Given the large amount of railway maintenance work in China, whereas the maintenance time window is continuously compressed, this paper proposes a novel network model-based maintenance planning and optimization method, transforming maintenance planning and optimization into an integer linear programming problem. Based on the dynamic inspection data of track geometry, the evaluation index of maintenance benefit and the model of the decay and recovery of the track geometry are constructed. The optimization objective is to maximize the railway network’s overall performance index, considering budget constraint, maximum length constraint, maximum number of maintenance activities within one single period constraint, and continuity constraint. Using this method, the track units are divided into several maintenance activities at one time. The combination of surrounding track units can be considered for each maintenance activity, and the specific location, measure, time, cost, and benefit can be determined. Finally, a 100 km high-speed railway network case study is conducted to verify the model’s effectiveness in complex optimization scenarios. The results show that this method can output an objective maintenance plan; the combination of unit track sections can be considered to expand the scope of maintenance, share the maintenance cost and improve efficiency; the spatial-temporal integrated maintenance planning and optimization can be achieved to obtain the optimal global solution.

This paper models 54,559 Chinese news items about education industry and scientific industry by machine learning during the COVID-19 epidemic to build China’s increased scientific research policy (ISRP) index. The result of interrupted time series analysis indicates that, the ISRP has an emphatic positive causality on the education industry advancement and promotes the development of the education industry. The ISRP also has a remarkable positive causality on the development of the scientific industry. Moreover, the result of causal network indicates that, a virtuous circle within the ISRP, the education industry and the scientific industry has been formed, which has promoted the sustainable development of the education chain.

Among contemporary computational techniques, Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) are favoured because of their capacity to tackle non-linear modelling and complex stochastic datasets. Nondeterministic models involve some computational intricacies when deciphering real-life problems but always yield better outcomes. For the first time, this study utilized the ANN and ANFIS models for modelling power generation/electric power output (EPO) from databases generated in a combined cycle power plant (CCPP). The study presents a comparative study between ANNs and ANFIS to estimate the power output generation of a combined cycle power plant in Turkey. The inputs of the ANN and ANFIS models are ambient temperature (AT), ambient pressure (AP), relative humidity (RH), and exhaust vacuum (V), correlated with electric power output. Several models were developed to achieve the best architecture as the number of hidden neurons varied for the ANNs, while the training process was conducted for the ANFIS model. A comparison of the developed hybrid models was completed using statistical criteria such as the coefficient of determination (R²), mean average error (MAE), and average absolute deviation (AAD). The R² of 0.945, MAE of 3.001%, and AAD of 3.722% for the ANN model were compared to those of R² of 0.9499, MAE of 2.843% and AAD of 2.842% for the ANFIS model. Even though both ANN and ANFIS are relevant in estimating and predicting power production, the ANFIS model exhibits higher superiority compared to the ANN model in accurately estimating the EPO of the CCPP located in Turkey and its environment.

PPGIS platforms have been widely used to map social actors since the emergence of open access webGIS platforms. This identification of citizen initiatives is based on the physical location, but is rarely combined with social networking. This research seeks to close that gap by using the platIC web-based mapping tool for citizen initiatives, together with their interrelationships. Therefore, a methodical procedure has been defined to construct a geolocalised graph by identifying and categorising linked nodes. Method steps have been tested in three case studies in the Malaga region: Malaga city, Benalmadena, and Valle del Genal. They were selected for a comparative analysis in three different urban and socio-economic scenarios, namely: a tourist destination with a high density of Spanish population and floating city users; a sun-and-beach destination with a significant presence of resident foreign population; and a rural area suffering from depopulation, respectively. Mapping reveals a higher density of citizen initiatives in central urban areas and with social conflicts. Social graphs show a wider interconnection of nodes in rural areas, but isolated nodes are spread more widely there. Monitoring active citizen initiatives could serve as a basis for local administration to involve the citizenry in the management of current issues in the urban and rural context. Future research may promote new plugins to improve participatory process through webGIS platforms.

Research networks organized around a particular topic are built as knowledge is produced and socialized. These are parts of a seminal or initial production, to which new authors and subtopics are added until research and knowledge networks are formed around a particular area. The purpose of the research was to find this type of relationship or network between authors, institutions, and countries that have contributed to the issue of the circular economy and specifically its relationship with sustainability. This allows those interested in the said object of study to know the research advances of the network, enter their research lines, or create new networks according to their interests or needs. The study used a bibliometric-type descriptive quantitative approach using the Scopus scientific database, the R Studio data analytics application, and the Bibliometrix library. The results were found to determine a relationship building from 2006, which makes it an emerging topic. However, the growth it has achieved in recent years of more than 31% shows a strong interest in the subject. Of the subtopics that have been addressed, sustainability, recycling, solid waste, wastewater, and renewable energy. Similarly, sectors such as construction, the automotive industry, tourism, cities, the agricultural sector, the chemical industry, and the implementation of technologies 4.0 and 5.0 in their processes stood out. The most prominent country in the scientific approach to this area is Italy. The most prominent author for his citations is Molina-Moreno, the source of knowledge that stands out for his contributions is the University of Granada and different networks have been built around their knowledge.

In this paper, we assess the results of experiment with different machine learning algorithms for the data classification on the basis of accuracy, precision, recall and F1-Score metrics. We collected metrics like Accuracy, F1-Score, Precision, and Recall: From the Neural Network model, it produced the highest Accuracy of 0.129526 also highest F1-Score of 0.118785, showing that it has the correct balance of precision and recall ratio that can pick up important patterns from the dataset. Random Forest was not much behind with an accuracy of 0.128119 and highest precision score of 0.118553 knit a great ability for handling relations in large dataset but with slightly lower recall in comparison with Neural Network. This ranked the Decision Tree model at number three with a 0.111792, Accuracy Score while its Recall score showed it can predict true positives better than Support Vector Machine (SVM), although it predicts more of the positives than it actually is a majority of the times. SVM ranked fourth, with accuracy of 0.095465 and F1-Score of 0.067861, the figure showing difficulty in classification of associated classes. Finally, the K-Neighbors model took the 6th place, with the predetermined accuracy of 0.065531 and the unsatisfactory results with the precision and recall indicating the problems of this algorithm in classification. We found out that Neural Networks and Random Forests are the best algorithms for this classification task, while K-Neighbors is far much inferior than the other classifiers.