emerged as a critical discipline, employing advanced methods to detect clandestine data within image files. At the core of our research is an innovative exploration into image steganalysis using an amalgamation of enhanced reinforcement learning techniques and online data augmentation. This methodology ensures the meticulous identification of concealed data within images. Our design integrates triple parallel dilated convolutions, enabling concurrent extraction of feature vectors from the input images. Once extracted, these vectors are synthesized, paving the way for subsequent classification tasks. To substantiate the efficacy of our approach, we conducted tests on a comprehensive dataset sourced from BossBase 1.01. Furthermore, to discern the influence of transfer learning on our proposed model, the BOWS dataset was employed. Notably, these datasets present a challenge due to its inherent imbalance. To counteract this, we incorporated an advanced Reinforcement Learning (RL) framework. Herein, the dataset samples are envisioned as states in a sequence of interrelated decisions, with the neural network playing the role of the decision-making agent. This agent is then incentivized or reprimanded based on its accuracy in discerning between the minority and majority classes. To bolster our classification capabilities, we innovatively employed data augmentation using images generated by a Generative Adversarial Network (GAN). Concurrently, a regularization mechanism was instituted to alleviate prevalent GAN-related challenges, such as mode collapse and unstable training dynamics. Our experimental outcomes underscore the potency of our methodology. The results highlight a remarkable capability to discern between pristine and steganographic images, registering an average accuracy rate of 85%.

SeismoNet: A proximal policy optimization-based earthquake early warning system using dilated convolution layers and online data augmentation

In seismic safety, Earthquake Early Warning (EEW) systems are indispensable for mitigating earthquake hazards. These systems strive to quickly evaluate earthquake magnitudes to determine which events warrant immediate alerts. Despite their importance, conventional approaches to rapid earthquake classification face significant hurdles, particularly with the skewed data distribution where instances requiring alerts are far less common. This study proposes an EEW method, called SeismoNet, that leverages a 7-second snapshot of three-dimensional seismic waveforms from the China Earthquake Network Center (CENC). SeismoNet incorporates a trio of dilated convolution layers to distill essential features for effective classification, addressing the critical challenge of data imbalance. Our novel integration of the Off-policy Proximal Policy Optimization (Off-policy PPO) algorithm enriches the model by rewarding accurate classifications, refining its sensitivity to less frequent yet critical seismic events. The training approach is conceptualized as a sequence of decision-making steps, with each seismic sample treated as a unique scenario. The model, acting as a decision-making agent, is rewarded or penalized based on its ability to differentiate between less and more common events. To further enhance classification accuracy, we employ a generative adversarial network (GAN) for dynamic data augmentation and a regularization technique to prevent common pitfalls like mode collapse and training instability. The efficacy of SeismoNet is underscored by its superior performance metrics, including an F-measure of 88.14% and a geometric mean of 90.66%, outperforming existing deep-learning solutions, traditional algorithms, and transfer learning methods. Our exhaustive evaluations, including ablation studies that remove key components like dilated convolutions and PPO, affirm the vital contribution of these elements to SeismoNet’s exceptional capability in EEW. SeismoNet can successfully issue timely warnings for significant seismic events, allowing for essential preventative measures and significantly reducing the potential impact on these communities.

One-shot neuroanatomy segmentation through online data augmentation and confidence aware pseudo label

