Search

Propose an optimized and improved traffic sign detection model based on YOLOv8n, addressing the issues of low accuracy and inaccurate detection, especially in adverse weather conditions, observed in current traditional network models. We leverage existing techniques, including the BoTNet (Bottleneck Transformers for Visual Recognition) module to enhance image classification capabilities, the ODConv (Omni-dimensional Dynamic Convolution) module to supplement attention for improved accuracy, and the LSKA (Large Separable Kernel Attention) module to reduce memory and computational complexity while enhancing small object detection capabilities. Additionally, we employ the WIoU (Wise Intersection over Union) loss function to enhance the model’s generalization performance. Without additional preprocessing to simulate adverse weather conditions, our results on the TT100K dataset, including mAP50, mAP95 (mAP is ’mean Average Precision’), and F1, relative to the original YOLOv8n model, show improvements of 3%, 4%, and 2.5% in misty conditions and 1%, 2.6%, and 1.7% in dark conditions, respectively. On the GTSDB dataset, in misty conditions, the improvements are 5%, 4.2%, and 2.3%, and in dark conditions, the improvements are 3%, 6.6%, and 6%. When 30% of the training set is augmented with fog, the detection performance of the improved model is comparable to, or even exceeds, that of the YOLOv8n model trained with the entire fog-augmented training set. This comprehensive result highlights the significant superiority of our model over the comparative model, demonstrating its practical applicability.

Abstract SULF1 has been implicated in a number of malignancies. The function of SULF1 in gastric cancer is disputed. The objective of this study was to examine the role and underlying molecular mechanisms of SULF1 in the context of gastric cancer. We found that the expression of SULF1 was increased in gastric cancer, especially in cancer-associated fibroblasts. The overexpression of SULF1 was found to be significantly correlated with unfavorable prognosis among individuals diagnosed with gastric cancer. Functionally, cancer-associated fibroblasts-derived SULF1 served as a oncogenic molecule which facilitated gastric cancer cells metastasis and CDDP resistance. Mechanistically, SULF1 regulated the communication between gastric cancer cells and cancer-associated fibroblasts in tumor microenvironment as a signaling molecule. Cancer-associated fibroblasts-secreted SULF1 interfered with the interaction between TGF-β1 and TGFBR3 by combining with TGFBR3 on gastric cancer cell membrane, subsequently activated TGF-β signaling pathway. In conclusion, our findings have presented novel approaches for potential treatment and prognosis prediction in individuals diagnosed with gastric cancer through the targeting of the CAFs-SULF1-TGFBR3-TGF-β1 signaling axis.

As one of the optically active components, phytoplankton are common photosynthetic organisms in oceans, nearshore, and inland water bodies. The variations in phytoplankton algal density play a crucial role in understanding primary productivity, carbon cycling, and early warning of algal blooms. In this study, three typical eutrophic lakes in China, Lake Taihu, Lake Chaohu, and Lake Dianchi, were taken as the research area. Algorithms for estimating algal density of cyanobacteria-dominated and non-cyanobacteria-dominated water types were developed based on Mie theory. The results demonstrated that the developed algorithm had favorable estimation performance for inland eutrophic lakes, with a determination coefficient (R2) of 0.88, a mean absolute percentage error (MAPE) of 51%, an unbiased mean absolute percentage error (UMAPE) of 39%, and a root mean square error (RMSE) of 23.99 × 106 cells/L. Furthermore, comparison with other algorithms for estimating algal density showed that the developed algorithm had the lowest MAPE of 60% and UMAPE of 43%, with the RMSE of 23.42 × 106cells/L. Extensive evaluation based on satellite-ground synchronous data demonstrated the applicability of the developed algorithm to the Sentinel-3 OLCI sensor, enabling the determination of spatial and temporal distribution characteristics of algal density in the three lakes from 2016 to 2022 using Sentinel-3 OLCI images. The results of algal density inversion revealed a continuous decreasing trend in algal density in Lake Dianchi from 2016 to 2022, while the algal density in Lake Taihu and Lake Chaohu both decreased after 2019.

