Search

Background: Persistent maladaptive changes of corticospinal tract (CST) and quadriceps strength deficits exist in patients with anterior cruciate ligament reconstruction (ACLR). This study aimed to investigate the relationships between the structural alterations of CST and quadriceps muscle strength deficits in patients with ACLR. Methods: Twenty-nine participants who had undergone unilateral ACLR (29 males; age = 32.61 ± 6.72 years) were enrolled in a cross-sectional investigation. We chose CST as a region of interest and performed diffusion tensor imaging (DTI) that measured the microstructure of white matter tracts. Maximal voluntary isometric quadriceps muscle strength was assessed using a hand-held dynamometer. Simple and partial correlation analyses were performed between the DTI outcomes and quadriceps muscle strength deficits in patients with ACLR before and after controlling for age, sex, BMI, Tegner activity score, and graft type. Sub-group analyses were also performed to investigate the relationships between the DTI outcomes of CST structure and quadriceps muscle strength deficits according to the graft type before and after controlling for age, sex, BMI, and Tegner activity score. Results: Lower limb symmetry index (LSI) of quadriceps muscle strength was associated with a higher ratio of radial diffusivity (RD, r = −0.379, p = 0.042) in corticospinal tracts of the injured hemisphere to those of the non-injured hemisphere in ACLR patients after controlling for age, BMI, Tegner activity score and graft type. In subgroup analyses of ACLR patients with hamstring autografts, we found that higher injured quadriceps muscle strength was associated with higher axial diffusivity (AD, r = 0.616, p = 0.033) of CST structure and lower LSI of quadriceps muscle strength was associated with higher ratio of mean diffusivity (MD, r = −0.682, p = 0.014) and RD (r = −0.759, p = 0.004) in corticospinal tracts of the injured hemisphere to those of the non-injured hemisphere in ACLR patients after controlling for age, BMI, Tegner activity score. Conclusion: Decreased integrity (higher ratio of RD) of CST microstructure in ACLR patients was significantly associated with lower quadriceps limb symmetry index, which hinted that quadriceps muscle strength deficits of injured side may be a demyelinating process of CST microstructure in ACLR.

N1-methyladenosine (m1A) modification is an epigenetic change that occurs on RNA molecules, regulated by a suite of enzymes including methyltransferases (writers), demethylases (erasers), and m1A-recognizing proteins (readers). This modification significantly impacts the function of RNA and various biological processes by affecting the structure, stability, translation, metabolism, and gene expression of RNA. Thereby, m1A modification is closely associated with the occurrence and progression of cancer. This review aims to explore the role of m1A modification in tumor immunity. m1A affects tumor immune responses by directly regulating immune cells and indirectly modulating tumor microenvironment. Besides, we also discuss the implications of m1A-mediated metabolic reprogramming and its nexus with immune checkpoint inhibitors, unveiling promising avenues for immunotherapeutic intervention. Additionally, the m1AScore, established based on the expression patterns of m1A modification, can be used to predict tumor prognosis and guide personalized therapy. Our review underscores the significance of m1A modification as a burgeoning frontier in cancer biology and immuno-oncology, with the potential to revolutionize cancer treatment strategies.

The study of motor muscle control mechanisms can improve rehabilitation therapy and human-computer interaction technology. The limitations of traditional electroencephalography (EEG) limit the comprehensive understanding of motor muscle control mechanisms. Therefore, this study aims to explore the mechanism of motor muscle control based on optical EEG images, in order to expand the understanding of the process of motor control. The study selected optical EEG imaging technology as the main data acquisition tool. Optical EEG images have higher spatiotemporal resolution and can provide more detailed neural activity information. This technology combines optical imaging with EEG images to obtain spatiotemporal information of brain activity in a short period of time. The device is composed of multiple optical sensors and can measure blood oxygen concentration and neuronal activity in the cerebral cortex. Preprocess EEG image data using image processing and signal processing techniques, then use computational methods and algorithms to detect activated regions, and evaluate their relationships using correlation analysis and statistical methods. By comparing EEG image data and motor muscle activity data under different motor tasks. The research results show that optical EEG imaging technology can provide more detailed information on brain neural activity and accurately capture the activity patterns of different motor muscles. These results provide new perspectives and methods for further studying the control mechanisms of motor muscles.

