Search

As a list of remotely sensed data sources is available, the effective processing of remote sensing images is of great significance in practical applications in various fields. This paper proposes a new lightweight network to solve the problem of remote sensing image processing by using the method of deep learning. Specifically, the proposed model employs ShuffleNet V2 as the backbone network, appropriately increases part of the convolution kernels to improve the classification accuracy of the network, and uses the maximum overlapping pooling layer to enhance the detailed features of the input images. Finally, Squeeze and Excitation (SE) blocks are introduced as the attention mechanism to improve the architecture of the network. Experimental results based on several multisource data show that our proposed network model has a good classification effect on the test samples and can achieve more excellent classification performance than some existing methods, with an accuracy of 91%, and can be used for the classification of remote sensing images. Our model not only has high accuracy but also has faster training speed compared with large networks and can greatly reduce computation costs. The demo code of our proposed method will be available at https://github.com/li-zi-qi. [ABSTRACT FROM AUTHOR]

Text summarizing (TS) takes key information from a source text and condenses it for the user while retaining the primary material. When it comes to text summaries, the most difficult problem is to provide broad topic coverage and diversity in a single summary. Overall, text summarization addresses the fundamental need to distill large volumes of information into more manageable and digestible forms, making it a crucial technology in the era of information abundance. It benefits individuals, businesses, researchers, and various other stakeholders by enhancing efficiency and comprehension in dealing with textual data. In this paper, proposed a novel Modified Generative adversarial network (MGAN) for summarize the text. The proposed model involves three stages namely pre-processing, Extractive summarization, and summary generation. In the first Phase, the Text similarity dataset is pre-processed using Lowering Casing, Tokenization, Lemmatization, and, Stop Word Removal. In the second Phase, the Extractive summarization is done in three steps Generating similarity metrics, Sentence Ranking, and Sentence Extractive. In the third stage, a generative adversarial network (GAN) employs summary generation to jointly train the discriminative model D and the generative model G. To classify texts and annotate their syntax, Generative Model G employs a convolutional neural network called Bidirectional Gated Recursive Unit (CNN-BiGRU). The performance analysis of the proposed MGAN is calculated based on the parameters like accuracy, specificity, Recall, and Precision metrics. The proposed MGAN achieves an accuracy range of 99%. The result shows that the proposed MGAN improves the overall accuracy better than 9%, 6.5% and 5.4% is DRM, LSTM, and CNN respectively. [ABSTRACT FROM AUTHOR]

Enhancers play an important role in the process of gene expression regulation. In DNA sequence abundance or absence of enhancers and irregularities in the strength of enhancers affects gene expression process that leads to the initiation and propagation of diverse types of genetic diseases such as hemophilia, bladder cancer, diabetes and congenital disorders. Enhancer identification and strength prediction through experimental approaches is expensive, time-consuming and error-prone. To accelerate and expedite the research related to enhancers identification and strength prediction, around 19 computational frameworks have been proposed. These frameworks used machine and deep learning methods that take raw DNA sequences and predict enhancer's presence and strength. However, these frameworks still lack in performance and are not useful in real time analysis. This paper presents a novel deep learning framework that uses language modeling strategies for transforming DNA sequences into statistical feature space. It applies transfer learning by training a language model in an unsupervised fashion by predicting a group of nucleotides also known as k-mers based on the context of existing k-mers in a sequence. At the classification stage, it presents a novel classifier that reaps the benefits of two different architectures: convolutional neural network and attention mechanism. The proposed framework is evaluated over the enhancer identification benchmark dataset where it outperforms the existing best-performing framework by 5%, and 9% in terms of accuracy and MCC. Similarly, when evaluated over the enhancer strength prediction benchmark dataset, it outperforms the existing best-performing framework by 4%, and 7% in terms of accuracy and MCC. [ABSTRACT FROM AUTHOR]

Multi-exposure fusion (MEF) is widely researched and applied to high dynamic range (HDR) imaging, where one of the most challenging problems is the artifacts caused by the motion of objects between input images. Recently, deep learning methods have been widely applied for HDR imaging with excellent results, showing significant advantages. However, many methods cannot avoid artifacts due to inaccurate alignment before merging HDR images. In this paper, we propose an end-to-end network (C-ED-GMNET) with a channel and spatial attention network, an encoder–decoder network and a gradual merging network for generating artifact-free HDR images in dynamic scenes. The attention module consists of two submodules to identify useful features and exclude harmful components in inputs from both channel and spatial dimensions, respectively. The attention-guided feature maps are sent to the encoders for further feature extraction, and then, the outputs are sent to a gradual merging module consisting of two steps to generate deep features progressively. Besides, the differences between the merged image and the original images are identified by applying global residual learning with all the inputs, and the merged image feature is recovered by the decoder to obtain the final HDR image. Quantitative and qualitative experiments on two public datasets show that the proposed C-ED-GMNET produces better results than existing state-of-the-art methods and significantly reduces the runtime due to the encoders which reduce the amount of computation. [ABSTRACT FROM AUTHOR]

Grain size and uniformity index of fragments produced by tunnel boring machine (TBM) reflect tunneling states. Traditional manual fragment identification methods will reduce tunneling safety and efficiency. Therefore, an automatic fragment classification method is significant. However, the fragments classification accuracy of existing deep learning methods will decrease under different tunnel projects with various kinds of fragments. In this paper, a rock fragment classification method is proposed based on convolutional neural network (CNN). To distinguish fragment and background with very similar grey level in the image, contrast limited adaptive histogram equalization is used to enhance fragment edge features. In addition, image regeneration is used in data preparation process to balance data set. During hyperparameter tuning in model training, this research applies Bayesian optimization to acquire optimum model. Experiments show that proposed CNN model can acquire an accuracy of 91.88% in classifying various types of fragments, improving 39.21%, 11.64%, 13.64% and 9.45%, respectively, compared with LeNet, ResNet, VGG and AlexNet. Batch normalization, DropBlock and global average pooling skills are used to alleviate overfitting of CNN model. Based on proposed model pre-trained on a single project data set and a small amount of new data, the migrated model can achieve 89.86% accuracy on a new tunnel data set. The experiment results demonstrate a great generalization ability of proposed model dealing with various kinds of fragments. Highlights: Developing a fragments image-based deep learning architecture to classify rock fragments produced by tunnel boring machine. Trained by Bayesian optimization, proposed method is tested on rock fragment images collected from tunnel projects and acquire better accuracy, precision and recall on the test set than the LeNet, ResNet, VGG and AlexNet based fragment classification models. By integrating the deep learning theories to alleviate model overfitting, proposed model has higher accuracy than existing image classification models when dealing with rock fragments under different tunnel projects. [ABSTRACT FROM AUTHOR]

This paper devises a technique for diagnosing and classifying osteoporosis using the femur bone's X-ray images. The devised approach uses the following phases: image acquisition, pre-processing, segmentation of femur boundary, measurement of femoral geometry, feature mining, and osteoporosis categorization. Here, femur boundary segmentation is done using the Deep Contour Aware Network (DCAN), which is trained by the Chronological Artificial Ecosystem Optimization (CAEO) algorithm. Then, the femoral geometry is measured and the most relevant features in the image are identified. Further, osteoporosis is classified using the Convolutional Neural Network (CNN) with Transfer Learning (TL), where the CNN is employed with the hyperparameters of the pre-trained model, LeNet. Here, the Chronological Artificial Ecosystem Tasmanian Devil Optimization (CAETDO) algorithm optimizes the classification process. The CAETDO-CNN-TL is examined based on metrics and have the values of 0.910, 0.927, 0.928, and 0.904 for precision, True Negative Rate (TNR), True Positive Rate (TPR), and accuracy, correspondingly. [ABSTRACT FROM AUTHOR]

