The year 2020 will remain in the memory of all mankind as the year of the COVID-19 pandemic. The pandemic has affected the world economy, caused more than a million deaths in 2020 alone, changed the way people work and learn and, last but not least, changed the way people interact in society. Social distancing, along with wearing a face mask, is the best solution to prevent the spread of COVID-19 virus. What happens when in certain spaces social distance is difficult and can be accidentally violated without intention? In the absence of widely available tests, not only for people but also for surfaces or indoor air, the risk of contamination is very difficult to assess. This paper proposes a simple method, with low cost and widely implementable, to warn of respecting the density of people in a room. It proposes a dual monitoring system based on Internet of Things (IoT) to assess the indoor air quality and risk of COVID-19 transmission.

Social media platforms make a significant contribution to modeling and influencing people’s opinions and decisions, including political views and orientation. Analyzing social media content can reveal trends and key triggers that will influence society. This paper presents an exhaustive analysis of the performance generated by various implementations of the Naïve Bayes classifier, combined with a semi-structured information approach, to identify the political orientation of Twitter users, based on their posts. As research methodology, we aggregate in a semi-structured format a database of over 86,000 political posts from Democrat (right) and Republican (left) ideologies. Such an approach allows us to associate a Democrat or Republican label to each tweet, in order to create and train the model. The semi-structured input data are processed using several NLP techniques and then the model is trained to classify the political orientation based on semantic criteria and semi-structured information. This paper examines several variations of the Naïve Bayes classifier suite: Gaussian Naïve Bayes, Multinomial Naïve Bayes, Calibrated Naïve Bayes algorithms, and tracks a variety of performance indices and their graphical representations: Prediction Accuracy, Precision, Recall, Confusion Matrix, Brier Score Loss, etc. We obtained an accuracy of around 80–85% in identifying the political orientation of the users. This leads us to the conclusion that this type of application can be integrated into a more complex system and can help in determining political trends or election results.

This paper presents an indoor air quality (IAQ) monitoring system designed for a better end-user experience. The monitoring system consists of elements, from the monitoring sensor to the monitoring interface, designed and implemented by the research team, especially for the proposed monitoring system. The monitoring solution is intended for users who live in houses without automatic ventilation systems. The air quality sensor is designed at a minimum cost and complexity to allow multi-zone implementation without significant effort. The user interface uses a spatial graphic representation that facilitates understanding areas with different air quality levels. Presentation of the outdoor air quality level supports the user’s decision to ventilate a space. An innovative element of the proposed monitoring interface is the real-time forecast of air quality evolution in each monitored space. The paper describes the implementation of an original monitoring solution (monitoring device, Edge/Cloud management system, innovative user monitoring interface) and presents the results of testing this system in a relevant environment. The research conclusions show the proposed solution’s benefits in improving the end-user experience, justified both by the technical results obtained and by the opinion of the users who tested the monitoring system.

The use of monitoring systems based on cloud computing has become common for smart buildings. However, the dilemma of centralization versus decentralization, in terms of gathering information and making the right decisions based on it, remains. Performance, dependent on the system design, does matter for emergency detection, where response time and loading behavior become very important. We studied several design options based on edge computing and containers for a smart building monitoring system that sends alerts to the responsible personnel when necessary. The study evaluated performance, including a qualitative analysis and load testing, for our experimental settings. From 700+ edge nodes, we obtained response times that were 30% lower for the public cloud versus the local solution. For up to 100 edge nodes, the values were better for the latter, and in between, they were rather similar. Based on an interpretation of the results, we developed recommendations for five real-world configurations, and we present the design choices adopted in our development for a complex of smart buildings.

This paper presents a method for functionally extending an IoT indoor air quality monitoring network by adding a cloud-level fire detection logic component. The proposed method does not aim to replace traditional fire detection systems at this stage of research, but to propose a solution for the development of fire detection capabilities and to improve the support provided to firefighting teams by providing a geospatial representation of the building in which a fire occurs. The proposed solution is based on a series of laboratory tests that demonstrated that air quality sensors can successfully detect the effects caused by an ignition event of common materials and can differentiate fire events from other events that can generate false-positive alarms by classic detection systems. The research involved five laboratory combustion tests based on the measurement of temperature, humidity, PM2.5 particle concentration, volatile organic compound index, and nitrogen oxide index. Following the tests, a warning mechanism and geospatial representation were designed using a system with ten IoT sensors to monitor the indoor air quality in a building on our university’s campus.

This paper presents the design and implementation of the Mood Detector application, which is designed to detect the mood and emotional state of the user by analyzing 3 physical parameters (pulse, skin electro conductivity and temperature) by using a machine learning algorithm which is trained with data from the users. The application has been tested repetitively until the results generated by the learning algorithm have been validated 100%, thus confirming that the machine learning algorithms provides the correct output. The application also integrates a music recommender system, which suggests the user to listen to specific playlists, designed according to his currently detected mood.