Set Of Training Images Research Articles

Plant Detection in RGB Images from Unmanned Aerial Vehicles Using Segmentation by Deep Learning and an Impact of Model Accuracy on Downstream Analysis.

Crop field monitoring using unmanned aerial vehicles (UAVs) is one of the most important technologies for plant growth control in modern precision agriculture. One of the important and widely used tasks in field monitoring is plant stand counting. The accurate identification of plants in field images provides estimates of plant number per unit area, detects missing seedlings, and predicts crop yield. Current methods are based on the detection of plants in images obtained from UAVs by means of computer vision algorithms and deep learning neural networks. These approaches depend on image spatial resolution and the quality of plant markup. The performance of automatic plant detection may affect the efficiency of downstream analysis of a field cropping pattern. In the present work, a method is presented for detecting the plants of five species in images acquired via a UAV on the basis of image segmentation by deep learning algorithms (convolutional neural networks). Twelve orthomosaics were collected and marked at several sites in Russia to train and test the neural network algorithms. Additionally, 17 existing datasets of various spatial resolutions and markup quality levels from the Roboflow service were used to extend training image sets. Finally, we compared several texture features between manually evaluated and neural-network-estimated plant masks. It was demonstrated that adding images to the training sample (even those of lower resolution and markup quality) improves plant stand counting significantly. The work indicates how the accuracy of plant detection in field images may affect their cropping pattern evaluation by means of texture characteristics. For some of the characteristics (GLCM mean, GLRM long run, GLRM run ratio) the estimates between images marked manually and automatically are close. For others, the differences are large and may lead to erroneous conclusions about the properties of field cropping patterns. Nonetheless, overall, plant detection algorithms with a higher accuracy show better agreement with the estimates of texture parameters obtained from manually marked images.

Variability of interobserver interpretation of selected helminth ova in the development of a training image set.

Diagnosis of soil-transmitted helminthiasis and schistosomiasis for surveillance relies on microscopic detection of ova in Kato-Katz (KK) prepared slides. Artificial intelligence (AI)-based platforms for parasitic eggs may be developed using a robust image set with defined labels by reference microscopists. This study aimed to determine interobserver variability among reference microscopists in identifying parasite ova. Images of parasite ova taken from KK prepared slides were labelled according to species by two reference microscopists (M1 and M2). A third reference microscopist (M3) labelled images when the first two did not agree. Frequency, percent agreement, κ statistics and variability score (VS) were generated for analysis. M1 and M2 agreed on 89.24% of the labelled images (κ=0.86, p<0.001). M3 had agreement with M1 and M2 (κ=0.30, p<0.001 and κ=0.28, p<0.001), resolving 89.29% of disagreement between them. The labelling of Schistosoma japonicum had the highest VS (κ=0.487, p=0.101) among the targeted ova. Reference microscopists were able to reliably reach consensus in 99.0% of the dataset. Training AI using this image set may provide more objective and reliable readings compared with that of reference microscopists.

METHOD OF INTEGRAL TRANSFORMATIONS IN SOLVING THE PROBLEM OF DETECTING SMALL VEHICLES IN IMAGES

The article proposes a method for forming a set of features on images based on three integral transformations: the Radon transform, the Steklov function and the Fourier transform. Using a discrete analog of these transformations, the values that form a set of features are calculated. Depending on the transformation parameters, the number of features can be changed. We selected the values of these parameters such that the number of features is 903. The use of this approach in solving the problem of detecting small-sized, and therefore poorly visible, vehicles in video images is shown. In addition, we have developed an improved version of the least squares method based on processing the obtained features using some transformations of the labels of the training set of images. The main essence of this method is to perform an affine transformation of the label value into a small neighborhood of its original value. A priori estimates show a decrease in the approximation error using the least squares method. The paper also shows a comparison of the developed approach with convolutional neural networks. This comparison allows us to say that it is not much inferior to them in such an indicator as the percentage of correct predictions. At the same time, in terms of prediction execution time, the method presented in the article works 3-4 times faster depending on the model used. In the practical part of the work, software tools from the OpenCV, Keras and Scikit-learn libraries were used.

