Enhancing Global Estimation of Fine Particulate Matter Concentrations by Including Geophysical a Priori Information in Deep Learning.

Global fine particulate matter (PM2.5) assessment is impeded by a paucity of monitors. We improve estimation of the global distribution of PM2.5 concentrations by developing, optimizing, and applying a convolutional neural network with information from satellite-, simulation-, and monitor-based sources to predict the local bias in monthly geophysical a priori PM2.5 concentrations over 1998-2019. We develop a loss function that incorporates geophysical a priori estimates and apply it in model training to address the unrealistic results produced by mean-square-error loss functions in regions with few monitors. We introduce novel spatial cross-validation for air quality to examine the importance of considering spatial properties. We address the sharp decline in deep learning model performance in regions distant from monitors by incorporating the geophysical a priori PM2.5. The resultant monthly PM2.5 estimates are highly consistent with spatial cross-validation PM2.5 concentrations from monitors globally and regionally. We withheld 10% to 99% of monitors for testing to evaluate the sensitivity and robustness of model performance to the density of ground-based monitors. The model incorporating the geophysical a priori PM2.5 concentrations remains highly consistent with observations globally even under extreme conditions (e.g., 1% for training, R2 = 0.73), while the model without exhibits weaker performance (1% for training, R2 = 0.51).

Macrophage membrane-coated nanoparticles for the treatment of infectious diseases.

Infectious diseases threaten human health severely, and traditional treatment techniques face multiple limitations. Macrophages as the important component of immune cells, display the unique biological properties, such as biocompatibility, immunocompatibility, targeting specificity, and immunoregulatory activity, and play a critical role in protecting the body against infections. The macrophage membrane-coated nanoparticles not only maintain the functions of the inner nanoparticles, but also inherit the characteristics of macrophages, making them excellent tools for improvement of drug delivery and therapeutic implications in infectious diseases (IDs). In this review, we describe the characteristics and functions of macrophage membrane-coated nanoparticles and their advantages and challenges in ID therapy. We first summarize the pathological features of IDs, providing enlightenment on how to fight against them. Next, we focus on the classification, characteristics, and preparation of macrophage membrane-coated nanoparticles. Finally, we comprehensively describe the progress of macrophage membrane-coated nanoparticles in combating IDs, including drug delivery, inhibition and killing of pathogens, and immune modulation. In the end of this review, a look forward to the challenges of this aspect is presented.

Comparison between intramedullary nail and conventional plate for displaced intra-articular calcaneal fractures: A meta-analysis.

OBJECTIVES: This study aimed to compare the efficacy and safety of the intramedullary nail and conventional plate for the treatment of displaced intra-articular calcaneal fractures from clinical comparative trials. MATERIALS AND METHODS: A comprehensive search of English databases was carried out in the Springer, PubMed, ScienceDirect, Web of Science, and Cochrane Library databases until September 2023. Studies on calcaneal fractures treated by an intramedullary nail or a plate were considered for inclusion. Endpoints included duration of operation, length of hospital stay, the Visual Analog Scale (VAS) score, postoperative functional score, radiological parameters, and complications. The mean difference (MD) and risk difference (RD) as the combined variables, as well as the 95% confidence intervals, (CIs) were calculated. RESULTS: Five retrospective controlled studies covering 473 feet at the one-year follow-up met the inclusion criteria. The meta-analysis demonstrated that there were significant differences in the duration of operation (MD: -10.81; 95% CI: -16.32, -5.31; p=0.0001), length of hospital stay (MD: -3.65; 95% CI: -4.35, -2.95; p<0.00001). No significant differences were found regarding postoperative American Orthopaedic Foot and Ankle Society (AOFAS) Ankle-Hindfoot Scale (MD: 0.36; 95% CI: -3.89, 4.61; p=0.87), VAS (MD: 1.95; 95% CI: -0.30, 4.21; p=0.09), or postoperative Böhler angle (MD: 0.94; 95% CI: -0.04, 1.92; p=0.06) between the two groups. The incidence of total complications (RD: -0.31; 95% CI: -0.46, -0.17; p<0.0001) and wound-healing complications (RD: -0.16; 95% CI: -0.30, -0.03; p=0.02) were lower in the intramedullary nail group. There were no significant differences in the incidences of revision surgery, implant removal, superficial wound infection, deep infection, and nonunion. CONCLUSION: Compared to conventional plates, the intramedullary nail showed a shorter duration of operation, reduced length of hospital stay, and fewer postoperative total complications and wound-healing complications in treating displaced intra-articular calcaneal fractures.

