Search

Abstract To discuss the application value of Case-based Learning (CBL) combined with Bridge-In, Objective, Pre-assessment, Participatory Learning, Post-assessment, and Summary (BOPPPS) model into master students’ program of oral and maxillofacial surgery. 38 master’s students in oral and maxillofacial surgery at Y2 and Y3 from January 2022 to December 2022 are selected as the research objects. They are randomly assigned into two learning groups, namely the traditional LBL (Learn-based Learning) (19 participants) and CBL combined with BOPPPS mode (19 participants). Their theoretical knowledge was assessed after training and the modified Mini-Clinical Evaluation Exercise (Mini-CEX) scale was used to score their clinical thinking. At the same time, the Personal Teaching Efficiency and the Teachers’ Sense of Teaching Efficiency (TSTE) were evaluated, and students’ satisfaction with teaching outcomes was investigated. The basic theoretical knowledge, clinical case analysis and total scores of the experimental group were better than those of the control group, with statistically significant difference (P 0.05), the other four items and total scores in the experimental group were better than those in the control group, with statistically significant difference (P 0.05). CBL combined with BOPPPS teaching method can improve students’ clinical critical thinking ability and help them adapt to the clinical rhythm. It is an effective measure to ensure teaching quality and is worthy of promotion. It is worthwhile to promote the application of CBL combined with BOPPPS mode into master’s course of oral and maxillofacial surgery, which not only improve the basic theoretical knowledge and speculative thinking ability of master’s students, but also improve the teaching efficiency.

Abstract Objective The major challenge in routine endocervical curettage (ECC) among Human Papillomavirus (HPV) 16/18-positive patients is that only a small fraction benefit. Nevertheless, current reported models often overestimate the validity and necessity of ECC, making it difficult to improve benefits for patients. This research hypothesized that assessing paired boxed gene 1 methylation levels (PAX1m) and clinical characteristics could enhance the predictive accuracy of detecting additional high-grade squamous intraepithelial lesions or worse (HSIL +) through ECC that were not identified by colposcopy-directed biopsy (CDB). Methods Data from 134 women with HPV16/18 positivity undergoing CDB and ECC between April 2018 and April 2022 were collected and analyzed. Quantitative methylation-specific polymerase chain reaction (qMSP) was utilized to measure PAX1m, expressed as ΔCp. Univariate and multivariate regression analyses were conducted to screen variables and select predictive factors. A nomogram was constructed using multivariate logistic regression to predict additional HSIL + detected by ECC. The discrimination, calibration, and clinical utility of the nomogram were evaluated using receiver operating characteristic curves (ROC) and the calibration plot. Results Age (odds ratio [OR], 5.654; 95% confidence interval [CI], 1.131–37.700), cytology (OR, 24.978; 95% CI, 3.085–540.236), and PAX1 methylation levels by grade (PAX1m grade) (OR, 7.801; 95% CI, 1.548–44.828) were independent predictive factors for additional detection of HSIL + by ECC. In HPV16/18-positive women, the likelihood of additional detection of HSIL + through ECC increased with the severity of cytological abnormalities, peaking at 43.8% for high-grade cytological lesions. Moreover, when cytological findings indicated low-grade lesions, PAX1 methylation levels were positively correlated with the additional detection of HSIL + by ECC (P value

Background: To explore the role of vaginal microbiota and metabolomics in the progression of cervical dysplasia. Methods: The patient group consists of female patients with low-grade, high-grade cervical dysplasia, and cervical cancer. Normal cervix samples from health volunteers were used as controls. The metabolic fingerprints of cervicovaginal lavage were analyzed using liquid chromatography-mass spectrometry, while the vaginal microbiota was examined through 16S rRNA sequencing. Bioinformatic analysis was adopted to investigate the interplay between hosts and microbes. The vaginal metabolic and microbiota profiles of 90 female patients with cervical dysplasia and 10 controls were analyzed to discover the biological characteristics underlying the progression of cervical cancer. Results: We found that Valyl-Glutamate, N, N′-Diacetylbenzidine, and Oxidized glutathione, which were involved in oxidative stress response, were discriminators to distinguish the normal cervix, invasive cervical carcinomas, and CIN3 from others. Cervical carcinoma was characterized by a large variety of vaginal microbes (dominated by non-Lactobacillus communities) compared to the control. These microbes affected amino acid and nucleotide metabolism, producing metabolites with cervical carcinoma and genital inflammation compared to the control group. Conclusions: This study revealed that cervicovaginal metabolic profiles were determined by cervical cancer, vaginal microbiota, and their interplays. ROS metabolism can be used to discriminate normal cervix, CIN3, and invasive cervical carcinoma.

Simulated body fluid (SBF) is widely utilized in preclinical research for estimating the mineralization efficacy of biomaterials. Therefore, it is of great significance to construct an efficient and stable SBF mineralization system. The conventional SBF solutions cannot maintain a stable pH value and are prone to precipitate homogeneous calcium salts at the early stages of the biomimetic process because of the release of gaseous CO2. In this study, a simple but efficient five times SBF buffered by 5 % CO2 was developed and demonstrated to achieve excellent mineralized microstructure on a type of polymer-aligned nanofibrous scaffolds, which is strikingly similar to the natural human bone tissue. Scanning electron microscopy and energy-dispersive X-ray examinations indicated the growth of heterogeneous apatite with a high-calcium-to-phosphate ratio on the aligned nanofibers under 5 times SBF buffered by 5 % CO2. Moreover, X-ray diffraction spectroscopy and Fourier transform infrared analyses yielded peaks associated with carbonated hydroxyapatite with less prominent crystallization. In addition, the biomineralized aligned polycaprolactone nanofibers demonstrated excellent cell attachment, alignment, and proliferation characteristics in vitro. Overall, the results of this study showed that 5 × SBFs buffered by 5 % CO2 partial pressure are attractive alternatives for the efficient biomineralization of scaffolds in bone tissue engineering, and could be used as a model for the prediction of the bone-bonding bioactivity of biomaterials.

Abstract This study group consists of a total of 61 patients who underwent fibula flap and iliac flap surgeries to repair mandibular defects. Patients’ Quality Of life (QOL) at 6 and 24 months after surgery is investigated and compared by the EORTC-QLQ-H&N and OHIP-14. The base data of the two groups of patients are collected and analysed by the SPSS 20.0 statistical software. Independent sample t test was conducted for EORTC-QLQ-H&N and OHIP-14 scores at two time points in each group. The 61 cases of free flap all survived and the difference in the location of the primary tumor between the two groups is statistically significant. The EORTC-QLQ-H&N showed that the score of speech, diet, social contact, and teeth all went up at 6 months after surgery, but went down dramatically at 24 months after surgery. The OHIP-14 showed that there was significant reduction in functional limitation at 24 months after surgery, with statistical significance (p

Abstract Photothermal materials have gained considerable attention in the field of anti‐/de‐icing due to its environmental friendliness and energy saving. However, it is always significantly challenging to obtain solar thermal materials with hierarchical structure and simultaneously demonstrate both the ultra‐long icing delay ability and the superior photothermal de‐icing ability. Here, a photothermal icephobic MOF‐based micro and nanostructure surface (MOF‐MNS) is presented, which consists of micron groove structure and fluorinated MOF nanowhiskers. The optimal MOF‐M250NS can achieve solar absorption of over 98% and produce a high temperature increment of 65.5 °C under 1‐sun illumination. Such superior photothermal‐conversion mechanism of MOF‐M250NS is elucidated in depth. In addition, the MOF‐M250NS generates an ultra‐long icing delay time of ≈3960 s at −18 °C without solar illumination, achieving the longest delay time, which isn't reported before. Due to its excellent solar‐to‐heat conversation ability, accumulated ice and frost on MOF‐M250NS can be rapidly melted within 720 s under 1‐sun illumination and it also holds a high de‐icing rate of 5.8 kg m−2 h−1. MOF‐M250NS possesses the versatility of mechanical robustness, chemical stability, and low temperature self‐cleaning, which can synergistically reinforce the usage of icephobic surfaces in harsh conditions.

