Search

Regional persistent extreme cold events are meteorological disasters that cause serious harm to people's lives and production; however, they are very difficult to predict. Low-temperature weather systems and their effects have a significant low-frequency oscillation period (10–20 d and 30–60 d). This paper uses deep learning to analyze the extended-range time scale and predict regional persistent extreme cold events. The dominant low-frequency oscillation components of cold events are obtained via wavelet transform and Butterworth filtering. The low-frequency oscillation component is decomposed via empirical orthogonal function decomposition to extract the main spatial mode and time coefficient. A convolutional neural network is used to establish the correlation between large-scale circulations and the time coefficient of the low-frequency oscillation component of the lowest temperature. The proposed deep learning model exhibits good prediction accuracy for regional persistent extreme cold events with low-frequency oscillations. [ABSTRACT FROM AUTHOR]

In recent years, deep neural networks have enabled countless innovations in the field of image classification. Encouraged by success in this field, researchers worldwide have demonstrated how to use Convolutional Neural Network techniques in medical imaging problems. In this article, the results were obtained through the use of the EfficientNet in the task of classifying 14 different diseases based on chest X-ray images coming from the NIH (National Institutes of Health) ChestX-ray14 dataset. The approach addresses dataset imbalances by introducing a custom split to ensure fair representation. Binary cross entropy loss is utilized to handle the multi-label difficulty. The model architecture comprises an EfficientNet backbone for feature extraction, succeeded by sequential layers including GlobalAveragePooling, Dense, and BatchNormalization. The main contribution of this paper is a proposed solution that outperforms previous state-of-the-art deep learning models average area under the receiver operating characteristic curve—AUC-ROC (score: 84.28%). The usage of the transfer-learning technique and traditional deep learning engineering techniques was shown to enable us to obtain such results on consumer-class GPUs (graphics processing units). [ABSTRACT FROM AUTHOR]

Three frequently encountered problems—a variety of fault types, data with insufficient labels, and missing fault types—are the common challenges in the early fault diagnosis of space flywheel rotor systems. Focusing on the above issues, this paper proposes an intelligent early fault diagnosis method based on the multi-channel convolutional neural network with hierarchical branch and similarity clustering (HB-SC-MCCNN). First, a similarity clustering (SC) method is integrated into the parameter-shared dual MCCNN architecture to set up as the basic structural block. The hierarchical branch model and additional loss are then added to SC-MCCNN to form a hierarchical branch network, which simplifies the problem of fault multi-classification into binary classification with multi-steps. Based on the self-learning characteristics of the proposed model, the unlabeled data and the missing fault types in the training set are re-labeled to realize the re-training of the network. The results of the experiments for comparing the abilities between the proposed method and several advanced deep learning models confirm that on the established early fault dataset of the space flywheel rotor system, the proposed method successfully achieves the hierarchical diagnosis and presents stronger competitiveness in the case of insufficient labeled data and missing fault types at the same time. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD) is a neurodegenerative disease that can cause dementia and result in a severe reduction in brain function, inhibiting simple tasks, especially if no preventative care is taken. Over 1 in 9 Americans suffer from AD-induced dementia, and unpaid care for people with AD-related dementia is valued at USD 271.6 billion. Hence, various approaches have been developed for early AD diagnosis to prevent its further progression. In this paper, we first review other approaches that could be used for the early detection of AD. We then give an overview of our dataset and propose a deep convolutional neural network (CNN) architecture consisting of 7,866,819 parameters. This model comprises three different convolutional branches, each having a different length. Each branch is comprised of different kernel sizes. This model can predict whether a patient is non-demented, mild-demented, or moderately demented with a 99.05% three-class accuracy. In summary, the deep CNN model demonstrated exceptional accuracy in the early diagnosis of AD, offering a significant advancement in the field and the potential to improve patient care. [ABSTRACT FROM AUTHOR]

Catastrophic forgetting, which means a rapid forgetting of learned representations while learning new data/samples, is one of the main problems of deep neural networks. In this paper, we propose a novel incremental learning framework that can address the forgetting problem by learning new incoming data in an online manner. We develop a new incremental learning framework that can learn extra data or new classes with less catastrophic forgetting. We adopt the hippocampal memory process to the deep neural networks by defining the effective maximum of neural activation and its boundary to represent a feature distribution. In addition, we incorporate incremental QR factorization into the deep neural networks to learn new data with both existing labels and new labels with less forgetting. The QR factorization can provide the accurate subspace prior, and incremental QR factorization can reasonably express the collaboration between new data with both existing classes and new class with less forgetting. In our framework, a set of appropriate features (i.e., nodes) provides improved representation for each class. We apply our method to the convolutional neural network (CNN) for learning Cifar-100 and Cifar-10 datasets. The experimental results show that the proposed method efficiently alleviates the stability and plasticity dilemma in the deep neural networks by providing the performance stability of a trained network while effectively learning unseen data and additional new classes. [ABSTRACT FROM AUTHOR]

Surface plasmon resonance microscopy (SPRM) combines the principles of traditional microscopy with the versatility of surface plasmons to develop label-free imaging methods. This paper describes a proof-of-principles approach based on deep learning that utilized the Y-Net convolutional neural network model to improve the detection and analysis methodology of SPRM. A machine-learning based image analysis technique was used to provide a method for the one-shot analysis of SPRM images to estimate scattering parameters such as the scatterer location. The method was assessed by applying the approach to SPRM images and reconstructing an image from the network output for comparison with the original image. The results showed that deep learning can localize scatterers and predict other variables of scattering objects with high accuracy in a noisy environment. The results also confirmed that with a larger field of view, deep learning can be used to improve traditional SPRM such that it localizes and produces scatterer characteristics in one shot, considerably increasing the detection capabilities of SPRM. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) sensor often produces a shadow in pairs with the target due to its slant-viewing imaging. As a result, shadows in SAR images can provide critical discriminative features for classifiers, such as target contours and relative positions. However, shadows possess unique properties that differ from targets, such as low intensity and sensitivity to depression angles, making it challenging to extract depth features from shadows directly using convolutional neural networks (CNN). In this paper, we propose a new SAR image-classification framework to utilize target and shadow information comprehensively. First, we design a SAR image segmentation method to extract target regions and shadow masks. Second, based on SAR projection geometry, we propose a data-augmentation method to compensate for the geometric distortion of shadows due to differences in depression angles. Finally, we introduce a feature-enhancement module (FEM) based on depthwise separable convolution (DSC) and convolutional block attention module (CBAM), enabling deep networks to fuse target and shadow features adaptively. The experimental results on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset show that when only using target and shadow information, the published deep-learning models can still achieve state-of-the-art performance after embedding the FEM. [ABSTRACT FROM AUTHOR]

Semantic change detection (SCD) holds a critical place in remote sensing image interpretation, as it aims to locate changing regions and identify their associated land cover classes. Presently, post-classification techniques stand as the predominant strategy for SCD due to their simplicity and efficacy. However, these methods often overlook the intricate relationships between alterations in land cover. In this paper, we argue that comprehending the interplay of changes within land cover maps holds the key to enhancing SCD's performance. With this insight, a Temporal-Transform Module (TTM) is designed to capture change relationships across temporal dimensions. TTM selectively aggregates features across all temporal images, enhancing the unique features of each temporal image at distinct pixels. Moreover, we build a Temporal-Transform Network (TTNet) for SCD, comprising two semantic segmentation branches and a binary change detection branch. TTM is embedded into the decoder of each semantic segmentation branch, thus enabling TTNet to obtain better land cover classification results. Experimental results on the SECOND dataset show that TTNet achieves enhanced performance when compared to other benchmark methods in the SCD task. In particular, TTNet elevates mIoU accuracy by a minimum of 1.5% in the SCD task and 3.1% in the semantic segmentation task. [ABSTRACT FROM AUTHOR]

