A Novel Coal Dust Characteristic Extraction to Enable Particle Size Analysis

Introduction20.4 With the exponential growth of Internet of Things (IoT) devices, security threats have become a major concern. Traditional malware detection techniques struggle to keep up with the ever-evolving attack landscape due to their reliance on predefined signatures and static rule-based detection. This paper explores the use of deep learning-based feature mapping combined with ensemble learning techniques to enhance IoT malware detection and classification. The proposed approach leverages convolutional neural networks (CNNs) for automatic feature extraction and ensemble models to improve classification accuracy while mitigating overfitting issues. Extensive experiments conducted on benchmark datasets demonstrate the superiority of our approach over traditional methods in terms of detection accuracy, false-positive rates, and computational efficiency. The results indicate that integrating deep learning and ensemble learning methods can significantly enhance the ability to detect and classify malicious IoT activities, making IoT environments more secure against evolving cyber threats.

Object detection is a fundamental task in computer vision, primarily used to identify the categories of objects within digital images. It finds extensive applications in intelligent transportation, human-computer interaction, and autonomous driving. We design an object detection algorithm based on CenterNet that enhances small object information, considering the informational characteristics of low-level features. First, the classic backbone network ResNet50 is employed for feature extraction. Drawing inspiration from feature pyramids, the output feature maps from the backbone network undergo multi-scale fusion to extract small object information from low-level features. Second, a feature selection module is added to model feature importance in deep feature maps, utilizing an adaptive feature fusion mechanism to reduce semantic gaps. Finally, a positional attention mechanism is applied to low-level features to capture contextual positional information. The performance of the improved CenterNet model is validated on the VisDrone2019 small object detection dataset for drones.

Convolutional Neural Networks (CNNs) have demonstrated an outstanding performance on a range of image classification problems in various domains. However, their major drawback is that they are “black box” and opaque classifiers. Taking into consideration the increasing demand for interpretable classification models, this paper introduces a novel meta-feature extraction scheme. This scheme is based on fuzzy sets, and it can be applied on the feature maps of a CNN. Initially, representative image prototypes are selected based on their deep feature map representation. Then, it constructs information granules from the feature maps, describing the content of each image class. It uses fuzzy sets to linguistically characterize the similarity between the deep feature maps of an image and the deep feature maps of the image prototypes. Thus, a classification outcome can be interpreted based on the features characterizing the different image classes involved in a classification problem. The experimental evaluation of the proposed scheme is performed on five publicly available image datasets. The results indicate that the proposed scheme outperforms other state-of-the-art classifiers, while providing an understandable interpretation of the classification result.

With the wide application of remote sensing images (RSIs) in military and civil fields, remote sensing object detection (RSOD) has gradually become a hot research direction. However, we observe two main challenges for remote sensing object detection, namely the complicated background and the small objects issues. Given the different appearances of generic objects and remote sensing objects, the detection algorithms designed for the former usually cannot perform well for the latter. We propose a novel global to local scale-aware detection network (GLSANet) for remote sensing object detection, aiming to solve the above mentioned two challenges. Firstly, we design a global semantic information interaction module (GSIIM) to excavate and reinforce the high-level semantic information in the deep feature map, which alleviates the obstacles of complex background on foreground objects. Secondly, we optimize the feature pyramid network to improve the performance of multiscale object detection in RSIs. Finally, a local attention pyramid (LAP) is introduced to highlight the feature representation of small objects gradually while suppressing the background and noise in the shallower feature maps. Extensive experiments on three public datasets demonstrate that the proposed method achieves superior performance compared with the state-of-the-art detectors, especially on small object detection dataset. Specifically, our algorithm reaches 94.57% mAP on NWPU VHR-10 dataset, 95.93% mAP on RSOD dataset and 77.9% mAP on DIOR dataset, respectively.

