Search

Hyperspectral unmixing is of vital importance within the realm of hyperspectral analysis, which is aimed to decide the fractional proportion (abundances) of fundamental spectral signatures (endmembers) at a subpixel level. Unsupervised unmixing techniques that employ autoencoder (AE) network have gained significant attention for its exceptional feature extraction capabilities. However, traditional AE-based methods lean towards focusing excessively on the information of spectral dimension in the data, resulting in limited ability to extract endmembers with meaningful physical interpretations, and achieve uncompetitive performance. In this paper, we propose a novel multi-domain dual-stream network, called MdsNet, which enhances performance by incorporating high-rank spatial information to guide the unmixing process. This approach allows us to uncover pure endmember data that is hidden within the original hyperspectral image (HSI). We first apply superpixel segmentation and smoothing operations as preprocessing steps to transform the HSI into a coarse domain. Then, MdsNet efficiently handles multi-domain data and employs attention generated from the approximate domain to learn meaningful information about the endmembers’ physical characteristic. Experimental results and ablation studies conducted on Synthetic and real datasets (Samson, Japser, Urban) outperform state-of-the-art techniques by more than 10% in terms of root mean squared error and spectral angle distance, illustrating the effectiveness and superiority of our proposed method. The source code is available at https://github.com/qiwenjjin/JAG-MdsNet.

Abstract Objective To investigate the association of serum anti-Jo-1 antibody levels with the disease activity and prognosis in anti-Jo-1-positive patients with antisynthetase syndrome (ASS). Methods This study included 115 anti-Jo-1-positive patients with ASS who were admitted to China-Japan Friendship Hospital between 2009 and 2019. Anti-Jo-1 antibody serum levels at initial admission and follow-up were determined by enzyme-linked immunosorbent assay (ELISA). Global and organ disease activity was assessed at baseline and follow-up according to the International Myositis Assessment and Clinical Studies guidelines. Results Among enrolled patients, 70 (60.9%) patients initially presented with interstitial lung disease (ILD), and 46 (40%) patients presented with with muscle weakness at initial admission. At baseline, patients with ILD had lower levels of anti-Jo-1 antibodies than those without ILD (p = 0.012). Baseline anti-Jo-1 antibody levels were higher in patients with muscle weakness, skin involvement, and arthritis (all p

Aim We aimed to explore a new and readily available practical marker for rapidly progressive interstitial lung disease (RP-ILD) and poor short-term outcomes in patients with idiopathic inflammatory myopathies (IIM).Methods A total of 1822 consecutive patients with IIM between 2009 and 2021 were evaluated retrospectively. All proven cases of naïve ILD with complete medical records were included. Red cell distribution width (RDW) values at the initial stage, 3 months and last follow-up were collected. The clinical characteristics and outcomes of the patients were recorded.Results We identified 532 patients with IIM with an average follow-up of 4 years. ILD prevalence was higher in patients of elevated RDW (p0 was higher in patients with RP-ILD and positive for anti-melanoma differentiation-associated gene 5 antibody who died within 3 months (87.5%) compared with those alive at 3 months (24.6%) (p

Currently, although energy conservation related research in buildings is a matter of great urgency in the context of an ever more serious energy crisis, people seem to pay more attention on the field of civil engineering, such as the design, construction, monitoring and maintenance management of building structures. This is also evidenced by the authors' extensive research and strong practical engineering experience in infrastructure projects such as bridges. This study first presents the general building energy situation. The state of the art of the energy in buildings is then reviewed, followed by pointing out the intelligent monitoring-based future direction, and then the final goal towards the smart city can be expected. Specifically, more than one hundred published papers are selected for sample analysis, taking into account different research topics and different publication dates etc. The research topics, research methods and research conclusions of these published papers are very different, and they have not yet produced results that could be generally accepted. Actually, most of the published papers focus on the analysis and conservation of building energy, including the energy model for analysis and prediction, the energy affected by resident behavior and building forms, the renewable energy utilization and zero energy building. While a small part of the published papers is concerned with the resilient structural energy dissipation and collapse-resistant. Furthermore, the intelligent monitoring of building energy, supported by advanced sensor development and big data analysis technology, is also providing us a more promising future on the way to the smart city. It should be further noted that the design and construction codes or standards related to building energy have not yet been retrieved, and these have a strong guiding significance for engineering practice. Therefore, more research needs to be done to expect a better practical outcome.

