|
|
Juan C. Basurto, P. C. and H. C. (2011). A Proximity-Aware Transparent Handoff Mobility Scheme for VoIP Communication over Infrastructure Mesh Networks. In International Congress of Electronic, Electrical and Systems Engineering-INTERCON 2011.
Abstract: Mobility Management plays a key role in Voice-over- IP (VoIP) communications over Wireless Mesh Networks (WMN) as clients should maintain adequate levels of Quality of Service (QoS) as they move across the network. This paper presents PATH, a Proximity-Aware Transparent Handoff mobility scheme for real time voice communications over wireless mesh networks. Our study focuses on Medium Access Control (MAC) layer procedures and relies on gratuitous ARP unicasting in order to provide fast-handoffs. An experimental evaluation has been conducted and its results are shown in this paper.
|
|
|
|
Ricardo Cajo, & Wilton Agila. (2015). Evaluation of algorithms for linear and nonlinear PID control for Twin Rotor MIMO System. In Computer Aided System Engineering (APCASE), 2015 Asia-Pacific Conference on, Quito, 2015 (pp. 214–219). IEEE.
Abstract: In this paper the linear and nonlinear PID control algorithms are analyzed and for a twin rotor MIMO system (TRMS), whose characteristic is not linear with two degrees of freedom and cross-links. The aim of this work is to stabilize the TRMS, to achieve a particular position and follow a trajectory in the shortest time. Mathematical modeling of helicopter model is simulated using MATLAB / Simulink, the two degrees of freedom are controlled both horizontally and vertically through the proposed controllers. Also nonlinear segmented observers for each degree of freedom are designed in order to measure statements required by the nonlinear controller. Followed, a comparative analysis of both algorithms is presented to evaluate their performance in the real TRMS.
|
|
|
|
Jacome-Galarza L.-R., R. R. M. - A., Paillacho Corredores J., Benavides Maldonado J.-L. (2022). Time series in sensor data using state of the art deep learning approaches: A systematic literature review. In VII International Conference on Science, Technology and Innovation for Society (CITIS 2021), mayo 26-28. Smart Innovation, Systems and Technologies. (Vol. 252, pp. 503–514).
Abstract: IoT (Internet of Things) and AI (Artificial Intelligence) are becoming
support tools for several current technological solutions due to significant advancements of these areas. The development of the IoT in various technological fields has contributed to predicting the behavior of various systems such as mechanical, electronic, and control using sensor networks. On the other hand, deep learning architectures have achieved excellent results in complex tasks, where patterns have been extracted in time series. This study has reviewed the most efficient deep learning architectures for forecasting and obtaining trends over time, together with data produced by IoT sensors. In this way, it is proposed to contribute to applications in fields in which IoT is contributing a technological advance such as smart cities, industry 4.0, sustainable agriculture, or robotics. Among the architectures studied in this article related to the process of time series data we have: LSTM (Long Short-Term Memory) for its high precision in prediction and the ability to automatically process input sequences; CNN (Convolutional Neural Networks) mainly in human activity
recognition; hybrid architectures in which there is a convolutional layer for data pre-processing and RNN (Recurrent Neural Networks) for data fusion from different sensors and their subsequent classification; and stacked LSTM Autoencoders that extract the variables from time series in an unsupervised way without the need of manual data pre-processing.Finally, well-known technologies in natural language processing are also used in time series data prediction, such as the attention mechanism and embeddings obtaining promising results.
|
|
|
|
Rafael E. Rivadeneira, Angel D. Sappa, & Boris X. Vintimilla. (2020). Thermal Image Super-Resolution: a Novel Architecture and Dataset. In The 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020); Valletta, Malta; 27-29 Febrero 2020 (Vol. 4, pp. 111–119).
Abstract: This paper proposes a novel CycleGAN architecture for thermal image super-resolution, together with a large
dataset consisting of thermal images at different resolutions. The dataset has been acquired using three thermal
cameras at different resolutions, which acquire images from the same scenario at the same time. The thermal
cameras are mounted in rig trying to minimize the baseline distance to make easier the registration problem.
The proposed architecture is based on ResNet6 as a Generator and PatchGAN as Discriminator. The novelty
on the proposed unsupervised super-resolution training (CycleGAN) is possible due to the existence of aforementioned thermal images—images of the same scenario with different resolutions. The proposed approach
is evaluated in the dataset and compared with classical bicubic interpolation. The dataset and the network are
available.
|
|
|
|
Cristhian A. Aguilera, C. A., Cristóbal A. Navarro, & Angel D. Sappa. (2020). Fast CNN Stereo Depth Estimation through Embedded GPU Devices. Sensors 2020, Vol. 2020-June(11), pp. 1–13.