Recently, deep learning-based brain segmentation methods have achieved great success. However, most approaches focus on supervised segmentation, which requires many high-quality labeled images. In this paper, we pay attention to one-shot segmentation, aiming to learn from one labeled image and a few unlabeled images. We propose an end-to-end unified network that joints deformation modeling and segmentation tasks. Our network consists of a shared encoder, a deformation modeling head, and a segmentation head. In the training phase, the atlas and unlabeled images are input to the encoder to get multi-scale features. The features are then fed to the multi-scale deformation modeling module to estimate the atlas-to-image deformation field. The deformation modeling module implements the estimation at the feature level in a coarse-to-fine manner. Then, we employ the field to generate the augmented image pair through online data augmentation. We do not apply any appearance transformations cause the shared encoder could capture appearance variations. Finally, we adopt supervised segmentation loss for the augmented image. Considering that the unlabeled images still contain rich information, we introduce confidence aware pseudo label for them to further boost the segmentation performance. We validate our network on three benchmark datasets. Experimental results demonstrate that our network significantly outperforms other deep single-atlas-based and traditional multi-atlas-based segmentation methods. Notably, the second dataset is collected from multi-center, and our network still achieves promising segmentation performance on both the seen and unseen test sets, revealing its robustness. The source code will be available at https://github.com/zhangliutong/brainseg.

A feature‐enhanced hybrid attention network for traffic sign recognition in real scenes

AbstractCurrently, traffic sign recognition techniques have been brought into the assistive driving of automobiles. However, small traffic sign recognition in real scenes is still a challenging task due to the class imbalance issue and the size limit of the traffic signs. To address the above issues, a feature‐enhanced hybrid attention network is proposed based on YOLOv5s for a small, fast, and accurate traffic sign detector. First, a series of online data augmentation strategies are designed in the preprocessing module for the model training. Second, the hybrid channel and spatial attention module CSAM are integrated into the backbone for a better feature extraction ability. Third, the channel attention module CAM is used in the detection head for a more efficient feature fusion ability. To validate the approach, extensive experiments are conducted based on the Tsinghua‐Tencent 100K dataset. It is found that the novel method achieves state‐of‐the‐art performance with only negligible increases in the model parameter and computational overhead. Specifically, the , parameters, and FLOPs are 85.8%, 7.13 M, and 16.1 G, respectively.

Predicting multifunctional peptides based on a multi-scale ResNet model combined with channel attention mechanisms

<abstract> <p>Peptides are biomolecules composed of multiple amino acid residues connected by peptide bonds, which are widely involved in physiological and biochemical processes in organisms and exhibit diverse functions. In previous studies, the focus was primarily on single-functional peptides. However, research trends indicate that an increasing number of multifunctional peptides are being identified and discovered. To address this challenge, we proposed a deep learning method based on multi-scale ResNet as the backbone combined with a channel attention mechanism (called MSRC) for the identification of multifunctional peptides. Furthermore, the data imbalance problem was solved through the comprehensive use of online data augmentation and confidence-based weighted loss functions. Experimental results demonstrated that the proposed MSRC method achieved an accuracy of 0.688 with an absolute true rate of 0.619. Notably, in predicting minority class peptides such as AEP, AHIVP, and BBP, the MSRC model exhibited heightened sensitivity, showcasing its exceptional capability in addressing issues related to minority classes. By enhancing the precision in identifying and predicting multifunctional peptides, the MSRC method was poised to contribute significantly to advancements in drug discovery, disease treatment, and biotechnology.</p> </abstract>

A lightweight network for photovoltaic cell defect detection in electroluminescence images based on neural architecture search and knowledge distillation

Nowadays, the rapid development of photovoltaic(PV) power stations requires increasingly reliable maintenance and fault diagnosis of PV modules in the field. Due to the effectiveness, convolutional neural network (CNN) has been widely used in the existing automatic defect detection of PV cells. However, the parameters of these CNN-based models are very large, which require stringent hardware resources and it is difficult to be applied in actual industrial projects. To solve these problems, we propose a novel lightweight high-performance model for automatic defect detection of PV cells in electroluminescence(EL) images based on neural architecture search and knowledge distillation. To auto-design an effective lightweight model, we introduce neural architecture search to the field of PV cell defect classification for the first time. Since the defect can be any size, we design a proper search structure of network to better exploit the multi-scale characteristic. To improve the overall performance of the searched lightweight model, we further transfer the knowledge learned by the existing pre-trained large-scale model based on knowledge distillation. Different kinds of knowledge are exploited and transferred, including attention information, feature information, logit information and task-oriented information. Experiments have demonstrated that the proposed model achieves the state-of-the-art performance on the public PV cell dataset of EL images under online data augmentation with accuracy of 91.74% and the parameters of 1.85M. The proposed lightweight high-performance model can be easily deployed to the end devices of the actual industrial projects and retain the accuracy.

