DSpace Angular :: Browsing by Author "Nunez, Felipe"

Browsing by Author "Nunez, Felipe"

Now showing 1 - 20 of 22

A Cyber-Physical System for Real-Time Physiological Data Monitoring and Analysis
(2024) Huanca, Fernando; Torres, Mario; Rodriguez-Fernandez, Maria; Nunez, Felipe
In the pursuit of a personalized healthcare experience, data-driven decision-making has become increasingly relevant. In this context, there is a growing need for technological systems specifically tailored to efficiently manage vast amounts of healthcare data. To address this need, in this work, we contribute by presenting a cyber-physical solution for monitoring and analyzing physiological data obtained from wearable devices. The proposed system is designed following a service-oriented architecture, which promotes modularity and enables efficient data access and analysis. The system is capable of ingesting and consolidating wearable data produced by a variety of commercial devices, scaling to accommodate a large number of data producers, and accepting queries from a multitude of consumers through various mechanisms. Performance tests conducted in various scenarios using real data demonstrate the system's effectiveness in maintaining real-time data access.
A Cyberphysical System for Data-Driven Real-Time Traffic Prediction on the Las Vegas I-15 Freeway
(2023) Guzman, Jose A.; Morris, Brendan T.; Nunez, Felipe
Mobility and transportation services in modern large-scale cities face traffic congestion as one of the main sources of discomfort and economic losses. In this context, taking preventive measures based on traffic predictions looks like an appealing alternative to mitigate congestion. The increasing availability of detectors in the transportation infrastructure has allowed tackling the traffic prediction problem by using a purely data-driven approach, where deep learning models have excelled. Unfortunately, the implementation of these techniques in real time is still under development. This work presents the implementation of a real-time traffic prediction application in the Las Vegas, NV, USA, urban area, built as a cyberphysical system with real-time data streaming from field sensors to a cloud-like environment where deep learning-based traffic predictors are hosted. Implementation results show the feasibility of doing traffic prediction in real time with the current technology and the usefulness of periodic retraining to maintain prediction accuracy.
A meta-learning approach to personalized blood glucose prediction in type 1 diabetes
(2023) Langarica, Saul; Rodriguez-Fernandez, Maria; Nunez, Felipe; Doyle III, Francis J.
Accurate blood glucose prediction is a critical element in modern artificial pancreas systems. Recently, many deep learning-based models have been proposed for glucose prediction, showing encouraging results in population modeling. However, due to the large amount of data required for training deep learning -based models, few studies have successfully addressed personalized modeling, which is critical to ensure safe policies in a closed-loop scheme given the high inter-patient variability. To address this concern, we propose a meta-learning-based technique for accurate personalized modeling that requires minimal data volume to personalize from its population version, needs few training iterations, and has a low risk of over-fitting. Results using the UVA/Padova simulator show that the proposed technique generalizes better and outperforms other approaches in standard and task-specific metrics, particularly for longer prediction horizons and higher degrees of distributional shifts.
A Probabilistic Approach to Blood Glucose Prediction in Type 1 Diabetes Under Meal Uncertainties
(2023) Langarica, Saul; Rodriguez-Fernandez, Maria; Doyle III, Francis J.; Nunez, Felipe
Currently, most reliable and commercialized artificial pancreas systems for type 1 diabetes are hybrid closed-loop systems, which require the user to announce every meal and its size. However, estimating the amount of carbohydrates in a meal and announcing each and every meal is an error-prone process that introduces important uncertainties to the problem, which when not considered, lead to sub-optimal outcomes of the controller. To address this problem, we propose a novel deep-learning-based model for probabilistic glucose prediction, called the Input and State Recurrent Kalman Network (ISRKN), which consists in the incorporation of an input and state Kalman filter in the latent space of a deep neural network so that the posterior distributions can be computed in closed form and the uncertainty can be propagated using the Kalman equations. In addition, the proposed architecture allows explicit estimation of the meal uncertainty distribution, whose parameters are encoded in the filter parameters. Results using the UVA/Padova simulator and data from a clinical trial show that the proposed model outperforms other probabilistic models using several probabilistic metrics across different degrees of distributional shifts.
