Artigos
URI permanente para esta coleçãohttps://repositorio.fei.edu.br/handle/FEI/798
Navegar
403 resultados
Filtros
Configurações
Resultados da Pesquisa
- Automatic detection of people with reduced mobility using YOLOv5 and data reduction strategy(2023-05-29) ADORNO, P. L. V.; JASENOVSKI, I. M.; SANTIAGO, D. F. DE M.; Leila Bergamasco© 2023 Copyright held by the owner/author(s).Context: A portion of the users in the São Paulo Metro are people who have physical limitations and need the help of wheelchairs or other similar devices. In this way, the Metro stations have elevators that allow these users to move between the floors of the station. In order, for the elevator to be used, it is necessary for the user to call the operators of the stations, who, in turn, check if the user who is requesting access to the elevator fits the target audience. Problem: This type of request requires manual validation by station operators, causing interruptions in their work routines and delays in passenger travel. Solution: To implement and evaluate artificial intelligence methods for automatic detection of people in wheelchairs or other auxiliary devices. IS Theory: This project was idealized from the perspective of Customer Focus Theory. Method: The You Only Look Once (YOLOv5) neural network was implemented in the Mobility Aids database. Tests were performed considering the original and modified base, composed of a reduced number of images, aiming to assess whether the accuracy of the model remains even with reduced database data. Summary of Results: The results obtained show an average accuracy of more than 92% with the modified database. Contribution: The results corroborated our methodology and we will be able to test in Sao Paulo subway with real images. In a long term, It is expected that by automating such a task, operators will be less overloaded and passengers with reduced mobility will gain more autonomy.
Artigo de evento 4 Citação(ões) na Scopus Elbow flexion and extension movements characterization by means of EMG(2008-01-05) BITTAR, L. M.; Castro, M.C.F.Electromyographic (EMG) signal is the electrical manifestation of neuromuscular activation associated with muscle contraction. The present work intends to characterize the behavior of the muscles biceps and triceps during elbow flexion and extension movements, without load. These movements were performed at horizontal and vertical planes. Three types of test were performed, for each plane, relating EMG signal with joint position. Five men volunteers, ages ranged between 18 and 21 years old, were selected to participate to the tests. The first test consisted to move 10 degrees for each three seconds until the allowed maximum flexion and then, to return at the same way to the initial position. For the second test, the same movement was made but continuously, without stopping at intermediate positions. And for the third test, continuously flexion and extension movements were repeated sequentially but for different amplitudes, increasing by 10 degrees each. The tests were repeated, three times each. Initially, graphical analysis of the data was made for standard behavior detection and, for a quantitative analysis, after EMG preprocessing, averages and variation coefficients were calculated from specific intervals at the beginning, middle and at the end of movement. Although an EMG signals inherent variability, results showed inter and intra subject's repeatability, but only for movements performed at the horizontal plane.Artigo de evento 0 Citação(ões) na Scopus Study of circular gate SOI nMOSFET devices at high temperatures(2008-05-12) ALMEIDA, L. M.; BELLODI, M.The aim of this work is to evaluate the drain leakage current behavior in a Circular Gate (CG) SOI nMOSFET fabricated in 0.13 μm SOI CMOS technology. This technology is analyzed operating since room temperature up to 300°C, where the channel length and the geometrical drain bias terminal influence are analyzed in the drain leakage current behavior, when the devices are operating at high temperatures, through 3D numerical simulations. Since the CG SOI nMOSFET is not a symmetrical structure, it is possible to have two different configurations as following: the one which structure is configured with external drain and another one, with internal drain. Analyzing the drain leakage current behavior as a function of channel length at high temperatures, it is possible to observe that for the same channel length, as the temperature increases, it becomes higher and it increases as the channel length reduces. On the other hand, when the devices are operating with external drain, the drain leakage current becomes lower as compared to the internal drain, for both devices operating at same conditions. The results show that the drain leakage current depends strongly on the channel length and its density distribution is non uniform along the silicon film thickness. Besides it, also was observed that the drain leakage current depends on drain terminal configuration. Then, in order to understand the drain configuration influence in the drain leakage current behavior at high temperatures, the electric field was analyzed into the silicon film.Artigo de evento 1 Citação(ões) na Scopus Spatial reasoning about string loops and holes in temporal asp(2020-09-12) CABALAR, P.; Paulo Santos© 2020 17th International Conference on Principles of Knowledge Representation and Reasoning, KR 2020. All rights reserved.This paper introduces a new formalism for the automated solution of spatial scenarios involving strings and holed objects. In particular, we revisit a previous formalisation that allows string loops to be treated as holes, but make a substantial modification by removing a previous limitation that prevented a string to cross its own loops. The formalisation introduced in the present paper relies on string segments as basic entities and achieves a greater degree of elaboration tolerance by using inertia to describe those parts of the physical scenario that are unaffected by a given action. As a representation language, we have used Temporal Answer Set Programming since it provides a simple and natural way to deal with time and inertia while, at the same time, it is accompanied by the automated tool telingo that allows a systematic testing of the effects of any sequence of actions. As an illustrative example, we have studied the African Ring puzzle, a problem involving loops crossed by a unique string, and provided the first formalisation of its solution, to the best of our knowledge.- Controlling gene regulatory networks with FQI-SARSA(2017-06-28) NISHIDA, C. E. H.; COSTA, A. H. R.; Reinaldo Bianchi© 2017 IEEE.External control of a gene regulatory network model can help accelerate the design of treatments to make it avoid diseased states. However, inferring this model and then controlling it has a exponential complexity of time and space, making large networks inviable for model dependent approaches. This is visible in the literature as only models with at most dozens of genes could be used in control problems. We propose to apply a batch reinforcement learning method Fitted Q-Iteration Sarsa for controlling partially observable gene regulatory networks directly from data, with a new reward function and a way to create experience tuples from gene expression samples. Our framework produces approximate stochastic policies without restricting it to time series samples, allowing it to freely manage the experience tuples. Results demonstrate that our method is more effective than previous studies, with a higher shifting between undesirable to desirable states and higher expected reward.