Reinforcement Learning and Stochastic Optimization with Deep Learning-Based Forecasting on Power Grid Scheduling

The emission of greenhouse gases is a major contributor to global warming. Carbon emissions from the electricity industry account for over 40% of the total carbon emissions. Researchers in the field of electric power are making efforts to mitigate this situation. Operating and maintaining the power grid in an economic, low-carbon, and stable environment is challenging. To address the issue, we propose a grid dispatching technique that combines deep learning-based forecasting technology, reinforcement learning, and optimization technology. Deep learning-based forecasting can forecast future power demand and solar power generation, while reinforcement learning and optimization technology can make charging and discharging decisions for energy storage devices based on current and future grid conditions. In the optimization method, we simplify the complex electricity environment to speed up the solution. The combination of proposed deep learning-based forecasting and stochastic optimization with online data augmentation is used to address the uncertainty of the dispatch system. A multi-agent reinforcement learning method is proposed to utilize team reward among energy storage devices. At last, we achieved the best results by combining reinforcement and optimization strategies. Comprehensive experiments demonstrate the effectiveness of our proposed framework.

LACTA: A lightweight and accurate algorithm for cherry tomato detection in unstructured environments

Developing cherry tomato detection algorithms for selective harvesting robots faces many challenges due to the influence of various environmental factors such as lighting, water mist, overlap, and occlusion. To this end, we present LACTA, a lightweight and accurate cherry tomato detection algorithm specifically designed for harvesting robot operation in complex environments. Our approach enhances the model’s generalization ability and robustness by selectively expanding the original dataset using a combination of offline and online data augmentation strategies. To effectively capture the small target featuresof cherry tomatoes, we construct an adaptive feature extraction network (AFEN) that focuses on extracting pertinent feature information to enhance the identification ability. Additionally, the proposed cross-layer feature fusion network (CFFN) preservesthe model’s lightweight nature while obtaining richer feature representations. Finally, the integration of efficient decoupled heads (EDH) further enhances the model’s detection performance. Experimental results demonstrate the adaptability and robustness of LACTA, achieving precision, recall, and mAP values of 94 %, 92.5 %, and 97.3 %, respectively. Compared to the original dataset, the offline-online combined data augmentation strategy improves precision, recall, and mAP by 1.6 %, 1.7 %, and 1.1 %, respectively. The AFEN + CFFN network structure significantly reduces computational complexity by 28 % and number of parameters by 72 %. With a compact size of only 2.88 M, the LACTA model can be seamlessly deployed into selective harvesting robots for the automated harvesting of cherry tomatoes in greenhouses. The code is available at https://github.com/ruyounuo/LACTA.

DKFD: Optimizing Common Pediatric Dermatoses Detection with Novel Loss Function and Post-Processing

Using appropriate classification and recognition technology can help physicians make clinical diagnoses and decisions more effectively as a result of the ongoing development of artificial intelligence technology in the medical field. There are currently a number of issues with the detection of common pediatric dermatoses, including the challenge of image collection, the low resolution of some collected images, the intra-class variability and inter-class similarity of disease symptoms, and the mixing of disease symptom detection results. To resolve these problems, we first introduced the Random Online Data Augmentation and Selective Image Super-Resolution Reconstruction (RDA-SSR) method, which successfully avoids overfitting in training, to address the issue of the small dataset and low resolution of collected images, increase the number of images, and improve the image quality. Second, for the issue of an imbalance between difficult and simple samples, which is brought on by the variation within and between classes of disease signs during distinct disease phases. By increasing the loss contribution of hard samples for classification on the basis of the cross-entropy, we propose the DK_Loss loss function for two-stage object detection, allowing the model to concentrate more on the learning of hard samples. Third, in order to reduce redundancy and improve detection precision, we propose the Fliter_nms post-processing method for the intermingling of detection results based on the NMS algorithm. We created the CPD-10 image dataset for common pediatric dermatoses and used the Faster R-CNN network training findings as a benchmark. The experimental results show that the RDA-SSR technique, while needing a similar collection of parameters, can improve mAP by more than 4%. Furthermore, experiments were conducted over the CPD-10 dataset and PASCAL VOC2007 dataset to evaluate the effectiveness of DK_Loss over the two-stage object detection algorithm, and the results of cross-entropy loss-function-based training are used as baselines. The findings demonstrated that, with DK_Loss taken into account, its mAP is 1–2% above the baseline. Furthermore, the experiments confirmed that the Fliter_nms post-processing method can also improve model precision.

