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 - 10 of 23
No Thumbnail Available
Publication

Towards Artificial Hydrocarbon Networks: The Chemical Nature of Data-Driven Approaches

2019 , Ponce, Hiram

Inspiration in nature has been widely explored, from macro to micro-scale. Natural phenomena mainly considers adaptability, optimization, robustness, organization, among other properties, to deal with complexity. When looking into chemical phenomena, stability and organization are two properties that emerge. Recently, artificial hydrocarbon networks (AHN), a supervised learning method inspired in the inner structures and mechanisms of chemical compounds, have been proposed as a data-driven approach in artificial intelligence. AHN have been successfully applied in data-driven approaches, such as: regression and classification models, control systems, signal processing, and robotics. To do so, molecules-the basic units of information in AHN-play an important role in the stability, organization and interpretability of this method. Until now, building the architecture of AHN has been treated as a whole entity; but distributed computing mechanisms, as well as the exploitation of hierarchical organization of molecules, can enhance the performance of AHN. Thus, this paper aims to discuss challenges and trends of artificial hydrocarbon networks as a data-driven method, with emphasis on packaging, distributed computing and hierarchical properties. Throughout this work, it presents a description of the main insights of AHN and the proposed distributed and hierarchical mechanisms in molecules. Potential applications and future trends on AHN are also discussed. © 2019 IEEE.

View
No Thumbnail Available
Publication

Credit Risk Models in the Mexican Context Using Machine Learning

2022 , López, Ana Lilia , López, Estefanía , Ponce, Hiram

The Default Rate is related to the period of the economic cycle in which they are observed, during expansion periods of the economy the default rate tends to be lower. But in contraction periods, the default rate tends to increase and this could be a risk for the stability of a country’s economy. Therefore, it is important to monitor the perspective of the economy in case it is expected to decrease or have abrupt movements. This work aims to identify the economic variables that determine the default rate of the Mexican Financial System and to find a machine learning model that forecasts the default rate. For this, we aggregate a dataset based on three official Mexican sources that compile data from 2013 to 2022, including the COVID-19 pandemic time frame. Then, we propose the analysis using two machine learning models. After the analysis, the results confirm that the artificial neural networks model shows better predictive power for the default rate values. We also implement an easy to use web application to estimate the default rate based on three simple variables. We anticipate this work might help on estimating the default rate and might impact on the strategic policies in the Mexican economy. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

View
No Thumbnail Available
Publication

Open Source Implementation for Fall Classification and Fall Detection Systems

2020 , Ponce, Hiram , Martinez-Villaseñor, Lourdes , Nuñez Martínez, José Pablo , Moya-Albor, Ernesto , Brieva, Jorge

Distributed social coding has created many benefits for software developers. Open source code and publicly available datasets can leverage the development of fall detection and fall classification systems. These systems can help to improve the time in which a person receives help after a fall occurs. Many of the simulated falls datasets consider different types of fall however, very few fall detection systems actually identify and discriminate between each category of falls. In this chapter, we present an open source implementation for fall classification and detection systems using the public UP-Fall Detection dataset. This implementation comprises a set of open codes stored in a GitHub repository for full access and provides a tutorial for using the codes and a concise example for their application. © 2020, Springer Nature Switzerland AG.

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

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

The development of an artificial organic networks toolkit for LabVIEW

2015 , Ponce, Hiram , Ponce, Pedro , Molina, Arturo

Two of the most challenging problems that scientists and researchers face when they want to experiment with new cutting-edge algorithms are the time-consuming for encoding and the difficulties for linking them with other technologies and devices. In that sense, this article introduces the artificial organic networks toolkit for LabVIEW™ (AON-TL) from the implementation point of view. The toolkit is based on the framework provided by the artificial organic networks technique, giving it the potential to add new algorithms in the future based on this technique. Moreover, the toolkit inherits both the rapid prototyping and the easy-to-use characteristics of the LabVIEW™ software (e.g., graphical programming, transparent usage of other softwares and devices, built-in programming event-driven for user interfaces), to make it simple for the end-user. In fact, the article describes the global architecture of the toolkit, with particular emphasis in the software implementation of the so-called artificial hydrocarbon networks algorithm. Lastly, the article includes two case studies for engineering purposes (i.e., sensor characterization) and chemistry applications (i.e., blood–brain barrier partitioning data model) to show the usage of the toolkit and the potential scalability of the artificial organic networks technique. © 2015 Wiley Periodicals, Inc.