Integrated and DC-powered superconducting microcomb.

Frequency combs, specialized laser sources emitting multiple equidistant frequency lines, have revolutionized science and technology with unprecedented precision and versatility. Recently, integrated frequency combs are emerging as scalable solutions for on-chip photonics. Here, we demonstrate a fully integrated superconducting microcomb that is easy to manufacture, simple to operate, and consumes ultra-low power. Our turnkey apparatus comprises a basic nonlinear superconducting device, a Josephson junction, directly coupled to a superconducting microstrip resonator. We showcase coherent comb generation through self-started mode-locking. Therefore, comb emission is initiated solely by activating a DC bias source, with power consumption as low as tens of picowatts. The resulting comb spectrum resides in the microwave domain and spans multiple octaves. The linewidths of all comb lines can be narrowed down to 1 Hz through a unique coherent injection-locking technique. Our work represents a critical step towards fully integrated microwave photonics and offers the potential for integrated quantum processors.

Study on the secondary oxidation behavior and microscopic characteristics of oxidized coal gangue.

Spontaneous combustion of coal gangue (CG) hills has caused varieties of secondary disasters that seriously endanger the ecological environment of the world. The emission law of index gases and their oxidation kinetics during the secondary oxidation process of CG with different ranks of oxidation were studied by using the temperature programmed device and online mass spectrometer (MS). Fourier transform infrared spectroscopy (FTIR) was used to reveal the changes of the CG internal active functional groups. The results showed that the energy required for the combustion of CG with low rank of pre-oxidation was significantly lower than that of the raw sample. However, as the oxidation rank increased, due to amounts of volatile components were released in the process of oxidation reaction, the CG in the combustion process of the emission of index gases and its oxygen consumption rate gradually reduced; the rapid oxidation stage shifted to the direction of the high temperature. In this study, the risk of spontaneous combustion of CG after oxidation at 80 â„ƒ under 3% oxygen concentration was the strongest. The results of this paper are of great guiding significance for exploring the spontaneous combustion characteristics of CG hills and their prevention by traditional covering method.

[Spectral Characteristics and Sources of Dissolved Organic Matter in Inflow Rivers of Baiyangdian Lake Water in Summer Flood Season].

DOM is the largest reservoir of organic carbon in the world, and it plays a crucial role in the biogeochemical cycles of natural water bodies. A river is a transition area connecting source water and receiving water that controls the DOM exchange between them. Therefore, in this study, ultraviolet visible spectroscopy (UV-vis) and three-dimensional fluorescence spectroscopy (EEMs) combined with parallel factor analysis (PARAFAC) were used to analyze the spectral characteristics and sources of dissolved organic matter in the Fuhe River, Xiaobai River, Baigouyin River, and Puhe River of Baiyangdian. The results showed that a245 and a355 in the Fuhe River and Xiaobai River were significantly higher than those in the Baigouyin River and Puhe River. E2/E3 showed that the DOM relative molecular mass of the inflow river water body was Puhe River > Baigouyin River > Fuhe River > Xiaobai River. Three components, tyrosine-like (C1), terrigenous humus (C2), and tryptophan-like (C3), were determined using three-dimensional fluorescence through PARAFAC. There was no difference among the fluorescence components (P>0.05), but there were differences among the C2 and C3 components (P<0.05). The proportion of easily degradable protein-like components (C1+C3) was higher than that of humus-like components (C2). The autogeny index BIX was greater than 1, and the humification index HIX was less than 4, indicating that the autogeny characteristics of the river bodies were obvious, and the humification degree was weak. The FI index was the highest (1.96±0.25), and the HIX index was the lowest (0.46±0.08), and the self-generated source characteristics gradually strengthened along the direction of the river entering the lake, indicating that the water body of the Fuhe River showed higher endogenous and autogenic characteristics. Based on the correlation analysis of fluorescence components and characteristic parameters of DOM, the correlations between the Fuhe River and Xiaobaihe River and between the Baigouyin River and Puhe River bodies were similar. The correlation between fluorescence components of DOM and water quality parameters of each lake was significantly different, and it was strongly correlated with nitrogen and phosphorus in water. According to multiple linear regression analysis, there was no significant difference among C1 components, but there was a significant difference between C2 and C3 components. In summary, the carbon cycle process of Baiyangdian Lake was further understood through the study on the DOM spectral characteristics and sources of the inflow river waters in the summer flood season.

