41 research outputs found
Multi-Branch Gated Fusion Network: A Method That Provides Higher-Quality Images for the USV Perception System in Maritime Hazy Condition
No full textImage data acquired by unmanned surface vehicle (USV) perception systems in hazy situations is characterized by low resolution and low contrast, which can seriously affect subsequent high-level vision tasks. To obtain high-definition images under maritime hazy conditions, an end-to-end multi-branch gated fusion network (MGFNet) is proposed. Firstly, residual channel attention, residual pixel attention, and residual spatial attention modules are applied in different branch networks. These attention modules are used to focus on high-frequency image details, thick haze area information, and contrast enhancement, respectively. In addition, the gated fusion subnetworks are proposed to output the importance weight map corresponding to each branch, and the feature maps of three different branches are linearly fused with the importance weight map to help obtain the haze-free image. Then, the network structure is evaluated based on the comparison with pertinent state-of-the-art methods using artificial and actual datasets. The experimental results demonstrate that the proposed network is superior to other previous state-of-the-art methods in the PSNR and SSIM and has a better visual effect in qualitative image comparison. Finally, the network is further applied to the hazy sea–skyline detection task, and advanced results are still achieved
Multiple features learning for ship classification in optical imagery
No full textThe sea surface vessel/ship classification is a challenging problem with enormous implications to the world’s global supply chain and militaries. The problem is similar to other well-studied problems in object recognition such as face recognition. However, it is more complex since ships’ appearance is easily affected by external factors such as lighting or weather conditions, viewing geometry and sea state. The large within-class variations in some vessels also make ship classification more complicated and challenging. In this paper, we propose an effective multiple features learning (MFL) framework for ship classification, which contains three types of features: Gabor-based multi-scale completed local binary patterns (MS-CLBP), patch-based MS-CLBP and Fisher vector, and combination of Bag of visual words (BOVW) and spatial pyramid matching (SPM). After multiple feature learning, feature-level fusion and decision-level fusion are both investigated for final classification. In the proposed framework, typical support vector machine (SVM) classifier is employed to provide posterior-probability estimation. Experimental results on remote sensing ship image datasets demonstrate that the proposed approach shows a consistent improvement on performance when compared to some state-of-the-art methods
Author response: Structural basis of host recognition and biofilm formation by Salmonella Saf pili
No full textAnaliza charakterystyk fraktalnych skupisk cząstek rudy pod obciążeniem quasi-statycznym
No full textTo investigate the quasi-static loading fracture characteristics of a certain wolframite ore, a crushing model of ore particle clusters was established using the Tavares model. The fracture characteristics of ore particle clusters under quasi-static loading were studied through simulation, and the results were compared with experimental data from crushing tests. The findings revealed that under different quasi-static loads, the post-crushing particle size distribution varied significantly. With increasing quasi-static loads, the proportion of smaller particles after crushing increased, indicating a higher degree of fragmentation in the ore particle clusters. Additionally, as the quasi-static load continued to increase, the average particle size of the ore particle clusters decreased. The average particle size provided a direct and intuitive measure of the fragmentation status of the ore particle clusters. Furthermore, the ore particle clusters exhibited fractal patterns during quasi-static loading, with the fractal dimension of particle size distribution ranging from 0.9205 to 1.3603 under different quasi-static loads. The fractal dimension increased with the increment of quasi-static load, indicating a higher level of fragmentation. Moreover, the fractal dimension of ore particle clusters during quasi-static loading exhibited a decreasing trend with the average particle size of fragmentation. This study contributes to a comprehensive understanding of the fractal characteristics associated with the quasi-static loading fracture of ore particle clusters.Aby zbadać charakterystykę pękania pod obciążeniem quasi-statycznym określonej rudy wolframitu, opracowano model kruszenia skupisk cząstek rudy przy użyciu modelu Tavaresa. Charakterystykę pękania skupisk cząstek rudy pod obciążeniem quasi-statycznym zbadano poprzez symulację, a wyniki porównano z danymi eksperymentalnymi z testów kruszenia. Wyniki badań wykazały, że przy różnych obciążeniach quasi-statycznych rozkład wielkości cząstek po kruszeniu znacznie się różnił. Wraz ze wzrostem obciążeń quasi-statycznych zwiększał się udział mniejszych cząstek po kruszeniu, co wskazuje na wyższy stopień rozdrobnienia skupisk cząstek rudy. Dodatkowo, w miarę dalszego wzrostu obciążenia quasi-statycznego, średni rozmiar cząstek w skupiskach cząstek rudy zmniejszał się. Średni rozmiar cząstek stanowił bezpośrednią i intuicyjną miarę stanu rozdrobnienia skupisk cząstek rudy. Co więcej, skupiska cząstek rudy wykazywały fraktalne wzory przy quasi-statycznym obciążeniu, z fraktalnym wymiarem rozkładu wielkości cząstek w zakresie od 0,9205 do 1,3603 przy różnych obciążeniach quasi-statycznych. Wymiar fraktalny wzrastał wraz ze wzrostem obciążenia quasi-statycznego, wskazując na wyższy stopień kruszenia. Co więcej, wymiar fraktalny skupisk cząstek rudy podczas quasi-statycznego obciążenia wykazywał tendencję malejącą wraz ze średnim rozmiarem cząstek kruszenia. Badanie to przyczynia się do wszechstronnego zrozumienia charakterystyki fraktalnej związanej z quasi-statycznym pękaniem obciążeniowym skupisk cząstek rudy