Automatic target recognition has been one of the hottest research in synthetic aperture radar (SAR) data processing. Noticing that popular recognition methods cannot utilize multiple features of SAR complex data, a method fused scattering center feature and deep convolutional neural network (CNN) feature is proposed in this letter. This method contains three key parts, namely, scattering center extraction and reconstruction block, CNN feature extraction block, and final feature fusion and classification block. In this process, the scattering center feature and CNN feature are fused at the level of feature maps, which retain the space information of 2-D feature maps. What is more, the proposed half end-to-end strategy realizes the automatic update of weighting parameters in feature extraction network and subnetwork, which promotes a better recognition efficiency. Experimental results on measured SAR data show that the proposed method can achieve better accuracy than other single feature-based methods and feature fusion methods.

To improve the accuracy in low resolution face recognition, a method based on super-resolution joint feature mapping is proposed. Firstly, a two-branch convolutional neural network is designed to extract features of high and low resolution face images. A super-resolution enhanced network cascading feature extraction network is used for feature mapping of low resolution face images. In this way, the high frequency information of low resolution image can be reconstructed, and features are extracted. Secondly, a fusion loss method is utilized, in which the loss of cosine and the image reconstruction are weighted and fusioned to increase the cosine similarity between image features of different resolutions. Finally, the experimental results based on FERET dataset validate that the test accuracy of two-branch framework is up to 98.2%, 99.1%, 99.5% with resolutions of 20× 20, 24× 24, and 36× 36 obtained by smooth downsampling. The proposed model outperforms up-to-date low resolution face recognition methods.

Land-use scene classification (LUSC) is a key technique in the field of remote sensing imagery (RSI) interpretation. A convolutional neural network (CNN) is widely used for its ability to autonomously and efficiently extract deep semantic feature maps (DSFMs) from large-scale RSI data. However, CNNs cannot accurately extract the rich spatial structure information of RSI, and the key information of RSI is easily lost due to many pooling layers, so it is difficult to ensure the information integrity of the spatial structure feature maps (SSFMs) and DSFMs of RSI with CNNs only for LUSC, which can easily affect the classification performance. To fully utilize the SSFMs and make up for the insufficiency of CNN in capturing the relationship information between the land-use objects of RSI, while reducing the loss of important information, we propose an effective dual-branch hybrid framework, HFCC-Net, for the LUSC task. The CNN in the upper branch extracts multi-scale DSFMs of the same scene using transfer learning techniques; the graph routing-based CapsNet in the lower branch is used to obtain SSFMs from DSFMs in different scales, and element-by-element summation achieves enhanced representations of SSFMs; a newly designed function is used to fuse the top-level DSFMs with SSFMs to generate discriminant feature maps (DFMs); and, finally, the DFMs are fed into classifier. We conducted sufficient experiments using HFCC-Net on four public datasets. The results show that our method has better classification performance compared to some existing CNN-based state-of-the-art methods.

Convolutional Neural Networks (CNNs) are frequently used algorithms because of their propensity to learn relevant and hierarchical features through their feature extraction technique. However, the availability of enormous volumes of data in various variations is crucial for their performance. Capsule networks (CapsNets) perform well on a small amount of data but perform poorly on complex images. To address this, we proposed a new Capsule Network architecture called Tri Texton-Dense CapsNet (TTDCapsNet) for better complex and medical image classification. The TTDCapsNet is made up of three hierarchic blocks of Texton-Dense CapsNet (TDCapsNet) models. A single TDCapsNet is a CapsNet architecture composed of a texton detection layer to extract essential features, which are passed onto an eight-layered block of dense convolution that further extracts features, and then the output feature map is given as input to a Primary Capsule (PC), and then to a Class Capsule (CC) layer for classification. The resulting feature map from the first PC serves as input into the second-level TDCapsNet, and that from the second PC serves as input into the third-level TDCapsNet. The routing algorithm receives feature maps from each PC for the various CCs. Routing the concatenation of the three PCs creates an additional CC layer. All these four feature maps combined, help to achieve better classification. On fashion-MNIST, CIFAR-10, Breast Cancer, and Brain Tumor datasets, the proposed model is evaluated and achieved validation accuracies of 94.90%, 89.09%, 95.01%, and 97.71% respectively. Findings from this work indicate that TTDCapsNet outperforms the baseline and performs comparatively well with the state-of-the-art CapsNet models using different performance metrics. This work clarifies the viability of using Capsule Network on complex tasks in the real world. Thus, the proposed model can be used as an intelligent system, to help oncologists in diagnosing cancerous diseases and administering treatment required.

