In this work we introduce a system pipeline for the analysis of earth’s electromagnetic field that is used to analyse precursors to earthquakes. Data gathered by the Swarm satellites are used to present the utility of our system. Our objective is to provide a streamlined method to analyze electromagnetic data over a region and investigate the relationship of precursory signals to seismic events. The process follows three distinct stages: data extraction, data pre-processing and anomaly detection. The first stage consists of the region selection and data extraction. The second stage consists of four different pre-processing methods that address the data sparsity problem and the cause of artificial anomalies. The last stage is the Anomaly Detection (AD) of the Swarm satellite data, over the investigated region. The different methods that are implemented are known to perform well in the field of AD. Following the presentation of our system, a case study is described where the seismic event of 6.2 M_w is in Ludian, China and occurred on 3^rd August 2014. The event is used to present the usefulness of our approach and pinpoint some critical problems regarding satellite data that were identified.

This paper proposes a non-invasive, data-driven methodology for monitoring and optimising machine utilisation in manufacturing environments. By analysing high-resolution power consumption data, the system automatically classifies machine states (off, idling, and working, and segments operational periods into discrete production events. Unsupervised learning techniques enable the identification of production patterns, product typologies, and anomalies, supporting improvements in operational efficiency and quality control. The approach also estimates energy consumption and cost using time-of-use tariffs, offering insights into both performance and sustainability. Experimental evaluations across multiple industrial settings demonstrate the method’s robustness, with high agreement with production records and significant potential for reducing idle time, improving scheduling, and enhancing resource allocation. This work presents a scalable and interpretable analytics framework to support data-driven decision-making in modern manufacturing operations.

The problem of data analytics in real-world electromagnetic (EM) applications poses a lot of algorithmic constraints. The process of big datasets, the requirement of prior knowledge, unknown location of anomalies, and variable length patterns are all issues that need to be addressed. In this application, we address those issues by proposing a fuzzy shape-based method with anomaly detection. This method is evaluated against 12 benchmark datasets of different kinds of anomalies and provides promising results based on the use of a new performance metric that takes into account the distance between the predicted and actual anomalies. Real-world EM data from the Earth’s magnetic field are provided by the SWARM satellite constellation relating to regions in China, Greece and Peru. The seismic events that occurred in those regions are compared against the SWARM data. Moreover, three other methods: GrammarViz, HOT-SAX, and CUSUM-EWMA are also applied to further investigate the possible linkages of EM anomalies with seismic events. The findings further our understanding of real-world data analytics in EM data and seismicity. Some proposals regarding the limitations of available data for the real-world datasets are also presented.