COVID-19 analysis from medical imaging is an important task that has been intensively studied in the last years due to the spread of the COVID-19 pandemic. In fact, medical imaging has often been used as a complementary or main tool to recognize the infected persons. On the other hand, medical imaging has the ability to provide more details about COVID-19 infection, including its severity and spread, which makes it possible to evaluate the infection and follow-up the patient's state. CT scans are the most informative tool for COVID-19 infection, where the evaluation of COVID-19 infection is usually performed through infection segmentation. However, segmentation is a tedious task that requires much effort and time from expert radiologists. To deal with this limitation, an efficient framework for estimating COVID-19 infection as a regression task is proposed. The goal of the Per-COVID-19 challenge is to test the efficiency of modern deep learning methods on COVID-19 infection percentage estimation (CIPE) from CT scans. Participants had to develop an efficient deep learning approach that can learn from noisy data. In addition, participants had to cope with many challenges, including those related to COVID-19 infection complexity and crossdataset scenarios. This paper provides an overview of the COVID-19 infection percentage estimation challenge (Per-COVID-19) held at MIA-COVID-2022. Details of the competition data, challenges, and evaluation metrics are presented. The best performing approaches and their results are described and discussed. [ABSTRACT FROM AUTHOR]

In this paper, we introduce a novel panoptic segmentation method called the Mask-Pyramid Network. Existing Mask RCNN-based methods first generate a large number of box proposals and then filter them at each feature level, which requires a lot of computational resources, while most of the box proposals are suppressed and discarded in the Non-Maximum Suppression process. Additionally, for panoptic segmentation, it is a problem to properly fuse the semantic segmentation results with the Mask RCNN-produced instance segmentation results. To address these issues, we propose a new mask pyramid mechanism to distinguish objects and generate much fewer proposals by referring to existing segmented masks, so as to reduce computing resource consumption. The Mask-Pyramid Network generates object proposals and predicts masks from larger to smaller sizes. It records the pixel area occupied by the larger object masks, and then only generates proposals on the unoccupied areas. Each object mask is represented as a H × W × 1 logit, which fits well in format with the semantic segmentation logits. By applying SoftMax to the concatenated semantic and instance segmentation logits, it is easy and natural to fuse both segmentation results. We empirically demonstrate that the proposed Mask-Pyramid Network achieves comparable accuracy performance on the Cityscapes and COCO datasets. Furthermore, we demonstrate the computational efficiency of the proposed method and obtain competitive results. [ABSTRACT FROM AUTHOR]

Medical imaging is crucial for the detection and diagnosis of breast cancer. Artificial intelligence and computer vision have rapidly become popular in medical image analyses thanks to technological advancements. To improve the effectiveness and efficiency of medical diagnosis and treatment, significant efforts have been made in the literature on medical image processing, segmentation, volumetric analysis, and prediction. This paper is interested in the development of a prediction pipeline for breast cancer studies based on 3D computed tomography (CT) scans. Several algorithms were designed and integrated to classify the suitability of the CT slices. The selected slices from patients were then further processed in the pipeline. This was followed by data generalization and volume segmentation to reduce the computation complexity. The selected input data were fed into a 3D U-Net architecture in the pipeline for analysis and volumetric predictions of cancer tumors. Three types of U-Net models were designed and compared. The experimental results show that Model 1 of U-Net obtained the highest accuracy at 91.44% with the highest memory usage; Model 2 had the lowest memory usage with the lowest accuracy at 85.18%; and Model 3 achieved a balanced performance in accuracy and memory usage, which is a more suitable configuration for the developed pipeline. [ABSTRACT FROM AUTHOR]

The purpose of pan-sharpening is to generate high-resolution multispectral (HRMS) images by combining multispectral images (MS) and panchromatic images (PAN), which have become an important part of remote sensing image processing. Therefore, how to better extract complete feature information from MS images and PAN images has become the focus of our attention. In this paper, we propose a new pansharpening method, called Transformer-based Dual-path cross fusion network (TDF) for Pan-sharpening remote sensing images, which aims to extract the spatial details of PAN images while maintaining the spectral fidelity of MS images. The whole network structure can be divided into two parts: in the encoder part, we adopt the Swin-Transformer module for the downsampling operation, which expands the sensory field of the network to the feature map, and then extracts the global information. However, since the Swin-Transformer module is not good at extracting pixel-level details, we introduce the Base Feature Extraction (BFE) and the Invertible Neural Network Block (INNB) modules for the interaction between the local and the global feature information. we also introduce the Edge-Enhancement Block (EEB) to further enhance the feature extraction at multi-scales during the image fusion process. In the decoder section, we once again employ the Swin Transformer module for downsampling. After the convolution operation and activation function, we utilize the Sub-Pixel Convolutional Neural Network for upsampling to generate the ultimate high-resolution multispectral images. Simulation experiments and real experiments are conducted on QuickBird (QB) and WorldView2 (WV2) datasets, which demonstrated our method are superior to the current methods. [ABSTRACT FROM AUTHOR]

Organizations managing high-performance computing systems face a multitude of challenges, including overarching concerns such as overall energy consumption, microprocessor clock frequency limitations, and the escalating costs associated with chip production. Evidently, processor speeds have plateaued over the last decade, persisting within the range of 2 GHz to 5 GHz. Scholars assert that brain-inspired computing holds substantial promise for mitigating these challenges. The spiking neural network (SNN) particularly stands out for its commendable power efficiency when juxtaposed with conventional design paradigms. Nevertheless, our scrutiny has brought to light several pivotal challenges impeding the seamless implementation of large-scale neural networks (NNs) on silicon. These challenges encompass the absence of automated tools, the need for multifaceted domain expertise, and the inadequacy of existing algorithms to efficiently partition and place extensive SNN computations onto hardware infrastructure. In this paper, we posit the development of an automated tool flow capable of transmuting any NN into an SNN. This undertaking involves the creation of a novel graph-partitioning algorithm designed to strategically place SNNs on a network-on-chip (NoC), thereby paving the way for future energy-efficient and high-performance computing paradigms. The presented methodology showcases its effectiveness by successfully transforming ANN architectures into SNNs with a marginal average error penalty of merely 2.65%. The proposed graph-partitioning algorithm enables a 14.22% decrease in inter-synaptic communication and an 87.58% reduction in intra-synaptic communication, on average, underscoring the effectiveness of the proposed algorithm in optimizing NN communication pathways. Compared to a baseline graph-partitioning algorithm, the proposed approach exhibits an average decrease of 79.74% in latency and a 14.67% reduction in energy consumption. Using existing NoC tools, the energy-latency product of SNN architectures is, on average, 82.71% lower than that of the baseline architectures. [ABSTRACT FROM AUTHOR]

Machine learning (ML) algorithms are increasingly applied to structure health monitoring (SHM) problems. However, their application to pile damage detection (PDD) is hindered by the complexity of the problem. A novel multi-sensor pile damage detection (MSPDD) method is proposed in this paper to extend the application of ML algorithms in the automatic identification of PDD. The time-series signals collected by multiple sensors during the pile integrity test are first processed by the traveling wave decomposition (TWD) theory and are then input into a hybrid one-dimensional (1D) convolutional and recurrent neural network. The hybrid neural network can achieve the automatic multi-task identification of pile damage detection based on the time series of MSPDD results. Finally, the analytical solution-based sample set is utilized to evaluate the performance of the proposed hybrid model. The outputs of the multi-task learning framework can provide a detailed description of the actual pile quality and provide strong support for the classification of pile quality as well. [ABSTRACT FROM AUTHOR]