Abstract: Current CNN-based stereo depth estimation models can barely run under real-time
constraints on embedded graphic processing unit (GPU) devices. Moreover, state-of-the-art
evaluations usually do not consider model optimization techniques, being that it is unknown what is
the current potential on embedded GPU devices. In this work, we evaluate two state-of-the-art models
on three different embedded GPU devices, with and without optimization methods, presenting
performance results that illustrate the actual capabilities of embedded GPU devices for stereo depth
estimation. More importantly, based on our evaluation, we propose the use of a U-Net like architecture
for postprocessing the cost-volume, instead of a typical sequence of 3D convolutions, drastically
augmenting the runtime speed of current models. In our experiments, we achieve real-time inference
speed, in the range of 5–32 ms, for 1216 368 input stereo images on the Jetson TX2, Jetson Xavier,
and Jetson Nano embedded devices.
|
|
|
|
Mónica Villavicencio, & Alain Abran. (2011). Facts and Perceptions Regarding Software Measurement in Education and in Practice: Preliminary Results. Journal of Software Engineering and Application, , pp. 227–234.
Abstract: How is software measurement addressed in undergraduate and graduate programs in universities? Do organizations consider that the graduating students they hire have an adequate knowledge of software measurement? To answer these and related questions, a survey was administered to participants who attended the IWSM-MENSURA 2010 conference in Stuttgart, Germany. Forty-seven of the 69 conference participants (including software development practitioners, software measurement consultants, university professors, and graduate students) took part in the survey. The results indicate that software measurement topics are: A) covered mostly at the graduate level and not at the undergraduate level, and B) not mandatory. Graduate students and professors consider that, of the measurement topics covered in university curricula, specific topics, such as measures for the requirements phase, and measurement techniques and tools, receive more attention in the academic context. A common observation of the practitioners who participated in the survey was that students hired as new employees bring limited software measurement-related knowledge to their organizations. Discussion of the findings and directions for future research are presented.
|
|
|
|
M. Diaz, Dennys Paillacho, C. Angulo, O. Torres, J. Gonzálalez, & J. Albo Canals. (2014). A Week-long Study on Robot-Visitors Spatial Relationships during Guidance in a Sciences Museum. In ACM/IEEE International Conference on Human-Robot Interaction (pp. 152–153).
Abstract: In order to observe spatial relationships in social human- robot interactions, a field trial was carried out within the CosmoCaixa Science Museum in Barcelona. The follow me episodes studied showed that the space configurations formed by guide and visitors walking together did not always fit the robot social affordances and navigation requirements to perform the guidance successfully, thus additional commu- nication prompts are considered to regulate effectively the walking together and follow me behaviors.
|
|
|
|
Miguel Oliveira, Vítor Santos, Angel D. Sappa, & Paulo Dias. (2015). Scene representations for autonomous driving: an approach based on polygonal primitives. In Iberian Robotics Conference (ROBOT 2015), Lisbon, Portugal, 2015 (Vol. 417, pp. 503–515). Springer International Publishing Switzerland 2016.
Abstract: In this paper, we present a novel methodology to compute a 3D scene representation. The algorithm uses macro scale polygonal primitives to model the scene. This means that the representation of the scene is given as a list of large scale polygons that describe the geometric structure of the environment. Results show that the approach is capable of producing accurate descriptions of the scene. In addition, the algorithm is very efficient when compared to other techniques.
|
|
|
|
Miguel Oliveira, Vítor Santos, Angel D. Sappa, Paulo Dias, & A. Paulo Moreira. (2016). Incremental Texture Mapping for Autonomous Driving. Robotics and Autonomous Systems Journal, Vol. 84, pp. 113–128.
Abstract: Autonomous vehicles have a large number of on-board sensors, not only for providing coverage all around the vehicle, but also to ensure multi-modality in the observation of the scene. Because of this, it is not trivial to come up with a single, unique representation that feeds from the data given by all these sensors. We propose an algorithm which is capable of mapping texture collected from vision based sensors onto a geometric description of the scenario constructed from data provided by 3D sensors. The algorithm uses a constrained Delaunay triangulation to produce a mesh which is updated using a specially devised sequence of operations. These enforce a partial configuration of the mesh that avoids bad quality textures and ensures that there are no gaps in the texture. Results show that this algorithm is capable of producing fine quality textures.
|
|
|
|
Wilton Agila, Ricardo Cajo, & Douglas Plaza. (2015). Experts Agents in PEM Fuel Cell Control. In 4ta International Conference on Renewable Energy Research and Applications (pp. 896–900). Palermo, Italy: IEEE.
Abstract: In the control of the PEM (Proton Exchange Membrane) fuel cell, the existence of both deliberative and reactive processes that facilitate the tasks of control resulting from a wide range of operating scenarios and range of conditions it is required. The latter is essential to adjust its parameters to the multiplicity of circumstances that may occur in the operation of the PEM stack. In this context, the design and development of an expert-agents based architecture for autonomous control of the PEM stack in top working conditions is presented. The architecture integrates perception and control algorithms using sensory and context information. It is structured in a hierarchy of levels with different time window and level of abstraction. The monitoring model and autonomic control of PEM stack has been validated with different types of PEM stacks and operating conditions demonstrating high reliability in achieving the objective of the proposed energy efficiency. Dynamic control of the wetting of the membrane is a clear example.
|
|
