Improving Surgical Scene Semantic Segmentation through a Deep Learning Architecture with Attention to Class Imbalance.

This article addresses the semantic segmentation of laparoscopic surgery images, placing special emphasis on the segmentation of structures with a smaller number of observations. As a result of this study, adjustment parameters are proposed for deep neural network architectures, enabling a robust segmentation of all structures in the surgical scene. The U-Net architecture with five encoder-decoders (U-Net5ed), SegNet-VGG19, and DeepLabv3+ employing different backbones are implemented. Three main experiments are conducted, working with Rectified Linear Unit (ReLU), Gaussian Error Linear Unit (GELU), and Swish activation functions. The applied loss functions include Cross Entropy (CE), Focal Loss (FL), Tversky Loss (TL), Dice Loss (DiL), Cross Entropy Dice Loss (CEDL), and Cross Entropy Tversky Loss (CETL). The performance of Stochastic Gradient Descent with momentum (SGDM) and Adaptive Moment Estimation (Adam) optimizers is compared. It is qualitatively and quantitatively confirmed that DeepLabv3+ and U-Net5ed architectures yield the best results. The DeepLabv3+ architecture with the ResNet-50 backbone, Swish activation function, and CETL loss function reports a Mean Accuracy (MAcc) of 0.976 and Mean Intersection over Union (MIoU) of 0.977. The semantic segmentation of structures with a smaller number of observations, such as the hepatic vein, cystic duct, Liver Ligament, and blood, verifies that the obtained results are very competitive and promising compared to the consulted literature. The proposed selected parameters were validated in the YOLOv9 architecture, which showed an improvement in semantic segmentation compared to the results obtained with the original architecture.

A Novel Robotic Controller Using Neural Engineering Framework-Based Spiking Neural Networks.

This paper investigates spiking neural networks (SNN) for novel robotic controllers with the aim of improving accuracy in trajectory tracking. By emulating the operation of the human brain through the incorporation of temporal coding mechanisms, SNN offer greater adaptability and efficiency in information processing, providing significant advantages in the representation of temporal information in robotic arm control compared to conventional neural networks. Exploring specific implementations of SNN in robot control, this study analyzes neuron models and learning mechanisms inherent to SNN. Based on the principles of the Neural Engineering Framework (NEF), a novel spiking PID controller is designed and simulated for a 3-DoF robotic arm using Nengo and MATLAB R2022b. The controller demonstrated good accuracy and efficiency in following designated trajectories, showing minimal deviations, overshoots, or oscillations. A thorough quantitative assessment, utilizing performance metrics like root mean square error (RMSE) and the integral of the absolute value of the time-weighted error (ITAE), provides additional validation for the efficacy of the SNN-based controller. Competitive performance was observed, surpassing a fuzzy controller by 5% in terms of the ITAE index and a conventional PID controller by 6% in the ITAE index and 30% in RMSE performance. This work highlights the utility of NEF and SNN in developing effective robotic controllers, laying the groundwork for future research focused on SNN adaptability in dynamic environments and advanced robotic applications.

Bioinspired Photoreceptors with Neural Network for Recognition and Classification of Sign Language Gesture.

This work addresses the design and implementation of a novel PhotoBiological Filter Classifier (PhBFC) to improve the accuracy of a static sign language translation system. The captured images are preprocessed by a contrast enhancement algorithm inspired by the capacity of retinal photoreceptor cells from mammals, which are responsible for capturing light and transforming it into electric signals that the brain can interpret as images. This sign translation system not only supports the effective communication between an agent and an operator but also between a community with hearing disabilities and other people. Additionally, this technology could be integrated into diverse devices and applications, further broadening its scope, and extending its benefits for the community in general. The bioinspired photoreceptor model is evaluated under different conditions. To validate the advantages of applying photoreceptors cells, 100 tests were conducted per letter to be recognized, on three different models (V1, V2, and V3), obtaining an average of 91.1% of accuracy on V3, compared to 63.4% obtained on V1, and an average of 55.5 Frames Per Second (FPS) in each letter classification iteration for V1, V2, and V3, demonstrating that the use of photoreceptor cells does not affect the processing time while also improving the accuracy. The great application potential of this system is underscored, as it can be employed, for example, in Deep Learning (DL) for pattern recognition or agent decision-making trained by reinforcement learning, etc.

Software-Defined Networking Solutions, Architecture and Controllers for the Industrial Internet of Things: A Review.

The use of Software-Defined Networking (SDN) in the communications of the Industrial Internet of Things (IIoT) demands more comprehensive solutions than those developed to date. The lack of an SDN solution applicable in diverse IIoT scenarios is the problem addressed in this article. The main cause of this problem is the lack of integration of a set of aspects that should be considered in a comprehensive SDN solution. To contribute to the solution of this problem, a review of the literature is conducted in this article, identifying the main requirements for industrial networks nowadays as well as their solutions through SDN. This review indicates that aspects such as security, independence of the network technology used, and network centralized management can be tackled using SDN. All the advantages of this technology can be obtained through the implementation of the same solution, considering a set of aspects proposed by the authors for the implementation of SDNs in IIoT networks. Additionally, after analyzing the main features and advantages of several architectures proposed in the literature, an architecture with distributed network control is proposed for all SDN network scenarios in IIoT. This architecture can be adapted through the inclusion of other necessary elements in specific scenarios. The distributed network control feature is relevant here, as it prevents a single fault-point for an entire industrial network, in exchange for adding some complexity to the network. Finally, the first ideas for the selection of an SDN controller suitable for IIoT scenarios are included, as this is the core element in the proposed architecture. The initial proposal includes the identification of six controllers, which correspond to different types of control planes, and ten characteristics are defined for selecting the most suitable controller through the Analytic Hierarchy Process (AHP) method. The analysis and proposal of different fundamental aspects for the implementation of SDNs in IIoT in this article contribute to the development of a comprehensive solution that is not focused on the characteristics of a specific scenario and would, therefore, be applicable in limited situations.