A Reinforcement Learning-Based Distributed Control Scheme for Cooperative Intersection Traffic Control
(2023) Guzman, Jose A.; Pizarro, German; Nunez, Felipe
Traffic congestion is a major source of discomfort and economic losses in urban environments. Recently, the proliferation of traffic detectors and the advances in algorithms to efficiently process data have enabled taking a data-driven approach to mitigate congestion. In this context, this work proposes a reinforcement learning (RL) based distributed control scheme that exploits cooperation among intersections. Specifically, a RL controller is synthesized, which manipulates traffic signals using information from neighboring intersections in the form of an embedding obtained from a traffic prediction application. Simulation results using SUMO show that the proposed scheme outperforms classical techniques in terms of waiting time and other key performance indices.
Age of information in IoT-based networked control systems: A MAC perspective
(2023) Mena, Juan P.; Nunez, Felipe
Timeliness of information is critical for accurate decision making in data-driven systems. As large-scale systems based on Internet of Things (IoT) technologies start populating shop floors, their performance in terms of timeliness must be assessed. This work analyzes age of information (AoI) in IoT-based control systems, where independent control loops share a wireless network. Analytical expressions for AoI under two typical MAC schemes used in IoT systems: CSMA/CA and TDMA are given and validated by simulations. The significance of the results is illustrated in the context of a design example.(c) 2022 Published by Elsevier Ltd.
An event-driven simulator for multi-line metro systems and its application to Santiago de Chile metropolitan rail network
(ELSEVIER, 2011) Grube, Pablo; Nunez, Felipe; Cipriano, Aldo
Metros are the principal means of public transportation in many of the world s cities and continue to grow in the face of rising demand Expanding metro infrastructure is costly however and at a certain point becomes unsustainable When this occurs the only feasible solution is to Improve the train s management system by using either offline approaches such as pre-programming schedules which use historic information or online approaches which employ system status information obtained during operation A new planning or control system be it on or off line requires prior testing that usually involves conducting simulations This paper presents the design and implementation of an event-driven dynamic simulator for multi-line metro systems and its practical application for studying different operating strategies The simulator is based on object-oriented programming and is capable of interacting with Matlab programs written by the user to design and evaluate real-time control strategies This article describes the model upon which the simulator is based presents the user interface and demonstrates how to use the simulator for operating strategies evaluation in the Santiago de Chile multi-line metropolitan rail network (C) 2010 Elsevier BV All rights reserved
Automatic Synthesis of Containerized Industrial Cyber-Physical Systems: A Case Study
(2023) Biskupovic, Angel; Torres, Mario; Nunez, Felipe
Industrial cyber-physical systems (ICPSs) are widely regarded as the next generation industrial control systems and as one of the core technologies of the ongoing fourth industrial revolution. Despite its advantages, ICPSs are heavily dependent on the underlying physical process and their synthesis is a customized effort, demanding in terms of resources, which if not conducted carefully may impact the performance of the system. This work proposes a methodology to tackle ICPS synthesis in a systematic way, by using a set of industrial agents that take as input and standardized process description file and automatically deploy a modular ICPS from predesigned functional containers. Concrete examples on a tanks system and an industrial paste thickener are presented to illustrate the potential of the proposed methodology.
Building an Open-Source DNA Assembler Device
(2023) Orostica, Boris; Nunez, Isaac; Matute, Tamara; Nunez, Felipe; Federici, Fernan
This article introduces an open-source thermal cycling machine designed specifically for Golden Gate DNA assembly. The prototype device can achieve efficiency similar to a commercial PCR thermocycler.