Abstract Background This study aimed to evaluate the association of triglyceride-glucose (TyG) index, an insulin resistance surrogate biomarker, with first stroke in a hypertensive population and to explore potential influencing factors. Methods This study, a cohort study among a rural Chinese hypertensive population, utilized data from the China Stroke Primary Prevention Trial (CSPPT). The TyG index was calculated as ln [fasting triglyceride (mg/dL) × fasting glucose (mg/dL)/2]. Multivariate analysis using Cox proportional hazards models was conducted. Results A total of 7569 hypertensive patients were included in this study. When TyG index was assessed as quartiles, compared with the reference group (Quartile 1), the hazard ratio of stroke was 1.04 in Quartile 2, 1.43 in Quartile 3, and 1.45 in Quartile 4, with a significant trend test (P = 0.013). When Quartiles 3 and 4 were combined (≥ 8.8), the hazard ratio was 1.41 compared with combined Quartiles 1 and 2 (

Abstract Purpose MUC1 is a membrane bound protein that can regulate tumor progression but its role in tumor metastasis and the metastatic microenvironment remains unclear. Methods We performed differential gene analysis for primary liver cancer (n = 31) and lung metastases (n = 31) using the Gene Expression Omnibus (GEO) dataset (GSE141016) and obtained RNA sequencing data from 374 liver cancer and 50 normal tissues from The Cancer Genome Atlas (TCGA). We analyzed the prognostic value of MUC1 and the relationship between MUC1 and the TME using online databases and a clinical cohort. Immunohistochemistry detected MUC1 in normal liver, liver cancer, and lung metastases. Multiplex immunohistochemistry staining detected immune cells in the metastatic microenvironment. Results High MUC1 expression levels in hepatocellular carcinoma are associated with worse clinical prognosis and higher rates of lung metastasis. In addition, we observed a correlation between MUC1 and multiple immune cells in the metastatic microenvironment. In paired primary liver cancer and lung metastatic tumor tissues from the same patient, we observed higher MUC1 protein levels in lung metastases than in primary liver cancer. Furthermore, MUC1 was negatively correlated with CD8+T and Treg cells in the metastatic tumor microenvironment and positively correlated with DC. In addition, we found that MUC1 was associated with CD8+T cell activation and function using flow cytometry in another cohort of patients with liver cancer. Conclusion These data confirm the potential of MUC1 as a prognostic marker and therapeutic target.

Background and purposeThe presence of microvascular invasion (MVI) is a crucial indicator of postoperative recurrence in patients with hepatocellular carcinoma (HCC). Detecting MVI before surgery can improve personalized surgical planning and enhance patient survival. However, existing automatic diagnosis methods for MVI have certain limitations. Some methods only analyze information from a single slice and overlook the context of the entire lesion, while others require high computational resources to process the entire tumor with a three-dimension (3D) convolutional neural network (CNN), which could be challenging to train. To address these limitations, this paper proposes a modality-based attention and dual-stream multiple instance learning(MIL) CNN.Materials and methodsIn this retrospective study, 283 patients with histologically confirmed HCC who underwent surgical resection between April 2017 and September 2019 were included. Five magnetic resonance (MR) modalities including T2-weighted, arterial phase, venous phase, delay phase and apparent diffusion coefficient images were used in image acquisition of each patient. Firstly, Each two-dimension (2D) slice of HCC magnetic resonance image (MRI) was converted into an instance embedding. Secondly, modality attention module was designed to emulates the decision-making process of doctors and helped the model to focus on the important MRI sequences. Thirdly, instance embeddings of 3D scans were aggregated into a bag embedding by a dual-stream MIL aggregator, in which the critical slices were given greater consideration. The dataset was split into a training set and a testing set in a 4:1 ratio, and model performance was evaluated using five-fold cross-validation.ResultsUsing the proposed method, the prediction of MVI achieved an accuracy of 76.43% and an AUC of 74.22%, significantly surpassing the performance of the baseline methods.ConclusionOur modality-based attention and dual-stream MIL CNN can achieve outstanding results for MVI prediction.

Passport security feature classification has always been an important issue in border checks. Current manual methods struggle to achieve satisfactory results in terms of consistency and stability for security features with high similarity. For this reason, this study designs and develops a deep learning-based passport security feature classification model that can identify similar security features. The proposed model is based on the ShuffleNet v2, and its network structure is further optimized by two aspects for our task. Firstly, we embed pixel attention in the model to enable the network to better focus on important features with discriminatory power. Secondly, we introduce focal loss to relieve the overfitting problem caused by data imbalance. Finally, the superiority of the proposed classification algorithm is verified with the constructed passport security features data. The classification accuracy of the proposed algorithm is enhanced by 0.8%.The experimental results show that the classification accuracy is as high as 95.5%.

