RESUMO

This paper presents a semi-automated, scalable, and homologous methodology towards IoT implemented in Python for extracting and integrating images in pedestrian and motorcyclist areas on the road for constructing a multiclass object classifier. It consists of two stages. The first stage deals with creating a non-debugged data set by acquiring images related to the semantic context previously mentioned, using an embedded device connected 24/7 via Wi-Fi to a free and public CCTV service in Medellin, Colombia. Through artificial vision techniques, and automatically performs a comparative chronological analysis to download the images observed by 80 cameras that report data asynchronously. The second stage proposes two algorithms focused on debugging the previously obtained data set. The first one facilitates the user in labeling the data set not debugged through Regions of Interest (ROI) and hotkeys. It decomposes the information in the nth image of the data set in the same dictionary to store it in a binary Pickle file. The second one is nothing more than an observer of the classification performed by the user through the first algorithm to allow the user to verify if the information contained in the Pickle file built is correct.

RESUMO

Nowadays, monitoring aspects related to sustainability and safety in mining activities worldwide are a priority, to mitigate socio-environmental impacts, promote efficient use of water, reduce carbon footprint, use renewable energies, reduce mine waste, and minimize the risks of accidents and fatalities. In this context, the implementation of sensor technologies is an attractive alternative for the mining industry in the current digitalization context. To have a digital mine, sensors are essential and form the basis of Industry 4.0, and to allow a more accelerated, reliable, and massive digital transformation, low-cost sensor technology solutions may help to achieve these goals. This article focuses on studying the state of the art of implementing low-cost sensor technologies to monitor sustainability and safety aspects in mining activities, through the review of scientific literature. The methodology applied in this article was carried out by means of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and generating science mapping. For this, a methodological procedure of three steps was implemented: (i) Bibliometric analysis as a quantitative method, (ii) Systematic review of literature as a qualitative method, and (iii) Mixed review as a method to integrate the findings found in (i) and (ii). Finally, according to the results obtained, the main advances, gaps, and future directions in the implementation of low-cost sensor technologies for use in smart mining are exposed. Digital transformation aspects for data measurement with low-cost sensors by real-time monitoring, use of wireless network systems, artificial intelligence, machine learning, digital twins, and the Internet of Things, among other technologies of the Industry 4.0 era are discussed.

RESUMO

Measuring lycopene in tomatoes is fundamental to the agrifood industry because of its health benefits. It is one of the leading quality criteria for consuming this fruit. Traditionally, the amount determination of this carotenoid is performed using the high-performance liquid chromatography (HPLC) technique. This is a very reliable and accurate method, but it has several disadvantages, such as long analysis time, high cost, and destruction of the sample. In this sense, this work proposes a low-cost sensor that correlates the lycopene content in tomato with the color present in its epicarp. A Raspberry Pi 4 programmed with Python language was used to develop the lycopene prediction model. Various regression models were evaluated using neural networks, fuzzy logic, and linear regression. The best model was the fuzzy nonlinear regression as the RGB input, with a correlation of R2 = 0.99 and a mean error of 1.9 × 10-5. This work was able to demonstrate that it is possible to determine the lycopene content using a digital camera and a low-cost integrated system in a non-invasive way.

RESUMO

Currently, remote laboratories have gained relevance in engineering education as tools to support active learning, experimentation, and motivation of students. Nonetheless, the costs and issues regarding their implementation and deployment limit the access of the students and educators to their advantages and features such as technical and educational. In this line, this study describes a fully open-source remote laboratory in hardware and software for education in automatic control systems employing Raspberry Pi and Python language with an approximate cost of USD 461. Even, by changing some components, the cost can be reduced to USD 420 or less. To illustrate the functionalities of the laboratory, we proposed a low-cost tank control system with its respective instrumentation, signal conditioning, identification, and control, which are exposed in this document. However, other experiments can be easily scalable and adaptable to the remote laboratory. Concerning the interface of the laboratory, we designed a complete user-friendly web interface with real-time video for the users to perform the different activities in automatic control such as identification or controller implementation through the programming language Python. The instructions to build and replicate the hardware and software are indicated in the open repositories provided for the project as well as in this paper. Our intention with this project is to offer a complete low-cost and open-source remote laboratory that can be adapted and used for the students, educators, and stakeholders to learn, experiment, and teach in the field of automatic control systems.

RESUMO

A device known as a pipeline inspection gauge (PIG) runs through oil and gas pipelines which performs various maintenance operations in the oil and gas industry. The PIG velocity, which plays a role in the efficiency of these operations, is usually determined indirectly from odometers installed in it. Although this is a relatively simple technique, the loss of contact between the odometer wheel and the pipeline results in measurement errors. To help reduce these errors, this investigation employed neural networks to estimate the speed of a prototype PIG, using the pressure difference that acts on the device inside the pipeline and its acceleration instead of using odometers. Static networks (e.g., multilayer perceptron) and recurrent networks (e.g., long short-term memory) were built, and in addition, a prototype PIG was developed with an embedded system based on Raspberry Pi 3 to collect speed, acceleration and pressure data for the model training. The implementation of the supervised neural networks used the Python library TensorFlow package. To train and evaluate the models, we used the PIG testing pipeline facilities available at the Petroleum Evaluation and Measurement Laboratory of the Federal University of Rio Grande do Norte (LAMP/UFRN). The results showed that the models were able to learn the relationship among the differential pressure, acceleration and speed of the PIG. The proposed approach can complement odometer-based systems, increasing the reliability of speed measurements.