The extensive use of corrugated board in the packaging industry is attributed to its excellent cushioning, mechanical properties, and environmental benefits like recyclability and biodegradability. The integrity of corrugated board depends on various factors, including its geometric design, paper quality, the number of layers, and environmental conditions such as humidity and temperature. This study introduces an innovative application of convolutional neural networks (CNNs) for analyzing and classifying images of corrugated boards, particularly those with deformations. For this purpose, a special device with advanced imaging capabilities, including a high-resolution camera and image sensor, was developed and used to acquire detailed cross-section images of the corrugated boards. The samples of seven types of corrugated board were studied. The proposed approach involves optimizing CNNs to enhance their classification performance. Despite challenges posed by deformed samples, the methodology demonstrates high accuracy in most cases, though a few samples posed recognition difficulties. The findings of this research are significant for the packaging industry, offering a sophisticated method for quality control and defect detection in corrugated board production. The best classification accuracy obtained achieved more than 99%. This could lead to improved product quality and reduced waste. Additionally, this study paves the way for future research on applying machine learning for material quality assessment, which could have broader implications beyond the packaging sector. [ABSTRACT FROM AUTHOR]

The hippocampus is known to play an important role in memory by processing spatiotemporal information of episodic experiences. By recording synchronized multiple-unit firing events (ripple firings with 300 Hz–10 kHz) of hippocampal CA1 neurons in freely moving rats, we previously found an episode-dependent diversity in the waveform of ripple firings. In the present study, we hypothesized that changes in the diversity would depend on the type of episode experienced. If this hypothesis holds, we can identify the ripple waveforms associated with each episode. Thus, we first attempted to classify the ripple firings measured from rats into five categories: those experiencing any of the four episodes and those before experiencing any of the four episodes. In this paper, we construct a convolutional neural network (CNN) to classify the current stocks of ripple firings into these five categories and demonstrate that the CNN can successfully classify the ripple firings. We subsequently indicate partial ripple waveforms that the CNN focuses on for classification by applying gradient-weighted class activation mapping (Grad-CAM) to the CNN. The method of t-distributed stochastic neighbor embedding (t-SNE) maps ripple waveforms into a two-dimensional feature space. Analyzing the distribution of partial waveforms extracted by Grad-CAM in a t-SNE feature space suggests that the partial waveforms may be representative of each category. [ABSTRACT FROM AUTHOR]

Various prediction approaches regarding liver diseases have been developed. Still, they are expensive and more complex. This work aims to design an effective method for identifying liver diseases at earlier stages. This paper presents a modified Mask-regionalconvolutional neural network (MRCNN) architecture for non-invasive liver disease prediction. The Pelican Optimization Algorithm (POA) is used to balance the bounding box regression and mask branching training losses of the RCNN model. The liver disease features are extracted from three datasets namely Indian liver patient records, Hepatitis C, and Cirrhosis Prediction datasets. The POA-modified MRCNN model is mainly used to identify the interrelationship that exists between different laboratory measurements and diagnoses. The efficiency of the proposed model is compared with different state-of-art methods such as Opposition-based Laplacian Equilibrium Optimizer, Adaptive Hybridized Deep CNN, SVM, and Tree-based classifiers in terms of Accuracy, Precision, Recall, F-measure, and Mathews Correlation Coefficient (MCC). The proposed model offers an MCC value of 94.89, an accuracy of 98%, a precision of 96.2%, an F-measure of 97.3%, and a recall of 95% respectively. The results demonstrate the efficiency of the proposed model in predicting liver disease at an early stage via automatic screening and minimizing the burden of physicians. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to leverage the advantages of physics-informed neural network (PINN) and convolutional neural network (CNN) by using Legendre multiwavelets (LMWs) as basis functions to approximate partial differential equations (PDEs). We call this method Physics-Informed Legendre Multiwavelets CNN (PiLMWs-CNN), which can continuously approximate a grid-based state representation that can be handled by a CNN. PiLMWs-CNN enable us to train our models using only physics-informed loss functions without any precomputed training data, simultaneously providing fast and continuous solutions that generalize to previously unknown domains. In particular, the LMWs can simultaneously possess compact support, orthogonality, symmetry, high smoothness, and high approximation order. Compared to orthonormal polynomial (OP) bases, the approximation accuracy can be greatly increased and computation costs can be significantly reduced by using LMWs. We applied PiLMWs-CNN to approximate the damped wave equation, the incompressible Navier–Stokes (N-S) equation, and the two-dimensional heat conduction equation. The experimental results show that this method provides more accurate, efficient, and fast convergence with better stability when approximating the solution of PDEs. [ABSTRACT FROM AUTHOR]

Accurate segmentation of knee cartilage in MR images is crucial for early diagnosis and treatment of knee conditions. Manual segmentation is time-consuming, leading researchers to explore automatic deep learning methods. However, the choice between 2D and 3D networks for organ segmentation remains debated. In this paper, we propose a hybrid 2D and 3D deep neural network approach, named UVNet, which combines the strengths of both techniques to enhance segmentation performance. Within this network structure, the 3D segmentation network serves as the backbone for feature extraction, while the 2D segmentation network functions as an information supplement network. Local and global MIP images are generated by employing various maximum intensity projection modes of knee MRI volumes as input for the information supplement network. By constructing a local and global MIP feature fusion module, the supplementary information obtained from the 2D segmentation network is fully integrated into the backbone network. We assess the quality of the proposed method using the Osteoarthritis Initiative (OAI) dataset and the 2010 Grand Challenge Knee Image Segmentation (SKI-10) dataset, comparing it to the Baseline Network and other advanced 2D and 3D segmentation methods. The experiments demonstrate that UVNet achieves competitive performance in the aforementioned two cartilage segmentation tasks. [ABSTRACT FROM AUTHOR]

Several deep learning and transformer models have been recommended in previous research to deal with the classification of hyperspectral images (HSIs). Among them, one of the most innovative is the bidirectional encoder representation from transformers (BERT), which applies a distance-independent approach to capture the global dependency among all pixels in a selected region. However, this model does not consider the local spatial-spectral and spectral sequential relations. In this paper, a dual-dimensional (i.e., spatial and spectral) BERT (the so-called D2BERT) is proposed, which improves the existing BERT model by capturing more global and local dependencies between sequential spectral bands regardless of distance. In the proposed model, two BERT branches work in parallel to investigate relations among pixels and spectral bands, respectively. In addition, the layer intermediate information is used for supervision during the training phase to enhance the performance. We used two widely employed datasets for our experimental analysis. The proposed D2BERT shows superior classification accuracy and computational efficiency with respect to some state-of-the-art neural networks and the previously developed BERT model for this task. [ABSTRACT FROM AUTHOR]

To reduce the reliance of existing mainstream vision-based crack detection algorithms on annotated datasets, this paper presents an unsupervised semantic segmentation-based approach. The proposed method first employs the Felzenszwalb-Huttenlocher algorithm for pre-segmenting the image, generating superpixels. Subsequently, a with an autoencoder model is designed to progressively approximate the superpixel segmentation results, and the optimal model is obtained by Bayesian optimization. Through comparative experiments with existing algorithms, it has been demonstrated that the proposed method performance comparable to supervised algorithms, even without the need for labeled data. As a result, the deployment complexity of the algorithm is significantly reduced, while expanding its applicability. [ABSTRACT FROM AUTHOR]

