The Internet is overloading its users with excessive information flows, so that effective content-based filtering becomes crucial in improving user experience and work efficiency. Latent semantic analysis has long been demonstrated as a promising information retrieval technique to search for relevant articles from large text corpora. We build Kvasir, a semantic recommendation system, on top of latent semantic analysis and other state-of-the-art technologies to seamlessly integrate an automated and proactive content provision service into web browsing. We utilize the processing power of Apache Spark to scale up Kvasir into a practical Internet service. In addition, we improve the classic randomized partition tree to support efficient indexing and searching of millions of documents. Herein we present the architectural design of Kvasir, the core algorithms, along with our solutions to the technical challenges in the actual system implementation.

The continuous positioning of a mobile user equipment (MU) in a prompt way is a fundamental requirement in several indoor applications related to ubiquitous computation, assisted living environments, and security/surveillance systems. Motivated by this fact, the current contribution reports a low-complexity visible light positioning (VLP) method suitable for indoor environments in the Big Data era. The proposed architecture consists of multiple light-emitting diodes (LEDs) as light sources and an MU equipped with a photodiode (PD). To guarantee higher spectral efficiency, the LEDs emit sinusoidal waveforms at slightly different predetermined frequencies. The light intensity received at the PD from every LED is continuously estimated after applying a short-time Fourier transformation. To this end, a grid-based numerical technique is proposed to recover the unknown MU position. Additionally, a closed-form solution is presented for the particular case of three LEDs that overrides the need for training points in the grid arrangement. Further, a method for handling noisy signals is proposed, based on averaging the calculated positions from densely overlapping received signals. Finally, a Kalman filter is employed as a post-processing precision improving tool. The proposed VLP efficiency is quantified through respective Monte Carlo simulations that allow the setting of different LED frequencies, received signal processing parameters, MU speed, and noise levels. The results reveal that the suggested approach is robust with significant tolerance in high ambient light levels, computationally efficient, and exhibits low positional error. Finally, to evaluate the performance improvements the new method introduces, we make comparisons against widely-used fingerprint approaches.

The Covid-19 pandemic made a significant impact on society, including the widespread implementation of lockdowns to prevent the spread of the virus. This measure led to a decrease in face-to-face social interactions and, as an equivalent, an increase in the use of social media platforms, such as Twitter. As part of Industry 4.0, sentiment analysis can be exploited to study public attitudes toward future pandemics and sociopolitical situations in general. This work presents an analysis framework by applying a combination of natural language processing techniques and machine learning algorithms to classify the sentiment of each tweet as positive, or negative. Through extensive experimentation, we expose the ideal model for this task and, subsequently, utilize sentiment predictions to perform time series analysis over the course of the pandemic. In addition, a change point detection algorithm was applied in order to identify the turning points in public attitudes toward the pandemic, which were validated by cross-referencing the news report at that particular period of time. Finally, we study the relationship between sentiment trends on social media and, news coverage of the pandemic, providing insights into the public’s perception of the pandemic and its influence on the news.