Optimising seismic imaging design parameters via bilevel learning

Abstract Full waveform inversion (FWI) is a standard algorithm in seismic imaging. It solves the inverse problem of computing a model of the physical properties of the earth’s subsurface by minimising the misfit between actual measurements of scattered seismic waves and numerical predictions of these, with the latter obtained by solving the (forward) wave equation. The implementation of FWI requires the a priori choice of a number of ‘design parameters’, such as the positions of sensors for the actual measurements and one (or more) regularisation weights. In this paper we describe a novel algorithm for determining these design parameters automatically from a set of training images, using a (supervised) bilevel learning approach. In our algorithm, the upper level objective function measures the quality of the reconstructions of the training images, where the reconstructions are obtained by solving the lower level optimisation problem—in this case FWI. Our algorithm employs (variants of) the BFGS quasi-Newton method to perform the optimisation at each level, and thus requires the repeated solution of the forward problem—here taken to be the Helmholtz equation. This paper focuses on the implementation of the algorithm. The novel contributions are: (i) an adjoint-state method for the efficient computation of the upper-level gradient; (ii) a complexity analysis for the bilevel algorithm, which counts the number of Helmholtz solves needed and shows this number is independent of the number of design parameters optimised; (iii) an effective preconditioning strategy for iteratively solving the linear systems required at each step of the bilevel algorithm; (iv) a smoothed extraction process for point values of the discretised wavefield, necessary for ensuring a smooth upper level objective function. The algorithm also uses an extension to the bilevel setting of classical frequency-continuation strategies, helping avoid convergence to spurious stationary points. The advantage of our algorithm is demonstrated on a problem derived from the standard Marmousi test problem.

Illuminating Entomological Dark Matter with DNA Barcodes in an Era of Insect Decline, Deep Learning, and Genomics.

Most insects encountered in the field are initially entomological dark matter in that they cannot be identified to species while alive. This explains the enduring quest for efficient ways to identify collected specimens. Morphological tools came first but are now routinely replaced or complemented with DNA barcodes. Initially too expensive for widespread use, these barcodes have since evolved into powerful tools for specimen identification and sorting, given that the evolution of sequencing approaches has dramatically reduced the cost of barcodes, thus enabling decentralized deployment across the planet. In this article, we review how DNA barcodes have become a key tool for accelerating biodiversity discovery and analyzing insect communities through both megabarcoding and metabarcoding in an era of insect decline. We predict that DNA barcodes will be particularly important for assembling image training sets for deep learning algorithms, global biodiversity genomics, and functional analysis of insect communities.Review in Advance first posted online on October 1, 2024. Updated on November 5, 2024. Changes may still occur before final publication.

Advanced YOLOv8-Based Efficient Detection Method for Sugarcane Stem Nodes

The precise identification of sugarcane stem nodes is crucial for intelligent seed cutting, planting placement, sugarcane garden production management process optimization, yield improvement, and economic benefits. However, efficiency, model complexity, and real-time performance are still issues with the sugarcane stem node detection methods are currently in use. This study decided to visually detect distinguish between sugarcane stem nodes in a structured scene using the advanced YOLOv8 model in order to address this issue. For the purpose of to create an image training set and a test set, a field sugarcane image collection experiment was first designed. The collected sugarcane images were manually labeled. The YOLOv8 network was then utilized as the sugarcane stem node detection model to find the ideal hyperparameter combination and train the model. Finally, field-based recognition experiments are carried out to verify the method's effectiveness and efficiency. Experimental results show that the precision, recall, mAP, single-frame inference time and model size of our method on the test set are 0.973, 0.958, 0.974,19.80 ms and 6.30 MB respectively. Compared with the Edgeyolo_S_Coco network and Edgeyolo_Tiny network, the mAP value of the YOLOv8_n network has increased by 1.70% and 1.30% respectively, the single-frame inference time has been reduced by 4.71 ms and 1.50 ms respectively, and the model size has been reduced by 33.70 MB and 17.50 MB respectively. This method has advantages in detection performance and generalization ability, and can effectively meet the requirements for algorithm accuracy and model complexity in outdoor environments, providing solid technical support for sugarcane harvesting and planting in intelligent agricultural production.

