Search

This document, titled "Computational Intelligence in Remote Sensing," discusses the application of computational intelligence (CI) methods in the field of remote sensing. It highlights recent research and progress in this area, categorizing the papers into four sections: computational intelligence methods in hyperspectral remote sensing images, object detection techniques in remote sensing images, deep learning approaches in remote sensing image classification, and intelligent optimization and control in satellite image applications. The document emphasizes the potential of CI in addressing the challenges of remote sensing and encourages further interdisciplinary cooperation to solve real-world problems. The authors express their gratitude to the contributors and highlight the achievements of the research papers in this journal. [Extracted from the article]

The growing adoption of electric propulsion systems in Maritime Autonomous Surface Ships (MASSs) necessitates advancements in shipboard electronics for safe, efficient, and reliable operation. These advancements are crucial for tasks such as real-time sensor data processing, control algorithms for autonomous navigation, and robust decision-making capabilities. This study investigates research trends in MASSs, using bibliographic analysis to identify policy and future research directions in this evolving field. We analyze 3363 MASS-related articles from the Web of Science database, employing co-occurrence word analysis and latent Dirichlet allocation (LDA) topic modeling. The findings reveal a rapidly growing field dominated by image recognition research. Keywords such as "datum", "image", and "detection" suggest a focus on collecting and analyzing marine data, particularly with deep learning for synthetic aperture radar imagery. LDA confirms this, with "image analysis and classification research" as the leading topic. The study also identifies national and organizational leaders in MASS research. However, research on Arctic routes lags behind that on other areas. This work provides valuable insights for policymakers and researchers, promoting a deeper understanding of MASSs and informing future policy and research agendas regarding the integration of electric propulsion systems within the maritime industry. [ABSTRACT FROM AUTHOR]

Ground-glass nodules (GGN) are the main manifestation of early lung cancer, and accurate and efficient identification of ground-glass pulmonary nodules is of great significance for the treatment of lung diseases. In response to the problem of traditional machine learning requiring manual feature extraction, and most deep learning models applied to 2D image classification, this paper proposes a Transformer-based recognition model for ground-glass nodules from the view of global 3D asymmetry feature representation. Firstly, a 3D convolutional neural network is used as the backbone to extract the features of the three-dimensional CT-image block of pulmonary nodules automatically; secondly, positional encoding information is added to the extracted feature map and input into the Transformer encoder layer for further extraction of global 3D asymmetry features, which can preserve more spatial information and obtain higher-order asymmetry feature representation; finally, the extracted asymmetry features are entered into a support vector machine or ELM-KNN model to further improve the recognition ability of the model. The experimental results show that the recognition accuracy of the proposed method reaches 95.89%, which is 4.79, 2.05, 4.11, and 2.74 percentage points higher than the common deep learning models of AlexNet, DenseNet121, GoogLeNet, and VGG19, respectively; compared with the latest models proposed in the field of pulmonary nodule classification, the accuracy has been improved by 2.05, 2.05, and 0.68 percentage points, respectively, which can effectively improve the recognition accuracy of ground-glass nodules. [ABSTRACT FROM AUTHOR]

The rapid increase in the number of vehicles has led to increasing traffic congestion, traffic accidents, and motor vehicle crime rates. The management of various parking lots has also become increasingly challenging. Vehicle-type recognition technology can reduce the workload of humans in vehicle management operations. Therefore, the application of image technology for vehicle-type recognition is of great significance for integrated traffic management. In this paper, an improved faster region with convolutional neural network features (Faster R-CNN) model was proposed for vehicle-type recognition. Firstly, the output features of different convolution layers were combined to improve the recognition accuracy. Then, the average precision (AP) of the recognition model was improved through the contextual features of the original image and the object bounding box optimization strategy. Finally, the comparison experiment used the vehicle image dataset of three vehicle types, including cars, sports utility vehicles (SUVs), and vans. The experimental results show that the improved recognition model can effectively identify vehicle types in the images. The AP of the three vehicle types is 83.2%, 79.2%, and 78.4%, respectively, and the mean average precision (mAP) is 1.7% higher than that of the traditional Faster R-CNN model. [ABSTRACT FROM AUTHOR]

Since plant diseases occurring during the growth process are a significant factor leading to the decline in both yield and quality, the classification and detection of plant leaf diseases, followed by timely prevention and control measures, are crucial for safeguarding plant productivity and quality. As the traditional convolutional neural network structure cannot effectively recognize similar plant leaf diseases, in order to more accurately identify the diseases on plant leaves, this paper proposes an effective plant disease image recognition method aECA-ResNet34. This method is based on ResNet34, and in the first and the last layers of this network, respectively, we add this paper's improved aECAnet with the symmetric structure. aECA-ResNet34 is compared with different plant disease classification models on the peanut dataset constructed in this paper and the open-source PlantVillage dataset. The experimental results show that the aECA-ResNet34 model proposed in this paper has higher accuracy, better performance, and better robustness. The results show that the aECA-ResNet34 model proposed in this paper is able to recognize diseases of multiple plant leaves very accurately. [ABSTRACT FROM AUTHOR]

Aiming at solving the issue of blurred images and difficult recognition of digital meters encountered by inspection robots in the inspection process, this paper proposes a deep-learning-based method for blurred image restoration and LED digital identification. Firstly, fast Fourier transform (FFT) is used to perform blur detection on the acquired images. Then, the blurred images are recovered using spatial-attention-improved adversarial neural networks. Finally, the digital meter region is extracted using the polygon-YOLOv5 model and corrected via perspective transformation. The digits in the image are extracted using the YOLOv5s model, and then recognized by the CRNN for digit recognition. It is experimentally verified that the improved adversarial neural network in this paper achieves 26.562 in the PSNR metric and 0.861 in the SSIM metric. The missing rate of the digital meter reading method proposed in the paper is only 1% and the accuracy rate is 98%. The method proposed in this paper effectively overcomes the image blurring problem caused by the detection robot during the detection process. This method solves the problems of inaccurate positioning and low digital recognition accuracy of LED digital meters in complex and changeable environments, and provides a new method for reading digital meters. [ABSTRACT FROM AUTHOR]

Fruit fly species classification is a fine-grained task as there is a small gap between species. In order to effectively identify and improve the recognition of fruit flies, a fine-grained image-recognition method based on a multi-channel self-attention mechanism was studied and a network framework for fine-grained image recognition based on deep learning was designed in this paper. In this framework, long-term and short-term memory networks are used to extract the underlying features in fruit fly fine-grained images. By inputting the underlying features in the multi-channel self-attention mechanism module, the global and local attention feature maps can be obtained.The weighted attention feature map can also be obtained by multiplying the weight of each channel and the attention feature map. The fine-grained image features of fruit flies were obtained by summing the weighted attention feature map. A softmax classifier was used to process the features and complete the recognition of the fruit fly fine-grained images. Two fine-grained image datasets of fruit flies were applied as experimental objects. Dataset 1 and Dataset 2 contain 11,778 images and 20,580 images from 46 different categories of fruit flies, respectively. The Kappa coefficient was used as the evaluation index to identify fruit fly images with different targets using the method proposed herein. The experimental results showed that, as the number of attention channels increased, the Kappa coefficient gradually increased, suggesting an improvement in the accuracy of fine-grained image recognition. The fine-grained image features extracted by introducing a multi-channel self-attention mechanism exhibited more distinct boundaries with a small amount of overlap, demonstrating strong feature extraction capabilities. When dealing with fine-grained images with either simple or complex backgrounds, the method proposed in this paper has good performance and generalization ability. Even if the target is small and varied in shape, it can still achieve highly accurate recognition. [ABSTRACT FROM AUTHOR]

