Ponce, Hiram
Thumbnail Image
Preferred name
Ponce, Hiram
Official Name
Ponce Espinosa, Hiram Eredín
Alternative Name
hponce
Main Affiliation
ORCID
Scopus Author ID
54911890000
Researcher ID
K-7593-2019

Research Output
Now showing 1 - 6 of 6
No Thumbnail Available
Publication

A Novel Artificial Hydrocarbon Networks Based Value Function Approximation in Hierarchical Reinforcement Learning

2017 , Ponce, Hiram

Reinforcement learning aims to solve the problem of learning optimal or near-optimal decision-making policies for a given domain problem. However, it is known that increasing the dimensionality of the input space (i.e. environment) will increase the complexity for the learning algorithms, falling into the curse of dimensionality. Value function approximation and hierarchical reinforcement learning have been two different approaches proposed to alleviate reinforcement learning from this illness. In that sense, this paper proposes a new value function approximation using artificial hydrocarbon networks –a supervised learning method inspired on chemical carbon networks– with regularization at each subtask in a hierarchical reinforcement learning framework. Comparative results using a greedy sparse value function approximation over the MAXQ hierarchical method was computed, proving that artificial hydrocarbon networks improves accuracy and efficiency on the value function approximation. © Springer International Publishing AG 2017.

View
No Thumbnail Available
Publication

A Comparative Analysis of Evolutionary Learning in Artificial Hydrocarbon Networks

2020 , Ponce, Hiram , Souza, Paulo

Artificial hydrocarbon networks (AHN) is a supervised learning model that is loosely inspired on the interactions of molecules in organic compounds. This method is able to model data in a hierarchical and robust way. However, the original training algorithm is very time-consuming. Recently, novel training algorithms have been applied, including evolutionary learning. Particularly, this training algorithm employed particle swarm optimization (PSO), as part of the procedure. In this paper, we present a benchmark of other meta-heuristic optimization algorithms implemented on the training method for AHN. In this study, PSO, harmony search algorithm, cuckoo search, grey wolf optimization and whale optimization algorithm, were tested. The experimental results were done using public data sets on regression and binary classification problems. From the results, we concluded that the best algorithm was cuckoo search optimization for regression problems, while there is no evidence that one of the algorithms performed better for binary classification problems. © 2020, Springer Nature Switzerland AG.

View
No Thumbnail Available
Publication

Design and Equilibrium Control of a Force-Balanced One-Leg Mechanism

2018 , Ponce, Hiram , Acevedo, Mario

The problem of equilibrium is critical for planning, control, and analysis of legged robot. Control algorithms for legged robots use the equilibrium criteria to avoid falls. The computational efficiency of the equilibrium tests is critical. To comply with this it is necessary to calculate the horizontal momentum rotation for every moment. For arbitrary contact geometries, more complex and computationally-expensive techniques are required. On the other hand designing equilibrium controllers for legged robots is a challenging problem. Nonlinear or more complex control systems have to be designed, complicating the computational cost and demanding robust actuators. In this paper, we propose a force-balanced mechanism as a building element for the synthesis of legged robots that can be easily balance controlled. The mechanism has two degrees of freedom, in opposition to the more traditional one degree of freedom linkages generally used as legs in robotics. This facilitates the efficient use of the “projection of the center of mass” criterion with the aid of a counter rotating inertia, reducing the number of calculations required by the control algorithm. Different experiments to balance the mechanism and to track unstable set-point positions have been done. Proportional error controllers with different strategies as well as learning approaches, based on an artificial intelligence method namely artificial hydrocarbon networks, have been used. Dynamic simulations results are reported. Videos of experiments will be available at: https://sites.google.com/up.edu.mx/smart-robotic-legs/. © 2018, Springer Nature Switzerland AG.

View
No Thumbnail Available
Publication

Versatility of Artificial Hydrocarbon Networks for Supervised Learning

2018 , Ponce, Hiram , Martinez-Villaseñor, Lourdes

Surveys on supervised machine show that each technique has strengths and weaknesses that make each of them more suitable for a particular domain or learning task. No technique is capable to tackle every supervised learning task, and it is difficult to comply with all possible desirable features of each particular domain. However, it is important that a new technique comply with the most requirements and desirable features of as many domains and learning tasks as possible. In this paper, we presented artificial hydrocarbon networks (AHN) as versatile and efficient supervised learning method. We determined the ability of AHN to solve different problem domains, with different data-sources and to learn different tasks. The analysis considered six applications in which AHN was successfully applied. © Springer Nature Switzerland AG 2018.

View
No Thumbnail Available
Publication

Stochastic parallel extreme artificial hydrocarbon networks: An implementation for fast and robust supervised machine learning in high-dimensional data

2020 , Ponce, Hiram , De Campos Souza, Paulo V. , Junio Guimarães, Augusto , González Mora, José Guillermo

Artificial hydrocarbon networks (AHN) – a supervised learning method inspired on organic chemical structures and mechanisms – have shown improvements in predictive power and interpretability in comparison with other well-known machine learning models. However, AHN are very time-consuming that are not able to deal with large data until now. In this paper, we introduce the stochastic parallel extreme artificial hydrocarbon networks (SPE-AHN), an algorithm for fast and robust training of supervised AHN models in high-dimensional data. This training method comprises a population-based meta-heuristic optimization with defined individual encoding and objective function related to the AHN-model, an implementation in parallel-computing, and a stochastic learning approach for consuming large data. We conducted three experiments with synthetic and real data sets to validate the training execution time and performance of the proposed algorithm. Experimental results demonstrated that the proposed SPE-AHN outperforms the original-AHN method, increasing the speed of training more than 10,000x times in the worst case scenario. Additionally, we present two case studies in real data sets for solar-panel deployment prediction (regression problem), and human falls and daily activities classification in healthcare monitoring systems (classification problem). These case studies showed that SPE-AHN improves the state-of-the-art machine learning models in both engineering problems. We anticipate our new training algorithm to be useful in many applications of AHN like robotics, finance, medical engineering, aerospace, and others, in which large amounts of data (e.g. big data) is essential. © 2019 Elsevier Ltd.

View
No Thumbnail Available
Publication

Non-contact breathing rate monitoring system using a magnification technique and convolutional networks

2020 , Brieva, Jorge , Ponce, Hiram , Moya-Albor, Ernesto

In this paper, we present a new non-contact strategy to estimate the breathing rate based on the Eulerian motion video magnification technique and a system based on a Convolutional Neural Network (CNN). After the magnification procedure, a CNN is trained to detect the inhalation and exhalation frames in the video. From this classification, the respiratory rate is estimated. The magnification procedure was carried out using the Hermite decomposition. Two strategies are used as input to the CNN. A CNN-ROI proposal where a region of interest is selected manually on the image frame and in the second case, a CNN-Whole-Image proposal where the entire image frame is selected. Finally, the RR is estimated from the classified frames. The CNN-ROI proposal is tested on five subjects in lying face down position and it is compared to a procedure using different image processing steps to tag the frames as inhalation or exhalation. The mean average error in percentage obtained for this proposal is 2.326±1.144%. The CNN-whole-image proposal is tested on eight subjects in lying face down position. The mean average error in percentage obtained for this proposal is 2.115 ± 1.135%. © COPYRIGHT 2020 SPIE. Downloading of the abstract is permitted for personal use ONLY.

View