Search

Your search keyword '"Tapia, Juan A."' showing total 113 results
Start Over Author "Tapia, Juan A." Publisher ieee
113 results on '"Tapia, Juan A."'

7. Iris Liveness Detection Competition (LivDet-Iris) – The 2023 Edition

Author

Tinsley, Patrick, primary, Purnapatra, Sandip, additional, Mitcheff, Mahsa, additional, Boyd, Aidan, additional, Crum, Colton, additional, Bowyer, Kevin, additional, Flynn, Patrick, additional, Schuckers, Stephanie, additional, Czajka, Adam, additional, Fang, Meiling, additional, Damer, Naser, additional, Liu, Xingyu, additional, Wang, Caiyong, additional, Sun, Xianyun, additional, Chang, Zhaohua, additional, Li, Xinyue, additional, Zhao, Guangzhe, additional, Tapia, Juan, additional, Busch, Christoph, additional, Aravena, Carlos, additional, and Schulz, Daniel, additional

Published
2023
Full Text
View/download PDF

8. SynFacePAD 2023: Competition on Face Presentation Attack Detection Based on Privacy-aware Synthetic Training Data

Author

Fang, Meiling, primary, Huber, Marco, additional, Fierrez, Julian, additional, Ramachandra, Raghavendra, additional, Damer, Naser, additional, Alkhaddour, Alhasan, additional, Kasantcev, Maksim, additional, Pryadchenko, Vasiliy, additional, Yang, Ziyuan, additional, Huangfu, Huijie, additional, Chen, Yingyu, additional, Zhang, Yi, additional, Pan, Yuchen, additional, Jiang, Junjun, additional, Liu, Xianming, additional, Sun, Xianyun, additional, Wang, Caiyong, additional, Liu, Xingyu, additional, Chang, Zhaohua, additional, Zhao, Guangzhe, additional, Tapia, Juan, additional, Gonzalez-Soler, Lazaro, additional, Aravena, Carlos, additional, and Schulz, Daniel, additional

Published
2023
Full Text
View/download PDF

22. Alcohol Consumption Detection from Periocular NIR Images Using Capsule Network

Author

Tapia, Juan, Droguett, Enrique Lopez, and Busch, Christoph

Subjects
FOS: Computer and information sciences, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition
Abstract

This research proposes a method to detect alcohol consumption from Near-Infra-Red (NIR) periocular eye images. The study focuses on determining the effect of external factors such as alcohol on the Central Nervous System (CNS). The goal is to analyse how this impacts on iris and pupil movements and if it is possible to capture these changes with a standard iris NIR camera. This paper proposes a novel Fused Capsule Network (F-CapsNet) to classify iris NIR images taken under alcohol consumption subjects. The results show the F-CapsNet algorithm can detect alcohol consumption in iris NIR images with an accuracy of 92.3% using half of the parameters as the standard Capsule Network algorithm. This work is a step forward in developing an automatic system to estimate "Fitness for Duty" and prevent accidents due to alcohol consumption.

Published
2022

25. Calculation of a Current Vector Trajectory for Enhanced Operation of Synchronous Reluctance Generators Including Saturation.

Author

Hoffer, Alvaro E., Moncada, Roberto H., Pavez-Lazo, Boris J., Tapia, Juan A., and Laurila, Lasse

Subjects
RELUCTANCE motors, SYNCHRONOUS generators, ELECTRIC power production, ELECTRIC power systems, ELECTRIC inductance, MAGNETIC flux
Abstract

This article proposes a simple method to calculate a current vector trajectory for the enhanced operation of the electric power generation system based on a synchronous reluctance machine (SynRM). Owing to magnetic saturation and cross magnetization, the performance and the torque capability of a SynRM vary according to the position and the value of the stator current. State-of-the-art control methods usually assume parameters with constant values, especially the inductance, neglecting saturation, leading to possible uncertainty in the machine operation. Therefore, a current vector trajectory to operate this type of machine, as a generator, in an extended speed range, with enhanced performance and considering magnetic saturation is proposed. A straightforward algorithm based on the inductance characteristic of the machine is used to calculate the trajectory of the stator current vector. This trajectory is evaluated via the numerical simulation of an experimentally validated finite-element model of a SynRM. The results show that the proposed current vector trajectory can improve the torque capability to 5% concerning the estimated trajectory without considering saturation. Experimental results are also provided to demonstrate the enhanced operation of the generator. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

32. Accurate Analytical Model for Synchronous Reluctance Machine With Multiple Flux Barriers Considering the Slotting Effect.

