Search

With the rapid development of remote sensing technology and the widespread application of remote sensing images, remote sensing object detection has become a hot research direction. However, we observe three primary challenges in remote sensing object detection: scale variations, small objects, and complex backgrounds. To address these challenges, we propose a novel detector, he Multi-Scale Context-Aware Network (MSCANet). First, we introduce a Multi-Scale Fusion Module (MSFM) that provides various scales of receptive fields to extract contextual information of objects at different scales adequately. Second, the Multi-Scale Guidance Module (MSGM) is proposed, which fuses deep and shallow feature maps from multiple scales, reducing the loss of feature information in small objects. Finally, we introduce the Context-Aware DownSampling Module (CADM). It dynamically adjusts context information weights at different scales, effectively reducing interference from complex backgrounds. Experimental results demonstrate that the proposed MSCANet achieves superior performance results with mean average precision (mAP) of 97.1% and 73.4% on the challenging RSOD and DIOR datasets, respectively, which indicates that the proposed network is suitable for remote sensing object detection and is of a great reference value. [ABSTRACT FROM AUTHOR]

Existing methods for makeup transfer mainly focus on the transfer of facial makeup, while overlooking the importance of hairstyles. To address this issue, we propose a composite makeup transfer model based on generative adversarial networks, which cleverly achieves composite transfer of facial makeup and hairstyles. Our model consists of two parallel branches: the facial makeup transfer branch and the hairstyle transfer branch. The facial makeup transfer branch integrates semantic correspondence learning and utilizes a bidirectional semantic correspondence feature transfer module to model and promote accurate semantic correspondence. During the generation process, we spatially distort the extracted makeup features to achieve semantic alignment with the target image. Subsequently, we fuse the distorted makeup features with the unmodified makeup-irrelevant features to generate facial makeup transfer results. In the hairstyle transfer branch, we introduce a occlusion repair module. This module leverages semantic relationships to repair facial occlusions in the source image. Then, combined with the pose consistency module, it generates hairstyle transfer results. Finally, the overall model’s generation effect is regulated through the comprehensive loss function we propose. Experimental results demonstrate that our method achieves visually accurate composite makeup and hairstyle transfer results. [ABSTRACT FROM AUTHOR]

Multi-interest sequential recommendations leverage users' historical behavior to provide recommendations that match multiple interests. Most of these methods have not fully extracted higher-order information hidden in users' interactions and have overlooked the multiple features of items. To this end, this paper proposes a multi-interest model called "multi-interest sequential recommendation with simplified graph convolution and item multi-features (SGCMF)". Firstly, a simplified graph convolution module is designed based on bipartite graphs, which utilizes mean pooling to aggregate neighboring information and employs a feedforward neural network (FNN) for nonlinear transformations and combinations. This method reduces redundant information and captures higher-order relationships, thereby simplifying the complexity of modeling high-order interactions and improving prediction accuracy. Secondly, an item multi-feature extraction module is proposed, which represents item features with multiple vectors, and analyzes each feature from multiple perspectives while preserving important relationships between features. The model correlates multiple features of the item with user interests, thereby achieving a fine-grained analysis of user interests. Extensive experiments are conducted on five real-world scenarios, and the results are compared with state-of-the-art methods. The experimental results show that SGCMF outperforms other baselines. [ABSTRACT FROM AUTHOR]

