Loading...
26 results
Search Results
Now showing 1 - 10 of 26
- A Systematic Review of IoT Solutions for Smart FarmingPublication . Navarro, Emerson; Costa, Nuno; Pereira, AntónioThe world population growth is increasing the demand for food production. Furthermore, the reduction of the workforce in rural areas and the increase in production costs are challenges for food production nowadays. Smart farming is a farm management concept that may use Internet of Things (IoT) to overcome the current challenges of food production. This work uses the preferred reporting items for systematic reviews (PRISMA) methodology to systematically review the existing literature on smart farming with IoT. The review aims to identify the main devices, platforms, network protocols, processing data technologies and the applicability of smart farming with IoT to agriculture. The review shows an evolution in the way data is processed in recent years. Traditional approaches mostly used data in a reactive manner. In more recent approaches, however, new technological developments allowed the use of data to prevent crop problems and to improve the accuracy of crop diagnosis.
- Plataforma Unidose para LaresPublication . Lopes, David Ferreira; Costa, Nuno; Pereira, AntónioA esperança média de vida tem aumentado devido às melhorias que se têm verificado nos serviços de saúde e pela evolução da medicina levando a um envelhecimento da população mundial. As famílias com vidas cada vez mais preenchidas e atarefadas não conseguem prestar o auxílio e o apoio necessário aos idosos levando estes a frequentar cada vez mais Lares e Centros de dia para idosos. Isto leva a que exista uma enorme responsabilidade pela saúde dos idosos por parte dos lares que os acolhem sobretudo ao nível da medicação, delegando grandes responsabilidades a funcionários da instituição. Os funcionários como seres humanos erram, podem errar, haver negligência ao darem a toma de medicação aos idosos. Cada vez mais os idosos têm menos capacidades financeiras devido a situação económica do país e alguns acabam mesmo por ter que deixar a medicação para sobreviverem. A Plataforma Unidose para Lares (PUL) é uma solução para tentar contrariar ou resolver estes problemas. É possível utilizar o sistema Unidose, que permite a venda dos comprimidos à unidade torando-se mais económico e também fazendo a prevenção da toma de medicamentos para não permitir negligencias nem faltas de tomas. Com a utilização da plataforma as vidas dos idosos e funcionários de lares vão ficar mais calmas, com menos preocupações, melhorando assim a qualidade de vida destes.
- Design of Kinematic Connectors for Microstructured Materials Produced by Additive ManufacturingPublication . Silva, Miguel R.; Dias-de-Oliveira, João A.; Pereira, António; Alves, Nuno M.; Sampaio, Álvaro M.; Pontes, António J.The main characteristic of materials with a functional gradient is the progressive composition or the structure variation across its geometry. This results in the properties variation in one or more specific directions, according to the functional application requirements. Cellular structure flexibility in tailoring properties is employed frequently to design functionally-graded materials. Topology optimisation methods are powerful tools to functionally graded materials design with cellular structure geometry, although continuity between adjacent unit-cells in gradient directions remains a restriction. It is mandatory to attain a manufacturable part to guarantee the connectedness between adjoining microstructures, namely by ensuring that the solid regions on the microstructure’s borders i.e., kinematic connectors) match the neighboring cells that share the same boundary. This study assesses the kinematic connectors generated by imposing local density restrictions in the initial design domain (i.e., nucleation) between topologically optimised representative unit-cells. Several kinematic connector examples are presented for two representatives unit-cells topology optimised for maximum bulk and shear moduli with different volume fractions restrictions and graduated Young’s modulus. Experimental mechanical tests (compression) were performed, and comparison studies were carried out between experimental and numerical Young’s modulus. The results for the single maximum bulk for the mean values for experimental compressive Young’s modulus (Ex¯ ) with 60%Vf show a deviation of 9.15% . The single maximum shear for the experimental compressive Young’s modulus mean values (Ex¯ ) with 60%Vf , exhibit a deviation of 11.73% . For graded structures, the experimental mean values of compressive Young’s moduli (Ex¯ ), compared with predicted total Young’s moduli (ESe ), show a deviation of 6.96 for the bulk graded structure. The main results show that the single type representative unit-cell experimental Young’s modulus with higher volume fraction presents a minor deviation compared with homogenized data. Both (i.e., bulk and shear moduli) graded microstructures show continuity between adjacent cells. The proposed method proved to be suitable for generating kinematic connections for the design of shear and bulk graduated microstructured materials.