The short message function of the BeiDou satellite system, due to its strong concurrent processing capabilities, can quickly and accurately send information to the target location in emergency situations. However, because of data redundancy and limitations on message length, a single piece of information often requires multiple transmissions through BeiDou short messages to be completed, resulting in limited transmission capacity. To improve the transmission capacity of information, it is necessary to compress the information during transmission using BeiDou’s short message communication function for maritime safety information. This paper proposes a Byte Encoding-enhanced Prediction by Partial Matching, variant D (BPPMd) algorithm that is particularly suitable for transmitting maritime safety information. Combined with a maritime safety information encoding algorithm (ME), it further improves compression efficiency, optimizes byte space, reduces information redundancy, and ensures the accuracy of the information. In this study, we constructed a maritime safety information dataset that includes three categories of information: meteorological warnings, navigation warnings, and disaster warnings. Experimental results show that the proposed algorithm is particularly suitable for compressing the maritime safety information dataset and outperforms other benchmark algorithms. Therefore, this study indicates that the proposed lossless compression method can be a feasible and effective solution for BeiDou short message communication.

Detecting hydrogen leaks remains a pivotal challenge demanding robust solutions. Among diverse detection techniques, the fiber-optic method distinguishes itself through unique benefits, such as its distributed measurement properties. The adoption of hydrogen-sensitive materials coated on fibers has gained significant traction in research circles, credited to its operational simplicity and exceptional adaptability across varied conditions. This manuscript offers an exhaustive investigation into hydrogen-sensitive materials and their incorporation into fiber-optic hydrogen sensors. The research profoundly analyzes the sensor architectures, performance indicators, and the spectrum of sensing materials. A detailed understanding of these sensors’ potentials and constraints emerges through rigorous examination, juxtaposition, and holistic discourse. Furthermore, this analysis judiciously assesses the inherent challenges tied to these systems, simultaneously highlighting potential pathways for future innovation. By spotlighting the hurdles and opportunities, this paper furnishes a view on hydrogen sensing technology, particularly related to optical fiber-based applications.

Colorectal cancer (CRC) is one of the most common types of cancer worldwide and the second leading cause of cancer-related death in the world. In recent years, the incidence of CRC has risen to the second place in China and more and more attention has been paid to its research. It has been found that the structure of intestinal flora is closely related to the occurrence and development of CRC. Probiotics, as a group of intestinal beneficial microorganisms, have the functions of regulating intestinal immunity, enhancing intestinal barrier and balancing of natural gut microflora. They play a significant role in the prevention and adjuvant therapy of CRC. This paper reviews the research progress on the effect of intestinal flora on CRC as well as the mechanism of probiotics on colorectal cancer, in order to lay a foundation for probiotics to prevent and alleviate CRC.

Introduction To investigate the clinical, radiographic and pathological features of interstitial lung disease (ILD) in patients with anti-melanoma differentiation-associated gene 5 antibody-positive dermatomyositis (anti-MDA5+DM).Methods We retrospectively analysed the medical records of patients with anti-MDA5+DM who had undergone radiological examination, and lung histopathology was performed on 17 of them.Results This study examined 329 patients with anti-MDA5+DM, of whom 308 (93.6%) were diagnosed with ILD and 177 (53.8%) exhibited rapidly progressive ILD (RPILD). The most common radiographic patterns were organising pneumonia (OP) (43.2%), non-specific interstitial pneumonia (NSIP) (26.4%) and NSIP+OP (18.5%). Histological analysis showed NSIP (41.2%) and NSIP+OP (47.1%) to be the predominant patterns. However, in the 17 patients who underwent lung histopathology, the coincidence rate between radiological and histopathological diagnoses was only 11.8%. Compared with patients without RPILD, those with RPILD showed a higher prevalence of NSIP+OP (26.6% vs 10.7%, p=0.001) and a lower prevalence of NSIP pattern (21.5% vs 37.4%, p=0.002) on high-resolution CT. Furthermore, patients with radiographic patterns of NSIP+OP or diffuse alveolar damage (DAD) had more risk factors for poor prognosis, with 12-month mortality rates of 45.9% and 100%, respectively.Conclusions RPILD was commonly observed in patients with anti-MDA5+DM. OP was identified as the predominant radiographic pattern, which corresponded to a histopathological pattern of NSIP or NSIP+OP. Notably, patients exhibiting radiographic patterns of NSIP+OP or DAD were shown to have a poor prognosis.