Detailed-based dictionary learning for low-light image enhancement using camera response model for industrial applications

Images captured in low-light environments are severely degraded due to insufficient light, which causes the performance decline of both commercial and consumer devices. One of the major challenges lies in how to balance the image enhancement properties of light intensity, detail presentation, and colour integrity in low-light enhancement tasks. This study presents a novel image enhancement framework using a detailed-based dictionary learning and camera response model (CRM). It combines dictionary learning with edge-aware filter-based detail enhancement. It assumes each small detail patch could be sparsely characterised in the over-complete detail dictionary that was learned from many training detail patches using iterative ℓ1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${{\\ell}}_{1}$$\\end{document}-norm minimization. Dictionary learning will effectively address several enhancement concerns in the progression of detail enhancement if we remove the visibility limit of training detail patches in the enhanced detail patches. We apply illumination estimation schemes to the selected CRM and the subsequent exposure ratio maps, which recover a novel enhanced detail layer and generate a high-quality output with detailed visibility when there is a training set of higher-quality images. We estimate the exposure ratio of each pixel using illumination estimation techniques. The selected camera response model adjusts each pixel to the desired exposure based on the computed exposure ratio map. Extensive experimental analysis shows an advantage of the proposed method that it can obtain enhanced results with acceptable distortions. The proposed research article can be generalised to address numerous other similar problems, such as image enhancement for remote sensing or underwater applications, medical imaging, and foggy or dusty conditions.

An improved 3D-UNet-based brain hippocampus segmentation model based on MR images

ObjectiveAccurate delineation of the hippocampal region via magnetic resonance imaging (MRI) is crucial for the prevention and early diagnosis of neurosystemic diseases. Determining how to accurately and quickly delineate the hippocampus from MRI results has become a serious issue. In this study, a pixel-level semantic segmentation method using 3D-UNet is proposed to realize the automatic segmentation of the brain hippocampus from MRI results. Methods: Two hundred three-dimensional T1-weighted (3D-T1) nongadolinium contrast-enhanced magnetic resonance (MR) images were acquired at Hangzhou Cancer Hospital from June 2020 to December 2022. These samples were divided into two groups, containing 175 and 25 samples. In the first group, 145 cases were used to train the hippocampus segmentation model, and the remaining 30 cases were used to fine-tune the hyperparameters of the model. Images for twenty-five patients in the second group were used as the test set to evaluate the performance of the model. The training set of images was processed via rotation, scaling, grey value augmentation and transformation with a smooth dense deformation field for both image data and ground truth labels. A filling technique was introduced into the segmentation network to establish the hippocampus segmentation model. In addition, the performance of models established with the original network, such as VNet, SegResNet, UNetR and 3D-UNet, was compared with that of models constructed by combining the filling technique with the original segmentation network. Results: The results showed that the performance of the segmentation model improved after the filling technique was introduced. Specifically, when the filling technique was introduced into VNet, SegResNet, 3D-UNet and UNetR, the segmentation performance of the models trained with an input image size of 48 × 48 × 48 improved. Among them, the 3D-UNet-based model with the filling technique achieved the best performance, with a Dice score (Dice score) of 0.7989 ± 0.0398 and a mean intersection over union (mIoU) of 0.6669 ± 0.0540, which were greater than those of the original 3D-UNet-based model. In addition, the oversegmentation ratio (OSR), average surface distance (ASD) and Hausdorff distance (HD) were 0.0666 ± 0.0351, 0.5733 ± 0.1018 and 5.1235 ± 1.4397, respectively, which were better than those of the other models. In addition, when the size of the input image was set to 48 × 48 × 48, 64 × 64 × 64 and 96 × 96 × 96, the model performance gradually improved, and the Dice scores of the proposed model reached 0.7989 ± 0.0398, 0.8371 ± 0.0254 and 0.8674 ± 0.0257, respectively. In addition, the mIoUs reached 0.6669 ± 0.0540, 0.7207 ± 0.0370 and 0.7668 ± 0.0392, respectively. Conclusion: The proposed hippocampus segmentation model constructed by introducing the filling technique into a segmentation network performed better than models built solely on the original network and can improve the efficiency of diagnostic analysis.

