Deep Information Research Articles

Insulating Glove Wearing State Detection for Substation Personnel Based on Faster‐YOLOv8

Electrical workers must wear insulating gloves during daily maintenance. Detecting the condition of these gloves is significant for power safety. Due to the limitations of existing detection algorithms in accuracy and lightweight on power construction sites, this paper proposes a Faster‐YOLOv8 algorithm to detect the wearing condition of insulating gloves. First, it replaces the Bottleneck in the C2f module with the Faster Block and introduces a new C2Faster module. This reduces model parameters while improving performance. Second, the feature pyramid is improved to enhance the combination of deep and shallow semantic information. This improvement aims to improve the network's focus on detecting small targets. Finally, the GSConv is introduced into the neck network to reduce the model parameters and calculation. Additionally, GSConv enhances feature information exchange through shuffle operation. The effectiveness of the Faster‐YOLOv8 algorithm is verified through comparisons with mainstream algorithms such as the Faster‐RCNN algorithm, SSD algorithm, YOLOv5 algorithm, and YOLOv7‐tiny algorithm. The results demonstrate that the Faster‐YOLOv8 algorithm outperforms the above algorithms in terms of detection accuracy. Compared with the original YOLOv8 network model, the mAP is improved by 3.8%, the mAP of the wrong glove increased by 9.8%, the model size is reduced by 33.3%, and the detection speed can reach 81 FPS. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

BD-YOLO: detection algorithm for high-resolution remote sensing images

This paper focuses on detecting extremely small targets in aerial images. Compared to common datasets, the average size of targets in remote sensing images is only 12.8 pixels, significantly smaller than those in common datasets. Therefore, directly applying existing detectors to aerial images is ineffective. To address this issue and ensure real-time performance, This paper propose BD-YOLO, which incorporates five key innovations. A dual Backbone route was proposed to maintain data integrity and achieve high-resolution aerial remote sensing detection. Additionally, a new feature fusion method was developed to comprehensively merge shallow and deep information. To supplement small-sized target information, a new network structure was proposed. The detector strategy used by BD-YOLO considers the detection accuracy of objects with different sizes. Furthermore, a lightweight method was adopted to ensure real-time performance of the algorithm. BD-YOLO outperformed YOLOv8s on the AI-TOD dataset, achieving a higher mAP by 2.4%. Similarly, on the Visdrone dataset, BD-YOLO achieved a 2.5% higher mAP compared to YOLOv8s. Additionally, on the Tinyperson dataset, BD-YOLO achieved a 0.6% higher mAP than YOLOv8s. Notably, BD-YOLO maintains real-time performance while ensuring accurate object detection.

Improved adaptive war strategy optimization algorithm assisted-adaptive multi-head graph attention mechanism network for remaining useful life of complex equipment

The remaining useful life (RUL) of complex equipment is an important criterion to ensure stable operation. In recent years, deep learning-based methods for predicting the RUL of complex equipment have attracted wide attention. However, it is only able to obtain the potential information in the Euclidean space, which hinders their ability to capture the deeply degradation information. Thus, graph neural networks have gradually entered the researchers’ field of vision. Despite the fact that graph neural networks are able to accomplish the task of RUL for complex equipment, there are still limitations that restrict the prediction performance in practical engineering. To address this challenge, an improved adaptive war strategy optimization algorithm assisted-adaptive multi-head graph attention mechanism network (IWSO-LMGAT) is proposed. For one thing, a learnable attention mechanism is proposed to adjust the weights of different heads dynamical and improve the limitation of GAT in obtaining deep degradation information. In addition, since hyperparameters are essential elements affecting the predicted result, inspired by the “no-free lunch” principle, an improved mathematical expression is described to avoid the issue such as precocity, fall into local optimums for WSO so that the optimal hyperparameters of the LMGAT could be obtained. The effectiveness and advancement of IWSO-LMGAT are validated on the CMAPSS dataset, and experimental results show that the proposed method could provide competitive forecasted results compared to traditional methods, that is, R2 = 0.9939, RMSE = 4.3638, and MAPE = 0.0137; this illustrates the IWSO-LMGAT’s potential for the RUL prediction of complex equipment.