- Applying deep learning to real-time UAV-based forest monitoring: Leveraging multi-sensor imagery for improved resultsPublication . Marques, Tomás; Carreira, Samuel; Miragaia, Rolando; Ramos, João; Pereira, AntónioRising global fire incidents necessitate effective solutions, with forest surveillance emerging as a crucial strategy. This paper proposes a complete solution using technology that integrates visible and infrared spectrum images through Unmanned Aerial Vehicles (UAVs) for enhanced detection of people and vehicles in forest environments. Unlike existing computer vision models relying on single-sensor imagery, this approach overcomes limitations posed by limited spectrum coverage, particularly addressing challenges in low-light conditions, fog, or smoke. The developed 4-channel model uses both types of images to take advantage of the strengths of each one simultaneously. This article presents the development and implementation of a solution for forest monitoring ranging from the transmission of images captured by a UAV to their analysis with an object detection model without human intervention. This model consists of a new version of the YOLOv5 (You Only Look Once) architecture. After the model analyzes the images, the results can be observed on a web platform on any device, anywhere in the world. For the model training, a dataset with thermal and visible images from the aerial perspective was captured with a UAV. From the development of this proposal, a new 4- channel model was created, presenting a substantial increase in precision and mAP (Mean Average Precision) metrics compared to traditional SOTA (state-of-the-art) models that only make use of red, green, and blue (RGB) images. Allied with the increase in precision, we confirmed the hypothesis that our model would perform better in conditions unfavorable to RGB images, identifying objects in situations with low light and reduced visibility with partial occlusions. With the model’s training using our dataset, we observed a significant increase in the model’s performance for images in the aerial perspective. This study introduces a modular system architecture featuring key modules: multisensor image capture, transmission, processing, analysis, and results presentation. Powered by an innovative object detection deep-learning model, these components collaborate to enable real-time, efficient, and distributed forest monitoring across diverse environments.
- Systematic Review of Emotion Detection with Computer Vision and Deep LearningPublication . Pereira, Rafael; Mendes, Carla; Ribeiro, José; Ribeiro, Roberto; Miragaia, Rolando; Rodrigues, Nuno; Costa, Nuno; Pereira, AntónioEmotion recognition has become increasingly important in the field of Deep Learning (DL) and computer vision due to its broad applicability by using human–computer interaction (HCI) in areas such as psychology, healthcare, and entertainment. In this paper, we conduct a systematic review of facial and pose emotion recognition using DL and computer vision, analyzing and evaluating 77 papers from different sources under Preferred Reporting Items for Systematic Reviews and MetaAnalyses (PRISMA) guidelines. Our review covers several topics, including the scope and purpose of the studies, the methods employed, and the used datasets. The scope of this work is to conduct a systematic review of facial and pose emotion recognition using DL methods and computer vision. The studies were categorized based on a proposed taxonomy that describes the type of expressions used for emotion detection, the testing environment, the currently relevant DL methods, and the datasets used. The taxonomy of methods in our review includes Convolutional Neural Network (CNN), Faster Region-based Convolutional Neural Network (R-CNN), Vision Transformer (ViT), and “Other NNs”, which are the most commonly used models in the analyzed studies, indicating their trendiness in the field. Hybrid and augmented models are not explicitly categorized within this taxonomy, but they are still important to the field. This review offers an understanding of state-of-the-art computer vision algorithms and datasets for emotion recognition through facial expressions and body poses, allowing researchers to understand its fundamental components and trends.