Thermal image visualization using multi-discriminator CycleGAN with unpaired thermal–visible image training set

Thermal imaging utilizes the differences in thermal radiation within a scene to capture images, effectively compensating for the limited imaging capabilities of visible-light cameras in low-light environments. In order to further enhance thermal imaging, we propose a novel approach that transforms the visualization of thermal images into an image conversion task. Our method, named TIVNet (Thermal Images Visualization Network), is based on a multi-discriminator cycle-consistent adversarial network (CycleGAN) and operates in the YUV color space to accurately colorize and represent thermal infrared images. The utilization of color and texture discriminators in our framework ensures that the converted images exhibit appropriate color styles and capture fine details, respectively. In the generator, we employed a Dense Residual Module (DRM) to facilitate the reuse of features and enhance the flow of information. By utilizing the DRM, we aim to enhance the overall performance and efficiency of the generator network. Additionally, we incorporated the Dual-channel Self-Attention Module(DCSA) to enhance the feature representation. By leveraging self-attention, the generator can effectively learn and exploit the inherent relationships between different regions, leading to improved feature representation and, consequently, more accurate colorization and representation of thermal infrared images. Notably, our proposed method leverages unsupervised learning, eliminating the need for a fully paired thermal infrared-visible image dataset. Through extensive experimentation on publicly available datasets as well as our own, we demonstrate that our approach outperforms state-of-the-art methods in thermal image visualization. Furthermore, the converted images produced by TIVNet exhibit a high level of realism, thereby enhancing the visual impact of thermal imaging. This improvement is particularly beneficial for human perception and subsequent target recognition tasks. Our findings suggest that the application of our method yields superior results both quantitatively and qualitatively, showcasing its potential for advancing thermal imaging capabilities.

Autoencoding Labeled Interpolator, Inferring Parameters from Image and Image from Parameters

The Event Horizon Telescope (EHT) provides an avenue to study black hole accretion flows on event-horizon scales. Fitting a semianalytical model to EHT observations requires the construction of synthetic images, which is computationally expensive. This study presents an image generation tool in the form of a generative machine-learning model, which extends the capabilities of a variational autoencoder. This tool can rapidly and continuously interpolate between a training set of images and can retrieve the defining parameters of those images. Trained on a set of synthetic black hole images, our tool showcases success in interpolating both black hole images and their associated physical parameters. By reducing the computational cost of generating an image, this tool facilitates parameter estimation and model validation for observations of black hole systems.

Garbage In [formula omitted] Garbage Out: Exploring GAN Resilience to Image Training Set Degradations

Generative Adversarial Networks (GANs) have received immense attention in recent years due to their ability to capture complex, high-dimensional data distributions without the need for extensive labeling. Since their conception in 2014, a wide array of GAN variants have been proposed featuring alternative architectures, optimizers, and loss functions with the goal of improving performance and training stability. This manuscript focuses on quantifying the resilience of a GAN architecture to specific modes of image degradation. We conduct systematic experimentation to empirically determine the effects of 10 fundamental image degradation modes, applied to the training image dataset, on the Fréchet inception distance (FID) of images generated by a conditional deep convolutional GAN (cDCGAN). We find that at the α=0.05 level, brightening, darkening, and blurring are statistically significantly more detrimental to the resulting GAN image quality than removing the degraded data completely, while other degradations are typically safe to keep in training datasets. Additionally, we find that in the case of randomized partial occlusion, the FID of the resulting GAN images approaches that of the degraded training set for increasing levels of occlusion, with the surprising result that GAN FID performance is equal to that of the training set at 75% degradation.