Traditional DeepLabV3+ image semantic segmentation methods face challenges in pitaya orchard environments characterized by multiple interference factors, complex image backgrounds, high computational complexity, and extensive memory consumption. This paper introduces an improved visual navigation path recognition method for pitaya orchards. Initially, DeepLabV3+ utilizes a lightweight MobileNetV2 as its primary feature extraction backbone, which is augmented with a Pyramid Split Attention (PSA) module placed after the Atrous Spatial Pyramid Pooling (ASPP) module. This improvement enhances the spatial feature representation of feature maps, thereby sharpening the segmentation boundaries. Additionally, an Efficient Channel Attention Network (ECANet) mechanism is integrated with the lower-level features of MobileNetV2 to reduce computational complexity and refine the clarity of target boundaries. The paper also designs a navigation path extraction algorithm, which fits the road mask regions segmented by the model to achieve precise navigation path recognition. Experimental findings show that the enhanced DeepLabV3+ model achieved a Mean Intersection over Union (MIoU) and average pixel accuracy of 95.79% and 97.81%, respectively. These figures represent increases of 0.59 and 0.41 percentage points when contrasted with the original model. Furthermore, the model's memory consumption is reduced by 85.64%, 84.70%, and 85.06% when contrasted with the Pyramid Scene Parsing Network (PSPNet), U-Net, and Fully Convolutional Network (FCN) models, respectively. This reduction makes the proposed model more efficient while maintaining high segmentation accuracy, thus supporting enhanced operational efficiency in practical applications. The test results for navigation path recognition accuracy reveal that the angle error between the navigation centerline extracted using the least squares method and the manually fitted centerline is less than 5°. Additionally, the average deviation between the road centerlines extracted under three different lighting conditions and the actual road centerline is only 2.66 pixels, with an average image recognition time of 0.10 s. This performance suggests that the study can provide an effective reference for visual navigation in smart agriculture. [ABSTRACT FROM AUTHOR]

The instance segmentation model based on deep learning has addressed the challenges in intelligently detecting water leakage in shield tunneling. Due to the limited generalization ability of the baseline model, occurrences of missed detections, false detections, and repeated detections are encountered during the actual detection of tunnel water leakage. This paper adopts Mask R-CNN as the baseline model and introduces a mask cascade strategy to enhance the quality of positive samples. Additionally, the backbone network in the model is replaced with RegNetX to enlarge the model's receptive field, and MDConv is introduced to enhance the model's feature extraction capability in the edge receptive field region. Building upon these improvements, the proposed model is named Cascade-MRegNetX. The backbone network MRegNetX features a symmetrical block structure, which, when combined with deformable convolutions, greatly assists in extracting edge features from corresponding regions. During the dataset preprocessing stage, we augment the dataset through image rotation and classification, thereby improving both the quality and quantity of samples. Finally, by leveraging pre-trained models through transfer learning, we enhance the robustness of the target model. This model can effectively extract features from water leakage areas of different scales or deformations. Through instance segmentation experiments conducted on a dataset comprising 766 images of tunnel water leakage, the experimental results demonstrate that the improved model achieves higher precision in tunnel water leakage mask detection. Through these enhancements, the detection effectiveness, feature extraction capability, and generalization ability of the baseline model are improved. The improved Cascade-MRegNetX model achieves respective improvements of 7.7%, 2.8%, and 10.4% in terms of AP, AP0.5, and AP0.75 compared to the existing Cascade Mask R-CNN model. [ABSTRACT FROM AUTHOR]

This document is the closing editorial for a special issue of the journal Applied Sciences on computer vision and pattern recognition based on deep learning. The issue includes 31 papers covering various topics such as image and video processing, object detection, object and scene recognition, visual application technologies, classification, segmentation, compression, and more. Each paper explores different methods and techniques to improve the performance and accuracy of deep learning models in these areas. The document provides a brief summary of each paper, highlighting their contributions and findings. [Extracted from the article]

Satellite remote sensing plays a significant role in the detection of smoke from forest fires. However, existing methods for detecting smoke from forest fires based on remote sensing images rely solely on the information provided by the images, overlooking the positional information and brightness temperature of the fire spots in forest fires. This oversight significantly increases the probability of misjudging smoke plumes. This paper proposes a smoke detection model, Forest Smoke-Fire Net (FSF Net), which integrates wildfire smoke images with the dynamic brightness temperature information of the region. The MODIS_Smoke_FPT dataset was constructed using a Moderate Resolution Imaging Spectroradiometer (MODIS), the meteorological information at the site of the fire, and elevation data to determine the location of smoke and the brightness temperature threshold for wildfires. Deep learning and machine learning models were trained separately using the image data and fire spot area data provided by the dataset. The performance of the deep learning model was evaluated using metric M A P , while the regression performance of machine learning was assessed with Root Mean Square Error ( R M S E ) and Mean Absolute Error ( M A E ). The selected machine learning and deep learning models were organically integrated. The results show that the Mask_RCNN_ResNet50_FPN and XGR models performed best among the deep learning and machine learning models, respectively. Combining the two models achieved good smoke detection results ( P r e c i s i o n smoke = 89.12 % ). Compared with wildfire smoke detection models that solely use image recognition, the model proposed in this paper demonstrates stronger applicability in improving the precision of smoke detection, thereby providing beneficial support for the timely detection of forest fires and applications of remote sensing. [ABSTRACT FROM AUTHOR]

Synthetic Aperture Radar (SAR) is an active microwave sensor that has attracted widespread attention due to its ability to observe the ground around the clock. Research on multi-scale and multi-category target detection methods holds great significance in the fields of maritime resource management and wartime reconnaissance. However, complex scenes often influence SAR object detection, and the diversity of target scales also brings challenges to research. This paper proposes a multi-category SAR image object detection model, CCDS-YOLO, based on YOLOv5s, to address these issues. Embedding the Convolutional Block Attention Module (CBAM) in the feature extraction part of the backbone network enables the model's ability to extract and fuse spatial information and channel information. The 1 × 1 convolution in the feature pyramid network and the first layer convolution of the detection head are replaced with the expanded convolution, Coordinate Conventional (CoordConv), forming a CRD-FPN module. This module more accurately perceives the spatial details of the feature map, enhancing the model's ability to handle regression tasks compared to traditional convolution. In the detector segment, a decoupled head is utilized for feature extraction, offering optimal and effective feature information for the classification and regression branches separately. The traditional Non-Maximum Suppression (NMS) is substituted with the Soft Non-Maximum Suppression (Soft-NMS), successfully reducing the model's duplicate detection rate for compact objects. Based on the experimental findings, the approach presented in this paper demonstrates excellent results in multi-category target recognition for SAR images. Empirical comparisons are conducted on the filtered MSAR dataset. Compared with YOLOv5s, the performance of CCDS-YOLO has been significantly improved. The mAP@0.5 value increases by 3.3% to 92.3%, the precision increases by 3.4%, and the mAP@0.5:0.95 increases by 6.7%. Furthermore, in comparison with other mainstream detection models, CCDS-YOLO stands out in overall performance and anti-interference ability. [ABSTRACT FROM AUTHOR]

Our image recognition system employs a deep learning model to differentiate between the left and right upper limbs in images, allowing doctors to determine the correct surgical position. From the experimental results, it was found that the precision rate and the recall rate of the intelligent image recognition system for preventing wrong-site upper limb surgery proposed in this paper could reach 98% and 93%, respectively. The results proved that our Artificial Intelligence Image Recognition System (AIIRS) could indeed assist orthopedic surgeons in preventing the occurrence of wrong-site left and right upper limb surgery. At the same time, in future, we will apply for an IRB based on our prototype experimental results and we will conduct the second phase of human trials. The results of this research paper are of great benefit and research value to upper limb orthopedic surgery. [ABSTRACT FROM AUTHOR]