Hyperspectral sensors acquire spectral responses from objects with a large number of narrow spectral bands. The large volume of data may be costly in terms of storage and computational requirements. In addition, hyperspectral data are often information-wise redundant. Band selection intends to overcome these limitations by selecting a small subset of spectral bands that provide more information or better performance for particular tasks. However, existing band selection techniques do not directly maximize the task-specific performance, but rather utilize hand-crafted metrics as a proxy to the final goal of performance improvement. In this paper, we propose a deep learning (DL) architecture composed of a constrained measurement learning network for band selection, followed by a classification network. The proposed joint DL architecture is trained in a data-driven manner to optimize the classification loss along band selection. In this way, the proposed network directly learns to select bands that enhance the classification performance. Our evaluation results with Indian Pines (IP) and the University of Pavia (UP) datasets show that the proposed constrained measurement learning-based band selection approach provides higher classification accuracy compared to the state-of-the-art supervised band selection methods for the same number of bands selected. The proposed method shows 89.08 % and 97.78 % overall accuracy scores for IP and UP respectively, being 1.34 % and 2.19 % higher than the second-best method. [ABSTRACT FROM AUTHOR]

Semantic segmentation of remote sensing images has been widely used in environmental protection, geological disaster discovery, and natural resource assessment. With the rapid development of deep learning, convolutional neural networks (CNNs) have dominated semantic segmentation, relying on their powerful local information extraction capabilities. Due to the locality of convolution operation, it can be challenging to obtain global context information directly. However, Transformer has excellent potential in global information modeling. This paper proposes a new hybrid convolutional and Transformer semantic segmentation model called CTFuse, which uses a multi-scale convolutional attention module in the convolutional part. CTFuse is a serial structure composed of a CNN and a Transformer. It first uses convolution to extract small-size target information and then uses Transformer to embed large-size ground target information. Subsequently, we propose a spatial and channel attention module in convolution to enhance the representation ability for global information and local features. In addition, we also propose a spatial and channel attention module in Transformer to improve the ability to capture detailed information. Finally, compared to other models used in the experiments, our CTFuse achieves state-of-the-art results on the International Society of Photogrammetry and Remote Sensing (ISPRS) Vaihingen and ISPRS Potsdam datasets. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) classification has been extensively applied for analyzing remotely sensed images. HSI data consist of multiple bands that provide abundant spatial information. Convolutional neural networks (CNNs) have emerged as powerful deep learning methods for processing visual data. In recent work, CNNs have shown impressive results in HSI classification. In this paper, we propose a hierarchical neural network architecture called feature extraction with hybrid spectral CNN (FE-HybridSN) to extract superior spectral–spatial features. FE-HybridSN effectively captures more spectral–spatial information while reducing computational complexity. Considering the prevalent issue of class imbalance in experimental datasets (IP, UP, SV) and real-world hyperspectral datasets, we apply the focal loss to mitigate these problems. The focal loss reconstructs the loss function and facilitates effective achievement of the aforementioned goals. We propose a framework (FEHN-FL) that combines FE-HybridSN and the focal loss for HSI classification and then conduct extensive HSI classification experiments using three remote sensing datasets: Indian Pines (IP), University of Pavia (UP), and Salinas Scene (SV). Using cross-entropy loss as a baseline, we assess the hyperspectral classification performance of various backbone networks and examine the influence of different spatial sizes on classification accuracy. After incorporating focal loss as our loss function, we not only compare the classification performance of the FE-HybridSN backbone network under different loss functions but also evaluate their convergence rates during training. The proposed classification framework demonstrates satisfactory performance compared to state-of-the-art end-to-end deep-learning-based methods, such as 2D-CNN, 3D-CNN, etc. [ABSTRACT FROM AUTHOR]

Currently, the task of maintaining cybersecurity and reliability in various computer systems is relevant. This problem can be solved by detecting anomalies in the log data, which are represented as a stream of textual descriptions of events taking place. For these purposes, reduction to a One-class classification problem is used. Standard One-class classification methods do not achieve good results. Deep learning approaches are more effective. However, they are not robust to outliers and require a lot of computational effort. In this paper, we propose a new robust approach based on a convolutional autoencoder using fuzzy clustering. The proposed approach uses a parallel convolution operation to feature extraction, which makes it more efficient than the currently popular Transformer architecture. In the course of the experiments, the proposed approach showed the best results for both the cybersecurity and the reliability problems compared to existing approaches. It was also shown that the proposed approach is robust to outliers in the training set. [ABSTRACT FROM AUTHOR]

Deep learning has achieved great successes in performing many visual recognition tasks, including object detection. Nevertheless, existing deep networks are computationally expensive and memory intensive, hindering their deployment in resource-constrained environments, such as mobile or embedded devices that are widely used by city travellers. Recently, estimating city-level travel patterns using street imagery has been shown to be a potentially valid way according to a case study with Google Street View (GSV), addressing a critical challenge in transport object detection. This paper presents a compressed deep network using tensor decomposition to detect transport objects in GSV images, which is sustainable and eco-friendly. In particular, a new dataset named Transport Mode Share-Tokyo (TMS-Tokyo) is created to serve the public for transport object detection. This is based on the selection and filtering of 32,555 acquired images that involve 50,827 visible transport objects (including cars, pedestrians, buses, trucks, motors, vans, cyclists and parked bicycles) from the GSV imagery of Tokyo. Then a compressed convolutional neural network (termed SVDet) is proposed for street view object detection via tensor train decomposition on a given baseline detector. The method proposed herein yields a mean average precision (mAP) of 77.6% on the newly introduced dataset, TMS-Tokyo, necessitating just 17.29 M parameters and a computational capacity of 16.52 G FLOPs. As such, it markedly surpasses the performance of existing state-of-the-art methods documented in the literature. [ABSTRACT FROM AUTHOR]

Smart home monitoring systems via internet of things (IoT) are required for taking care of elders at home. They provide the flexibility of monitoring elders remotely for their families and caregivers. Activities of daily living are an efficient way to effectively monitor elderly people at home and patients at caregiving facilities. The monitoring of such actions depends largely on IoT-based devices, either wireless or installed at different places. This paper proposes an effective and robust layered architecture using multisensory devices to recognize the activities of daily living from anywhere. Multimodality refers to the sensory devices of multiple types working together to achieve the objective of remote monitoring. Therefore, the proposed multimodal-based approach includes IoT devices, such as wearable inertial sensors and videos recorded during daily routines, fused together. The data from these multi-sensors have to be processed through a pre-processing layer through different stages, such as data filtration, segmentation, landmark detection, and 2D stick model. In next layer called the features processing, we have extracted, fused, and optimized different features from multimodal sensors. The final layer, called classification, has been utilized to recognize the activities of daily living via a deep learning technique known as convolutional neural network. It is observed from the proposed IoT-based multimodal layered system's results that an acceptable mean accuracy rate of 84.14% has been achieved. [ABSTRACT FROM AUTHOR]