Online electronic signature recognition using sparse classification techniques that support neural models

With the rapid development of information technology, electronic signature plays an increasingly important role in people’s production practice. However, there are a large number of hackers maliciously stealing information in the network. In order to avoid this phenomenon, we urgently need to strengthen the research on online electronic signature recognition technology. Based on the sparse classification technology of neural model, this paper constructs an online electronic signature recognition model by using convolutional neural network and sparse classification technology. We first extract the local features of online electronic signatures, construct feature vectors and perform sparse representation. Sub-model we construct a scheme for online electronic signature recognition based on neural models and sparse classification techniques using a combination of algorithms. We first extract the local features of online electronic signatures, construct feature vectors and perform sparse representation. At the same time, the features in the training image set are extracted, local feature sets are constructed, feature dictionaries are created, and the vectors in the feature dictionaries are matched with the global sparse vectors constructed by the electronic signatures to be detected, and the matching results are finally obtained. At the same time, the features in the training image set are extracted, the local feature set is constructed, the feature dictionary is created, and the vector in the feature dictionary is matched with the global sparse vector constructed by the electronic signature to be detected, and finally the matching result is obtained. In order to verify the accuracy of the model, we first extracted 1000 respondents for online e-signature recognition experimental results show that the recognition accuracy of online e-signature has been significantly improved. Finally, in order to determine the optimal number of training sets for the model constructed in this experiment, we analyzed the correlation between training and sample size and recognition accuracy. Finally, it was concluded that the recognition accuracy increased with the increase of the number of training samples. Electronic signatures can quickly examine the signature results, and electronic signature recognition can be used to fix and tamper-proof evidence to enhance the security and trustworthiness of signatures, and it is imperative to improve the security of electronic signatures. In this paper, we study online electronic signature recognition technology, using neural model and sparse classification to construct an efficient and accurate recognition model. Experiments show that the model is effective and the number of training samples affects the recognition accuracy. This paper provides a new approach for the development of this technique. When the training samples are greater than 1300, the recognition accuracy is stable at 95%. This research has certain theoretical and practical significance, and promotes the rapid development of online electronic signature recognition.

That’s BAD: blind anomaly detection by implicit local feature clustering

Recent studies on visual anomaly detection (AD) of industrial objects/textures have achieved quite good performance. They consider an unsupervised setting, specifically the one-class setting, in which we assume the availability of a set of normal (i.e., anomaly-free) images for training. In this paper, we consider a more challenging scenario of unsupervised AD, in which we detect anomalies in a given set of images that might contain both normal and anomalous samples. The setting does not assume the availability of known normal data and thus is completely free from human annotation, which differs from the standard AD considered in recent studies. For clarity, we call the setting blind anomaly detection (BAD). We show that BAD can be converted into a local outlier detection problem and propose a novel method named PatchCluster that can accurately detect image- and pixel-level anomalies. Experimental results show that PatchCluster shows a promising performance without the knowledge of normal data, even comparable to the SOTA methods applied in the one-class setting needing it.

Learning-based surface deformation recovery for large radio telescope antennas

Abstract The surface deformation of the main reflector in a large radio telescope is closely related to its working efficiency, which is important for some astronomical science studies. Here, we present a deep learning-based surface deformation recovery framework using non-interferometric intensity measurements as input. The recurrent convolutional neural network (RCNN) is developed to establish the inverse mapping relationship between the surface deformation of the main reflector and the intensity images at the aperture plane and at a near-field plane. Meanwhile, a physical forward propagation model is adopted to generate a large amount of data for pre-training in a computationally efficient manner. Then, the inverse mapping relationship is adjusted and improved by transfer learning using experimental data, which achieves a 15-fold reduction in the number of training image sets required, which is helpful to facilitate the practical application of deep learning in this field. In addition, the RCNN model can be trained as a denoiser, and it is robust to the axial positioning error of the measuring points. It is also promising to extend this method to the study of adaptive optics.