With the popularity of mobile devices, lightweight deep learning models have important value in various application scenarios. However, how to effectively fuse the feature information from different dimensions while ensuring the model's lightness and high accuracy is a problem that has not been fully solved. In this paper, we propose a novel feature fusion module, called φunit, which can fuse the features extracted by different dimensional networks according to the order of feature information with a small computational cost, avoiding the problems of information fragmentation caused by simple feature stacking in traditional information fusion. Based on φunit, this paper further builds an extremely lightweight model φNet, which can achieve performance close to the highest accuracy on several public datasets under the condition of very limited parameter scale. The core idea of φunit is to use deconvolution to reduce the discrepancy among the features to be fused, and to lower the possibility of feature information fragmentation after fusion by fusing the features from different dimensions sequentially. φNet is a lightweight network composed of multiple φunits and bottleneck modules, with a parameter scale of only 1.24 M, much smaller than traditional lightweight models. This paper conducts experiments on public datasets, and φNet achieves an accuracy of 71.64% on the food101 dataset, and an accuracy of 75.31% on the random 50-category food101 dataset, both higher than or close to the highest accuracy. This paper provides a new idea and method for feature fusion of lightweight models, and also provides an efficient model selection for deep learning applications on mobile devices. [ABSTRACT FROM AUTHOR]

With the rapid development of Internet technology, the number of global Internet users is rapidly increasing, and the scale of the Internet is also expanding. The huge Internet system has accelerated the spread of bad information, including bad images. Bad images reflect the vulgar culture of the Internet. They will not only pollute the Internet environment and impact the core culture of society but also endanger the physical and mental health of young people. In addition, some criminals use bad images to induce users to download software containing computer viruses, which also greatly endanger the security of cyberspace. Cyberspace governance faces enormous challenges. Most existing methods for classifying bad images face problems such as low classification accuracy and long inference times, and these limitations are not conducive to effectively curbing the spread of bad images and reducing their harm. To address this issue, this paper proposes a classification method (RepVGG-SimAM) based on RepVGG and a simple parameter-free attention mechanism (SimAM). This method uses RepVGG as the backbone network and embeds the SimAM attention mechanism in the network so that the neural network can obtain more effective information and suppress useless information. We used pornographic images publicly disclosed by data scientist Alexander Kim and violent images collected from the internet to construct the dataset for our experiment. The experimental results prove that the classification accuracy of the method proposed in this paper can reach 94.5% for bad images, that the false positive rate of bad images is only 4.3%, and that the inference speed is doubled compared with the ResNet101 network. Our proposed method can effectively identify bad images and provide efficient and powerful support for cyberspace governance. [ABSTRACT FROM AUTHOR]

Action and identification problems are the challenges that visually impaired people often encounter in their lives. The high price of existing commercial intelligent auxiliary equipment has placed enormous economic pressure on most visually impaired people in developing countries. In order to solve this problem, this paper proposes a smart wearable system that performs image recognition. The system adopts the method of cloud and local cooperative processing. The cloud server mainly performs image processing, while the local unit only uploads images and feedback results. Therefore, the processor of the system does not need to use expensive high-performance hardware, and the cost is greatly reduced. Moreover, the algorithm running on the cloud server can also guarantee the speed and accuracy of recognition. In addition, we have changed the traditional video continuous scanning strategy to a mechanism for capturing points of interest, reducing power consumption. The attitude correction mechanism based on error codes of the system can effectively help the visually impaired to cope with the common living scenes, and the multiple priority feedbacks and arbitration mechanism will ensure real-time feedback of the system. The proposed smart wearable device has been tested in the actual scene, which proves to be helpful to the visually impaired people. It helps them find the right people and objects and read text. [ABSTRACT FROM AUTHOR]

Urban underground pipeline networks are a key component of urban infrastructure, and a large number of older urban areas lack information about their underground pipelines. In addition, survey methods for underground pipelines are often time-consuming and labor-intensive. While the manhole cover serves as the hub connecting the underground pipe network with the ground, the generation of underground pipe network can be realized by obtaining the location and category information of the manhole cover. Therefore, this paper proposed a manhole cover detection method based on UAV aerial photography to obtain ground images, using image super-resolution reconstruction and image positioning and classification. Firstly, the urban image was obtained by UAV aerial photography, and then the YOLOv8 object detection technology was used to accurately locate the manhole cover. Next, the SRGAN network was used to perform super-resolution processing on the manhole cover text to improve the clarity of the recognition image. Finally, the clear manhole cover text image was input into the VGG16_BN network to realize the manhole cover classification. The experimental results showed that the manhole cover classification accuracy of this paper's method reached 97.62%, which verified its effectiveness in manhole cover detection. The method significantly reduces the time and labor cost and provides a new method for manhole cover information acquisition. [ABSTRACT FROM AUTHOR]

In recent years, the defect image classification method based on deep transfer learning has been widely explored and researched, and the task of source and target domains with the same painting defect image class has been solved successfully. However, in real applications, due to the complexity and uncertainty of ship painting conditions, it is very likely that there are unknown classes of painting defects, and the traditional deep learning model cannot identify a few classes, which leads to model overfitting and reduces its generalization ability. In this paper, a zero-shot Image classification method for ship painting defects based on IDATLWGAN is proposed to identify new unknown classes of defects in the target domain. The method is based on a deep convolutional neural network combined with adversarial transfer learning. First, a preprocessed ship painting defect dataset is used as input for the domain-invariant feature extractor. Then, the domain invariant feature extractor takes domain invariant features from the source and target domains. Finally, Defect discriminators and domain alignment discriminators are employed to classify the known categories of unlabeled defects and unknown categories of unlabeled defects in the target domain and to further reduce the distance between the edge distributions of the source and target domains. The experimental results show that the proposed model in this paper extracts a better distribution of invariant features in the source and target domains compared to other existing transfer learning models. It can successfully complete the migration task and accurately recognize the painting defects of known categories and new unknown categories, which is a perfect combination of intelligent algorithms and engineering practice. [ABSTRACT FROM AUTHOR]

In this paper, we discuss the implementation of artificial self-awareness mechanisms and self-reflection abilities in deep neural networks. While the current limitations of research prevent achieving cognitive capabilities on par with natural biological entities, the incorporation of basic self-awareness and self-reflection mechanisms in deep learning architectures offers substantial advantages in tackling specific problems across various scientific fields, including geosciences. In the first section, we outline the foundational architecture of our deep learning approach termed Self-Aware Learning (SAL). The subsequent part of the paper highlights the practical benefits of this machine learning methodology through synthetic tests and applications addressed to automatic classification and image analysis of real petrological data sets. We show how Self-Aware Learning allows enhanced accuracy, reduced overfitting problems, and improved performances compared to other existing methods. [ABSTRACT FROM AUTHOR]

In this paper, we have developed the SEMAR (Smart Environmental Monitoring and Analytics in Real-Time) IoT application server platform for fast deployments of IoT application systems. It provides various integration capabilities for the collection, display, and analysis of sensor data on a single platform. Recently, Artificial Intelligence (AI) has become very popular and widely used in various applications including IoT. To support this growth, the integration of AI into SEMAR is essential to enhance its capabilities after identifying the current trends of applicable AI technologies in IoT applications. In this paper, we first provide a comprehensive review of IoT applications using AI techniques in the literature. They cover predictive analytics, image classification, object detection, text spotting, auditory perception, Natural Language Processing (NLP), and collaborative AI. Next, we identify the characteristics of each technique by considering the key parameters, such as software requirements, input/output (I/O) data types, processing methods, and computations. Third, we design the integration of AI techniques into SEMAR based on the findings. Finally, we discuss use cases of SEMAR for IoT applications with AI techniques. The implementation of the proposed design in SEMAR and its use to IoT applications will be in future works. [ABSTRACT FROM AUTHOR]