Contrastive blind denoising autoencoder for real time denoising of industrial IoT sensor data
(2023) Langarica, Saul; Nunez, Felipe
In an industrial IoT setting, ensuring the quality of sensor data is a must when data-driven algorithms operate on the upper layers of the control system. Unfortunately, the common place in industrial facilities is to find sensor time series heavily corrupted by noise and outliers. This work proposes a purely data-driven self-supervised learning-based approach, based on a blind denoising autoencoder, for real time denoising of industrial sensor data. The term blind stresses that no prior knowledge about the noise is required for denoising, in contrast to typical denoising autoencoders. Blind denoising is achieved by using a noise contrastive estimation (NCE) regularization on the latent space of the autoencoder, which not only helps to denoise but also induces a meaningful and smooth latent space that can be exploited in other downstream tasks. Experimental evaluation in both a simulated system and a real industrial process shows that the proposed technique outperforms classical denoising methods.
Deep Learning-Based Glucose Prediction Models: A Guide for Practitioners and a Curated Dataset for Improved Diabetes Management
(2024) Langarica, Saul; De La Vega, Diego; Cariman, Nawel; Miranda, Martin; Andrade, David C.; Nunez, Felipe; Rodriguez-Fernandez, Maria
Accurate short- and mid-term blood glucose predictions are crucial for patients with diabetes struggling to maintain healthy glucose levels, as well as for individuals at risk of developing the disease. Consequently, numerous efforts from the scientific community have focused on developing predictive models for glucose levels. This study harnesses physiological data collected from wearable sensors to construct a series of data-driven models based on deep learning approaches. We systematically compare these models to offer insights for practitioners and researchers venturing into glucose prediction using deep learning techniques. Key questions addressed in this work encompass the comparison of various deep learning architectures for this task, determining the optimal set of input variables for accurate glucose prediction, comparing population-wide, fine-tuned, and personalized models, and assessing the impact of an individual's data volume on model performance. Additionally, as part of our outcomes, we introduce a meticulously curated dataset inclusive of data from both healthy individuals and those with diabetes, recorded in free-living conditions. This dataset aims to foster research in this domain and facilitate equitable comparisons among researchers.
Early-Warning System for Supervision of Urban Water Services: Case Study of Coquimbo, Chile
(2023) Aguirre, Paula; Bravo, Marilyn; Torres, Mario; Langarica, Saul; Oyarzun, Muriel; Nunez, Felipe
The combination of rapid urbanization, population growth, and the hydric stress due to climate change effects demand innovative, optimized approaches to the operation and supervision of urban water services. In Chile, the Superintendency of Sanitary Services has underscored the need for automatized data integration and analysis tools that foster an evidence-based, preventive approach to the supervision of urban water systems. This motivates the development of a pilot supervision and early-warning system, conceived as a cybernetic entity whose objective is to enable efficient access, analysis, and predictive modeling of the data provided by water service companies, so as to identify risks and inefficiencies in water services, monitor their evolution, and anticipate possible failures. This article discusses the development and implementation of a prototype system that provides tools for visualization, statistical and temporal analysis of georeferenced data on water pressures, network disruptions, and client complaints and deploys machine learning capabilities for predicting the quality of service indicators at different locations. The initial implementation in one region of Chile has been shown to expedite the exploitation of data on urban water services, reduce time lags in the detection of service disruptions, and generate evidence for the planning and execution of supervision activities. Based on this successful pilot, a roadmap for geographical and technological expansion is formulated, including other technological, organizational, and regulatory gaps that must be addressed to establish a data-driven framework for the supervision of urban water services.
