Explore the vast range of titles available.

Automatic segmentation of infected lesions from computed tomography (CT) of COVID-19 patients is crucial for accurate diagnosis and follow-up assessment. The remaining challenges are the obvious scale difference between different types of COVID-19 lesions and the similarity between the lesions and normal tissues. This work aims to segment lesions of different scales and lesion boundaries correctly by utilizing multiscale and multilevel features. A novel multiscale dilated convolutional network (MSDC-Net) is proposed against the scale difference of lesions and the low contrast between lesions and normal tissues in CT images. In our MSDC-Net, we propose a multiscale feature capture block (MSFCB) to effectively capture multiscale features for better segmentation of lesions at different scales. Furthermore, a multilevel feature aggregate (MLFA) module is proposed to reduce the information loss in the downsampling process. Experiments on the publicly available COVID-19 CT Segmentation dataset demonstrate that the proposed MSDC-Net is superior to other existing methods in segmenting lesion boundaries and large, medium, and small lesions, and achieves the best results in Dice similarity coefficient, sensitivity and mean intersection-over-union (mIoU) scores of 82.4%, 81.1% and 78.2%, respectively. Compared with other methods, the proposed model has an average improvement of 10.6% and 11.8% on Dice and mIoU. Compared with the existing methods, our network achieves more accurate segmentation of lesions at various scales and lesion boundaries, which will facilitate further clinical analysis. In the future, we consider integrating the automatic detection and segmentation of COVID-19, and conduct research on the automatic diagnosis system of COVID-19.

This paper presents an innovative methodology for the dynamic emergency response scheme selection (ERSS) problem in post-major natural disasters. It employs a combination of subjective and objective composite weights and the integrated ELECTRE-score approach. The study aims to provide a practical approach for continuously determining optimal decision schemes at various time points during the decision period in the aftermath of significant natural disasters while accommodating evolving real-world scenarios. Firstly, the probabilistic T-spherical hesitant fuzzy set (Pt-SHFS) captures decision-makers’ ambivalence and hesitation regarding diverse evaluation attributes of different schemes. Subsequently, Pt-SHFS is integrated with the best–worst method (BWM) to determine subjective weights, followed by the structured CRITIC method to amalgamate subjective weights and derive the final combination weights of criteria. Additionally, this paper proposes applying a penalty-incentive mechanism to establish dynamic attribute weights during scenario evolution. Furthermore, the ELECTRE-score method, which may fully exploit the advantages of non-compensation situations, is adopted to obtain more reliable dynamic optimal decision outcomes. Consequently, based on these foundations, an integrated dynamic ERSS approach is formulated to determine optimal dynamic emergency response schemes. Finally, a case study on the Gansu Jishishan earthquake, sensitivity analysis, comparative analysis, and continuous analysis are conducted to verify the practicality, stability, and effectiveness of the proposed approach. The result shows that the proposed comprehensive approach can depict variances among experts’ information, dynamically adjust attribute weights in response to evolving scenarios, and assign a score range and a representative score to each scheme at each decision state. Sensitivity and comparative analyses show this model has strong stability and dynamics. Furthermore, the proposed approach can effectively deal with the complex dynamic situation in the earthquake rescue process, such as the secondary collapse of buildings after the earthquake, the damage of materials caused by heavy rain, and the occurrence of aftershocks. The model can continuously optimize decision-making and provide scientific and reliable support for emergency decision-making.

Magnesium sulfate is commonly utilized in critical care due to its vasodilatory, bronchodilatory, and neuroprotective properties. However, its impact on mortality outcomes in patients with chronic obstructive pulmonary disease (COPD) requiring intensive care remains inadequately defined. A retrospective cohort study was conducted on patients with COPD who were admitted to the ICU at Beth Israel Deaconess Medical Center in Boston from 2008 to 2019. Early administration of magnesium sulfate was considered for intravenous administration within 48 h of ICU admission. Propensity-score-based methods, such as inverse probability weighting, were employed to evaluate the correlation between early use of magnesium sulfate and 28-day mortality. A total of 3,651 ICU admissions for COPD were included, of which 1,148 (31.4%) patients received magnesium sulfate within the first 48 h. Administering magnesium sulfate early was linked to a reduced 28-day mortality rate (hazard ratio 0.76, 95% confidence interval 0.60-0.95), with consistent results across predefined subgroups. This correlation remained consistent regardless of baseline serum magnesium levels and did not increase the risk of acute kidney injury (AKI). The calculated E-value of 1.96 indicates that significant unmeasured confounding factors would be necessary to fully account for the observed relationship. In this single-center retrospective cohort, early magnesium sulfate administration in critically ill patients with COPD was associated with lower 28-day mortality without an observed increase in AKI risk. These results advocate for prospective multicenter studies to validate these connections, investigate optimal dosing approaches, and pinpoint the patient subgroups most likely to benefit from this intervention.