A brain–computer interface (BCI) is a computer-based system that allows for communication between the brain and the outer world, enabling users to interact with computers using neural activity. This brain signal is obtained from electroencephalogram (EEG) signals. A significant obstacle to the development of BCIs based on EEG is the classification of subject-independent motor imagery data since EEG data are very individualized. Deep learning techniques such as the convolutional neural network (CNN) have illustrated their influence on feature extraction to increase classification accuracy. In this paper, we present a multi-branch (five branches) 2D convolutional neural network that employs several hyperparameters for every branch. The proposed model achieved promising results for cross-subject classification and outperformed EEGNet, ShallowConvNet, DeepConvNet, MMCNN, and EEGNet_Fusion on three public datasets. Our proposed model, EEGNet Fusion V2, achieves 89.6% and 87.8% accuracy for the actual and imagined motor activity of the eegmmidb dataset and scores of 74.3% and 84.1% for the BCI IV-2a and IV-2b datasets, respectively. However, the proposed model has a bit higher computational cost, i.e., it takes around 3.5 times more computational time per sample than EEGNet_Fusion. [ABSTRACT FROM AUTHOR]

Crowd counting, as a basic computer vision task, plays an important role in many fields such as video surveillance, accident prediction, public security, and intelligent transportation. At present, crowd counting tasks face various challenges. Firstly, due to the diversity of crowd distribution and increasing population density, there is a phenomenon of large-scale crowd aggregation in public places, sports stadiums, and stations, resulting in very serious occlusion. Secondly, when annotating large-scale datasets, positioning errors can also easily affect training results. In addition, the size of human head targets in dense images is not consistent, making it difficult to identify both near and far targets using only one network simultaneously. The existing crowd counting methods mainly use density plot regression methods. However, this framework does not distinguish the features between distant and near targets and cannot adaptively respond to scale changes. Therefore, the detection performance in areas with sparse population distribution is not good. To solve such problems, we propose an adaptive multi-scale far and near distance network based on the convolutional neural network (CNN) framework for counting dense populations and achieving a good balance between accuracy, inference speed, and performance. However, on the feature level, in order to enable the model to distinguish the differences between near and far features, we use stacked convolution layers to deepen the depth of the network, allocate different receptive fields according to the distance between the target and the camera, and fuse the features between nearby targets to enhance the feature extraction ability of pedestrians under nearby targets. Secondly, depth information is used to distinguish distant and near targets of different scales and the original image is cut into four different patches to perform pixel-level adaptive modeling on the population. In addition, we add density normalized average precision (nAP) indicators to analyze the accuracy of our method in spatial positioning. This paper validates the effectiveness of NF-Net on three challenging benchmarks in Shanghai Tech Part A and B, UCF_ CC_50, and UCF-QNRF datasets. Compared with SOTA, it has more significant performance in various scenarios. In the UCF-QNRF dataset, it is further validated that our method effectively solves the interference of complex backgrounds. [ABSTRACT FROM AUTHOR]

Video anomaly event detection (VAED) is one of the key technologies in computer vision for smart surveillance systems. With the advent of deep learning, contemporary advances in VAED have achieved substantial success. Recently, weakly supervised VAED (WVAED) has become a popular VAED technical route of research. WVAED methods do not depend on a supplementary self-supervised substitute task, yet they can assess anomaly scores straightway. However, the performance of WVAED methods depends on pretrained feature extractors. In this paper, we first address taking advantage of two pretrained feature extractors for CNN (e.g., C3D and I3D) and ViT (e.g., CLIP), for effectively extracting discerning representations. We then consider long-range and short-range temporal dependencies and put forward video snippets of interest by leveraging our proposed temporal self-attention network (TSAN). We design a multiple instance learning (MIL)-based generalized architecture named CNN-ViT-TSAN, by using CNN- and/or ViT-extracted features and TSAN to specify a series of models for the WVAED problem. Experimental results on publicly available popular crowd datasets demonstrated the effectiveness of our CNN-ViT-TSAN. [ABSTRACT FROM AUTHOR]

As an essential technology for intelligent transportation management and traffic risk prevention and control, vehicle detection plays a significant role in the comprehensive evaluation of the intelligent transportation system. However, limited by the small size of vehicles in satellite remote sensing images and lack of sufficient texture features, its detection performance is far from satisfactory. In view of the unclear edge structure of small objects in the super-resolution (SR) reconstruction process, deep convolutional neural networks are no longer effective in extracting small-scale feature information. Therefore, a vehicle detection network based on remote sensing images (VDNET-RSI) is constructed in this article. The VDNET-RSI contains a two-stage convolutional neural network for vehicle detection. In the first stage, a partial convolution-based padding adopts the improved Local Implicit Image Function (LIIF) to reconstruct high-resolution remote sensing images. Then, the network associated with the results from the first stage is used in the second stage for vehicle detection. In the second stage, the super-resolution module, detection heads module and convolutional block attention module adopt the increased object detection framework to improve the performance of small object detection in large-scale remote sensing images. The publicly available DIOR dataset is selected as the experimental dataset to compare the performance of VDNET-RSI with that of the state-of-the-art models in vehicle detection based on satellite remote sensing images. The experimental results demonstrated that the overall precision of VDNET-RSI reached 62.9%, about 6.3%, 38.6%, 39.8% higher than that of YOLOv5, Faster-RCNN and FCOS, respectively. The conclusions of this paper can provide a theoretical basis and key technical support for the development of intelligent transportation. [ABSTRACT FROM AUTHOR]

With the continuous development of surface observation methods and technologies, we can acquire multiple sources of data more effectively in the same geographic area. The quality and availability of these data have also significantly improved. Consequently, how to better utilize multi-source data to represent ground information has become an important research question in the field of geoscience. In this paper, a novel model called multi-modal transformer cascaded fusion net (MMTCFN) is proposed for fusion and classification of multi-modal remote sensing data, Hyperspectral Imagery (HSI) and LiDAR data. Feature fusion and feature extraction are the two stages of the model. First, in the feature extraction stage, a three-branch cascaded Convolutional Neural Network (CNN) framework is employed to fully leverage the advantages of convolutional operators in extracting shallow-level local features. Based on this, we generated multi-modal long-range integrated deep features utilizing the transformer-based vectorized pixel group transformer (VPGT) module during the feature fusion stage. In the VPGT block, we designed a vectorized pixel group embedding that preserves the global features extracted from the three branches in a non-overlapping multi-space manner. Moreover, we introduce the DropKey mechanism into the multi-head self-attention (MHSA) to alleviate overfitting caused by insufficient training samples. Finally, we employ a probabilistic decision fusion strategy to integrate multiple class estimations, assigning a specific category to each pixel. This model was experimented on three HSI-LiDAR datasets with balanced and unbalanced training samples. The proposed model outperforms the other seven SOTA approaches in terms of OA performance, proving the superiority of MMTCFN for the HSI-LiDAR classification task. [ABSTRACT FROM AUTHOR]

