Inconsistent Distribution Research Articles

Study of the influence of construction stages on the analysis of tall reinforced concrete buildings

This dissertation project proposes to investigate the influence of considering construction stages in tall reinforced concrete buildings by evaluating conventional strategies, which do not take the construction stages into account, and strategies that consider them in an approximate way, including a model interpreted as a reference, known as construction effect. Nowadays, with the development of structural analysis and design programs, a change in the structural calculation is observed, moving from conventional models to those that describe the real sequence of loading and construction. Since the structure is subjected to internal forces as it is built, it is desirable for structural engineers to consider the loading being applied progressively and the evolution of the mechanical properties of materials with time. The conventional method, by considering the action of all loads on the completed structure and the modulus of elasticity of concrete at 28 days, does not reflect the reality of constructions. The main distinction between analysis strategies lies in how displacements along the height of the building are treated. In the conventional model, since the loads are applied in a single step, displacements occur simultaneously and cumulatively. On the other hand, in incremental analysis, the loads acting on a given floor do not cause displacements, or consequent internal forces, on an upper floor not yet built. Analysis without consideration of the construction stages may result in an inconsistent distribution of internal forces and may not represent the real behavior of the structure, wich may even result in inadequate design and consequent pathological manifestations and/or collapse of the structure. Therefore, it is intended to conduct a comparison between the methods of conventional analysis, axial stiffness increaser, called the approximate method, and incremental analysis, seeking to understand the main differences in terms of internal forces and the design of buildings. For this purpose, softwares for modeling, analysis, and structural design that allow the simulation of these strategies will be used.

Transient gas path fault diagnosis of aero-engine based on domain adaptive offline reinforcement learning

Real-time measurement parameters are crucial for diagnosing faults in aero-engine gas path performance, ensuring engine reliability, and mitigating potential economic losses. Traditional aero-engines performance diagnosis was mainly based on the measurements of steady-state condition and lacked the utilization of data under transient conditions. Gas path diagnosis of aero-engines under transient conditions is crucial for early fault detection and safety of flight within the envelope. The challenge lies in the inconsistent distribution of performance deviations caused by variable operating conditions, especially with complex fault types, which can undermine diagnostic credibility. To improve reliability of gas path diagnosis under transient conditions, an offline reinforcement learning fault diagnosis framework based on a transient aero-engine performance model is proposed. To address the issue of variable operating conditions during transient states, a domain adaptive approach is utilized to reconstruct the measurement baseline and facilitate the transfer of different performance deviation distributions. Additionally, by adding spool acceleration as a measurement parameter, the multi-component fault coupling is solved. Finally, validation with actual operating data simulates fault cases, demonstrating the proposed method's efficacy in quantitatively detecting gradual, sudden, and multiple component faults under transient conditions with high accuracy and efficiency. The method proposed in this study achieves a computational speed improvement by 64% compared to the conventional method, achieving a time of 0.13 seconds, with an average error of less than 0.00389%. Additionally, it demonstrates strong robustness in the presence of noise, with an average error of less than 0.03125%. This proposed method improves real-time fault detection under transient conditions for its higher accuracy and efficiency, and therefore significantly enhance gas path health monitoring and diagnosis capability.

A novel two-stage method via adversarial strategy for remaining useful life prediction of bearings under variable conditions

It is critical to accurately predict the remaining useful life (RUL) of rolling bearings to avoid severe accidents and financial losses in the industry. Nevertheless, accurately determining the initial prediction time (IPT) continues to pose a challenge, and significant differences in the data distribution of bearings under different operating conditions are frequently overlooked. To deal with these problems, we propose a novel two-stage method based on the adversarial strategy for RUL prediction of bearings under variable conditions. Firstly, we create reliable health indicators in an unsupervised manner by recording the coded characteristics of the bearing’s state of health. Secondly, an adaptive threshold method based on rate-of-change (ATMROC) is developed to perform accurate health state classification. Finally, we propose a RUL prediction network based on the attention depth-gated recurrent unit with domain invariance (DIADGRU) to handle the inconsistent distribution of degradation features under different operating conditions. Experiments of RUL prediction on PHM2012 and XITU-SY datasets are implemented, and the promising results validate the effectiveness of the proposed method.

