Search

Abstract Medical imaging is indispensable for accurate diagnosis and effective treatment, with modalities like MRI and CT providing diverse yet complementary information. Traditional image fusion methods, while essential in consolidating information from multiple modalities, often suffer from poor image quality and loss of crucial details due to inadequate handling of semantic information and limited feature extraction capabilities. This paper introduces a novel medical image fusion technique leveraging unsupervised image segmentation to enhance the semantic understanding of the fusion process. The proposed method, named DUSMIF, employs a multi-branch, multi-scale deep learning architecture that integrates advanced attention mechanisms to refine the feature extraction and fusion processes. An innovative approach that utilizes unsupervised image segmentation to extract semantic information is introduced, which is then integrated into the fusion process. This not only enhances the semantic relevance of the fused images but also improves the overall fusion quality. The paper proposes a sophisticated network structure that extracts and fuses features at multiple scales and across multiple branches. This structure is designed to capture a comprehensive range of image details and contextual information, significantly improving the fusion outcomes. Multiple attention mechanisms are incorporated to selectively emphasize important features and integrate them effectively across different modalities and scales. This approach ensures that the fused images maintain high quality and detail fidelity. A joint loss function combining content loss, structural similarity loss, and semantic loss is formulated. This function not only guides the network in preserving image brightness and texture but also ensures that the fused image closely resembles the source images in both content and structure. The proposed method demonstrates superior performance over existing fusion techniques in objective assessments and subjective evaluations, confirming its effectiveness in enhancing the diagnostic utility of fused medical images.

ABSTRACT: Meat qualities of free-range chicken (Xuan-Zhou) (XZ-FRC) are closely associated with slaughter age and directly influence the economic benefits of supplier and consumer's preference. Understanding of the relationship between meat qualities and ages will be of prime important to explore a better slaughter age of XZ-FRC. In this study, the quality traits of breast and thigh muscles from XZ-FRCs at 9 to 14 wk were analyzed to establish a relatively reliable method for selecting a better slaughter age. The results showed that the effects of slaughter ages on color (CIE L*, a* and b* values), shear force, centrifugal loss, and flavor of XZ-FRCs were significant (P < 0.05). There were greater differences in meat qualities, whatever breast or thigh muscles, between same or different ages. Eleven feature indexes used for colligation evaluation of slaughter age were selected by combining the quality characteristics and data analysis. The score of colligation evaluation for XZ-FRCs at 12 wk was higher than that at 9 and 14 wk, suggesting that the 12 wk was an optimal slaughter age. This work would provide a reference method that helps the producers of livestock and poultry to select a better slaughter age.

Purpose: To explore the utility of high frequency oscillations (HFO) and long-range temporal correlations (LRTCs) in preoperative assessment of epilepsy. Methods: MEG ripples were detected in 59 drug-resistant epilepsy patients, comprising 5 with parietal lobe epilepsy (PLE), 21 with frontal lobe epilepsy (FLE), 14 with lateral temporal lobe epilepsy (LTLE), and 19 with mesial temporal lobe epilepsy (MTLE) to identify the epileptogenic zone (EZ). The results were compared with clinical MEG reports and resection area. Subsequently, LRTCs were quantified at the source-level by detrended fluctuation analysis (DFA) and life/waiting -time at 5 bands for 90 cerebral cortex regions. The brain regions with larger DFA exponents and standardized life-waiting biomarkers were compared with the resection results. Results: Compared to MEG sensor-level data, ripple sources were more frequently localized within the resection area. Moreover, source-level analysis revealed a higher proportion of DFA exponents and life-waiting biomarkers with relatively higher rankings, primarily distributed within the resection area (p

In optimal control, it is often necessary to solve Hamilton-Jacobi-Isaacs (HJI) partial differential equation, but it is not only difficult to solve, sometimes even impossible to solve. It is possible to avoid solving the HJI equation by using inverse optimal methods. We investigate inverse optimality of regulation design for Korteweg-de Vries-Burgers (KdVB) equation. Two kinds of boundary control laws are achieved to regulate the state of closed-loop system to the set point from any initial value. In order to regulate the convergent speed of the closed-loop system, one or two parameters are designed in the boundary control laws. We proved that boundary control laws are optimal for two meaningful functionals, respectively. The effectiveness of the proposed design has been shown through simulations, and the convergence speed of the closed-loop system accelerates with increase of adjustable parameters.