Diabetic Retinopathy (DR) Image Synthesis Using DCGAN and Classification of DR Using Transfer Learning Approaches

Diabetic retinopathy (DR) refers to a diabetes complexity that immensely impacts the eyes. This is classified into 5 various stages of the severity in accordance with the international convention. Despite that, optimization of a grading model to have a robust generalizability needs a huge number of balanced training data that is very complicated to gather, especially for greater levels of severity. A vast amount of medical data is complex and has a very high-priced method which requires cooperation between the clinics and researchers. The issue is usually attempted to be figured out with the usage of the traditional methods of data augmentation by making certain changes to images of retina dataset for instance rotation, cropping, size and zooming. In this suggested paper, the latest methods or techniques of data augmentation is exhibited which is called as deep convolutional generative adversial network (DC-GAN) and variational auto encoders (VAE). This is a particular method which is responsible for the production of artificial medical images. In addition to this, to improve DR, we can also take the aid of the classification models which are resnet50, densenet201, InceptionV3 and VGG19 for the purpose of classification of the eye related diseases. The proposed method is depicted on the Asia Pacific Tele-Ophthalmology Society (APTOS)-Blindness dataset. First, the present-day online data augmentation techniques have been utilized, and the artificial images of retina are produced by the ease of DCGAN. Then, a method of classifying is used for both techniques. Ultimately, after the method training which is done by using the real & synthetic clinical images and the outcome exhibits which the proposed model determines every stage or phase of DR and achieve the accuracy of 98.66% with using of ResNet-50 which is contrary to the current existing techniques.

Convolutional neural network with data augmentation for object classification in automotive ultrasonic sensing

Today's low-cost automotive ultrasonic sensors perform distance measurements of obstacles within the close range of vehicles. For future parking assist systems and autonomous driving applications, the performance of the sensors should be further increased. This paper examines the processing of sensor data for the classification of different object classes and traversability of obstacles using a single ultrasonic sensor. The acquisition of raw time signals, transformation into time-frequency images, and classification using machine learning methods are described. Stationary and dynamic measurements at a velocity of 0.5 m/s of various objects have been carried out in a semi-anechoic chamber and on an asphalt parking space. We propose a scalogram-based signal processing chain and a convolutional neural network, which outperforms a LeNet-5-like baseline. Additionally, several methods for offline and online data augmentation are presented and evaluated. It is shown that carefully selected augmentation methods are useful to train more robust models. Accuracies of 90.1% are achieved for the classification of seven object classes in the laboratory and 66.4% in the outdoor environment. Traversability is correctly classified at an accuracy of 96.4% and 91.5%, respectively.