Automatic computation of the area irradiated by ultrashort laser pulses in Sb materials through texture segmentation of TEM images

Semantic image segmentation has a wide range of applications. When it comes to medical image segmentation, its accuracy is even more important than those of other areas because the performance gives useful information directly applicable to disease diagnosis, surgical planning, and history monitoring. The state-of-the-art models in medical image segmentation are variants of encoder-decoder architecture, which is called U-Net. To effectively reflect the spatial features in feature maps in encoder-decoder architecture, we propose a spatially adaptive weighting scheme for medical image segmentation. Specifically, the spatial feature is estimated from the feature maps, and the learned weighting parameters are obtained from the computed map, since segmentation results are predicted from the feature map through a convolutional layer. Especially in the proposed networks, the convolutional block for extracting the feature map is replaced with the widely used convolutional frameworks: VGG, ResNet, and Bottleneck Resent structures. In addition, a bilinear up-sampling method replaces the up-convolutional layer to increase the resolution of the feature map. For the performance evaluation of the proposed architecture, we used three data sets covering different medical imaging modalities. Experimental results show that the network with the proposed self-spatial adaptive weighting block based on the ResNet framework gave the highest IoU and DICE scores in the three tasks compared to other methods. In particular, the segmentation network combining the proposed self-spatially adaptive block and ResNet framework recorded the highest 3.01% and 2.89% improvements in IoU and DICE scores, respectively, in the Nerve data set. Therefore, we believe that the proposed scheme can be a useful tool for image segmentation tasks based on the encoder-decoder architecture.

Most existing small object detection methods rely on residual blocks to process deep feature maps. However, these residual blocks, composed of multiple large-kernel convolution layers, incur high computational costs and contain redundant information, which makes it difficult to improve detection performance for small objects. To address this, we designed an improved feature pyramid network called L Feature Pyramid Network (L-FPN), which optimizes the allocation of computational resources for small object detection by reconstructing the original FPN structure. Based on L-FPN, we further proposed a small object detector named BPD-YOLO. We introduce a Dual-phase Asymptotic Feature Fusion mechanism (DAFF), where the shallow and deep semantic features extracted from the backbone network are initially fused in parallel to mitigate the semantic gap. Subsequently, the intermediate semantic layers are progressively integrated, enabling effective fusion of both shallow and deep feature representations. Additionally, we designed the Deep Spatial Pyramid Fusion module (DSPF), which generates multi-scale feature representations as an alternative to conventional residual block stacking, thereby reducing computational overhead. In the shallow feature extraction stage, DSPF focuses on semantic integration and enhances the extraction of small object features. This strategy, which adaptively selects different modules based on the resolution of the feature maps, is referred to as the Decoupled feature Extraction-semantic Integration mechanism (DEI). Finally, we conducted extensive experiments and thorough evaluations on both the VisDrone and TinyPerson datasets. The results demonstrate that, on the VisDrone dataset, compared to the baseline model YOLOv8n + p2, our BPD-YOLO model with L-FPN achieves a 2.8% improvement in mAP50 and a 1.4% increase in mAP50-95. On the TinyPerson dataset, BPD-YOLO further demonstrates its superiority in high-resolution feature extraction, effectively enhancing detection accuracy while significantly reducing computational costs.