Accurate and reliable estimation of the pelvic tilt is one of the essential pre-planning factors for total hip arthroplasty to prevent common post-operative complications such as implant impingement and dislocation. Inspired by the latest advances in deep learning-based systems, our focus in this paper has been to present an innovative and accurate method for estimating the functional pelvic tilt (PT) from a standing anterior–posterior (AP) radiography image. We introduce an encoder–decoder-style network based on a concurrent learning approach called VGG-UNET (VGG embedded in U-NET), where a deep fully convolutional network known as VGG is embedded at the encoder part of an image segmentation network, i.e., U-NET. In the bottleneck of the VGG-UNET, in addition to the decoder path, we use another path utilizing light-weight convolutional and fully connected layers to combine all extracted feature maps from the final convolution layer of VGG and thus regress PT. In the test phase, we exclude the decoder path and consider only a single target task i.e., PT estimation. The absolute errors obtained using VGG-UNET, VGG, and Mask R-CNN are 3.04 ± 2.49, 3.92 ± 2.92, and 4.97 ± 3.87, respectively. It is observed that the VGG-UNET leads to a more accurate prediction with a lower standard deviation (STD). Our experimental results demonstrate that the proposed multi-task network leads to a significantly improved performance compared to the best-reported results based on cascaded networks. [ABSTRACT FROM AUTHOR]

The complex flow of a supersonic jet (Mach number 2.4–2.5) around the blunt aerodynamic body (consisting of a cylinder with a diameter of 16 mm and a truncated cone) was studied using the high-speed shadowgraph technique and computer vision-based visual data processing. The problem considered is directly related to the rocket and space systems stages safe separation problem in a sufficiently dense atmosphere. For systems with a sequential arrangement of stages, their separation often occurs under the rocket engine jet action. The occurrence of lateral forces in violation of axial symmetry can lead to overturning of the discarded stage and undesirable interaction with the outgoing stage. The goals of the paper were to study the pulsation characteristics of the incoming supersonic jet streamlining the body, as well as the pulsations of the bow shock wave in both axisymmetric and asymmetric flows. The recording frame rate in the experiments was up to 775 000 fps. Computer vision and various machine learning approaches were used to process a large number of shadowgraph images. Canny edge detection and Hough transform, as well as a convolutional neural network (CNN) based on YOLOv2 architecture, were used to automatically track the position of the bow shock relative to the body. Jet sound generation was studied - the amplitude dependence on the distance from the nozzle and the evolution in time. The position of the bow shock relative to the streamlined body and flow pulsations over time were analyzed. Bow shock pulsation spectra at zero angle of attack were compared to those at a small angle of attack (α = 2.5°–3°). The power spectral density was also estimated. The slope of the spectra for the zero angle of attack case was found to be horizontal and the spectra for the small angle of attack case had a slope close to −5/3. The strongest of the measured bow shock frequencies were found to be close to those of the jet mixing layer pulsations. The hardware signal spectrum was also measured and this signal can be considered as noise. The described approach makes it possible to obtain the physical characteristics of the flow at any point of interest. It was also shown that the automation of flow visualization experiments using computer vision techniques allows to increase the speed of data processing and obtaining new physical information, which may be important for engineers developing aircraft and spacecraft technologies. • Supersonic jet flow around a blunt body was studied experimentally and also numerically. • Computer vision tools were applied to supersonic flow investigation. • Spectra of jet generated acoustic waves were determined. • Time dependent bow shock positions were automatically measured by the neural network. • Amplitudes of bow shock pulsations and flow fluctuations depend on the angle of the body relative to the jet direction. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks can effectively improve the performance of single-image super-resolution reconstruction. Deep networks tend to achieve better performance than others. However, the deep CNNs will lead to a dramatic increase in the size of parameters, limiting its application on embedding and resource-constrained devices, such as smart phone. To address the common problems of blurred image edges, inflexible convolution kernel size selection and slow convergence during training procedure due to redundant network structure in image super-resolution algorithms, this paper proposes a lightweight single-image super-resolution network that fuses multi-level features. The components are mainly two-level nested residual blocks. To better extract features and reduce the number of parameters, each residual block adopts an asymmetric structure. Firstly, it expands twice and then compresses the number of channels twice. Secondly, in the residual block, the feature information of different channels is weighted and fused by adding an autocorrelation weight unit. The quality of the reconstructed image of the proposed method is superior to the existing image super-resolution reconstruction methods in both subjective perception and objective evaluation indicators, and the reconstruction performance is better when the factor is large. [ABSTRACT FROM AUTHOR]

This paper proposes an efficient method for rectifying distorted document images via deep learning, ultimately improving the legibility of graphics and text in documents. The framework comprises two interconnected UNets, working in tandem to predict a 3D coordinate map and a forward map for the input distorted document image, respectively. At the beginning of the process, a page mask is predicted and used as input to both U-Nets to help improve the performance of their tasks. In the last step, the predicted forward map is transformed into a corresponding backward map, which is utilized to rectify the distorted image. The experimental results not only reveal that the predicted page masks and 3D coordinate maps significantly enhance the accuracy of predicting forward maps for subsequent rectification but also demonstrate satisfactory results both globally and locally. [ABSTRACT FROM AUTHOR]

Mobile fitness applications provide the opportunity to show users real-time feedback on their current fitness activity. For such applications, it is essential to accurately track the user's current fitness activity using available mobile sensors, such as inertial measurement units (IMUs). Convolutional neural networks (CNNs) have been shown to produce strong results in different time series classification tasks, including the recognition of daily living activities. However, fitness activities can present unique challenges to the human activity recognition task (HAR), including greater similarity between individual activities and fewer available data for model training. In this paper, we evaluate the applicability of CNNs to the fitness activity recognition task (FAR) using IMU data and determine the impact of input data size and sensor count on performance. For this purpose, we adapted three existing CNN architectures to the FAR task and designed a fourth CNN variant, which we call the scaling fully convolutional network (Scaling-FCN). We designed a preprocessing pipeline and recorded a running exercise data set with 20 participants, in which we evaluated the respective recognition performances of the four networks, comparing them with three traditional machine learning (ML) methods commonly used in HAR. Although CNN architectures achieve at least 94% test accuracy in all scenarios, two traditional ML architectures surpass them in the default scenario, with support vector machines (SVMs) achieving 99.00 ± 0.34% test accuracy. The removal of all sensors except one foot sensor reduced the performance of traditional ML architectures but improved the performance of CNN architectures on our data set, with our Scaling-FCN reaching the highest accuracy of 99.86 ± 0.11% on the test set. Our results suggest that CNNs are generally well suited for fitness activity recognition, and noticeable performance improvements can be achieved if sensors are dropped selectively, although traditional ML architectures can still compete with or even surpass CNNs when favorable input data are utilized. [ABSTRACT FROM AUTHOR]

Precise and content-aware style transfer in oil painting remains a significant research focus. This involves preserving the semantic content of the original image while accurately emulating the desired painting style. Developing robust algorithms for accurate recognition and classification of various patterns within oil paintings remains a challenge which identify and categorize styles, textures and visual elements to contribute comprehensive understanding of the artwork. The conventional image style transfer algorithm mainly relies on mathematical modeling to characterize image texture facilitating the combination of a content image with a style image to realize style transfer effects. These algorithms neglect the distribution of image edges leading to blurred contours in the resulting images. To address these limitations, this paper proposed a novel decoration pattern style migration algorithm based on SRCNN (Super Resolution Convolutional Neural Network) model using UNet-based architecture. The algorithm leverages the Laplace operator for image sharpening by accentuating edge distributions. Downsampling techniques are used to generate low-resolution images mitigating the protracted duration of image style transfer iterations. The incorporation of Gaussian sampling and a parallelization algorithm contributes to the efficacy of this method in facilitating the transfer of oil painting styles. The proposed model achieves better results using Facades data set, i.e., variance (6.35%), standard deviation (8.67%), uncertainty (11.21%), SSIM score (94.45%), PSNR score (40.24%), MSE score (6.21%) and accuracy (95.00%). For the Monet2photo data set, i.e., variance (7.25%), standard deviation (9.78%), uncertainty (12.78%), SSIM score (91.69%), PSNR score (43.71%), MSE score (8.67%) and accuracy (92.00%). Our proposed method outperforms classical methods using both data sets. [ABSTRACT FROM AUTHOR]

