GLORIA

GEOMAR Library Ocean Research Information Access

X

Your email was sent successfully. Check your inbox.

An error occurred while sending the email. Please try again.

Proceed reservation?

Export
  • 1
    Online Resource
    Online Resource
    A Multi-Task-Based Deep Multi-Scale Information Fusion Method for Intelligent Diagnosis of Bearing Faults
    MDPI AG ; 2023
    In:  Machines Vol. 11, No. 2 ( 2023-02-01), p. 198-
    Details
    In: Machines, MDPI AG, Vol. 11, No. 2 ( 2023-02-01), p. 198-
    Abstract: The use of deep learning for fault diagnosis is already a common approach. However, integrating discriminative information of fault types and scales into deep learning models for rich multitask fault feature diagnosis still deserves attention. In this study, a deep multitask-based multiscale feature fusion network model (MEAT) is proposed to address the limitations and poor adaptability of traditional convolutional neural network models for complex jobs. The model performed multidimensional feature extraction through convolution at different scales to obtain different levels of fault information, used a hierarchical attention mechanism to weight the fusion of features to achieve an accuracy of 99.95% for the total task of fault six classification, and considered two subtasks in fault classification to discriminate fault size and fault type through multi-task mapping decomposition. Of these, the highest accuracy of fault size classification reached 100%. In addition, Precision, ReCall, and Sacore F1 all reached the index of 1, which achieved the accurate diagnosis of bearing faults.
    Type of Medium: Online Resource
    ISSN: 2075-1702
    URL: Article
    DOI: 10.3390/machines11020198
    Language: English
    Publisher: MDPI AG
    Publication Date: 2023
    detail.hit.zdb_id: 2704328-9
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 2
    Online Resource
    Online Resource
    The Machine-Learning-Mediated Interface of Microbiome and Genetic Risk Stratification in Neuroblastoma Reveals Molecular Pathways Related to Patient Survival
    MDPI AG ; 2022
    In:  Cancers Vol. 14, No. 12 ( 2022-06-10), p. 2874-
    Details
    In: Cancers, MDPI AG, Vol. 14, No. 12 ( 2022-06-10), p. 2874-
    Abstract: Currently, most neuroblastoma patients are treated according to the Children’s Oncology Group (COG) risk group assignment; however, neuroblastoma’s heterogeneity renders only a few predictors for treatment response, resulting in excessive treatment. Here, we sought to couple COG risk classification with tumor intracellular microbiome, which is part of the molecular signature of a tumor. We determine that an intra-tumor microbial gene abundance score, namely M-score, separates the high COG-risk patients into two subpopulations (Mhigh and Mlow) with higher accuracy in risk stratification than the current COG risk assessment, thus sparing a subset of high COG-risk patients from being subjected to traditional high-risk therapies. Mechanistically, the classification power of M-scores implies the effect of CREB over-activation, which may influence the critical genes involved in cellular proliferation, anti-apoptosis, and angiogenesis, affecting tumor cell proliferation survival and metastasis. Thus, intracellular microbiota abundance in neuroblastoma regulates intracellular signals to affect patients’ survival.
    Type of Medium: Online Resource
    ISSN: 2072-6694
    URL: Article
    DOI: 10.3390/cancers14122874
    Language: English
    Publisher: MDPI AG
    Publication Date: 2022
    detail.hit.zdb_id: 2527080-1
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 3
    Online Resource
    Online Resource
    Design and Analysis Method of Piezoelectric Liquid Driving Device with Elastic External Displacement
    MDPI AG ; 2024
    In:  Micromachines Vol. 15, No. 4 ( 2024-04-13), p. 523-
    Details
    In: Micromachines, MDPI AG, Vol. 15, No. 4 ( 2024-04-13), p. 523-
    Abstract: In piezoelectric drive, resonant drive is an important driving mode in which the external elastic force and electric drive signal are the key factors. In this paper, the effects of the coupling of external elastic force and liquid parameters with the structure on the vibrator resonance frequency and liquid drive are analyzed by numerical simulation. The fluid-structure coupling model for numerical analysis of the elastic force was established, the principle of microdroplet generation and the coupling method of the elastic force were studied, and the changes in the resonant frequency and mode induced by the changes in the liquid parameters in different cavities were analyzed. Through the coupled simulation and calculation of the pressure and deformation of the cavity, the laser vibration measurement test was carried out to test the effect of the vibration mode analysis. The driving model of the fluid jet driven by the elastic force on the piezoelectric drive was further established. The changing shape of the fluid jet under different elastic forces was analyzed, and the influence law of the external elastic force on the change in the droplet separation was determined. It provides reference support for further external microcontrol of droplet motion.
    Type of Medium: Online Resource
    ISSN: 2072-666X
    URL: Article
    DOI: 10.3390/mi15040523
    Language: English
    Publisher: MDPI AG
    Publication Date: 2024
    detail.hit.zdb_id: 2620864-7
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 4
    Online Resource
    Online Resource
    The Impact of Aerosol Vertical Distribution on a Deep Convective Cloud
    MDPI AG ; 2021
    In:  Atmosphere Vol. 12, No. 6 ( 2021-05-25), p. 675-
    Details
    In: Atmosphere, MDPI AG, Vol. 12, No. 6 ( 2021-05-25), p. 675-
    Abstract: This study investigates the effects of aerosol vertical distribution on a deep convective cloud system. We intend to elucidate the mechanisms for aerosols entering the cloud from different heights, and how they affect cloud microphysics and precipitation. A thermal bubble is released at 1.5 km initially to run an idealized case using the Weather Research and Forecast (WRF) model. The aerosol layer with high concentration was initially put at different altitudes in the model to study the mechanisms and the number of aerosols entering the cloud. It was found that there are three mechanisms for aerosols from different heights to enter the cloud, depending on their relative height with the thermal bubble. Aerosols from lower altitudes (below 1 km) enter the cloud through pumping, while aerosols from higher altitudes (2–3 km, 3–5 km) enter the cloud through entrainment. Both mechanisms lead to low cloud condensation nuclei (CCN) concentration in the cloud. Only aerosols from intermediate altitudes (1–2 km), which is the same as the initial height of the thermal bubble, enter the cloud mainly by ascending with the bubble and lead to high CCN concentration in the cloud. The differences in activated CCN concentration affect the microphysical processes and precipitation remarkably. For the simulations with an initial aerosol layer at 1–2 km and 0–5 km, aerosols can enter the cloud more efficiently than the other four simulations. More activated CCNs in these two simulations lead to more graupels with smaller sizes at higher altitudes, which delays the precipitation but makes the precipitation last longer. However, the accumulated precipitation is similar in all six simulations, no matter what aerosol vertical distribution is like. The results in this study indicate that the altitude of aerosol layers determines the mechanisms for aerosols entering clouds, CCN concentration in the cloud, and to what extent the cloud microphysical processes and precipitation are affected.
    Type of Medium: Online Resource
    ISSN: 2073-4433
    URL: Article
    DOI: 10.3390/atmos12060675
    Language: English
    Publisher: MDPI AG
    Publication Date: 2021
    detail.hit.zdb_id: 2605928-9
    SSG: 23
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
Close ⊗
This website uses cookies and the analysis tool Matomo. More information can be found here...