Deep learning has substantially pushed forward remote sensing image change detection through extracting discriminative hierarchical features. However, as the increasingly high resolution remote sensing images have abundant spatial details but limited spectral information, the use of conventional backbone networks would give rise to blurry boundaries between different semantics among hierarchical features. This explains why most false alarms in the final predictions distribute around change boundaries. To alleviate the problem, we pay attention to feature refinement and propose deep learning networks that deliver improved separability (ISNet). Our ISNet reaps the advantages from two strategies applied to refining bi-temporal feature hierarchies: (i) margin maximization that clarifies the gap between changed and unchanged semantics, and (ii) targeted arrangement of attention mechanisms that directs the use of channel attention and spatial attention for highlighting semantic and positional information, respectively. Specifically, we insert channel attention modules into share-weighted backbone networks to facilitate semantic-specific feature extraction. The semantic boundaries in the extracted bi-temporal hierarchical features are then clarified by margin maximization modules, followed by spatial attention modules to enhance positional change responses. A top-down fusion pathway makes the final refined features cover multi-scale representations and have strong separability for remote sensing image change detection. Extensive experimental evaluations demonstrate that our ISNet achieves state-of-the-art performance on the LEVIR-CD, SYSU-CD, and Season-Varying datasets, in terms of Overall Accuracy (OA), Intersection-of-Union (IoU), and F1 score. Code is available at https://github.com/xingronaldo/ISNet.

We propose a novel face recognition method using a Hierarchical Feature Relational Network (HFRN) which extracts facial part representations around facial landmark points, and predicts hierarchical latent relations between facial part representations. These hierarchical latent relations should be unique relations within the same identity and discriminative relations among different identities for face recognition task. To do this, the HFRN extracts appearance features as facial parts representations around facial landmark points on the feature maps, globally pool these extracted appearance features onto single feature vectors, and captures the relations for the pairs of appearance features. The HFRN captures the locally detailed relations in the low-level layers and the locally abstracted global relations in the high-level layers for the pairs of appearance features extracted around facial landmark points projected on each layer, respectively. These relations from low-level layers to high-level layers are concatenated into a single hierarchical relation feature. To further improve the accuracy of face recognition, we combine the global appearance feature with the hierarchical relation feature. In experiments, the proposed method achieves the comparable performance in the 1:1 face verification and 1:N face identification tasks compared to existing state-of-the-art methods on the challenging IARPA Janus Benchmark A (IJB-A) and IARPA Janus Benchmark B (IJB-B) datasets.

3D fluorescence microscopy of living organisms has increasingly become an essential and powerful tool in biomedical research and diagnosis. An exploding amount of imaging data has been collected, whereas efficient and effective computational tools to extract information from them are still lagging behind. This is largely due to the challenges in analyzing biological data. Interesting biological structures are not only small, but are often morphologically irregular and highly dynamic. Although tracking cells in live organisms has been studied for years, existing tracking methods for cells are not effective in tracking subcellular structures, such as protein complexes, which feature in continuous morphological changes including split and merge, in addition to fast migration and complex motion. In this paper, we first define the problem of multi-object portion tracking to model the protein object tracking process. A multi-object tracking method with portion matching is proposed based on 3D segmentation results. The proposed method distills deep feature maps from deep networks, then recognizes and matches objects' portions using an extended search. Experimental results confirm that the proposed method achieves 2.96% higher on consistent tracking accuracy and 35.48% higher on event identification accuracy than the state-of-art methods.

To address the issue of multi-scale detection, current detectors usually generate hierarchical feature pyramid by a naive combination of top-down features with lateral features. Due to the limited effective receptive fields in the top-down pathway, the generated regions are only associated with the neighbor regions of the coarse feature maps, which is harmful for pyramidal feature generation. And considering the weak representation of simply merging of top-down and lateral pathways, the pyramidal feature maps with strong semantics are difficult to obtain. In this paper, we present the Residual Dilation based Feature Pyramid Network (RDFPN) to exploit the inherent correlation of regions in feature pyramid. The goal of RDFPN is to produce more appropriate hierarchical feature maps for multi-scale detection. With Residual-50 network in Faster R-CNN framework, RDFPN outperforms the original FPN on the challenging COCO dataset without bells and whistles.