Improving the perception of low-light enhanced images.

Improving images captured under low-light conditions has become an important topic in computational color imaging, as it has a wide range of applications. Most current methods are either based on handcrafted features or on end-to-end training of deep neural networks that mostly focus on minimizing some distortion metric -such as PSNR or SSIM- on a set of training images. However, the minimization of distortion metrics does not mean that the results are optimal in terms of perception (i.e. perceptual quality). As an example, the perception-distortion trade-off states that, close to the optimal results, improving distortion results in worsening perception. This means that current low-light image enhancement methods -that focus on distortion minimization- cannot be optimal in the sense of obtaining a good image in terms of perception errors. In this paper, we propose a post-processing approach in which, given the original low-light image and the result of a specific method, we are able to obtain a result that resembles as much as possible that of the original method, but, at the same time, giving an improvement in the perception of the final image. More in detail, our method follows the hypothesis that in order to minimally modify the perception of an input image, any modification should be a combination of a local change in the shading across a scene and a global change in illumination color. We demonstrate the ability of our method quantitatively using perceptual blind image metrics such as BRISQUE, NIQE, or UNIQUE, and through user preference tests.

Dual contrastive learning based image-to-image translation of unstained skin tissue into virtually stained H&E images

Staining is a crucial step in histopathology that prepares tissue sections for microscopic examination. Hematoxylin and eosin (H&E) staining, also known as basic or routine staining, is used in 80% of histopathology slides worldwide. To enhance the histopathology workflow, recent research has focused on integrating generative artificial intelligence and deep learning models. These models have the potential to improve staining accuracy, reduce staining time, and minimize the use of hazardous chemicals, making histopathology a safer and more efficient field. In this study, we introduce a novel three-stage, dual contrastive learning-based, image-to-image generative (DCLGAN) model for virtually applying an "H&E stain" to unstained skin tissue images. The proposed model utilizes a unique learning setting comprising two pairs of generators and discriminators. By employing contrastive learning, our model maximizes the mutual information between traditional H&E-stained and virtually stained H&E patches. Our dataset consists of pairs of unstained and H&E-stained images, scanned with a brightfield microscope at 20 × magnification, providing a comprehensive set of training and testing images for evaluating the efficacy of our proposed model. Two metrics, Fréchet Inception Distance (FID) and Kernel Inception Distance (KID), were used to quantitatively evaluate virtual stained slides. Our analysis revealed that the average FID score between virtually stained and H&E-stained images (80.47) was considerably lower than that between unstained and virtually stained slides (342.01), and unstained and H&E stained (320.4) indicating a similarity virtual and H&E stains. Similarly, the mean KID score between H&E stained and virtually stained images (0.022) was significantly lower than the mean KID score between unstained and H&E stained (0.28) or unstained and virtually stained (0.31) images. In addition, a group of experienced dermatopathologists evaluated traditional and virtually stained images and demonstrated an average agreement of 78.8% and 90.2% for paired and single virtual stained image evaluations, respectively. Our study demonstrates that the proposed three-stage dual contrastive learning-based image-to-image generative model is effective in generating virtual stained images, as indicated by quantified parameters and grader evaluations. In addition, our findings suggest that GAN models have the potential to replace traditional H&E staining, which can reduce both time and environmental impact. This study highlights the promise of virtual staining as a viable alternative to traditional staining techniques in histopathology.

Information-theoretical analysis of the neural code for decoupled face representation.