Musharakah Financing: Profitability Improvement Tool for Islamic Banks

Islamic commercial banks are part of country’s financial system and play a crucial role in business industry. Similar to other business firms, Islamic commercial banks seek profits, growth and sustainability. This study attempted to analyze the effects of musharakah financing on the profitability of Islamic commercial banks. The majority of literature of finance relates to traditional finance, which has so many weaknesses. In contrast, this study focuses on Islamic banking theory with specific emphasis on Musharakah financing which is essential mechanism in the practice of Islamic banking and finance. The data were analyzed using statistical package for social science to examine the extant of the effects of musharakah financing on the profitability of Islamic commercial banks. Results: The results showed that musharakah financing has a positive effect on profitability of Islamic commercial banks (r = 0.882, p < 0.05). The study concludes that increase in Musharakah financing significantly improves profitability of Islamic commercial banks. The study presents several managerial implications, suggesting the importance of increasing service exposure to attract new customers, enhance public awareness towards musharakah financing, conduct regular visits to gain deep and accurate information concerning the operations of joint ventures business, and finally, the bank should have clearly written policy on musharakah agreement, financing, management and control systems. This study contributes to the existing literature on Islamic finance and banking, highlighting its growing global practice and theory, driven by community ethical and financial needs, innovation, and market competitiveness.

Understanding the SARS-CoV-2–Human Liver Interactome Using a Comprehensive Analysis of the Individual Virus–Host Interactions

Many metabolic processes at the molecular level support both viral attack strategies and human defenses during COVID-19. This knowledge is of vital importance in the design of antiviral drugs. In this study, we extracted 18 articles (2021–2023) from PubMed reporting the discovery of hub nodes specific for the liver during COVID-19, identifying 142 hub nodes. They are highly connected proteins from which to obtain deep functional information on viral strategies when used as functional seeds. Therefore, we evaluated the functional and structural significance of each of them to endorse their reliable use as seeds. After filtering, the remaining 111 hubs were used to obtain by STRING an enriched interactome of 1111 nodes (13,494 interactions). It shows the viral strategy in the liver is to attack the entire cytoplasmic translational system, including ribosomes, to take control of protein biosynthesis. We used the SARS2-Human Proteome Interaction Database (33,791 interactions), designed by us with BioGRID data to implement a reverse engineering process that identified human proteins actively interacting with viral proteins. The results show 57% of human liver proteins are directly involved in COVID-19, a strong impairment of the ribosome and spliceosome, an antiviral defense mechanism against cellular stress of the p53 system, and, surprisingly, a viral capacity for multiple protein attacks against single human proteins that reveal underlying evolutionary–topological molecular mechanisms. Viral behavior over time suggests different molecular strategies for different organs.

National values in the translation of Kazakh literary works

This article examines the translation of Kazakh cultural objects in literary works, which holds significant importance for Kazakh language and culture. The article analyzes the significance of national hair ornaments and belts in the works of Kazakh writers and their translation into Russian and English. Kazakh people believe that the hair ornament sholpy protects a girl or a young woman from evil forces. This type of hair ornament has both material and spiritual significance in Kazakh culture. In Kazakh literary works, the value of the analyzed jewelry is connected with its affiliation to a person and social status. It is presented as a symbol of female beauty. The belt is a valuable piece of nomadic clothing and a highly valued sacred object in Kazakh culture. Specific functional and semantic meanings as well as translation in literary works have been considered. The importance of translation as a “golden bridge” between different cultures is on the rise. As in other spheres, the requirements for translation are updated depending on the purpose and stage. The anthropocentric trend in modern linguistics raises the question of the relationship between language, man and culture, and poses the task of being able to convey the world view of one nation in the language of another, preserving all cultural and spiritual characteristics, taking into account deep information about people’s background knowledge. The article also analyzes the problem of background knowledge and the peculiarities of translating Kazakh culture-specific elements with spiritual significance for the people. These elements should be taken into account when translating literary works.

