DS-CNN: Deep Convolutional Neural Networks for Facial Emotion Detection in Children with Down Syndrome during Dolphin-Assisted Therapy.

In Mexico, according to data from the General Directorate of Health Information (2018), there is an annual incidence of 689 newborns with Trisomy 21, well-known as Down Syndrome. Worldwide, this incidence is estimated between 1 in every 1000 newborns, approximately. That is why this work focuses on the detection and analysis of facial emotions in children with Down Syndrome in order to predict their emotions throughout a dolphin-assisted therapy. In this work, two databases are used: Exploratory Data Analysis, with a total of 20,214 images, and the Down's Syndrome Dataset database, with 1445 images for training, validation, and testing of the neural network models. The construction of two architectures based on a Deep Convolutional Neural Network manages an efficiency of 79%, when these architectures are tested with a large reference image database. Then, the architecture that achieves better results is trained, validated, and tested in a small-image database with the facial emotions of children with Down Syndrome, obtaining an efficiency of 72%. However, this increases by 9% when the brain activity of the child is included in the training, resulting in an average precision of 81%. Using electroencephalogram (EEG) signals in a Convolutional Neural Network (CNN) along with the Down's Syndrome Dataset (DSDS) has promising advantages in the field of brain-computer interfaces. EEG provides direct access to the electrical activity of the brain, allowing for real-time monitoring and analysis of cognitive states. Integrating EEG signals into a CNN architecture can enhance learning and decision-making capabilities. It is important to note that this work has the primary objective of addressing a doubly vulnerable population, as these children also have a disability.

A Comprehensive Review on Smart Grids: Challenges and Opportunities.

Recently, the operation of distribution systems does not depend on the state or utility based on centralized procedures, but rather the decentralization of the decisions of the distribution companies whose objectives are the efficiency of interconnectivity. Therefore, distribution companies are exposed to greater risks, and due to this, the need to make decisions based on increasingly reliable models has grown up considerably. Therefore, we present a survey of key aspects, technologies, protocols, and case studies of the current and future trend of Smart Grids. This work proposes a taxonomy of a large number of technologies in Smart Grids and their applications in scenarios of Smart Networks, Neural Networks, Blockchain, Industrial Internet of Things, or Software-Defined Networks. Therefore, this work summarizes the main features of 94 research articles ranging the last four years. We classify these survey, according Smart Grid Network Topologies, because it can group as the main axis the sensors applied to Smart Grids, as it shows us the interconnection forms generalization of the Smart Networks with respect to the sensors found in a home or industry.

VirtualCPR: Virtual Reality Mobile Application for Training in Cardiopulmonary Resuscitation Techniques.

Deaths due to heart diseases are a leading cause of death in Mexico. Cardiovascular diseases are considered a public health problem because they produce cardiorespiratory arrests. During an arrest, cardiac and/or respiratory activity stops. A cardiorespiratory arrest is rapidly fatal without a quick and efficient intervention. As a response to this problem, the VirtualCPR system was designed in the present work. VirtualCPR is a mobile virtual reality application to support learning and practicing of basic techniques of cardiopulmonary resuscitation (CPR) for experts or non-experts in CPR. VirtualCPR implements an interactive virtual scenario with the user, which is visible by means of employment of virtual reality lenses. User's interactions, with our proposal, are by a portable force sensor for integration with training mannequins, whose development is based on an application for the Android platform. Furthermore, this proposal integrates medical knowledge in first aid, related to the basic CPR for adults using only the hands, as well as technological knowledge, related to development of simulations on a mobile virtual reality platform by three main processes: (i) force measurement and conversion, (ii) data transmission and (iii) simulation of a virtual scenario. An experiment by means of a multifactorial analysis of variance was designed considering four factors for a CPR session: (i) previous training in CPR, (ii) frequency of compressions, (iii) presence of auditory suggestions and (iv) presence of color indicator. Our findings point out that the more previous training in CPR a user of the VirtualCPR system has, the greater the percentage of correct compressions obtained from a virtual CPR session. Setting the rate to 100 or 150 compressions per minute, turning on or off the auditory suggestions and turning the color indicator on or off during the session have no significant effect on the results obtained by the user.

Non-Parametric Evaluation Methods of the Brain Activity of a Bottlenose Dolphin during an Assisted Therapy.