Remote Sensing Image processing is a traditional research field, where RSI object detection is one of the most important directions. This paper focuses on an inherent problem of multi-stage object detection frameworks: the coupling error transmitting problem. In brief, because of the coupling method between the classifier and the regressor, the traditional multi-stage Detection frameworks tend to be fallible when encountering coarse object proposals. To deal with this problem, this article proposes a novel deep learning-based multi-stage object detection framework. Specifically, a novel network head architecture with a multi-to-one coupling method is proposed to avoid the coupling error of the traditional network head architecture. Moreover, it is found that the traditional network head architecture is more efficient than the novel network architecture when encountering fine object proposals. Considering this phenomenon, a proposal-consistent cooperation mechanism between the network heads is proposed. This mechanism makes the traditional network head and the novel network head develop each other's advantages and avoid the disadvantages. Experiments with different backbone networks on three publicly available data sets have shown the effectiveness of the proposed method since mAP is proposed as 0.7% to 12.3% on most models and data sets. [ABSTRACT FROM AUTHOR]

The creation of crop type maps from satellite data has proven challenging and is often impeded by a lack of accurate in situ data. Street-level imagery represents a new potential source of in situ data that may aid crop type mapping, but it requires automated algorithms to recognize the features of interest. This paper aims to demonstrate a method for crop type (i.e., maize, wheat and others) recognition from street-level imagery based on a convolutional neural network using a bottom-up approach. We trained the model with a highly accurate dataset of crowdsourced labelled street-level imagery using the Picture Pile application. The classification results achieved an AUC of 0.87 for wheat, 0.85 for maize and 0.73 for others. Given that wheat and maize are two of the most common food crops grown globally, combined with an ever-increasing amount of available street-level imagery, this approach could help address the need for improved global crop type monitoring. Challenges remain in addressing the noise aspect of street-level imagery (i.e., buildings, hedgerows, automobiles, etc.) and uncertainties due to differences in the time of day and location. Such an approach could also be applied to developing other in situ data sets from street-level imagery, e.g., for land use mapping or socioeconomic indicators. [ABSTRACT FROM AUTHOR]

Simple Summary: Structure name standardization is a critical problem in Radiotherapy planning systems to correctly identify the various Organs-at-Risk, Planning Target Volumes and 'Other' organs for monitoring present and future medications. We propose a deep neural network-based approach on the multimodal vision-language prostate cancer patient data that provides state-of-the-art results for structure name standardization. Our framework considers for the first time, both the bony anatomy along with radiation dose information and the textual physician-given names of the structures present in the prostate of cancer patients. The pipeline presented here, helps in automatic standardization of structure names given by physicians with high accuracy. Our pipeline can successfully standardize the Organs-at-Risk and the Planning Target Volumes, which are of utmost interest to the clinicians and simultaneously, performs very well on the 'Other' organs. We performed comprehensive experiments by varying input data modalities to show that using masked images and masked dose data with text outperforms the combination of other input modalities. We also undersampled the majority class, i.e., the 'Other' class, at different degrees and conducted extensive experiments to demonstrate that a small amount of majority class undersampling is essential for superior performance. Overall, our proposed integrated, deep neural network-based architecture for prostate structure name standardization can solve several challenges associated with multimodal data. Physicians often label anatomical structure sets in Digital Imaging and Communications in Medicine (DICOM) images with nonstandard random names. Hence, the standardization of these names for the Organs at Risk (OARs), Planning Target Volumes (PTVs), and 'Other' organs is a vital problem. This paper presents novel deep learning methods on structure sets by integrating multimodal data compiled from the radiotherapy centers of the US Veterans Health Administration (VHA) and Virginia Commonwealth University (VCU). These de-identified data comprise 16,290 prostate structures. Our method integrates the multimodal textual and imaging data with Convolutional Neural Network (CNN)-based deep learning approaches such as CNN, Visual Geometry Group (VGG) network, and Residual Network (ResNet) and shows improved results in prostate radiotherapy structure name standardization. Evaluation with macro-averaged F1 score shows that our model with single-modal textual data usually performs better than previous studies. The models perform well on textual data alone, while the addition of imaging data shows that deep neural networks achieve better performance using information present in other modalities. Additionally, using masked images and masked doses along with text leads to an overall performance improvement with the CNN-based architectures than using all the modalities together. Undersampling the majority class leads to further performance enhancement. The VGG network on the masked image-dose data combined with CNNs on the text data performs the best and presents the state-of-the-art in this domain. [ABSTRACT FROM AUTHOR]

Some diseases are known to cause or coincide with volume changes of certain structures in the body. Since these changes can be used to identify diseases, in this paper, we aimed to discover such new correlations. To this end, we trained a machine learning model based on the TotalSegmentator model on computed tomography (CT) image data, to segment 104 anatomical structures, while trying to improve the accuracy of the model. We then used the model to segment CT scans of decedents who had at least one of 18 diseases. After correlating the structure volumes with disease occurrences, a possible new correlation between chronic artery failure and iliac artery volume was found and others were confirmed. However, due to the limitations of the model and the underlying data, further research is required. [ABSTRACT FROM AUTHOR]

Convolutional Neural Networks (CNNs) have exhibited remarkable potential in effectively tackling the intricate task of classifying MRI images, specifically in Alzheimer's disease detection and brain tumor identification. While CNNs optimize their parameters automatically through training processes, finding the optimal values for these parameters can still be a challenging task due to the complexity of the search space and the potential for suboptimal results. Consequently, researchers often encounter difficulties determining the ideal parameter settings for CNNs. This challenge necessitates using trial-and-error methods or expert judgment, as the search for the best combination of parameters involves exploring a vast space of possibilities. Despite the automatic optimization during training, the process does not guarantee finding the globally-optimal parameter values. Hence, researchers often rely on iterative experimentation and expert knowledge to fine-tune these parameters and maximize CNN performance. This poses a significant obstacle in developing real-world applications that leverage CNNs for MRI image analysis. This paper presents a new hybrid model that combines the Particle Swarm Optimization (PSO) algorithm with CNNs to enhance detection and classification capabilities. Our method utilizes the PSO algorithm to determine the optimal configuration of CNN hyper-parameters. Subsequently, these optimized parameters are applied to the CNN architectures for classification. As a result, our hybrid model exhibits improved prediction accuracy for brain diseases while reducing the loss of function value. To evaluate the performance of our proposed model, we conducted experiments using three benchmark datasets. Two datasets were utilized for Alzheimer's disease: the Alzheimer's Disease Neuroimaging Initiative (ADNI) and an international dataset from Kaggle. The third dataset focused on brain tumors. The experimental assessment demonstrated the superiority of our proposed model, achieving unprecedented accuracy rates of 98.50%, 98.83%, and 97.12% for the datasets mentioned earlier, respectively. [ABSTRACT FROM AUTHOR]