In complex scenarios, current detection algorithms often face challenges such as misdetection and omission when identifying irregularities in pedestrian mask wearing. This paper introduces an enhanced detection method called IPCRGC-YOLOv7 (Improved Partial Convolution Recursive Gate Convolution-YOLOv7) as a solution. Firstly, we integrate the Partial Convolution structure into the backbone network to effectively reduce the number of model parameters. To address the problem of vanishing training gradients, we utilize the residual connection structure derived from the RepVGG network. Additionally, we introduce an efficient aggregation module, PRE-ELAN (Partially Representative Efficiency-ELAN), to replace the original Efficient Long-Range Attention Network (ELAN) structure. Next, we improve the Cross Stage Partial Network (CSPNet) module by incorporating recursive gated convolution. Introducing a new module called CSPNRGC (Cross Stage Partial Network Recursive Gated Convolution), we replace the ELAN structure in the Neck part. This enhancement allows us to achieve higher order spatial interactions across different network hierarchies. Lastly, in the loss function component, we replace the original cross-entropy loss function with Efficient-IoU to enhance loss calculation accuracy. To address the challenge of balancing the contributions of high-quality and low-quality sample weights in the loss, we propose a new loss function called Wise-EIoU (Wise-Efficient IoU). The experimental results show that the IPCRGC-YOLOv7 algorithm improves accuracy by 4.71%, recall by 5.94%, mean Average Precision (mAP@0.5) by 2.9%, and mAP@.5:.95 by 2.7% when compared to the original YOLOv7 algorithm, which can meet the requirements for mask wearing detection accuracy in practical application scenarios. [ABSTRACT FROM AUTHOR]

Background: Breast cancer has the highest incidence rate of cancer worldwide, and brain metastases (BrM) are among the most malignant cases. While some patients have benefited from immune checkpoint inhibitors (ICIs), the complex anatomical structure of the brain and the heterogeneity of metastatic tumors have made it difficult to characterize the tumor immune microenvironment (TME) of metastatic tumors. Methods: To address this, we used single‐cell RNA sequencing (scRNA‐seq) to analyze immune cells in the cerebrospinal fluid (CSF) of BrM patients with breast cancer, thereby providing a comprehensive view of the immune microenvironment landscape of BrM. Results: Based on canonical marker genes, we identified nine cell types, and further identified their subtypes through differential expression gene (DEG) analysis. We compared the changes in cells and functions in the immune microenvironment of patients with different prognoses. Our analysis revealed a series of genes that promote tumor immune function (CCR5, LYZ, IGKC, MS4A1, etc.) and inhibit tumor immune function (SCGB2A2, CD24, etc.). Conclusions: The scRNA‐seq in CSF provides a noninvasive method to describe the TME of breast cancer patients and guide immunotherapy. [ABSTRACT FROM AUTHOR]

Mapping-based cross-domain recommendation (CDR) can effectively tackle the cold-start problem in traditional recommender systems. However, existing mapping-based CDR methods ignore data-sparse users in the source domain, which may impact the transfer efficiency of their preferences. To this end, this paper proposes a novel method named Neighbor Interaction-based Personalized Transfer for Cross-Domain Recommendation (NIPT-CDR). This proposed method mainly contains two modules: (i) an intra-domain item supplementing module and (ii) a personalised feature transfer module. The first module introduces neighbour interactions to supplement the potential missing preferences for each source domain user, particularly for those with limited observed interactions. This approach comprehensively captures the preferences of all users. The second module develops an attention mechanism to guide the knowledge transfer process selectively. Moreover, a meta-network based on users' transferable features is trained to construct personalised mapping functions for each user. The experimental results on two real-world datasets show that the proposed NIPT-CDR method achieves significant performance improvements compared to seven baseline models. The proposed model can provide more accurate and personalised recommendation services for cold-start users. [ABSTRACT FROM AUTHOR]