The significance of neuroendocrine component in cases with intrahepatic cholangiocarcinoma: A SEER-based retrospective cohort study

ObjectiveTo evaluate the significance of neuroendocrine component in cases with intrahepatic cholangiocarcinoma (IHCC). MethodsCases with IHNECA and IHBDAC from the Surveillance, Epidemiology, and End Results (SEER) database were retrospectively reviewed and analyzed. Comparative analyses in terms of clinic-pathological features and long-term survival were performed between cases with intrahepatic neuroendocrine carcinoma (IHNECA) and intrahepatic bile duct adenocarcinoma (IHBDAC). ResultsA total of 5211 cases with IHCC were included (103 with IHNECA and 5108 with IHBDAC). Comparable age status (P=0.168), sex status (P=0.274), and cirrhosis status (P=0.480) were acquired between two groups while inconsistent distributions in races (P=0.027) and marital status (P=0.028) were also acquired. Cases with IHBDAC were generally in a more advanced stage and shared a worse prognosis. A significantly higher incidence of lymph node metastasis was detected among cases with IHBDAC (24.8% vs 15.5%, P=0.031). Although the overall surgery rate was comparable between two groups (P=0.519), chemotherapy (53.0% vs 37.9%, P=0.002) and radiotherapy (6.0% vs 1.0%, P=0.032) were more frequently performed with a much higher cancer-related death (CRD) (79.4% vs 58.3%, P<0.001) acquired in cases with IHBDAC. INHECA served as an independent protective factor for cases with IHCC. Even after matching, cases with IHBDCA still shared a higher incidence with CRD (P=0.010) and a worse prognosis, especially for cases who received surgery. ConclusionIHNECA was associated with less aggressive tumor biological features and worse prognosis. More in-depth research focusing on IHNECA with more detailed clinical and pathological data is required.

Is conventional functional liver remnant volume higher than 40% still sufficient to prevent post-hepatectomy liver failure in jaundiced patients with hilar cholangiocarcinoma? A single-center experience in China.

Our study aims to evaluate the predictive accuracy of functional liver remnant volume (FLRV) in post-hepatectomy liver failure (PHLF) among surgically-treated jaundiced patients with hilar cholangiocarcinoma (HCCA). We retrospectively reviewed surgically-treated jaundiced patients with HCCA between June, 2000 and June, 2018. The correlation between FRLV and PHLF were analyzed. The optimal cut off value of FLRV in jaundiced HCCA patients was also identified and its impact was furtherly evaluated. A total of 224 jaundiced HCCA patients who received a standard curative resection (43 patients developed PHLF) were identified. Patients with PHLF shared more aggressive clinic-pathological features and were generally in a more advanced stage than those without PHLF. An obvious inconsistent distribution of FLRV in patients with PHLF and those without PHLF were detected. FLRV (continuous data) had a high predictive accuracy in PHLF. The newly-acquired cut off value (FLRV = 53.5%, sensitivity = 81.22%, specificity = 81.4%) showed a significantly higher predictive accuracy than conventional FLRV cut off value (AUC: 0.81 vs. 0.60, p < 0.05). Moreover, patients with FLRV lower than 53.5% also shared a significantly higher major morbidity rate as well as a worse prognosis, which were not detected for FLRV of 40%. For jaundiced patients with HCCA, a modified FLRV of 53.5% is recommended due to its great impact on PHLF, as well as its correlation with postoperative major morbidities as well as overall prognosis, which might help clinicians to stratify patients with different therapeutic regimes and outcomes. Future multi-center studies for training and validation are required for further validation.

Tissue distribution of Coxiella burnetii and antibody responses in macropods co-grazing with livestock in Queensland, Australia.