Dumpsites are hard to locate globally. Here the authors apply deep networks to satellite images to provide an effective and low-cost way to detect dumpsites with the new method saving more than 96.8% of the manual time with a strong sensitivity to dumpsites.

High resolution is a key trend in the development of synthetic aperture radar (SAR), which enables the capture of fine details and accurate representation of backscattering properties. However, traditional high-resolution SAR imaging algorithms face several challenges. First, these algorithms tend to focus on local information, neglecting nonlocal information between different pixel patches. Second, speckle is more pronounced and difficult to filter out in high-resolution SAR images. Third, the process of high-resolution SAR imaging generally involves high time and computational complexity, making real-time imaging difficult to achieve. To address these issues, we propose a hyperpixel high-resolution SAR imaging network (HPHR-SAR-Net) for rapid despeckling in high-resolution modes. Based on the concept of hyperpixel techniques, we initially combine nonconvex and nonlocal total variation as compound regularization. This approach more effectively despeckles and manages the relationship between pixels while reducing bias effects caused by convex constraints. Subsequently, we solve the compound regularization model using the alternating direction method of multipliers (ADMM) algorithm and unfold it into a deep unfolding network (DUN). The network's parameters are adaptively learned in a data-driven manner, and the learned network significantly increases imaging speed. Additionally, the proposed HPHR-SAR-Net is compatible with high-resolution imaging modes, such as spotlight, staring spotlight, and sliding spotlight. In this article, we demonstrate the superiority of HPHR-SAR-Net through experiments in both simulated and real SAR scenarios. The results indicate that HPHR-SAR-Net can rapidly perform high-resolution SAR imaging from raw echo data, producing accurate imaging results.

Few-shot learning, which aims to learn the concept of novel category from extremely limited labeled samples, has received intense interests in remote sensing image scene classification. Most of the existing methods inherit the philosophy of prototype learning and tackle classification as the prototype-based metric matching problem. Despite the achievement that has been obtained so far, the problems of interclass metric misalignment and intraclass variations have become two main challenges that obstacle the performance. In this article, a novel transductive learning framework with conditional metric embedding is proposed to remedy these problems. First, a conditional metric embedding mechanism is introduced to perform anisotropic embedding for each pair of the support category and query instance. This design provides the model with flexible scalability to accommodate the metric biases across classes. Second, a transductive prototype learning strategy is presented to enhance the robustness of the prototype against intraclass variations. The unlabeled query instances are transformed into pseudo instances equipped with credibility coefficients and then leveraged to calibrate the prototype estimation bias in low-data regimes. Third, a long-term consistency regularization is designed, which continuously memorizes the historical prototypes to generate additional supervision of interclass separation in the global label space. Benefiting from this design, the discriminability of the prototypes obtains obvious improvement. Finally, extensive experiments are conducted on three public benchmark remote sensing datasets. The experimental results demonstrate the validity and the superiority of the proposed method in low-shot conditions.

In the area of synthetic aperture radar (SAR), the ultrahigh resolution is always a continuous pursuit for researchers. To realize ultrahigh resolution, microwave photonics technology is an excellent solution since it has advantages of low transmission loss, ultrawide bandwidth (UWB), etc. However, with the improvement of resolution, new problems arise as the impact of more systematical errors becomes non-negligible, for example, the synchronization error between the transmit channel and the mixing channel, unknown system delay during signal reception, and the fluctuation of frequency for UWB signals. These factors will bring the degradation of the focusing quality of SAR images together with the motion errors and the trajectory measurement errors, causing not only residual range cell migration and azimuth phase error, but also higher order phase error along the range frequency dimension. In this article, we discuss the adverse influence of the above factors and give a detailed analysis of the 2-D phase error of the coarse focused image processed by range migration algorithm. Then, to compensate for the above unknown systematical errors, a 2-D autofocus method is proposed, and the effectiveness is validated by experiments on both simulated and real data.

Abstract Background 2020 World Health Organization Classification of Female Genital Tumors removed ovarian seromucinous carcinoma as a distinct entity and recategorized it as ovarian endometrioid carcinoma with mucinous differentiation according to its pathological features. The aim of this study was to find whether ovarian seromucinous carcinoma truly represented a distinct category of ovarian tumors or an analogue of ovarian endometrioid carcinoma. Methods Twelve patients diagnosed with ovarian seromucinous carcinoma and received surgery at the Xiangya Hospital from January 2010 to December 2019 were included in this study. Clinicopathological features such as clinical symptoms, serological indicators, surgical information, postoperative findings, chemotherapy sensitivity, follow-up information, HE staining and IHC staining images and other clinicopathologic features were collected. Using t-test and Kaplan Meier to perform statistical analysis. Pathological review was conducted using the 2014 World Health Organization criteria. All pathological diagnoses were reviewed by two experienced pathologists. Results The age of 12 patients diagnosed with ovarian seromucinous carcinoma ranged from 23 to 68 years, with a median age of 46.8 years. Serum level of CA125 was elevated in 10 patients, and CA125/CEA ratio was less than 25 in 6 patients. Eleven patients underwent radical ovarian cancer surgery, and one patient underwent fertility preservation surgery. The progression free survival and overall survival of ovarian seromucinous carcinoma is 46.8 months and 50.2 months. Kaplan-Meier survival curve showed that the prognosis of ovarian seromucinous carcinoma and ovarian endometrioid carcinoma was significantly different (P = 0.03). The prognosis of ovarian seromucinous carcinoma and ovarian mucinous carcinoma was similar. Conclusion Although ovarian seromucinous carcinoma and ovarian endometrioid carcinoma are similar in pathologic morphology, their clinical features and prognosis are significantly different. The signs, serum biomarker and prognosis of the ovarian seromucinous carcinoma are similar with ovarian mucinous carcinoma. Therefore, ovarian seromucinous carcinoma is not suitable to be directly classified as ovarian endometrioid carcinoma.

With the rapid development of China’s aerospace information acquisition technology, aerospace data presents the characteristics of large data volume, large number of types, rapid growth and relatively low value density.Remote sensing satellite data is an important part of aerospace big data.How to make use of the scale effect and the complementary advantages of the data of different satellites, so as to improve the processing accuracy and efficiency, is the key problem to be solved in the remote sensing satellite big data processing system.The development history of our country’s remote sensing satellite ground data processing system was reviewed briefly.The core difficulties faced by the ground processing system were pointed out.A high-precision processing technology for remote sensing satellite big data based on stability feature mining was proposed.And a preliminary implementation was given.The method provides a useful reference for the development of our country’s aerospace big data processing system.