Super-resolution reconstruction technology is a crucial approach to enhance the quality of remote sensing optical images. Currently, the mainstream reconstruction methods leverage convolutional neural networks (CNNs). However, they overlook the global information of the images, thereby impacting the reconstruction effectiveness. Methods based on Transformer networks have demonstrated the capability to improve reconstruction quality, but the high model complexity renders them unsuitable for remote sensing devices. To enhance reconstruction performance while maintaining the model lightweight, a distillation Transform-CNN Network is proposed in this article. The strategy employs the Transformer network as a teacher network, guiding its long-range features into a compact CNN, achieving distillation across networks. Simultaneously, to rectify misinformation in the teacher network, prior information is introduced to ensure accurate information transfer. Concerning the student network, a novel upsampling approach is devised, utilizing inherent information in downsampled feature maps for padding, thereby avoiding the introduction of zero-information feature points in the traditional deconvolution process. Experimental evaluations conducted on multiple publicly available remote sensing image datasets demonstrate that the proposed method, while maintaining a smaller parameter count, achieves outstanding reconstruction quality for remote sensing images, surpassing existing approaches.

With the establishment of smart grids, there is a growing demand for metering electric meters in urban areas. Given the diverse sizes and delicate nature of these meters, traditional scheduling solutions are unable to cater to the multifaceted requirements of urban environments, meters loading, and subsequent logistics scheduling. This study presents an intelligent scheduling model for electric meters in an urban context, taking into account various constraints such as urban traffic congestion, three-dimensional packing of metering devices, delivery time windows, and heterogeneous vehicles. To solve this, we design an improved whale optimization algorithm using a hybrid multi-phase heuristic approach (IWOA-HMOHA). Simulation results show that compared with the traditional meter logistics scheduling strategy, the IWOA-HMOHA algorithm reduces the objective function by 5.4%~ 26.1% compared with other similar algorithms. In addition, compared with the traditional first-in-last-out cargo packing method, the vehicle space utilization rate is improved by 12.62%. The proposed models and algorithms demonstrate excellent adaptability to a range of urban constraints, offering valuable insights and a robust framework essential for the development of logistics solutions in urban.

In order to accurately predict the power consumption data of charging piles, assist related enterprises to accurately predict the benefits of charging piles and further optimize the relationship between households and transformers, this paper proposes an improved Gate Recurrent Unit (IGRU) prediction model based on spline interpolation. This method first extracts relevant data features based on Pearson correlation analysis, and then fuses feature data and performs spline interpolation input prediction network model for charging pile load pre-diction. Finally, based on the power consumption data of 174 charging piles in the jurisdiction of a provincial capital city in southwest China, the prediction accuracy of the model is verified. Through case analysis and experimental comparison, it shows that the improve gate recurrent unit (IGRU) prediction model designed in this paper is superior to the traditional deep learning prediction model in terms of stability, prediction accuracy and generalization ability.

In this work, the frequency dependence of ferroelectric and electrocaloric properties in barium titanate-based ceramics was studied based on Maxwell relations. It is found that the maximum and remnant polarization will decrease while the coercive field increases a lot with rising frequency from 0.1 to 10[Formula: see text]Hz, indicating that polarization rotation and domain switching become difficult at high frequencies. The electrocaloric properties show the different frequency dependence at different phase structures. Isothermal entropy change ([Formula: see text]) and adiabatic temperature change ([Formula: see text]) are similar around/above Curie temperature ([Formula: see text], showing tiny frequency dependence. However, [Formula: see text] and [Formula: see text] display the obvious frequency dependence below [Formula: see text], especially in the orthorhombic–tetragonal phase-transition region with a stable ferroelectric phase, and this frequency dependence becomes more obvious under a low-electric field. It is also found that increasing the frequency can weaken the electric field dependence of electrocaloric strength. This work gives a general profile of frequency dependence for electrocaloric properties in ferroelectric ceramics.