Evaluation of Complexity Issues in Building Information Modeling Diffusion Research
No full textThis study aimed to ascertain the research status of complexity issues in building information modeling (BIM) diffusion and identify future research directions in this field. A total of 366 relevant journal articles were holistically evaluated. The visualization analysis indicated that management aspects, emergent trends (such as green building, facility management, and automation), and theme clusters (such as interoperability, waste management, laser scanning, stakeholder management, and energy efficiency) are shaping BIM research towards complexity. Areas such as supply chain, cost, digital twin, and web are also essential. The manual qualitative evaluation classified the complexity issues in BIM diffusion research into three types (complexities of network-based BIM evolution, impact of BIM adoption circumstances, and BIM-based complexity reduction for informed decision making). It was concluded that BIM has been shifting towards information models and systems-based life cycle management, waste control for healthy urban environments, and complex data analysis from a big data perspective, not only in building projects but also in heritage and infrastructure, or at the city scale, for informed decision making and automatic responses. Future research should investigate the co-evolution between collaborative networks and BIM artefacts and work processes, quality improvement of BIM-based complex networks, BIM post-adoption behaviors influenced by complex environmental contexts, and BIM-based complexity reduction approaches
A study of the correlation between stroke and gut microbiota over the last 20years: a bibliometric analysis
No full textPurposeThis study intends to uncover a more thorough knowledge structure, research hotspots, and future trends in the field by presenting an overview of the relationship between stroke and gut microbiota in the past two decades.MethodStudies on stroke and gut microbiota correlations published between 1st January 2002 and 31st December 2021 were retrieved from the Web of Science Core Collection and then visualized and scientometrically analyzed using CiteSpace V.ResultsA total of 660 papers were included in the study, among which the United States, the United Kingdom, and Germany were the leading research centers. Cleveland Clinic, Southern Medical University, and Chinese Academy of Science were the top three institutions. The NATURE was the most frequently co-cited journal. STANLEY L HAZEN was the most published author, and Tang WHW was the most cited one. The co-occurrence analysis revealed eight clusters (i.e., brain-gut microbiota axis, fecal microbiome transplantation, gut microbiota, hypertension, TMAO, ischemic stroke, neuroinflammation, atopobiosis). “gut microbiota,” “Escherichia coli,” “cardiovascular disease,” “risk,” “disease,” “ischemic stroke,” “stroke,” “metabolism,” “inflammation,” and “phosphatidylcholine” were the most recent keyword explosions.ConclusionFindings suggest that in the next 10 years, the number of publications produced annually may increase significantly. Future research trends tend to concentrate on the mechanisms of stroke and gut microbiota, with the inflammation and immunological mechanisms, TMAO, and fecal transplantation as hotspots. And the relationship between these mechanisms and a particular cardiovascular illness may also be a future research trend
An emotion analysis dataset of course comment texts in massive online learning course platforms
No full textDatasets are critical for emotion analysis in the machine learning field. This study aims to explore emotion analysis datasets and related benchmarks in online learning, since, currently, there are very few studies that explore the same. We have scientifically labeled the topic and nine-category emotion of 4715 comment texts in online learning platforms using the “three-person voting label method” based on the “sentence-level” and multi-category labeling dimensions with our self-developed system. After testing the consistency of the labeling results using the Fleiss Kappa method, we found that the consistency of the dataset was about 0.51, representing a moderate strength of agreement. Based on the dataset, the prediction accuracy of the Long-Short Term Memory (LSTM) method is about 0.68. This dataset provides a benchmark for the multi- category emotion dataset in the Chinese online learning field. It can provide a basis for the subsequent solution of emotion analysis, monitoring, and intervention in the education field. It can also provide a reference for constructing subsequent datasets in the education field.We need to remind you that this is a Chinese dataset. If you want to use this dataset, please contact the author and you should request for the dataset below