Abstract Background Previous experimental studies have suggested that the consumption of soy isoflavones may have a potential impact on lowering blood pressure. Nevertheless, epidemiological studies have presented conflicting outcomes concerning the correlation between soy isoflavone consumption and blood pressure levels. Consequently, a comprehensive meta-analysis of all eligible randomized controlled trials (RCTs) was conducted to explore the influence of soy isoflavones on systolic blood pressure (SBP) and diastolic blood pressure (DBP) in adults. Methods A thorough search of PubMed, Embase, and the Cochrane Library for relevant literature up to April 30, 2023 was conducted. RCTs involving adults that compared soy isoflavone supplementation with a placebo (the same matrix devoid of soy isoflavone) were included. The combined effect size was presented as the weighted mean difference (WMD) along with 95% confidence interval (CI), employing a fixed-effects model. Results Our meta-analysis included a total of 24 studies involving 1945 participants. The results revealed a significant reduction in both SBP and DBP with soy isoflavone supplementation. Subgroup analyses suggested more pronounced reductions in SBP and DBP for interventions lasting ≥6 months, in individuals receiving mixed-type soy isoflavone, and among patients with metabolic syndrome or prehypertension. However, we did not detect significant nonlinear associations between supplementation dosage and intervention duration concerning both SBP and DBP. The overall quality of evidence was deemed moderate. Conclusions The current meta-analysis revealed that supplementation with soy isoflavones alone effectively reduces blood pressure. Additional high-quality studies are required to investigate the efficacy of blood pressure reduction through supplementation with an optimal quantity and proportion of soy isoflavone.

Abstract Necroptosis is a kind of programmed cell death that causes the release of damage-associated molecular patterns and inflammatory disease including skin inflammation. Activation of receptor-interacting serine/threonine kinase 1 (RIPK1), RIPK3, and mixed lineage kinase domain-like protein (MLKL) is the hallmark of tumour necrosis factor α (TNF)-induced necroptosis. Here, we screened a small-molecule compound library and found that saracatinib inhibited TNF-induced necroptosis. By targeting MLKL, Saracatinib interfered with the phosphorylation, translocation, and oligomerization of MLKL induced by TNF. Consistently, mutation of the saracatinib-binding site of MLKL reduced the inhibitory effect of saracatinib on TNF-induced necroptosis. In an imiquimod (IMQ)-induced psoriasis mouse model, saracatinib effectively blocked MLKL phosphorylation and inflammatory responses in vivo. Taken together, these findings indicate that saracatinib inhibits necroptosis by targeting MLKL, providing a potential therapeutic approach for skin inflammation-related diseases such as psoriasis.

Three new 24-membered macrolactines, amylomacrolactines A–C (1–3), along with two known compounds 4 and 5, were isolated from the Arctic bacteria Bacillus amyloliquefaciens SCSIO 41392. The configurations of 1–3 were assigned by a combination of coupling constants, NOESY, and analysis of MM2-optimized conformation, as well as by comparison with reports in the literature. Compounds 1 and 2 showed quorum sensing (QS) inhibitory activities against the Pseudomonas aeruginosa (P. aeruginosa) PQS system and suppressed PQS-regulated virulence factor pyocyanin synthesis. In addition, compounds 3–5 affected the production of another essential virulence factor, siderophore of pyoverdine (PVD), in P. aeruginosa. More importantly, compound 5 showed an anti-biofilm activity against P. aeruginosa. Altogether, the isolated compounds displayed multiple bacterial virulence inhibition activities, which is worthy of further exploration for novel analogues in antimicrobial drug development.

Abstract Necroptosis is a form of regulated cell death that has been implicated in multiple diseases. TNF-induced necroptosis is regulated by necrosomes, complexes consisting of RIPK1, RIPK3 and MLKL. In this study, by screening of a small-compound library, we identified dozens of compounds that inhibited TNF-induced necroptosis. According to the mechanisms by which they inhibited necroptosis, these compounds were classified into different groups. We then identified Ibrutinib as an inhibitor of RIPK3 and found that Quizartinib protected against the TNF-induced systemic inflammatory response syndrome in mice by inhibiting the activation of RIPK1. Altogether, our work revealed dozens of necroptosis inhibitors, suggesting new potential approaches for treating necroptosis-related diseases.

BackgroundSyndrome of inappropriate antidiuretic(SIAD) occurs secondary to various diseases, which is characterised by hypotonic hyponatremia and impaired urinary diluting capacity. Research on SIAD in both domestic and international contexts has a long history. This study objectively and comprehensively analyses the research trends, hotspots and development of SIAD research of the past 20 years using the method of bibliometric analysis.MethodsThe 2003–2022 data in the Web of Science Core Collection database were searched. The Bibliometrix software package, VOSviewer and CiteSpace were used to mine, extract and visualise the retrieved literature, and the generated maps were used in analysing the main topics and trends in the field of SIAD research.ResultsA total of 1215 articles published in 623 journals were included in the analysis, with a total of 18,886 citations. Results showed that the research output on SIAD has continuously increased in the past 20 years, and the United States had the highest number of publications and citations. Keywords with the highest burst strength in recent years were the most mentioned keywords, in addition to the search terms ‘hyponatremia’, ‘covid-19’, and ‘mortality’. Thus, the relationship among SIAD, covid-19 and mortality may become research frontiers and trends. Fifteen milestone articles were identified through co-citation analysis, which mainly focused on the pathophysiology and treatment of SIAD.ConclusionBased on bibliometric analysis and knowledge mapping, this study summarises development trends in the field of SIAD research, providing references for current and future research into SIAD.