In this paper, we introduce misclassification information for the improved training of convolutional neural network classifiers (CNNCs) for image recognition. We construct an additional autoencoder neural network, called tutor, that forces the CNNCs to learn the difference between the misclassified picture and the picture corresponding to the misclassified category. Making full use of the classification results to guide the CNNCs for purposeful learning is expected to improve learning efficiency and classification performance. We integrate the proposed tutor into several state-of-the-art CNNCs architectures and demonstrate improvement in their recognition performance on CIFAR-10/100 and MNIST datasets. Our results suggest that making the most of misclassification information to guide the training of the model can lead to significant performance improvement. [ABSTRACT FROM AUTHOR]

• The deep learning model can better extract the deeper features of the multi-point deformation sequence. • MVMD algorithm reduces the complexity of multi-point displacement sequence. • The model considers the spatiotemporal characteristics of dam deformation, the prediction accuracy is obviously improved. It is difficult for single measuring point model to synchronously characterize the spatial correlation of deformation sequence of concrete dam and the similarity of displacements of different measuring points. Considering the limitation of conventional model in dealing with spatial-temporal data structure, In this study, a deep learning technique for multi-point and multi-output deformation prediction of concrete dams is proposed, which is based on Multivariate Variational Mode Decomposition (MVMD) and three-dimensional convolutional neural network (3D-CNN) combined model. Firstly, the multi-point sequence is decomposed into several relatively stable sub-sequences with different frequency scales by MVMD, which reduces the complexity of the multi-point displacement sequence. Then, In order to enhance the model 's ability to fit the time and spatial features of the sequence, the 3D-CNN model is used to predict the decomposed components and reconstruct the displacement data of the measuring points. This study focuses on the principle, process and calculation steps of the proposed model, and verifies the proposed model through the deformation data of three typical measuring points. The test results show that the prediction model proposed in this paper is an effective method for dam deformation prediction. [ABSTRACT FROM AUTHOR]

Automatic extraction of building contours from high-resolution images is of great significance in the fields of urban planning, demographics, and disaster assessment. Network models based on convolutional neural network (CNN) and transformer technology have been widely used for semantic segmentation of buildings from high resolution remote sensing images (HRSI). However, the fixed geometric structure and the local receptive field of the convolutional kernel are not good at global feature extraction, and the transformer technique with self-attention mechanism introduces computational redundancies and extracts local feature details poorly in the process of modeling the global contextual information. In this paper, a dual-branch fused reconstructive transformer network, DFRTNet, is proposed for efficient and accurate building extraction. In the encoder, the traditional transformer is reconfigured by designing the local and global feature extraction module (LGFE); the branch of global feature extraction (GFE) performs dynamic range attention (DRA) based on the idea of top-k attention for extracting global features; furthermore, the branch of local feature extraction (LFE) is used to obtain fine-grained features. The multilayer perceptron (MLP) is employed to efficiently fuse the local and global features. In the decoder, a simple channel attention module (CAM) is used in the up-sampling part to enhance channel dimension features. Our network achieved the best segmentation accuracy on both the WHU and Massachusetts building datasets when compared to other mainstream and state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Hand gesture recognition, which is one of the fields of human–computer interaction (HCI) research, extracts the user's pattern using sensors. Radio detection and ranging (RADAR) sensors are robust under severe environments and convenient to use for hand gestures. The existing studies mostly adopted continuous-wave (CW) radar, which only shows a good performance at a fixed distance, which is due to its limitation of not seeing the distance. This paper proposes a hand gesture recognition system that utilizes frequency-shift keying (FSK) radar, allowing for a recognition method that can work at the various distances between a radar sensor and a user. The proposed system adopts a convolutional neural network (CNN) model for the recognition. From the experimental results, the proposed recognition system covers the range from 30 cm to 180 cm and shows an accuracy of 93.67% over the entire range. [ABSTRACT FROM AUTHOR]

The widespread availability of digitized fine art collections in museums and galleries has generated a demand for efficient software tools. These tools enable rapid retrieval and semantic classification of art images. Traditional image classification methods often rooted in shallow structure learning algorithms offer the capacity to extract various image features. However, there is need for deep understanding of fundamental painting knowledge during this process due to the reason that certain features may be lost. In this paper, we present an innovating approach for classifying digital paintings based on artist attribution. Our approach centers on the creations of multi-scale pyramid representation derived from a given painting image which facilitate the incorporation of both global and local information within a single image. The training of Convolutional Neural Network (CNN) algorithm is performed for the assignment of class labels on each level of the pyramid. To establish connections among localized image patches, we use Markov Random Fields through the optimization of the Gibbs energy function. We validate the proposed approach which referred to as the multi-scale CNN framework using fusion-based Markov random field using two challenging painting image datasets: WikiArt and Web Gallery of Art (WGA). The proposed model archives better results using WikiArt dataset for painting image classification, i.e., precision (74.12%), recall (70.23%), F1-score (72.65%), and accuracy (80.00%). Using Web Gallery of Art (WGA) dataset for painting image classification, the model achieves the following results: precision (75.88%), recall (77.25%), F1-score (76.44%), and accuracy (78.00%). Our proposed method outperforms state-of-the-art methods excelling not only in image classification but also in terms of computational efficiency. [ABSTRACT FROM AUTHOR]

The fifth-generation (5G) mobile cellular network is vulnerable to various security threats. Radio frequency fingerprint (RFF) identification is an emerging physical layer authentication technique which can be used to detect spoofing and distributed denial of service attacks. In this paper, the performance of RFF identification is studied for 5G mobile phones. The differential constellation trace figure (DCTF) is extracted from the physical random access channel (PRACH) preamble. When the database of all 64 PRACH preambles is available at the gNodeB (gNB), an index-based DCTF identification scheme is proposed, and the classification accuracy reaches 92.78% with a signal-to-noise ratio of 25 dB. Moreover, due to the randomness in the selection of preamble sequences in the random access procedure, when only a portion of the preamble sequences can be trained, a group-based DCTF identification scheme is proposed. The preamble sequences generated from the same root value are grouped together, and the untrained sequences can be identified based on the trained sequences within the same group. The classification accuracy of the group-based scheme is 89.59%. An experimental system has been set up using six 5G mobile phones of three models. The 5G gNB is implemented on the OpenAirInterface platform. [ABSTRACT FROM AUTHOR]

In this paper, we have researched implementing convolutional neural network (CNN) models for devices with limited resources, such as smartphones and embedded computers. To optimize the number of parameters of these models, we studied various popular methods that would allow them to operate more efficiently. Specifically, our research focused on the ResNet-101 and VGG-19 architectures, which we modified using techniques specific to model optimization. We aimed to determine which approach would work best for particular requirements for a maximum accepted accuracy drop. Our contribution lies in the comprehensive ablation study, which presents the impact of different approaches on the final results, specifically in terms of reducing model parameters, FLOPS, and the potential decline in accuracy. We explored the feasibility of implementing architecture compression methods that can influence the model’s structure. Additionally, we delved into post-training methods, such as pruning and quantization, at various model sparsity levels. This study builds upon our prior research to provide a more comprehensive understanding of the subject matter at hand. [ABSTRACT FROM AUTHOR]