A phase-locked loop (PLL) of a phase-shifting power supply for the power system is designed in this paper. Taking the industrial frequency current as the reference signal, the input and output characteristics of the phase-frequency detector with charge pump are analyzed. In addition, the transfer function of the PLL system is analyzed by combining the passive second-order low-pass filter and the voltage-controlled oscillator. As a result, the influence of parameters such as charge pump current, phase margin, and loop bandwidth on the performance of the PLL is investigated, and the optimal parameters of each section are obtained. The results show that the optimized PLL has a locking time of 0.75 s, a pull-out range of 63.16 Hz, and a locking range of 43.82 Hz, with high stability and noise immunity.

BackgroundMechanical thrombectomy (MT) is one of the effective treatment methods for acute ischemic stroke (AIS), which requires a period of dual antiplatelet therapy (DAPT) after endovascular treatment. This study aimed to compare the efficacy and safety of 3-month DAPT and 1-month DAPT in AIS patients receiving MT through a retrospective study.MethodsAIS patients who received MT from May 2018 to March 2023 were grouped into a 1-month group (1-M group) and a 3-month group (3-M group) according to the duration of DAPT after MT. The primary outcome was the mRS score at 90 days. Secondary outcomes included a good prognosis (mRS score of 0–2) at 90 days post-surgery, 6-month mortality, recurrence of cerebral infarction, Barthel's index, Montreal Cognitive Assessment (MoCA) score, and incidence of symptomatic intracranial hemorrhage (sICH) during hospitalization.ResultA total of 147 patients with AIS were included in the final analysis, with 78 patients in the 1-M group and 69 patients in the 3-M group. The baseline and neurological characteristics were comparable between both groups. At 3-month follow-up, a total of 61 patients had an mRS of 0–2 at 90 days, with an average mRS of 3.3 ± 0.9 for all patients. There was no statistically significant difference in the mRS between the two groups of patients at 90 days (P > 0.05). There was no statistically significant difference in the mortality rate and incidence of sICH between the two groups of patients during the 6-month follow-up period (P > 0.05), but the recurrence rate of AIS in the 3-M group was lower than that in the 1-M group (P < 0.05). The improvement of Barthel index and MoCA in patients in the 3-M group was higher than those in the 1-M group at 6 months but not statistically different (P > 0.05).ConclusionFor AIS patients undergoing mechanical thrombectomy, compared to 1-month DAPT, 3-month DAPT can reduce the recurrence rate of IS during a 6-month follow-up period, without increasing the mortality and risk of cerebral hemorrhage.

Abstract Perovskite-type lead-free piezoelectric ceramics allow access to illustrious piezoelectric coefficients (d 33) through intricate composition design and experimental modulation. Developing a swift and accurate technology for identifying (K, Na)NbO3 (KNN)-based ceramic compositions with high d 33 in exceedingly large “compositional” space will establish an innovative research paradigm surpassing the traditional empirical trial-and-error method. Herein, we demonstrate an interpretable machine learning (ML) framework for quick evaluation of KNN-based ceramics with high d 33 based on data from published literature. Specifically, a thorough feature construction was carried out from the global and local dimensions to establish tree regression models with d 33 as the target property. Subsequently, the feature-property mapping rules of KNN-based piezoelectric ceramics are further optimized through feature screening. To intuitively understand the correlation mechanisms between ML regression targets and features, the sure independence screening and sparsifying operator (SISSO) method was employed to extract the essential descriptors to explain d 33. A straightforward descriptor, $${\text{e}}^{({{NM}}_{\text{B}}-{{MV}}_{\text{B}})}\cdot {ST}/{(I{D}_{\text{A}})}^{2}$$ e ( NM B − MV B ) ⋅ ST / ( I D A ) 2 , consisting of only four easily accessible parameters, can accelerate the evaluation of a series of novel KNN-based ceramics with high d 33 while exhibiting strong theoretical interpretability. This work not only provides a tool for the rapid discovery of high piezoelectric performance in KNN-based ceramics but also offers a data-driven route for the design of property descriptors in perovskites.