Assuntos

RESUMO

This work describes the development of a Point-of-Care (POC) Lab-on-a-Chip (LOC) instrument for diagnosis of SARS-CoV-2 by Reverse-Transcription Loop-mediated isothermal amplification (RT-LAMP). The hardware is based on a Raspberry Pi computer ($35), a video camera, an Arduino Nano microcontroller, a printed circuit board as a heater and a 3D printed housing. The chips were manufactured in polymethyl methacrylate (PMMA) using a CO2 laser cutting machine and sealed with a PCR optic plastic film. The chip temperature is precisely controlled by a proportional-integral-derivative (PID) algorithm. During the RT-LAMP amplifications the chip was maintained at ∼ (65.0 ± 0.1) °C for 25 minutes and 5 minutes cooling down, totaling a 30 minutes of reaction .The software interpretation occurs in less than a second. The chip design has four 25 µL chambers, two for clinical samples and two for positive and negative control-samples. The RT-LAMP master mix solution added in the chip chambers contains the pH indicator Phenol Red, that is pink (for pH ∼ 8.0) before amplification and becomes yellow (pH ∼ 6.0) if the genetic material is amplified. The RT-LAMP SARS-CoV-2 diagnostic was made by color image recognition using the OpenCV machine vision software library. The software was programmed to automatically distinguish the HSV color parameter distribution in each one of the four chip chambers. The instrument was successfully tested for SARS-CoV-2 diagnosis, in 22 clinic samples, 11 positives and 11 negatives, achieving an assertiveness of 86% when compared to the results obtained by RT-LAMP standard reactions performed in conventional PCR equipment.

RESUMO

The adequate automatic detection of driver fatigue is a very valuable approach for the prevention of traffic accidents. Devices that can determine drowsiness conditions accurately must inherently be portable, adaptable to different vehicles and drivers, and robust to conditions such as illumination changes or visual occlusion. With the advent of a new generation of computationally powerful embedded systems such as the Raspberry Pi, a new category of real-time and low-cost portable drowsiness detection systems could become standard tools. Usually, the proposed solutions using this platform are limited to the definition of thresholds for some defined drowsiness indicator or the application of computationally expensive classification models that limits their use in real-time. In this research, we propose the development of a new portable, low-cost, accurate, and robust drowsiness recognition device. The proposed device combines complementary drowsiness measures derived from a temporal window of eyes (PERCLOS, ECD) and mouth (AOT) states through a fuzzy inference system deployed in a Raspberry Pi with the capability of real-time response. The system provides three degrees of drowsiness (Low-Normal State, Medium-Drowsy State, and High-Severe Drowsiness State), and was assessed in terms of its computational performance and efficiency, resulting in a significant accuracy of 95.5% in state recognition that demonstrates the feasibility of the approach.

Assuntos

RESUMO

The design of a remotely operated vehicle (ROV) with a size of 18.41 cm × 29.50 cm × 33.50 cm, and a weight of 15.64 kg, is introduced herein. The main goal is to capture underwater video by remote control communication in real time via Ethernet protocol. The ROV moves under the six brushless motors governed through a smart PID controller (Proportional + Integral + Derivative) and by using pulse-wide modulation with short pulses of 1 µs to improve the stability of the position in relation to the translational, ascent or descent, and rotational movements on three axes to capture images of 800 × 640 pixels on a video graphic array standard. The motion control, 3D position, temperature sensing, and video capture are performed at the same time, exploiting the four cores of the Raspberry Pi 3, using the threading library for parallel computing. In such a way, experimental results show that the video capture stage can process up to 42 frames per second on a Raspberry Pi 3. The remote control of the ROV is executed under a graphical user interface developed in Python, which is suitable for different operating systems, such as GNU/Linux, Windows, Android, and OS X. The proposed ROV can reach up to 100 m underwater, thus solving the issue of divers who can only reach 30 m depth. In addition, the proposed ROV can be useful in underwater applications such as surveillance, operations, maintenance, and measurement.

RESUMO

Raspberry Pi is a low-cost computer created with educational purposes. It uses Linux and, most of times, freeware applications, particularly a software for viewing DICOM images. With an external monitor, the supported resolution (1920 × 1200 pixels) allows for the set up of simple viewing workstations at a reduced cost.

Raspberry Pi é um computador de baixo custo criado com propostas educativas. Utiliza o Linux e seus softwares são gratuitos, em sua maioria. Há softwares para visualização de imagens no formato DICOM. Com o uso de um monitor externo, a resolução suportada (1920 × 1200 pixels) permite a criação de estações de visualização simples de exames com custo reduzido.