Human activity recognition has attracted the attention of researchers around world. This is an interesting problem that can be addressed in different ways. Many approaches have been presented during last years. These applications present solutions to recognize kinds activities such as if person walking, running, jumping, jogging, or falling, among others. Amongst all these activities, fall detection special importance because it a common dangerous event for people ages with more negative...

<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> This paper introduces a Web-based control laboratory for experimentation on nonlinear multiple-input–multiple-output (MIMO) system: the three-tank plant. Using this application, automation technician students can learn in practical way many fundamental aspects of processes. The client-side virtual has been developed using programming support provided by <emphasis emphasistype="italic">Easy Java...

As spacecraft missions become more complex and ambitious, it becomes increasingly important to track the status health of in real-time ensure mission success. Anomaly detection is a crucial part telemetry analysis, allowing engineers quickly identify unexpected or abnormal behaviour reflected on data take appropriate corrective action. Traditional statistical methods based threshold setting are often inadequate for detecting anomalies this context, requiring development sophisticated...

The new information technologies provide great opportunities in control education. One of them is the use remote labs to teach behavior systems through a network. In this paper, approach create interactive networked described. Two main software tools are used: Matlab and Easy Java Simulations. first one widely used tool community, whereas second an authoring tool, designed build applications without special programming skills. created by give students opportunity face effects network delays...

Designing and developing web-enabled remote laboratories for pedagogical purposes is not an easy task. Often, developers (generally, educators who know the subjects they teach but lack of technical programming skills required to build Internet-based educational applications) end up discarding idea exploring these new teaching learning experiences mainly due issues that must be mastered. To tackle this problem, authors present a novel technique allows create labs in quick, didactical,...

In recent years, much effort has been devoted to the development of applications capable detecting different types human activity. this field, fall detection is particularly relevant, especially for elderly. On one hand, some use wearable sensors that are integrated into cell phones, necklaces or smart bracelets detect sudden movements person wearing device. The main drawback these systems devices must be placed on a person's body. This major because they can uncomfortable, in addition fact...

Recently, the scientific community has placed great emphasis on recognition of human activity, especially in area health and care for elderly. There are already practical applications activity unusual conditions that use body sensors such as wrist-worn devices or neck pendants. These relatively simple may be prone to errors, might uncomfortable wear, forgotten not worn, unable detect more subtle incorrect postures. Therefore, other proposed methods based images videos carry out recognition,...

Contribution: A competency assessment framework that enables learning analytics for course monitoring and continuous improvement.Our work fills the gap in systematic methods higher education.Background: Many institutions are shifting toward competency-based education (CBE), thus encouraging their educators to start evaluating students under this paradigm.Previous research shows structured models fundamental guiding adoption.Intended Outcomes: An model CBE is easy adopt use, while...

The increasing complexity of autonomous vehicles has exposed the limitations many existing control systems. Reinforcement learning (RL) is emerging as a promising solution to these challenges, enabling agents learn and enhance their performance through interaction with environment. Unlike traditional algorithms, RL facilitates via recursive process that can be fully simulated, thereby preventing potential damage actual robot. This paper presents design development an RL-based algorithm for...

The aim of this study is to propose a system that capable recognising the identity person, indicating whether person drunk using only information extracted from thermal face images. proposed divided into two stages, recognition and classification. In stage, test images are recognised robust algorithms: Weber local descriptor (WLD) binary pattern (LBP). classification stage uses Fisher linear discriminant reduce dimensionality features, those features classified classifier based on Gaussian...

The use of mobile robots for teaching automatic control is becoming more popular in engineering curricula. Currently, many robot simulators with high-graphical capabilities can be easily used by instructors to teach engineering. However, the real not as straightforward simulations. There are hardware and software details that must considered before applying control. This paper presents development an easy-to-use platform robots. laboratory has been carefully designed conceal all technical...

This article presents a closed-loop position control of mobile robot, which is capable moving from its current to target point by manipulating linear and angular velocities. The main objective this modify an existing law based on the kinematic model improve response when robot backwards oriented reach destination in less time with shorter trajectory. Stability proposed validated Lyapunov Criterion. Some procedures are implemented test approach both simulation MATLAB, experimentally Khepera IV robot.

The aim of this article is to present a new face recognition system based on the fusion visible and thermal features obtained from most current local matching descriptors by maximizing rates through use genetic algorithms. considers comparison performance proposed methodology against five methods classic techniques used commonly in literature. These were selected considering their recognition. are evaluated using standard visible/thermal database, Equinox along with PUCV-VTF, designed for...

Competency-based education is becoming increasingly adopted by higher institutions all over the world. This paper presents a framework that assists instructors in this pedagogical paradigm and its corresponding open-source implementation. The supports formal definition of competency assessment models students' evaluation under these models. It also provides distinct learning analytics for identifying course shortcomings validating corrective actions have introduced course. Finally, reports...

This study presents an artificial intelligence-based approach for the pose detection of passengers’ skeletons when boarding and alighting from urban bus in Valparaíso, Chile. Using AlphaPose estimator activity recognition model based on Random Forest, video data were processed to analyze poses activities passengers. The results obtained allow evaluation safety ergonomics public transportation, providing valuable information improving design accessibility buses. not only enhances...

This paper describes how to use Easy Java Simulations (Ejs for short), a software tool designed create interactive simulations in Java, turn existing models created using Simulink into really dynamic, virtual labs. The user basically needs connect variables the Ejs model an easy-to-use, very natural interface. takes then care of all technical tasks required keep perfect synchronization between both tools. main advantage is that can benefit extended graphic capabilities more realistic...

Internet-based technologies can supplement traditional laboratories with remote or simulated experimentation sessions. The authors describe their virtual and laboratory, which uses a nonlinear system that students run from anywhere on the Internet. implementation integrates both open source commercial software tools.

In this paper, we analyze the problems produced by temporal variations of infrared face images when used in recognition systems. The present thermal are mainly due to different environmental conditions, physiological changes subjects, and differences detectors' responsivity at time capture, which affect performance To perform created two databases that include capture sessions with real variable conditions. We also propose criteria quantify between data sets. systems have been developed...

This paper presents a library for V-REP simulator to incorporate the Khepera IV robot model. The contains model of this and some examples use with its corresponding results. has been developed using Autodesk Inventor visual design Lua language programming code. allows implementation experiments one multi-robots approaches. After in environment, users can transform many simulations into real robots.

The current computational advance allows the development of technological solutions using tools, such as mobile robots and programmable electronic systems. We present a design that integrates Khepera IV robot with an NVIDIA Jetson Xavier NX board. This system executes algorithm for navigation control based on computer vision use model object detection. Among functionalities this integration adds to in generating guided driving are trajectory tracking safe detection traffic signs...