Kenaf is one of the most important natural cannabis plants. Molecular marker-assisted breeding is vital for accelerating the breeding process of kenaf. However, the number of kenaf markers is insufficient for molecular marker-assisted breeding. Using transcriptome sequencing data for salt-stressed kenaf plants, the number and distribution of simple sequence repeats (SSRs) and single nucleotide variations (SNVs) in the expressed sequences were determined. The objectives of this study were to elucidate the sequence variations in kenaf genes expressed in response to salt stress and to identify stable and dependable molecular markers. Primers were designed for SSR loci and then EST-SSR molecular markers were generated. The subsequent analyses revealed that 30.50% of the unigenes contained SSR motifs, most of which were single nucleotides followed by trinucleotides and dinucleotides. The unigenes containing SSRs were mostly associated with kenaf salt tolerance. Additionally, 10,483 SNVs were detected in contig sequences. Of the 3995 differentially expressed genes encoding interacting proteins, 1297 contained SSRs. Most of these genes were associated with metabolic pathways (e.g., 03000 transcription factors, B09132 signal transduction, and 04122 sulfur relay system). We designed 20 pairs of EST-SSR primers to genotype 30 kenaf varieties (lines), of which 9 primer pairs were ideal for genotyping (e.g., 1 highly polymorphic marker and 2 moderately polymorphic markers). The primer pairs designed for the EST-SSR markers in the kenaf genome may be useful SSR molecular markers for future research on kenaf. The verified polymorphic markers may be applicable to the molecular marker-assisted breeding of salt-tolerant kenaf varieties. [ABSTRACT FROM AUTHOR]

WRKY gene family is one of the largest transcription factor families involved in various physiological processes of plants. Flax (Linum usitatissimum) is an important stem fiber crop, and it is also an economically important crop in natural fiber and textile industries around the world. In this study, 105 WRKY genes were obtained by screening the whole genome of flax. There were 26 in group I, 68 in group II, 8 in group III and 3 in group UN. The characteristics of the WRKY motif and gene structure in each group are similar. The promoter sequence of WRKY genes includes photoresponsive elements, core regulatory elements and 12 cis-acting elements under abiotic stress. Similar to A. thaliana and Compositae plants, WRKY genes are evenly distributed on each chromosome, with segmental and tandem repeated events, which play a major role in the evolution of WRKY genes. The flax WRKY gene family is mainly concentrated in group I and group II. This study is mainly based on genome-wide information to classify and analyze the flax WRKY gene family, laying a foundation for further understanding the role of WRKY transcription factors in species evolution and functional analysis. [ABSTRACT FROM AUTHOR]

The plasmid vector platform is the most commonly used vector for the expression of the versatile CRISPR-Cas technique and the promoter is a crucial element for the expression vector, thus profiling the impact of the promoters on CRISPR editors provides the basic information for the gene-editing toolkits and can be a guideline for its design. Herein, we made a parallel comparison among four commonly used promoters (CAG, ~ 1700 bp; EF1a core, ~ 210 bp; CMV, ~ 500 bp; and PGK, ~ 500 bp) in CRISPR-Cas12a system in mammalian cells to explore the impact of promoters on this powerful tool. We found that without badly damaging targeting specificity, the CAG promoter-driving Cas12a editor exhibited the most active (efficiency takes as 100%, specificity index = ~ 75%) in genomic cleavage, multiplex editing, transcriptional activation, and base editing, followed by promoter CMV (efficiency = 70 ~ 90% (vs CAG), specificity index = ~ 78%), and then EF1a core and PGK (both efficiency = 40–60%, vs CAG) but with higher specificity (specificity index = ~ 84% and ~ 82%, respectively). Therefore, CAG is recommended in the CRISPR-Cas12a system for the applications that need a robust editing activity but without size limitation, CMV mostly can be an alternative for CAG when requiring a smaller space, EF1a is similar to PGK with relatively high specificity, but has a smaller size, thus is more suitable for in vivo therapeutic applications. The data outlined the properties of the widely used promoters in the CRISPR-Cas12a system, which can be a guide for its applications and can be a useful resource for the gene-editing field. [ABSTRACT FROM AUTHOR]

Mapping-based cross-domain recommendation (CDR) can effectively tackle the cold-start problem in traditional recommender systems. However, existing mapping-based CDR methods ignore data-sparse users in the source domain, which may impact the transfer efficiency of their preferences. To this end, this paper proposes a novel method named Neighbor Interaction-based Personalized Transfer for Cross-Domain Recommendation (NIPT-CDR). This proposed method mainly contains two modules: (i) an intra-domain item supplementing module and (ii) a personalised feature transfer module. The first module introduces neighbour interactions to supplement the potential missing preferences for each source domain user, particularly for those with limited observed interactions. This approach comprehensively captures the preferences of all users. The second module develops an attention mechanism to guide the knowledge transfer process selectively. Moreover, a meta-network based on users' transferable features is trained to construct personalised mapping functions for each user. The experimental results on two real-world datasets show that the proposed NIPT-CDR method achieves significant performance improvements compared to seven baseline models. The proposed model can provide more accurate and personalised recommendation services for cold-start users. [ABSTRACT FROM AUTHOR]