The purpose of this study was to explore the potential of the development and application of Paecilomyces hepiali, a fungus with edible and medicinal value, as a foodborne antioxidant and anti-aging agent. Its n-butanol extract (PHE) from rice cultures was selected for anti-aging experiment because of significant free radical scavenging activity in vitro. In vivo, PHE could significantly prolong the mean lifespan, 50 % survival days, and the maximum lifespan of Drosophila on a high-fat diet. It is amazing that the mean lifespan increased from 19.1 days to 32.9 days, 50 % survival days increased from 15.7 days to 34.3 days, and the maximum lifespan extended from 44.7 days to 52.7 days, when the high-fat female Drosophila model was fed with 10 μg/mL PHE. Further research showed that PHE reduced the accumulation of peroxide products and increased the activity of antioxidant enzymes. Then, through antioxidant activity tracking, dimerumic acid (compound 1, the IC50 value of 3.4 μg/mL on DPPH free radicals scavenging activity), 4,5-dihydroxy-3-methoxypentanoic acid (compound 2, new compound), and thymidine (compound 3) were isolated from PHE. It is worth mentioning that dimerumic acid, the major antioxidant compound of PHE (content up to 3 %), was discovered in P. hepiali for the first time. It was concluded that PHE showed excellent anti-aging activity at a very low concentration on fat diet-induced high fat Drosophila melanogaster, and dimerumic acid may be its main material basis. These results indicated that PHE had the potential to be developed as antioxidant and anti-aging agent in the healthcare industry.

Recently, transformer has gradually attracted interest for its excellence in modeling the long-range dependencies of spatial-spectral features in HSI. However, transformer has the problem of the quadratic computational complexity due to the self-attention mechanism, which is heavier than other models and thus has limited adoption in HSI processing. Fortunately, the recently emerging state space model-based Mamba shows great computational efficiency while achieving the modeling power of transformers. Therefore, in this paper, we first proposed spectral-spatial Mamba (SS-Mamba) for HSI classification. Specifically, SS-Mamba mainly includes a spectral-spatial token generation module and several stacked spectral-spatial Mamba blocks. Firstly, the token generation module converts any given HSI cube to spatial and spectral tokens as sequences. And then these tokens are sent to stacked spectral-spatial mamba blocks (SS-MB). Each SS-MB includes two basic mamba blocks and a spectral-spatial feature enhancement module. The spatial and spectral tokens are processed separately by the two basic mamba blocks, correspondingly. Moreover, the feature enhancement module modulates spatial and spectral tokens using HSI sample’s center region information. Therefore, the spectral and spatial tokens cooperate with each other and achieve information fusion within each block. The experimental results conducted on widely used HSI datasets reveal that the proposed SS-Mamba requires less processing time compared with transformer. The Mamba-based method thus opens a new window for HSI classification.

Radar jamming recognition is a key step in electronic countermeasures, and accurate and sufficient labeled samples are essential for supervised learning-based recognition methods. However, in real practice, collected radar jamming samples often have weak labels (i.e., noisy-labeled or unlabeled ones), which degrade recognition performance. Additionally, recognition performance is hindered by limitations in capturing the global features of radar jamming. The Transformer (TR) has advantages in modeling long-range relationships. Therefore, a weakly supervised Transformer is proposed to address the issues of performance degradation under weak supervision. Specifically, complementary label (CL) TR, called RadarCL-TR, is proposed to improve radar jamming recognition accuracy with noisy samples. CL learning and a cleansing module are successively utilized to detect and remove potentially noisy samples. Thus, the adverse influence of noisy samples is mitigated. Additionally, semi-supervised learning (SSL) TR, called RadarSSL-PL-TR, is proposed to boost recognition performance under unlabeled samples via pseudo labels (PLs). Network generalization is improved by training with pseudo-labeling unlabeled samples. Moreover, the RadarSSL-PL-S-TR is proposed to further promote recognition performance, where a selection module identifies reliable pseudo-labeling samples. The experimental results show that the proposed RadarCL-TR and RadarSSL-PL-S-TR outperform comparison methods in recognition accuracy by at least 7.07% and 6.17% with noisy and unlabeled samples, respectively.