Lane detection networks based on deep neural networks and temporal information

In the past few years, the lane detection technique has become a key factor for autonomous driving systems and self-driving cars on the road. Among the various vehicle subsystems, the lane detection module is one of the essential parts of the Advanced Driver Assistance System (ADAS). Conventional lane detection approaches use machine vision algorithms to find straight lines in road scene images. However, it is challenging to identify straight or curved lane markings in complex environments. To deal with this problem, this paper presents a lane detection technique based on deep learning. It is combined with a 3D convolutional network, so the temporal information is added to the network architecture. Using the front camera images, the system can immediately detect the lane marking information ahead. Moreover, we propose an approach for improvement by adding the time axis to the network architecture. In addition to using 3D-ResNet50, the temporal convolution and spatial convolution are separated for processing. The accuracy is 91.34% improved after adding time and space split convolution with LeakyReLU. The experiments carried out using real scene images have demonstrated the feasibility of the proposed technique for applications to various complex scenes.

Rice Counting and Localization in Unmanned Aerial Vehicle Imagery Using Enhanced Feature Fusion

In rice cultivation and breeding, obtaining accurate information on the quantity and spatial distribution of rice plants is crucial. However, traditional field sampling methods can only provide rough estimates of the plant count and fail to capture precise plant locations. To address these problems, this paper proposes P2PNet-EFF for the counting and localization of rice plants. Firstly, through the introduction of the enhanced feature fusion (EFF), the model improves its ability to integrate deep semantic information while preserving shallow spatial details. This allows the model to holistically analyze the morphology of plants rather than focusing solely on their central points, substantially reducing errors caused by leaf overlap. Secondly, by integrating efficient multi-scale attention (EMA) into the backbone, the model enhances its feature extraction capabilities and suppresses interference from similar backgrounds. Finally, to evaluate the effectiveness of the P2PNet-EFF method, we introduce the URCAL dataset for rice counting and localization, gathered using UAV. This dataset consists of 365 high-resolution images and 173,352 point annotations. Experimental results on the URCAL demonstrate that the proposed method achieves a 34.87% reduction in MAE and a 28.19% reduction in RMSE compared to the original P2PNet while increasing R2 by 3.03%. Furthermore, we conducted extensive experiments on three frequently used plant counting datasets. The results demonstrate the excellent performance of the proposed method.

A short note on deep contextual spatial and spectral information fusion for hyperspectral image processing: Case of pork belly properties prediction

AbstractThis study demonstrates a new approach to process hyperspectral images where both the contextual spatial information as well as the spectral information are used to predict sample properties. The deep contextual spatial information is extracted using the deep feature extraction from pretrained resnet‐18 deep learning architecture, while the spectral information was readily available as the average pixel values. To fuse the information in a complementary way, a multiblock modeling approach called sequential orthogonalized partial least squares was used. The sequential model guarantees that the information learned is complementary from spatial and spectral domains. The potential of the approach is demonstrated to predict several physical and chemical properties in pork bellies.

Research on improved small scale face detection algorithm based on Yolov5

To address the challenges of dense scenarios with densely distributed small-scale faces, severe occlusions, and unclear features leading to inaccurate detection and high miss rates, we propose a lightweight small-scale face detection algorithm based on YOLOv5. The aim is to enhance the accuracy and precision of target detection. Firstly, we introduce the Convolutional Block Attention Module (CBAM) into the existing backbone network, obtaining more detailed features by comprehensively considering both spatial and channel dimensions. Next, in the Neck network, we embed involution to enhance channel information and weight distribution. Finally, a new feature fusion layer is added to improve the capture capability of feature information for smaller pixels and smaller targets in visible areas by integrating deep semantic information with shallow semantic information. The experimental results demonstrate that the improved model exhibits an increase in the average precision across all three subsets of the public WIDER FACE dataset, with improvements of 3.2%, 3.4%, and 2.6% respectively. The detection frame rate reaches 87 frames per second (FPS), significantly enhancing the detection performance of facial targets. This improvement meets the accuracy and real-time requirements for detecting small-scale facial targets in dense scenarios.

Multiple-in-Single-Out Object Detector Leveraging Spiking Neural Membrane Systems and Multiple Transformers.

