Search

Methane is a kind of harmful gas produced in the process of coal mining. Because of its flammable and explosive characteristics, it poses a great threat to safety during coal mining. In practice, accurate and real-time gas concentration forecasting is becoming an essential issue for reducing methane risks and accidents. Given the complex spatial correlation and temporal variation of sensor data in a coal mine monitoring system, deep learning algorithms have been widely applied due to their revolutionary feature representation capability. However, existing deep learning models utilize recurrent neural networks, which can barely provide satisfactory accuracy due to their ignorance of realistic working conditions of a coal face or an insufficiency in capturing representative spatio-temporal patterns. In this paper, we propose an attention-based spatio-temporal encoder–decoder network approach, named the ASTED model, for methane concentration forecasting. The ASTED model is built based on the integration of the spatial, temporal and environmental information. Specifically, the multi-attention mechanism is used to learn the dynamic spatio-temporal dependencies, and the feature fusion module is used to incorporate the data from different mine sensors. Finally, we employ the LSTM-based encoder–decoder model to generate the final prediction results. Experiments demonstrate that the ASTED model can obtain the dynamic spatio-temporal correlation from multiple sensor readings and achieve the best performance compared with various state-of-the-art solutions. [ABSTRACT FROM AUTHOR]

Under the configuration of the new generation communication network, the algorithm based on machine learning has been widely used in network optimization and mobile user behavior prediction. Therefore, the optimization method with hyper-parameters will have a huge development space in the field of mobile communication network. However, for non-professionals, the bottleneck that restricts the further development and application of the whole machine learning is the selection of suitable machine learning algorithm and the determination of suitable algorithm hyper-parameters. Researchers have proposed to use automatic machine learning algorithm to solve this remarkable problem. This article forms a technical manual that can be easily searched by researchers with summarizing related hyper-parameter optimization methods and proposing the corresponding algorithm framework. Moreover, through the comparison of related optimization methods, we highlight the characteristics and deficiencies of related algorithms in the new generation of mobile networks, and put forward suggestions for future improvement. [ABSTRACT FROM AUTHOR]

Machine learning models have been widely used in various domains. However, the internal mechanisms of popular models, such as neural networks and support vector machines, are difficult for humans to understand; such models are often called "black boxes". In this study, a general method is proposed to gain insight into the black boxes of supervised learning models by visualizing the impacts of input features on their prediction results. Compared with the existing methods, which may overlook the overall understanding of prediction models by analyzing the feature impacts for each individual observation or ignore the impact differences by providing a single impact pattern for all observations, the proposed method distinguishes some typical impact patterns that correspond to different groups of observations. The method maps the detected impact patterns into feature space using tree rules that help locate the impact patterns in the feature space. More importantly, the feature relationships embedded in the prediction models can be revealed through this tree rule-based feature relationship network. We apply the proposed method to various simulated and real data, and the results demonstrate how it can help us understand how features affect model prediction results and the relationships among features. [ABSTRACT FROM AUTHOR]