Dolphin-Assisted Therapies (DAT) are alternative therapies aimed to reduce anxiety levels, stress relief and physical benefits. This paper is focused on measuring and analyzing dolphins brain activity when DAT is taking place in order to identify if there is any differences in female dolphin's neuronal signal when it is interacting with control or intervention subjects, performing our research in Delfiniti, Ixtapa, Mexico facilities. We designed a wireless and portable electroencephalographic single-channel signal capture sensor to acquire and monitor the brain activity of a female bottle-nose dolphin. This EEG sensor was able to show that dolphin activity at rest is characterized by high spectral power at slow-frequencies bands. When the dolphin participated in DAT, a 23.53% increment in the 12-30 Hz frequency band was observed, but this only occurred for patients with some disease or disorder, given that 0.5-4 Hz band keeps it at 17.91% when there is a control patient. Regarding the fractal or Self-Affine Analysis, we found for all samples studied that at the beginning the dolphin's brain activity behaved as a self-affine fractal described by a power-law until the fluctuations of voltage reached the crossovers, and after the crossovers these fluctuations left this scaling behavior. Hence, our findings validate the hypothesis that the participation in a DAT of a Patient with a certain disease or disorder modifies the usual behavior of a female bottle-nose dolphin.

Biomedical Signal Acquisition Using Sensors under the Paradigm of Parallel Computing.

There are several pathologies attacking the central nervous system and diverse therapies for each specific disease. These therapies seek as far as possible to minimize or offset the consequences caused by these types of pathologies and disorders in the patient. Therefore, comprehensive neurological care has been performed by neurorehabilitation therapies, to improve the patients' life quality and facilitating their performance in society. One way to know how the neurorehabilitation therapies contribute to help patients is by measuring changes in their brain activity by means of electroencephalograms (EEG). EEG data-processing applications have been used in neuroscience research to be highly computing- and data-intensive. Our proposal is an integrated system of Electroencephalographic, Electrocardiographic, Bioacoustic, and Digital Image Acquisition Analysis to provide neuroscience experts with tools to estimate the efficiency of a great variety of therapies. The three main axes of this proposal are: parallel or distributed capture, filtering and adaptation of biomedical signals, and synchronization in real epochs of sampling. Thus, the present proposal underlies a general system, whose main objective is to be a wireless benchmark in the field. In this way, this proposal could acquire and give some analysis tools for biomedical signals used for measuring brain interactions when it is stimulated by an external system during therapies, for example. Therefore, this system supports extreme environmental conditions, when necessary, which broadens the spectrum of its applications. In addition, in this proposal sensors could be added or eliminated depending on the needs of the research, generating a wide range of configuration limited by the number of CPU cores, i.e., the more biosensors, the more CPU cores will be required. To validate the proposed integrated system, it is used in a Dolphin-Assisted Therapy in patients with Infantile Cerebral Palsy and Obsessive-Compulsive Disorder, as well as with a neurotypical one. Event synchronization of sample periods helped isolate the same therapy stimulus and allowed it to be analyzed by tools such as the Power Spectrum or the Fractal Geometry.

Energy-Efficient Industrial Internet of Things Software-Defined Network by Means of the Peano Fractal.

The Industrial Internet of Things (IIoT) network generates great economic benefits in processes, system installation, maintenance, reliability, scalability, and interoperability. Wireless sensor networks (WSNs) allow the IIoT network to collect, process, and share data of different parameters among Industrial IoT sense Node (IISN). ESP8266 are IISNs connected to the Internet by means of a hub to share their information. In this article, a light-diffusion algorithm in WSN to connect all the IISNs is designed, based on the Peano fractal and swarm intelligence, i.e., without using a hub, simply sharing parameters with two adjacent IINSs, assuming that any IISN knows the parameters of the rest of these devices, even if they are not adjacent. We simulated the performance of our algorithm and compared it with other state-of-the-art protocols, finding that our proposal generates a longer lifetime of the IIoT network when few IISNs were connected. Thus, there is a saving-energy of approximately 5% but with 64 nodes there is a saving of more than 20%, because the IIoT network can grow in a 3 n way and the proposed topology does not impact in a linear way but log 3 , which balances energy consumption throughout the IIoT network.