Author

Gallardo, Cesar, Tapia, Juan A., Degano, Michele, and Mahmoud, Hanafy

Subjects
*RELUCTANCE motors, *AIR gap flux, *ELECTRIC flux, *FINITE element method, *ACTINIC flux, *MAGNETIC circuits
Abstract

This article presents an accurate analytical model (AM) for synchronous reluctance machine (SynRM) that incorporates the effect of stator slots on the air gap flux density and torque waveforms. From the formulation of magnetic potential in the air gap for both the stator and rotor, the flux density is obtained, considering the first harmonic of the flux density and the electric loading, the average torque is calculated using the Lorentz’s force. The ripple torque is obtained from the energy stored in magnetic circuit. The method is developed for a rotor with one flux barrier per pole and then extended to a larger number of barriers. To validate the results obtained by the AM proposed finite element analysis have been carried out. Several comparisons have been derived considering different rotor positions as well as different harmonic orders, and the pros and cons of the method are highlighted. The model performs fast and can predict results with high accuracy, and can be adopted to speed up the preliminary design and optimizations of this type of motors, with respect to finite element. In addition, from the analytical expressions it is possible to obtain all the correlations between electrical, magnetic, and geometrical characteristics of the machine, with the advantage of enabling a faster machine design. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

33. NIR Iris Challenge Evaluation in Non-cooperative Environments: Segmentation and Localization

Author

Wang, Caiyong, primary, Wang, Yunlong, additional, Zhang, Kunbo, additional, Muhammad, Jawad, additional, Lu, Tianhao, additional, Zhang, Qi, additional, Tian, Qichuan, additional, He, Zhaofeng, additional, Sun, Zhenan, additional, Zhang, Yiwen, additional, Liu, Tianbao, additional, Yang, Wei, additional, Wu, Dongliang, additional, Liu, Yingfeng, additional, Zhou, Ruiye, additional, Wu, Huihai, additional, Zhang, Hao, additional, Wang, Junbao, additional, Wang, Jiayi, additional, Xiong, Wantong, additional, Shi, Xueyu, additional, Zeng, Shao, additional, Li, Peihua, additional, Sun, Haodong, additional, Wang, Jing, additional, Zhang, Jiale, additional, Wang, Qi, additional, Wu, Huijie, additional, Zhang, Xinhui, additional, Li, Haiqing, additional, Chen, Yu, additional, Chen, Liang, additional, Zhang, Menghan, additional, Sun, Ye, additional, Zhou, Zhiyong, additional, Boutros, Fadi, additional, Damer, Naser, additional, Kuijper, Arjan, additional, Tapia, Juan, additional, Valenzuela, Andres, additional, Busch, Christoph, additional, Gupta, Gourav, additional, Raja, Kiran, additional, Wu, Xi, additional, Li, Xiaojie, additional, Yang, Jingfu, additional, Jing, Hongyan, additional, Wang, Xin, additional, Kong, Bin, additional, Yin, Youbing, additional, Song, Qi, additional, Lyu, Siwei, additional, Hu, Shu, additional, Premk, Leon, additional, Vitek, Matej, additional, Struc, Vitomir, additional, Peer, Peter, additional, Khiarak, Jalil Nourmohammadi, additional, Jaryani, Farhang, additional, Nasab, Samaneh Salehi, additional, Moafinejad, Seyed Naeim, additional, Amini, Yasin, additional, and Noshad, Morteza, additional