Coxiella burnetii, the causative agent of Q fever, is a zoonotic bacteria of global public health significance. The organism has a complex, diverse, and relatively poorly understood animal reservoir but there is increasing evidence that macropods play some part in the epidemiology of Q fever in Australia. The aim of this cross-sectional survey was to estimate the animal- and tissue-level prevalence of coxiellosis amongst eastern grey (Macropus giganteus) and red (Osphranter rufus) kangaroos co-grazing with domestic cattle in a Q fever endemic area in Queensland. Serum, faeces and tissue samples from a range of organs were collected from 50 kangaroos. A total of 537 tissue samples were tested by real-time PCR, of which 99 specimens from 42 kangaroos (84% of animals, 95% confidence interval [CI], 71% to 93%) were positive for the C. burnetii IS1111 gene when tested in duplicate. Twenty of these specimens from 16 kangaroos (32%, 95% CI 20% to 47%) were also positive for the com1 or htpAB genes. Serum antibodies were present in 24 (57%, 95% CI 41% to 72%) of the PCR positive animals. There was no statistically significant difference in PCR positivity between organs and no single sample type consistently identified C. burnetii positive kangaroos. The results from this study identify a high apparent prevalence of C. burnetii amongst macropods in the study area, albeit seemingly with an inconsistent distribution within tissues and in relatively small quantities, often verging on the limits of detection. We recommend Q fever surveillance in macropods should involve a combination of serosurveys and molecular testing to increase chances of detection in a population, noting that a range of tissues would likely need to be sampled to confirm the diagnosis in a suspect positive animal.

Joint multi-omics discriminant analysis with consistent representation learning using PANDA.

Integrative multi-omics analysis provides deeper insight and enables better and more realistic modeling of the underlying biology and causes of diseases than does single omics analysis. Although several integrative multi-omics analysis methods have been proposed and demonstrated promising results in integrating distinct omics datasets, inconsistent distribution of the different omics data, which is caused by technology variations, poses a challenge for paired integrative multi-omics methods. In addition, the existing discriminant analysis-based integrative methods do not effectively exploit correlation and consistent discriminant structures, necessitating a compromise between correlation and discrimination in using these methods. Herein we present PAN-omics Discriminant Analysis (PANDA), a joint discriminant analysis method that seeks omics-specific discriminant common spaces by jointly learning consistent discriminant latent representations for each omics. PANDA jointly maximizes between-class and minimizes within-class omics variations in a common space and simultaneously models the relationships among omics at the consistency representation and cross-omics correlation levels, overcoming the need for compromise between discrimination and correlation as with the existing integrative multi-omics methods. Because of the consistency representation learning incorporated into the objective function of PANDA, this method seeks a common discriminant space to minimize the differences in distributions among omics, can lead to a more robust latent representations than other methods, and is against the inconsistency of the different omics. We compared PANDA to 10 other state-of-the-art multi-omics data integration methods using both simulated and real-world multi-omics datasets and found that PANDA consistently outperformed them while providing meaningful discriminant latent representations. PANDA is implemented using both R and MATLAB, with codes available at https://github.com/WuLabMDA/PANDA.

Bearing fault diagnosis based on transfer learning with dual-flow manifold ResNet and improved CapsNet

In intelligent fault diagnosis for rolling bearings, the variable operating conditions of rotating machinery lead to inconsistent distributions between training and testing data, inevitably decreasing fault diagnosis accuracy. To overcome this issue, we propose a bearing fault diagnosis method based on transfer learning with a dual-flow manifold residual network and improved capsule network (DMRCN). Firstly, we introduce a dual-flow manifold residual network structure consisting of continuous wide-kernel convolution, continuous narrow-kernel convolution, and manifold learning spatial information description blocks. This architecture is utilized to extract low-level features from the data. Then, we present a novel architecture of the capsule network with self-attention output. We incorporate a self-attention mechanism into the dynamic routing algorithm to transfer richer high-level features from the low-level capsule layer to the higher-level capsule layer. During training, we propose a loss function known as global-local distribution discrepancy loss to enhance the model’s generalization ability and accelerate model convergence. Finally, we validate the performance of DMRCN in cross-condition transfer fault diagnosis on both the Case Western Reserve University public dataset and a laboratory-built bearing experimental rig dataset. Experimental results demonstrate that DMRCN outperforms other commonly used deep transfer learning methods regarding fault diagnosis across different operating conditions.

Debiased Graph Neural Networks With Agnostic Label Selection Bias.

