Search

With the continuous development of the internet, an increasing number of images have been tampered with on the network, accompanied by a growing range of techniques to cover up tampering traces.However, most current detection models neglect the impact of image post-processing on tamper detection algorithms, limiting their real-life applications.To address these issues, a general image tampering location model based on enhanced samples and the pseudo-twin network was proposed.The pseudo-twin network enabled the model to learn tampering features in real images.On one hand, by applying convolution constraints, the image content was suppressed, allowing the model to focus more on residual trace information of tampering.The two-branch structure of the network facilitated the comprehensive utilization of image feature information.By utilizing enhanced samples, the model could dynamically generate the most crucial pictures for learning tamper types, enabling targeted training of the model.This approach ensured that the model converged in all directions, ultimately obtaining the global optimal model.The idea of data enhancement was employed to automatically generate abundant tampered images and corresponding masks, effectively resolving the limited tampering dataset issue.Extensive experiments were conducted on four datasets, demonstrating the feasibility and effectiveness of the proposed model in pixel-level tamper detection.Particularly on the Columbia dataset, the algorithm achieves a 33.5% increase in F1 score and a 23.3% increase in MCC score.These results indicate that the proposed model harnesses the advantages of deep learning models and significantly improves the effectiveness of tamper location detection.

Nasopharyngeal carcinoma (NPC) is one of the most common malignant tumors of the head and neck region. NPC has the characteristics of insidious onset, strong invasiveness and early lymph node metastasis. A variety of signaling pathways play a role in the invasion and metastasis of nasopharyngeal carcinoma, but the specific mechanism has not yet been fully elucidated. Recent studies have found that DNA methylation of nasopharyngeal carcinoma-related genes can affect the invasion and metastasis of nasopharyngeal carcinoma through a variety of signaling pathways including Wnt/β-catenin, PI3K/AKT and MAPK signaling pathways. This article reviews the specific mechanism of DNA methylation affecting the invasion and metastasis of nasopharyngeal carcinoma through the above-mentioned signaling pathways.

Groundwater is the main clean water resource in northern China, and its quality is critical for both human health and social sustainable development. Due to complex anthropogenic and/or geogenic processes, the sources of groundwater contaminants are not easy to determine. The Tabu River Basin, located in northern China, is an agriculture and pasture interlaced area in which phreatic groundwater is the predominant water resource for domestic and agricultural purposes. Groundwater with abnormally high levels of NO3−, F−, and TDS was observed here based on 87 groundwater samples collected from the phreatic aquifer in 2022. In this study, hydrogeochemical and isotopic methods were used to trace groundwater contaminants in the phreatic aquifer, and a risk assessment was conducted to analyze their threat to human health. The results indicated that NO3− in the phreatic groundwater primarily originated from manure, the high concentration of TDS was highly associated with irrigation, and the enrichment of F− was mainly controlled by geogenic factors, including alkaline condition, competitive adsorption, the dissolution of fluorine-bearing minerals, and cation exchange. A principal component analysis (PCA) showed that both anthropogenic (PC1, 50.7%) and geogenic (PC2, 19.9%) factors determined the quality of the phreatic groundwater in the study area. The human health risk assessment demonstrated that 98.9%, 92.0%, and 80.5% of the groundwater samples exceeded the permissible limit of the total noncarcinogenic risk for children, adult females, and adult males, respectively. The monitoring results from 2022 to 2023 suggested that phreatic groundwater contamination could not be mitigated through natural attenuation under the existing external pressures. Measures need to be taken to decrease the contamination of phreatic groundwater and enhance the groundwater sustainability in the Tabu River Basin. The findings of this study can provide a reference for sustainable groundwater development in the Tabu River Basin and other arid and semi-arid regions worldwide. [ABSTRACT FROM AUTHOR]

Background: Central pancreatectomy is a surgical procedure for benign and low-grade malignant tumors which located in the neck and proximal body of the pancreas that facilitates the preservation of pancreatic endocrine and exocrine functions but has a high morbidity rate, especially postoperative pancreatic fistula (POPF). The aim of this systematic review and meta-analysis was to evaluate the safety and effectiveness between minimally invasive central pancreatectomy (MICP) and open central pancreatectomy (OCP) basing on perioperative outcomes. Methods: An extensive literature search to compare MICP and OCP was conducted from October 2003 to October 2023 on PubMed, Medline, Embase, Web of Science, and the Cochrane Library. Fixed-effect models or random effects were selected based on heterogeneity, and pooled odds ratios (ORs) or mean differences (MDs) with 95% confidence intervals (CIs) were calculated. Results: A total of 10 studies with a total of 510 patients were included. There was no significant difference in POPF between MICP and OCP (OR = 0.95; 95% CI [0.64, 1.43]; P = 0.82), whereas intraoperative blood loss (MD = − 125.13; 95% CI [− 194.77, -55.49]; P < 0.001) and length of hospital stay (MD = − 2.86; 95% CI [− 5.00, − 0.72]; P = 0.009) were in favor of MICP compared to OCP, and there was a strong trend toward a lower intraoperative transfusion rate in MICP than in OCP (MD = 0.34; 95% CI [0.11, 1.00]; P = 0.05). There was no significant difference in other outcomes between the two groups. Conclusion: MICP was as safe and effective as OCP and had less intraoperative blood loss and a shorter length of hospital stay. However, further studies are needed to confirm the results. [ABSTRACT FROM AUTHOR]