X-ray diagnostics are widely used to detect various diseases, such as bone fracture, pneumonia, or intracranial hemorrhage. This method is simple and accessible in most hospitals, but requires an expert who is sometimes unavailable. Today, some diagnoses are made with the help of deep learning algorithms based on Convolutional Neural Networks (CNN), but these algorithms show limitations. Recently, Capsule Networks (CapsNet) have been proposed to overcome these problems. In our work, CapsNet is used to detect whether a chest X-ray image has disease (COVID or pneumonia) or is healthy. An improved model called DRCaps is proposed, which combines the advantage of CapsNet and the dilation rate (dr) parameter to manage images with 226 × 226 resolution. We performed experiments with 16,669 chest images, in which our model achieved an accuracy of 90%. Furthermore, the model size is 11M with a reconstruction stage, which helps to avoid overfitting. Experiments show how the reconstruction stage works and how we can avoid the max-pooling operation for networks with a stride and dilation rate to downsampling the convolution layers. In this paper, DRCaps is superior to other comparable models in terms of accuracy, parameters, and image size handling. The main idea is to keep the model as simple as possible without using data augmentation or a complex preprocessing stage. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have been extensively utilized in medical image processing to automatically extract meaningful features and classify various medical conditions, enabling faster and more accurate diagnoses. In this paper, LeNet, a classic CNN architecture, has been successfully applied to breast cancer data analysis. It demonstrates its ability to extract discriminative features and classify malignant and benign tumors with high accuracy, thereby supporting early detection and diagnosis of breast cancer. LeNet with corrected Rectified Linear Unit (ReLU), a modification of the traditional ReLU activation function, has been found to improve the performance of LeNet in breast cancer data analysis tasks via addressing the "dying ReLU" problem and enhancing the discriminative power of the extracted features. This has led to more accurate, reliable breast cancer detection and diagnosis and improved patient outcomes. Batch normalization improves the performance and training stability of small and shallow CNN architecture like LeNet. It helps to mitigate the effects of internal covariate shift, which refers to the change in the distribution of network activations during training. This classifier will lessen the overfitting problem and reduce the running time. The designed classifier is evaluated against the benchmarking deep learning models, proving that this has produced a higher recognition rate. The accuracy of the breast image recognition rate is 89.91%. This model will achieve better performance in segmentation, feature extraction, classification, and breast cancer tumor detection. [ABSTRACT FROM AUTHOR]

Timely information about the need to thin forests is vital in forest management to maintain a healthy forest while maximizing income. Currently, very-high-spatial-resolution remote sensing data can provide crucial assistance to experts when evaluating the maturity of thinnings. Nevertheless, this task is still predominantly carried out in the field and demands extensive resources. This paper presents a deep convolutional neural network (DCNN) to detect the necessity and urgency of carrying out thinnings using only remote sensing data. The approach uses very-high-spatial-resolution RGB and near-infrared orthophotos; a canopy height model (CHM); a digital terrain model (DTM); the slope; and reference data, which, in this case, originate from spruce-dominated forests in the Austrian Alps. After tuning, the model achieves an F1 score of 82.23% on our test data, which indicates that the model is usable in a practical setting. We conclude that DCNNs are capable of detecting the need to carry out thinnings in forests. In contrast, attempts to assess the urgency of the need for thinnings with DCNNs proved to be unsuccessful. However, additional data, such as age or yield class, have the potential to improve the results. Our investigation into the influence of each individual input feature shows that orthophotos appear to contain the most relevant information for detecting the need for thinning. Moreover, we observe a gain in performance when adding the CHM and slope, whereas adding the DTM harms the model's performance. [ABSTRACT FROM AUTHOR]

Photoacoustic (PA) imaging can be used to monitor high-intensity focused ultrasound (HIFU) therapies because ablation changes the optical absorption spectrum of the tissue, and this change can be detected with PA imaging. Multi-wavelength photoacoustic (MWPA) imaging makes this change easier to detect by repeating PA imaging at multiple optical wavelengths and sampling the optical absorption spectrum more thoroughly. Real-time pixel-wise classification in MWPA imaging can assist clinicians in monitoring HIFU lesion formation and will be a crucial milestone towards full HIFU therapy automation based on artificial intelligence. In this paper, we present a deep-learning-based approach to segment HIFU lesions in MWPA images. Ex vivo bovine tissue is ablated with HIFU and imaged via MWPA imaging. The acquired MWPA images are then used to train and test a convolutional neural network (CNN) for lesion segmentation. Traditional machine learning algorithms are also trained and tested to compare with the CNN, and the results show that the performance of the CNN significantly exceeds traditional machine learning algorithms. Feature selection is conducted to reduce the number of wavelengths to facilitate real-time implementation while retaining good segmentation performance. This study demonstrates the feasibility and high performance of the deep-learning-based lesion segmentation method in MWPA imaging to monitor HIFU lesion formation and the potential to implement this method in real time. [ABSTRACT FROM AUTHOR]

Universal adversarial perturbations are image-agnostic and model-independent noise that, when added to any image, can mislead the trained deep convolutional neural networks into the wrong prediction. Since these universal adversarial perturbations can seriously jeopardize the security and integrity of practical deep learning applications, the existing techniques use additional neural networks to detect the existence of these noises at the input image source. In this paper, we demonstrate an attack strategy that, when activated by rogue means (e.g., malware, trojan), can bypass these existing countermeasures by augmenting the adversarial noise at the AI hardware accelerator stage. We demonstrate the accelerator-level universal adversarial noise attack on several deep learning models using co-simulation of the software kernel of the Conv2D function and the Verilog RTL model of the hardware under the FuseSoC environment. [ABSTRACT FROM AUTHOR]

With the advent of smart mobile devices, end users get used to transmitting and storing their individual privacy in them, which, however, has aroused prominent security concerns inevitably. In recent years, numerous researchers have primarily proposed to utilize motion sensors to explore implicit authentication techniques. Nonetheless, for them, there are some significant challenges in real-world scenarios. For example, depending on the expert knowledge, the authentication accuracy is relatively low due to some difficulties in extracting user micro features, and noisy labels in the training phrase. To this end, this paper presents a real-time sensor-based mobile user authentication approach, ST-SVD, a semi-supervised Teacher–Student (TS) tri-training algorithm, and a system with client–server (C-S) architecture. (1) With S-transform and singular value decomposition (ST-SVD), we enhance user micro features by transforming time-series signals into 2D time-frequency images. (2) We employ a Teacher–Student Tri-Training algorithm to reduce label noise within the training sets. (3) To obtain a set of robust parameters for user authentication, we input the well-labeled samples into a CNN (convolutional neural network) model, which validates our proposed system. Experimental results on large-scale datasets show that our approach achieves authentication accuracy of 96.32%, higher than the existing state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The accurate classification of seizure types using electroencephalography (EEG) signals plays a vital role in determining a precise treatment plan and therapy for epilepsy patients. Among the available deep network models, Convolutional Neural Networks (CNNs) are the most widely adopted models for learning and representing EEG signals. However, typical CNNs have high computational complexity, leading to overfitting problems. This paper proposes the design of two effective, lightweight deep network models; the 1D multiscale neural network (1D-MSCNet) model and the Long Short-term Memory (LSTM)-based compact CNN (EEG-LSTMNet) model. The 1D-MSCNet model comprises three modules: a spectral–temporal convolution module, a spatial convolution module, and a classification module. It extracts features from input EEG trials at multiple frequency/time ranges, identifying relationships between the spatial distribution of their channels. The EEG-LSTMNet model includes three convolutional layers, namely temporal, depthwise, and separable layers, a single LSTM layer, and two fully connected classification layers to extract discriminative EEG feature representations. Both models have been applied to the same EEG trials collected from the Temple University Hospital (TUH) database. Results revealed F1-score values of 96.9% and 98.4% for the 1D-MSCNet and EEG-LSTMNet, respectively. Based on the demonstrated outcomes, both models outperform related state-of-the-art methods due to their architectures' adoption of 1D modules and layers that reduce the computational effort needed, solve the overfitting problem, and enhance classification efficiency. Hence, both models could be valuable additions for neurologists to help them decide upon precise treatments and drugs for patients depending on their type of seizure. [ABSTRACT FROM AUTHOR]