The particulate backscattering coefficient (bbp) plays an important role in the underwater light field. However, it is difficult to accurately estimate bbp(λ) in turbid inland water with complex optical properties. To accurately estimate the backscattering coefficients in inland water, a simple classification method based on the shape of remote sensing reflectance was first proposed to distinguish two water types (i.e., water type 1 and water type 2) with different backscattering characteristics. Then, trigonometric functions were developed to simulate the backscattering coefficients at all bands in water type 1 and the backscattering coefficients in the visible band of water type 2, whereas a linear function was built to estimate the backscattering coefficients in the near-infrared band of water type 2. The proposed algorithm was compared with four state-of-the-art methods and validated by an independently measured dataset of three lakes in the middle and lower reaches of the Yangtze River in 2020. The results showed that the proposed algorithm performed well in inland waters, with all mean absolute percentage errors < 40% and root-mean-square errors < 0.25 m−1. Finally, the algorithm was applied to Ocean and Land Color Instrument images from 2016 to 2020 in Lake Taihu and Lake Hongze. It was found that the backscattering coefficients in Lake Taihu and Lake Hongze showed opposite seasonal variation trends, and the bbp(676) in Lake Hongze began to decrease since 2017, whereas no obvious interannual variation was observed in Taihu Lake in recent five years.

Accurate monitoring of emergent aquatic vegetation (EAV) and floating-leave aquatic vegetation (FAV), is vital because vegetation provides a critical habitat for aquatic animals and plays a critical role in protecting biodiversity. However, owing to the interference of water spectrum signals, it is difficult to extract the emerging aquatic vegetation information from remote sensing images, especially to distinguish between EAV and FAV. This study first proposed an enhanced aquatic vegetation index based on the difference in two short-wave infrared (SWIR) bands to extract the aquatic vegetation above the water surface, and then, the EAV and FAV were further distinguished coupled with the phenological characteristics, subsequently, a case study of Taihu Lake for accurately extracting seasonal and annual distributions. The results demonstrate that the proposed aquatic vegetation index is highly sensitive to EAV and FAV, and can further distinguish EAV from them coupled with phenological difference. Additionally, the dramatic changes in EAV and FAV in time and space indicated that human purse seine culture has had a great influence on the succession of aquatic vegetation, which may lead to the deterioration of the water ecology environment. Using the SWIR bands coupled with phenological difference is a promising method for recognizing aquatic vegetation above the water surface owing that it can weaken and eliminate the impact of algal bloom at the same time.

Abstract Based on the fundamentals of expert system (ES) and decision support system (DSS), we developed an integrated system, the expert decision support system (EDSS), to design and optimize sandstone acidizing. The new system combines knowledge of the ES with DSS models to facilitate decision-making for qualitatively and quantitatively acidizing sandstone reservoirs; this approach greatly strengthens the system’s working capability and widens its applicable range. This article introduces the design principle, system structure, functional modules, multi bases, and development process of the EDSS. We illustrate the representation method of the expert’s knowledge, establishing the knowledge decision tree, and creating quantitative mathematic models for decision support and inference process via different reasonings (rule-based vs. case-based). These methods and methodologies worked together to operate different functional modules for inference from both knowledge and calculation. The EDSS connected different design considerations of the acidizing technology. A field test case study proved that the proposal provided by the EDSS was very efficient.

Transient pressure analysis is a crucial tool to forecast the production performance during the exploration and production process in gas reservoirs. Usually, a regular shaped outer boundary is assumed in previous studies for well-testing analysis, which is just a simplification of practical cases and cannot reflect the actual boundaries of reservoirs. In this paper, a mathematical model is established to analyze the transient pressure behaviors of a horizontal well in an arbitrarily shaped gas reservoir. Dimensionless treatment, Laplace transformation, and boundary element method are applied in solving the model, which is verified by comparing with the results from the source function method. Based on the Stehfest numerical inversion method, the models of single-porosity media and dual-porosity media are solved respectively. Then, the time-domain curves of pseudo pressure and its derivative are obtained, and the flow regimes are identified. Finally, the impacts of some critical parameters on pressure transient behaviors are analyzed, including storativity ratio, interporosity coefficient, well length, and well orientation. This paper presents an effective way to handle complex external boundary problems in gas reservoirs.