This paper discusses the problem of recognizing defective epoxy drop images for the purpose of performing vision-based die attachment inspection in integrated circuit (IC) manufacturing based on deep neural networks. Two supervised and two unsupervised recognition models are considered. The supervised models examined are an autoencoder (AE) network together with a multi-layer perceptron network (MLP) and a VGG16 network, while the unsupervised models examined are an autoencoder (AE) network together with k-means clustering and a VGG16 network together with k-means clustering. Since in practice very few defective epoxy drop images are available on an actual IC production line, the emphasis in this paper is placed on the impact of data augmentation on the recognition outcome. The data augmentation is achieved by generating synthesized defective epoxy drop images via our previously developed enhanced loss function CycleGAN generative network. The experimental results indicate that when using data augmentation, the supervised and unsupervised models of VGG16 generate perfect or near perfect accuracies for recognition of defective epoxy drop images for the dataset examined. More specifically, for the supervised models of AE+MLP and VGG16, the recognition accuracy is improved by 47% and 1%, respectively, and for the unsupervised models of AE+Kmeans and VGG+Kmeans, the recognition accuracy is improved by 37% and 15%, respectively, due to the data augmentation. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) are to be effective in many application domains, especially in the computer vision area. In order to achieve lower latency CNN processing, and reduce power consumption, developers are experimenting with using FPGAs to accelerate CNN processing in several applications. Current FPGA CNN accelerators usually use the same acceleration approaches as GPUs, where operations from different network layers are mapped to the same hardware units working in a multiplexed manner. This will result in high flexibility in implementing different types of CNNs; however, this will degrade the latency that accelerators can achieve. Alternatively, we can reduce the latency of the accelerator by pipelining the processing of consecutive layers, at the expense of more FPGA resources. The continued increase in hardware resources available in FPGAs makes such implementations feasible for latency-critical application domains. In this paper, we present FPQNet, a fully pipelined and quantized CNN FPGA implementation that is channel-parallel, layer-pipelined, and network-parallel, to decrease latency and increase throughput, combined with quantization methods to optimize hardware utilization. In addition, we optimize this hardware architecture for the HDMI timing standard to avoid extra hardware utilization. This makes it possible for the accelerator to handle video datasets. We present prototypes of the FPQNet CNN network implementations on an Alpha Data 9H7 FPGA, connected with an OpenCAPI interface, to demonstrate architecture capabilities. Results show that with a 250 MHz clock frequency, an optimized LeNet-5 design is able to achieve latencies as low as 9.32 µs with an accuracy of 98.8% on the MNIST dataset, making it feasible for utilization in high frame rate video processing applications. With 10 hardware kernels working concurrently, the throughput is as high as 1108 GOPs. The methods in this paper are suitable for many other CNNs. Our analysis shows that the latency of AlexNet, ZFNet, OverFeat-Fast, and OverFeat-Accurate can be as low as 69.27, 66.95, 182.98, and 132.6 µs, using the architecture introduced in this paper, respectively. [ABSTRACT FROM AUTHOR]

To address difficulties in the early detection of small gas pipeline leaks, a method is proposed for the image recognition of micropores inside small gas pipelines. First, we design a feature fusion network (Neck) for a small gas pipeline internal micropores identification network model, introducing BiFPN (bi-directional feature pyramid network) into the Neck, and enhancing the micropores feature fusion capability of the network model using cross-scale feature information fusion. Second, we design a classification prediction network (Head) for a small gas pipeline internal micropores identification network model, constructing a small target detection layer in the classification prediction network, and improving the microporosity detection rate of the network model by improving the detection capability for small leakages. Then, micropore datasets are fed into the network model separately to train the model. Finally, comparison and ablation experiments are used to verify the micropore recognition ability of the network model. The experimental results show that the precision of the image recognition method for micropores inside small gas pipelines is 94.7%, the detection rate is 96.6%, and the average precision is 95.5%, which can better realize the early detection of leakages in small gas pipelines. [ABSTRACT FROM AUTHOR]

Hyperspectral image classification is widely applied in several fields. Since existing datasets focus on a single scene, current deep learning-based methods typically divide patches randomly on the same image as training and testing samples. This can result in similar spatial distributions of samples, which may incline the network to learn specific spatial distributions in pursuit of falsely high accuracy. In addition, the large variation between single-scene datasets has led to research in cross-scene hyperspectral classification, focusing on domain adaptation and domain generalization while neglecting the exploration of the generalizability of models to specific variables. This paper proposes two approaches to address these issues. The first approach is to train the model on the original image and then test it on the rotated dataset to simulate cross-scene evaluation. The second approach is constructing a new cross-scene dataset for spatial distribution variations, named GF14-C17&C16, to avoid the problems arising from the existing single-scene datasets. The image conditions in this dataset are basically the same, and only the land cover distribution is different. In response to the spatial distribution variations, this paper proposes a constrained spectral attention mechanism and a constrained spatial attention mechanism to limit the fitting of the model to specific feature distributions. Based on these, this paper also constructs a constrained spectral–spatial attention residual network (CSSARN). Extensive experimental results on two public hyperspectral datasets and the GF14-C17&C16 dataset have demonstrated that CSSARN is more effective than other methods in extracting cross-scene spectral and spatial features. [ABSTRACT FROM AUTHOR]

With the increasing demand for high-resolution images, handling high-dimensional image data has become a key aspect of intelligence algorithms. One effective approach is to preserve the high-dimensional manifold structure of the data and find the accurate mappings in a lower-dimensional space. However, various non-sparse, high-energy occlusions in real-world images can lead to erroneous calculations of sample relationships, invalidating the existing distance-based manifold dimensionality reduction techniques. Many types of noise are difficult to capture and filter in the original domain but can be effectively separated in the frequency domain. Inspired by this idea, a novel approach is proposed in this paper, which obtains the high-dimensional manifold structure according to the correlationships between data points in the frequency domain and accurately maps it to a lower-dimensional space, named Frequency domain-based Manifold Dimensionality Reduction (FMDR). In FMDR, samples are first transformed into frequency domains. Then, interference is filtered based on the distribution in the frequency domain, thereby emphasizing discriminative features. Subsequently, an innovative kernel function is proposed for measuring the similarities between samples according to the correlationships in the frequency domain. With the assistance of these correlationships, a graph structure can be constructed and utilized to find the mapping in a low-dimensional space. To further demonstrate the effectiveness of the proposed algorithm, FMDR is employed for the semi-supervised classification problems in this paper. Experiments using public image datasets indicate that, compared to baseline algorithms and state-of-the-art methods, our approach achieves superior recognition performance. Even with very few labeled data, the advantages of FMDR are still maintained. The effectiveness of FMDR in dimensionality reduction and feature extraction of images makes it widely applicable in fields such as image processing and image recognition. [ABSTRACT FROM AUTHOR]

The zero-shot image classification technique aims to explore the semantic information shared between seen and unseen classes through visual features and auxiliary information and, based on this semantic information, to complete the knowledge migration from seen to unseen classes in order to complete the classification of unseen class images. Previous zero-shot work has either not extracted enough features to express the relationship between the sample classes or has only used a single feature mapping method, which cannot fully explore the information contained in the features and the connection between the visual–semantic features. To address the above problems, this paper proposes an embedded zero-shot image classification model based on bidirectional feature mapping (BFM). It mainly contains a feature space mapping module, which is dominated by a bidirectional feature mapping network and supplemented with a mapping network from visual to category label semantic feature space. Attention mechanisms based on attribute guidance and visual guidance are further introduced to weight the features to reduce the difference between visual and semantic features to alleviate the modal difference problem, and then the category calibration loss is utilized to assign a larger weight to the unseen class to alleviate the seen class bias problem. The BFM model proposed in this paper has been experimented on three public datasets CUB, SUN, and AWA2, and has achieved 71.9%, 62.8%, and 69.3% and 61.6%, 33.2%, and 66.6% accuracies under traditional and generalized zero-sample image classification settings, respectively. The experimental results verify the superiority of the BFM model in the field of zero-shot image classification. [ABSTRACT FROM AUTHOR]