A dynamic prediction model of landslide displacement based on VMD-SSO-LSTM approach.

Addressing the limitations of existing landslide displacement prediction models in capturing the dynamic characteristics of data changes, this study introduces a novel dynamic displacement prediction model for landslides. The proposed method combines Variational Mode Decomposition (VMD) with Sparrow Search Optimization (SSO) and Long Short-Term Memory (LSTM) techniques to formulate a comprehensive VMD-SSO-LSTM model. Through the application of VMD, the method dissects cumulative displacement and rainfall data, thereby extracting distinct components such as trend, periodicity, and fluctuation components for displacement, as well as low-frequency and high-frequency components for rainfall. Furthermore, leveraging Gray Correlational Analysis, the interrelationships between the periodic component of displacement and the low-frequency component of rainfall, as well as the fluctuation component of displacement and the high-frequency component of rainfall, are established. Building upon this foundation, the SSO-LSTM model dynamically predicts the interrelated displacement components, synthesizing the predicted values of each component to generate real-time dynamic forecasts. Simulation results underscore the effectiveness of the proposed VMD-SSO-LSTM model, indicating root-mean-square error (RMSE) and mean absolute percentage error (MAPE) values of 1.2329 mm and 0.1624%, respectively, along with a goodness of fit (R2) of 0.9969. In comparison to both back propagation (BP) prediction model and LSTM prediction model, the VMD-SSO-LSTM model exhibits heightened predictive accuracy.

Dynamic Bayesian network structure learning based on an improved bacterial foraging optimization algorithm.

With the rapid development of artificial intelligence and data science, Dynamic Bayesian Network (DBN), as an effective probabilistic graphical model, has been widely used in many engineering fields. And swarm intelligence algorithm is an optimization algorithm based on natural selection with the characteristics of distributed, self-organization and robustness. By applying the high-performance swarm intelligence algorithm to DBN structure learning, we can fully utilize the algorithm's global search capability to effectively process time-based data, improve the efficiency of network generation and the accuracy of network structure. This study proposes an improved bacterial foraging optimization algorithm (IBFO-A) to solve the problems of random step size, limited group communication, and the inability to maintain a balance between global and local searching. The IBFO-A algorithm framework comprises four layers. First, population initialization is achieved using a logistics-sine chaotic mapping strategy as the basis for global optimization. Second, the activity strategy of a colony foraging trend is constructed by combining the exploration phase of the Osprey optimization algorithm. Subsequently, the strategy of bacterial colony propagation is improved using a "genetic" approach and the Multi-point crossover operator. Finally, the elimination-dispersal activity strategy is employed to escape the local optimal solution. To solve the problem of complex DBN learning structures due to the introduction of time information, a DBN structure learning method called IBFO-D, which is based on the IBFO-A algorithm framework, is proposed. IBFO-D determines the edge direction of the structure by combining the dynamic K2 scoring function, the designed V-structure orientation rule, and the trend activity strategy. Then, according to the improved reproductive activity strategy, the concept of "survival of the fittest" is applied to the network candidate solution while maintaining species diversity. Finally, the global optimal network structure with the highest score is obtained based on the elimination-dispersal activity strategy. Multiple tests and comparison experiments were conducted on 10 sets of benchmark test functions, two non-temporal and temporal data types, and six data samples of two benchmark 2T-BN networks to evaluate and analyze the optimization performance and structure learning ability of the proposed algorithm under various data types. The experimental results demonstrated that IBFO-A exhibits good convergence, stability, and accuracy, whereas IBFO-D is an effective approach for learning DBN structures from data and has practical value for engineering applications.