Most existing graph neural networks (GNNs) are proposed without considering the selection bias in data, i.e., the inconsistent distribution between the training set with the test set. In reality, the test data are not even available during the training process, making selection bias agnostic. Training GNNs with biased selected nodes leads to significant parameter estimation bias and greatly impacts the generalization ability on test nodes. In this article, we first present an experimental investigation, which clearly shows that the selection bias drastically hinders the generalization ability of GNNs, and theoretically proves that the selection bias will cause the biased estimation on GNN parameters. Then to remove the bias in GNN estimation, we propose a novel debiased GNNs (DGNN) with a differentiated decorrelation regularizer. The differentiated decorrelation regularizer estimates a sample weight for each labeled node such that the spurious correlation of learned embeddings could be eliminated. We analyze the regularizer in causal view and it motivates us to differentiate the weights of the variables based on their contribution to the confounding bias. Then, these sample weights are used for reweighting GNNs to eliminate the estimation bias, and thus, help to improve the stability of prediction on unknown test nodes. Comprehensive experiments are conducted on several challenging graph datasets with two kinds of label selection biases. The results well verify that our proposed model outperforms the state-of-the-art methods and DGNN is a flexible framework to enhance existing GNNs.

The Potential of Natural Carotenoids-Containing Sericin of the Domestic Silkworm Bombyx mori.

Sericin derived from the white cocoon of Bombyx mori has been attracting more attention for its utilization in food, cosmetics, and biomedicine. The potential health benefits of natural carotenoids for humans have also been well-established. Some rare strains of Bombyx mori (B. mori) produce yellow-red cocoons, which endow a potential of natural carotenoid-containing sericin. We hypothesized that natural carotenoid-containing sericin from yellow-red cocoons would exhibit better properties compared with white cocoon sericin. To investigate the physicochemical attributes of natural carotenoid-containing sericin, we bred two silkworm strains from one common ancestor, namely XS7 and XS8, which exhibited different cocoon colors as a result of the inconsistent distribution of lutein and β-carotene. Compared with white cocoon sericin, the interaction between carotenoids and sericin molecules in carotenoid-containing sericin resulted in a unique fluorescence emission at 530, 564 nm. The incorporation of carotenoids enhanced the antibacterial effect, anti-cancer ability, cytocompatibility, and antioxidant of sericin, suggesting potential wide-ranging applications of natural carotenoid-containing sericin as a biomass material. We also found differences in fluorescence characteristics, antimicrobial effects, anti-cancer ability, and antioxidants between XS7 and XS8 sericin. Our work for the first time suggested a better application potential of natural carotenoid-containing sericin as a biomass material than frequently used white cocoon sericin.

A two-view deep interpretable TSK fuzzy classifier under mutually teachable classification criterion

Most of the existing classification techniques generally requires the consistent distribution assumption between training and testing samples. However, recent results theoretically reveal that enhanced classification performance may be achieved by breaking this assumption and meanwhile managing to satisfy a subtle assumption between a prediction function, training and testing samples. Although such a subtle assumption is too hard to be leveraged as a criterion for designing a single-view classifier, this study as the first attempt exhibits its natural yet distinctive value in designing a two-view classifier. In this study, originating from the inconsistent distribution assumption between training and testing samples, a new mutually teachable classification criterion is proposed, and accordingly a two-view deep interpretable Tagaki-Sugeno-Kang fuzzy classifier called Tvd-TFC is developed. In order to keep both promising classification performance and high interpretability of Tvd-TFC, it simply takes our recent work-- deep Tagaki-Sugeno-Kang fuzzy classifier (D-TSK-FC) as a basic component of each deep sub-classifier for each view. The distinctive novelty of Tvd-TFC exists in that its double deep structures along with two respective views are interchangeably learnt in deep learning manner according to the proposed mutually teachable classification criterion. The proposed learning algorithm can not only minimize the testing error along with each view but also ensure the consistency between two views. Experimental results on two-view datasets demonstrate that the proposed classifier Tvd-TFC realizes enhanced or at least comparable classification performance and simultaneously has better interpretability in contrast to the comparative classifiers.

Single-cell multi-omics analysis of lineage development and spatial organization in the human fetal cerebellum

Human cerebellum encompasses numerous neurons, exhibiting a distinct developmental paradigm from cerebrum. Here we conducted scRNA-seq, scATAC-seq and spatial transcriptomic analyses of fetal samples from gestational week (GW) 13 to 18 to explore the emergence of cellular diversity and developmental programs in the developing human cerebellum. We identified transitory granule cell progenitors that are conserved across species. Special patterns in both granule cells and Purkinje cells were dissected multidimensionally. Species-specific gene expression patterns of cerebellar lobes were characterized and we found that PARM1 exhibited inconsistent distribution in human and mouse granule cells. A novel cluster of potential neuroepithelium at the rhombic lip was identified. We also resolved various subtypes of Purkinje cells and unipolar brush cells and revealed gene regulatory networks controlling their diversification. Therefore, our study offers a valuable multi-omics landscape of human fetal cerebellum and advances our understanding of development and spatial organization of human cerebellum.