- Assessment of the dimensional and geometric precision of micro-details produced by material jettingPublication . Silva, Miguel R.; Pereira, António; Sampaio, Álvaro M.; Pontes, António J.Additive Manufacturing (AM) technology has been increasing its penetration not only for the production of prototypes and validation models, but also for final parts. This technology allows producing parts with almost no geometry restrictions, even on a micro-scale. However, the micro-Detail (mD) measurement of complex parts remains an open field of investigation. To be able to develop all the potential that this technology offers, it is necessary to quantify a process’s precision limitations, repeatability, and reproducibility. New design methodologies focus on optimization, designing microstructured parts with a complex material distribution. These methodologies are based on mathematical formulations, whose numerical models assume the model discretization through volumetric unitary elements (voxels) with explicit dimensions and geometries. The accuracy of these models in predicting the behavior of the pieces is influenced by the fidelity of the object’s physical reproduction. Despite that the Material Jetting (MJ) process makes it possible to produce complex parts, it is crucial to experimentally establish the minimum dimensional and geometric limits to produce parts with mDs. This work aims to support designers and engineers in selecting the most appropriate scale to produce parts discretized by hexahedral meshes (cubes). This study evaluated the dimensional and geometric precision of MJ equipment in the production of mDs (cubes) comparing the nominal design dimensions. A Sample Test (ST) with different sizes of mDs was modeled and produced. The dimensional and geometric precision of the mDs were quantified concerning the nominal value and the calculated deviations. From the tests performed, it was possible to conclude that: (i) more than 90% of all analyzed mDs exhibit three dimensions (xyz) higher than the nominal ones; (ii) for micro-details smaller than 423 μm, they show a distorted geometry, and below 212 μm, printing fails.
- UAV Landing Using Computer Vision Techniques for Human DetectionPublication . Safadinho, David; Ramos, João; Ribeiro, Roberto; Filipe, Vítor; Barroso, João; Pereira, AntónioThe capability of drones to perform autonomous missions has led retail companies to use them for deliveries, saving time and human resources. In these services, the delivery depends on the Global Positioning System (GPS) to define an approximate landing point. However, the landscape can interfere with the satellite signal (e.g., tall buildings), reducing the accuracy of this approach. Changes in the environment can also invalidate the security of a previously defined landing site (e.g., irregular terrain, swimming pool). Therefore, the main goal of this work is to improve the process of goods delivery using drones, focusing on the detection of the potential receiver. We developed a solution that has been improved along its iterative assessment composed of five test scenarios. The built prototype complements the GPS through Computer Vision (CV) algorithms, based on Convolutional Neural Networks (CNN), running in a Raspberry Pi 3 with a Pi NoIR Camera (i.e., No InfraRed-without infrared filter). The experiments were performed with the models Single Shot Detector (SSD) MobileNet-V2, and SSDLite-MobileNet-V2. The best results were obtained in the afternoon, with the SSDLite architecture, for distances and heights between 2.5-10 m, with recalls from 59%-76%. The results confirm that a low computing power and cost-effective system can perform aerial human detection, estimating the landing position without an additional visual marker.
- Special Issue on Body Area NetworksPublication . Pereira, António; Costa, Nuno; Fernández-Caballero, Antonio
- Fatigue behaviour of epoxy-steel single lap joints under variable frequencyPublication . Reis, P.N.B.; Monteiro, J.F.R.; Pereira, António; Ferreira, J.F.R.; J.D.M. CostaThis work investigates the loading frequency effects on the fatigue behaviour of adhesively-bonded steel lap joints. S-N diagrams of fatigue tests, under constant amplitude loading, were obtained for frequencies ranging between 2 and 40 Hz. The fatigue life for variable frequency tests was estimated based on constant frequency S-N curves, using a linear cumulative damage rule. It is possible to conclude that, for the higher shear stresses, the frequency presents only a marginal effect on fatigue life. On the other hand, for the lower shear stresses, the fatigue life of the adhesive joints is very dependant on the frequency level. Good correlations were obtained between fatigue life predictions and experimental results. © 2015 Elsevier Ltd. All rights reserved.
- Effect of adherends and environment on static and transverse impact response of adhesive lap jointsPublication . Reis, P.N.B.; Soares, J.R.L.; Pereira, António; Ferreira, J.A.M.Impact response of adhesive joints has received limited attention compared to quasi-static loading. On the other hand, there are very few studies combining moisture and its effect on the impact strength. Therefore, the present paper aims to study the effect of moisture on the tensile and impact strength of single lap joints with different adherends (high limit elastic steel and a commercial composite). It was possible to conclude that adhesive joints with steel adherends are very sensitive to the environment and exposure time. For adhesive joints with composite adherends, the water showed a marginal effect. A marked hygrothermal effect was observed for all joints. For impact loads the environment effect is similar, but much more severe than that observed in tensile tests. For both tests, adhesive failures occurred for adhesive joints with steel adherends and delaminations for joints involving composite.
- «
- 1 (current)
- 2
- 3
- »