Delaying the First Nucleation Event of Amorphous Solid Dispersions Above the Polymer Overlap Concentration (c*): PVP and PVPVA in Posaconazole.

A thorough understanding of effects of polymers on crystallization of amorphous drugs is essential for rational design of robust amorphous solid dispersion (ASD), since crystallization of the amorphous drug negates their solubility advantage. In this work, we measured the first nucleation time (t0, time to form the first critical nucleus in fresh liquid/glass) in posaconazole (POS)/polyvinylpyrrolidone vinyl acetate (PVPVA) and POS/polyvinylpyrrolidone (PVP K25) ASDs and showed that the polymer overlap concentration (c*, concentration above which adjacent polymer chains begin to contact) is critical in controlling crystallization of ASDs. When polymer concentration c < c*, t0 of POS ASDs is approximately equal to that of the neat amorphous POS, but it increases significantly when c > c*. This observation supports the view that the effective inhibitory effect of crystallization in ASDs above c* is primarily correlated with delay in the first nucleation event. Our finding is useful in efficient polymer selection and performance prediction of high drug loaded ASD formulations.

Distortion Effect on the UHPC Box Girder with Vertical Webs: Theoretical Analysis and Case Study.

Distortion deformation usually imposes a potential threat to bridge safety. In order to comprehensively understand the distortion effect on thin-walled ultra-high performance concrete (UHPC) box girders, an innovative approach encompassing the governing distortion differential equation is introduced in this study based on the general definition of distortion angle within the cross-section plane. The analytical results obtained from the proposed method are in accordance with those obtained from the energy method, and exhibit favorable agreement with experimental findings documented in the existing literature. Furthermore, a finite element model is developed on the ANSYS 2021 R1 software platform with the employment of a Shell 63 element. Numerical outcomes are also in good agreement with the experimental data, affirming the validity and reliability of the findings. In addition, parameter analysis results indicate that the distortion angle remains approximately constant at a location approximately 1/10 of the span from the mid-span cross-section of the box girder, regardless of changes in the span-to-depth ratio. Increasing the web thickness yields a notable reduction in the distortion effects, and decreasing the wall thickness can effectively mitigate the distortion-induced transverse bending moment. Compared with normal-strength concrete box girders, UHPC box girders can reduce the distortion angle within the span range, which is beneficial for maintaining the overall stability of the box girders. The outcomes obtained from this study yield engineers an enhanced understanding of distortion effect on the UHPC girder performance.

A new insight into the mechanism of the tabletability flip phenomenon.

Tabletability is an outcome of interparticulate bonding area (BA) - bonding strength (BS) interplay, influenced by the mechanical properties, size and shape, surface energetics of the constituent particles, and compaction parameters. Typically, a more plastic active pharmaceutical ingredient (API) exhibits a better tabletability than less plastic APIs due to the formation of a larger BA during tablet compression. Thus, solid forms of an API with greater plasticity are traditionally preferred if other critical pharmaceutical properties are comparable. However, the tabletability flip phenomenon (TFP) suggests that a solid form of an API with poorer tabletability may exhibit better tabletability when formulated with plastic excipients. In this study, we propose another possible mechanism of TFP, wherein softer excipient particles conform to the shape of harder API particles during compaction, leading to a larger BA under certain pressures and, hence, better tabletability. In this scenario, the BA-BS interplay is dominated by BA. Accordingly, TFP should tend to occur when API solid forms are formulated with a soft excipient. We tested this hypothesis by visualizing the deformation of particles in a model compressed tablet by nondestructive micro-computed tomography and by optical microscopy when the particles were separated from the tablet. The results confirmed that soft particles wrapped around hard particles at their interfaces, while an approximately flat contact was formed between two adjacent soft particles. In addition to the direct visual evidence, the BA-dominating mechanism was also supported by the observation that TFP occurred in the p-aminobenzoic acid polymorph system only when mixed with a soft excipient.

Unconventional Superconducting Diode Effects via Antisymmetry and Antisymmetry Breaking.