Deep learning-based methods have demonstrated remarkable success in object detection tasks when abundant training data are available. However, in the industrial domain, acquiring a sufficient amount of training data has been a challenge. Currently, many synthetic datasets are created using 3D modeling software, which can simulate real-world scenarios and objects but often cannot achieve complete accuracy and realism. In this paper, we propose a synthetic data generation framework for industrial object detection tasks based on image-to-image translation. To address the issue of low image quality that can arise during the image translation process, we have replaced the original feature extraction module with the Residual Dense Block (RDB) module. We employ the RDB-CycleGAN network to transform CAD models into realistic images. Additionally, we have introduced the SSIM loss function to strengthen the network constraints of the generator and conducted a quantitative analysis of the improved RDB-CycleGAN-generated synthetic data. To evaluate the effectiveness of our proposed method, the synthetic data we generate effectively enhance the performance of object detection algorithms on real images. Compared to using CAD models directly, synthetic data adapt better to real-world scenarios and improve the model’s generalization ability.

In recent years, the utilization of dual-arm robots has gained substantial prominence across various industries owing to their collaborative operational capabilities. In order to achieve collision avoidance and facilitate cooperative task completion, efficient path planning plays a pivotal role. The high dimensionality associated with collaborative task execution in dual-arm robots renders existing path planning methods ineffective for conducting efficient exploration. This paper introduces a multi-agent path planning reinforcement learning algorithm that integrates an experience replay strategy, a shortest-path constraint, and the policy gradient method. To foster collaboration and avoid competition between the robot arms, the proposed approach incorporates a mechanism known as “reward cooperation, punishment competition” during the training process. Our algorithm demonstrates strong performance in the control of dual-arm robots and exhibits the potential to mitigate the challenge of reward sparsity encountered during the training process. The effectiveness of the proposed algorithm is validated through simulations and experiments, comparing the results with existing methods and showcasing its superiority in dual-arm robot path planning.

In the context of utilizing BeiDou short-message communication (SMC) for transmitting maritime safety information, challenges arise regarding information redundancy and limited message length. To address these issues, compressing the data content of SMC becomes essential. This paper proposes a dual-stage compression model based on Beidou SMC for compressing maritime safety information, aiming to achieve efficient compression and reduce information redundancy. In the first stage, a binary encoding method (MBE) specifically designed for maritime safety information is proposed to optimize the byte space of the short messages, ensuring the accuracy, integrity, and reliability of the information. In the second stage, we propose a data compression algorithm called XH based on a hash dictionary, which efficiently compresses maritime safety information and reduces information redundancy. Different maritime data have corresponding structures and compositions, which can have a significant impact on the evaluation of compression algorithms. We create a database considering six categories of objects: waves, sea ice, tsunamis, storms, weather, and navigation warnings. Experimental results demonstrate that the proposed model achieves significant compression efficiency and performance on the maritime safety data set, outperforming other benchmark algorithms.