Generalizable Reconstruction for Accelerating MR Imaging via Federated Learning with Neural Architecture Search.

Heterogeneous data captured by different scanning devices and imaging protocols can affect the generalization performance of the deep learning magnetic resonance (MR) reconstruction model. While a centralized training model is effective in mitigating this problem, it raises concerns about privacy protection. Federated learning is a distributed training paradigm that can utilize multi-institutional data for collaborative training without sharing data. However, existing federated learning MR image reconstruction methods rely on models designed manually by experts, which are complex and computationally expensive, suffering from performance degradation when facing heterogeneous data distributions. In addition, these methods give inadequate consideration to fairness issues, namely ensuring that the model's training does not introduce bias towards any specific dataset's distribution. To this end, this paper proposes a generalizable federated neural architecture search framework for accelerating MR imaging (GAutoMRI). Specifically, automatic neural architecture search is investigated for effective and efficient neural network representation learning of MR images from different centers. Furthermore, we design a fairness adjustment approach that can enable the model to learn features fairly from inconsistent distributions of different devices and centers, and thus facilitate the model to generalize well to the unseen center. Extensive experiments show that our proposed GAutoMRI has better performances and generalization ability compared with seven state-of-the-art federated learning methods. Moreover, the GAutoMRI model is significantly more lightweight, making it an efficient choice for MR image reconstruction tasks. The code will be made available at https://github.com/ternencewu123/GAutoMRI.

Semantics Disentangling for Cross-modal Retrieval.

Cross-modal retrieval (e.g., query a given image to obtain a semantically similar sentence, and vice versa) is an important but challenging task, as the heterogeneous gap and inconsistent distributions exist between different modalities. The dominant approaches struggle to bridge the heterogeneity by capturing the common representations among heterogeneous data in a constructed subspace which can reflect the semantic closeness. However, insufficient consideration is taken into the fact that learned latent representations are actually heavily entangled with those semantic-unrelated features, which obviously further compounds the challenges of cross-modal retrieval. To alleviate the difficulty, this work makes an assumption that the data are jointly characterized by two independent features: semantic-shared and semantic-unrelated representations. The former presents characteristics of consistent semantics shared by different modalities, while the latter reflects the characteristics with respect to the modality yet unrelated to semantics, such as background, illumination, and other low-level information. Therefore, this paper aims to disentangle the shared semantics from the entangled features, andthus the purer semantic representation can promote the closeness of paired data. Specifically, this paper designs a novel Semantics Disentangling approach for Cross-Modal Retrieval (termed as SDCMR) to explicitly decouple the two different features based on variational auto-encoder. Next, the reconstruction is performed by exchanging shared semantics to ensure the learning of semantic consistency. Moreover, a dual adversarial mechanism is designed to disentangle the two independent features via a pushing-and-pulling strategy. Comprehensive experiments on four widely used datasets demonstrate the effectiveness and superiority of the proposed SDCMR method by achieving a new bar on performance when compared against 15 state-of-the-art methods.

Ensemble Active Learning by Contextual Bandits for AI Incubation in Manufacturing

