Category: 7. Maths

Continue Reading

  • Outlier-tolerant relative positioning method based on multi-source information fusion for unmanned aerial vehicles

    Outlier-tolerant relative positioning method based on multi-source information fusion for unmanned aerial vehicles

    In this section, the outlier-tolerant LS method is applied to the relative positioning of two UAVs via multi-source information fusion, to avoid the adverse impact of abnormal measurement data on the accuracy of relative positioning and ensure…

    Continue Reading

  • Climate change prediction in Saudi Arabia using a CNN GRU LSTM hybrid deep learning model in al Qassim region

    Climate change prediction in Saudi Arabia using a CNN GRU LSTM hybrid deep learning model in al Qassim region

    We conducted our experiments using Jupyter Notebook version 7.2.1, a popular tool for data analysis and visualization in Python. Jupyter Notebook offers a versatile environment for writing, running, and documenting code, as well as creating…

    Continue Reading

  • Research and application of deep learning object detection methods for forest fire smoke recognition

    Research and application of deep learning object detection methods for forest fire smoke recognition

    Evaluation and analysis of loss functions

    In object detection tasks, model performance is typically assessed through the comprehensive optimization of multiple loss functions to ensure effective learning of various target attributes. This study…

    Continue Reading

  • Multimodal anomaly detection in complex environments using video and audio fusion

    Multimodal anomaly detection in complex environments using video and audio fusion

    Datasets collection

    To assess the effectiveness of the proposed algorithm in different scenes, two enhanced public video datasets are selected: the UCSD Ped2 dataset (dataset A), which mainly contains outdoor scenes of pedestrians walking, and…

    Continue Reading

  • A hierarchical model for community identification in complex networks through modularity and genetic algorithm

    A hierarchical model for community identification in complex networks through modularity and genetic algorithm

    Identification of community structures in complex networks using similarity or modularity criteria is a common practice. Existing related methods are not capable of accurately estimating the exact number of nodes present in each community. This…

    Continue Reading

  • Modeling the decarburization of expansion droplets based on the solid phase ratio of slag and data fitting during BOF steelmaking process

    Modeling the decarburization of expansion droplets based on the solid phase ratio of slag and data fitting during BOF steelmaking process

    For the multiphase slag conditions, the impact of the solid phase ratio on the physicochemical properties of slag need be considered. In this section, the solid phase ratio was analyzed at different FeO contents, and the improved decarburization…

    Continue Reading

  • Interpolation and differentiation of alchemical degrees of freedom in machine learning interatomic potentials

    Interpolation and differentiation of alchemical degrees of freedom in machine learning interatomic potentials

    Alchemical graph and message passing

    Prototypical MLIP construction

    Our objective here is to introduce modifications to the non-learnable parts of the MLIPs so that we can model the alchemical compositions of materials without further fine-tuning…

    Continue Reading

  • Developing an intuitive decision support system for equitable vaccine distribution during pandemics

    Developing an intuitive decision support system for equitable vaccine distribution during pandemics

    Key stakeholders and roles in the Norwegian vaccine distribution network

    The interviews with key stakeholders revealed that, after the H1N1 pandemic 2009, new policy guidelines were developed for new (influenza) pandemics/epidemics at the national…

    Continue Reading

  • Discrete wavelet integrated convolutional residual network for bearing fault diagnosis under noise and variable operating conditions

    Discrete wavelet integrated convolutional residual network for bearing fault diagnosis under noise and variable operating conditions

    To illustrate the anti-noise capabilities of the proposed DWCResNet in varying circumstances, a bearing fault diagnosis validation is conducted utilising the Case Western Reserve University (CWRU) bearing data and the Paderborn University (PU)…

    Continue Reading