Mobile telecoms operators possess an enormous quantity of data, which could be used to reduce the cost of installing new infrastructure, to provide a better QoS or to plan their infrastructure. Thus, they are concerned to model, understand and predict SMS and calls activity levels in their infrastructures. Besides, SMS and call activities analysis can open new business opportunities for geomarketing as well as trade area analysis. In the present effort, we detected activity zones with a difference of only 0.5 km from the reference activity areas extracted from Geo-tweets. We also used Markov chains to represent and predict SMS and call activity levels, achieving a prediction success rate between 80% and 90%.

In the last decades, mobile phones have become the major medium for communication between humans. The site effect is the loss of subscribers. Consequently, Telecoms operators invest in developing algorithms for quantifying the risk to churn and to influence other subscribers to churn. The objective is to prioritize the retention of subscribers in their network due to the cost of obtaining a new subscriber is four times more expensive than retaining subscribers. Hence, we use Extremely Random Forest to classify churners and non-churners obtaining a Lift value at 10% of 5.5. Then, we rely on graph-based measures such as Degree of Centrality and Page rank to measure emitted and received influence in the social network of the carrier. Our methodology allows summarising churn risk score, relying on a Fuzzy Logic system, combining the churn probability and the risk of the churner to leave the ...

In the last years, smartphones have become the major device for communication enabling Telco operators to capture subscribers’ whereabouts. This location information allows computing eostatistics to study transportation systems, traffic jams, origin-destination matrix, etc. The first task to accomplish the aforementioned objectives is to detect routes that people use to go from A to B. Thus, in the present effort, we propose a method to extract automatically routes from CDR data relying on clustering and community detection algorithms.

This paper reviews the most recent literature on experiments with different Machine Learning, Deep Learning and Natural Language Processing techniques applied to predict judicial and administrative decisions. Among the most outstanding findings, we have that the most used data mining techniques are Support Vector Machine (SVM), K Nearest Neighbours (K-NN) and Random Forest (RF), and in terms of the most used deep learning techniques, we found Long-Term Memory (LSTM) and transformers such as BERT. An important finding in the papers reviewed was that the use of machine learning techniques has prevailed over those of deep learning. Regarding the place of origin of the research carried out, we found that 64% of the works belong to studies carried out in English-speaking countries, 8% in Portuguese and 28% in other languages (such as German, Chinese, Turkish, Spanish, etc.). Very few works of...

In this paper, we introduce an innovative, low-cost and easy experimental setup to be used in a traditional ripple tank when a frequency generator is unavailable. This configuration was carried out by undergraduate students. The current project allowed them to experiment and to study the relationship between the wavelength and the oscillation period of a mechanical wave, among other things. Under this setup, students could evaluate the mechanism not only qualitative but also in a quantitative fashion with a high degree of confidence. The results obtained for the propagation speed of the mechanical waves in different media with this alternative design coincided with those acquired using a commercial device designed for this purpose.

The COVID-19 crisis has produced worldwide changes from people’s lifestyles to travel restrictions imposed by world’s nations aiming to keep the virus out. Several countries have created digital information applications to help control and manage the COVID-19 crisis, such as the creation of contact tracing apps. The Peruvian government in collaboration with several institutions developed PerúEnTusManos, an epidemiological tracing application. The application uses georeferencing to study users’ movements and creates individual mobility patterns from the Peruvian citizens as well as detects crowds. In this article, we present a process to detect possible infected individuals based on probabilities assigned to people that had contact with someone who tested positive for COVID-19, using data collected from PerúEnTusManos. The preliminary evaluation shows promising results when detect...