An Industrial Cyber-physical System (ICPS) provides a digital foundation for data-driven decision-making by artificial intelligence (AI) models. However, the poor data quality (e.g., inconsistent distribution, imbalanced classes) of high-speed, large-volume data streams poses significant challenges to the online deployment of offline-trained AI models. As an alternative, updating AI models online based on streaming data enables continuous improvement and resilient modeling performance. However, for a supervised learning model (i.e., a base learner), it is labor-intensive to annotate all streaming samples to update the model. Hence, a data acquisition method is needed to select the data for annotation to ensure data quality while saving annotation efforts. In the literature, active learning methods have been proposed to acquire informative samples. Different acquisition criteria were developed for exploration of under-represented regions in the input variable space or exploitation of the well-represented regions for optimal estimation of base learners. However, it remains a challenge to balance the exploration-exploitation trade-off under different online annotation scenarios. On the other hand, an acquisition criterion learned by AI adapts itself to a scenario dynamically, but the ambiguous consideration of the trade-off limits its performance in frequently changing manufacturing contexts. To overcome these limitations, we propose an ensemble active learning method by contextual bandits ( CbeAL ). CbeAL incorporates a set of active learning agents (i.e., acquisition criteria) explicitly designed for exploration or exploitation by a weighted combination of their acquisition decisions. The weight of each agent will be dynamically adjusted based on the usefulness of its decisions to improve the performance of the base learner. With adaptive and explicit consideration of both objectives, CbeAL efficiently guides the data acquisition process by selecting informative samples to reduce the human annotation efforts. Furthermore, we characterize the exploration and exploitation capability of the proposed agents theoretically. The evaluation results in a numerical simulation study and a real case study demonstrates the effectiveness and efficiency of CbeAL in manufacturing process modeling of the ICPS.

Application of Indian ink markers for locating gastric varices under endoscopic ultrasonography.

The present study aimed to investigate the accuracy of endoscopic ultrasonography (EUS) combined with Indian ink in locating target vessels of gastric varices (GVs) compared with conventional endoscopic techniques. Additionally, the characteristics of GVs under conventional endoscopy were also explored. All 50 cirrhotic patients with GVs between August 2021 and December 2022 were included in the study. Firstly, conventional endoscopy was employed to identify GVs and to record the expected injection sites. Subsequently, EUS was used to locate the perforated vessel and the injection site was them marked with India ink followed by injection with cyanoacrylate (CYA). Finally, conventional endoscopy was used to examine GVs, to identify the marker points of Indian ink and to compare whether the injection points under conventional endoscopy were consistent with those marked with Indian ink. Furthermore, patients with consistent and inconsistent distribution of endoscopic markers and injection sites were divided into two groups. EUS could detect the perforating vessels in real time and intuitively. The distribution of markers using EUS was significantly different compared with the injection points obtained by conventional endoscopy (P < 0.001). Therefore, 20 cases were allocated to the consistent group and 30 cases to the non-consistent group. 16 patients who showed red wale signs were obtained in the consistent group and 11 patients in the non-consistent group (P = 0.048). The diameter of the largest GVs was 13.5 (10-15) mm in the consistent group compared with 10 (7.5-10) mm in the non-consistent group (P = 0.006). EUS could provide the exact location of GVs, thus more accurately describing the endoscopic characteristics of the GVs. Furthermore, the red wale signs and diameter of the largest GVs obtained using conventional endoscopy were helpful in determining the location of target GVs.

Proteome analysis of Daboia russelii venom, a medically important snake from the Indian sub-continent

Daboia russelii is a category-I medically important snake throughout the Indian sub-continent contributing to majority of snakebite incidences in this part of the world. As such, extensive studies on its venom composition and search of efficient and appropriate interventions for its treatment become crucial. In this study, the proteome of Daboia russelii venom from Tanore, Rajshahi, Bangladesh was profiled using a combination of chromatographic and mass spectrometric techniques. A total of 37 different proteins belonging to 11 different snake venom protein families were detected. Proteomics analysis revealed the presence of major phospholipase A2 toxins. Daboiatoxin (both A and B subunits), the main lethal PLA2 toxin in the venom of Daboia siamensis (Myanmar viper) which is neurotoxic, myotoxic and cytotoxic was detected. Presence of Daboxin P, which is a major protein in the venom of Indian Daboia russelii with strong anticoagulant activity, was also observed. Inconsistent distribution of such lethal toxins in the venom of same species calls for more investigations of snake venoms from lesser explored regions and formulation of better alternatives to the current antivenom therapy for efficient treatment.