A Chinese family was identified to have two patients with rickets, an adult female and a male child (proband), both exhibiting signs related to X-linked hypophosphatemic rickets (XLH). Gene sequencing analysis revealed a deletion of adenine at position 1985 (c.1985delA) in the PHEX-encoding gene. To investigate the relationship between this mutation and the pathogenicity of XLH, as well as analyze the effects of different dosages of PHEX gene mutations on clinical phenotypes, we developed a rat model carrying the PHEX deletion mutation. The CRISPR/Cas9 gene editing technology was employed to construct the rat model with the PHEX gene mutation (c.1985delA). Through reproductive procedures, five genotypes of rats were obtained: female wild type (X/X), female heterozygous (-/X), female homozygous wild type (-/-), male wild type (X/Y), and male hemizygous (-/Y). The rats with different genotypes underwent analysis of growth, serum biochemical parameters, and bone microstructure. The results demonstrated the successful generation of a stable rat model inheriting the PHEX gene mutation. Compared to the wild-type rats, the mutant rats displayed delayed growth, shorter femurs, and significantly reduced bone mass. Among the female rats, the homozygous individuals exhibited the smallest body size, decreased bone mass, shortest femur length, and severe deformities. Moreover, the mutant rats showed significantly lower blood phosphorus concentration, elevated levels of FGF23 and alkaline phosphatase, and increased expression of phosphorus regulators. In conclusion, the XLH rat model with the PHEX gene mutation dosage demonstrated its impact on growth and development, serum biochemical parameters, and femoral morphology.

During postharvest storage and transportation, fruits and vegetables are prone to decay and deterioration due to the infection of pathogenic bacteria. The control of postharvest diseases mainly relies on chemical synthetic fungicides, but long-term use will lead to environmental pollution and food safety problems. Biological control has the characteristic of green environmental protection and is gradually being applied. Bacillus, as an important biocontrol bacterium, plays an important role in the prevention and control of postharvest diseases of fruits and vegetables. At present, there are a lot of studies on the prevention and control of postharvest diseases of fruits and vegetables by biocontrol Bacillus. In this paper, the species, action mechanism and application status of biocontrol Bacillus in postharvest diseases are reviewed in order to provide reference for the application and development of biocontrol bacillus in postharvest diseases of fruits and vegetables.

Neoadjuvant chemotherapy (NAC) for breast cancer is widely used in the clinical setting to improve the chance of surgery, breast conservation and quality of life for patients with advanced breast cancer. A more accurate efficacy evaluation system is important for the decision of surgery timing and chemotherapy regimen implementation. However, current methods, encompassing imaging techniques such as ultrasound and MRI, along with non-imaging approaches like pathological evaluations, often fall short in accurately depicting the therapeutic effects of NAC. Imaging techniques are subjective and only reflect macroscopic morphological changes, while pathological evaluation is the gold standard for efficacy assessment but has the disadvantage of delayed results. In an effort to identify assessment methods that align more closely with real-world clinical demands, this paper provides an in-depth exploration of the principles and clinical applications of various assessment approaches in the neoadjuvant chemotherapy process.

Abstract The long-term impact of COVID-19 among those with mild infections is not well characterized. Among 81 adults who completed online assessments at 3- and 12-months following infection, quality of life scores did not significantly improve over time. Among 62 subjects who also completed telephone interviews, respiratory symptoms or exercise limitation were reported by 42% at a median follow-up of 387 days (IQR 251–402 days). Those with persistent respiratory symptoms scored lower on the EQ-5D visual analog score compared to those without. Persistent respiratory symptoms were associated with a lower likelihood of full-time employment at 1 year (aOR 0.09, 95%CI 0.01–0.91; P = 0.041). In an adjusted linear regression, persistent respiratory symptoms (P = 0.037) and female sex (P = 0.016) were both independent risks for increased visits to a primary care provider. This cohort study demonstrates that respiratory symptoms are frequent at 1 year following COVID-19 and more importantly, are associated with negative impacts on employment, quality of life, and health care utilization. Further research is needed to determine the pathophysiology and risk factors for persistent symptoms as well as optimal management strategies to improve the level of functioning and quality of life.

Abstract Autophagy classically functions as a physiological process to degrade cytoplasmic components, protein aggregates, and/or organelles, as a mechanism for nutrient breakdown, and as a regulator of cellular architecture. Its biological functions include metabolic stress adaptation, stem cell differentiation, immunomodulation and diseases regulation, and so on. Current researches have proved that autophagy dysfunction may contribute to the pathogenesis of some myopathies through impairment of myofibres regeneration. Studies of autophagy inhibition also indicate the importance of autophagy in muscle regeneration, while activation of autophagy can restore muscle function in some myopathies. In this review, we aim to report the mechanisms of action of autophagy on muscle regeneration to provide relevant references for the treatment of regenerating defective myopathies by regulating autophagy. Results have shown that one key mechanism of autophagy regulating the muscle regeneration is to affect the differentiation fate of muscle stem cells (MuSCs), including quiescence maintenance, activation and differentiation. The roles of autophagy (organelle/protein degradation, energy facilitation, and/or other) vary at different myogenic stages of the repair process. When the muscle is in homeostasis, basal autophagy can maintain the quiescence state and stemness of MuSCs by renewing organelle and protein. After injury, the increased autophagy flux contributes to meet biological energy demand of MuSCs during activation and proliferation. By mitochondrial remodelling, autophagy during differentiation can promote the metabolic transformation and balance mitochondrial‐mediated apoptosis signals in myoblasts. Autophagy in mature myofibres is also essential for the degradation of necrotic myofibres, and may affect the dynamics of MuSCs by affecting the secretion spectrum of myofibres or the recruitment of supporting cells. Except for myogenic cells, autophagy also plays an important role in regulating the function of non‐myogenic cells in the muscle microenvironment, which is also essential for successful muscle recovery. Autophagy can regulate the immune microenvironment during muscle regeneration through the recruitment and polarization of macrophages, while autophagy in endothelial cells can regulate muscle regeneration in an angiogenic or angiogenesis‐independent manner. Drug or nutrition targeted autophagy has been preliminarily proved to restore muscle function in myopathies by promoting muscle regeneration, and further understanding the role and mechanism of autophagy in various cell types during muscle regeneration will enable more effective combinatorial therapeutic strategies.