Compared with traditional physical commodities, data are intangible and easy to leak, and the related trading process has problems, such as complex participating roles, lengthy information flow, poor supervisory coverage and difficult information traceability. To handle these problems, we construct a distributed supervision model for data trading based on blockchain, and conduct multi-party hierarchical and multi-dimensional supervision of the whole process of data trading through collaborative supervision before the event, at present and after the event. First, the characteristics of information flow in the data trading process are analyzed, and the main subject and key supervision information in the data trading process are sorted out and refined. Secondly, combined with the actual business process of data trading supervision, a multi-channel structure of distributed supervision is proposed by adopting an access–verification–traceability strategy. Finally, under the logical framework of the supervision model, the on-chain hierarchical structure and the data hybrid storage method of “on-chain + off-chain” are designed, and multi-supervisor-oriented hierarchical supervision and post-event traceability are realized through smart contracts. The results show that the constructed blockchain-based distributed supervision model of data trading can effectively isolate and protect sensitive and private information between data trading, so as to realize the whole process, multi-subject and differentiated supervision of key information of data trading, and provide an effective and feasible method for the controllable and safe supervision of data trading.

We present a PyTorch-based framework for forward folded reactor neutrino spectrum fitting that accelerates the two main bottlenecks: IBD mapping and detector response, using (i) result caching, (ii) banded sparse matrices, and (iii) blocked construction of the response. On an Intel Xeon Gold 6338 CPU, these techniques reduce per-fit walltime by ≈ 7 × (median over 5 runs) relative to a dense, unoptimized implementation, with < 10 - 6 relative spectral error versus a double-precision baseline. The framework has been applied to reactor-neutrino oscillation analyses and is reusable in other neutrino experiments that rely on forward-folded energy spectra, enabling practical Feldman–Cousins coverage studies and large parameter scans at substantially lower computational cost.

Batch process monitoring datasets usually contain missing data, which decreases the performance of data-driven modeling for fault identification and optimal control. Many methods have been proposed to impute missing data; however, they do not fulfill the need for data quality, especially in sensor datasets with different types of missing data. We propose a hybrid missing data imputation method for batch process monitoring datasets with multi-type missing data. In this method, the missing data is first classified into five categories based on the continuous missing duration and the number of variables missing simultaneously. Then, different categories of missing data are step-by-step imputed considering their unique characteristics. A combination of three single-dimensional interpolation models is employed to impute transient isolated missing values. An iterative imputation based on a multivariate regression model is designed for imputing long-term missing variables, and a combination model based on single-dimensional interpolation and multivariate regression is proposed for imputing short-term missing variables. The Long Short-Term Memory (LSTM) model is utilized to impute both short-term and long-term missing samples. Finally, a series of experiments for different categories of missing data were conducted based on a real-world batch process monitoring dataset. The results demonstrate that the proposed method achieves higher imputation accuracy than other comparative methods.

As the development of the Internet of Things (IoT) continues, Federated Learning (FL) is gaining popularity as a distributed machine learning framework that does not compromise the data privacy of each participant. However, the data held by enterprises and factories in the IoT often have different distribution properties (Non-IID), leading to poor results in their federated learning. This problem causes clients to forget about global knowledge during their local training phase and then tends to slow convergence and degrades accuracy. In this work, we propose a method named FedRAD, which is based on relational knowledge distillation that further enhances the mining of high-quality global knowledge by local models from a higher-dimensional perspective during their local training phase to better retain global knowledge and avoid forgetting. At the same time, we devise an entropy-wise adaptive weights module (EWAW) to better regulate the proportion of loss in single-sample knowledge distillation versus relational knowledge distillation so that students can weigh losses based on predicted entropy and learn global knowledge more effectively. A series of experiments on CIFAR10 and CIFAR100 show that FedRAD has better performance in terms of convergence speed and classification accuracy compared to other advanced FL methods.