ObjectiveTo explore the clinical features and prognoses of dermatomyositis (DM) associated with a double-positive anti-MDA5 and anti-aminoacyl-tRNA synthetase (anti-ARS) antibody presentation.MethodsWe retrospectively analyzed 1280 consecutive patients with idiopathic inflammatory myopathy (IIM). Individuals with anti-MDA5 and anti-ARS antibodies (anti-MDA5+/ARS+) were compared to anti-MDA5-/ARS+ and anti-MDA5+/ARS- control individuals based on clinical, pulmonary radiological characteristics, treatment, and follow-up information.ResultsSix individuals (0.47%) presented with anti-MDA5+/ARS+; of these, 2 (33.3%) were anti-PL-12+, 2 (33.3%) were anti-Jo-1+, 1 (16.7%) was anti-EJ+, and 1 (16.7%) was anti-PL-7+. Hallmark cutaneous manifestations, including Gottron’s sign (100%), heliotrope rash (50%), mechanic’s hand (66.7%), and skin ulcers (16.7%) were common. Anti-MDA5+/ARS+ patients tended to have higher ferritin levels (p = 0.038) than anti-MDA5-/ARS+ group, and higher CD4+ T-cell counts (p = 0.032) compared to the anti-MDA5+/ARS- group. Radiologically, NSIP with OP overlap was predominant (60%). Consolidation (60%), ground-glass attenuation (GGA) (80%), traction bronchiectasis (80%), and intralobular reticulation (100%) were common in anti-MDA5+/ARS+ individuals. All were diagnosed with ILD and 50% were categorized as RPILD. All patients received glucocorticoids combined with one or more immunosuppressants. Most (83.3%) had a good prognosis following treatment, but there was no difference in the survival rate between the three subgroups.ConclusionPresentation with anti-MDA5+/ARS+ DM was rare. The clinical and radiological characteristics of anti-MDA5+/ARS+ DM combined the features of anti-MDA5+ and anti-ARS+ individuals. Individuals with anti-MDA5+/ARS+ antibodies may respond well to glucocorticoid therapy; glucocorticoids combined with one or more immunosuppressants may be considered a basic treatment approach.

AimTo characterize the clinical features of autoimmune pancreatitis (AIP) in China and compare differences between our Chinese cohort and Western cohorts.MethodsThis was a retrospective study of patients with AIP that was carried out in the China-Japan Friendship Hospital between January 2010 and April 2021. We included a total of 50 patients (46 males and 4 females) aged between 27 and 86 years who fulfilled the international Consensus Diagnostic (ICD) Criteria. For comparative purposes, we included data from seven representative Western cohorts.ResultWhen comparing Chinese and Western patients, we found that obstructive jaundice was the most frequent initial symptom (68 vs. 43%, P < 0.001). Extra-pancreatic organ involvement was more common in Chinese patients (68 vs. 30%, P < 0.001). Sclerosing cholangitis was the most frequent extrapancreatic lesion (48 vs. 24%, P = 0.001). The elevation of serum IgG4 was more obvious in our cohort (86 vs. 49%, P < 0.001). Conversely, the rates of ANA-positivity were significantly higher in Western populations (17 vs. 50%, P = 0.006). With regards to imaging, diffuse swelling was significantly more common in China (44 vs. 27%, P = 0.021). Steroid therapy was used more frequently in our Chinese patients (84 vs. 59%, P = 0.001). The steroid-response rate was also significantly higher in our Chinese patients (85 vs. 54%, P = 0.001); However, the rate of resection was higher in Western cohorts (2 vs. 31%, P < 0.001). There was no significant difference between the two populations with regards to recurrence rate (33 vs. 33%, P = 1.000).ConclusionThis study identified significant differences between Chinese and Western populations of patients with AIP. Within the Chinese population, AIP was more likely to have jaundice and extra-pancreatic organ involvement, and elevated serum IgG4 levels. Chinese patients were also showed favorable responses to treatment with glucocorticoids.

Acute liver failure (ALF) is a serious clinical disorder with high fatality rates. Mahuang decoction (MHD), a well-known traditional Chinese medicine, has multiple pharmacological effects, such as anti-inflammation, anti-allergy, anti-asthma, and anti-hyperglycemia. In this study, we investigated the protective effect of MHD against ALF. In the lipopolysaccharide and D-galactosamine (LPS/D-GalN)-induced ALF mouse model, the elevated activities of the serum alanine and aspartate transaminases as well as the liver pathological damage were markedly alleviated by MHD. Subsequently, a metabolomics study based on the ultrahigh performance liquid chromatograph coupled with Q Exactive Orbitrap mass spectrometry was carried to clarify the therapeutic mechanisms of MHD against ALF. A total of 36 metabolites contributing to LPS/D-GalN-induced ALF were identified in the serum samples, among which the abnormalities of 27 metabolites were ameliorated by MHD. The analysis of metabolic pathways revealed that the therapeutic effects of MHD are likely due to the modulation of the metabolic disorders of tricarboxylic acid (TCA) cycle, retinol metabolism, tryptophan metabolism, arginine and proline metabolism, nicotinate and nicotinamide metabolism, phenylalanine metabolism, phenylalanine, tyrosine and tryptophan synthesis, as well as cysteine and methionine metabolism. This study demonstrated for the first time that MHD exerted an obvious protective effect against ALF mainly through the regulation of TCA cycle and amino acid metabolism, highlighting the importance of metabolomics to investigate the drug-targeted metabolic pathways.