With the development of deep learning, great progress has been made in object detection of remote sensing (RS) imagery. However, the object detector is hard to generalize well from one labeled dataset (source domain) to another unlabeled dataset (target domain) due to the discrepancy of data distribution (domain shift). Currently, adversarial-based domain adaptation methods align the semantic features of source and target domain features to alleviate the domain shift. But they fail to avoid the alignment of noisy background features and neglect the instance-level features, which are inappropriate for detection models that focus on instance location and classification. To mitigate domain shift existing in object detection, we propose a reconstructed feature alignment network (RFA-Net) for unsupervised cross-domain object detection in RS imagery. The RFA-Net includes one sequential data augmentation module deployed on data level for providing solid gains on unlabeled data, one sparse feature reconstruction module deployed on feature level to intensify instance feature for feature alignment, and one pseudo-label generation module deployed on label level for the supervision of the unlabeled target domain. Extensive experiments illustrate that our proposed RFA-Net is effective to alleviate the domain shift problem in domain adaptation object detection of RS imagery.

Airborne laser scanning point cloud semantic labeling, which aims to identify the category of each point, plays a significant role in many applications, such as forest observing, powerline extraction, etc. Under the guidance of deep learning technology, the interpretation thought of point clouds has also greatly changed. However, owing to the irregular and unordered natures of point clouds, it is relatively difficult for classification model to distinguish some objects with similar geometry by single-modal data only. Fortunately, additional gain information, e.g., color spectrum which can be complementary to geometric information, is able to effectively promote the classification effect. Therefore, the design of fusion strategy is a critical part in model construction. In this article, aiming to capture more abstract semantic information for color spectrum data, we elaborate a color spectrum fusion (CSF) module. It can be flexibly integrated into a classification pipeline with just negligible parameters. Then, we expand data fusion thoughts for point clouds and color spectrum and investigate three possible fusion strategies. Accordingly, we develop three architectures to construct CSF-Nets. Ultimately, by taking a weighted cross entropy loss, we can train our CSF-Nets in an end-to-end manner. Experiments on two extensively used datasets: Vaihingen 3D and LASDU show that the presented three fusion approaches all can improve the performance, while the earlier fusion strategy performs the best. Besides, compared with other well-performed methods, CSF-Net is still able to achieve satisfactory performance on overall accuracy and m$F_{1}$-score indicator. This also validates the effectiveness of our multimodal fusion network.

Ship detection and classification in synthetic aperture radar (SAR) images play a vital role for wide applications. Due to the unique SAR imaging mechanism, ship detection and classification tasks have faced numerous challenges, such as land interference, image defocus, and noise. Many detectors and classifiers have been presented to handle these problems. However, the general deep learning-based detectors and classifiers lack the combination of SAR characteristics, which leads to poor performance. Compared with optical images, SAR images lack the texture information of ships, which brings great difficulties to the recognition task. To address the above issues, a novel deep learning-based ship detection and classification network combined with scattering characteristics is proposed in this article. First, to accurately locate ships in large-scale SAR images, this article designs a strong scattering point aware network (SPAN) by capturing the strong scattering points that existed in the ship area. SPAN recognizes the ship category according to their distribution characteristics. Second, to compensate for the feature loss caused by the down-sampling operation, this article designs a more suitable resolution recovery module to replace the bilinear interpolation method. Third, a region of interest automatic generation module is proposed to fully utilize the axis-align feature of oriented proposal boxes and the sufficient information of horizontal proposal boxes. Furthermore, the classification encoder module extracts the distribution feature of scattering points to classify SAR ships. Finally, the comprehensive experiments in the large-scale dataset for ship detection and classification in SAR images (LDSD) demonstrate the superior performance of the proposed method.

Corona Virus Disease 2019 (COVID-19) is presently the largest international public health event, individuals infected by the virus not only have symptoms such as fever, dry cough, and lung infection at the time of onset, but also possibly have sequelae in the cardiovascular system, respiratory system, nervous system, mental health and other aspects. However, numerous studies have depicted that the active ingredients in tea show good antiviral effects and can treat various diseases by regulating multiple pathways, and the therapeutic effects are associated with the categories of chemical components in tea. In this review, the differences in the content of key active ingredients in different types of tea are summarized. In addition, we also highlighted their effects on COVID-19 and connected sequelae, further demonstrating the possibility of developing a formulation for the prevention and treatment of COVID-19 and its sequelae through tea extracts. We have a tendency to suggest forestalling and treating COVID-19 and its sequelae through scientific tea drinking.

Abstract This study has analyzed 41 patients with mandibular ameloblastoma who underwent a partial mandibulectomy and reconstruction by folding the free fibular flap. In the preoperative and postoperative (6 months and 24 months after surgery), the Quality of Life (QOL) of these patients was assessed by using the University of Washington Quality of Life Questionnaire (UW-QOL) and the medical outcome study short form-36 (SF-36) questionnaires. SPSS 20.0 statistical software was used to conduct statistical analysis on the base data of the two groups of patients. Independent sample t test was conducted for sf-36 and UW-QOL scores at two time points in each group. The SF-36 survey showed that body pain (54.54 ± 8.10), general health (55.27 ± 7.54), and health changes (58.29 ± 9.60) decreased significantly at 6 months after surgery, but the mean score at 24 months after surgery all exceeded the preoperational level. At 24 months after the surgery, the vitality (80.41 ± 3.74), social function (81.61 ± 4.07), emotional role (82.39 ± 4.07), psychological health (81.66 ± 4.37) and total score (704.00 ± 31.53) all returned to the preoperative level, which was statistically significant compared with 6 months after surgery. However, there was no significant difference compared with the preoperative level. The UW-QOL survey showed that chewing (56.68 ± 7.23), speech (54.54 ± 7.7) and taste (62.29 ± 10.15) have significantly changed at 6 months after the surgery, and the difference was statistically significant at 24 months after surgery. Saliva generation decreased slightly (80.76 ± 3.35) at 6 months after surgery, but quickly returned to the preoperative level (81.59 ± 4.06). The total score of the patients almost recovered to the preoperative level at 24 months after surgery. The folded the fibular flap can not only repair the defects of soft tissue and bone tissue, but also restore the height of the alveolar ridge to, avoid the imbalance of crown and root ratio after implantation and reduce the occurrence of peri-implant inflammation, so that a true functional reconstruction can be realized.

Abstract Background Numerous studies on discovering the roles of long non-coding RNAs (lncRNAs) in the occurrence, development and prognosis progresses of various human diseases have drawn substantial attentions. Since only a tiny portion of lncRNA-disease associations have been properly annotated, an increasing number of computational methods have been proposed for predicting potential lncRNA-disease associations. However, traditional predicting models lack the ability to precisely extract features of biomolecules, it is urgent to find a model which can identify potential lncRNA-disease associations with both efficiency and accuracy. Results In this study, we proposed a novel model, SVDNVLDA, which gained the linear and non-linear features of lncRNAs and diseases with Singular Value Decomposition (SVD) and node2vec methods respectively. The integrated features were constructed from connecting the linear and non-linear features of each entity, which could effectively enhance the semantics contained in ultimate representations. And an XGBoost classifier was employed for identifying potential lncRNA-disease associations eventually. Conclusions We propose a novel model to predict lncRNA-disease associations. This model is expected to identify potential relationships between lncRNAs and diseases and further explore the disease mechanisms at the lncRNA molecular level.

