A subset of parasagittal and parafalcine (PSPF) meningiomas may show early progression/recurrence (P/R) after surgery. This study applied machine learning using combined clinical and texture features to predict P/R in PSPF meningiomas. A total of 57 consecutive patients with pathologically confirmed (WHO grade I) PSPF meningiomas treated in our institution between January 2007 to January 2019 were included. All included patients had complete preoperative magnetic resonance imaging (MRI) and more than one year MRI follow-up after surgery. Preoperative contrast-enhanced T1WI, T2WI, T1WI, and T2 fluid-attenuated inversion recovery (FLAIR) were analyzed retrospectively. The most significant 12 clinical features (extracted by LightGBM) and 73 texture features (extracted by SVM) were combined in random forest to predict P/R, and personalized radiomic scores were calculated. Thirteen patients (13/57, 22.8%) had P/R after surgery. The radiomic score was a high-risk factor for P/R with hazard ratio of 15.73 (p < 0.05) in multivariate hazards analysis. In receiver operating characteristic (ROC) analysis, an AUC of 0.91 with cut-off value of 0.269 was observed in radiomic scores for predicting P/R. Subtotal resection, low apparent diffusion coefficient (ADC) values, and high radiomic scores were associated with shorter progression-free survival (p < 0.05). Among different data input, machine learning using combined clinical and texture features showed the best predictive performance, with an accuracy of 91%, precision of 85%, and AUC of 0.88. Machine learning using combined clinical and texture features may have the potential to predict recurrence in PSPF meningiomas.

Air pollution in cities is a severe and worrying problem because it causes threats to economic development and health. Furthermore, with the development of industry and technology, rapid population growth, and the massive expansion of cities, the total amount of pollution emissions continue to increase. Hence, observing and predicting the air quality index (AQI), which measures fatal pollutants to humans, has become more and more critical in recent years. However, there are insufficient air quality monitoring stations for AQI observation because the construction and maintenance costs are too high. In addition, finding an available and suitable place for monitoring stations in cities with high population density is difficult. This study proposes a spatial-temporal model to predict the long-term AQI in a city without monitoring stations. Our model calculates the spatial-temporal correlation between station and region using an attention mechanism and leverages the distance information between all existing monitoring stations and target regions to enhance the effectiveness of the attention structure. Furthermore, we design a hybrid predictor that can effectively combine the time-dependent and time-independent predictors using the dynamic weighted sum. Finally, the experimental results show that the proposed model outperforms all the baseline models. In addition, the ablation study confirms the effectiveness of the proposed structures.

To alleviate the impact of fake news on our society, predicting the popularity of fake news posts on social media is a crucial problem worthy of study. However, most related studies on fake news emphasize detection only. In this paper, we focus on the issue of fake news influence prediction, i.e., inferring how popular a fake news post might become on social platforms. To achieve our goal, we propose a comprehensive framework, MUFFLE, which captures multi-modal dynamics by encoding the representation of news-related social networks, user characteristics, and content in text. The attention mechanism developed in the model can provide explainability for social or psychological analysis. To examine the effectiveness of MUFFLE, we conducted extensive experiments on real-world datasets. The experimental results show that our proposed method outperforms both state-of-the-art methods of popularity prediction and machine-based baselines in top-k NDCG and hit rate. Through the experiments, we also analyze the feature importance for predicting fake news influence via the explainability provided by MUFFLE.

In this work, a novel decision assistant system for urban transportation, called Route Scheme Assistant (RSA), is proposed to address two crucial issues that few former researches have focused on: route-based passenger flow (PF) inference and multivariant high-PF route recommendation. First, RSA can estimate the PF of arbitrary user-designated routes effectively by utilizing Deep Neural Network (DNN) for regression based on geographical information and spatial-temporal urban informatics. Second, our proposed Bidirectional Prioritized Spanning Tree (BDPST) intelligently combines the parallel computing concept and Gaussian mixture model (GMM) for route recommendation under users’ constraints running in a timely manner. We did experiments on bus-ticket data of Tainan and Chicago and the experimental results show that the PF inference model outperforms baseline and comparative methods from 41% to 57%. Moreover, the proposed BDPST algorithm's performance is not far away from the optimal PF and outperforms other comparative methods from 39% to 71% in large-scale route recommendations.

The success of mediation is affected by many factors, such as the context of the quarrel, the personality of both parties, and the negotiation skill of the mediator, which lead to uncertainty for the work of prediction. This article takes a different approach from that of previous legal prediction research. It analyzes and predicts whether two parties in a dispute can reach an agreement peacefully through the conciliation of mediation. With the inference result, we can know whether mediation is a more practical and time-saving method to solve the dispute. Existing works about legal case prediction mostly focus on prosecution or criminal cases. In this work, we propose a long short-term memory (LSTM)–based framework, called LSTMEnsembler, to predict mediation results by assembling multiple classifiers. Among these classifiers, some are powerful for modeling the numerical and categorical features of case information, for example, XGBoost and LightGBM. Some are effective for dealing with textual data, for example, TextCNN and BERT. The proposed LSTMEnsembler aims to not only combine the effectiveness of different classifiers intelligently but also to capture temporal dependencies from previous cases to boost the performance of mediation prediction. Our experimental results show that our proposed LSTMEnsembler can achieve 85.6% for F-measure on real-world mediation data.