Most existing multi-scale object detectors depend on multi-level feature maps. The Feature Pyramid Networks (FPN) is a significant architecture for object detection that utilizes these multi-level feature maps. However, the use of FPN also increases the detector's complexity. For object detection methods that only use a single-level feature map, the detection performance is limited to some extent because the single-level feature map cannot balance deep semantic information and shallow detail information. We introduce a novel detector- the Spiking Neural P Multiple-in-Single-out (SNPMiSo) detector to address these challenges. The SNPMiSo detector is constructed based on SNP-like neurons. In SNPMiSo, we employ two kinds of Transformers to boost the important features across different-level feature maps separately. After enhancing the features, we use an incremental upsampling module to upsample and merge the two feature maps. This combined feature map is input into the NAF dilated residual module and the NAF dual-branch detection head. This process allows us to extract multi-scale features and carry out detection tasks. Our tests show promising results: On the COCO dataset, SNPMiSo attains an Average Precision (AP) of 38.7, an improvement of 1.0 AP over YOLOF.In addition, SNPMiSo demonstrates a quicker detection speed, outperforming some advanced multi-level and single-level object detectors.

Semantic segmentation for multisource remote sensing images incorporating feature slice reconstruction and attention upsampling

ABSTRACT Multisource remote sensing images have rich features and high interpretability and are widely employed in many applications. However, highly unbalanced category distributions and complex backgrounds have created some difficulties in the application of remote sensing image semantic segmentation tasks, such as low accuracy of small target segmentation and inaccurate edge extraction. To solve these problems, in this paper, a feature map segmentation reconstruction module and an attention upsampling module are proposed. In the encoder part, the input feature map is equally segmented, and the segmented feature map is enlarged to effectively improve the small target feature information expression ability in the model. In the decoder part, the key segmentation and location information of shallow features are obtained using the global view. The deep semantic information and shallow spatial location information are fully combined to achieve a more refined upsampling operation. In addition, the attention mechanism of the spatial and channel squeeze and excitation block (scSE) is applied to pay more attention to important features and to suppress irrelevant background and redundant information. To verify the effectiveness of the proposed method, the WHU-OPT-SAR dataset and six state-of-the-art algorithms are utilized in comparative experiments. The experimental results show that our model has demonstrated the best performance and low computational complexity. With only approximately half the floating-point operation count and the number of model parameters of the MCANet model, which is specially designed for the dataset, our model surpasses MCANet by 1.52% and 1.53% in terms of mean intersection over union (mIoU) and F1 score, respectively. In particular, for small object regions such as roads and other categories, compared to the baseline model, the IoU and F1 score of our model are improved by 5.27% and 3.99% and by 5.68% and 5.65%, respectively. These results demonstrate the superior performance of our model in terms of accuracy and efficiency.

Pixel-wise crack defect segmentation with dual-encoder fusion network

Automatic crack defect detection plays an important role in early road maintenance. However, the crack defect detection accuracy is seriously affected by some challenging factors, such as complex background, class imbalance issue, poor texture, etc. In this paper, a deep crack defect segmentation network with dual-path encoding and hierarchical fusion schemes, named DEHF-Net, is presented to accurately and effectively segment the crack defects generated in crack images. In order to capture rich feature information of crack defects, a dual-path encoder unit is built to extract the spatial information and context information from crack images simultaneously. On the basis, to strengthen the features extracted from two encoding paths, an attention fusion (AF) block and feature enhancement (FE) block are proposed for effective feature learning to achieve information complementarity of dual-branch encoding paths. Meanwhile, to alleviate the problem of semantic gaps arising from large information differences between the encoding path and decoding path, a residual refinement unit (RRU) is also introduced to enable effective refinement of edges and details. Finally, to make the segmentation results more significant on multi-scale cracks, a weighted hierarchical fusion (WHF) block is introduced in the decoding stage to fuse the shallow texture information with the deep semantic information more effectively. Experimental results show the proposed model has obtained an excellent performance comparison with advanced methods.

