This review examines the role of machine learning (ML) techniques in advancing building energy management and decarbonisation efforts within the UK building sector. Through a comprehensive analysis of recent literature, the paper evaluates various ML approaches-including supervised, unsupervised, and reinforcement learning-and their applications in energy consumption prediction, HVAC optimisation, and renewable energy integration. The review identifies significant advancements in predictive modelling and system optimisation, with case studies demonstrating energy savings of up to 75% through ML-enhanced management systems. Key challenges including data quality, model interpretability, and system integration are analysed, alongside emerging solutions. The findings indicate that while ML technologies offer substantial potential for improving building energy efficiency, their successful implementation requires standardized frameworks and enhanced data collection practices. The paper concludes with recommendations for policymakers, building managers, and researchers to facilitate wider adoption of ML solutions in building energy management.
The study of topic evolution aims to analyze the behavior of different research fields by utilizing various features such as the relationships between articles. In recent years, many published papers consider more than one field of study which has led to a significant increase in the number of inter-field and interdisciplinary articles. Therefore, we can analyze the similarity/dissimilarity and convergence/divergence of research fields based on topic analysis of the published papers. Our research intends to create a methodology for studying the evolution of the research fields. In this paper, we propose an embedding approach for modeling each research topics as a multidimensional vector. Using this model, we measure the topic’s distances over the years and investigate how topics evolve over time. The proposed similarity metric showed many advantages over other alternatives (such as Jaccard similarity) and it resulted in better stability and accuracy. As a case study, we applied the proposed method to subsets of computer science for experimental purposes, and the results were quite comprehensible and coherent.
Thousands of research papers are being published every day, and among all these research works, one of the fastest-growing fields is computer science (CS). Thus, learning which research areas are trending in this particular field of study is advantageous to a significant number of scholars, research institutions, and funding organizations. Many scientometric studies have been done focusing on analyzing the current CS trends and predicting future ones from different perspectives as a consequence. Despite the large datasets from this vast number of CS publications and the power of deep learning methods in such big data problems, deep neural networks have not yet been used to their full potential in this area. Therefore, the objective of this paper is to predict the upcoming years' CS trends using long short-term memory neural networks. Accordingly, CS papers from 1940 and their corresponding fields of study from the microsoft academic graph dataset have been exploited for solving this research trend prediction problem. The prediction accuracy of the proposed method is then evaluated using RMSE and coefficient of determination (R2) metrics. The evaluations show that the proposed method outperforms the baseline approaches in terms of the prediction accuracy in all considered time periods. Subsequently, adopting the proposed method's predictions, we investigate future trending areas in computer science research from various viewpoints.
Artificial Intelligence (AI) is one of the hottest trending research topics of computer science. As it is a fast-growing domain, analyzing its changes during different periods will help researchers analyze its evolution in order to develop their career path according to possible changes in the future. In this paper, we investigate how AI subfields are becoming closer or further from each other. This research also offers a general methodology for studying the relationships and interactions of research topics over time. In this regard, we adopt a topic embedding approach to examine how various sub-fields of AI evolve over time. Topic embedding is a method to convert topics to meaningful mathematical models so that their latent relationships remain. Besides being computationally efficient, this method has proven the ability to reveal significant patterns regarding the relationships between sub-domains.