Fault tolerant measurement system based on Takagi-Sugeno fuzzy models for a gas turbine in a combined cycle power plant
(ELSEVIER, 2011) Berrios, Rodrigo; Nunez, Felipe; Cipriano, Aldo
A fault tolerant measurement system for a gas turbine in a combined cycle power plant, based on dynamic models, principal component analysis (PCA) and Q test, is presented. The proposed scheme makes use of a model-based symptom generator, which delivers fault signals obtained by using direct identification of parity relations and structured residuals. Symptoms are then analyzed in a statistical module achieving fault diagnosis and reconstruction of the faulty signals. The scheme presents as main advantage the ability of detecting faults in both input and output sensors due to its particular structure. Tests carried out on the gas turbine of the San Isidro combined cycle power plant in the V Region, Chile, show that Takagi-Sugeno fuzzy models present the best fitting performance and an acceptable computational cost in comparison with autoregressive exogenous. state space, and neural models. Real time software based on this scheme has been developed and connected to Osisoft PI System'. The software is running at Endesa Monitoring and Diagnosis Center in Santiago. Chile. (C) 2011 Elsevier B.V. All rights reserved.
Hierarchical hybrid fuzzy strategy for column flotation control
(PERGAMON-ELSEVIER SCIENCE LTD, 2010) Nunez, Felipe; Tapia, Luis; Cipriano, Aldo
Column flotation is widely used in the concentration of low grade ores. Often column flotation concentrate is the final product of a very complex circuit, and therefore control of the metallurgical performance has direct impact in the plant performance. Several control schemes has been implemented for the stabilization of column flotation process, including decentralized control. model predictive control and fuzzy approaches, which attempt to control froth depth, water bias and air holdup. At the same time many efforts have been oriented to improve process instrumentation, with the aim of providing better measurements for control purposes. Instrumentation improvements have made feasible the design of strategies focused on recovery and concentrate grade control. In this work we present the design and implementation of a new advanced controller for column flotation process. The controller was implemented in a 10 columns cleaning stage following a hierarchical scheme with two control levels: an improving level with the aim of metallurgical performance control of the whole process, and a stabilizing level in charge of the distribution of control actions in each column. The controller design was made based on a hybrid scheme with three different operation scenarios, defined by a recovery-concentrate grade domain partition. Results show that the controller is able to keep the process in the normal operation scenario 80% of the analyzed time; on the other hand, when the process was operated only with local control it achieved the normal operation scenario 43% of the analyzed time. Results also show that the controller is capable of increasing concentrate grade and recovery mean values, despite variations on feed grade; while reducing recovery and concentrate grade standard deviations. (C) 2009 Elsevier Ltd. All rights reserved.
High-Gain Adaptive Control With Switching Derivation Order and Its Application to a Class of Multiagent Systems
(2024) Gallegos, Javier; Aguila-Camacho, Norelys; Nunez, Felipe
This article presents the design and analysis of a switching high-gain adaptive control scheme for a class of nonlinear systems. Adaptation is included in the scheme to estimate the controller gains, using differential equations whose order can switch between 1 (integer order) and some real number (fractional order) in the interval (0,1) , depending on the error level. This switching strategy permits obtaining lower values for controller gains due to fractional orders, resulting in improved robustness, while simultaneously guaranteeing fast convergence of the state to the origin due to the integer order, leading to a better balance between system behavior and control energy efficiency. Applications to multiagent systems are presented to illustrate the potential of the proposed scheme.
length Design of an IoT-PLC: A containerized programmable logical controller for the industry 4.0
(2022) Mellado, Jacob; Nunez, Felipe
The Programmable-logical-controller (PLC) has been the key building block of industrial control systems throughout the whole automation revolution, where its role has been mainly to command low-level regulatory feedback control loops. Despite the great recent advances in automation technologies, driven by the paradigm of the Industry 4.0 and its hyper-connected ecosystem, the PLC has not seen yet a modernized version targeting the functionalities an Industry 4.0-oriented control system requires. In this work, a device named IoT-PLC is designed and prototyped, in an effort to generate a PLC tailored for the Industry 4.0 revolution. The proposed IoT-PLC operates as a containerized piece of equipment, with each functionality packaged within a separate container. The IoT-PLC has regulatory control capabilities, fog-computing functionalities as filtering and field data storage, and multiple wireless interfaces managed independently. Moreover, it uses a virtual device model that works as an abstraction method to represent real entities, so that IoT-PLC applications can interact transparently and with straightforward compatibility with upper cloud layers. Live migration functionalities add flexibility by allowing a loop reconfiguration without restarting the controller. Laboratory experiments illustrate the effectiveness and potential of the proposed device.