Abstract Background Obesity leads to a decline in the exercise capacity of skeletal muscle, thereby reducing mobility and promoting obesity-associated health risks. Dietary intervention has been shown to be an important measure to regulate skeletal muscle function, and previous studies have demonstrated the beneficial effects of docosahexaenoic acid (DHA; 22:6 ω-3) on skeletal muscle function. At the molecular level, DHA and its metabolites were shown to be extensively involved in regulating epigenetic modifications, including DNA methylation, histone modifications, and small non-coding microRNAs. However, whether and how epigenetic modification of mRNA such as N6-methyladenosine (m6A) mediates DHA regulation of skeletal muscle function remains unknown. Here, we analyze the regulatory effect of DHA on skeletal muscle function and explore the involvement of m6A mRNA modifications in mediating such regulation. Results DHA supplement prevented HFD-induced decline in exercise capacity and conversion of muscle fiber types from slow to fast in mice. DHA-treated myoblasts display increased mitochondrial biogenesis, while slow muscle fiber formation was promoted through DHA-induced expression of PGC1α. Further analysis of the associated molecular mechanism revealed that DHA enhanced expression of the fat mass and obesity-associated gene (FTO), leading to reduced m6A levels of DNA damage-induced transcript 4 (Ddit4). Ddit4 mRNA with lower m6A marks could not be recognized and bound by the cytoplasmic m6A reader YTH domain family 2 (YTHDF2), thereby blocking the decay of Ddit4 mRNA. Accumulated Ddit4 mRNA levels accelerated its protein translation, and the consequential increased DDIT4 protein abundance promoted the expression of PGC1α, which finally elevated mitochondria biogenesis and slow muscle fiber formation. Conclusions DHA promotes mitochondrial biogenesis and skeletal muscle fiber remodeling via FTO/m6A/DDIT4/PGC1α signaling, protecting against obesity-induced decline in skeletal muscle function.

Background: Current artificial intelligence (AI) in histopathology typically specializes on a single task, resulting in a heavy workload of collecting and labeling a sufficient number of images for each type of cancer. Heterogeneous transfer learning (HTL) is expected to alleviate the data bottlenecks and establish models with performance comparable to supervised learning (SL). Methods: An accurate source domain model was trained using 28,634 colorectal patches. Additionally, 1000 sentinel lymph node patches and 1008 breast patches were used to train two target domain models. The feature distribution difference between sentinel lymph node metastasis or breast cancer and CRC was reduced by heterogeneous domain adaptation, and the maximum mean difference between subdomains was used for knowledge transfer to achieve accurate classification across multiple cancers. Result: HTL on 1000 sentinel lymph node patches (L-HTL-1000) outperforms SL on 1000 sentinel lymph node patches (L-SL-1-1000) (average area under the curve (AUC) and standard deviation of L-HTL-1000 vs. L-SL-1-1000: 0.949 ± 0.004 vs. 0.931 ± 0.008, p value = 0.008). There is no significant difference between L-HTL-1000 and SL on 7104 patches (L-SL-2-7104) (0.949 ± 0.004 vs. 0.948 ± 0.008, p value = 0.742). Similar results are observed for breast cancer. B-HTL-1008 vs. B-SL-1-1008: 0.962 ± 0.017 vs. 0.943 ± 0.018, p value = 0.008; B-HTL-1008 vs. B-SL-2-5232: 0.962 ± 0.017 vs. 0.951 ± 0.023, p value = 0.148. Conclusions: HTL is capable of building accurate AI models for similar cancers using a small amount of data based on a large dataset for a certain type of cancer. HTL holds great promise for accelerating the development of AI in histopathology.