In-service bridge structural performance analysis and prediction are usually complicated and challenging because of many unknown and uncertain factors. Contrary to the traditional structural appearance inspections and load tests, structural health monitoring (SHM) can provide a perspective for online analysis, prediction, and early warning. So far, SHM has been widely used in many bridge structures, and a lot of bridge SHM data have also been collected. However, the existing studies usually focus on some independent and unsystematic analysis methods, which are hard to use widely in engineering applications to reveal the overall structural performance. This study focuses on the structural performance analysis and prediction of the highway in-service bridge. The dynamic problems in bridge SHM are pointed out firstly, followed by a detailed analysis about the characteristics of bridge SHM data. With the consideration of different characteristics, three targeted analysis methods are proposed. An urban concrete-filled steel tube (CFST) truss girder bridge (opened to traffic in 1995) is also presented, which once experienced some prominent vibration problems. The bridge SHM system is designed and stalled after several appearance inspections, load tests, and some reinforcement measures. The data mining methods proposed (distribution function, association analysis, and time-series analysis) are employed for the analysis and prediction of structural response and deterioration extent. This study can provide some references for maintenance and management and can also build a foundation for further online analysis and early warning.

In recent years, endmember variability has received much attention in the field of hyperspectral unmixing. To solve the problem caused by the inaccuracy of the endmember signature, the endmembers are usually modeled to assume followed by a statistical distribution. However, those distribution-based methods only use the spectral information alone and do not fully exploit the possible local spatial correlation. When the pixels lie on the inhomogeneous region, the abundances of the neighboring pixels will not share the same prior constraints. Thus, in this paper, to achieve better abundance estimation performance, a method based on the Gaussian mixture model (GMM) and spatial group sparsity constraint is proposed. To fully exploit the group structure, we take the superpixel segmentation (SS) as preprocessing to generate the spatial groups. Then, we use GMM to model the endmember distribution, incorporating the spatial group sparsity as a mixed-norm regularization into the objective function. Finally, under the Bayesian framework, the conditional density function leads to a standard maximum a posteriori (MAP) problem, which can be solved using generalized expectation-maximization (GEM). Experiments on simulated and real hyperspectral data demonstrate that the proposed algorithm has higher unmixing precision compared with other state-of-the-art methods.

Gaussian mixture model (GMM) has been one of the most representative models for hyperspectral unmixing while considering endmember variability. However, the GMM unmixing models only have proper smoothness and sparsity prior constraints on the abundances and thus do not take into account the possible local spatial correlation. When the pixels that lie on the boundaries of different materials or the inhomogeneous region, the abundances of the neighboring pixels do not have those prior constraints. Thus, we propose a novel GMM unmixing method based on superpixel segmentation (SS) and low-rank representation (LRR), which is called GMM-SS-LRR. we adopt the SS in the first principal component of HSI to get the homogeneous regions. Moreover, the HSI to be unmixed is partitioned into regions where the statistical property of the abundance coefficients have the underlying low-rank property. Then, to further exploit the spatial data structure, under the Bayesian framework, we use GMM to formulate the unmixing problem, and put the low-rank property into the objective function as a prior knowledge, using generalized expectation maximization to solve the objection function. Experiments on synthetic datasets and real HSIs demonstrated that the proposed GMM-SS-LRR is efficient compared with other current popular methods.

On-line and continuous measurements of coal powder size distribution in coal-fired plants remain challenging. A coal powder size measurement system based on digital holography (DH) is developed. The effects of several factors, i.e. pixel size, recording distance, particle size, and concentration, on particle size measurement by the DH method are quantified by simulation, yielding the suitable pixel size, recording distance and particle concentration. The measurement system is implemented based on the simulation results and applied to measure particle size distribution of pulverized coal samples. Results show that the particles are clearly reconstructed from the hologram, and the measured size distributions agree well with those of the samples measured by laser particle size analyzer. This work shows that the digital holographic sizer has great potential in coal powder size distribution measurement in power plant pipes. [ABSTRACT FROM AUTHOR]