Symmetry breaking plays a pivotal role in unlocking intriguing properties and functionalities in material systems. For example, the breaking of spatial and temporal symmetries leads to a fascinating phenomenon: the superconducting diode effect. However, generating and precisely controlling the superconducting diode effect pose significant challenges. Here, we take a novel route with the deliberate manipulation of magnetic charge potentials to realize unconventional superconducting flux-quantum diode effects. We achieve this through suitably tailored nanoengineered arrays of nanobar magnets on top of a superconducting thin film. We demonstrate the vital roles of inversion antisymmetry and its breaking in evoking unconventional superconducting effects, namely a magnetically symmetric diode effect and an odd-parity magnetotransport effect. These effects are nonvolatilely controllable through in situ magnetization switching of the nanobar magnets. Our findings promote the use of antisymmetry (breaking) for initiating unconventional superconducting properties, paving the way for exciting prospects and innovative functionalities in superconducting electronics.

Structural and functional abnormalities in the medial prefrontal cortex were associated with pain and depressive symptoms in patients with adhesive capsulitis.

Introduction: Chronic pain and depression have been shown to coexist in patients with adhesive capsulitis (AC). Recent studies identified the shared brain plasticity between pain and depression; however, how such neuroplasticity contributes to AC remains unclear. Here, we employed a combination of psychophysics, structural MRI, and functional MRI techniques to examine the brain's structural and functional changes in AC. Methods: Fifty-two patients with AC and 52 healthy controls (HCs) were included in our study. Voxelwise comparisons were performed to reveal the differences in grey matter volume (GMV) and regional homogeneity (ReHo) between AC and HCs. Furthermore, region of interest to whole brain functional connectivity (FC) was calculated and compared between the groups. Finally, Pearson correlation coefficients were computed to reveal the association between clinical data and brain alterations. Mediation analyses were performed to investigate the path association among brain alterations and clinical measures. Results: Three main findings were observed: (1) patients with AC exhibited a higher depression subscale of hospital anxiety and depression scale (HADS-D) score correlating with the GMV within the right medial prefrontal cortices (mPFC) compared with HCs; (2) relative to HCs, patients with AC exhibited lower ReHo within the right mPFC, which largely overlapped with the structural abnormalities; (3) the impact of pain duration on HADS-D score was mediated by ventral part of medial prefrontal cortices (vmPFC) GMV in patients with AC. Conclusion: In summary, our current findings suggest that vmPFC alterations correlate with both the pain duration and the emotional comorbidities experienced by patients with AC. Our research provides an enhanced comprehension of the underlying mechanisms of AC, thereby facilitating the development of more effective treatment approaches for AC.

A propensity score-integrated approach for leveraging external data in a randomized controlled trial with time-to-event endpoints.

In a randomized controlled trial with time-to-event endpoint, some commonly used statistical tests to test for various aspects of survival differences, such as survival probability at a fixed time point, survival function up to a specific time point, and restricted mean survival time, may not be directly applicable when external data are leveraged to augment an arm (or both arms) of an RCT. In this paper, we propose a propensity score-integrated approach to extend such tests when external data are leveraged. Simulation studies are conducted to evaluate the operating characteristics of three propensity score-integrated statistical tests, and an illustrative example is given to demonstrate how these proposed procedures can be implemented.

Stanniocalcin 2 governs cancer cell adaptation to nutrient insufficiency through alleviation of oxidative stress.