Recently, deep learning methods, especially convolutional neural networks (CNNs), have achieved good performance for hyperspectral image (HSI) classification. However, due to limited training samples of HSIs and the high volume of trainable parameters in deep models, training deep CNN-based models is still a challenge. To address this issue, this study investigates contrastive learning (CL) as a pre-training strategy for HSI classification. Specifically, a supervised contrastive learning (SCL) framework, which pre-trains a feature encoder using an arbitrary number of positive and negative samples in a pair-wise optimization perspective, is proposed. Additionally, three techniques for better generalization in the case of limited training samples are explored in the proposed SCL framework. First, a spatial–spectral HSI data augmentation method, which is composed of multiscale and 3D random occlusion, is designed to generate diverse views for each HSI sample. Second, the features of the augmented views are stored in a queue during training, which enriches the positives and negatives in a mini-batch and thus leads to better convergence. Third, a multi-level similarity regularization method (MSR) combined with SCL (SCL–MSR) is proposed to regularize the similarities of the data pairs. After pre-training, a fully connected layer is combined with the pre-trained encoder to form a new network, which is then fine-tuned for final classification. The proposed methods (SCL and SCL–MSR) are evaluated on four widely used hyperspectral datasets: Indian Pines, Pavia University, Houston, and Chikusei. The experiment results show that the proposed SCL-based methods provide competitive classification accuracy compared to the state-of-the-art methods.

The accurate classification of radar jamming signal is a core step of anti-jamming. Recently, convolutional neural network (CNN) based methods have shown their powerfulness in signal processing. In this paper, a deep fusion method based on CNN is proposed to classify jamming signal acting on pulse compression radar. The proposed method consists of three subnetworks (i.e., 1D-CNN, 2D-CNN, and fusion network). 1D-CNN is used to extract deep features of original radar jamming signal. Meanwhile, in order to extract the time-frequency features, short time Fourier transform (STFT) is applied to jamming signal to obtain time-frequency spectrograms. Then, 2D-CNN is used to extract deep time-frequency features, which are useful for further features fusion processing. Fusion network is used to deeply fuse the extracted features of the aforementioned CNNs and softmax is used to finish the task of radar jamming signal classification. In addition, in order to alleviate the problem of overfitting and improve the generalization ability of proposed model, soft label smoothing is proposed. The experimental results reveal that the proposed method provides competitive results in term of classification accuracy.

Jamming is a big threat to radar system survival and anti-jamming is a part of the solution. The classification of radar jamming signal is the first step toward to anti-jamming. Recently, as an important part of deep learning, convolutional neural network (CNN) based methods have shown their capability in discriminant feature extraction and accurate classification. In this study, in order to harness the powerfulness of deep learning, CNN based methods are proposed to classify radar jamming signal acting on pulse compression radar. Specifically, a 1D-CNN is designed for radar jamming signal classification under the condition of sufficient training samples. Furthermore, due to the fact that the collection of sufficient training samples is time-consuming and expensive, a CNN-based siamese network is proposed for radar jamming signal classification to deal with the issue of limited training samples. The experimental results with sufficient and limited training samples show that the CNN-based classification methods obtain good classification performance in terms of classification accuracy and show a huge potential for radar jamming signal classification.

Object detection in remote-sensing images (RSIs) is always a vibrant research topic in the remote-sensing community. Recently, deep-convolutional-neural-network (CNN)-based methods, including region-CNN-based and You-Only-Look-Once-based methods, have become the de-facto standard for RSI object detection. CNNs are good at local feature extraction but they have limitations in capturing global features. However, the attention-based transformer can obtain the relationships of RSI at a long distance. Therefore, the Transformer for Remote-Sensing Object detection (TRD) is investigated in this study. Specifically, the proposed TRD is a combination of a CNN and a multiple-layer Transformer with encoders and decoders. To detect objects from RSIs, a modified Transformer is designed to aggregate features of global spatial positions on multiple scales and model the interactions between pairwise instances. Then, due to the fact that the source data set (e.g., ImageNet) and the target data set (i.e., RSI data set) are quite different, to reduce the difference between the data sets, the TRD with the transferring CNN (T-TRD) based on the attention mechanism is proposed to adjust the pre-trained model for better RSI object detection. Because the training of the Transformer always needs abundant, well-annotated training samples, and the number of training samples for RSI object detection is usually limited, in order to avoid overfitting, data augmentation is combined with a Transformer to improve the detection performance of RSI. The proposed T-TRD with data augmentation (T-TRD-DA) is tested on the two widely-used data sets (i.e., NWPU VHR-10 and DIOR) and the experimental results reveal that the proposed models provide competitive results (i.e., centuple mean average precision of 87.9 and 66.8 with at most 5.9 and 2.4 higher than the comparison methods on the NWPU VHR-10 and the DIOR data sets, respectively) compared to the competitive benchmark methods, which shows that the Transformer-based method opens a new window for RSI object detection.