In recent years, classification and identification of Earth's surface materials has been a challenging research topic in the field of earth science and remote sensing (RS). Although deep learning techniques have achieved some results in remote sensing image classification, there are still some challenges for multimodal remote sensing data classification, such as information redundancy between multimodal remote sensing images. In this paper, we propose a multimodal remote sensing data classification method IFF-Net based on irregular feature fusion, called IFF-Net. The IFF-Net architecture utilizes weight-shared residual blocks for feature extraction while maintaining the independent batch normalization (BN) layer. During the training phase, the redundancy of the current channel is determined by evaluating the judgement factor of the BN layer. If this judgment factor falls below a predefined threshold, it indicates that the current channel information is redundant and should be substituted with another channel. Sparse constraints are imposed on some of the judgment factors in order to remove extra channels and enhance generalization. Furthermore, a module for feature normalization and calibration has been devised to leverage the spatial interdependence of multimodal features in order to achieve improved discrimination. Two standard datasets are used in the experiments to validate the effectiveness of the proposed method. The experimental results show that the IFF-NET method proposed in this paper exhibits significantly superior performance compared to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Currently, complex scene classification strategies are limited to high-definition image scene sets, and low-quality scene sets are overlooked. Although a few studies have focused on artificially noisy images or specific image sets, none have involved actual low-resolution scene images. Therefore, designing classification models around practicality is of paramount importance. To solve the above problems, this paper proposes a two-stage classification optimization algorithm model based on MPSO, thus achieving high-precision classification of low-quality scene images. Firstly, to verify the rationality of the proposed model, three groups of internationally recognized scene datasets were used to conduct comparative experiments with the proposed model and 21 existing methods. It was found that the proposed model performs better, especially in the 15-scene dataset, with 1.54% higher accuracy than the best existing method ResNet-ELM. Secondly, to prove the necessity of the pre-reconstruction stage of the proposed model, the same classification architecture was used to conduct comparative experiments between the proposed reconstruction method and six existing preprocessing methods on the seven self-built low-quality news scene frames. The results show that the proposed model has a higher improvement rate for outdoor scenes. Finally, to test the application potential of the proposed model in outdoor environments, an adaptive test experiment was conducted on the two self-built scene sets affected by lighting and weather. The results indicate that the proposed model is suitable for weather-affected scene classification, with an average accuracy improvement of 1.42%. [ABSTRACT FROM AUTHOR]

Convolutional Neural Networks (CNNs) are a kind of artificial neural network designed to extract features and find out patterns for tasks such as segmentation, recognizing objects, and drawing up classification. Within a CNNs architecture, pooling operations are used until the number of parameters and the computational complexity are reduced. Numerous papers have focused on investigating the impact of pooling on the performance of Convolutional Neural Networks (CNNs), leading to the development of various pooling models. Recently, a fuzzy pooling operation based on type-1 fuzzy sets was introduced to cope with the local imprecision of the feature maps. However, in fuzzy set theory, it is not always accurate to assume that the degree of non-membership of an element in a fuzzy set is simply the complement of the degree of membership. This is due to the potential existence of a hesitation degree, which implies a certain level of uncertainty. To overcome this limitation, intuitionistic fuzzy sets (IFS) were introduced to incorporate the concept of a degree of hesitation. In this paper, we introduce a novel pooling operation based on intuitionistic fuzzy sets to incorporate the degree of hesitation heretofore neglected by a fuzzy pooling operation based on classical fuzzy sets, and we investigate its performance in the context of image classification. Intuitionistic pooling is performed in four steps: bifuzzification (by the transformation of data through the use of membership and non-membership maps), first aggregation (through the transformation of the IFS into a standard fuzzy set, second aggregation (through the transformation and use of a sum operator), and the defuzzification of feature map neighborhoods by using a max operator. IFS pooling is used for the construction of an intuitionistic pooling layer that can be applied as a drop-in replacement for the current, fuzzy (type-1) and crisp, pooling layers of CNN architectures. Various experiments involving multiple datasets demonstrate that an IFS-based pooling can enhance the classification performance of a CNN. A benchmarking study reveals that this significantly outperforms even the most recent pooling models, especially in stochastic environments. [ABSTRACT FROM AUTHOR]

Image watermarking often involves the use of handheld devices under non-structured conditions for authentication purposes, particularly in the print-cam process where smartphone cameras are used to capture watermarked printed images. However, these images frequently suffer from perspective distortions, making them unsuitable for automated information detection. To address this issue, Cam-Unet, an end-to-end neural network architecture, is presented to predict the mapping from distorted images to rectified ones, specifically tailored for print-cam challenges applied to ID images. Given the limited availability of large-scale real datasets containing ground truth distortions, we created an extensive synthetic dataset by subjecting undistorted images to print-cam attacks. The proposed network is trained on this dataset, using various data augmentation techniques to improve its generalization capabilities. Accordingly, this paper presents an image watermarking system for the print-cam process. The approach combines Fourier transform-based watermarking with Cam-Unet as perspective distortion correction. Results show that the proposed method outperforms existing watermarking approaches typically employed to counter print-cam attacks and achieves an optimal balance between efficiency and cost-effectiveness. [ABSTRACT FROM AUTHOR]

Global Navigation Satellite Systems (GNSS) offer comprehensive position, navigation, and timing (PNT) estimates worldwide. Given the growing demand for reliable location awareness in both indoor and outdoor contexts, the advent of fifth-generation mobile communication technology (5G) has enabled expansive coverage and precise positioning services. However, the power received by the signal of interest (SOI) at terminals is notably low. This can lead to significant jamming, whether intentional or unintentional, which can adversely affect positioning receivers. The diagnosis of jamming types, such as classification, assists receivers in spectrum sensing and choosing effective mitigation strategies. Traditional jamming diagnosis methodologies predominantly depend on the expertise of classification experts, often demonstrating a lack of adaptability for diverse tasks. Recently, researchers have begun utilizing convolutional neural networks to re-conceptualize a jamming diagnosis as an image classification issue, thereby augmenting recognition performance. However, in real-world scenarios, the assumptions of independent and homogeneous distributions are frequently violated. This discrepancy between the source and target distributions frequently leads to subpar model performance on the test set or an inability to procure usable evaluation samples during training. In this paper, we introduce LJCD-Net, a deep adversarial migration-based cross-domain jamming generalization diagnostic network. LJCD-Net capitalizes on a fully labeled source domain and multiple unlabeled auxiliary domains to generate shared feature representations with generalization capabilities. Initially, our paper proposes an uncertainty-guided auxiliary domain labeling weighting strategy, which estimates the multi-domain sample uncertainty to re-weight the classification loss and specify the gradient optimization direction. Subsequently, from a probabilistic distribution standpoint, the spatial constraint imposed on the cross-domain global jamming time-frequency feature distribution facilitates the optimization of collaborative objectives. These objectives include minimizing both the source domain classification loss and auxiliary domain classification loss, as well as optimizing the inter-domain marginal probability and conditional probability distribution. Experimental results demonstrate that LJCD-Net enhances the recognition accuracy and confidence compared to five other diagnostic methods. [ABSTRACT FROM AUTHOR]