Remote Sensing Images Secure Distribution Scheme Based on Deep Information Hiding

To ensure the security of highly sensitive remote sensing images (RSIs) during their distribution, it is essential to implement effective content security protection methods. Generally, secure distribution schemes for remote sensing images often employ cryptographic techniques. However, sending encrypted data exposes communication behavior, which poses significant security risks to the distribution of remote sensing images. Therefore, this paper introduces deep information hiding to achieve the secure distribution of remote sensing images, which can serve as an effective alternative in certain specific scenarios. Specifically, the Deep Information Hiding for RSI Distribution (hereinafter referred to as DIH4RSID) based on an encoder–decoder network architecture with Parallel Attention Mechanism (PAM) by adversarial training is proposed. Our model is constructed with four main components: a preprocessing network (PN), an embedding network (EN), a revealing network (RN), and a discriminating network (DN). The PN module is primarily based on Inception to capture more details of RSIs and targets of different scales. The PAM module obtains features in two spatial directions to realize feature enhancement and context information integration. The experimental results indicate that our proposed algorithm achieves relatively higher visual quality and secure level compared to related methods. Additionally, after extracting the concealed content from hidden images, the average classification accuracy is unaffected.

A multi-stage integrated model based on deep neural network for credit risk assessment with unbalanced data

PurposeWith the rapid growth of the domestic lending industry, assessing whether the borrower of each loan is at risk of default is a pressing issue for financial institutions. Although there are some models that can handle such problems well, there are still some shortcomings in some aspects. The purpose of this paper is to improve the accuracy of credit assessment models.Design/methodology/approachIn this paper, three different stages are used to improve the classification performance of LSTM, so that financial institutions can more accurately identify borrowers at risk of default. The first approach is to use the K-Means-SMOTE algorithm to eliminate the imbalance within the class. In the second step, ResNet is used for feature extraction, and then two-layer LSTM is used for learning to strengthen the ability of neural networks to mine and utilize deep information. Finally, the model performance is improved by using the IDWPSO algorithm for optimization when debugging the neural network.FindingsOn two unbalanced datasets (category ratios of 700:1 and 3:1 respectively), the multi-stage improved model was compared with ten other models using accuracy, precision, specificity, recall, G-measure, F-measure and the nonparametric Wilcoxon test. It was demonstrated that the multi-stage improved model showed a more significant advantage in evaluating the imbalanced credit dataset.Originality/valueIn this paper, the parameters of the ResNet-LSTM hybrid neural network, which can fully mine and utilize the deep information, are tuned by an innovative intelligent optimization algorithm to strengthen the classification performance of the model.

ESGN: Efficient Stereo Geometry Network for Fast 3D Object Detection

Fast stereo based 3D object detectors have made great progress recently. However, they suffer from the inferior accuracy. We argue that the main reason is due to the poor geometry-aware feature representation in 3D space. To solve this problem, we propose an efficient stereo geometry network (ESGN). The key in our ESGN is an efficient geometry-aware feature generation (EGFG) module. Our EGFG module first uses a stereo correlation and reprojection module to construct multi-scale stereo volumes in camera frustum space, second employs a multi-scale bird&#x2019;s eye view (BEV) projection and fusion module to generate multiple geometry-aware features. In these two steps, we adopt deep multi-scale information fusion for discriminative geometry-aware feature generation, without any complex aggregation networks. In addition, we introduce a deep geometry-aware feature distillation scheme to guide stereo feature learning with a LiDAR-based detector. The experiments are performed on the classical KITTI dataset. On KITTI test set, our ESGN outperforms the fast state-of-art-art detector YOLOStereo3D by 5.14% on mAP_3<i>d</i> at 62<i>ms</i>. To the best of our knowledge, our ESGN achieves a best trade-off between accuracy and speed. We hope that our efficient stereo geometry network can provide more possible directions for fast 3D object detection.

Confidence-diffusion instance contrastive learning for unsupervised domain adaptation

Unsupervised domain adaptation (UDA) aims to utilize knowledge from a related but inconsistently distributed source domain for target model training. The challenge of significant domain divergence, known as domain drift, can impact model performance. Although domain drift can lead to a decrease in the performance of the model in the target domain, effectively utilizing the relational information between unlabeled data can alleviate this issue. The new method of UDA, namely, confidence-diffusion instance contrastive learning (CDICL) in proposed in this article mines the deep information of the data in the target data by analyzing the pseudo labels of the target sample pairs. In this article, we propose a novel approach to unsupervised domain adaptation by constructing an information perception space via instance contrastive learning. This space incorporates samples from both source and target domains. Each target sample is assigned a pseudo-label and a corresponding confidence score, which is based on the category prior of the source samples. Throughout the training process, we continuously update the confidence associated with each pseudo-label. The classification task is performed based on the relationship of the target sample with the source domain samples. This method ensures that sample pairs belonging to the same class, regardless of whether they originate from the source or target domain, are drawn closer while those from different classes are simultaneously distanced. This approach offers a fresh perspective on unsupervised domain adaptation. The effectiveness of CDICL in UDA tasks has been demonstrated through experiments on three datasets: Office-31, Office-Home and VisDA-2017.