Improving Many-to-Many Neural Machine Translation via Selective and Aligned Online Data Augmentation

Multilingual neural machine translation (MNMT) models are theoretically attractive for low- and zero-resource language pairs with the impact of cross-lingual knowledge transfer. Existing approaches mainly focus on English-centric directions and always underperform compared to their pivot-based counterparts for non-English directions. In this work, we aim to build a many-to-many MNMT system with an emphasis on the quality of non-English directions by exploring selective and aligned online data augmentation algorithms. Based on our findings showing that the augmented synthetic samples are not “the more, the better” we propose selective online back-translation (SOBT) and thoroughly study different selection criteria to pick suitable samples for training. Furthermore, we boost SOBT with cross-lingual online substitution (CLOS) to align token representations and encourage transfer learning. Our intuition is based on the hypothesis that a universal cross-lingual representation leads to a better multilingual translation performance, especially for non-English directions. Comparing to previous state-of-the-art many-to-many MNMT models and conventional pivot-based methods, experiments on IWSLT2014 and OPUS-100 translation benchmarks show that our approach achieves a competitive or even better performance on English-centric directions and achieves up to ∼12 BLEU for non-English directions. All of our models and codes are publicly available.

Internal Wave Signature Extraction From SAR and Optical Satellite Imagery Based on Deep Learning

Internal waves (IWs) are a common characteristic of oceans and serve a crucial role in transmitting energies between large-scale tides and small-scale mixing. This study developed a deep-learning-based method for extracting IW signatures on multiple satellite imagery from synthetic aperture radar (SAR) and optical sensors in sun-synchronous and geostationary orbits with varying spatial resolution. We collected 1115 satellite images, including 116 ENVISAT ASAR (Advanced SAR), 839 MODIS (MODerate-resolution Imaging Spectroradiometer), and 160 Himawari-8 AHI (Advanced Himawari Imager) images with clear IW signatures in the South China Sea (SCS), Sulu Sea, and Celebes Sea for model training. Considering the distinct IW characteristics under different imaging mechanisms, the specially tailored IW Extraction network (IWE-Net) leverages three modifications to improve the accuracy and robustness: online data augmentation, squeeze and excitation blocks, and Matthews correlation coefficient loss. The overall mean Precision, Recall, and F1-score of the IWE-Net model are 85.75%, 85.67%, and 85.71%, demonstrating the model is accurate for IW signature extraction.We also proved the transferability of our method to sea areas worldwide, long-term periods, and Sentinel satellite sensors completely independent of the model training. Globally, the number of IW images and extracted pixels show an obvious tidal-related double-peak distribution. Furthermore, we processed 15461 MODIS images in the northeastern SCS to present a holistic IW distribution map over the past 22 years. An unreported IW silent zone caused by drastic topography changes has been discovered, indicating the great potential of deep learning in information retrieval from remote sensing imagery.

A fast and lightweight detection algorithm for passion fruit pests based on improved YOLOv5

A fast and lightweight detection algorithm is presented to improve the recognition rate and shorten the detection time of passion fruit pest detection. Based on the traditional YOLOv5 model, a new point-line distance loss function is proposed to reduce redundant computations and shorten detection time. Then, the attention module is added to the network for adaptive attention, which can focus on the target object in the channel and space dimensions to improve the detection and identification rates. Finally, the mixup online data augmentation algorithm is added to expand the online training set, which increases the model robustness and prevents over-fitting. The experimental results demonstrate the effectiveness of the proposed model. The results show the mean Average Precision is 96.51%, and the mean detection time is 7.7 ms, fulfilling the requirements of accuracy and real-time. Meanwhile, the proposed model keeps the lightweight characteristics of the traditional YOLOv5, which has a good application prospect in intelligent agriculture.

Food Recognition Using Extreme Learning Machines

Abstract: New pictures of current classes are always arriving in open-ended continuous learning, and new classes are constantly appearing. Due to the great generalization capacity which was before deep learning networks, transfer learning was utilized to identify the most effective network for feature extraction from food photos. During transfer learning, it leverages online data augmentation to make up for the paucity of datasets from other orientations. Experimental research has demonstrated that the model's capability to categorize food photos from various potential orientations has been greatly improved by online data augmentation. Second, this study effort decreases the dimensions of retrieved features by using the Relief F technique to rank features. The redundant characteristics make the model's computations more difficult. The best epoch is achieved by getting a training accuracy of 98 percent and a validation accuracy of 92 percent.