The etiology of cardiovascular disease is still an unsolved world problem, and high morbidity, disability, and mortality are the main characteristics of cardiovascular diseases. There is, therefore, a need for effective and rapid early prediction of likely outcomes in patients with cardiovascular disease using artificial intelligence (AI) techniques. The Internet of Things (IoT) is becoming a catalyst for enhancing the capabilities of AI applications. Data are collected through IoT sensors and analyzed and predicted using machine learning (ML). Existing traditional ML models do not handle data inequities well and have relatively low model prediction accuracy. To address this problem, considering the data observation mechanism and training methods of different algorithms, this paper proposes an ensemble framework based on stacking model fusion, from Support Vector Machines (SVM), K-Nearest Neighbor (KNN), Logistic Regression (LR), Random Forest (RF), Extra Tree (ET), Gradient Boosting Decision Tree (GBDT), XGBoost, LightGBM, CatBoost, and Multilayer Perceptron (MLP) (10 classifiers to select the optimal base learners). In order to avoid the overfitting phenomenon generated by the base learners, we use the Logistic Regression (LR) simple linear classifier as the meta learner. We validated the proposed algorithm using a fused Heart Dataset from several UCI machine learning repositories and another publicly available Heart Attack Dataset, and compared it with 10 single classifier models. The experimental results show that the proposed stacking classifier outperforms other classifiers in terms of accuracy and applicability.

In order to reduce the harm of earthquakes to human society, all governments actively promote the construction and development of earthquake emergency rescue work. The earthquake emergency response involves many departments, multiple personnel and large rescue forces, which presents a great challenge to the ability to carry out cross-departmental rescue work in a collaborative and joint manner. A novel collaboration approach based on traditional and logical Petri nets is proposed to improve the cross-departmental collaboration in earthquake emergency response. The approach extends the synchronization of transitions in traditional Petri nets to that of traditional and logical transitions in traditional and logical Petri nets, and defines the intersection of related logical functions. The approach builds a model for the earthquake emergency response plans of various departments with the help of traditional and logical Petri net models, and then performs synchronous intersection operations on the two kinds of Petri nets and merges the two kinds of Petri nets into new logical Petri nets. Meanwhile, through realizing the collaboration ability of cross-departmental work, the approach improves the rescue efficiency and reduces the damage of the earthquake emergency.

In order to improve the efficiency of conformance checking in business process management, a business alignment approach is presented based on transition systems between relation matrices and Petri nets. Firstly, a log-based relation matrix of the events is obtained according to the event log. Then, the events in the relation matrix are observed and the transitions in the model are firing, and the activities in the log and in the model are compared. Next, the states of the log and the model are recorded until no new state can be generated, so a transition system can be obtained which includes optimal alignments between the event log and the process model. Finally, two detailed algorithms are presented to obtain an optimal alignment and all optimal alignments between the trace and the model based on the given cost function, respectively. The availability and effectiveness of the proposed approach are proved theoretically.

Several unexpected behaviors may occur during actual treatment of clinical pathways, which will have negative impact on the implementation and the future work. To increase the performance of current deviation detection algorithms, a method is presented according to business alignment, which can effectively detect the anomaly in the implementation of the clinical pathways, provide judgment basis for the intervention in the process of the clinical pathway implementation, and play a crucial role in improving the clinical pathways. Firstly, the noise in diagnosis and treatment logs of clinical pathways will be removed. Then, the synchronous composition model is constructed to embody the deviations between the actual process and the theoretical model. Finally, algorithm is selected to search for optimal alignment. A clinical pathway for ST-Elevation Myocardial Infarction (STEMI) under COVID-19 is used as a case study, and the superiority and effectiveness of this method in deviation detection are illustrated in the result of experiments.

Chinese emergency event domain Named Entity Recognition faces key challenges: ambiguous long-entity boundaries, complex nesting, and poor deep contextual modeling. To address these, we propose RT-GPNet, an end-to-end span-based framework. Its core includes a Dual-Stage Contextual Encoder (RoBERTa cascaded with Multi-Layer Custom Transformer Blocks) for task-specific feature refinement, boosting long-range dependency modeling. The critical innovation is the Rotary Position-aware Span Localization Head, integrating Dynamic Frequency Rotary Position Embedding into GlobalPointer—infusing fine-grained relative position awareness to enhance boundary detection precision and enable nested entity extraction. Additionally, a boundary-sensitive learning objective ensures robust convergence with sparse domain data. Extensive experiments demonstrate the framework’s superior performance and robustness: RT-GPNet not only achieves a competitive 78.96% F1-score on the target Chinese emergency corpus, significantly outperforming mainstream baselines, but also demonstrates exceptional cross-domain and cross-lingual universality. Specifically, generalization tests on the ACE2005 English nested NER dataset (F1-score = 87.62%) and the CMeEE Chinese medical dataset (F1-score = 74.39%) verify that the proposed architecture is fundamentally domain-agnostic and language-independent.