The wind microclimate plays an important role in architectural design, and computational fluid dynamics is a method commonly used for analyzing the issue. However, due to its high technical difficulty and time-consuming nature, it limits the interaction and exploration between designers and environment performance analyses. To address the issue, scholars have proposed a series of approximation models based on machine learning that have partially improved computational efficiency. However, these methods face challenges in terms of balancing applicability, prediction accuracy, and sample size. In this paper, we propose a method based on the classic Vggnet deep convolutional neural network as the backbone to construct an approximate model for predicting steady-state flow fields in urban areas. The method is trained on a small amount of sample data and can be extended to calculate the wind environment performance. Furthermore, we investigated the differences between geometric representation methods, such as the Boolean network representation and signed distance function, as well as different structure models, such as Vgg-CFD-11, Vgg-CFD-13, Vgg-CFD-16, and Vgg-CFD-19. The results indicate that the model can be trained using a small amount of sample data, and all models generally possess the ability to predict the wind environment. The best performance on the validation set and test set was achieved with an RMSE (Root Mean Square Error) of 0.7966 m/s and 2.2345 m/s, respectively, and an R-Squared score of 0.9776 and 0.8455. Finally, we embedded the best-performing model into an architect-friendly urban comprehensive analysis platform, URBAN NEURAL-CFD. [ABSTRACT FROM AUTHOR]

Ground-based cloud images contain a wealth of cloud information and are an important part of meteorological research. However, in practice, ground cloud images must be segmented and classified to obtain the cloud volume, cloud type and cloud coverage. Existing methods ignore the relationship between cloud segmentation and classification, and usually only one of these is studied. Accordingly, our paper proposes a novel method for the joint classification and segmentation of cloud images, called CloudY-Net. Compared to the basic Y-Net framework, which extracts feature maps from the central layer, we extract feature maps from four different layers to obtain more useful information to improve the classification accuracy. These feature maps are combined to produce a feature vector to train the classifier. Additionally, the multi-head self-attention mechanism is implemented during the fusion process to enhance the information interaction among features further. A new module called Cloud Mixture-of-Experts (C-MoE) is proposed to enable the weights of each feature layer to be automatically learned by the model, thus improving the quality of the fused feature representation. Correspondingly, experiments are conducted on the open multi-modal ground-based cloud dataset (MGCD). The results demonstrate that the proposed model significantly improves the classification accuracy compared to classical networks and state-of-the-art algorithms, with classification accuracy of 88.58%. In addition, we annotate 4000 images in the MGCD for cloud segmentation and produce a cloud segmentation dataset called MGCD-Seg. Then, we obtain a 96.55 mIoU on MGCD-Seg, validating the efficacy of our method in ground-based cloud imagery segmentation and classification. [ABSTRACT FROM AUTHOR]

Although measuring worker productivity is crucial, the measurement of the productivity of each worker is challenging due to their dispersion across various construction jobsites. This paper presents a framework for measuring productivity based on an inertial measurement unit (IMU) and activity classification. Two deep learning algorithms and three sensor combinations were utilized to identify and analyze the feasibility of the framework in masonry work. Using the proposed method, worker activity classification could be performed with a maximum accuracy of 96.70% using the convolutional neural network model with multiple sensors, and a minimum accuracy of 72.11% using the long short-term memory (LSTM) model with a single sensor. Productivity could be measured with an accuracy of up to 96.47%. The main contributions of this study are the proposal of a method for classifying detailed activities and an exploration of the effect of the number of IMU sensors used in measuring worker productivity. [ABSTRACT FROM AUTHOR]

Brain cancer is widely recognised as one of the most aggressive types of tumors. In fact, approximately 70% of patients diagnosed with this malignant cancer do not survive. In this paper, we propose a method aimed to detect and localise brain cancer, starting from the analysis of magnetic resonance images. The proposed method exploits deep learning, in particular convolutional neural networks and class activation mapping, in order to provide explainability by highlighting the areas of the medical image related to brain cancer (from the model point of view). We evaluate the proposed method with 3000 magnetic resonances using a free available dataset. The results we obtained are encouraging. We reach an accuracy ranging from 97.83% to 99.67% in brain cancer detection by exploiting four different models: VGG16, ResNet50, Alex_Net, and MobileNet, thus showing the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Many "Industry 4.0" applications rely on data-driven methodologies such as Machine Learning and Deep Learning to enable automatic tasks and implement smart factories. Among these applications, the automatic quality control of manufacturing materials is of utmost importance to achieve precision and standardization in production. In this regard, most of the related literature focused on combining Deep Learning with Nondestructive Testing techniques, such as Infrared Thermography, requiring dedicated settings to detect and classify defects in composite materials. Instead, the research described in this paper aims at understanding whether deep neural networks and transfer learning can be applied to plain images to classify surface defects in carbon look components made with Carbon Fiber Reinforced Polymers used in the automotive sector. To this end, we collected a database of images from a real case study, with 400 images to test binary classification (defect vs. no defect) and 1500 for the multiclass classification (components with no defect vs. recoverable vs. non-recoverable). We developed and tested ten deep neural networks as classifiers, comparing ten different pre-trained CNNs as feature extractors. Specifically, we evaluated VGG16, VGG19, ResNet50 version 2, ResNet101 version 2, ResNet152 version 2, Inception version 3, MobileNet version 2, NASNetMobile, DenseNet121, and Xception, all pre-trainined with ImageNet, combined with fully connected layers to act as classifiers. The best classifier, i.e., the network based on DenseNet121, achieved a 97% accuracy in classifying components with no defects, recoverable components, and non-recoverable components, demonstrating the viability of the proposed methodology to classify surface defects from images taken with a smartphone in varying conditions, without the need for dedicated settings. The collected images and the source code of the experiments are available in two public, open-access repositories, making the presented research fully reproducible. [ABSTRACT FROM AUTHOR]

Food additives are utilized in countless food products available for sale. They enhance or obtain a specific flavor, extend the storage time, or obtain a desired texture. This paper presents an automatic classification system for five food additives based on their absorbance in the ultraviolet domain. Solutions with different concentrations were created by dissolving a measured additive mass into distilled water. The analyzed samples were either simple (one additive solution) or mixed (two additive solutions). The substances presented absorbance peaks between 190 nm and 360 nm. Each substance presents a certain number of absorbance peaks at specific wavelengths (e.g., acesulfame potassium presents an absorbance peak at 226 nm, whereas the peak associated with potassium sorbate is at 254 nm). Therefore, each additive has a distinctive spectrum that can be used for classification. The sample classification was performed using deep learning techniques. The samples were associated with numerical labels and divided into three datasets (training, validation, and testing). The best classification results were obtained using CNN (convolutional neural network) models. The classification of the 404 spectra with a CNN model with three convolutional layers obtained a mean testing accuracy of 92.38% ± 1.48%, whereas the mean validation accuracy was 93.43% ± 2.01%. [ABSTRACT FROM AUTHOR]