- Dynamic analysis of the fractional PID controller(2018-07-05) HERDEIRO, J. T.; Renato AguiarCopyright © 2018 by SCITEPRESS – Science and Technology Publications, Lda. All rights reservedThis article presents as main objective the study and application of the fractional PID controller in a positioning system, a controller that has basis on the fractional calculus theory originated in 1695 and, despite having generated several paradoxes in the decade, nowadays there are important applications of this theory, as the one reported in this paper. Initially, the controller will be designed by means of computational simulation for the nominal model of a plant, using a program in Matlab and optimization algorithms and, then, applying in a real process using a data acquisition technique in order to analyse its dynamic behavior in the presence of real external disturbances. Given that the fractional PID is a generalization of the traditional PID, the goal is to obtain, in practice, the benefits of this one in relation to the another, mainly observing the requirements of robustness and stability that must be present in the system.
- Combining Deep Learning and Multi-class Discriminant Analysis for Granite Tiles Classification(2018-01-05) FILISBINO, T.; GIRALDI, G.; SIMO, L.; Carlos E. Thomaz© 2017 IEEE.Convolutional neural networks (CNNs) have become the state-of-the-art in automatic feature learning which has led to outstanding performance on pattern recognition applications. On the other hand, methodologies for discriminant analysis on multiclass problems have been proposed to determine the discriminant contribution of each feature. In this paper, we combine the capabilities of CNN and multi-class discriminant analysis to propose a general data-driven methodology for feature learning and discriminability for texture classification. The whole pipeline has two main blocks: (a) An approach that understands intrinsic patterns in small image patches using CNNs customized for the focused problem; (b) A multi-class discriminant analysis technique, fed with the CNN output, to select the most discriminant features for classification tasks. Our experimental results have shown that the feature spaces generated by the combination of CNN and discriminant analysis allow higher recognition rates using very much less CNN features in five-class granite image analysis.
- Control of gene regulatory networks basin of attractions with batch reinforcement learning(2018) Nishida C.E.H.; Costa A.H.R.; Bianchi R.A.D.C.© 2018 IEEE.Basin of attraction contains biological functions and channels cell behavior, so when a gene network is in an unhealthy basin it may cause diseases. Control techniques can support the design of therapies that promote the transition of a biological system from diseased to healthier basins. Most control methods first infer a gene network and then derive a control strategy to avoid diseased states. However, this approach is limited to few genes and may cause other diseases, as the biological side of the problem is not considered. While changing between basins may change diseased biological function for a healthier one, state avoidance can change functions in an unexpected way. We propose to extend a batch reinforcement learning method FQI-Sarsa, to change basin of attractions in a partial observable network. Using a batch reinforcement learning technique avoids the most time consuming phases that are the inference and control of the gene network. Results demonstrate that our method, BOAFQI-Sarsa, is more effective than previous studies that do not consider basins in their computations.
- Wearable large-area touch sensor: Design, simulation and experimental results(2019-08-05) PESSOA, P. S.; Renato Giacomini; BORELLI, C.; BUHLER, R. T.© 2019 IEEE.This work describes a wearable large-area touch sensor, which has been developed for healthcare purpose. The created model grants real-time response of an individual that touches the fabric, allowing its use as cloth. One of the main goals achieved is the creation of a fabric sensor with flexibility and satisfying humidity transportation levels. Besides the sensor itself a digital system was designed to read sensor information and provide data on the position and intensity of the touch. Furthermore, the developed Simulink model allows accurate simulation of the elaborated sensor, with many trimming tools and adjusts.
- Analysis of the scattering mechanisms in the accumulation layer of junctionless nanowire transistors at high temperature(2019-08-05) RIBEIRO, T. A.; Marcelo Antonio Pavanello© 2019 IEEE.This work studies the effects of high temperature on the scattering mechanisms of Junctionless Nanowire Transistors with several fin width from nanowire to quasi-planar devices. With the variation of the temperature it was possible to analyze the impact of the scattering mechanisms on the devices. For nanowire devices at room temperature a degradation of up to 19% was seen from the maximum mobility to the mobility at higher gate bias to around 15% at 500K, while quasi-planar devices show a degradation of around 12% for all temperatures. Further analysis shows that the impact of the surface roughness for nanowires increase the degradation of these devices, where a reduction of its degradation at higher temperature shows the phonon scattering as the main scattering mechanism.