Processing faces accurately and efficiently is a key capability of humans and other animals that engage in sophisticated social tasks. Recent studies reported a decoupled coding for faces in the primate inferotemporal cortex, with two separate neural populations coding for the geometric position of (texture-free) facial landmarks and for the image texture at fixed landmark positions, respectively. Here, we formally assess the efficiency of this decoupled coding by appealing to the information-theoretic notion of description length, which quantifies the amount of information that is saved when encoding novel facial images, with a given precision. We show that despite decoupled coding describes the facial images in terms of two sets of principal components (of landmark shape and image texture), it is more efficient (i.e., yields more information compression) than the encoding in terms of the image principal components only, which corresponds to the widely used eigenface method. The advantage of decoupled coding over eigenface coding increases with image resolution and is especially prominent when coding variants of training set images that only differ in facial expressions. Moreover, we demonstrate that decoupled coding entails better performance in three different tasks: the representation of facial images, the (daydream) sampling of novel facial images, and the recognition of facial identities and gender. In summary, our study provides a first principle perspective on the efficiency and accuracy of the decoupled coding of facial stimuli reported in the primate inferotemporal cortex.

Unsupervised domain adaptation with local structure preservation for colon histopathological image classification

The histopathological image classification method, based on deep learning, can be used to assist pathologists in cancer recognition in colon histopathology. The popularization of automatic and accurate histopathological image classification methods in this way is of great significance. However, smaller medical institutions with limited medical resources may lack colon histopathology image training sets with reliable labeled information; thus they may be unable to meet the needs of deep learning for many labeled training samples. Therefore, in this paper, the colon histopathological image set with rich label information from a certain medical institution is taken as the source domain; the colon histopathological image set from a smaller medical institution with limited medical resources is taken as the target domain. Considering the potential differences between histopathological images obtained by different institutions, this paper proposes a classification learning framework, namely unsupervised domain adaptation with local structure preservation for colon histopathological image classification, which can learn an adaptive classifier by performing distribution alignment and preserving intra-domain local structure to predict the labels of the colon histopathological images from institutions with lower medical resources. Extensive experiments demonstrate that the proposed framework shows significant improvement in accuracy and specificity of colon histopathological images without reliable labeled information compared to models without unsupervised domain adaptation. Specifically, in an affiliated hospital in Fuyang City, Anhui Province, the classification accuracy of benign and malignant colon histopathological images reaches 96.21%. The results of comparative experiments also show promising classification performance of our method in comparison with other unsupervised domain adaptation methods.

Identification of composite power quality disturbances based on relative position matrix

With the integration of large-scale nonlinear loads and distributed power sources into the grid, composite power quality disturbances (PQDs) events are becoming increasingly common, which significantly degrade the quality of power supply. Therefore, this paper focuses on studying the accurate classification of composite PQDs to mitigate the risk of power quality deterioration. However, traditional classification methods perform barely satisfactory in terms of accuracy and robustness in the classification of PQDs. To address these issues, this paper proposes a method for recognizing composite PQDs based on relative position matrix (RPM). Initially, utilizing the RPM method, the initial one-dimensional PQD time series data is transformed into two-dimensional image data while preserving its high-frequency characteristics. This process results in the creation of an informative and feature-rich image training set. Subsequently, an end-to-end framework for PQDs classification was developed. The framework utilizes convolutional neural networks to automatically extract multi-scale spatial and temporal features from image data. This design aims to automate the classification of composite PQDs, eliminating the need for labor-intensive manual signal processing and feature extraction. This integration ensures a more accurate and robust classification. Finally, the proposed method is tested on a case involving 30 types of PQDs at varying noise levels and compared with existing power quality disturbance classification methods, and results show that the proposed method has better performance than the previously established methods.

Neural network approach for shape-based euhedral pyrite identification in X-ray CT data with adversarial unsupervised domain adaptation

We explore an attenuation and shape-based identification of euhedral pyrites in high-resolution X-ray Computed Tomography (XCT) data using deep neural networks. To deal with the scarcity of annotated data we generate a complementary training set of synthetic images. To investigate and address the domain gap between the synthetic and XCT data, several deep learning models, with and without domain adaption, are trained and compared. We find that a model trained on a small set of human annotations, while displaying over-fitting, can rival the human annotators. The unsupervised domain adaptation approaches are successful in bridging the domain gap, which significantly improves their performance. A domain-adapted model, trained on a dataset that fuses synthetic and real data, is the overall best-performing model. This highlights the possibility of using synthetic datasets for the application of deep learning in mineralogy.