Aimed at the problems of small object detection in high resolution remote sensing images, such as difficult detection, diverse scales, and dense distribution, this study proposes a new method, DCE_YOLOX, which is more focused on small objects. The method uses depthwise separable deconvolution for upsampling, which can effectively recover lost feature information and combines dilated convolution and CoTNet to extract local contextual features, which can make full use of the hidden semantic information. At the same time, EcaNet is added to the enhanced feature extraction network of the baseline model to make the model more focused on information-rich features; secondly, the network input resolution is optimized, which can avoid the impact of image scaling to a certain extent and improve the accuracy of small object detection. Finally, CSL is used to calculate the angular loss to achieve the rotated object detection of remote sensing images. The proposed method in this study achieves 83.9% accuracy and 76.7% accuracy for horizontal object detection and rotationally invariant object detection, respectively, in the DOTA remote sensing dataset; it even achieves 96% accuracy for rotationally invariant object detection in the HRSC2016 dataset. It can be concluded that our algorithm has a better focus on small objects, while it has an equally good focus on other objects and is well suited for applications in remote sensing, and it has certain reference significance for realizing the detection of small objects in remote sensing images. [ABSTRACT FROM AUTHOR]

Facial expression recognition methods based on convolutional neural networks have greatly improved the recognition accuracy. However, the feature information of face images has not been fully extracted in these methods, which are mainly due to insufficient features of facial expressions in some Key positions, such as eyes, nose, and mouth. Adjusting the weights of these key positions can improve the accuracy of facial expression recognition. To address this problem, we propose a differential weight-based multi-dimension and multi-scale HOG algorithm (MDS-HOG). It can extract various types of deep features, thus enriching facial expression feature information. First, facial expression data is preprocessed using ENM region acquisition. Then, on the basis of the original HOG algorithm, the diagonal gradient information of the image is added to obtain the multi-dimension HOG feature. Furthermore, a multi-scale spatial pyramid is constructed to extract multi-scale HOG features. Finally, according to the different contributions of different face regions, a differential weight EMN algorithm is proposed to deal with the weight distribution of face sub-regions. Experimental results demonstrate that the proposed algorithm exhibits superior performance compared with the original and other improved HOG algorithms on JAFFE and CK+ datasets. [ABSTRACT FROM AUTHOR]

Despite the rapid development of pedestrian detection algorithms, the balance between detection accuracy and efficiency is still far from being achieved due to edge GPUs (low computing power) limiting the parameters of the model. To address this issue, we propose the YOLOv4-TP-Tiny based on the YOLOv4 model, which mainly includes two modules, two-dimensional attention (TA) and pedestrian-based feature extraction (PFM). First, we integrate the TA mechanism into the backbone network, which increases the attention of the network to the visible area of pedestrians and improves the accuracy of pedestrian detection. Then, the PFM is used to replace the original spatial pyramid pooling (SPP) structure in the YOLOv4 to obtain the YOLOv4-TP algorithm, which can adapt to different sizes of people to obtain higher detection accuracy. To maintain detection speed, we replaced the normal convolution with a ghost network with a TA mechanism, resulting in more feature maps with fewer parameters. We constructed a one-way multi-scale feature fusion structure to replace the down-sampling process, thereby reducing network parameters to obtain the YOLOv4-TP-Tiny model. The experimental results show that the YOLOv4-TP-tiny has 58.3% AP and 31 FPS in the winder person pedestrian dataset. With the same hardware conditions and dataset, the AP of the YOLOv4-tiny is 55.9%, and the FPS is 29. [ABSTRACT FROM AUTHOR]