Representing art using a robotic system is part of artificial intelligence in our lives, especially in the realm of emotional expression. Developing a painting robot involves addressing how to enable the robot to emulate human artistic processes, which often include imprecise techniques or errors akin to those made by human artists. This paper discusses our development of an innovative painting robot utilizing the sim-to-real approach within learning technology. Specifically, this pipeline operates under a deep reinforcement learning (DRL) framework designed to learn drawing strategies from training data derived from real-world settings, aiming for the robot's proficiency in emulating human artistic expressions. Accordingly, the framework comprises two modules when given a target drawing image: the first module trains in a simulated environment to break down the target image into individual strokes; the second module then learns how to execute these strokes in a real environment. Our experiments have shown that this system can meet our objectives effectively. [ABSTRACT FROM AUTHOR]

To research the AE warning mechanism of cemented paste backfilling (CPB), the uniaxial compression test with AE monitoring was carried out on CPB. The effects of different moisture content, cement proportion, and loading rate on AE characteristics of CPB were analyzed. And a damage model based on AE is established. The results show that the increase of water content, gypsum content, and loading rate can enhance the ductility of CPB and lengthen the AE warning area. However, the increase of moisture content will lead to the delay of AE signal peak, which is bad for the early warning. With the increase of loading rate, the failure mode of specimens gradually changes from splitting failure to shear failure. The cracks produced under different failure modes can correspond to the peaks of AE signals. The damage model based on AE shows that the damage process of CPB samples can be divided into three stages, linear-exponential-linear. The experimental results can further research the optimal conditions for ae monitoring of backfill, and provide a theoretical basis for ae monitoring and warning of backfill.

With the rapid development of urban rail transit and underground space construction, the advantages of the concealed excavation method are gradually highlighted in the urban center area affected by a complex engineering environment. At present, the pipe curtain method with a flexible section and wide application of the soil layer is being widely used in engineering, but the research on the stability of the excavation face during the construction of the pipe curtain method in soft soil areas still has not formed a complete system. Therefore, this paper analyzes the stability of the excavation face under different reinforcement conditions and the influence of different spacing, numbers, and strength of MJS (metro jet system) zones on the stability of the excavation face of the pipe curtain method based on the actual project of the Guiqiao Road Station of the Shanghai Metro, China, and gives a reference for the reinforcement of the palm face in the excavation process of the pipe curtain method in soft soil areas. The study shows that the safety coefficient of the excavation face decreases with the increase in the slope angle of the excavation face, with the increase in spacing of the MJS zone, and with the increase in height of the MJS zone arrangement, while the safety coefficient of the excavation face increases with the increase in strength of the MJS zones themselves and the increase in the strength of the soil between the MJS zones. Further, the machine learning model is applied to predict the stability of the excavation face under different cases, and the relevant fitting accuracy is above 0.9, which can predict the stability of the excavation better. [ABSTRACT FROM AUTHOR]

The rapid expansion of metro networks, e.g., in many cities of China, continuously introduces the operation of new stations every year. Due to the lack of historical data and complicate variations of short-term passenger flow in the early stage of operation, it is difficult to accurately predict inbound and outbound passenger flows of new metro stations in the short term, which would be the database for train scheduling for new stations before operation, dynamic capacity optimization for new stations under operation, short-term prediction of cycle sharing demands near new stations, and so on. Traditional methods usually failed to exactly reflect the complicate rules or were unusable without the new station's historical data. In order to solve the above problems, this paper proposes a short-term inbound and outbound passenger flow prediction model for new metro stations at the early stage of operation by combining the K-means clustering algorithm, an improved spatiotemporal long short-term memory model (Sp-LSTM), and a real-time feedback error model (mean absolute error, MAE), where passenger flows' spatial-temporal characteristics and land-use relevance are considered. The application in Guangzhou Metro, China, where Line 21 is regarded as a new line, shows that the proposed K-Sp-LSTM model has the best prediction accuracy compared with traditional methods. [ABSTRACT FROM AUTHOR]