Abstract This retrospective study investigated the clinicopathological characteristics of secretory carcinoma of salivary glands (SCSG) in 23 patients with histopathologically confirmed SCSG between January 2010 and December 2020. In total, 13 males and 10 females (ratio, 1.3:1) aged 10 − 69 years (median, 45 years) were enrolled in this study; the average disease duration was 2.44 years (0.25–20 years). Twenty-one patients (91.3%) had SCSG in the parotid gland, and two (8.7%) in the submandibular gland. All patients had single nodules of diameters 0.8–4.8 cm (average 2.6 cm); five with lymph node metastases, and two with distant metastases. Immunohistochemically, tumors stained positive for S-100, mammaglobin, CK7, GATA3 and pan-Trk, and negative for DOG1, P63, and calponin, with Ki-67 positivity from 1 to 50%. ETV6 gene rearrangement was confirmed in 15 patients. All patients underwent oncological resection, four had radioactive particles implanted postoperatively, one received chemotherapy, and seven underwent chemoradiotherapy. Six patients had regional recurrences, two distant metastases, and one died before the last follow-up. SCSGs are typically indolent, with a low locoregional recurrence rate and excellent survival. Prognosis is correlated to clinical stage, pathological grade, and surgical procedures.

Cross-modal remote sensing retrieval (RSCR) has an increasing importance due to the ability to quickly and flexibly retrieve valuable data from enormous remote sensing (RS) images. However, traditional RSCR methods tend to focus on the retrieval between two modalities, when the number of modalities increases, the contradiction between the increasing semantic gap and the small amount of paired data causes the model fail to learn a superior modal representation. In this paper, inspired by the visual-based modal center in RS, we construct a multi-source cross-modal retrieval network (MCRN) that manages to unify RS retrieval tasks under multiple retrieval sources. To solve the data heterogeneity caused by multiple data sources, we propose a shared pattern transfer module (SPTM) based on pattern memory and combine the theory of generative adversarial to achieve the semantic representation unbound from modality. Simultaneously, to cope with the lack of annotation data in the RS scenario, multiple unimodal self-supervised frameworks are unified to obtain robust pre-training parameters for the designed MCRN by combining domain alignment and contrastive learning. Finally, we come up with the multi-source triplet loss, the unimodal contrast loss, and the semantic consistency loss, which efficaciously make MCRN achieve competitive results through multitask learning for semantic alignment. We construct multimodal datasets M-RSICD and M-RSITMD, conduct extensive experiments and provide a complete benchmark to facilitate the development of RS multi-source cross-modal retrieval. The code of the MCRN method and the proposed dataset have been open to access at [Link].

With the development and popularization of remote sensing earth observation technology and the remote sensing satellite system, the problems of insufficient proactiveness, relevance and timeliness of large-scale remote sensing supporting services are increasingly prominent, which seriously restricts the application of remote sensing resources in multi-domain and cross-disciplinary. It is urgent to help terminal users make appropriate decisions according to real-time network environment and domain requirements, and obtain the optimal resources efficiently from the massive remote sensing resources. In this paper, we propose a recommendation algorithm using fusion of attention and multi-perspective (MRS_AMRA). Based on MRS_AMRA, we further implement an active service recommendation model (MRS_ASRM) for massive multi-source remote sensing resources by combining streaming pushing technology. Firstly, we construct value evaluation functions from multi-perspective in terms of remote sensing users, data and services to enable the adaptive provision of remote sensing resources. Then, we define multi-perspective heuristic policies to support resource discovery, and fusion these policies through the attention network, to achieve the accurate pushing of remote sensing resources. Finally, we implement comparative experiments to simulate accurate recommendation scenarios, compared with state-of-the-art algorithms, such as DIN and Geoportal. Furthermore, MRS_AMRA achieves an average improvement of 10.5% in the recommendation accuracy NDCG@K, and in addition, we developed a prototype system to verify the effectiveness and timeliness of MRS_ASRM.

The objects presented in synthetic-aperture radar (SAR) images are the products of the joint actions of ground objects and SAR sensors in specific geospatial contexts. With the accumulation of massive time-domain SAR data, scholars have the opportunity to better understand ground-object targets and sensor systems, providing some useful feedback for SAR-data processing. Aiming at normalized and low-cost SAR radiometric monitoring, this paper proposes a new hyper-pixel concept for handling multi-pixel ensembles of semantic ground targets. The special hyper-pixel in this study refers to low-rise single-family residential areas, and its radiation reference is highly stable in the time domain when the other dimensions are fixed. The stability of its radiometric data can reach the level of 0.3 dB (1σ), as verified by the multi-temporal data from Sentinel-1. A comparison with tropical-rainforest data verified its availability for SAR radiometric monitoring, and possible radiation variations and radiation-intensity shifts in the Sentinel-1B SAR products ere experimentally monitored. In this paper, the effects of seasonal climate and of the relative geometrical states observed on the intensity of the hyper-pixel’s radiation are investigated. This paper proposes a novel hyper-pixel concept for processing and interpreting SAR-image data. The proposed residential hyper-pixel is shown to be useful in multi-temporal-data observations for normalized radiometric monitoring and has the potential to be used for cross-calibration, in addition to other applications.

The rapid development of deep learning brings effective solutions for remote sensing image interpretation. Training deep neural network models usually require a large number of manually labeled samples. However, there is a limitation to obtain sufficient labeled samples in remote sensing field to satisfy the data requirement. Therefore, it is of great significance to conduct the research on few-shot learning for remote sensing image interpretation. First, this article provides a bibliometric analysis of the existing works for remote sensing interpretation related to few-shot learning. Second, two categories of few-shot learning methods, i.e., the data-augmentation-based and the prior-knowledge-based, are introduced for the interpretation of remote sensing images. Then, three typical remote sensing interpretation applications are listed, including scene classification, semantic segmentation, and object detection, together with the corresponding public datasets and the evaluation criteria. Finally, the research status is summarized, and some possible research directions are provided. This article gives a reference for scholars working on few-shot learning research in the remote sensing field.

Electromagnetic (EM) scattering calculation is a very important part of most synthetic aperture radar (SAR) target image simulation methods. It affects the intensity of the radar echo signal to a great extent, thus affecting the quality of the final simulation image. EM reflection models are usually approximate formulas derived under certain assumptions. The errors between these models and the actual situation can cause significant differences between simulated images and real images. To solve this problem, we propose a novel modified SAR target image simulation framework, in which the deep neural network (DNN) is embedded to calculate the EM reflection, so that the DNN can directly learn and fit the EM reflection models from real SAR images. First, the intensity calculation of radar signal in a single reflection is separated from the cumulative calculation of multiple radar reflection signals intensity in each pixel. Thus, the approximate calculation formulas of EM reflection can be replaced with the DNN models. Next, the DNN model is trained with the backpropagation algorithm to learn the actual EM reflection model from real SAR images. Finally, the fitted EM reflection models and an image post-processing model are applied to simulate images of the target under different imaging angles. In the simulation framework, the functions of the neural network models are limited to calculating the reflection coefficient and adding sidelobe and speckle noise. The imaging model is still the original simulation method based on ray tracing, which ensures the correctness and generalization of the simulation method. Experiments show that the proposed simulation method can significantly improve the quality of the simulation image. When the image is normalized to [0, 1], the minimum mean square error between the simulated SAR images and the real images of the Sandia laboratory implementation of cylinders target can reach 0.003. The visualization results of the DNN models show that the fitted reflection coefficient calculation curve and the convolution kernel used for image post-processing are consistent with the laws in the theoretical model. In addition, when the proposed method is used to simulate complex targets, the similarity of simulation images can also be significantly improved.