Accurate and timely information on urban vegetation (UV) can be used as an important indicator to estimate the health of cities. Due to the low cost of RGB cameras, true color imagery (TCI) has been widely used for high spatial resolution UV mapping. However, the current index-based and classifier-based UV mapping approaches face problems of the poor ability to accurately distinguish UV and the high reliance on massive annotated samples, respectively. To address this issue, an index-guided semantic segmentation (IGSS) framework is proposed in this paper. Firstly, a novel cross-scale vegetation index (CSVI) is calculated by the combination of TCI and Sentinel-2 images, and the index value can be used to provide an initial UV map. Secondly, reliable UV and non-UV samples are automatically generated for training the semantic segmentation model, and then the refined UV map can be produced. The experimental results show that the proposed CSVI outperformed the existing five RGB vegetation indices in highlighting UV cover and suppressing complex backgrounds, and the proposed IGSS workflow achieved satisfactory results with an OA of 87.72% ∼ 88.16% and an F1 score of 87.73% ∼ 88.37%, which is comparable with the fully-supervised method.

Abstract Structural superlubricity, a state of nearly zero friction and no wear between two contact surfaces under relative sliding, holds immense potential for research and application prospects in micro-electro-mechanical systems devices, mechanical engineering, and energy resources. A critical step towards the practical application of structural superlubricity is the mass transfer and high throughput performance evaluation. Limited by the yield rate of material preparation, existing automated systems, such as roll printing or massive stamping, are inadequate for this task. In this paper, a machine learning-assisted system is proposed to realize fully automated selective transfer and tribological performance measurement for structural superlubricity materials. Specifically, the system has a judgment accuracy of over 98% for the selection of micro-scale graphite flakes with structural superlubricity properties and complete the 100 graphite flakes assembly array to form various pre-designed patterns within 100 mins, which is 15 times faster than manual operation. Besides, the system is capable of automatically measuring the tribological performance of over 100 selected flakes on Si3N4, delivering statistical results for new interface which is beyond the reach of traditional methods. With its high accuracy, efficiency, and robustness, this machine learning-assisted system promotes the fundamental research and practical application of structural superlubricity.

As industrial technology continues to advance through integration, society's demand for electricity is rapidly increasing. To meet the requirements of refined grid management and address the elevated challenges arising from the increased electrical load, this paper delves into the investigation of distribution vehicle scheduling for the practical scenario of batch rotation of smart meters. Initially, based on the practical distribution task requirements of a provincial metrology verification center, a multi-level optimization model is constructed for the batch rotation and distribution vehicle scheduling of smart meters. The primary objective is to maximize the enhancement of smart meter distribution efficiency while minimizing the overall distribution cost. Moreover, this paper introduces a refined Grey Wolf Optimization algorithm (OLC-GWO) based on Opposition-based Learning, Levy flight strategy, and Cauchy mutation to solve the model. By generating an opposite population to improve the quality of initial feasible solutions and further harnessing the global search capabilities of Levy flight and Cauchy mutation operators, the algorithm's effectiveness is enhanced. The algorithm is subjected to testing using multiple benchmark functions and its performance is compared with variants of GWO, as well as several cutting-edge intelligent optimization algorithms including Particle Swarm Optimization (PSO), Harris Hawks Optimization (HHO), and Honey Bee Algorithm (HBA). The results indicate that OLC-GWO exhibits excellent performance in terms of convergence speed and optimization capability. Finally, the improved algorithm is subjected to simulation experiments by incorporating order data from the practical distribution operations of a provincial metrology verification center. The outcomes verify the efficiency of the proposed algorithm, reinforcing the practical significance of the established model in addressing the real-world challenge of batch rotation and distribution vehicle scheduling for smart meters.

