In the manufacturing process involving grinding wheels, challenges in fine-tuning grinding machines are typically addressed by craftsmen through subjective observations of sparks and sounds. However, most current anomaly detection methods mainly aim at a single modality, whereas existing multimodal methods cannot effectively cope with a common issue. To address this, this paper introduces an innovative mechanism, AI-Based Multimodal Anomaly Detection (AMAD), designed to optimize the efficiency and accuracy of grinding wheel production lines. The proposed AMAD includes data preprocessing and multimodal anomaly detection, accurately identifying anomalies in grinding wheel operation videos. In the data preprocessing phase, the proposed AMAD utilizes Mel Frequency Cepstral Coefficients (MFCC) and AutoEncoder for audio processing and segmentation for video processing. In the multimodal anomaly detection phase, the proposed AMAD employs Convolutional Neural Networks (CNN) for audio analysis and Convolutional Long Short-Term Memory (ConvLSTM) for video analysis. By combining both audio and video modalities, the proposed AMAD effectively predicts whether the input video represents normal or abnormal grinding wheel operations. This multimodal approach not only improves the accuracy of anomaly detection but also enhances the robustness of the system. Simulation results demonstrate that the proposed AMAD significantly improves performance in anomaly detection in terms of precision, recall, and F1-Score.

Fuel cell electric buses (FCEBs) are widely recognized as a promising low-carbon solution for long-distance public transportation. However, their adoption in intercity coach services remains limited, particularly at the demonstration stage, where multiple technological, economic, policy, and infrastructure factors interact. Prior research has predominantly examined these factors in isolation, with limited attention to their interrelationships. To address this gap, the present study proposes a hybrid multi-criteria decision-making (MCDM) framework that integrates a modified Delphi-based expert screening method, interval type-2 fuzzy sets (IT2FS), and the DEMATEL-based Analytic Network Process (DANP). Using the STEEP framework, twenty candidate criteria derived from the literature were screened by ten experts and refined to fifteen criteria relevant to the Taiwanese intercity coach context. A second panel of twelve experts then assessed the perceived directional influence relationships among the retained criteria using linguistic judgments modeled with IT2FS, and DANP was applied to derive network-adjusted priority weights. Expert assessments indicate that policy stability and long-term commitment, financial incentives and subsidy schemes, and infrastructure investment benefits received the highest priority weights in the current Taiwanese context. The perceived influence structure further indicates that the policy and technology dimensions primarily function as net influencing dimensions, whereas the economic and social dimensions are more strongly positioned as net-receiving dimensions within the expert-judgment network. These findings should be interpreted as context-specific, expert-based assessments rather than objectively established or statistically causal determinants of FCEB adoption. The results provide a structured decision-support perspective for governments, coach operators, and hydrogen supply-chain stakeholders when evaluating priorities for FCEB deployment in Taiwan and comparable demonstration-stage contexts.