Search

The core quality data, such as interior ballistic performance, are seriously unbalanced in the plasticizing and molding process, which makes it difficult for traditional supervised learning methods to accurately predict this kind of index. A Tri-training weighted ensemble JITL-RVM model based on an integrated confidence evaluation strategy is proposed to solve the above problem. The method is based on Tri-training semi-supervised regression architecture and uses both labeled and unlabeled data for modeling. First of all, the traditional single similarity measure method is difficult to use to evaluate the real similarity between data samples reliably and stably. This method realizes diversity enhancement and data expansion of the data set for modelling through ensemble just-in-time modelling based on three homologous and heterogeneous mixed similarity measures. Secondly, a new integrated confidence evaluation strategy is used to select the unlabeled samples, and the pseudo-labeled data, which can improve the prediction performance of the model, can be selected. To improve the prediction effect of the model, the pseudo-label value of the data is revised continuously. The integrated confidence evaluation strategy can overcome many shortcomings of the traditional confidence evaluation method based on Co-training regression (Coreg). Finally, the final quality prediction value is obtained through weighted integration fusion, which reflects the difference between different models and further improves the prediction accuracy. The experimental results of interior ballistic performance prediction of single-base gun propellant show the effectiveness and superiority of the proposed method, and it can improve the RMSE, R2, and PHR to 0.8074, 0.9644, and 93.3%, respectively. [ABSTRACT FROM AUTHOR]

The feeding and weighing of oxidizer agents is the key process of solid rocket motor propellant preparation, and its accuracy directly affects the burning performance of solid rocket motors. At present, the existing multi-batch feeding methods have the problem of low accuracy and high time consumption of the oxidizer agent. In this paper, an improved mass flow rate regulation method based on variable frequency control is proposed to improve accuracy and reduce time consumption. The nonlinear variation process of the mass flow rate during the opening and closing process of the air-operated pinch valve is analyzed. The periodic opening and closing frequency of the air-operated pinch valve is introduced to establish the mathematical model of the mass flow rate and frequency, and then, the model parameters are obtained through the discrete element method. The plan of the method of variable frequency regulation and the frequency parameters were determined using the multi-objective optimization method. The experiments are carried out, and the results show that compared to the existing multi-batch feeding method, optimized with the improved mass flow rate regulation methods based on the variable frequency control method, improved the feeding and weighing accuracy by 0.37% and reduced time consumption by 25.6%. [ABSTRACT FROM AUTHOR]

Computing the connected component (CC) of a graph is a basic graph computing problem, which has numerous applications like graph partitioning and pattern recognition. Existing methods for computing CC suffer from memory wall problems because of the frequent data transmission between CPU and memory. To overcome this challenge, in this article, we propose to accelerate CC computation with the emerging processing-in-memory (PIM) architecture through an algorithm–architecture co-design manner. The innovation lies in computing CC with bitwise logical operations (such as AND and OR), and the customized data flow management methods to accelerate computation and reduce energy consumption. As a proof of concept, experimental results with computational spin-transfer torque magnetic RAM (STT-MRAM) arrays demonstrate on average $19.8\times $ and $12.4\times $ speedups compared with the CPU and GPU implementations, and a $35.4 \times $ energy efficiency improvement over the CPU implementation. Moreover, we investigate the potential associations between graph computing and bitwise Boolean logic, which could help design more general in-memory graph computing accelerators in the future. [ABSTRACT FROM AUTHOR]

Recently, two-dimensional (2D) Ruddlesden–Popper perovskites have attracted extensive attention in the research society owing to their unique organic and inorganic layered structure induced superb stability. However, the quantum confinement effect and dielectric confinement effect caused by the layered structure of 2D perovskites limit the carrier transport and further hinder performance improvement of 2D perovskite optoelectronic devices. To resolve this problem, we have adjusted carrier density and carrier lateral transport in 2D perovskites by a layer optimization strategy. A series of 2D perovskite PEA2MA(n−1)PbnI3n+1 single crystals with varying layers (n = 1–5) have been synthesized by an in situ reverse temperature crystallization procedure, and ultra-high efficiency lateral structured photodetectors have been achieved. When n is 4, the photodetector shows the highest responsivity of 3077 A W−1 which is over 20 times higher than previous reports. A record external quantum efficiency of 7.2 × 106% is also achieved. The density functional theory calculations also confirm that directional migration of perovskite carriers is optimal when the layer number of the 2D perovskite PEA2MA(n−1)PbnI3n+1 is 4. This research shows that the layer number n is a key parameter in tuning the carrier density and lateral transport properties of the 2D PEA2MA(n−1)PbnI3n+1 perovskite, and a balance between these two parameters can be achieved when n is 4. This work is instructive for the fabrication of high-performance 2D perovskite optoelectronic devices. [ABSTRACT FROM AUTHOR]