Biomedical information retrieval for diagnosis, treatment and prognosis has been studied for a long time. In particular, image recognition using deep learning has been shown to be very effective for cancers and diseases. In these fields, scaphoid fracture recognition is a hot topic because the appearance of scaphoid fractures is not easy to detect. Although there have been a number of recent studies on this topic, no studies focused their attention on surgical treatment recommendations and nonsurgical prognosis status classification. Indeed, a successful treatment recommendation will assist the doctor in selecting an effective treatment, and the prognosis status classification will help a radiologist recognize the image more efficiently. For these purposes, in this paper, we propose potential solutions through a comprehensive empirical study assessing the effectiveness of recent deep learning techniques on surgical treatment recommendation and nonsurgical prognosis status classification. In the proposed system, the scaphoid is firstly segmented from an unknown X-ray image. Next, for surgical treatment recommendation, the fractures are further filtered and recognized. According to the recognition result, the surgical treatment recommendation is generated. Finally, even without sufficient fracture information, the doctor can still make an effective decision to opt for surgery or not. Moreover, for nonsurgical patients, the current prognosis status of avascular necrosis, non-union and union can be classified. The related experimental results made using a real dataset reveal that the surgical treatment recommendation reached 80% and 86% in accuracy and AUC (Area Under the Curve), respectively, while the nonsurgical prognosis status classification reached 91% and 96%, respectively. Further, the methods using transfer learning and data augmentation can bring out obvious improvements, which, on average, reached 21.9%, 28.9% and 5.6%, 7.8% for surgical treatment recommendations and nonsurgical prognosis image classification, respectively. Based on the experimental results, the recommended methods in this paper are DenseNet169 and ResNet50 for surgical treatment recommendation and nonsurgical prognosis status classification, respectively. We believe that this paper can provide an important reference for future research on surgical treatment recommendation and nonsurgical prognosis classification for scaphoid fractures. [ABSTRACT FROM AUTHOR]

The safety and robustness of convolutional neural networks (CNNs) have raised increasing concerns, especially in safety-critical areas, such as medical applications. Although CNNs are efficient in image classification, their predictions are often sensitive to minor, for human observers, invisible modifications of the image. Thus, a modified, corrupted image can be visually equal to the legitimate image for humans but fool the CNN and make a wrong prediction. Such modified images are called adversarial images throughout this paper. A popular method to generate adversarial images is backpropagating the loss gradient to modify the input image. Usually, only the direction of the gradient and a given step size were used to determine the perturbations (FGSM, fast gradient sign method), or the FGSM is applied multiple times to craft stronger perturbations that change the model classification (i-FGSM). On the contrary, if the step size is too large, the minimum perturbation of the image may be missed during the gradient search. To seek exact and minimal input images for a classification change, in this paper, we suggest starting the FGSM with a small step size and adapting the step size with iterations. A few decay algorithms were taken from the literature for comparison with a novel approach based on an index tracking the loss status. In total, three tracking functions were applied for comparison. The experiments show our loss adaptive decay algorithms could find adversaries with more than a 90% success rate while generating fewer perturbations to fool the CNNs. [ABSTRACT FROM AUTHOR]

The objectives of this paper are to investigate the trade-offs between a physically constrained neural network and a deep, convolutional neural network and to design a combined ML approach ("VarioCNN"). Our solution is provided in the framework of a cyberinfrastructure that includes a newly designed ML software, GEOCLASS-image (v1.0), modern high-resolution satellite image data sets (Maxar WorldView data), and instructions/descriptions that may facilitate solving similar spatial classification problems. Combining the advantages of the physically-driven connectionist-geostatistical classification method with those of an efficient CNN, VarioCNN provides a means for rapid and efficient extraction of complex geophysical information from submeter resolution satellite imagery. A retraining loop overcomes the difficulties of creating a labeled training data set. Computational analyses and developments are centered on a specific, but generalizable, geophysical problem: The classification of crevasse types that form during the surge of a glacier system. A surge is a glacial catastrophe, an acceleration of a glacier to typically 100–200 times its normal velocity. GEOCLASS-image is applied to study the current (2016-2024) surge in the Negribreen Glacier System, Svalbard. The geophysical result is a description of the structural evolution and expansion of the surge, based on crevasse types that capture ice deformation in six simplified classes. [ABSTRACT FROM AUTHOR]

Featured Application: The research introduced in the paper develops an automatic bird species recognition system powered by feature enhancement and contrast learning, aimed at advancing ecological conservation and biological research. This system bolsters the precision of identifying bird species, aiding in the protection of endangered birds and automating the monitoring of bird populations and their migratory behaviors. It also supports in-depth behavioral and ecological research and evaluates the impact of human activities on avian life. The technology's potential applications are vast, including its use in citizen science initiatives, environmental impact assessments, educational programs, and the tourism sector, where it can provide real-time species identification, thereby enriching eco-tourism experiences and raising biodiversity awareness. Accurate bird species recognition is crucial for ecological conservation, wildlife monitoring, and biological research, yet it poses significant challenges due to the high variability within species and the subtle similarities between different species. This paper introduces an automatic bird species recognition method from images that leverages feature enhancement and contrast learning to address these challenges. Our method incorporates a multi-scale feature fusion module to comprehensively capture information from bird images across diverse scales and perspectives. Additionally, an attention feature enhancement module is integrated to address noise and occlusion within images, thus enhancing the model's robustness. Furthermore, employing a siamese network architecture allows effective learning of common features within instances of the same class and distinctions between different bird species. Evaluated on the CUB200-2011 dataset, our proposed method achieves state-of-the-art performance, surpassing existing methods with an accuracy of 91.3% and F1 score of 90.6%. Moreover, our approach showcases a notable advantage in scenarios with limited training data. When utilizing only 5% of the training data, our model still achieves a recognition accuracy of 65.2%, which is significantly higher than existing methods under similar data constraints. Notably, our model exhibits faster execution times compared to existing methods, rendering it suitable for real-time applications. [ABSTRACT FROM AUTHOR]

This paper proposes a multi-perspective adaptive examination cheating behavior detection method to meet the demand for automated monitoring throughout the entire process in paperless online exams. Unlike current dual-perspective cheating behavior detection methods, we expand the monitoring field of view by using three cameras with different perspectives: the overhead perspective, the horizontal perspective, and the face perspective. This effectively covers areas where cheating may occur. An adaptive cheating behavior detection system based on three perspectives is proposed, including a gaze direction recognition model based on Swin Transformer, a cheating tool detection model based on Lightweight-YOLOv5-Coordinate Attention, and a cheating behavior determination model based on Multilayer Perceptron. To reduce computational complexity and ensure efficient processing while expanding the monitoring field of view, the system uses the results of the gaze direction recognition model to adaptively select the cheating behavior detection model from different perspectives, reducing the three-perspective system to dual-perspective. In online simulation tests, our method achieves cheating behavior determination at 35 frames per second, with an average recognition rate of 95%. It has good real-time performance, accuracy, and a large monitoring range. [ABSTRACT FROM AUTHOR]

Medical image diagnosis using deep learning has shown significant promise in clinical medicine. However, it often encounters two major difficulties in real-world applications: (1) domain shift, which invalidates the trained model on new datasets, and (2) class imbalance problems leading to model biases towards majority classes. To address these challenges, this paper proposes a transfer learning solution, named Dynamic Weighting Translation Transfer Learning (DTTL), for imbalanced medical image classification. The approach is grounded in information and entropy theory and comprises three modules: Cross-domain Discriminability Adaptation (CDA), Dynamic Domain Translation (DDT), and Balanced Target Learning (BTL). CDA connects discriminative feature learning between source and target domains using a synthetic discriminability loss and a domain-invariant feature learning loss. The DDT unit develops a dynamic translation process for imbalanced classes between two domains, utilizing a confidence-based selection approach to select the most useful synthesized images to create a pseudo-labeled balanced target domain. Finally, the BTL unit performs supervised learning on the reassembled target set to obtain the final diagnostic model. This paper delves into maximizing the entropy of class distributions, while simultaneously minimizing the cross-entropy between the source and target domains to reduce domain discrepancies. By incorporating entropy concepts into our framework, our method not only significantly enhances medical image classification in practical settings but also innovates the application of entropy and information theory within deep learning and medical image processing realms. Extensive experiments demonstrate that DTTL achieves the best performance compared to existing state-of-the-art methods for imbalanced medical image classification tasks. [ABSTRACT FROM AUTHOR]

