Edwin J. Coronel-González’s research while affiliated with Politecnica Salesiana University and other places

During the last few years, the field of automatic speech recognition (ASR) has been growing exponentially, due to the diverse applications and solutions it offers. For this reason, this paper presents a multiclass language classifier based on recurrent convolutional neural networks, whose objective is to classify the audios of the KALAKA-3 database, according to their language. To meet this objective, the mel frequency cepstral coefficients (MFCCs) were extracted from each of the audios in the database, with which the training process is carried out. A recurrent convolutional neural network (CRNN) was created for this process, resulting in an accuracy of 98% using the testing data, and 40% using the Eval data. This work sets a precedent for improving real-time translators, since in the future it would be possible to listen to a few seconds of a conversation, identify it, and automatically perform a translation process, which would be very useful in various applications.KeywordsArtificial intelligenceNeural networksCRNNDatabaseKALAKA-3

Provisioning of health services such as care, monitoring, and remote surgery is being improved thanks to fifth-generation cellular technology (5G). As 5G expands globally, more smart healthcare applications have been developed due to its extensive eMBB (Enhanced Mobile Broadband) and URLLC (Ultra-Reliable Low Latency Communications) features that can be used to generate healthcare systems that allow minimizing the face-to-face assistance of patients at hospital centers. This powerful network provides high transmission speeds, ultra-low latency, and a network capacity greater than that of 4G. Fifth-generation cellular technology is expected to be a means to provide excellent quality of medical care, through its technological provision to the use of IoMT (Internet of Medical Things) devices. Due to the numerous contributions in research on this topic, it is necessary to develop a review that provides an orderly perspective on research trends and niches for researchers to use as a starting point for their work. In this context, this article presents a systematic review based on PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses), with article selection based on inclusion and exclusion criteria that avoid bias. This research was based on research questions that were answered from the included works. These questions focus on technical characteristics, health benefits, and security protocols necessary for the development of smart healthcare applications. We have identified that a high percentage of existing works in the literature are proposals (56.81%, n = 25) and theoretical studies (22.73%, n = 10); few implementations (15.91%, n = 7) and prototypes (4.55%, n = 2) exist, due to the limited global deployment of 5G. However, the panorama looks promising based on proposals and future work that these technological systems allow, all based on improving healthcare for people.