Triangles are the basic substructure of networks and triangle counting (TC) has been a fundamental graph computing problem in numerous fields such as social network analysis. Nevertheless, like other graph computing problems, due to the high memory-computation ratio and random memory access pattern, TC involves a large amount of data transfers thus suffers from the bandwidth bottleneck in the traditional Von-Neumann architecture. To overcome this challenge, in this paper, we propose to accelerate TC with the emerging processing-in-memory (PIM) architecture through an algorithm-architecture co-optimization manner. To enable the efficient in-memory implementations, we come up to reformulate TC with bitwise logic operations (such as AND), and develop customized graph compression and mapping techniques for efficient data flow management. With the emerging computational Spin-Transfer Torque Magnetic RAM (STT-MRAM) array, which is one of the most promising PIM enabling techniques, the device-to-architecture co-simulation results demonstrate that the proposed TC in-memory accelerator outperforms the state-of-the-art GPU and FPGA accelerations by $12.2\times$ 12. 2 × and $31.8\times$ 31. 8 × , respectively, and achieves a $34\times$ 34 × energy efficiency improvement over the FPGA accelerator. [ABSTRACT FROM AUTHOR]

Our work overcomes the long‐standing challenge to achieve comprehensive improvements in thermo/mechanical properties of poly(lactic acid) (PLA), especially for impact toughness, strength, ductility, stiffness, and heat resistance. Simple deformation or microfibrillation of spherulites can create excellent thermo/mechanical properties making PLA compete against conventional petrochemical‐based polymers. It was performed by pressure‐induced‐flow (PIF) processing, and produced typical deformed spherulite structure and brick‐mud structure. It was found that the critical deformation degree of spherulites was around 2.7, beyond which spherulites would fragment. Through three transition stages of spherulite structures, deformed spherulite structures, and brick‐mud structure, PLA exhibited an enhancement of orientation, storage modulus and glass transition temperature. And a substantial increase was proved in impact strength (105.6 kJ/m2), tensile strength (148.4 MPa) and elongation at break (107.7%), which can be comparable to most engineering plastics. Both the deformed spherulite structures and the brick‐mud structures can enhance the impact toughness of PLA by increasing the fracture path of cracks. Besides, the evolution of the microstructure for a sandwich structure during PIF‐processing was proposed. [ABSTRACT FROM AUTHOR]

The pressure‐induced‐flow (PIF) processing method is used to fabricate oriented, self‐toughening poly(lactic acid) (PIF‐PLA) with excellent mechanical properties. However, residual internal stress in PIF‐PLA may lead to their deformation and cracking. Hence, to eliminate internal stress, solid‐state supercritical carbon dioxide foaming (sc‐CO2 foaming) is applied to PIF‐PLA, with the resultant structure being called FOAM‐PLA. The microstructure and mechanical properties of the PLAs are characterized pre‐ and post‐foaming. Scanning electron microscopy results show PIF‐PLA to exhibit oriented texture structures composed of staggered microfibers. Following sc‐CO2 foaming, the PIF‐PLA is converted into a bimodal cellular structure consisting of micro and nano‐cells. According to the 2D wide‐angle X‐ray diffraction and Raman spectra results, this structure of the FOAM‐PLA can, through a marginal reduction of orientation, release significant amounts of internal stress. Moreover, the impact strength of FOAM‐PLA is found to be 32.7 kJ m−2, which is 10.2 times higher than that of crystalline PLA. This paper depicts the evolution of the PLA microstructure through the stages of PIF‐processing and the subsequent solid‐state sc‐CO2 foaming. Meanwhile, the mechanism of the internal stress reduction is promoted. [ABSTRACT FROM AUTHOR]