The building extraction from synthetic aperture radar (SAR) images has always been a challenging research topic. Recently, the deep convolution neural network brings excellent improvements in SAR segmentation. The fully convolutional network and other variants are widely transferred to the SAR studies because of their high precision in optical images. They are still limited by their processing in terms of the geometric distortion of buildings, the variability of building structures, and scattering interference between adjacent targets in the SAR images. In this article, a unified framework called selective spatial pyramid dilated (SSPD) network is proposed for the fine building segmentation in SAR images. First, we propose a novel encoder–decoder structure for the fine building feature reconstruction. The enhanced encoder and the dual-stage decoder, composed of the CBM and the SSPD module, extract and recover the crucial multiscale information better. Second, we design the multilayer SSPD module based on the selective spatial attention. The multiscale building information with different attention on multiple branches is combined, optimized, and adaptively selected for adaptive filtering and extracting features of complex multiscale building targets in SAR images. Third, according to the building features and SAR imaging mechanism, a new loss function called L-shape weighting loss (LWloss) is proposed to heighten the attention on the L-shape footprint characteristics of the buildings and reduce the missing detection of line buildings. Besides, LWloss can also alleviate the class imbalance problem in the optimization stage. Finally, the experiments on a large-scene SAR image dataset demonstrate the effectiveness of the proposed method and verify its superiority over other approaches, such as the region-based Markov random field, U-net, and DeepLabv3+.

In this article, we introduce the 2020 Gaofen Challenge and relevant scientific outcomes. The 2020 Gaofen Challenge is an international competition, which is organized by the China High-Resolution Earth Observation Conference Committee and the Aerospace Information Research Institute, Chinese Academy of Sciences and technically cosponsored by the IEEE Geoscience and Remote Sensing Society and the International Society for Photogrammetry and Remote Sensing. It aims at promoting the academic development of automated high-resolution earth observation image interpretation. Six independent tracks have been organized in this challenge, which cover the challenging problems in the field of object detection and semantic segmentation. With the development of convolutional neural networks, deep-learning-based methods have achieved good performance on image interpretation. In this article, we report the details and the best-performing methods presented so far in the scope of this challenge.

Semantic segmentation in aerial images has become an indispensable part in remote sensing image understanding for its extensive application prospects. It is crucial to jointly reason the 2-D appearance along with 3-D information and acquire discriminative global context to achieve better segmentation. However, previous approaches require accurate elevation data (e.g., nDSM and Digital Surface Model (DSM)) as additional inputs to segment semantics, which sorely limits their applications. On the other hand, due to the various forms of objects in complex scenes, the global context is generally dominated by features of salient patterns (e.g., large objects) and tends to smooth inconspicuous patterns (e.g., small stuff and boundaries). In this article, a novel joint framework named height-embedding context reassembly network (HECR-Net) is proposed. First, considering the fact that the corresponding elevation data is insufficient while we still want to exploit the serviceable height information, to alleviate the above data constraint, our method simultaneously predicts semantic labels and height maps from single aerial images by distilling height-aware embeddings implicitly. Second, we introduce a novel context-aware reorganization module to generate a discriminative feature with global context appropriately assigned to each local position. It benefits from both the global context aggregation module for ambiguity eliminating and local feature redistribution module for detailed refinement. Third, we make full use of the learning height-aware embeddings to promote the performance of semantic segmentation via introducing a modality-affinitive propagation block. Finally, without bells and whistles, the segmentation results on ISPRS Vaihingen and Potsdam data set illustrate that the proposed HECR-Net achieves state-of-the-art performance.

To accurately extract various ground objects from polarimetric synthetic aperture radar (PolSAR) images is a challenging research topic. The deep convolutional neural networks are widely used in SAR segmentation due to their remarkable performance in optical remote sensing images. However, they are still limited by the geometric deformation of the objects, the strong scattering interference among adjacent objects, and the difficulty in distinguishing similar things. A large part of the reason lies in the insufficient utilization and the damage of feature mining for PolSAR data. In this article, focusing on the scattering matrix and the polarimetric coherency matrix, a polarimetric space reconstruction network is proposed. First, to maintain the relatively initial spatial constraints and the complete polarimetric information, the inputs are arranged by a spatial amplification coding method for the polarimetric coherency and scattering matrices. Second, a statistics enhancement module based on scattering characteristics is proposed to mine the differential expression among multiple scattering and polarimetric components, which supplements the local feature representation of convolutional operators. Third, the designed dual self-attention mechanism can capture the amplitude and phase relations of matrix element context adaptively. The proposed method keeps the spatiality of each scattering vector and fully explores the complementary information involved in the fully polarimetric data. Moreover, it accomplishes the accurate land cover classification for PolSAR images, especially the traditional confusing categories, such as water and roads. The experimental results on the E-SAR, AIRSAR, Gaofen-3, and RADARSAT-2 datasets show that the proposed method is effective and promising for PolSAR image segmentation.

Ship detection in synthetic aperture radar (SAR) images is a significant and challenging task. Recently, deep convolutional neural networks have been applied to solve the detection problem and made a great breakthrough. Previous works mostly rely on the manually designed anchor boxes to search for the region of interests, which is less flexible and suffers from a heavy computational load. Moreover, these detectors have limited performance in large-scale and complex scenes due to the strong interference of inshore background and the variability of object imaging characteristics. In this article, a novel ship detection method based on the scattering-keypoint-guided network is proposed to remedy these problems. First, an anchor-free network is built to eliminate the effect of anchor boxes, in which a more robust representation scheme is designed for the arbitrary oriented objects. Second, a context-aware feature selection module is introduced to dynamically learn both local and context features. In this process, the semantic information of objects can be enhanced while suppressing the background interference. Third, according to the SAR imaging mechanism, a set of scattering keypoints is defined to describe the local scattering regions and reflect the discriminative structural characteristics of ships. Based on this conception, a novel feature adaption method is proposed with the purpose of dealing with the imaging variability issue. Furthermore, to demonstrate the effectiveness of the proposed improvements, we build the Gaofen-3 ship detection dataset. Meanwhile, the public SAR ship detection dataset is introduced to verify the robustness and generalization ability of the detector. Experimental results on these two datasets show that the proposed method achieves the state-of-the-art performance.

Open Set Fine-Grained Recognition (OSFGR) aims at distinguishing known fine-grained categories from the data (contain known and unknown categories). The feature distribution of the known fine-grained category usually has the characteristics of small inter-class variance and large intra-class variance. Directly using the traditional Open Set Recognition (OSR) method on OSFGR does not achieve competitive performance. This is mainly due to the fact that the traditional OSR method is designed based on SoftMax function, whose translation invariance for input weakens the representation ability for the known fine-grained category in OSFGR. To settle this problem, we present a unified method based on class activation mapping value (CAMV) for OSFGR, which preserves the original discriminate feature. Besides, most OSR methods are based on the discrimination model with multi-class thresholds. When most known categories need to recognize, it will face the high computational cost and low efficiency. To overcome this problem, we propose the discrimination model with fusion one-class thresholds, which can greatly improve the inference speed without losing the recognition accuracy. Meanwhile, our idea can settle the extreme situation of OSR (only one known category). Our method achieves the state-of-art performance on the fine-grained open set datasets consisting of 4 public fine-grained datasets.

An azimuth multi-channel Synthetic Aperture Radar (SAR) can be used to obtain high-resolution wide-swath SAR images. Accurate estimation of the phase error between channels is the key to ensuring image quality. In this study, we present a channel phase error estimation method based on the error backpropagation algorithm. During the physical process of a multi-channel SAR echo generation, this method constructs an observation matrix with the parameters to be estimated including the phase error between channels. The initial SAR echo is generated using the initial channel error matrix and initial target scattering coefficient matrix, and the error between the echo and measured multi-channel SAR echo is calculated. Using the backpropagation algorithm commonly used in deep learning, the abovementioned parameters are continuously trained and optimized. Finally, the estimation of the phase error between channels is obtained along with the target scattering coefficient. This method combines the error backpropagation method with the principle of multi-channel SAR channel error. Phase estimation and imaging are realized based on the sparsity assumption, which provides a new approach for estimating an error in a multi-channel SAR. The effectiveness of the presented method is validated using multi-channel SAR simulation data.