Solid tumours often endure nutrient insufficiency during progression. How tumour cells adapt to temporal and spatial nutrient insufficiency remains unclear. We previously identified STC2 as one of the most upregulated genes in cells exposed to nutrient insufficiency by transcriptome screening, indicating the potential of STC2 in cellular adaptation to nutrient insufficiency. However, the molecular mechanisms underlying STC2 induction by nutrient insufficiency and subsequent adaptation remain elusive. Here, we report that STC2 protein is dramatically increased and secreted into the culture media by Gln-/Glc-deprivation. STC2 promoter contains cis-elements that are activated by ATF4 and p65/RelA, two transcription factors activated by a variety of cellular stress. Biologically, STC2 induction and secretion promote cell survival but attenuate cell proliferation during nutrient insufficiency, thus switching the priority of cancer cells from proliferation to survival. Loss of STC2 impairs tumour growth by inducing both apoptosis and necrosis in mouse xenografts. Mechanistically, under nutrient insufficient conditions, cells have increased levels of reactive oxygen species (ROS), and lack of STC2 further elevates ROS levels that lead to increased apoptosis. RNA-Seq analyses reveal STC2 induction suppresses the expression of monoamine oxidase B (MAOB), a mitochondrial membrane enzyme that produces ROS. Moreover, a negative correlation between STC2 and MAOB levels is also identified in human tumour samples. Importantly, the administration of recombinant STC2 to the culture media effectively suppresses MAOB expression as well as apoptosis, suggesting STC2 functions in an autocrine/paracrine manner. Taken together, our findings indicate that nutrient insufficiency induces STC2 expression, which in turn governs the adaptation of cancer cells to nutrient insufficiency through the maintenance of redox homeostasis, highlighting the potential of STC2 as a therapeutic target for cancer treatment.

Entinostat, nivolumab and ipilimumab for women with advanced HER2-negative breast cancer: a phase Ib trial.

We report the results of 24 women, 50% (N = 12) with hormone receptor-positive breast cancer and 50% (N = 12) with advanced triple-negative breast cancer, treated with entinostat + nivolumab + ipilimumab from the dose escalation (N = 6) and expansion cohort (N = 18) of ETCTN-9844 ( NCT02453620 ). The primary endpoint was safety. Secondary endpoints were overall response rate, clinical benefit rate, progression-free survival and change in tumor CD8:FoxP3 ratio. There were no dose-limiting toxicities. Among evaluable participants (N = 20), the overall response rate was 25% (N = 5), with 40% (N = 4) in triple-negative breast cancer and 10% (N = 1) in hormone receptor-positive breast cancer. The clinical benefit rate was 40% (N = 8), and progression-free survival at 6 months was 50%. Exploratory analyses revealed that changes in myeloid cells may contribute to responses; however, no correlation was noted between changes in CD8:FoxP3 ratio, PD-L1 status and tumor mutational burden and response. These findings support further investigation of this treatment in a phase II trial.

Seamless Micro-Electro-Mechanical System-Inertial Navigation System/Polarization Compass Navigation Method with Data and Model Dual-Driven Approach.

The integration of micro-electro-mechanical system-inertial navigation systems (MEMS-INSs) with other autonomous navigation sensors, such as polarization compasses (PCs) and geomagnetic compasses, has been widely used to improve the navigation accuracy and reliability of vehicles in Internet of Things (IoT) applications. However, a MEMS-INS/PC integrated navigation system suffers from cumulative errors and time-varying measurement noise covariance in unknown, complex occlusion, and dynamic environments. To overcome these problems and improve the integrated navigation system's performance, a dual data- and model-driven MEMS-INS/PC seamless navigation method is proposed. This system uses a nonlinear autoregressive neural network (NARX) based on the Gauss-Newton Bayesian regularization training algorithm to model the relationship between the MEMS-INS outputs composed of the specific force and angular velocity data and the PC heading's angular increment, and to fit the integrated navigation system's dynamic characteristics, thus realizing data-driven operation. In the model-driven part, a nonlinear MEMS-INS/PC loosely coupled navigation model is established, the variational Bayesian method is used to estimate the time-varying measurement noise covariance, and the cubature Kalman filter method is then used to solve the nonlinear problem in the model. The robustness and effectiveness of the proposed method are verified experimentally. The experimental results show that the proposed method can provide high-precision heading information stably in complex, occluded, and dynamic environments.

Mitochondria-Associated Protein FgNdk1 Regulates the Development, Pathogenicity, and SDHI Fungicide Sensitivity of Fusarium graminearum by Interacting with Succinate Dehydrogenase.