Objective Methods Results Conclusion In this study, we investigated the safety and practicability of ultra‐fast track anesthesia (UFTA) for endoscopic thoracic sympathectomy (ETS).A total of 72 patients with palmar hyperhidrosis undergoing ETS were randomly divided into three groups: the UFTA group (group I), the group undergoing single‐lumen tracheal intubation with local infiltration anesthesia technique (group II), and the group undergoing single‐lumen tracheal intubation with routine anesthesia (group III). Mean arterial pressure (MAP) and heart rate (HR) were recorded for all three groups at the following six time points: Before anesthetics administration (T0), the time of intubating or inserting laryngeal mask airway (T1), the time of incising skin (T2), the time of disconnecting of the right sympathetic nerve (T3), the time of disconnecting of the left sympathetic nerve (T4), the time of withdrawing the tracheal tube or laryngeal mask airway (T5), and the time of transferring the patient to a post‐anesthesia care unit (PACU) (T6). The three groups were compared from the following perspectives: surgery duration; anesthesia recovery duration, that is, the duration from discontinuation of anesthesia to extubating the tracheal tube; the dose of propofol and remifentanil per kilogram body mass per unit time interval (the time at the end of the procedure, which lasted from anesthesia induction to incision suturing); and the visual analog scale (VAS) in the resting state in the PACU.Based on pairwise comparisons, the average HR and average MAP values of the three groups differed significantly from T2 to T6 (p < 0.05). As demonstrated by the correlation analysis between remifentanil and propofol with HR and MAP, the doses of the total amount of remifentanil and propofol were lower, and group I used less remifentanil and propofol than group II. No patient in group I experienced throat discomfort following surgery. Patients in groups II and III experienced a range of postoperative discomfort. The VAS scores of groups I and II were significantly lower than those of group III, with group I lower than group II.When utilized in ETS, UFTA can provide effective anesthesia for minor traumas. It is safe, effective, and consistent with the enhanced recovery philosophy of fast‐track surgery departments. [ABSTRACT FROM AUTHOR]

Sensor-based rehabilitation physical training assessment methods have attracted significant attention in refined evaluation scenarios. A refined rehabilitation evaluation method combines the expertise of clinicians with advanced sensor-based technology to capture and analyze subtle movement variations often unobserved by traditional subjective methods. Current approaches center on either body postures or muscle strength, which lack more sophisticated analysis features of muscle activation and coordination, thereby hindering analysis efficacy in deep rehabilitation feature exploration. To address this issue, we present a multimodal network algorithm that integrates surface electromyography (sEMG) and stress distribution signals. The algorithm considers the physical knowledge a priori to interpret the current rehabilitation stage and efficiently handles temporal dynamics arising from diverse user profiles in an online setting. Besides, we verified the performance of this model using a learned-nonuse phenomenon assessment task in 24 subjects, achieving an accuracy of 94.7%. Our results surpass those of conventional feature-based, distance-based, and ensemble baseline models, highlighting the advantages of incorporating multimodal information rather than relying solely on unimodal data. Moreover, the proposed model presents a network design solution for rehabilitation physical training that requires deep bioinformatic features and can potentially assist real-time and home-based physical training work.

Introduction: The blood oxygen level-dependent (BOLD) signal derived from functional neuroimaging is commonly used in brain network analysis and dementia diagnosis. Missing the BOLD signal may lead to bad performance and misinterpretation of findings when analyzing neurological disease. Few studies have focused on the restoration of brain functional time-series data., Methods: In this paper, a novel U -shaped convolutional transformer GAN (UCT-GAN) model is proposed to restore the missing brain functional time-series data. The proposed model leverages the power of generative adversarial networks (GANs) while incorporating a U -shaped architecture to effectively capture hierarchical features in the restoration process. Besides, the multi-level temporal-correlated attention and the convolutional sampling in the transformer-based generator are devised to capture the global and local temporal features for the missing time series and associate their long-range relationship with the other brain regions. Furthermore, by introducing multi-resolution consistency loss, the proposed model can promote the learning of diverse temporal patterns and maintain consistency across different temporal resolutions, thus effectively restoring complex brain functional dynamics., Results: We theoretically tested our model on the public Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, and our experiments demonstrate that the proposed model outperforms existing methods in terms of both quantitative metrics and qualitative assessments. The model's ability to preserve the underlying topological structure of the brain functional networks during restoration is a particularly notable achievement., Conclusion: Overall, the proposed model offers a promising solution for restoring brain functional time-series and contributes to the advancement of neuroscience research by providing enhanced tools for disease analysis and interpretation., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2024 Zuo, Li, Shi, Hong, Zhu, Chen, Wu and Guo.)