Chronic exposure to noise is a detrimental environmental factor that can contribute to occupational noise-induced deafness (ONID) in industrial workers. ONID is caused by both environmental and genetic factors, and negatively impacts workers and manufacturing industries in China. Polymorphisms in the paraoxonase 2 gene (PON2) is associated with noise-induced hearing loss, and PON3 expression may modulate oxidative stress in cells and tissues by reducing the levels of reactive oxygen species, which are prominent in ONID. We conducted a matched case-control study to investigate whether PON3 polymorphisms and activity were associated with susceptibility to ONID. We genotyped PON3 single nucleotide polymorphisms (SNPs) using Sanger sequencing and measured the plasma PON3 activity using enzyme-linked immunosorbent assay. Conditional logistic regression models were fitted to evaluate the potential risk factors of ONID. A total of 300 subjects were included (n = 150 ONID and n = 150 control cases) from October 2017 to October 2019. We identified two types of genotypes for the PON3 SNPs. The independent risk factors for ONID were genotype CT and allele C with Odd's ratio (OR) = 2.12 (95% confidence interval [CI]: 1.18–3.84) and OR = 1.68 (95% CI: 1.06–2.66) for SNP rs11767787; AG and allele A with OR = 2.09 (95% CI: 1.25–3.47) and OR = 1.87 (95% CI: 1.19–2.93) for SNP rs13226149; and CT and allele T with OR = 2.59 (95% CI: 1.44–4.67) and OR = 1.95 (95% CI: 1.22–3.14) for SNP rs17882539, respectively. Furthermore, the plasma PON3 level (> 1504 U/L) was observed to be a protective factor associated with the lowest level of ONID (less than 991 U/L) after adjusting for confounding factors (OR = 0.27, 95% CI: 0.13–0.54). In conclusion, the PON3 polymorphisms rs11767787, rs13226149, and rs17882539 and plasma PON3 activity are associated with susceptibility to ONID in the Chinese population. [ABSTRACT FROM AUTHOR]

Background: Many studies have confirmed that circular RNAs (circRNAs) play a key role in the biological progression of cancers. However, the function of a novel circRNA, circ_0046599, in hepatocellular carcinoma (HCC) progression has not been explored. Methods: Quantitative real-time polymerase chain reaction (qRT-PCR) was performed to measure the expression of circ_0046599, microRNA (miR)-1258 and Ribophorin II (RPN2). Subcellular fractionation location assay was used to localize circ_0046599 in HCC cells. The circular characteristic of circ_0046599 was verified using Ribonuclease R (RNase R) digestion assay. Besides, cell counting kit 8 (CCK8) assay, colony formation assay, wound healing assay and transwell assay were used to detect cell proliferation, migration and invasion, respectively. The lactate production and glucose level were determined by Lactate and Glucose Assay Kits. Furthermore, the protein levels of glycolysis, metastasis and proliferation-related marker proteins, as well as RPN2 were tested by Western blot (WB) analysis. Moreover, dual-luciferase reporter assay and RNA immunoprecipitation (RIP) assay were employed to confirm the interactions among circ_0046599, miR-1258 and RPN2. In addition, mice xenograft models were applied to observe the effect of circ_0046599 silencing on HCC tumor growth in vivo. Results: Circ_0046599 was highly expressed in HCC tissues and cells, and its knockdown could suppress HCC cell proliferation, migration, invasion and glycolysis process. MiR-1258 could be targeted by circ_0046599, and its inhibitor could invert the suppressing effect of circ_0046599 knockdown on HCC progression. Further, RPN2 was a target of miR-1258. Overexpressed RPN2 could reverse the inhibiting effect of miR-1258 overexpression on HCC progression. Also, knockdown of circ_0046599 could restrain HCC tumor growth in vivo. Conclusion: Our results provided new evidence that circ_0046599 could promote the progression of HCC by increasing RPN2 expression via sponging miR-1258. [ABSTRACT FROM AUTHOR]

