Artigos
URI permanente para esta coleçãohttps://repositorio.fei.edu.br/handle/FEI/798
Navegar
735 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.
- Junctionless nanowire transistors effective channel length extraction through capacitance characteristics(2023-10-05) SILVA, E. M.; TREVISOLI, R.; Rodrigo Doria© 2023 Elsevier LtdThis work aims to extract the effective channel length (LEFF) of Junctionless Nanowire Transistors (JNT) through the maximum gate capacitance of the devices. The LEFF extraction has been done by extrapolating the maximum gate capacitance as a function of the devices’ channel length (LMASK) and has shown that LEFF is around 10–15 nm longer than LMASK for devices of different channel doping concentrations.
- Impact of series resistance on the drain current variability in inversion mode and junctionless nanowire transistors(2023-10-05) SILVA, L. M. B. DA; Marcelo Antonio Pavanello; CASSÉ, M.; BARRAUD, S.; VINET, M.; FAYNOT, O.; Michelly De Souza© 2023 Elsevier LtdThis work analyzes the influence of source-drain series resistance variability over the drain current in junctionless and inversion mode nanowire transistors. A comparison between drain current and Y-function variability is presented using experimental data of nanowires with different widths and channel lengths. The source-drain series resistance variability is also presented. The results indicates that source-drain series resistance influence is higher on drain current variability for junctionless than inversion mode nanowire transistors.
Artigo 45 Citação(ões) na Scopus Heuristically accelerated Q-learning: A new approach to speed up reinforcement learning(2004-01-05) Reinaldo Bianchi; RIBEIRO, C. H. C.; COSTA, A. H. R.This work presents a new algorithm, called Heuristically Accelerated Q-Learning (HAQL), that allows the use of heuristics to speed up the well-known Reinforcement Learning algorithm Q-learning. A heuristic function H that influences the choice of the actions characterizes the HAQL algorithm. The heuristic function is strongly associated with the policy: it indicates that an action must be taken instead of another. This work also proposes an automatic method for the extraction of the heuristic function H from the learning process, called Heuristic from Exploration. Finally, experimental results shows that even a very simple heuristic results in a significant enhancement of performance of the reinforcement learning algorithm. © Springer-Verlag 2004.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 8 Citação(ões) na Scopus Study of matching properties of graded-channel SOI MOSFETs(2008-01-05) Michelly De Souza; FLANDRE, D.; Marcelo Antonio PavanelloIn this paper an overall analysis on the matching properties of Graded-Channel (GC) SOI MOSFETs in comparison to conventional SOI transistors is performed. Experimental results show that GC devices present poorer matching behavior in comparison to conventional SOI counterpart for equal mask channel length, whereas for same effective channel length, almost the same matching behavior. The analytical model for the drain current of GC devices is used to investigate the reasons for this matching worsening. Two-dimensional numerical simulations are used to validate the model-based analysis both in linear and saturation regions.Artigo 1 Citação(ões) na Scopus The Haar wavelets used how expansion function in the method of the moments in the solution of some electrostatic problems(2010-08-05) Aldo Belardi; CARDOSO, J. R.; SARTORI, C. A. F.This work presents the methodology from the determination the charge superficial density and electrical fields, in three simple structures to a finite straight wire, square plane plates and the capacitance between to plane plate, all finite and submitted to a constant potential. That involves the method of the moments using as expansion function the Haar wavelets instead of the pulse function, in order to reach a good precision and reducing the computational execution time. We also intend to take advantages of the wavelets application through the Cholesky decomposition, talking about formation of scattered matrixes, and the detection of nulls values.Artigo 17 Citação(ões) na Scopus Thin-film lateral SOI pin diodes for thermal sensing reaching the cryogenic regime(2010-09-01) Michelly De Souza; RUE, B.; FLANDRE, D.; Marcelo Antonio PavanelloThis paper presents the performance of lateral SOI PIN diodes for temperature sensing in the range of 100 K to 400 K. Experimental results indicate that PIN diodes can be used to implement temperature sensors with high accuracy in cryogenic regime, provided that a suitable temperature range is chosen for calibration. Numerical simulations using Atlas two-dimensional simulator were performed in order to confirm this hypothesis and extend the analysis, verifying the accuracy of the existing model.Artigo 2 Citação(ões) na Scopus Performance of source follower buffers implemented with standard and strained triple-gate nFinFETs(2010-09-05) Marcelo Antonio Pavanello; MARTINO, J. A.; SIMOEN, E.; ROOYACKERS, R.; COLLAERT, N.; CLAEYS, C.In this work the application of standard and strained triple-gate FinFETs in unity-gain source-follower configuration is compared. The analysis is performed by evaluating the buffer voltage gain with respect to the fin width and channel length as well as the total harmonic distortion. It is demonstrated that the application of strained material in narrow FinFETs, when the devices are operating in double-gate mode, can be beneficial for the performance of buffers in any channel length. On the other hand, for triple-gate FinFETs or quasi-planar ones the degradation of the output conductance overcomes the transconductance improvements from strained material and the performance of standard buffers is better than of strained ones. Narrow strained buffers also offer better harmonic distortion.