The topological connectivity information derived from the brain functional network can bring new insights for diagnosing and analyzing dementia disorders. The brain functional network is suitable to bridge the correlation between abnormal connectivities and dementia disorders. However, it is challenging to access considerable amounts of brain functional network data, which hinders the widespread application of data-driven models in dementia diagnosis. In this study, a novel distribution-regularized adversarial graph auto-Encoder (DAGAE) with transformer is proposed to generate new fake brain functional networks to augment the brain functional network dataset, improving the dementia diagnosis accuracy of data-driven models. Specifically, the label distribution is estimated to regularize the latent space learned by the graph encoder, which can make the learning process stable and the learned representation robust. Also, the transformer generator is devised to map the node representations into node-to-node connections by exploring the long-term dependence of highly-correlated distant brain regions. The typical topological properties and discriminative features can be preserved entirely. Furthermore, the generated brain functional networks improve the prediction performance using different classifiers, which can be applied to analyze other cognitive diseases. Attempts on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate that the proposed model can generate good brain functional networks. The classification results show adding generated data can achieve the best accuracy value of 85.33%, sensitivity value of 84.00%, specificity value of 86.67%. The proposed model also achieves superior performance compared with other related augmented models. Overall, the proposed model effectively improves cognitive disease diagnosis by generating diverse brain functional networks., Competing Interests: Conflicts of Interest: The authors declare that they have no conflicts of interest to report regarding the present study.

Recent years have witnessed a significant advancement in brain imaging techniques that offer a non-invasive approach to mapping the structure and function of the brain. Concurrently, generative artificial intelligence (AI) has experienced substantial growth, involving using existing data to create new content with a similar underlying pattern to real-world data. The integration of these two domains, generative AI in neuroimaging, presents a promising avenue for exploring various fields of brain imaging and brain network computing, particularly in the areas of extracting spatiotemporal brain features and reconstructing the topological connectivity of brain networks. Therefore, this study reviewed the advanced models, tasks, challenges, and prospects of brain imaging and brain network computing techniques and intends to provide a comprehensive picture of current generative AI techniques in brain imaging. This review is focused on novel methodological approaches and applications of related new methods. It discussed fundamental theories and algorithms of four classic generative models and provided a systematic survey and categorization of tasks, including co-registration, super-resolution, enhancement, classification, segmentation, cross-modality, brain network analysis, and brain decoding. This paper also highlighted the challenges and future directions of the latest work with the expectation that future research can be beneficial., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Gong, Jing, Chen, Pun, Huang, Saha, Nieuwoudt, Li, Hu and Wang.)

In recent years, human activity recognition (HAR) technologies in e-health have triggered broad interest. In literature, mainstream works focus on the body's spatial information (i.e. postures) which lacks the interpretation of key bioinformatics associated with movements, limiting the use in applications requiring comprehensively evaluating motion tasks' correctness. To address the issue, in this article, a Wearables-based Multi-column Neural Network (WMNN) for HAR based on multi-sensor fusion and deep learning is presented. Here, the Tai Chi Eight Methods were utilized as an example as in which both postures and muscle activity strengths are significant. The research work was validated by recruiting 14 subjects in total, and we experimentally show 96.9% and 92.5% accuracy for training and testing, for a total of 144 postures and corresponding muscle activities. The method is then provided with a human-machine interface (HMI), which returns users with motion suggestions (i.e. postures and muscle strength). The report demonstrates that the proposed HAR technique can enhance users' self-training efficiency, potentially promoting the development of the HAR area.