Explore new clinical application of Huanglian and corresponding compound prescriptions from their traditional use
No full textHuanglian is a commonly used Chinese medicinal herb in the ancient and the present. It has a history of 2000 years in clinical application, having the efficacy of "Clear away heat and remove dampness, purge the sthenic fire and eliminate toxic materials", therefore can be used for various diseases or syndromes in types of dampness-heat and fire-toxin by internal or external use. Compound prescriptions mainly based on Huanglian or prescribed by Huanglian, such as Puji Xiaodu Yin, Huanglian Jiedu Tang, Zhusha Anshen Wan, Qingying Tang, Angong Niuhuang Wan, Niuhuang Qingxin Wan, Jiaotai Wan, Huanglian Ejiao Tang, Zuojin Wan, Danggui Longhui Wan, Huanglian Yanggan Wan, Wu Xiexin Tang, Lianpu Yin, Gegen Huangqin Huanglian Tang, Baitouweng Tang, Xianglian Wan etc. All of these are well-known formulas for clearing away toxin of heat-fire of heart and liver, as well as dampness-heat of stomach and intestines. Nowadays, Huanglian is generally considered as a kind of antibiotic and antivirus herb and is widely used for many infective diseases. In fact, it is also used to cure cardiovascular and cerebrovascular diseases, diabetes and cancer based on pharmacological studies. Having been using Huanglian in treating the above diseases and having conducted clinical and experimental research on cancer and liver diseases, the author observed that Huanglian and its compound prescriptions have obvious effects on liver diseases such as acute or chronic hepatitis, liver fibrosis, liver cirrhosis and liver cancer due to types of dampness-heat and fire-toxin. Part of the effects has been proved by experimental research and it is worth carrying out more research in this area for development and clinical application.link_to_subscribed_fulltex
Interleukin-33 promotes inflammation-induced lymphangiogenesis via ST2/TRAF6-mediated Akt/eNOS/NO signalling pathway
No full textAbstractThe interplay between inflammation and lymphangiogenesis is mediated by various cytokines. However, most of these molecules and their associated mechanism are yet to be defined. Here, we explored the role of IL-33 in modulating inflammation-induced lymphangiogenesis (ILA) and its underlying mechanisms using an ILA mouse model and a lymphatic endothelial cell (LEC) line. Our results show that IL-33 promoted the proliferation, migration and tube formation of LECs and ILA in vivo. The pro-lymphangiogenic activity of IL-33 was abolished by ST2 blockage. In mechanisms, IL-33 induced the phosphorylation of Akt/eNOS to produce NO in LECs. The IL-33-induced Akt/eNOS activation was suppressed by the PI3K-specific-inhibitor wortmannin, and NO-production was inhibited by both wortmannin and the NO synthase-inhibitor NMA. Knock-down of ST2 or TRAF6 suppressed Akt/eNOS phosphorylation and NO production. The reduction of NO treated with wortmannin or NMA abolished the promoting effects of IL-33 on the chemotactic motility and tube formation of HDLECs. In vivo, IL-33-induced ILA was also impaired in eNOS−/− mice. In conclusion, our study is the first to show that IL-33 promotes inflammation-induced lymphangiogenesis via a ST2/TRAF6-mediated Akt/eNOS/NO signalling pathway. This findings may provide us more opportunities to treat inflammation and lymphangiogenesis associated diseases.</jats:p
MASS-LSVD: A Large-Scale First-View Dataset for Marine Vessel Detection
No full textIn this paper, we release a new large-scale dataset containing multiple categories of ships and floating objects at sea, which we call MASS-LSVD. It is used to train and validate target detection algorithms and future large models for ship autopiloting. The dataset was captured by a visible light camera installed aboard the world’s first intelligent research, teaching, and training ship, “Xinhongzhuan”. This MASS (maritime autonomous surface ship) was operated by Dalian Maritime University, China. We have collected more than 4000 h of video of the “Xinhongzhuan” vessel’s voyage in the Bohai Sea and other areas, which are carefully classified and filtered to cover as much as possible the various types of sample data in the marine environment, such as light intensity, weather, hull shading, data from ocean-going voyages, entering and exiting ports, etc. The dataset contains 64,263 1K-resolution images captured from video footage, covering four main ship types: Fishing Boat, Bulk Carrier, Cruise Ship, Container ship, and an ‘Other Ships’ class, for vessels that cannot be specifically classified. The dataset currently contains 64,263 pairs of 1K-resolution images covering four common ship types (fishing boat, bulk carrier, cruise ship, container, and other ship, where no specific ship type can be determined). All the images have been labeled with high-precision manual bounding boxes. In this paper, the MASS-LSVD dataset is used as the basis for training various target detection algorithms and comparing them with other datasets, which compensates for the lack of first-view images in the vessel target detection dataset, and MASS-LSVD is expected to be used to facilitate the research and application of autonomous ship navigation models in the framework of computer vision