Nucleoside diphosphate kinase (NDK) plays an important role in many cellular processes in all organisms. In this study, we functionally characterized a nucleoside diphosphate kinase (FgNdk1) in Fusarium graminearum, a causal agent of Fusarium head blight (FHB). FgNdk1 was involved in the generation of energy in the electron-transfer chain by interacting with succinate dehydrogenase (FgSdhA, FgSdhC1, and FgSdhC2). Deletion of FgNdk1 not only resulted in abnormal mitochondrial morphology, decreased ATP content, defective fungal development, and impairment in the formation of the toxisome but also led to the suppressed expression level of DON biosynthesis enzymes, decreased DON biosynthesis, and declined pathogenicity as well. Furthermore, deletion of FgNdk1 caused increasing transcriptional levels of FgSdhC1 and FgdhC2, in the presence of pydiflumetofen, related to the decreased sensitivity to SDHI fungicides. Overall, this study identified a new regulatory mechanism of FgNdk1 in the pathogenicity and SDHI fungicide sensitivity of Fusarium graminearum.

ASP: Learn a Universal Neural Solver!

Applying machine learning to combinatorial optimization problems has the potential to improve both efficiency and accuracy. However, existing learning-based solvers often struggle with generalization when faced with changes in problem distributions and scales. In this paper, we propose a new approach called ASP: Adaptive Staircase Policy Space Response Oracle to address these generalization issues and learn a universal neural solver. ASP consists of two components: Distributional Exploration, which enhances the solver's ability to handle unknown distributions using Policy Space Response Oracles, and Persistent Scale Adaption, which improves scalability through curriculum learning. We have tested ASP on several challenging COPs, including the traveling salesman problem, the vehicle routing problem, and the prize collecting TSP, as well as the real-world instances from TSPLib and CVRPLib. Our results show that even with the same model size and weak training signal, ASP can help neural solvers explore and adapt to unseen distributions and varying scales, achieving superior performance. In particular, compared with the same neural solvers under a standard training pipeline, ASP produces a remarkable decrease in terms of the optimality gap with 90.9% and 47.43% on generated instances and real-world instances for TSP, and a decrease of 19% and 45.57% for CVRP.

Formation optimization of airborne radar coordinated detection system using an improved Artificial Fish Swarm Algorithm.

In modern air combat, collaborative detection and engagement among multiple aircraft have gradually become a predominant combat approach. In response to the challenges posed by modern stealth aircraft, although their external factors such as coatings significantly reduce the chances of enemy detection, once these stealth aircraft activate their radar systems, they become susceptible to detection. Therefore, an application model has been proposed to mitigate enemy detection of our stealth aircraft through a collaborative approach. The underlying principle involves employing the concept of multi-aircraft collaboration, where the aircraft are divided into transmitters and receivers. The transmitters emit radar waves while the receivers are responsible for receiving these waves. This approach effectively mitigates the increased probability of enemy detection resulting from the activation of our receivers' radar systems. The optimization problem we aim to address is determining the optimal formation configuration for cooperative flight, specifically a formation with a specific configuration that maximizes the detectable range. This optimization problem is known as the configuration optimization problem for Airborne Radar Network with Separate Transmitting and Receiving (ARN-STAR). Existing methods for this problem typically suffer from limitations in either effectiveness or efficiency. To overcome these limitations, we propose an optimized configuration method based on an improved Artificial Fish Swarm Algorithm (IFSA) for ARN-STAR. Firstly, leveraging the distribution characteristics of the target radar wave's spatial scattering and the concept of dual-radar spatial diversity, we establish a mathematical model and an optimization objective function for ARN-STAR. Secondly, to address efficiency concerns, we optimize the computational process using the IAFS, successfully improving the speed of computation. To address the issue of effectiveness, we introduce adaptive adjustments to the movement step size of the artificial fish and improve the implementation of the three behavioral modes, thereby avoiding local optima and enhancing the accuracy of finding the optimal configuration. Finally, using our self-developed multi-aircraft collaborative simulation platform, we apply the improved AFSA to obtain the optimal formation configuration scheme and compare it with other methods. Simulation results demonstrate that our proposed method effectively solves the problem of finding the optimal formation configuration in multi-aircraft collaborative detection scenarios with "one transmission and multiple receptions." It overcomes the low computational efficiency associated with traditional methods while maintaining good accuracy. This approach enables the enhancement of overall combat capabilities while ensuring the safety of our aircraft to the greatest extent possible. It should be noted that the scenarios discussed in this study are at the configurational configuration level between UAVs, rather than involving the design of the UAVs combat control system itself.