The Yangtze River Delta (YRD) is one of the regions with the most intensive human activities. The eutrophication of lakes in this area is becoming increasingly serious with consequent negative impacts on the water supply of the surrounding cities. But the spatial-temporal characteristics and driving factors of the trophic state of the lake in this region are still not clearly addressed. In this study, a semi-analytical algorithm for estimating the trophic index (TSI) using particle absorption at 645 nm based on MODIS images is proposed to monitor and evaluate the trophic state of 41 large lakes (larger than 10 km2) in the YRD from 2002 to 2020. The performance of the proposed algorithm is evaluated using an independent dataset. Results showed that the root-mean-square error (RMSE) of the algorithm is less than 6 and the mean absolute percentage error (MAPE) does not exceed 8%, indicating that it can be applied for remotely deriving the TSI in the YRD. The spatial-temporal patterns revealed that there were significantly more lakes with moderate eutrophication in the Lower Yangtze River (LYR) than in the Lower Huaihe River (LHR). The overall average value of the TSI reaches a maximum in summer and a minimum in winter. The TSI value in the YRD over the period 2002–2020 showed a downward trend, especially after 2013. Individually, 33 lakes showed a downward trend and 8 lakes showed an upward trend. Furthermore, marked seasonal and interannual temporal variations can be clearly observed in the LYR and LHR and the sum of the variance contributions of seasonal and interannual components is more than 50%. Multiple linear regression analysis showed that human activities can explain 65% of the variation in the lake TSI in the YRD.

Ubiquitin ligase TRAF6 catalyzes assembly of free polyubiquitin chains for TAK1 activation in the IL-1R/TLR pathways, but the mechanism underlying its processivity is unclear. Here, the authors show that TRAF6 coiled-coil oligomerization domain primes its interaction with Ubc13/Ub~Ubc13 to confer processivity.

The accurate remote estimation of the Secchi disk depth (ZSD) in turbid waters is essential in the monitoring the ecological environment of lakes. Using the field measured ZSD and the remote sensing reflectance (Rrs(λ)) data, a new semi-analytical algorithm (denoted as ZSDZ) for retrieving ZSD was developed from Rrs(λ), and it was applied to Geostationary Ocean Color Imager (GOCI) images in extremely turbid waters. Our results are as follows: (1) the ZSDZ performs well in estimating ZSD in turbid water bodies (0.15 m < ZSD < 2.5 m). By validating with the field measured data that were collected in four turbid inland lakes, the determination coefficient (R2) is determined to be 0.89, with a mean absolute square percentage error (MAPE) of 22.39%, and root mean square error (RMSE) of 0.24 m. (2) The ZSDZ improved the retrieval accuracy of ZSD in turbid waters and outperformed the existing semi-analytical schemes. (3) The developed algorithm and GOCI data are in order to map the hourly variation of ZSD in turbid inland waters, the GOCI-derived results reveal a significant spatiotemporal variation in our study region, which are significantly driven by wind forcing. This study can provide a new approach for estimating water transparency in turbid waters, offering important support for the management of inland waters.

Power quality signal feature selection is an effective method to improve the accuracy and efficiency of power quality (PQ) disturbance classification. In this paper, an entropy-importance (EnI)-based random forest (RF) model for PQ feature selection and disturbance classification is proposed. Firstly, 35 kinds of signal features extracted from S-transform (ST) with random noise are used as the original input feature vector of RF classifier to recognize 15 kinds of PQ signals with six kinds of complex disturbance. During the RF training process, the classification ability of different features is quantified by EnI. Secondly, without considering the features with zero EnI, the optimal perturbation feature subset is obtained by applying the sequential forward search (SFS) method which considers the classification accuracy and feature dimension. Then, the reconstructed RF classifier is applied to identify disturbances. According to the simulation results, the classification accuracy is higher than that of other classifiers, and the feature selection effect of the new approach is better than SFS and sequential backward search (SBS) without EnI. With the same feature subset, the new method can maintain a classification accuracy above 99.7% under the condition of 30 dB or above, and the accuracy under 20 dB is 96.8%.