AIGC is currently a hot field and a future trend in AI applications, and addressing the challenge of digitally reconstructing cultural heritage under the influence of AI technology is a pressing issue that requires immediate resolution. The article proposes an application framework for AIGC technology that is based on refining its meaning and designing a specific process for applying it to the digital reconstruction of cultural heritage. A high-definition camera is used to acquire relevant images of cultural heritage. The image features are extracted by the SIFT algorithm optimized by the PROSAC algorithm. The color features are acquired by combining the color histogram, color moment, and color correlation diagram. The 3D laser scanning technology is used to obtain the 3D point cloud data of the cultural heritage; the KD-tree improved ICP algorithm is introduced to improve the efficiency of point cloud alignment; the dense reconstruction of the 3D point cloud data of the cultural heritage is realized based on CMVS/PMVS; and the immersive 3D experience system of the cultural heritage is constructed by combining with platforms such as Unity3D. The average matching rate of the optimized SITF algorithm to the image features of cultural heritage is about 74.91%, and the maximum alignment time of the ICP algorithm to the cultural heritage point cloud data based on KD-tree is 9.241 s. The cultural heritage immersive 3D experience system has a satisfaction rate of 56.75%, and the density reconstructed model’s surface has an average deviation of only 0.34 mm from the real surface. The user satisfaction rating for the immersive 3D experience system for cultural heritage is 56.75%. Based on AIGC technology, it can revitalize cultural heritage and achieve digital reconstruction and inheritance innovation of cultural heritage.

It is essential for realizing the most suitable product buffer packaging design to quantify the vibration transmission characteristics of the product packaging system. The experiment system for the vibration transmission path of protective packaging is designed in this paper. The practical system is used to analyze the vibration transfer path of the product packaging system and identify the critical transfer path. The concepts of the cushions’ contribution rate and the cushions’ weighted contribution rate are introduced. The product cushioning based on the weighted equal contribution rate of the cushions is proposed. It has been verified by experiments that the system can accurately identify the transfer path with the weighted contribution rate of the cushions as a reference for the design of product buffer packaging, which improves the utilization rate of buffer packaging materials and reduces the cost of packaging materials. The weighted equal contribution rates of buffer pads 1, 2, 3, and 4 are 40%, 27%, 22%, and 11%, respectively. For the needs of experiment teaching, the teaching content based on the protective packaging transfer path testing system is designed, which provides a reference for the practical education of the packaging specialty.

Abstract As one of the most promising alternatives to graphite negative electrodes, silicon oxide (SiO x ) has been hindered by its fast capacity fading. Solid electrolyte interphase (SEI) aging on silicon SiO x has been recognized as the most critical yet least understood facet. Herein, leveraging 3D focused ion beam-scanning electron microscopy (FIB-SEM) tomographic imaging, we reveal an exceptionally characteristic SEI microstructure with an incompact inner region and a dense outer region, which overturns the prevailing belief that SEIs are homogeneous structure and reveals the SEI evolution process. Through combining nanoprobe and electron energy loss spectroscopy (EELS), it is also discovered that the electronic conductivity of thick SEI relies on the percolation network within composed of conductive agents (e.g., carbon black particles), which are embedded into the SEI upon its growth. Therefore, the free growth of SEI will gradually attenuate this electron percolation network, thereby causing capacity decay of SiO x . Based on these findings, a proof-of-concept strategy is adopted to mechanically restrict the SEI growth via applying a confining layer on top of the electrode. Through shedding light on the fundamental understanding of SEI aging for SiO x anodes, this work could potentially inspire viable improving strategies in the future.

[Introduction] With the rapid development of AC/DC distribution networks and distributed generation technology, the role of DC microgrids in distribution networks is becoming increasingly important and will become an important component of future distribution networks. Due to the small coverage area and low line impedance of the DC microgrid, when an inter pole short circuit fault occurs, the fault current increases rapidly and has a large amplitude, which can reach more than 10 times the rated working current. This makes it difficult to set the protection of DC microgrids and requires high equipment selection, which restricts the rapid development of DC microgrids. [Method] In response to the above issues, taking the DC microgrid as the research object, starting from the working principle of inter pole faults in the DC microgrid, the fault characteristics on the DC side of the DC microgrid were analyzed. In response to the shortcomings of existing main current limiting methods, a voltage controllable fault current controller was proposed to achieve precise control of fault current. The simulation model of DC microgrid and fault current controller was built for simulation verification. [Result] The simulation results show that the fault current controller can significantly reduce the fault current and achieve precise control of the fault current, making the system controllable before and after the fault without locking the protection. During steady-state operation, the fault current controller can also assist the VSC (Voltage Source Converter) in further stabilizing the DC bus voltage. [Conclusion] To cooperate with the normal operation of the relay protection device and avoid VSC triggering overcurrent protection blocking, it is recommended to set the fault current control range between 1~2 pu.