In recent years, deep convolutional neural networks (DCNNs) have shown promising performance in medical image analysis, including breast lesion classification in 2D ultrasound (US) images. Despite the outstanding performance of DCNN solutions, explaining their decisions remains an open investigation. Yet, the explainability of DCNN models has become essential for healthcare systems to accept and trust the models. This paper presents a novel framework for explaining DCNN classification decisions of lesions in ultrasound images using the saliency maps linking the DCNN decisions to known cancer characteristics in the medical domain. The proposed framework consists of three main phases. First, DCNN models for classification in ultrasound images are built. Next, selected methods for visualization are applied to obtain saliency maps on the input images of the DCNN models. In the final phase, the visualization outputs and domain-known cancer characteristics are mapped. The paper then demonstrates the use of the framework for breast lesion classification from ultrasound images. We first follow the transfer learning approach and build two DCNN models. We then analyze the visualization outputs of the trained DCNN models using the EGrad-CAM and Ablation-CAM methods. We map the DCNN model decisions of benign and malignant lesions through the visualization outputs to the characteristics such as echogenicity, calcification, shape, and margin. A retrospective dataset of 1298 US images collected from different hospitals is used to evaluate the effectiveness of the framework. The test results show that these characteristics contribute differently to the benign and malignant lesions' decisions. Our study provides the foundation for other researchers to explain the DCNN classification decisions of other cancer types. [ABSTRACT FROM AUTHOR]

Architecture is a representative of a city. It is also a spatial carrier of urban culture. Identifying the architectural features in a city can help with urban transformation and promote urban development. The use of visual saliency models in regional architectural texture recognition can effectively enhance the effectiveness of regional architectural texture recognition. In this paper, the improved visual saliency model first enhances the texture images of regional buildings through histogram enhancement technology, and uses visual saliency algorithms to extract the visual saliency of the texture features of regional buildings. Then, combined with the maximum interclass difference method of threshold segmentation, the visual saliency image is segmented to achieve accurate target recognition. Finally, the feature factor iteration of the Bag of Visual Words model and the function classification of support vector machines were used to complete the recognition of regional architectural texture features. Through experimental verification, the constructed regional architectural texture feature recognition method based on visual saliency model can effectively enhance the recognition image. This method performs well in boundary contour separation and visual saliency, with an average recognition rate of 0.814 for texture features in different building scenes, indicating high stability. [ABSTRACT FROM AUTHOR]

An important part of diagnostics is to gain insight into properties that characterize a disease. Machine learning has been used for this purpose, for instance, to identify biomarkers in genomics. However, when patient data are presented as images, identifying properties that characterize a disease becomes far more challenging. A common strategy involves extracting features from the images and analyzing their occurrence in healthy versus pathological images. A limitation of this approach is that the ability to gain new insights into the disease from the data is constrained by the information in the extracted features. Typically, these features are manually extracted by humans, which further limits the potential for new insights. To overcome these limitations, in this paper, we propose a novel framework that provides insights into diseases without relying on handcrafted features or human intervention. Our framework is based on deep learning (DL), explainable artificial intelligence (XAI), and clustering. DL is employed to learn deep patterns, enabling efficient differentiation between healthy and pathological images. Explainable artificial intelligence (XAI) visualizes these patterns, and a novel "explanation-weighted" clustering technique is introduced to gain an overview of these patterns across multiple patients. We applied the method to images from the gastrointestinal tract. In addition to real healthy images and real images of polyps, some of the images had synthetic shapes added to represent other types of pathologies than polyps. The results show that our proposed method was capable of organizing the images based on the reasons they were diagnosed as pathological, achieving high cluster quality and a rand index close to or equal to one. [ABSTRACT FROM AUTHOR]

With the development of new technologies inside car mechanisms with various sensors connected to the IoT, a new generation of automation is attracting attention. However, there are still some factors that are difficult to detect. Among them, one of the highest risk factors is black ice. A road covered with black ice, which is hard to see from a distance, is not only the cause of damage to vehicles passing over the spot, but it also puts lives at risk. Hence, the detection of black ice is essential. A lot of research has been done on this topic with various sensors and methods. However, hyperspectral imaging has not been used for this particular purpose. Therefore, in this paper, black ice classification has been performed with the help of hyperspectral imaging in collaboration with a deep learning model for the first time. With abundant spectral and spatial information, hyperspectral imaging is a good way to analyze any material. In this paper, a 2D–3D Convolutional Neural Network (CNN) has been used to classify hyperspectral images of black ice. The spectral data were preprocessed, and the dimension of the image cube was reduced with the help of Principal Component Analysis (PCA). The proposed method was then compared with the existing method for better evaluation. [ABSTRACT FROM AUTHOR]

Crack identification plays a vital role in preventive maintenance strategies during highway pavement maintenance. Therefore, accurate identification of cracks in highway pavement images is the key to highway maintenance work. In this paper, an improved U-Net network adopting multi-scale feature prediction fusion and the improved parallel attention module was put forward to better identify concrete cracks. Multiscale feature prediction fusion combines multiple U-Net features generated by intermediate layers for aggregated prediction, thus using global information from different scales. The improved parallel attention module is used to process the U-Net decoded output of multi-scale feature prediction fusion, which can give more weight to the target region in the image and further capture the global contextual information of the image to improve the recognition accuracy. Improving the bottleneck layer is used to improve the robustness of the model and prevent overfitting. Experiments show that the improved U-Net network in this paper has a significant improvement over the original U-Net network. The performance of the proposed method in this paper was investigated on two publicly available datasets (Crack500 and CFD) and compared with competing methods proposed in the literature. Using the Crack500 dataset, the method in this paper achieved the highest score in precision (89.60%), recall (95.83%), mIOU (83.80%), and F1-score (92.61%). Similarly, for the CFD dataset, the method in this paper achieved high values for precision (93.29%), mIOU (82.07%), recall (86.26%), and F1-score (89.64%). Thus, the method has several advantages for identifying cracks in highway pavements and is an ideal tool for practical work. In future work, identifying more crack types and model light-weighting are the key objectives. Meanwhile, this paper provides a new idea for road crack identification. [ABSTRACT FROM AUTHOR]

Transformers are models that implement a mechanism of self-attention, individually weighting the importance of each part of the input data. Their use in image classification tasks is still somewhat limited since researchers have so far chosen Convolutional Neural Networks for image classification and transformers were more targeted to Natural Language Processing (NLP) tasks. Therefore, this paper presents a literature review that shows the differences between Vision Transformers (ViT) and Convolutional Neural Networks. The state of the art that used the two architectures for image classification was reviewed and an attempt was made to understand what factors may influence the performance of the two deep learning architectures based on the datasets used, image size, number of target classes (for the classification problems), hardware, and evaluated architectures and top results. The objective of this work is to identify which of the architectures is the best for image classification and under what conditions. This paper also describes the importance of the Multi-Head Attention mechanism for improving the performance of ViT in image classification. [ABSTRACT FROM AUTHOR]