Today, diabetes is one of the most common, chronic, and, due to some complications, deadliest diseases in the world. The early detection of diabetes is very important for its timely treatment since it can stop the progression of the disease. The proposed method can help not only to predict the occurrence of diabetes in the future but also to determine the type of the disease that a person experiences. Considering that type 1 diabetes and type 2 diabetes have many differences in their treatment methods, this method will help to provide the right treatment for the patient. By transforming the task into a classification problem, our model is mainly built using the hidden layers of a deep neural network and uses dropout regularization to prevent overfitting. We tuned a number of parameters and used the binary cross-entropy loss function, which obtained a deep neural network prediction model with high accuracy. The experimental results show the effectiveness and adequacy of the proposed DLPD (Deep Learning for Predicting Diabetes) model. The best training accuracy of the diabetes type data set is 94.02174%, and the training accuracy of the Pima Indians diabetes data set is 99.4112%. Extensive experiments have been conducted on the Pima Indians diabetes and diabetic type datasets. The experimental results show the improvements of our proposed model over the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In memory computing and high-end distributed storage demand low latency, high throughput, and zero data loss simultaneously from datacenter networks. Existing reactive congestion control approaches cannot both minimize queuing latency and ensure zero data loss. A token-oriented proactive approach can achieve them together by controlling congestion even before sending data packets. However, state-of-the-art token-oriented approaches only strive to optimize network-level metrics: maximizing throughput while achieving flow-level fairness. This article answers the question of how to support objective-aware traffic scheduling in token-oriented approaches. The novelty of Token-Oriented in-network Prioritization (TOP) is that it prioritizes tokens instead of data packets. We make three contributions. Via simulations over a hypothetical TOP system, our first contribution is demonstrating the potential performance gain that can be brought by TOP. Second, we investigate the applicability of TOP. Although the overhead of enabling necessary TOP features in switches is trivial, we find that mainstream commodity datacenter switches do not support them. We hence propose a readily-deployable remedy to achieve in-network prioritization by pushing both switch and end-host hardware capacity to an extreme end. Lastly, we implement a running TOP system with Linux hosts and commodity switches, and evaluate TOP in testbeds and with large-scale simulations for various scenarios. [ABSTRACT FROM AUTHOR]

The article titled "Expression recognition algorithm based on MDS-HOG feature optimization and differential weights" has been retracted by the publisher, in agreement with the Editor-in-Chief of the Journal of Combinatorial Optimization. The retraction was a result of an investigation that revealed concerns about compromised editorial handling and peer review process, inappropriate or irrelevant references, and the article not being in scope of the journal or guest-edited issue. The publisher and Editor-in-Chief no longer have confidence in the results and conclusions of this article, although the authors disagree with the retraction. Springer Nature, the publisher, remains neutral regarding jurisdictional claims and institutional affiliations. [Extracted from the article]

Fuzzy support vector machine (FSVM) is a part of machine learning with its good classification effect. So far, there are two most commonly used FSVM models: FSVM on account of class core and fuzzy support vector machine on account of hyperplane that is over class core. Each has its own problems: FSVM on account of class core are dependent on the geometric shape of sample sets. Although FSVM on account of hyperplane that is over class core can solve the above problems to some extent. However, this algorithm has low generalization ability and high time complexity. Therefore, Inspired by these two common models, the paper proposes an improved membership function method. By analyzing and calculating the potential support vector sample points, adjustment factor is obtained, which drives the class core to adjust along the direction away from the outliers. In this way, membership of noise and outliers are reduced and the membership of support vector will also increase to some extent. In this paper, a new experimental comparison method is used, which can make the comparison of classification effect more obvious and convincing. The experimental part compares the proposed FSVM model with the above two FSVM models. It shows that the proposed algorithm improves the stability and classification accuracy to some extent. [ABSTRACT FROM AUTHOR]