Automatic modulation classification (AMC) plays a key role in cognitive radio. For AMC, convolutional neural networks (CNNs) have been explored in previous works extensively and deliver the best performance. However, temporal dependencies of signals modeled by CNNs are inherently implicit and insufficient. As a result, models need more data to learn discriminative features automatically. In this work, we propose a hybrid model named HybridNet, where a bidirectional gated recurrent unit (Bi-GRU) is placed after CNN to capture temporal dependencies explicitly. In addition, we investigate why varying Signal-to-Noise Ratio (SNR) dataset makes performance deteriorate. By visualization, we discover that the increase of the intra-class divergence under sharply varying SNR is the central cause. To this end, channel-wise attention is adopted in HybridNet to learn different patterns existing in SNR, which does not require SNR labels in the training process or inference values of SNR. On RadioML2016.10b, our HybridNet obtains the best accuracy among all scales of training data. Especially, in small datasets, our model obtains 87.4% accuracy that is 9.7% higher than the baseline method.

With the needs of continuous data quality assessment for massive Gaofen-3 (GF-3) polarimetric data, an automatic and efficient quality evaluation method is urgently needed. In this article, an automated polarimetric SAR data quality assessment method is conducted using a classic convolution neural network (VGG-16). The method is first pretrained, performance-tested, and robustness-tested on Radarsat-2 fully polarimetric data, then trained by selected SAR scenes of GF-3 for being applied on GF-3 data. The network is supposed to fulfill the work of automatically and accurately selecting those distributed targets satisfying quality evaluation under various scenes. A PolSAR data assessment method based on these distributed targets proposed by the authors in previous work is then applied to give the evaluation results. Experiments on GF-3 data and the comparison to prior works and corner reflectors on polarimetric distortion assessment results verify the effectiveness and advantages of the proposed method. The polarization data quality of GF-3 at different beams is also obtained. The technique and strategy in this article are practical and contributing to the long-term quality assessment of PolSAR data.

Weakly Supervised Semantic Segmentation (WSSS) with only image-level labels reduces the annotation burden and has been rapidly developed in recent years. However, current mainstream methods only employ a single image’s information to localize the target and do not account for the relationships across images. When faced with Remote Sensing (RS) images, limited to complex backgrounds and multiple categories, it is challenging to locate and differentiate between the categories of targets. As opposed to previous methods that mostly focused on single-image information, we propose CISM, a novel cross-image semantic mining WSSS framework. CISM explores cross-image semantics in multi-category RS scenes for the first time with two novel loss functions: the Common Semantic Mining (CSM) loss and the Non-common Semantic Contrastive (NSC) loss. In particular, prototype vectors and the Prototype Interactive Enhancement (PIE) module were employed to capture semantic similarity and differences across images. To overcome category confusions and closely related background interferences, we integrated the Single-Label Secondary Classification (SLSC) task and the corresponding single-label loss into our framework. Furthermore, a Multi-Category Sample Generation (MCSG) strategy was devised to balance the distribution of samples among various categories and drastically increase the diversity of images. The above designs facilitated the generation of more accurate and higher-granularity Class Activation Maps (CAMs) for each category of targets. Our approach is superior to the RS dataset based on extensive experiments and is the first WSSS framework to explore cross-image semantics in multi-category RS scenes and obtain cutting-edge state-of-the-art results on the iSAID dataset by only using image-level labels. Experiments on the PASCAL VOC2012 dataset also demonstrated the effectiveness and competitiveness of the algorithm, which pushes the mean Intersection-Over-Union (mIoU) to 67.3% and 68.5% on the validation and test sets of PASCAL VOC2012, respectively.

Ship detection from synthetic aperture radar (SAR) images has become a major research field in recent years. It plays a major role in monitoring the ocean, marine rescue activities, and marine safety warnings. However, there are still some factors that restrict further improvements in detecting performance, e.g., multi-scale ship transformation and unfocused images caused by motion. In order to resolve these issues, in this paper, a doppler feature matrix fused with a multi-layer feature pyramid network (D-MFPN) is proposed for SAR ship detection. The D-MFPN takes single-look complex image data as input and consists of two branches: the image branch designs a multi-layer feature pyramid network to enhance the positioning capacity for large ships combined with an attention module to refine the feature map’s expressiveness, and the doppler branch aims to build a feature matrix that characterizes the ship’s motion state by estimating the doppler center frequency and frequency modulation rate offset. To confirm the validity of each branch, individual ablation experiments are conducted. The experimental results on the Gaofen-3 satellite ship dataset illustrate the D-MFPN’s optimal performance in defocused ship detection tasks compared with six other competitive convolutional neural network (CNN)-based SAR ship detectors. Its satisfactory results demonstrate the application value of the deep-learning model fused with doppler features in the field of SAR ship detection.

The nonradical process in the peroxydisulfate (PDS) oxidation system is a promising method for antibiotic removal in water. In this study, CuO@CNT was successfully synthesized by a facile approach to catalyze PDS. The removal efficiency of the antibiotic sulfamethoxazole (SMX) was 90.6% in 50 min, and the stoichiometric efficiency (ΔSMX/ΔPDS) was 0.402. The very different degradation efficiency of common organic contaminants revealed the selective oxidation of the surveyed system. The process of 1O2 oxidation and the electron-transfer regime was exhibited by chemical quenching tests, electron paramagnetic resonance (EPR) determination, a UV–vis spectrophotometer, X-ray photoelectron spectroscopy (XPS) detection, and cyclic voltammetry (CV) measurements. Sustainable catalysis was promoted by the circulation between the surface electron-rich centers of Cu(II) and Cu(III). Dissolved oxygen (DO) and a metastable Cu(III) intermediate contributed to the generation of 1O2. Still, a portion of SMX was removed by the mildly activated PDS. Moreover, the influence factors (pH, dosage, water matrix) were examined, and suppressions were acceptable by common anions and real water. Distinguished from the radical process, unique intermediate products were ascertained via the theoretical calculation and liquid chromatography–mass spectrometry (LC-MS) detection. Furthermore, CuO@CNT showed a satisfactory activation ability in the cycling experiments. Overall, this study developed CNT to be a supporter of CuO, unveiled the mechanism of catalysis, and evaluated the application potential of the nonradical process.

Image collection summarisation aims to represent a large‐scale multi‐modal collection with a small subset of images and tags, helping navigate a large image dataset. Most extant methods leverage the contributions of text‐to‐visual summaries, ignoring the visual contribution to the textual topic. When the tags are weakly labelled, the textual topic cannot accurately reflect the visual summary. To solve this, the authors propose a novel model, joint optimisation of convex non‐negative matrix factorisation, which incorporates images and tags in a beneficial way. The objective function contains visual and textual error functions, sharing the same indicator matrix, connecting different modal relations. Then, they propose an iterative algorithm to optimise the proposed model. Finally, they explore the effects of different visual feature representations (e.g. bag‐of‐words and deep learning) on multi‐modal collection summary. Our proposed method is then compared with state‐of‐the‐art algorithms using two multi‐modal datasets (i.e. MIRFlickr and NUS‐WIDE‐SCENE). Experimental results demonstrate the effectiveness of their proposed approach.