Recently, the technologies of on-device AI have been accelerated with the development of new hardware and software platforms. Therefore, many researchers and engineers focus on how to enable ML technologies on mobile devices with limited hardware resources. In this paper, we revisit on-device ML designed to support ML technologies on mobile devices and describe the three challenges when using on-device ML in detail. Then, we propose a new data management policy, called Overlay-ML, which efficiently solves two challenges that we discovered. Especially, we designed Overlay-ML to work in the application space with two key ideas. The first key idea is to extend the limited memory space using the usable space of the underlying storage device. The second key idea is to provide data transparency, which hides where the data is stored so that running ML models think the data is stored in the same place. For evaluation, we implemented an image detection application based on TensorFlow Lite which is a well-known on-device ML framework, and modified it to enable the features of Overlay-ML. All evaluation was performed on two state-of-the-art smartphones that are high-end embedded devices. Our evaluation results clearly show Overlay-ML can effectively prevent unexpected termination by Android OS and present a good loss value in real-world workload. [ABSTRACT FROM AUTHOR]

The number of patients with cardiovascular diseases worldwide is increasing rapidly, while medical resources are increasingly scarce. Heart sound classification, as the most direct means of discovering cardiovascular diseases, is attracting the attention of researchers around the world. Although great progress has been made in heart sound classification in recent years, most of them are based on traditional statistical feature methods and temporal dimension features. These traditional temporal dimension feature representation and classification methods cannot achieve good classification accuracy. This paper proposes a new partition attention module and Fusionghost module, and the entire network framework is named PANet. Without segmentation of the heart sound signal, the heart sound signal is converted into a bispectrum and input into the proposed framework for feature extraction and classification tasks. The network makes full use of multi-scale feature extraction and feature map fusion, improving the network feature extraction ability. This paper conducts a comprehensive study of the performance of different network parameters and different module numbers, and compares the performance with the most advanced algorithms currently available. Experiments have shown that for two classification problems (normal or abnormal), the classification accuracy rate on the 2016 PhysioNet/CinC Challenge database reached 97.89%, the sensitivity was 96.96%, and the specificity was 98.85%. [ABSTRACT FROM AUTHOR]

The census and management of hazard-bearing entities, along with the integrity of data quality, form crucial foundations for disaster risk assessment and zoning. By addressing the challenge of feature confusion, prevalent in single remotely sensed image recognition methods, this paper introduces a novel method, Spatially Constrained Deep Learning (SCDL), that combines deep learning with spatial constraint strategies for the extraction of disaster-bearing bodies, focusing on dams as a typical example. The methodology involves the creation of a dam dataset using a database of dams, followed by the training of YOLOv5, Varifocal Net, Faster R-CNN, and Cascade R-CNN models. These models are trained separately, and highly confidential dam location information is extracted through parameter thresholding. Furthermore, three spatial constraint strategies are employed to mitigate the impact of other factors, particularly confusing features, in the background region. To assess the method's applicability and efficiency, Qinghai Province serves as the experimental area, with dam images from the Google Earth Pro database used as validation samples. The experimental results demonstrate that the recognition accuracy of SCDL reaches 94.73%, effectively addressing interference from background factors. Notably, the proposed method identifies six dams not recorded in the GOODD database, while also detecting six dams in the database that were previously unrecorded. Additionally, four dams misdirected in the database are corrected, contributing to the enhancement and supplementation of the global dam geo-reference database and providing robust support for disaster risk assessment. In conclusion, leveraging open geographic data products, the comprehensive framework presented in this paper, encompassing deep learning target detection technology and spatial constraint strategies, enables more efficient and accurate intelligent retrieval of disaster-bearing bodies, specifically dams. The findings offer valuable insights and inspiration for future advancements in related fields. [ABSTRACT FROM AUTHOR]

This paper discusses the challenges of the hyperparameter tuning in deep learning models and proposes a green approach to the neural architecture search process that minimizes its environmental impact. The traditional approach of neural architecture search involves sweeping the entire space of possible architectures, which is computationally expensive and time-consuming. Recently, to address this issue, performance predictors have been proposed to estimate the performance of different architectures, thereby reducing the search space and speeding up the exploration process. The proposed approach aims to develop a performance predictor by training only a small percentage of the possible hyperparameter configurations. The suggested predictor can be queried to find the best configurations without training them on the dataset. Numerical examples of image denoising and classification enable us to evaluate the performance of the proposed approach in terms of performance and time complexity. [ABSTRACT FROM AUTHOR]

The use of in-hole imaging to investigate geological structure characteristics is one of the crucial methods for the study of rock mass stability and rock engineering design. The in-hole images are usually influenced by the lighting and imaging characteristics, resulting in the presence of interference noise regions in the images and consequently impacting the classification accuracy. To enhance the analytical efficacy of in-hole images, this paper employs the proposed optimal non-concentric ring segmentation method to establish a new database. This method establishes the transformation function based on the Ansel Adams Zone System and the fluctuation values of the grayscale mean, adjusting the gray-level distribution of images to extract two visual blind spots of different scales. Thus, the inner and outer circles are located with these blind spots to achieve the adaptive acquisition of the optimal ring. Finally, we use the optimal non-concentric ring segmentation method to traverse all original images to obtain the borehole image classification database. To validate the effectiveness of this method, we conduct experiments using various segmentation and classification evaluation metrics. The results show that the Jaccard and Dice of the optimal non-concentric ring segmentation approach are 88.43% and 98.55%, respectively, indicating superior segmentation performance compared to other methods. Furthermore, after employing four commonly used classification models to validate the performance of the new classification database, the results demonstrate a significant improvement in accuracy and macro-average compared to the original database, with the highest increase in accuracy reaching 4.2%. These results fully demonstrate the effectiveness of the proposed optimal non-concentric ring segmentation method. [ABSTRACT FROM AUTHOR]

Aiming to solve the problems of different spectral bands and spatial pixels contributing differently to hyperspectral image (HSI) classification, and sparse connectivity restricting the convolutional neural network to a globally dependent capture, we propose a HSI classification model combined with multi-scale residual spectral–spatial attention and an improved transformer in this paper. First, in order to efficiently highlight discriminative spectral–spatial information, we propose a multi-scale residual spectral–spatial feature extraction module that preserves the multi-scale information in a two-layer cascade structure, and the spectral–spatial features are refined by residual spectral–spatial attention for the feature-learning stage. In addition, to further capture the sequential spectral relationships, we combine the advantages of Cross-Attention and Re-Attention to alleviate computational burden and attention collapse issues, and propose the Cross-Re-Attention mechanism to achieve an improved transformer, which can efficiently alleviate the heavy memory footprint and huge computational burden of the model. The experimental results show that the overall accuracy of the proposed model in this paper can reach 98.71%, 99.33%, and 99.72% for Indiana Pines, Kennedy Space Center, and XuZhou datasets, respectively. The proposed method was verified to have high accuracy and effectiveness compared to the state-of-the-art models, which shows that the concept of the hybrid architecture opens a new window for HSI classification. [ABSTRACT FROM AUTHOR]

Affected by the improper operation of the workers, environmental changes during drying and curing or the quality of the paint itself, diverse defects are produced during the process of ship painting. The traditional defect recognition method relies on expert knowledge or experience to detect defects, which is not conducive to ensuring the effectiveness of defect recognition. Therefore, this paper proposes an image generation and recognition model which is suitable for small samples. Based on a deep convolutional neural network (DCNN), the model combines a conditional variational autoencoder (DCCVAE) and auxiliary conditional Wasserstein GAN with gradient penalty (ACWGAN-GP) to gradually expand and generate various coating defect images for solving the overfitting problem due to unbalanced data. The DCNN model is trained based on newly generated image data and original image data so as to build a coating defect image classification model suitable for small samples, which is conducive to improving classification performance. The experimental results showed that our proposed model can achieve up to 92.54% accuracy, an F-score of 88.33%, and a G mean value of 91.93%. Compared with traditional data enhancement methods and classification algorithms, our proposed model can identify various defects in the ship painting process more accurately and consistently, which can provide effective theoretical and technical support for ship painting defect detection and has significant engineering research value and application prospects. [ABSTRACT FROM AUTHOR]