In recent years, supervised learning-based methods have achieved excellent performance for hyperspectral image (HSI) classification. However, the collection of training samples with labels is not only costly but also time-consuming. This fact usually causes the existence of weak supervision, including incorrect supervision where mislabeled samples exist and incomplete supervision where unlabeled samples exist. Focusing on the inaccurate supervision and incomplete supervision, the weakly supervised classification of HSI is investigated in this paper. For inaccurate supervision, complementary learning (CL) is firstly introduced for HSI classification. Then, a new method, which is based on selective CL and convolutional neural network (SeCL-CNN), is proposed for classification with noisy labels. For incomplete supervision, a data augmentation-based method, which combines mixup and Pseudo-Label (Mix-PL) is proposed. And then, a classification method, which combines Mix-PL and CL (Mix-PL-CL), is designed aiming at better semi-supervised classification capacity of HSI. The proposed weakly supervised methods are evaluated on three widely-used hyperspectral datasets (i.e., Indian Pines, Houston, and Salinas datasets). The obtained results reveal that the proposed methods provide competitive results compared to the state-of-the-art methods. For inaccurate supervision, the proposed SeCL-CNN has outperformed the state-of-the-art method (i.e., SSDP-CNN) by 0.92%, 1.84%, and 1.75% in terms of OA on the three datasets, when the noise ratio is 30%. And for incomplete supervision, the proposed Mix-PL-CL has outperformed the state-of-the-art method (i.e., AROC-DP) by 1.03%, 0.70%, and 0.82% in terms of OA on the three datasets, with 25 training samples per class.

Recently, many convolutional neural network (CNN)-based methods have been proposed to tackle the classification task of hyperspectral images (HSI). In fact, CNN has become the de-facto standard for HSI classification. It seems that the traditional neural networks such as multi-layer perceptron (MLP) are not competitive for HSI classification. However, in this study, we try to prove that the MLP can achieve good classification performance of HSI if it is properly designed and improved. The proposed Modified-MLP for HSI classification contains two special parts: spectral–spatial feature mapping and spectral–spatial information mixing. Specifically, for spectral–spatial feature mapping, each input sample of HSI is divided into a sequence of 3D patches with fixed length and then a linear layer is used to map the 3D patches to spectral–spatial features. For spectral–spatial information mixing, all the spectral–spatial features within a single sample are feed into the solely MLP architecture to model the spectral–spatial information across patches for following HSI classification. Furthermore, to obtain the abundant spectral–spatial information with different scales, Multiscale-MLP is proposed to aggregate neighboring patches with multiscale shapes for acquiring abundant spectral–spatial information. In addition, the Soft-MLP is proposed to further enhance the classification performance by applying soft split operation, which flexibly capture the global relations of patches at different positions in the input HSI sample. Finally, label smoothing is introduced to mitigate the overfitting problem in the Soft-MLP (Soft-MLP-L), which greatly improves the classification performance of MLP-based method. The proposed Modified-MLP, Multiscale-MLP, Soft-MLP, and Soft-MLP-L are tested on the three widely used hyperspectral datasets. The proposed Soft-MLP-L leads to the highest OA, which outperforms CNN by 5.76%, 2.55%, and 2.5% on the Salinas, Pavia, and Indian Pines datasets, respectively. The obtained results reveal that the proposed models provide competitive results compared to the state-of-the-art methods, which shows that the MLP-based methods are still competitive for HSI classification.

Jamming is a big threat to the survival of a radar system. Therefore, the recognition of radar jamming signal type is a part of radar countermeasure. Recently, convolutional neural networks (CNNs) have shown their effectiveness in radar signal processing, including jamming signal recognition. However, most of existing CNN methods do not regard radar jamming as a complex value signal. In this study, a complex-valued CNN (CV-CNN) is investigated to fully explore the inherent characteristics of a radar jamming signal, and we find that we can obtain better recognition accuracy using this method compared with a real-valued CNN (RV-CNN). CV-CNNs contain more parameters, which need more inference time. To reduce the parameter redundancy and speed up the recognition time, a fast CV-CNN (F-CV-CNN), which is based on pruning, is proposed for radar jamming signal fast recognition. The experimental results show that the CV-CNN and F-CV-CNN methods obtain good recognition performance in terms of accuracy and speed. The proposed methods open a new window for future research, which shows a huge potential of CV-CNN-based methods for radar signal processing.

In recent years, many convolutional neural network (CNN)-based methods have been proposed to address the scene classification tasks of remote sensing images. Since the number of training samples in RS datasets is generally small, data augmentation is often used to expand the training set. It is, however, not appropriate when original data augmentation methods keep the label and change the content of the image at the same time. In this study, label augmentation (LA) is presented to fully utilize the training set by assigning a joint label to each generated image, which considers the label and data augmentation at the same time. Moreover, the output of images obtained by different data augmentation is aggregated in the test process. However, the augmented samples increase the intra-class diversity of the training set, which is a challenge to complete the following classification process. To address the above issue and further improve classification accuracy, Kullback–Leibler divergence (KL) is used to constrain the output distribution of two training samples with the same scene category to generate a consistent output distribution. Extensive experiments were conducted on widely-used UCM, AID and NWPU datasets. The proposed method can surpass the other state-of-the-art methods in terms of classification accuracy. For example, on the challenging NWPU dataset, competitive overall accuracy (i.e., 91.05%) is obtained with a 10% training ratio.