View
No Thumbnail Available
Publication

Click-event sound detection in automotive industry using machine/deep learning

2021 , Espinosa Loera, Ricardo Abel , Ponce, Hiram , Gutiérrez, Sebastián

In the automotive industry, despite the robotic systems on the production lines, factories continue employing workers in several custom tasks getting for semi-automatic assembly operations. Specifically, the assembly of electrical harnesses of engines comprises a set of connections between electrical components. Despite the task is easy to perform, employees tend not to notice that a few components are not being connected properly due to physical fatigue provoked by repetitive tasks. This yields a low quality of the assembly production line and possible hazards. In this work, we propose a sound detection system based on machine/deep learning (ML/DL) approaches to identify click sounds produced when electrical harnesses are connected. The purpose of this system is to count the number of connections properly made and to feedback to the employees. We collect and release a public dataset of 25,000 click sounds of 25 ms length at 22 kHz during three months of assembly operations in an automotive production line located in Mexico. Then, we design an ML/DL-based methodology for click sound detection of assembled harnesses under real conditions of a noisy environment (noise level ranging from −16.67 dB to −12.87 dB) including other machinery sounds. Our best ML/DL model (i.e., a combination between five acoustic features and an optimized convolutional neural network) is able to detect click sounds in a real assembly production line with an accuracy of 94.55±0.83 %. To the best of our knowledge, this is the first time a click sounds detection system in assembling electrical harnesses of engines for giving feedback to the workers is proposed and implemented in a real-world automotive production line. We consider this work valuable for the automotive industry on how to apply ML/DL approaches for improving the quality of semi-automatic assembly operations. © 2021 Elsevier B.V.

View
No Thumbnail Available
Publication

Non-Contact Breathing Rate Estimation Using Machine Learning with an Optimized Architecture

2023 , Brieva, Jorge , Ponce, Hiram , Moya-Albor, Ernesto

The breathing rate monitoring is an important measure in medical applications and daily physical activities. The contact sensors have shown their effectiveness for breathing monitoring and have been mostly used as a standard reference, but with some disadvantages for example in burns patients with vulnerable skins. Contactless monitoring systems are then gaining attention for respiratory frequency detection. We propose a new non-contact technique to estimate the breathing rate based on the motion video magnification method by means of the Hermite transform and an Artificial Hydrocarbon Network (AHN). The chest movements are tracked by the system without the use of an ROI in the image video. The machine learning system classifies the frames as inhalation or exhalation using a Bayesian-optimized AHN. The method was compared using an optimized Convolutional Neural Network (CNN). This proposal has been tested on a Data-Set containing ten healthy subjects in four positions. The percentage error and the Bland–Altman analysis is used to compare the performance of the strategies estimating the breathing rate. Besides, the Bland–Altman analysis is used to search for the agreement of the estimation to the reference.The percentage error for the AHN method is (Formula presented.) with and agreement with respect of the reference of ≈99%. © 2023 by the authors.

View
No Thumbnail Available
Publication

Eye Control and Motion with Deep Reinforcement Learning: In Virtual and Physical Environments

2024-01-01 , Arizmendi, Sergio , Paz, Asdrubal , González, Javier , Ponce, Hiram

Attention mechanism in computer vision refers to scan, detect, and track a target object. This paper aims to develop and virtually train a machine learning model for object attention mechanism, combining object detection and mechanical automation. For this, we use Unity 3D Engine to model a simple scene in which two virtual cameras align together to realize a monocular attention in specific objects. Deep reinforcement learning, via ML-agent’s library, was used to train a model that aligns the virtual cameras. Moreover, the model was transferred to a physical camera to replicate the performance of attention mechanism.

View
No Thumbnail Available
Publication

Ventilator Pressure Prediction Using a Regularized Regression Model

2022 , Arellano, Amaury , Bustamante, Erick , Garza, Carlos , Ponce, Hiram

The mechanical ventilation is one of the most frequent methods used in Intensive Care Units (ICUs) to improve the breathing of patients. During the early days of the COVID-19 pandemic, the use of mechanical ventilators has been crucial. In this work, we propose to build a Lasso regression model based on lung simulators for predicting the airway pressure in the respiratory circuit of ventilators while breathing. We model the whole breathing process in two separate states. After that, we analyze the feature importance in the regression model to better understand the ventilator pressure prediction. We anticipate this model would help improving the patient’s health and overcoming the cost barrier of new methods for mechanical ventilators. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

View