Design and Implementation of Intelligent Agent Training Systems for Virtual Vehicles.

This paper presents the results of the design, simulation, and implementation of a virtual vehicle. Such a process employs the Unity videogame platform and its Machine Learning-Agents library. The virtual vehicle is implemented in Unity considering mechanisms that represent accurately the dynamics of a real automobile, such as motor torque curve, suspension system, differential, and anti-roll bar, among others. Intelligent agents are designed and implemented to drive the virtual automobile, and they are trained using imitation or reinforcement. In the former method, learning by imitation, a human expert interacts with an intelligent agent through a control interface that simulates a real vehicle; in this way, the human expert receives motion signals and has stereoscopic vision, among other capabilities. In learning by reinforcement, a reward function that stimulates the intelligent agent to exert a soft control over the virtual automobile is designed. In the training stage, the intelligent agents are introduced into a scenario that simulates a four-lane highway. In the test stage, instead, they are located in unknown roads created based on random spline curves. Finally, graphs of the telemetric variables are presented, which are obtained from the automobile dynamics when the vehicle is controlled by the intelligent agents and their human counterpart, both in the training and the test track.

Development of an expert system for pre-diagnosis of hypertension, diabetes mellitus type 2 and metabolic syndrome.

This study involved the development of an expert system for the pre-diagnosis of hypertension, diabetes mellitus type 2 and metabolic syndrome. The expert system has been developed using web technologies, PHP, Apache and MySQL with CLIPS tool; the expert system includes three algorithms designed by the authors, one for each disease. The objective of this study is to provide an expert system capable of performing a pre-diagnosis for early detection of hypertension, diabetes mellitus type 2 and metabolic syndrome. The methodology to build the system consists in associated risk factors, clinical variables diagnosis criteria based on World Health Organization standards in three algorithms and then develop a program that interacts with users, besides the expert system is compared with the existing expert systems in order to show its originality and innovation. The rules of systems are designed using CLIPS systems and the Architecture Apache, MySQL and PHP for the user interface and database. The system was validated by 72 patient(s) and 3 real doctors, the total result over 72 patient(s) is low risk 16.6 percent, moderate risk 30.5 percent, moderate high risk 13.8 percent, high risk 23.6 percent, very high risk 15.2 percent, and the doctors' feedback was similar to that shown by the system. The number of rules to create the algorithms and the criteria used were adequate and sufficient to obtain the pre-diagnosis of each disease; in addition, the languages used to design and create the web application were stable. All users who used the system obtained similar results to those obtained by doctors.

Automatized follow-up and alert system for patients with chronic hypertension.

This article presents the development and implementation of a monitoring system for patients with chronic hypertension. Technological advances in wireless communication are increasingly used today to send and receive information through smartphones. This also applies to devices for measuring blood pressure, which can be efficiently integrated with smartphones. Telemedicine is used in a variety of health fields, and in the past 5 years, it has extended its reach to the online monitoring of patients. The objective of this study is to create an integrated system capable of conducting the follow-up, through mobile communication (smartphones), of patients with chronic diseases such as hypertension. An iHealth equipment certified by the Food and Drug Administration is used. The blood pressure values from users are uploaded via Internet and stored in an integral system for processing. The monitoring system developed not only informs users about their disease status but also sends them alerts generated during monitoring. This work uses the telecommunication technology existing through smartphones. The integrated system developed ensures the follow-up of the blood pressure of a large number of users. In addition, this system can be further applied to diseases such as diabetes and metabolic syndrome. The system developed was easy to use and efficient to monitor patients with chronic diseases such as high blood pressure.

Material particulado y gases contaminantes en la comuna de El Bosque ¿cuánto influyen en la cantidad de consultas por enfermedades respiratorias? / Association between air pollution and emergency consultations for respiratory diseases

Background Air pollution has a direct influence on health. Aim To determine the association between particulate matter and contaminant gas concentrations in the environment with the number of consultations for respiratory diseases in emergency rooms in Metropolitan Santiago, Chile. Material and Methods During five years, the daily number emergency consultations for respiratory diseases and the daily concentrations of particulate matter and contaminant gases in a community of Santiago, were recorded. The degree of change of these variables during summer and winter was determined. Their correlation coefficients with a 0 to 100 days gap, were calculated. Results During winter, there was a higher number of consultations and higher pollution levels, except for O3, which increased in summer. There were positive correlations between the concentrations of different pollutants (mainly 2.5 and 10 μm particulate matter, CO and NO2). There was a negative association between consultations for respiratory diseases and O3 concentrations, an almost negligible association with SO2 and variable positive and significant associations with the concentration of other pollutants, with variations according to the time gap. Conclusions Pollution and respiratory diseases increase during winter. There are variable associations between pollutant concentrations and the number of consultations for respiratory diseases.