Background: The combination of telemedicine systems integrating mobile technologies with the use of continuous glucose monitors improves patients' glycemic control but demands a higher interaction with information technology tools that must be assessed. In this article, we analyze patients' behavior from the use-of-the-system point of view, identifying how continuous monitoring may change the interaction of patients with the mobile telemedicine system. Methods: Patients' behavior were evaluated in a clinical experiment consisting of a 2-month crossover randomized study with 10 type 1 diabetes patients. During the entire experiment, patients used the DIABTel telemedicine system, and during the intervention phase, they wore a continuous glucose monitor. Throughout the experiment, all user actions were automatically registered. This article analyzes the occurrence of events and the behavior patterns in blood glucose (BG) self-monitoring and insulin adjustments. A subjective evaluation was also performed based on the answers of the patients to a questionnaire delivered at the end of the study. Results: The number of sessions established with the mobile Smart Assistant was considerably higher during the intervention period than in the control period (29.0 versus 18.8, p < .05), and it was also higher than the number of Web sessions (29.0 versus 22.2, p < .01). The number of daily boluses was higher during the intervention period than in the control period (5.27 versus 4.40, p < .01). The number of daily BG measurements was also higher during the intervention period (4.68 versus 4.05, p < .05) and, in percentage, patients increased the BG measurements not associated to meals while decreasing the percentage of preprandial measurements. The subjective evaluation shows that patients would recommend the use of DIABTel in routine care. Conclusions: The use of a continuous glucose monitor changes the way patients manage their diabetes, as observed in the increased number of daily insulin bolus, the increased number of daily BG measurements, and the differences in the distribution of BG measurements throughout the day. Continuous monitoring also increases the interaction of patients with the information system and modifies their patterns of use. We can conclude that mobile technologies are especially useful in scenarios of tight monitoring in diabetes, and they are well accepted by patients.

The growing number of connected wireless devices is causing interference in traditional radio frequency bands, which restricts communications capacity and efficiency. This issue motivates the pursuit of alternative technologies, such as optical wireless communication, which could potentially resolve electromagnetic congestion. This technology leverages the visible and infrared spectrum, along with other wavelengths, to transmit data. Recently, photovoltaic (PV) modules have emerged as an innovative solution for data reception and enhancing self-sufficiency. However, within a range of industrial settings, including factories, warehouses, and offices, data transmission may be affected by fluctuations in lighting conditions. This work focuses on exploring the impact of lighting conditions on the frequency response of visible light communication (VLC) systems that utilize silicon PV cells as photodetectors, a crucial aspect to optimize the efficiency of data transmission. This analysis opens new possibilities for the effective deployment of PV cells as optical receivers in indoor settings, thereby significantly enhancing the usage of VLC technology in industrial applications.

This work aims to provide the hardware (HW) design of the optoelectronics interfaces for a visible-light communication (VLC) system that can be employed for several use cases. Potential applications include the transmission of ultra-high-definition (UHD) streaming video through existing reading lamps installed in passenger vans. In this use case, visible light is employed for the downlink, while infrared light is used for the uplink channel, acting as a remote controller. Two primary components -a Light Fidelity (LiFi) router and a USB dongle—were designed and implemented. The ‘LiFi Router’, handling the downlink channel, comprises components such as a visible Light-Emitting Diode (LED) and an infrared receiver. Operating at a supply voltage of 12 V and consuming current at 920 mA, it is compatible with standard voltage buses found in transport vehicles. The ‘USB dongle’, responsible for the uplink, incorporates an infrared LED and a receiver optimized for visible light. The USB dongle works at a supply voltage of 5 V and shows a current consumption of 1.12 A, making it well suited for direct connection to a universal serial bus (USB) port. The bandwidth achieved for the downlink is 11.66 MHz, while the uplink’s bandwidth is 12.27 MHz. A system competent at streaming UHD video with the feature of being single-input multiple-output (SIMO) was successfully implemented via the custom hardware design of the optical transceivers and optoelectronics interfaces. To ensure the system’s correct performance at a distance of 110 cm, the minimum signal-to-noise ratio (SNR_min) for both optical links was maintained at 10.74 dB. We conducted a proof-of-concept test of the VLC system in a passenger van and verified its optimal operation, effectively illustrating its performance in a real operating environment. Exemplifying potential implementations possible with the hardware system designed in this work, a bit rate of 15.2 Mbps was reached with On–Off Keying (OOK), and 11.25 Mbps was obtained with Quadrature Phase Shift Keying (QPSK) using Orthogonal Frequency-Division Multiplexing (OFDM) obtaining a bit-error rate (BER) of 3.3259 × 10⁻⁵ in a passenger van at a distance of 72.5 cm between the LiFi router and the USB dongle. As a final addition, a solar panel was installed on the passenger van’s roof to power the user’s laptop and the USB dongle via a power bank battery. It took 13.4 h to charge the battery, yielding a battery life of 22.3 h. This characteristic renders the user’s side of the system entirely self-powered.

Streaming services are increasingly leveraging Artificial Intelligence (AI) technologies for improved content cataloging, user experiences in content discovery, and personalization. A significant challenge in this domain is the automated assignment of microgenres to movies. This study introduces and evaluates approaches based on clustering, topic modeling, and word embedding to address this task. The evaluation employs a preprocessed dataset containing movie-related data—title tags, synopses, genres, and reviews—alongside a predefined microgenre list. Comparisons of three activation functions (binary step, ramp, and sigmoid) gauge their effectiveness in augmenting microgenre tags. Results demonstrate the superiority of the word embedding approach over clustering and topic modeling in terms of mean accuracy. Even more, the word embedding approach stands as the sole fully automated solution. Analysis indicates that incorporating review-based tags introduces noise and undermines accuracy. Besides, the word embedding approach yields optimal outcomes using the sigmoid function, effectively doubling assigned tags while maintaining matching quality. This sheds light on the potential of word embedding methods within the movie domain.

The use of keywords is increasingly being applied across diverse domains, including the movie industry, whose main platforms are adopting advanced natural language processing techniques. Algorithms for automatic extraction of keywords can provide relevant information in this domain. The most novel approaches covering several categories (statistics, graphs, word embedding, and hybrid) have been considered in a model study framework. They have been implemented, applied, and evaluated with standard datasets. In addition, a movie dataset with gold standard keywords, based on textual metadata from synopses and reviews, has been specifically developed for this scope. Keyword extraction models have been evaluated in terms of F-score and computation time. Furthermore, content analysis, both quantitative and qualitative, of the extracted keywords in the movie context has been performed. Results show a great variability in model performance and computation time among the different models. Qualitative results, in addition to F-score and computation time, demonstrate that keyword extraction works better with synopses than with reviews. The quantitative content analysis revealed that EmbedRank effectively reduces redundancy and limits the use of proper nouns, leading to high-quality keywords.