The number of safety accidents caused by excavation of deep foundation pits in subway stations has been increasing rapidly in recent years. Thus, precisely predicting the safety risks for subway deep foundation pits bears importance. Existing methods, such as machine learning models, have been established for predicting such risks. However, these methods are unable to provide accurate results for deep foundation pits in subway stations due to small and unbalanced data samples. In this research, an intelligent model based on random forest (RF) was established for risk prediction of deep foundation pits in subway stations. To achieve such a goal, different types of monitoring data and risk level monitoring were introduced to the RF for training the model and estimating unknown relationships between monitoring values and safety risks of pits. An actual deep foundation pit in a subway station of the Wuhan Metro was used to demonstrate the applicability of the developed RF risk prediction model. The results showed that the superiority of the proposed RF risk prediction model can be used as a basis to implement a decision-making tool for predicting safety risks of subway foundation pits. The importance evaluation function of the model provides the ability to aid onsite engineers in determining the causes of safety risks, thus facilitating the implementation of emergency measures in advance.

Accurately predicting risks during the construction of deep foundation pits is pivotal to ensuring the safety of the workforce of public and adjacent structures. Existing methods for assessing such risks are cumbersome and are unable to accurately provide the certainty required to ensure safety levels. This paper presents a novel prediction method that utilizes the support vector machine (SVM) to determine the safety risks that can materialize during the construction of deep pit foundations in subway infrastructure projects. The development of the SVM risk prediction model involves the following steps: (1) identification of risk factors from industry experts; (2) processing the sampled data; and (3) training and testing. A case study is used to demonstrate the predictive capability of the developed SVM approach. By inputting data on a daily basis, the safety risks associated with deep foundation pits can be monitored; this enables decision-makers to formulate appropriate control measures.

Objective: An electroencephalogram (EEG)-based brain-computer interface (BCI) enables direct communication between the human brain and a computer. Due to individual differences and non-stationarity of EEG signals, such BCIs usually require a subject-specific calibration session before each use, which is time-consuming and user-unfriendly. Transfer learning (TL) has been proposed to shorten or eliminate this calibration, but existing TL approaches mainly consider offline settings, where all unlabeled EEG trials from the new user are available. Methods: This article proposes Test-Time Information Maximization Ensemble (T-TIME) to accommodate the most challenging online TL scenario, where unlabeled EEG data from the new user arrive in a stream, and immediate classification is performed. T-TIME initializes multiple classifiers from the aligned source data. When an unlabeled test EEG trial arrives, T-TIME first predicts its labels using ensemble learning, and then updates each classifier by conditional entropy minimization and adaptive marginal distribution regularization. Our code is publicized. Results: Extensive experiments on three public motor imagery based BCI datasets demonstrated that T-TIME outperformed about 20 classical and state-of-the-art TL approaches. Significance: To our knowledge, this is the first work on test time adaptation for calibration-free EEG-based BCIs, making plug-and-play BCIs possible.

A risk is a predominant problem in the developing countries construction projects. Although numerous studies have been concerned on risk, there is a limited study on a mechanism to identify the typical risks and effects level. This paper presents an approach for evaluating the risks in case of schedule delays at the various lifecycles of construction projects. The methodology applied is an integrated model of the technique for order preference by similarity to ideal solution (TOPSIS) and fuzzy comprehensive evaluation (FCE). In this study, common criteria, sub-criteria, and attributes are constructed to make a decision concerning the influence level of risk of delay at the construction project lifecycle. The results showed that the construction stage (44%) is highly influenced, the second highly influenced stage is post construction (37%), and the least risked stage is pre-construction (35%). The construction projects in Ethiopia have faced an average delay risk of 38% at a high and very high-risk level. This work is expected to serve as a tool to assist managers in the management and control of schedule delays to mitigate their risks.

Artificial intelligence (AI) approaches, such as deep learning models, are increasingly used to determine risks in construction. However, the black-box nature of AI models makes their inner workings difficult to understand and interpret. Deploying explainable artificial intelligence (XAI) can help explain why and how the output of AI models is generated. This article addresses the following research question: How can we accurately identify the critical factors influencing tunnel-induced ground settlement and provide counterfactual explanations to support risk-based decision-making? We apply an XAI approach using counterfactual explanations to help understand decision-making surrounding risks when considering control ground settlement. Our approach consists of a: 1) construction of Kernel principal components analysis-based deep neural network (DNN) model; 2) generation of counterfactual explanations; 3) analysis of risk prediction and assessment factors' importance, necessity, and sufficiency. We apply our approach to the San-yang road tunnel project in Wuhan, China. The results demonstrate that the KPCA-DNN model better predicted ground settlement based on high-dimensional input features than the baseline model (i.e., AdaBoost and RandomForest). The bubble chamber pressure→ cutter-head speed→ equipment inclination is also identified as the primary risk path. Our findings indicate that using counterfactual explanations enables transparency and trust in AI-based risk models to be acquired. Moreover, our approach can help site managers, engineers, and tunnel-boring machine operators understand how to manage better and mitigate the risk of ground settlement.