Cushioning performance design of meta-sandwich structures inspired by Kirigami

ABSTRACT Novel ultralight meta-sandwich structures inspired by Kirigami (MSS) are proposed in this study. The topological designs of uniform (MSS-U) and non-uniform (MSS-N) sizes are studied based on the inconsistent distribution of the biomaterials. First, MSS-U and MSS-N are manufactured using laser powder bed fusion (LPBF) technology, and energy absorption prediction formulas are successfully derived by extracting the experimental deformation features. It is found that MSS-N exhibits a higher energy absorption level than MSS-U. Compared to the conventional corrugated sandwich structures (CSS), the MSS achieves better crashworthiness indicators and more folding numbers. Moreover, the parameter effect of the MSS is analysed, and the minimum/maximum thickness and folding angle significantly influence the crashworthiness responses. The mechanical properties of MSS-N can be regulated by changing the folding angle while maintaining the same thickness. The MSS proposed in this study can achieve a higher energy absorption efficiency at the same density compared to other existing mechanical structures. Interestingly, the feasibility of applying MSS to automobiles and plant protection drones is verified by changing the materials and macro-configurations. The design concept presented in this study provides a promising method for obtaining sandwich structures with excellent cushioning properties for engineering protective equipment.

Possibilistic distribution distance metric: a robust domain adaptation learning method.

The affective Brain-Computer Interface (aBCI) systems, which achieve predictions for individual subjects through training on multiple subjects, often cannot achieve satisfactory results due to the differences in Electroencephalogram (EEG) patterns between subjects. One tried to use Subject-specific classifiers, but there was a lack of sufficient labeled data. To solve this problem, Domain Adaptation (DA) has recently received widespread attention in the field of EEG-based emotion recognition. Domain adaptation (DA) learning aims to solve the problem of inconsistent distributions between training and test datasets and has received extensive attention. Most existing methods use Maximum Mean Discrepancy (MMD) or its variants to minimize the problem of domain distribution inconsistency. However, noisy data in the domain can lead to significant drift in domain means, which can affect the adaptability performance of learning methods based on MMD and its variants to some extent. Therefore, we propose a robust domain adaptation learning method with possibilistic distribution distance measure. Firstly, the traditional MMD criterion is transformed into a novel possibilistic clustering model to weaken the influence of noisy data, thereby constructing a robust possibilistic distribution distance metric (P-DDM) criterion. Then the robust effectiveness of domain distribution alignment is further improved by a fuzzy entropy regularization term. The proposed P-DDM is in theory proved which be an upper bound of the traditional distribution distance measure method MMD criterion under certain conditions. Therefore, minimizing P-DDM can effectively optimize the MMD objective. Secondly, based on the P-DDM criterion, a robust domain adaptation classifier based on P-DDM (C-PDDM) is proposed, which adopts the Laplacian matrix to preserve the geometric consistency of instances in the source domain and target domain for improving the label propagation performance. At the same time, by maximizing the use of source domain discriminative information to minimize domain discrimination error, the generalization performance of the learning model is further improved. Finally, a large number of experiments and analyses on multiple EEG datasets (i.e., SEED and SEED-IV) show that the proposed method has superior or comparable robustness performance (i.e., has increased by around 10%) in most cases.

Adversarial pre-optimized graph representation learning with double-order sampling for cross-modal retrieval

Cross-modal retrieval aims at retrieving relevant information across different media data, such as images and text. However, inconsistent distribution of different modal data causes a heterogeneity gap, which becomes an intractable issue. Previous researches aim at finding a semantic share space for various modalities, in which the similarity of them can be calculated by a uniform measurement. Graph representation learning has shown excellent performance in many tasks, like information retrieval. However, it is difficult to construct the most proper cross-modal graph which can better present the semantics of multi-modal data. Besides, the projected representations of various modal data optimized by the supervised class labels and unsupervised graph context learning are insufficiently aligned. To address these issues, this paper presents an Adversarial Pre-optimized Graph Representation Learning (AP-GRL) for cross-modal retrieval. Similar to mainstream methods, AP-GRL aims to learn a shared representation for various modalities. We design an adaptive pre-optimization mechanism to optimize the cross-modal data and their relationships, which is different from previously fixed graph. The raw constructed cross-modal graph is optimized by maximum posterior probability estimation. To fully exploit the graph, we proposed a double-order sampling strategy to take the width and depth into representation learning. Besides, we adopt adversarial learning with Wasserstein distance to reduce domain discrepancy in the domain-invariant representation learning. Extensive experiments on five widely used datasets demonstrate that AP-GRL outperforms state-of-the-art cross-modal retrieval methods.