Automatic guided vehicles have become an important part of transporting goods in dynamic environments, and how to design an efficient path planning method for multiple AGVs is a current research hotspot. Due to the complex road conditions in dynamic environments, there may be dynamic obstacles and situations in which only the target point is known but a complete map is lacking, which leads to poor path planning and long planning time for multiple automatic guided vehicles (AGVs). In this paper, a two-level path planning method (referred to as GA-KL, genetic KL method) for multi-AGVs is proposed by integrating the scheduling policy into global path planning and combining the global path planning algorithm and local path planning algorithm. First, for local path planning, we propose an improved Q-learning path optimization algorithm (K-L, Kohonen Q-learning algorithm) based on a Kohonen network, which can avoid dynamic obstacles and complete autonomous path finding using the autonomous learning function of the Q-learning algorithm. Then, we adopt the idea of combining global and local planning by combining the K-L algorithm with the improved genetic algorithm; in addition, we integrate the scheduling policy into global path planning, which can continuously adjust the scheduling policy of multi-AGVs according to changes in the dynamic environment. Finally, through simulation and field experiments, we verified that the K-L algorithm can accomplish autonomous path finding; compared with the traditional path planning algorithm, the algorithm achieved improves results in path length and convergence time with various maps; the convergence time of the algorithm was reduced by about 6.3%, on average, and the path length was reduced by about 4.6%, on average. The experiments also show that the GA-KL method has satisfactory global search capability and can effectively avoid dynamic obstacles. The final experiments also demonstrated that the GA-KL method reduced the total path completion time by an average of 12.6% and the total path length by an average of 8.4% in narrow working environments or highly congested situations, which considerably improved the efficiency of the multi-AGVs.

Owing to excellent high-temperature mechanical properties, i.e., high heat resistance, high strength, and high corrosion resistance, Ti alloys can be widely used as structural components, such as blades and wafers, in aero-engines. Due to the complex shapes, however, it is difficult to fabricate these components via traditional casting or plastic forming. It has been proved that additive manufacturing (AM) is an effective method of manufacturing such complex components. In this study, four main additive manufacturing processes for Ti alloy components were reviewed, including laser powder bed melting (SLM), electron beam powder bed melting (EBM), wire arc additive manufacturing (WAAM), and cold spraying additive manufacturing (CSAM). Meanwhile, the technological process and mechanical properties at high temperature were summarized. It is proposed that the additive manufacturing of titanium alloys follows a progressive path comprising four key developmental stages and research directions: investigating printing mechanisms, optimizing process parameters, in situ addition of trace elements, and layered material design. It is crucial to consider the development stage of each specific additive manufacturing process in order to select appropriate research directions. Moreover, the corresponding post-treatment was also analyzed to tailor the microstructure and high-temperature mechanical properties of AMed Ti alloys. Thereafter, to improve the mechanical properties of the product, it is necessary to match the post-treatment method with an appropriate additive manufacturing process. The additive manufacturing and the following post-treatment are expected to gradually meet the high-temperature mechanical requirements of all kinds of high-temperature structural components of Ti alloys.

Carbonates, the main components of oil shale that influence oil and gas accumulation, are becoming increasingly significant in oil shale studies. This paper aims to examine the formation mechanisms of various carbonate minerals in shale and their impact on oil enrichment. In the Dongying Depression, two predominant types of carbonate minerals have been identified: micritic carbonate and grain carbonate. Micritic carbonate primarily forms through biogenic processes, where alternating carbonate and clay mineral laminae result from the periodic stratification of lacustrine water bodies. These layers are relatively thin. Micritic carbonate rocks contain low organic matter and predominantly feature narrow slit-like pores, leading to a tight pore structure that hinders oil shale accumulation. In contrast, grain carbonate formation is governed by diagenetic processes. Influenced by deep fluids, these carbonate laminae are mainly composed of lens-shaped, coarsely crystalline calcite and exhibit significant thickness. Grain carbonate rocks have a relatively high organic matter content, with pore spaces primarily consisting of bottleneck- and slit-shaped throats. This configuration enhances reservoir capacity and creates favorable conditions for oil shale accumulation.