The state-of-the-art object detection frameworks require the training on large-scale datasets, which is the crux of the present dilemma: overfitting or degrading performance with insufficient samples and time-consuming training process. On the basis of meta-learning, this paper proposes a generalized Few-Shot Detection (FSD) framework to overcome the above drawbacks of the current advances in object detection. The proposed framework consists of a meta-learner and an object detector. It can learn the general knowledge and proper fast adaptation strategies across many tasks. The meta-learner can teach the detector how to learn from few examples in just one updating step. Here, the object detector can be any supervised learning detection models in theory. Specifically, the proposed FSD framework employs Single-Shot MultiBox Detector (SSD) as the object detector in this paper, thus called Meta-SSD. Besides, a novel benchmark is constructed from Pascal VOC dataset for training and evaluation of meta-learning FSD. Experiments show that the Meta-SSD yields a promising result for FSD. Furthermore, the properties of Meta-SSD is analyzed. This paper can serve as a strong baseline and provide some inspiration for meta-learning FSD.

Semantic segmentation performs pixel-wise classification for given images, which can be widely used in autonomous driving, robotics, medical diagnostics and etc. The recent advanced approaches have witnessed rapid progress in semantic segmentation. However, these supervised learning based methods rely heavily on large-scale datasets to acquire strong generalizing ability, such that they are coupled with some constraints. Firstly, human annotation of pixel-level segmentation masks is laborious and time-consuming, which causes relatively expensive training data and make it hard to deal with urgent tasks in dynamic environment. Secondly, the outstanding performance of the above data-hungry methods will decrease with few available training examples. In order to overcome the limitations of the supervised learning semantic segmentation methods, this paper proposes a generalized meta-learning framework, named Meta-Seg. It consists of a meta-learner and a base-learner. Specifically, the meta-learner learns a good initialization and a parameter update strategy from a distribution of few-shot semantic segmentation tasks. The base-learner can be any semantic segmentation models theoretically and can implement fast adaptation (that is updating parameters with few iterations) under the guidance of the meta-learner. In this work, the successful semantic segmentation model FCN8s is integrated into Meta-Seg. Experiments on the famous few-shot semantic segmentation dataset PASCAL $5^{i}$ prove Meta-Seg is a promising framework for few-shot semantic segmentation. Besides, this method can provide with reference for the relevant researches of meta-learning semantic segmentation.

Polarization calibration without artificial calibrators has been one of the focuses of research and discussion for PolSAR communities. However, there is limited research on the treatment of dual-polarization systems and the calibration methods for getting rid of distributed targets. In this paper, we contribute to proposing a new and convenient method for estimating the polarimetric channel imbalance phase at the transmitter and receiver, which can be used for both quad-pol and dual-pol SAR systems. We found a brand-new reference object in the urban area scene, namely the effective dihedrals. A statistical calculation method was proposed correspondingly, which obtained an effective estimation of the channel imbalance phases. The theoretical explanation of the proposed method was consistent with the statistical phenomena presented in the experiments. The technique was illustrated and verified through C-band SAR images, including GaoFen-3 (GF-3) data and Sentinel-1 data. The technique was also validated and successfully applied in airborne SAR data of P, L, S, C, and X bands. The estimation error could be within 7° when crosstalk items were less than −30 dB. The method realizes a fast and low-cost dual-polarization phase imbalance estimation and provides a new technical approach to supplement the traditional tropical-rainforest-based quad-pol system calibration. The method can be conveniently applied to the monitoring of polarization distortion parameters, ensuring good polarization SAR data quality.

The accumulation of heavy metals (HMs) in the water-level fluctuation zone (WLFZ) of the Three Gorges Reservoir (TGR) area is potentially harmful to the water environment. In order to reveal whether nitrogen (N) deposition is a potential driving factor for the migration and transformation of HMs (Cd, Cr, Cu, Ni, and Pb), a simulated N deposition experiment was performed on the soil in the WFLZ of the TGR. The results showed that the accumulative release amounts of HMs increased with the increase of N deposition. It was found that the Elovich equation, double-constant equation, and parabolic diffusion equation could well describe the release process of Cu, Cd, Cr, and Ni, while the double-constant equation, parabolic diffusion equation, and first-order equation could be applicable for Pb. The exchangeable fractions of HMs increased to varying degrees after the N deposition treatment, wherein Ni was most significant, indicating that N deposition could increase the ecological risk of HM pollution in the TGR area. The results provide insight into the major factors affecting the release of different HMs under N deposition in this vulnerable region ecologically.

The goal of treating articular cartilage (AC) injury is to regenerate cartilage tissue and to integrate the neo-cartilage with surrounding host cartilage. However, most current studies tend to focus on engineering cartilage; interface integration has been somewhat neglected. An endogenous regenerative strategy that simultaneously increases the recruitment of bone marrow mesenchymal stem cells (BMSCs) and chondrocytes may improve interface integration and cartilage regeneration. In this study, a novel functionalized self-assembling peptide hydrogel (KLD-12/KLD-12-LPP, KLPP) containing link protein N-peptide (LPP) was designed to optimize cartilage repair. KLPP hydrogel was characterized using transmission electron microscopy (TEM) and rheometry. KLPP hydrogel shared a similar microstructure to KLD-12 hydrogel which possesses a nanostructure with a fiber diameter of 25–35 nm. In vitro experiments showed that KLPP hydrogel had little cytotoxicity, and significantly induced chondrocyte migration and increased BMSC migration compared to KLD-12 hydrogel. In vivo results showed that defects treated with KLPP hydrogel had higher overall International Cartilage Repair Society (ICRS) scores, Safranin-O staining scores and cumulative histology scores than untreated defects or defects treated with KLD-12 hydrogel, although defects treated with KLD-12 and KLPP hydrogels received similar type II collagen immunostaining scores. All these findings indicated that the simple injectable functionalized self-assembling peptide hydrogel KLPP facilitated simultaneous recruitment of endogenous chondrocytes and BMSCs to promote interface integration and improve cartilage regeneration, holding great potential as a one-step surgery strategy for endogenous cartilage repair.

Multiple-object tracking (MOT) has received an increasing attention due to the rapid development of autonomous driving. However, the MOT problem is still challenging mainly due to the occlusion and scale variation. Motivated by the fact that the discriminative correlation filters-based (DCFB) tracking algorithms can tackle these problems and significantly improve the accuracy of single object tracking, how to exploit the DCFB tracking algorithms for MOT is worthy studying. Moreover, the corrupted training samples due to the occlusion make DCFB tracking methods to update the appearance model of target uncorrected and result in tracking drift. In this paper, we exploit Markov decision process to integrate the DCFB tracking method into our MOT framework and address the update problem of the appearance model in DCFB tracking method. Moreover, in order to overcome the challenges of occlusion and scale variation, to prevent target drift during tracking, we use two DCFB trackers with different update frequencies and a novel update strategy to predict the location of targets. The part-based method is used to extract robust features to tackling the challenges of occlusion and scale change. In order to verify the efficiency of our algorithm, experiments are performed based on KITTI tracking benchmark. The results demonstrate that our method achieves state-of-the-art performance and outperforms the state-of-the-art algorithms in road scenarios.