Deep learning architectures are being increasingly adopted for human activity recognition using radar technology. A majority of these architectures are based on convolutional neural networks (CNNs) and accept radar micro-Doppler signatures as input. The state-of-the-art CNN-based models employ batch normalization (BN) to optimize network training and improve generalization. In this paper, we present whitening-aided CNN models for classifying human activities with radar sensors. We replace BN layers in a CNN model with whitening layers, which is shown to improve the model's accuracy by not only centering and scaling activations, similar to BN, but also decorrelating them. We also exploit the rotational freedom afforded by whitening matrices to align the whitened activations in the latent space with the corresponding activity classes. Using real data measurements of six different activities, we show that whitening provides superior performance over BN in terms of classification accuracy for a CNN-based classifier. This demonstrates the potential of whitening-aided CNN models to provide enhanced human activity recognition with radar sensors. [ABSTRACT FROM AUTHOR]

The Smart Grid aims to enhance the electric grid's reliability, safety, and efficiency by utilizing digital information and control technologies. Real-time analysis and state estimation methods are crucial for ensuring proper control implementation. However, the reliance of Smart Grid systems on communication networks makes them vulnerable to cyberattacks, posing a significant risk to grid reliability. To mitigate such threats, efficient intrusion detection and prevention systems are essential. This paper proposes a hybrid deep-learning approach to detect distributed denial-of-service attacks on the Smart Grid's communication infrastructure. Our method combines the convolutional neural network and recurrent gated unit algorithms. Two datasets were employed: The Intrusion Detection System dataset from the Canadian Institute for Cybersecurity and a custom dataset generated using the Omnet++ simulator. We also developed a real-time monitoring Kafka-based dashboard to facilitate attack surveillance and resilience. Experimental and simulation results demonstrate that our proposed approach achieves a high accuracy rate of 99.86%. [ABSTRACT FROM AUTHOR]

The rapid development of cloud computing and deep learning makes the intelligent modes of applications widespread in various fields. The identification of Raman spectra can be realized in the cloud, due to its powerful computing, abundant spectral databases and advanced algorithms. Thus, it can reduce the dependence on the performance of the terminal instruments. However, the complexity of the detection environment can cause great interferences, which might significantly decrease the identification accuracies of algorithms. In this paper, a deep learning algorithm based on the Dense network has been proposed to satisfy the realization of this vision. The proposed Dense convolutional neural network has a very deep structure of over 40 layers and plenty of parameters to adjust the weight of different wavebands. In the kernel Dense blocks part of the network, it has a feed-forward fashion of connection for each layer to every other layer. It can alleviate the gradient vanishing or explosion problems, strengthen feature propagations, encourage feature reuses and enhance training efficiency. The network's special architecture mitigates noise interferences and ensures precise identification. The Dense network shows more accuracy and robustness compared to other CNN-based algorithms. We set up a database of 1600 Raman spectra consisting of 32 different types of liquid chemicals. They are detected using different postures as examples of interfered Raman spectra. In the 50 repeated training and testing sets, the Dense network can achieve a weighted accuracy of 99.99%. We have also tested the RRUFF database and the Dense network has a good performance. The proposed approach advances cloud-enabled Raman spectra identification, offering improved accuracy and adaptability for diverse identification tasks. [ABSTRACT FROM AUTHOR]

To solve the problems of low accuracy and false counts of existing models in road damage object detection and tracking, in this paper, we propose Road-TransTrack, a tracking model based on transformer optimization. First, using the classification network based on YOLOv5, the collected road damage images are classified into two categories, potholes and cracks, and made into a road damage dataset. Then, the proposed tracking model is improved with a transformer and a self-attention mechanism. Finally, the trained model is used to detect actual road videos to verify its effectiveness. The proposed tracking network shows a good detection performance with an accuracy of 91.60% and 98.59% for road cracks and potholes, respectively, and an F1 score of 0.9417 and 0.9847. The experimental results show that Road-TransTrack outperforms current conventional convolutional neural networks in terms of the detection accuracy and counting accuracy in road damage object detection and tracking tasks. [ABSTRACT FROM AUTHOR]

In this paper, we present a comprehensive assessment of individuals' mental engagement states during manual and autonomous driving scenarios using a driving simulator. Our study employed two sensor fusion approaches, combining the data and features of multimodal signals. Participants in our experiment were equipped with Electroencephalogram (EEG), Skin Potential Response (SPR), and Electrocardiogram (ECG) sensors, allowing us to collect their corresponding physiological signals. To facilitate the real-time recording and synchronization of these signals, we developed a custom-designed Graphical User Interface (GUI). The recorded signals were pre-processed to eliminate noise and artifacts. Subsequently, the cleaned data were segmented into 3 s windows and labeled according to the drivers' high or low mental engagement states during manual and autonomous driving. To implement sensor fusion approaches, we utilized two different architectures based on deep Convolutional Neural Networks (ConvNets), specifically utilizing the Braindecode Deep4 ConvNet model. The first architecture consisted of four convolutional layers followed by a dense layer. This model processed the synchronized experimental data as a 2D array input. We also proposed a novel second architecture comprising three branches of the same ConvNet model, each with four convolutional layers, followed by a concatenation layer for integrating the ConvNet branches, and finally, two dense layers. This model received the experimental data from each sensor as a separate 2D array input for each ConvNet branch. Both architectures were evaluated using a Leave-One-Subject-Out (LOSO) cross-validation approach. For both cases, we compared the results obtained when using only EEG signals with the results obtained by adding SPR and ECG signals. In particular, the second fusion approach, using all sensor signals, achieved the highest accuracy score, reaching 82.0%. This outcome demonstrates that our proposed architecture, particularly when integrating EEG, SPR, and ECG signals at the feature level, can effectively discern the mental engagement of drivers. [ABSTRACT FROM AUTHOR]

Automatic target recognition (ATR) algorithms are used to classify a given synthetic aperture radar (SAR) image into one of the known target classes by using the information gleaned from a set of training images that are available for each class. Recently, deep learning methods have been shown to achieve state-of-the-art classification accuracy if abundant training data are available, especially if they are sampled uniformly over the classes and in their poses. In this paper, we consider the ATR problem when a limited set of training images are available. We propose a data-augmentation approach to incorporate SAR domain knowledge and improve the generalization power of a data-intensive learning algorithm, such as a convolutional neural network (CNN). The proposed data-augmentation method employs a physics-inspired limited-persistence sparse modeling approach, which capitalizes on the commonly observed characteristics of wide-angle synthetic aperture radar (SAR) imagery. Specifically, we fit over-parametrized models of scattering to limited training data, and use the estimated models to synthesize new images at poses and sub-pixel translations that are not available in the given data in order to augment the limited training data. We exploit the sparsity of the scattering centers in the spatial domain and the smoothly varying structure of the scattering coefficients in the azimuthal domain to solve the ill-posed problem of the over-parametrized model fitting. The experimental results show that, for the training on the data-starved regions, the proposed method provides significant gains in the resulting ATR algorithm's generalization performance. [ABSTRACT FROM AUTHOR]

Sea fog is a weather hazard along the coast and over the ocean that seriously threatens maritime activities. In the deep learning approach, it is difficult for convolutional neural networks (CNNs) to fully consider global context information in sea fog research due to their own limitations, and the recognition of sea fog edges is relatively vague. To solve the above problems, this paper puts forward an ECA-TransUnet model for daytime sea fog recognition, which consists of a combination of a CNN and a transformer. By designing a two-branch feed-forward network (FFN) module and introducing an efficient channel attention (ECA) module, the model can effectively take into account long-range pixel interactions and feature channel information to capture the global contextual information of sea fog data. Meanwhile, to solve the problem of insufficient existing sea fog detection datasets, we investigated sea fog events occurring in the Yellow Sea and Bohai Sea and their territorial waters, extracted remote sensing images from Moderate Resolution Imaging Spectroradiometer (MODIS) data at corresponding times, and combined data from the Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observation (CALIPSO), cloud and sea fog texture features, and waveband feature information to produce a manually annotated sea fog dataset. Our experiments showed that the proposed model achieves 94.5% accuracy and an 85.8% F1 score. Compared with the existing models relying only on CNNs such as UNet, FCN8s, and DeeplabV3+, it achieves state-of-the-art performance in sea fog recognition. [ABSTRACT FROM AUTHOR]