Published
2021
Full Text
View/download PDF

37. Iris Liveness Detection Competition (LivDet-Iris) - The 2020 Edition

Author

Das, Priyanka, primary, Mcfiratht, Joseph, additional, Fang, Zhaoyuan, additional, Boyd, Aidan, additional, Jang, Ganghee, additional, Mohammadi, Amir, additional, Purnapatra, Sandip, additional, Yambay, David, additional, Marcel, Sebastien, additional, Trokielewicz, Mateusz, additional, Maciejewicz, Piotr, additional, Bowyer, Kevin, additional, Czajka, Adam, additional, Schuckers, Stephanie, additional, Tapia, Juan, additional, Gonzalez, Sebastian, additional, Fang, Meiling, additional, Damer, Naser, additional, Boutros, Fadi, additional, Kuijper, Arian, additional, Sharma, Renu, additional, Chen, Cunjian, additional, and Ross, Arun, additional

Published
2020
Full Text
View/download PDF

38. Iris Liveness Detection Using a Cascade of Dedicated Deep Learning Networks.

Author

Tapia, Juan E., Gonzalez, Sebastian, and Busch, Christoph

Abstract

Iris pattern recognition has significantly improved the biometric authentication field due to its high stability and uniqueness. Such physical characteristics have played an essential role in security applications and other related areas. However, presentation attacks, also known as spoofing techniques, can bypass biometric authentication systems using artefacts such as printed images, artificial eyes, textured contact lenses, etc. Many liveness detection methods that improve the robustness of these systems have been proposed. The first International Iris Liveness Detection competition, where the effectiveness of liveness detection methods is evaluated, was first launched in 2013, and its latest iteration was held in 2020. In this paper, we present the approach that won the LivDet-Iris 2020 competition using two-class scenarios (bona fide iris images vs. presentation attack iris images). Additionally, we propose new three-class and four-class scenarios that complement the competition results. These methods use a serial architecture based on a MobileNetV2 modification, trained from scratch to classify bona fide iris images versus presentation attack images. The bona fide class consists of live iris images, whereas the attack presentation instrument classes consist of cadaver, printed, and contact lenses images, for a total of four species. All the images were pre-processed and weighted per class to present a fair evaluation. This approach is primarily focused on detecting the bona fide class over improving the detection of presentation attack instruments. For the two, three, and four classes scenarios BPCER10 values of 0.99%, 0.16%, and 0.83% were obtained respectively, whereas for the BPCER20 values of 3.09%, 0.16%, and 3.77% were obtained, with the best model overall being the proposed 3-class serial model. This work reaches competitive results according to the reported results in the LivDet-Iris 2020 competition. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

43. Analysis and Assessment of Use of Voltage and Current Inverters Applied to the Ozone Generation in High Frequency.

Author

Aqui-Tapia, Juan Antonio, Ponce-Silva, Mario, Rodriguez-Benitez, Oscar Miguel, and Saavedra-Benitez, Yesica Imelda

Subjects
*OZONE, *POWER density, *VOLTAGE, *PRODUCT management software, *PARTIAL discharges, *PULSE width modulation transformers
Abstract

The study of this article mainly focuses on the assessment and performance of current and voltage inverters in ozone generation, applying power density modulation (PDM) and typical operation. The topologies designed were a voltage-source full-bridge inverter (VSFBI), a current-source full-bridge inverter (CSFBI), and a CSFBI without considers the PDM. The inverters were analyzed and implemented considering an inductor–capacitor–capacitor (LCC) series–parallel resonant tank for the VSFBI and an LC parallel resonant tank for the CSFBI. The duty cycle impact (Dm) of the modulation signal was analyzed, and all inverters were compared. Based on the results, the decrease in Dm allows increasing the ozone generation because of avoiding the dissociation of the ozone molecules. The maximum concentration and efficacy presented by the VSFBI in ozone production were 620 gr/m3 and 0.155 gr/min. Also, the maximum electrical efficiency was 91%; it was presented by the CSFBI without PDM. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results