With the advancement in modern imaging techniques like CT scan, MRI, PET scan etc., a vast amount of data is generated every day in the field of healthcare. Big data contains hidden information, which necessitates the development of intelligent systems to analyze it and extract relevant information, allowing for accurate and cost-effective decisions in the medical field. By utilizing the untapped potential of the big data available in the medical field, very precise models can be developed for the medical diagnosis of retinal diseases. Optical coherence tomography (OCT) is a non-invasive imaging test that captures different, distinctive layers of the retina and optic nerve in a living eye to map and measure their thickness, that helps diagnose various retinal disorders. With the advancement of the application of deep learning-based techniques in the field of medical sciences, the use of convolutional neural network (CNN) based approaches for disease detection is gaining popularity. While the manual examination of 3D OCT images for the diagnosis of retinal disorders requires extensive time and expert intervention, the use of CNNs provides an effective automated option that provides results with higher accuracy while also reducing the time involved in the overall process. In this paper, we have implemented the aforementioned idea by proposing OCT-CNN, a CNN architecture, that automatically classifies retinal OCT images and identifies potential disorders in a living eye. Several techniques have been employed to enhance the performance of the proposed approach, including digital enhancement of the images, dropout regularization, adaptive learning rates, and early stopping of training to attain optimal performance. The performance of the proposed OCT-CNN is evaluated on the UCSD dataset against several popular deep CNN architectures and existing state-of-the-art approaches to automatic retinal OCT classification. The proposed OCT-CNN attains the best performance on all evaluated metrics, pushing the classification accuracies to 99.28% on CNV, 99.9% on DME, 99.38% on DRUSEN, and 100% on NORMAL images, indicating its superiority over existing state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

Dry eye disease (DED) is a chronic eye disease and a common complication among the world's population. Evaporation of moisture from tear film or a decrease in tear production leads to an unstable tear film which causes DED. The tear film breakup time (TBUT) test is a common clinical test used to diagnose DED. In this test, DED is diagnosed by measuring the time at which the first breakup pattern appears on the tear film. TBUT test is subjective, labour-intensive and time-consuming. These weaknesses make a computer-aided diagnosis of DED highly desirable. The existing computer-aided DED detection techniques use expensive instruments for image acquisition which may not be available in all eye clinics. Moreover, among these techniques, TBUT-based DED detection techniques are limited to finding only tear film breakup area/time and do not identify the severity of DED, which can essentially be helpful to ophthalmologists in prescribing the right treatment. Additionally, a few challenges in developing a DED detection approach are less illuminated video, constant blinking of eyes in the videos, blurred video, and lack of public datasets. This paper presents a novel TBUT-based DED detection approach that detects the presence/absence of DED from TBUT video. In addition, the proposed approach accurately identifies the severity level of DED and further categorizes it as normal, moderate or severe based on the TBUT. The proposed approach exhibits high performance in classifying TBUT frames, detecting DED, and severity grading of TBUT video with an accuracy of 83%. Also, the correlation computed between the proposed approach and the Ophthalmologist's opinion is 90%, which reflects the noteworthy contribution of our proposed approach. [ABSTRACT FROM AUTHOR]

Single image super‐resolution (SISR) has been revolutionized by convolutional neural networks (CNN). However, existing SISR algorithms have feature extraction and adaptive adjustment limitations, leading to information duplication and unsatisfactory image reconstruction. In this paper, we propose a deep and adaptive feature extraction attention network (DAAN), which first fully extracts shallow features and then adaptively captures precise and fine‐scale features by a deep feature extraction block (DFEB). It includes multi‐dimensional feature extraction blocks (MFEBs) that combine large kernel and dynamic convolution layers to improve large‐scale information utilization effectively. Finally, an enhanced spatial attention block (ESAB) to further selectively reinforce the transmission of details. A large number of experimental results show that our proposed model reconstruction performance is superior to existing classical methods. [ABSTRACT FROM AUTHOR]

Vision Transformers (ViTs) have become one of the main architectures in deep learning with the self-attention mechanism, and are becoming an alternative to Convolutional Neural Networks (CNNs) for remote sensing scene classification tasks. However, the earlier self-attention layer of ViTs focuses on local features rather than global features, and the deeper self-attention layer focuses on global features but ignores the different impact of different frequency information. This will greatly increase the training and computational cost due to the quadratic complexity of the self-attention mechanism on the long sequence representation. In this paper, we propose a hybrid CNN – vision transformer structure (HCVNet), which uses convolutional layers to replace the earlier self-attention layers, and a novel Frequency Multi-head Self Attention (F-MSA) mechanism to replace the deeper self-attention layers. Specifically, F-MSA is a dual-stream structure that reduces the computational cost and improves the classification performance by encoding the high/low frequency information separately. In addition, a Semantic-aware Localization (SaL) module is introduced, which can guide the selection of crop by learning prior knowledge, avoiding the issue of pure background sampling. Our method performed an accuracy value of 97.20 ± 0.02% on the Aerial Image Dataset and 93.89 ± 0.03% on the NWPU-RESISC45 Dataset, with low complexity costs. [ABSTRACT FROM AUTHOR]

Precise surveillance and assessment of spinal disorders are important for improving health care and patient survival rates. The assessment of spinal disorders, such as scoliosis assessment, depends heavily on precise vertebra landmark localization. However, existing methods usually search for only a handful of keypoints in a high-resolution image. In this paper, we propose the S2D-VLI VLDet network, a unified end-to-end vertebra landmark detection network for the assessment of scoliosis. The proposed network considers the spatially relevant information both from inside and between vertebrae. The new vertebral line interpolation method converts the training labels from sparse to dense, which can improve the network learning process and method performance. In addition, through the combined use of the Cartesian and polar coordinate systems in our method, the symmetric mean absolute percentage error (SMAPE) in scoliosis assessment can be reduced substantially. Specifically, as shown in the experiments, the SMAPE value decreases from 9.82 to 8.28. The experimental results indicate that our proposed approach is beneficial for estimating the Cobb angle and identifying landmarks in X-ray scans with low contrast. [ABSTRACT FROM AUTHOR]

Surface-enhanced Raman spectroscopy (SERS) has wide diagnostic applications due to narrow spectral features that allow multiplex analysis. We have previously developed a multiplexed, SERS-based nanosensor for micro-RNA (miRNA) detection called the inverse molecular sentinel (iMS). Machine learning (ML) algorithms have been increasingly adopted for spectral analysis due to their ability to discover underlying patterns and relationships within large and complex data sets. However, the high dimensionality of SERS data poses a challenge for traditional ML techniques, which can be prone to overfitting and poor generalization. Non-negative matrix factorization (NMF) reduces the dimensionality of SERS data while preserving information content. In this paper, we compared the performance of ML methods including convolutional neural network (CNN), support vector regression, and extreme gradient boosting combined with and without NMF for spectral unmixing of four-way multiplexed SERS spectra from iMS assays used for miRNA detection. CNN achieved high accuracy in spectral unmixing. Incorporating NMF before CNN drastically decreased memory and training demands without sacrificing model performance on SERS spectral unmixing. Additionally, models were interpreted using gradient class activation maps and partial dependency plots to understand predictions. These models were used to analyze clinical SERS data from single-plexed iMS in RNA extracted from 17 endoscopic tissue biopsies. CNN and CNN-NMF, trained on multiplexed data, performed most accurately with RMSElabel = 0.101 and 9.68 × 10–2, respectively. We demonstrated that CNN-based ML shows great promise in spectral unmixing of multiplexed SERS spectra, and the effect of dimensionality reduction on performance and training speed. Graphical abstract This is a visual representation of the abstract. [ABSTRACT FROM AUTHOR]

Due to the periodic changes of climate, cracks are widely developed in expansive soils, leading to the destruction of soil integrity, the deterioration of physical strength, and eventually the instability of the expansive soil slope and other disasters. In this paper, a deep learning-based modeling method was proposed for soil crack networks characterization through steps of segmentation, quantification and simulation. Inspired by the U-Net convolutional neural network, a dilated convolution module was added to the backbone to enhance the crack segmentation capability and a subpixel edge detection algorithm was followed for accurate crack edge detection. Then, a deterministic or stochastic method was designed for crack network simulation. A case study of an expansive soil slope on the bank of Wadong Main Canal in the Pi-Shi-Hang Irrigation District, China, was conducted. Results show that the dilated U-Net model gained 0.24 and 0.25 improvement in F1-score and IoU (Intersection over Union) comparing to the conventional segmentation method (Otsu) and crack edge precision was further improved by 5.38%. The performances of proposed method including the image labeling, effect of crack thickness and environmental conditions, etc., are also explored. To validate the simulated crack network, crack areas at different depths were measured through X-ray images. Comparing with the simulation result, mean error rate of 1.05% was achieved. Thus, the proposed method can efficiently characterize soil crack networks using the field acquired crack images. [ABSTRACT FROM AUTHOR]