Abstract The incidence of rheumatoid arthritis (RA) is increasing with age. DNA fragments is known to accumulate in certain autoimmune diseases, but the mechanistic relationship among ageing, DNA fragments and RA pathogenesis remain unexplored. Here we show that the accumulation of DNA fragments, increasing with age and regulated by the exonuclease TREX1, promotes abnormal activation of the immune system in an adjuvant‐induced arthritis (AIA) rat model. Local overexpression of TREX1 suppresses synovial inflammation in rats, while conditional genomic deletion of TREX1 in AIA rats result in higher levels of circulating free (cf) DNA and hence abnormal immune activation, leading to more severe symptoms. The dysregulation of the heterodimeric transcription factor AP-1, formed by c-Jun and c-Fos, appear to regulate both TREX1 expression and SASP induction. Thus, our results confirm that DNA fragments are inflammatory mediators, and TREX1, downstream of AP-1, may serve as regulator of cellular immunity in health and in RA.

The project of China initiative Accelerator Driven Subcritical (CiADS) system has been started to construct in southeast China's Guangdong province since 2019, which is expected to be checked and accepted in the year 2025. In order to make the students in University of Chinese Academy of Sciences (UCAS) better understand the main characteristic and the operation condition in the subcritical nuclear facility, the training platform for CiADS has been developed based on the Cave Automatic Virtual Environment (CAVE) in the Institute of Modern Physics Chinese Academy of Sciences (IMPCAS). The CAVE platform is a kind of non-head mounted virtual reality display system, which can provide the immersive experience and the alternative training platform to substitute the dangerous operation experiments with strong radioactivity. In this paper, the CAVE platform for the training scenarios in CiADS system has been presented with real-time simulation feature, where the required devices to generate the auditory and visual senses with the interactive mode have been detailed. Moreover, the three dimensional modeling database has been created for the different operation conditions, which can bring more freedom for the teachers to generate the appropriate training courses for the students. All the user-friendly features will offer a deep realistic impression to the students for the purpose of getting the required knowledge and experience without the large costs in the traditional experimental nuclear reactor.

The number of failures serves as a critical indicator that dynamically impacts the reliability of self-announcing failure products, making it highly practical to incorporate the failure count into reliability management throughout the entire product life cycle. This paper investigates comprehensive methodologies for effectively managing the reliability of self-announcing failure products throughout both the warranty and post-warranty stages, taking into account factors such as the failure count, mission cycles, and limited time duration. Three renewable warranty strategies are introduced alongside proposed models for post-warranty replacements. By analyzing variables like the failure number, mission cycles, and time constraints, these proposed warranties provide practical frameworks for efficient reliability management during the warranty stage. Additionally, the introduced warranties utilize cost and time metrics to extract valuable insights that inform decision making and enable effective reliability management during the warranty stage. Moreover, this study establishes cost and time metrics for key post-warranty replacements, facilitating the development of individual cost rates and model applications in other post-warranty scenarios. Analyses of the renewable free-repair–replacement warranties demonstrate that establishing an appropriate number of failures as the replacement threshold can effectively reduce warranty-servicing costs and extend the coverage duration.

The results of resistance characteristics in different grains during ventilation experiments showed that the resistance of unit grain layer was positively correlated with the surface wind speed of grain, and the polynomial quadratic function had the higher fitting degree for them. When the surface wind speed of grain was at the same level, the resistance of unit grain layer in soybean was lower, followed by corn but that of rice and wheat was higher, indicating that the resistance of unit grain layer was related to grain structure、surface smoothness and porosity. The resistance of net was positively correlated with the surface wind speed of grain, with the increase of surface wind speed and the resistance of net during ventilation process. The resistance of net could increase sharply when the surface wind speed increased to a certain extent. In order to avoid the waste of energies, the large volume shouldn’t choose blindly during the process of ventilation. The ventilation uniformity of grain increased gradually with the increase of the grain layer thickness, which was less affected by the ventilation volume when the ventilation uniformity of different grains was compared, rice was lower, follow by wheat, and soybean and corn was higher, which was related to grain shape and stacking structure.