On the Relation Between Peak Age and Stability in Control Loops Over Non-Beacon Enabled CSMA/CA
(2021) Mena, Juan P.; Nunez, Felipe
The proliferation of the Internet of Things has enabled implementing control loops using low-capable devices over non-deterministic networks. This letter addresses the use of non-beacon enabled CSMA/CA and motivates the need of minimizing the probability of peak age surpassing a bound, given in terms of two indicators of control over networks: the maximum allowable transmit interval and the maximum allowable delay. A concrete analytical result for calculating the probability is given, which represents an improvement of 50% with respect to a known bound at the optimal rate in a 5-loops control system.
Predictive Control for Current Distortion Mitigation in Mining Power Grids
(2023) Gomez, Juan S. S.; Navas-Fonseca, Alex; Flores-Bahamonde, Freddy; Tarisciotti, Luca; Garcia, Cristian; Nunez, Felipe; Rodriguez, Jose; Cipriano, Aldo Z. Z.
Current distortion is a critical issue of power quality because the low frequency harmonics injected by adjustable speed drives increase heating losses in transmission lines and induce torque flickering in induction motors, which are widely used in mining facilities. Although classical active filtering techniques mitigate the oscillatory components of imaginary power, they may not be sufficient to clean the sensitive nodes of undesirable power components, some of which are related to real power. However, the usage of power electronic converters for distributed generation and energy storage, allows the integration of complementary power quality control objectives in electrical systems, by using the same facilities required for active power transferring. This paper proposes a predictive control-based scheme for mitigating the current distortion in the coupling node between utility grid and the mining facility power system. Instead of the classical approach of active filtering, this task is included as a secondary level objective control referred into the microgrid control hierarchy. Hardware-in-the-Loop simulation results showed that the proposed scheme is capable of bounding the current distortion, according to IEEE standard 1547, for both individual harmonics and the total rated current distortion, through inequality constraints of the optimization problem.
Random forest model predictive control for paste thickening
(2021) Diaz, Pablo; Salas, Juan C.; Cipriano, Aldo; Nunez, Felipe
As processes involved in mineral processing operations increase their complexity, automation and control become critical to ensure an economically viable and environmentally sustainable operation. In the context of modern mineral processing, paste thickening stands out as a relatively new method for producing high density slurries that has proven challenging for standard control algorithms. In this setting, the use of machine-learning-based models within a predictive control strategy arises as an appealing alternative. This work presents a Random Forest Model Predictive Control scheme for paste thickening based on a purely data-driven approach for modeling and evolutionary strategies for solving the associated optimization problem. Results show that the proposed strategy outperforms conventional predictive control both qualitatively and quantitatively.
Robust Adaptive Average Consensus Over a Time-Varying and Nonbalanced Environment
(2024) Gallegos, Javier A.; Schlotterbeck, Constanza; Nunez, Felipe
Average consensus is a fundamental problem in distributed control that still lacks a general solution when the agents face nonideal conditions and uncertain environments. This note contributes to the topic by addressing average consensus in networks of agents that: 1) interact over a time-varying and nonbalanced environment and 2) face parametric and nonparametric disturbances. It is shown that an adaptive strategy, which combines surplus variables and virtual agents, effectively solves the exact average consensus problem in this nonideal and uncertain setup. A numerical example is presented to illustrate the potential of the proposed approach.

Browsing by Author "Nunez, Felipe"

Results Per Page

Sort Options