Handwritten character recognition (HCR) is a challenging task because of high intra-class dissimilarity and high inter-class similarity among the character images. Therefore, the features that are used to represent the character images should be such that they maximize the inter-class variations and minimize intra-class variations. In this paper, a multilevel approach for recognition of Meitei Mayek handwritten characters using fusion of features strategy is presented. The proposed methodology has two levels of recognition. The first level employs a simple CNN. A method to identify the structurally similar character classes based on the probability values of the softmax function is also proposed. The fused feature set is employed in the second-level recognition to distinguish between these character classes, thereby enhancing the discriminative power of the fused feature set by reducing the search space in the second level. The fused feature set is a combination of traditional handcrafted feature descriptors and deep features learned by CNN. The fused feature set is fed to an SVM for second-level recognition. The experimental results show a superior performance of the proposed methodology in identifying the structurally similar character classes. This achieves an overall recognition accuracy of 97.08%, which sets the benchmark on the concerned Meitei Mayek handwritten character dataset. The methodology also shows significant results on MNIST, DIDA and CArDIS datasets. [ABSTRACT FROM AUTHOR]

At present, decision-making solutions developed based on deep learning (DL) models have received extensive attention in predictive maintenance (PM) applications along with the rapid improvement of computing power. Relying on the superior properties of shared weights and spatial pooling, convolutional neural networks (CNNs) can learn effective representations of health states from industrial data. Many developed CNN-based schemes, such as advanced CNNs that introduce residual learning and multi-scale learning, have shown good performance in health states recognition tasks under the assumption that all the classes are known. However, these schemes have no ability to deal with new abnormal samples that belong to state classes not part of the training set. In this paper, a collective decision framework for different CNNs is proposed. It is based on a one-vs.-rest network (OVRN) to simultaneously achieve classification of known and unknown health states. OVRNs learn class-specific discriminative features and enhance the ability to reject new abnormal samples incorporated to different CNNs. According to the validation results on the public dataset of the Tennessee Eastman process (TEP), the proposed CNN-based decision schemes incorporating an OVRN have outstanding recognition ability for samples of unknown heath states while maintaining satisfactory accuracy on known states. The results show that the new DL framework outperforms state-of-the-art CNNs, and the one based on residual and multi-scale learning has the best overall performance. [ABSTRACT FROM AUTHOR]

Control charts with conditional expected value (CEV) can be used with novel statistical techniques to monitor the means of moderately and lowly censored data. In recent years, machine learning and deep learning have been successfully combined with quality technology to solve many process control problems. This paper proposes a residual control chart combining a convolutional neural network (CNN) and support vector regression (SVR) for type-I censored data with the Weibull model. The CEV and exponentially weighted moving average (EWMA) statistics are used to generate training data for the CNN and SVR. The average run length shows that the proposed chart approach outperforms the traditional EWMA CEV chart approach in various shift sizes and censored rates. The proposed chart approach is suitable to be used in detecting small shift size for highly censored data. An illustrative example presents the application of the proposed method in an electronics industry. [ABSTRACT FROM AUTHOR]

Background: The Gleason grading system has been the most effective prediction for prostate cancer patients. This grading system provides this possibility to assess prostate cancer's aggressiveness and then constitutes an important factor for stratification and therapeutic decisions. However, determining Gleason grade requires highly-trained pathologists and is time-consuming and tedious, and suffers from inter-pathologist variability. To remedy these limitations, this paper introduces an automatic methodology based on transfer learning with pretrained convolutional neural networks (CNNs) for automatic Gleason grading of prostate cancer tissue microarray (TMA). Methods: Fifteen pretrained (CNNs): Efficient Nets (B0-B5), NasNetLarge, NasNetMobile, InceptionV3, ResNet-50, SeResnet 50, Xception, DenseNet121, ResNext50, and inception_resnet_v2 were fine-tuned on a dataset of prostate carcinoma TMA images. Six pathologists separately identified benign and cancerous areas for each prostate TMA image by allocating benign, 3, 4, or 5 Gleason grade for 244 patients. The dataset was labeled by these pathologists and majority vote was applied on pixel-wise annotations to obtain a unified label. Results: Results showed the NasnetLarge architecture is the best model among them in the classification of prostate TMA images of 244 patients with accuracy of 0.93 and area under the curve of 0.98. Conclusion: Our study can act as a highly trained pathologist to categorize the prostate cancer stages with more objective and reproducible results. [ABSTRACT FROM AUTHOR]

Hyperspectral Unmixing (HU), which involves decomposing mixed pixels in hyperspectral images into endmembers and abundance fractions, plays a critical role in spectral analysis. Recent advancements in deep learning methods have shown successful applications in hyperspectral analysis. This paper proposes an end-to-end network structure that combines a Convolutional Neural Network (CNN) and a Multilayer Perceptron (MLP). The 3D-CNN extracts high-level features from both spatial and spectral neighbourhoods of hyperspectral image patches, while the MLP maps these abstracted features to abundance fractions. Considering the challenge of acquiring manual labels, we adopt a Semi-Supervised learning approach that leverages unlabelled data to enhance training. We divide our training data into labelled and unlabelled subsets, defining distinct loss functions for each. Additionally, we introduce a neighbourhood similarity constraint to fully exploit spatial context information. To address scenarios where no labelled data is available, we employ Generative Adversarial Networks (GANs) to generate synthetic labelled samples. Experimental evaluations conducted on both synthetic and real datasets validate the effectiveness of our proposed method, which outperforms several commonly used and state-of-the-art HU methods. [ABSTRACT FROM AUTHOR]

In recent years, decomposition-based combination models have been widely used in wind power prediction. This type of method decomposes the highly volatile wind power into some relatively smooth subsequences, which reduces the difficulty of modeling. However, this might use information from future data in advance, creating the illusion of high prediction accuracy. Therefore, this paper proposes a wind power ultra-short-term prediction model based on fixed scale dual mode decomposition (FSDMD) and deep learning networks. First, the wind power series after fixed scale blocking is decomposed using ensemble empirical mode decomposition (EEMD), and use the improved variational mode decomposition (VMD) based on Spearman rank order correlation coefficient (SROCC) to decompose the obtained high-frequency components twice. Then, the appropriate mode components were selected by calculating the SROCC and experimental analysis, and combined with the convolutional neural network (CNN) and the bidirectional long short-term memory (BiLSTM) network to train the model. Finally, the historical data of wind turbines in a wind farm in Northwest China is used for example verification, and the comparison with other models in the two scenarios of sufficient and insufficient features. The results show that the proposed FSDMD–CNN–BiLSTM model has high prediction accuracy in both scenarios. Especially in the scenario of insufficient features, compared with CNN-BiLSTM model, RMSE, MAE and MAPE are reduced by 8.20,14.24 and 0.15, respectively. In addition, this paper verifies that mode decomposition can improve the performance of prediction model without using future features, which provides ideas for solving similar problems. [ABSTRACT FROM AUTHOR]

