AI, Robotics and Space

Browse

Browsing AI, Robotics and Space by Subject "4605 Data Management and Data Science"

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    Enhancing performance and interpretability of multivariate time-series model through sparse saliency
    (IEEE, 2024-09-24) Kong, Xiangqi; Xing, Yang; Liu, Zeyu; Tsourdos, Antonios; Wikander, Andreas
    Explainable time-series modelling is an essential task for modern intelligent transportation systems (ITS). How-ever, balancing accuracy and interpretability in multivariate time series forecasting presents significant challenges. These challenges arise from the necessity to understand the significance of features and their temporal variations. Factors such as autocorrelation in time series and data processing techniques like sliding windows expand feature sets, thereby complicating pattern recognition using traditional post-hoc explanation methods and making the issue even more complex. To overcome these challenges, in this study, we propose a flexible post-process approach which generates sparse and normalized saliency values based on existing saliency generation methods such as GradientSHAP. Additionally, an optional window aggregation and alignment strategy is introduced to align with the original time series dataset, enhancing the intuitive understanding of feature importance. Furthermore, the potential use of sparse saliency for data augmentation to improve the model is explored. Lastly, we utilize naturalistic data from San Francisco airport to demonstrate our approach for ITS time-series prediction and explanation. The evaluation results indicate that integrating sparse saliency from high-performing models not only boosts the performance of XGBoost models by 10.92% but also simplifies model complexity, facilitating easier interpretation.
  • Thumbnail Image
    ItemOpen Access
    How to find opinion leader on the online social network?
    (Springer, 2025-05-01) Jin, Bailu; Zou, Mengbang; Wei, Zhuangkun; Guo, Weisi
    Online social networks (OSNs) provide a platform for individuals to share information, exchange ideas, and build social connections beyond in-person interactions. For a specific topic or community, opinion leaders are individuals who have a significant influence on others’ opinions. Detecting opinion leaders and modeling influence dynamics is crucial as they play a vital role in shaping public opinion and driving conversations. Existing research have extensively explored various graph-based and psychology-based methods for detecting opinion leaders, but there is a lack of cross-disciplinary consensus between definitions and methods. For example, node centrality in graph theory does not necessarily align with the opinion leader concepts in social psychology. This review paper aims to address this multi-disciplinary research area by introducing and connecting the diverse methodologies for identifying influential nodes. The key novelty is to review connections and cross-compare different multi-disciplinary approaches that have origins in: social theory, graph theory, compressed sensing theory, and control theory. Our first contribution is to develop cross-disciplinary discussion on how they tell a different tale of networked influence. Our second contribution is to propose trans-disciplinary research method on embedding socio-physical influence models into graph signal analysis. We showcase inter- and trans-disciplinary methods through a Twitter case study to compare their performance and elucidate the research progression with relation to psychology theory. We hope the comparative analysis can inspire further research in this cross-disciplinary area.
  • Thumbnail Image
    ItemOpen Access
    Mitigating no fault found phenomena through ensemble learning: a mixture of experts approach
    (IEEE, 2024-09-24) Liu, Zeyu; Kong, Xiangqi; Chen, Yang; Wang, Ziyue; Jia, Huamin; Al-Rubaye, Saba
    In the aviation industry, the reliance on precise fault diagnostic decision-making is critical for equipment maintenance. A significant challenge encountered is the erroneous categorization of components under 'No Fault Found' (NFF), which subjects these components to unwarranted repairs or further testing. Such misclassifications not only trap on airlines through costly cycles of unnecessary maintenance but also exacerbate degeneration and potential safety hazards. Consequently, there is a heightened demand for the development of effective fault diagnosis models that are adapting to the aircraft complex systems and adeptly addressing issues related to the NFF phenomenon. In this study, we draw inspiration from ensemble learning and propose a multiple Naive Bayes experts (MNBMoEs) approach based on a mixture of experts (MoEs) model. This method leverages the predictive advantages of each sub-model on specific features, allowing the hybrid expert decision to outperform any single expert. It also includes a quantitative analysis method for the NFF issue, derived from the confusion matrix according to the industrial definition of NFF. Experiments evaluated on public datasets results show that the ensemble learning approach, based on Mixture of Multiple Naive-Bayes expert models, can effectively utilize the strengths of different models, improving fault diagnosis accuracy to 96.96%, with a maximum reduction in NFF occurrence rates of up to 94.17% and 84.2% model performance improvement.