YOLO-B:An infrared target detection algorithm based on bi-fusion and efficient decoupled.

The YOLO-B infrared target detection algorithm is proposed to address the problems of incomplete extraction of detailed features and missed and wrong detection of infrared targets by YOLOv5s. The algorithm improves the SPPF of YOLOv5s feature extraction network by proposing the CSPPF structure to increase the sensory field of the model. The Bifusion Neck structure is invoked to fuse the shallow location information with deep semantic information to enhance the feature extraction capability of the model. Taking fully into account the different information of concern for classification and localization, the efficient decoupled head is used as the prediction head of this algorithm, which reduces the latency while maintaining the accuracy. WIoUv3 loss is used as a bounding box regression loss function to reduce the harmful gradient generated by low-quality examples and reduce the competitiveness of high-quality anchor frames. Comparative experiments were conducted for each of the four improvement points, and the experimental results showed that each improvement point had the highest detection accuracy in the comparative experiments of the same category. All improvement points are fused in turn and ablation experiments are performed. The YOLO-B algorithm improves 1.9% in accuracy, 7.3% in recall, 3.8% in map_0.5, and 4.6% in map_0.5:0.95 compared to YOLOv5s. When compared with YOLOv7 and YOLOv8s, the proposed algorithm has better performance in terms of the number of parameters and detection accuracy.

Seismic probing of buried ancient terrane boundaries - insight into Fennoscandia’s Palaeoproterozoic continental formation

Terrane boundaries are usually mapped from structures, lithologies and ages of the bedrock geology. Geophysical studies occasionally used to image terrane boundaries at depth typically yield localised information. In this contribution we demonstrate that it is possible to map Palaeoproterozoic terrane boundaries over large areas in northwest Fennoscandia through modelling of the crustal structure using receiver function inversion. Our new model suggests the existence of three “arms” of thick crust interpreted as deep expressions of Palaeoproterozoic terrane boundaries. We also observe previously unknown high velocity lower crust that we relate to Palaeoproterozoic rifting. The deep structural information shows that crustal structures can be preserved over billions of years and yields a three-dimensional crustal terrane model. This model improves our understanding of Palaeoproterozoic tectonics and continent formation processes.

Flexible drug-target interaction prediction with interactive information extraction and trade-off

Drug-target interaction (DTI) prediction refers to the use of computational methods and models to predict the interaction between drugs and biological targets. DTI can help researchers understand the mechanism of action of drugs, discover new drug targets, and screen drug candidates. Recently, a large number of DTI models integrating deep drug-target interaction features have emerged to make up for the dilemma of incomplete information on shallow drug and target features. However, these models ignore the challenge of overlapping interaction information by simply integrating deep interaction information. This paper proposes a flexible DTI prediction with interactive information extraction and trade-off (FDTIIT) to address the above challenges. The main idea of FDTIIT is to use flexible mutual attention to extract interaction information about drugs and targets, and then limit the dependence between them to avoid redundant information. Specifically, FDTIIT mainly includes three parts: drug and target representation, drug-target interactive information extraction, and drug-target interactive information trade-off. Among them, the drug and target representation module mainly uses the graph convolutional network and convolutional neural network to learn the representation of drugs and targets. Then, the drug-target interactive information extraction module extracts the drug information hidden in the target and the target information hidden in the drug based on mutual attention. To avoid possible information overlap between drug representation and target representation after the fusion of interaction information, FDTIIT designs an interactive information trade-off module. This module limits the dependence between drug and target representation, providing more comprehensive information to support high-performance drug-target interaction prediction. Multiple experiments designed on three publicly available datasets validated FDTIIT’s effectiveness.