Accurate detection of pavement markings at the pixel level is crucial for enhancing traffic safety. The majority of current advanced deep-learning networks predominantly focus on localized features, neglecting the global context of pavement image. Such networks often result in discontinuous segmentation outcomes and suboptimal recovery of local details. In this paper, a robust model named C-Transformer is proposed to provide an effective solution to this challenge. The contributions of this paper primarily involve two aspects. Firstly, the proposed C-Transformer is designed to succinctly integrate convolution operations and self-attention, facilitating a comprehensive understanding of essential features. Secondly, an efficient Feed-Forward Network called Inverse Residual Feed-Forward Network is also proposed in this paper and deployed in C-Transformer to improve latent representations. Experimental results demonstrate that, compared to other state-of-the-art networks, the proposed C-Transformer achieves a performance enhancement of 0.93% in F-measure and a 1.64% improvement in Intersection-Over-Union. In particular, the robustness and effectiveness of the C-Transformer in accurate pavement marking detection are proved through field test results. This paper illustrates the feasibility of employing a hybrid Convolutional neural network-Transformer-based network for automatic robust pavement marking detection under noisy conditions. [ABSTRACT FROM AUTHOR]

The paper investigates the application of machine learning (ML) for voltage sag source localization (VSSL) in electrical power systems. To overcome feature-selection challenges for traditional ML methods and provide more meaningful sequential features for deep learning methods, the paper proposes three time-sample-based feature forms, and evaluates an existing feature form. The effectiveness of these feature forms is assessed using k-means clustering with k = 2 referred to as downstream and upstream classes, according to the direction of voltage sag origins. Through extensive voltage sag simulations, including noises in a regional electrical power network, k-means identifies a sequence involving the multiplication of positive-sequence current magnitude with the sine of its angle as the most prominent feature form. The study develops further traditional ML methods such as decision trees (DT), support vector machine (SVM), random forest (RF), k-nearest neighbor (KNN), an ensemble learning (EL), and a designed one-dimensional convolutional neural network (1D-CNN). The results found that the combination of 1D-CNN or SVM with the most prominent feature achieved the highest accuracies of 99.37% and 99.13%, respectively, with acceptable/fast prediction times, enhancing VSSL. The exceptional performance of the CNN was also approved by field measurements in a real power network. However, selecting the best ML methods for deployment requires a trade-off between accuracy and real-time implementation requirements. The research findings benefit network operators, large factory owners, and renewable energy park producers. They enable preventive maintenance, reduce equipment downtime/damage in industry and electrical power systems, mitigate financial losses, and facilitate the assignment of power-quality penalties to responsible parties. • Comprehensive study on enhanced voltage sag source localization assisted by ML. • Proposing three new time sample-based feature forms, effective for ML methods. • Identifying the most influential feature form (form 4) utilizing k-means clustering. • Developing diverse supervised models, including a designed one-dimensional CNN. • CNN-Feature form 4 achieved 99.37% accuracy with an acceptable prediction speed. [ABSTRACT FROM AUTHOR]

The paper investigates the application of machine learning (ML) for voltage sag source localization (VSSL) in electrical power systems. To overcome feature-selection challenges for traditional ML methods and provide more meaningful sequential features for deep learning methods, the paper proposes three time-sample-based feature forms, and evaluates an existing feature form. The effectiveness of these feature forms is assessed using k-means clustering with k = 2 referred to as downstream and upstream classes, according to the direction of voltage sag origins. Through extensive voltage sag simulations, including noises in a regional electrical power network, k-means identifies a sequence involving the multiplication of positive-sequence current magnitude with the sine of its angle as the most prominent feature form. The study develops further traditional ML methods such as decision trees (DT), support vector machine (SVM), random forest (RF), k-nearest neighbor (KNN), an ensemble learning (EL), and a designed one-dimensional convolutional neural network (1D-CNN). The results found that the combination of 1D-CNN or SVM with the most prominent feature achieved the highest accuracies of 99.37% and 99.13%, respectively, with acceptable/fast prediction times, enhancing VSSL. The exceptional performance of the CNN was also approved by field measurements in a real power network. However, selecting the best ML methods for deployment requires a trade-off between accuracy and real-time implementation requirements. The research findings benefit network operators, large factory owners, and renewable energy park producers. They enable preventive maintenance, reduce equipment downtime/damage in industry and electrical power systems, mitigate financial losses, and facilitate the assignment of power-quality penalties to responsible parties. • Comprehensive study on enhanced voltage sag source localization assisted by ML. • Proposing three new time sample-based feature forms, effective for ML methods. • Identifying the most influential feature form (form 4) utilizing k-means clustering. • Developing diverse supervised models, including a designed one-dimensional CNN. • CNN-Feature form 4 achieved 99.37% accuracy with an acceptable prediction speed. [ABSTRACT FROM AUTHOR]

In personal identity recognition systems, detecting a person's age, gender, and language using voice signal characteristics is a crucial issue, especially because of the importance of security considerations. Age, gender, and language classification problems are important in signal processing because they are used to analyze and understand human behavior, interactions, and preferences. This can be especially useful in the fields of human-computer interaction, psychology, and social science research. In this paper, a new system for detecting a speaker's age, gender, and language based on deep learning models is presented. Deep learning models have shown great efficacy in various fields of signal processing. For this paper, a range of deep models were tested, including convolutional neural networks (CNNs), recurrent neural network (RNN), and a fine-tuning ResNet34 architecture. Additionally, techniques such as transfer learning were applied to improve the efficiency of the proposed system. The input voice signals are preprocessed by applying the spectro-temporal transform to obtain additional features that can be fed to the ResNet34 model, which is designed specifically for the task of voice signal processing. The dataset used in this paper was sourced from the Mozilla common voice initiative, which is dedicated to advancing speech recognition and language identification technologies. The performance of the proposed algorithm was evaluated in the presence of Gaussian noise to determine its robustness. The experimental results demonstrated that the proposed algorithm significantly outperformed basic algorithms and other deep neural networks in terms of age and gender recognition from voice signals. [ABSTRACT FROM AUTHOR]

[Display omitted] • A fast accurate non-destructive quantitative analysis method of blended fabrics has been developed successfully using NIR and CNN-LSTM. • The CNN network structure in this paper is designed to adapt to a small sample regression. • The CNN-LSTM network designed in this paper can more accurately analyze the cotton content of cotton-polyester blended fabrics than PLS, CNN, and LSTM. • This CNN-LSTM method can accurately predict the cotton content of cotton-polyester blended fabrics with only simple MSC preprocessing. Accurate and rapid quantitative analysis of fiber content is important for blended fabric quality control and supervision. In this paper, a deep learning method based on an improved hybrid network of convolutional neural network (CNN) and long short-term memory (LSTM) to fast and accurate determine cotton content of cotton-polyester blended fabrics using near-infrared (NIR) spectroscopy. The cotton-polyester blended fabric samples were partitioned into training set, validation set and testing set in the ratio of 6:2:2 to develop the quantitative model of cotton content of blended fabric. Firstly, a one-dimensional CNN architecture is designed and modeled to obtain the CNN parameters and to evaluate the spectral preprocessing methods. Then, the CNN structure is modified and improved using LSTM to obtain a CNN-LSTM structure. The root mean square error (RMSE) of the validation set obtained by CNN model is 0.83%, which is 34.03% lower than that of the traditional partial least squares (PLS) model, and the RMSE of the testing set obtained by CNN model is 0.88%, which is 25.88% lower than that of the PLS model. The RMSE of the validation set obtained by CNN-LSTM model is 0.65%, which is 47.85% lower than that of the PLS model, and the RMSE of the testing set obtained by CNN-LSTM model is 0.75%, which is 36.57% lower than that of the PLS model. Compared with PLS and CNN models, the CNN-LSTM model can more accurately analyze the cotton content proportion of cotton-polyester blended fabrics, which provides a new fast and non-invasive method for the quantitative detection of fabrics. [ABSTRACT FROM AUTHOR]