Ship detection is of great importance and full of challenges in the field of remote sensing. The complexity of application scenarios, the redundancy of detection region, and the difficulty of dense ship detection are all the main obstacles that limit the successful operation of traditional methods in ship detection. In this paper, we propose a brand new detection model based on multitask rotational region convolutional neural network to solve the problems above. This model is mainly consisting of five consecutive parts: dense feature pyramid network, adaptive region of interest (ROI) align, rotational bounding box regression, prow direction prediction and rotational nonmaximum suppression (R-NMS). First of all, the low-level location information and high-level semantic information are fully utilized through multiscale feature networks. Then, we design adaptive ROI align to obtain high quality proposals which remain complete spatial and semantic information. Unlike most previous approaches, the prediction obtained by our method is the minimum bounding rectangle of the object with less redundant regions. Therefore, the rotational region detection framework is more suitable to detect the dense object than traditional detection model. Additionally, we can find the berthing and sailing direction of ship through prediction. A detailed evaluation based on SRSS for rotation detection shows that our detection method has a competitive performance.

Unlike single geospatial objects extraction from high-resolution remote sensing images, the task of road extraction faces more challenges, including its narrowness, sparsity, diversity, multiscale characteristics, and class imbalance. Focusing on these challenges, this paper proposes an end-to-end framework called the multiple feature pyramid network (MFPN). In MFPN, we design an effective feature pyramid and a tailored pyramid pooling module, taking advantage of multilevel semantic features of high-resolution remote sensing images. In the optimization stage, a weighted balance loss function is presented to solve the class imbalance problem caused by the sparseness of roads. The proposed novel loss function is more sensitive to the misclassified and the sparse real labeled pixels and helps to focus on the spare set of hard pixels in the training stage. Compared with the cross-entropy loss function, the weighted balance loss can reduce training time dramatically for the same precision. Experiments on two challenging datasets of high-resolution remote sensing images which illustrate the performance of the proposed algorithm have achieved significant improvements, especially for narrow rural roads.

Synthetic aperture radar (SAR) images have been widely used for ship monitoring. The traditional methods of SAR ship detection are difficult to detect small scale ships and avoid the interference of inshore complex background. Deep learning detection methods have shown great performance on various object detection tasks recently but using deep learning methods for SAR ship detection does not show an excellent performance it should have. One of the important reasons is that there is no effective model to handle the detection of multiscale ships in multiresolution SAR images. Another important reason is it is difficult to handle multiscene SAR ship detection including offshore and inshore, especially it cannot effectively distinguish between inshore complex background and ships. In this paper, we propose a densely connected multiscale neural network based on faster-RCNN framework to solve multiscale and multiscene SAR ship detection. Instead of using a single feature map to generate proposals, we densely connect one feature map to every other feature maps from top to down and generate proposals from each fused feature map. In addition, we propose a training strategy to reduce the weight of easy examples in the loss function, so that the training process more focus on the hard examples to reduce false alarm. Experiments on expanded public SAR ship detection dataset, verify the proposed method can achieve an excellent performance on multiscale SAR ship detection in multiscene.

Relation detection plays a crucial role in knowledge base question answering, and it is challenging because of the high variance of relation expression in real-world questions. Traditional relation detection models based on deep learning follow an encoding-comparing paradigm, where the question and the candidate relation are represented as vectors to compare their semantic similarity. Max- or average-pooling operation, which is used to compress the sequence of words into fixed-dimensional vectors, becomes the bottleneck of information flow. In this paper, we propose an attention-based word-level interaction model (ABWIM) to alleviate the information loss issue caused by aggregating the sequence into a fixed-dimensional vector before the comparison. First, attention mechanism is adopted to learn the soft alignments between words from the question and the relation. Then, fine-grained comparisons are performed on the aligned words. Finally, the comparison results are merged with a simple recurrent layer to estimate the semantic similarity. Besides, a dynamic sample selection strategy is proposed to accelerate the training procedure without decreasing the performance. Experimental results of relation detection on both SimpleQuestions and WebQuestions datasets show that ABWIM achieves the state-of-the-art accuracy, demonstrating its effectiveness.

Background: Chronic kidney disease (CKD) is closely related to the cardiovascular events in vascular calcification (VC). However, little has known about the characteristics of kidney injury caused by VC. Fibroblast growth factor 21 (FGF21) is an endocrine factor, which takes part in various metabolic actions with the potential to alleviate metabolic disorder diseases. Even FGF21 has been regarded as a biomarker in CKD, the role of FGF21 in CKD remains unclear. Therefore, in this study, we evaluate the FGF21 on the kidney injury in VC rats. Methods: The male Sprague-Dawley rats were divided into three groups: (1) control group, (2) Vitamin D3 plus nicotine (VDN)-induced VC group, (3) FGF21-treated VDN group. After 4 weeks, the rats were killed and the blood was collected for serum creatinine, urea nitrogen, calcium, and phosphate measurement. Moreover, the renal tissues were homogenized for alkaline phosphatases (ALPs) activity and calcium content. The levels of FGF21 protein were measured by radioimmunoassay. The levels of β-Klotho and FGF receptor 1 (FGFR1) protein were measured by enzyme-linked immunosorbent assay (ELISA). The structural damage and calcifications in aortas were stained by Alizarin-red S. Moreover, the structure of kidney was observed by hematoxylin and eosin staining. Results: The renal function impairment caused by VDN modeling was ameliorated by FGF21 treatment, inhibited the elevated serum creatinine and urea level by 20.5% (34.750 ± 4.334 μmol/L vs. 27.630 ± 2.387 μmol/L) and 4.0% (7.038 ± 0.590 mmol/L vs. 6.763 ± 0.374 mmol/L; P < 0.01), respectively, together with the structural damages of glomerular atrophy and renal interstitial fibrosis. FGF21 treatment downregulated the ALP activity, calcium content in the kidney of VC rats by 42.1% (P < 0.01) and 11.7% (P < 0.05) as well as ameliorated the aortic injury and calcification as compared with VDN treatment alone group, indicating an ameliorative effect on VC. ELISA assays showed that the expression of β-Klotho, a component of FGF21 receptor system, was increased in VDN-treated VC rats by 37.4% (6.588 ± 0.957 pg/mg vs. 9.054 ± 0.963 pg/mg; P < 0.01), indicating an FGF21-resistant state. Moreover, FGF21 treatment downregulated the level of β-Klotho in renal tissue by 16.7% (9.054 ± 0.963 pg/mg vs. 7.544 ± 1.362 pg/mg; P < 0.05). However, the level of FGFR1, the receptor of FGF21, kept unchanged under VDN and VDN plus FGF21 administration (0.191 ± 0.0376 ng/mg vs. 0.189 ± 0.032 ng/mg vs. 0.181 ± 0.034 ng/mg; P > 0.05). Conclusions: In the present study, FGF21 was observed to ameliorate the kidney injury in VDN-induced VC rats. FGF21 might be a potential therapeutic factor in CKD by cutting off the vicious circle between VC and kidney injury.

Herein, the Co3O4/NiCo2O4 nanocomposite has been prepared as a novel electrochemical sensor to accurately detect hydrogen peroxide (H2O2) and glucose. ZIF-67 is a metal-organic framework (MOF) with Co as the center metal ion. Co3O4 can be obtained by calcination of ZIF-67 at 700 °C, which can retain the structure of ZIF-67. The hollow Co3O4 nanocrystal was synthesized based on a calcination process of ZIF-67. This open structure can promote the whole Co3O4/NiCo2O4 nanocomposite larger accessible surface area and reactive sites. Co3O4 has good electrocatalytic performance, which has been applied in many fields. Moreover, H2O2 and dopamine sensing tests indicate that the as-prepared non-enzymatic electrochemical biosensor has good detection properties. The testing results indicate the as-prepared biosensor has a wide detection range, low detection limit, high selectivity, and long-term stability. These testing results suggest the potential application in food security, biomedicine, environmental detection, and pharmaceutical analysis.