The thickness of the indium tin oxide (ITO) layer is a critical parameter affecting the performance of solar cells. Traditional measurement methods require sample collection, leading to manufacturing interruptions and potential quality issues. In this paper, we propose a real-time, non-contact approach using deep learning and optical interference phenomena to estimate the thickness of ITO layers in solar cells. We develop a convolutional neural network (CNN) model that processes microscopic images of solar cells and predicts the ITO layer thickness. In addition, mean absolute error (MAE) and mean squared error (MSE) loss functions are combined to train the model. Experimental results demonstrate the effectiveness of our approach in accurately estimating the ITO layer thickness. The integration of computer vision and deep learning techniques provides a valuable tool for non-destructive testing and quality control in the manufacturing of solar cells. The loss of the model after training is reduced to 0.83, and the slope of the test value in the scatter plot with the true value of the ellipsometer is approximately equal to 1, indicating the high reliability of the model. [ABSTRACT FROM AUTHOR]

Waste disposal remains a challenge due to land availability, and environmental and health issues related to the main disposal method, landfilling. Combining computer vision (machine learning) and robotics to sort waste is a cost-effective solution for landfilling activities limitation. The objective of this study was to combine transfer and ensemble learning to process collected waste images and classify landfill waste into nine classes. Pretrained CNN models (Inception–ResNet-v2, EfficientNetb3, and DenseNet201) were used as base models to develop the ensemble network, and three other single CNN models (Models 1, 2, and 3). The single network performances were compared to the ensemble model. The waste dataset, initially grouped in two classes, was obtained from Kaggle, and reorganized into nine classes. Classes with a low number of data were improved by downloading additional images from Google search. The Ensemble Model showed the highest prediction precision (90%) compared to the precision of Models 1, 2, and 3, 86%, 87%, and 88%, respectively. All models had difficulties predicting overlapping classes, such as glass and plastics, and wood and paper/cardboard. The environmental costs for the Ensemble network, and Models 2 and 3, approximately 15 g CO2 equivalent per training, were lower than the 19.23 g CO2 equivalent per training for Model 1. [ABSTRACT FROM AUTHOR]

In recent years, integrating structured light with deep learning has gained considerable attention in three-dimensional (3D) shape reconstruction due to its high precision and suitability for dynamic applications. While previous techniques primarily focus on processing in the spatial domain, this paper proposes a novel time-distributed approach for temporal structured-light 3D shape reconstruction using deep learning. The proposed approach utilizes an autoencoder network and time-distributed wrapper to convert multiple temporal fringe patterns into their corresponding numerators and denominators of the arctangent functions. Fringe projection profilometry (FPP), a well-known temporal structured-light technique, is employed to prepare high-quality ground truth and depict the 3D reconstruction process. Our experimental findings show that the time-distributed 3D reconstruction technique achieves comparable outcomes with the dual-frequency dataset (p = 0.014) and higher accuracy than the triple-frequency dataset (p = 1.029 × 10 − 9 ), according to non-parametric statistical tests. Moreover, the proposed approach's straightforward implementation of a single training network for multiple converters makes it more practical for scientific research and industrial applications. [ABSTRACT FROM AUTHOR]

Minimal invasive surgery, more specifically laparoscopic surgery, is an active topic in the field of research. The collaboration between surgeons and new technologies aims to improve operation procedures as well as to ensure the safety of patients. An integral part of operating rooms modernization is the real-time communication between the surgeon and the data gathered using the numerous devices during surgery. A fundamental tool that can aid surgeons during laparoscopic surgery is the recognition of the different phases during an operation. Current research has shown a correlation between the surgical tools utilized and the present phase of surgery. To this end, a robust surgical tool classifier is desired for optimal performance. In this paper, a deep learning framework embedded with a custom attention module, the P-CSEM, has been proposed to refine the spatial features for surgical tool classification in laparoscopic surgery videos. This approach utilizes convolutional neural networks (CNNs) integrated with P-CSEM attention modules at different levels of the architecture for improved feature refinement. The model was trained and tested on the popular, publicly available Cholec80 database. Results showed that the attention integrated model achieved a mean average precision of 93.14%, and visualizations revealed the ability of the model to adhere more towards features of tool relevance. The proposed approach displays the benefits of integrating attention modules into surgical tool classification models for a more robust and precise detection. [ABSTRACT FROM AUTHOR]

The combination of a blood cell analyzer and artificial microscopy to detect white blood cells is used in hospitals. Blood cell analyzers not only have large throughput, but they also cannot detect cell morphology; although artificial microscopy has high accuracy, it is inefficient and prone to missed detections. In view of the above problems, a method based on Fourier ptychographic microscopy (FPM) and deep learning to detect peripheral blood leukocytes is proposed in this paper. Firstly, high-resolution and wide-field microscopic images of human peripheral blood cells are obtained using the FPM system, and the cell image data are enhanced with DCGANs (deep convolution generative adversarial networks) to construct datasets for performance evaluation. Then, an improved DETR (detection transformer) algorithm is proposed to improve the detection accuracy of small white blood cell targets; that is, the residual module Conv Block in the feature extraction part of the DETR network is improved to reduce the problem of information loss caused by downsampling. Finally, CIOU (complete intersection over union) is introduced as the bounding box loss function, which avoids the problem that GIOU (generalized intersection over union) is difficult to optimize when the two boxes are far away and the convergence speed is faster. The experimental results show that the mAP of the improved DETR algorithm in the detection of human peripheral white blood cells is 0.936. In addition, this algorithm is compared with other convolutional neural networks in terms of average accuracy, parameters, and number of inference frames per second, which verifies the feasibility of this method in microscopic medical image detection. [ABSTRACT FROM AUTHOR]

A global health emergency resulted from the COVID-19 epidemic. Image recognition techniques are a useful tool for limiting the spread of the pandemic; indeed, the World Health Organization (WHO) recommends the use of face masks in public places as a form of protection against contagion. Hence, innovative systems and algorithms were deployed to rapidly screen a large number of people with faces covered by masks. In this article, we analyze the current state of research and future directions in algorithms and systems for masked-face recognition. First, the paper discusses the importance and applications of facial and face mask recognition, introducing the main approaches. Afterward, we review the recent facial recognition frameworks and systems based on Convolution Neural Networks, deep learning, machine learning, and MobilNet techniques. In detail, we analyze and critically discuss recent scientific works and systems which employ machine learning (ML) and deep learning tools for promptly recognizing masked faces. Also, Internet of Things (IoT)-based sensors, implementing ML and DL algorithms, were described to keep track of the number of persons donning face masks and notify the proper authorities. Afterward, the main challenges and open issues that should be solved in future studies and systems are discussed. Finally, comparative analysis and discussion are reported, providing useful insights for outlining the next generation of face recognition systems. [ABSTRACT FROM AUTHOR]