A novel processing technology for the fabrication of particle reinforced metal matrix composites, powder thixoforming (PTF), was proposed and 6061 Al-based composites reinforced with 10% volume fractions of SiC particles (SiCp) were fabricated. The effects of processing parameters, such as reheating time, mould temperature and reheating temperature, on its microstructure and mechanical properties were investigated. The results indicated that all the three processing parameters exerted a significant influence on the microstructure and mechanical properties. The behavior of SiCp changes with the processing parameters. The best comprehensive mechanical properties with an ultimate tensile strength (UTS) of 228 MPa, elongation of 5.3% and a Vickers hardness of 66.4 HV are obtained when the composite is thixoforged under the reheating temperature of 660 0C for 90 min and the mould temperature of 250 0C.

Recently, a great many deep convolutional neural network (CNN)-based methods have been proposed for hyperspectral image (HSI) classification. Although the proposed CNN-based methods have the advantages of spatial feature extraction, they are difficult to handle the sequential data with and CNNs are not good at modeling the long-range dependencies. However, the spectra of HSI are a kind of sequential data, and HSI usually contains hundreds of bands. Therefore, it is difficult for CNNs to handle HSI processing well. On the other hand, the Transformer model, which is based on an attention mechanism, has proved its advantages in processing sequential data. To address the issue of capturing relationships of sequential spectra in HSI in a long distance, in this study, Transformer is investigated for HSI classification. Specifically, in this study, a new classification framework titled spatial-spectral Transformer (SST) is proposed for HSI classification. In the proposed SST, a well-designed CNN is used to extract the spatial features, and a modified Transformer (a Transformer with dense connection, i.e., DenseTransformer) is proposed to capture sequential spectra relationships, and multilayer perceptron is used to finish the final classification task. Furthermore, dynamic feature augmentation, which aims to alleviate the overfitting problem and therefore generalize the model well, is proposed and added to the SST (SST-FA). In addition, to address the issue of limited training samples in HSI classification, transfer learning is combined with SST, and another classification framework titled transferring-SST (T-SST) is proposed. At last, to mitigate the overfitting problem and improve the classification accuracy, label smoothing is introduced for the T-SST-based classification framework (T-SST-L). The proposed SST, SST-FA, T-SST, and T-SST-L are tested on three widely used hyperspectral datasets. The obtained results reveal that the proposed models provide competitive results compared to the state-of-the-art methods, which shows that the concept of Transformer opens a new window for HSI classification.

Hyperspectral remote sensing obtains abundant spectral and spatial information of the observed object simultaneously. It is an opportunity to classify hyperspectral imagery (HSI) with a fine-grained manner. In this study, the fine-grained classification of HSI, which contains a large number of classes, is investigated. On one hand, traditional classification methods cannot handle fine-grained classification of HSI well; on the other hand, deep learning methods have shown their powerfulness in fine-grained classification. So, in this paper, deep learning is explored for HSI supervised and semi-supervised fine-grained classification. For supervised HSI fine-grained classification, densely connected convolutional neural network (DenseNet) is explored for accurate classification. Moreover, DenseNet is combined with pre-processing technique (i.e., principal component analysis or auto-encoder) or post-processing technique (i.e., conditional random field) to further improve classification performance. For semi-supervised HSI fine-grained classification, a generative adversarial network (GAN), which includes a discriminative CNN and a generative CNN, is carefully designed. The GAN fully uses the labeled and unlabeled samples to improve classification accuracy. The proposed methods were tested on the Indian Pines data set, which contains 33,3951 samples with 52 classes. The experimental results show that the deep learning-based methods provide great improvements compared with other traditional methods, which demonstrate that deep models have huge potential for HSI fine-grained classification.

Capsule networks can be considered to be the next era of deep learning and have recently shown their advantages in supervised classification. Instead of using scalar values to represent features, the capsule networks use vectors to represent features, which enriches the feature presentation capability. This paper introduces a deep capsule network for hyperspectral image (HSI) classification to improve the performance of the conventional convolutional neural networks (CNNs). Furthermore, a modification of the capsule network named Conv-Capsule is proposed. Instead of using full connections, local connections and shared transform matrices, which are the core ideas of CNNs, are used in the Conv-Capsule network architecture. In Conv-Capsule, the number of trainable parameters is reduced compared to the original capsule, which potentially mitigates the overfitting issue when the number of available training samples is limited. Specifically, we propose two schemes: (1) A 1D deep capsule network is designed for spectral classification, as a combination of principal component analysis, CNN, and the Conv-Capsule network, and (2) a 3D deep capsule network is designed for spectral-spatial classification, as a combination of extended multi-attribute profiles, CNN, and the Conv-Capsule network. The proposed classifiers are tested on three widely-used hyperspectral data sets. The obtained results reveal that the proposed models provide competitive results compared to the state-of-the-art methods, including kernel support vector machines, CNNs, and recurrent neural network.