Hiram Calvo

Dr. Hiram Calvo

Instituto Politécnico Nacional
orcid

Research Focus & Metrics

Academic Career Length

24Years (2003-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 November 2016 in Soft Computing
Verified
Journal Article
Closed access
PDF file
ÁHÁngel Hernández-Castañeda
Ángel Hernández-Castañeda
Hiram CalvoHiram Calvo
Hiram Calvo
AGAlexander Gelbukh
Alexander Gelbukh
JFJorge J. García Flores
Jorge J. García Flores

1 February 2019 in Applied Sciences
Verified
Journal Article
Open access
PDF file
CGCristyan R. Gil
Cristyan R. Gil
Hiram CalvoHiram Calvo
Hiram Calvo
Juan Humberto Sossa AzuelaJuan Humberto Sossa Azuela
Juan Humberto Sossa Azuela
Programming robots for performing different activities requires calculating sequences of values of their joints by taking into account many factors, such as stability and efficiency, at the same time. Particularly for walking, state of the art techniques to approximate these sequences are based on reinforcement learning (RL). In this work we propose a multi-level system, where the same RL method is used first to learn the configuration of robot joints (poses) that allow it to stand with stability, and then in the second level, we find the sequence of poses that let it reach the furthest distance in the shortest time, while avoiding falling down and keeping a straight path. In order to evaluate this, we focus on measuring the time it takes for the robot to travel a certain distance. To our knowledge, this is the first work focusing both on speed and precision of the trajectory at the same time. We implement our model in a simulated environment using q-learning. We compare with the built-in walking modes of an NAO robot by improving normal-speed and enhancing robustness in fast-speed. The proposed model can be extended to other tasks and is independent of a particular robot model.

29 October 2020 in IEEE Access
Verified
Journal Article
Open access
Marco A. Moreno-ArmendarizMarco A. Moreno-Armendariz
Marco A. Moreno-Armendariz
CDCarlos A. Duchanoy
Carlos A. Duchanoy
Hiram CalvoHiram Calvo
Hiram Calvo
MMMiguelangel Moreno-Sotelo
Miguelangel Moreno-Sotelo
This work presents a model based on Deep Neural Networks for the prediction of apparent personality. It can quantify personality traits with the Five-Factor model (Big Five) from a Portrait image. In order to evaluate the effectiveness of this approach, a new corpus of 30,935 portraits with their associated personality trait was extracted from an existing resource of videos (First Impressions, ChaLearn) tagged with redundant pairwise comparisons to ensure consistency. We propose several models using Convolutional Neural Networks to automatically extract features from a portrait that are indicators of personality traits; then the models classify these characteristics into a binary class for each Big Five factor: openness to experience (O), conscientiousness (C), extraversion (E), agreeableness (A), and neuroticism (N). In addition, we experiment with feature encoding and transfer learning to enrich the representation of images with additional untagged portraits (~45,000 and ~200M), reaching a percentage of accuracy within the state of the art (albeit not directly comparable), obtaining 65.86% as a classifier averaging the 5 factors (O=61.48%, C=69.56%, E=73.23%, A=60.68%, N=64.35%). Compared to human judgment (mean accuracy of 56.66%), the model obtained higher average performance and higher accuracy in 4 of the 5 factors of the Big Five model. In addition, in comparison with the state of the art this model shows several advantages: (1) it requires only a single portrait to make the prediction, being this a non-invasive and easily accessible resource (e.g. selfies) (2) the extraction of features from the portrait is done automatically, (3) a single model performs the extraction of characteristics and classification.

30 November 2019 in Sensors
Verified
Journal Article
Open access
PDF file
Marco A. Moreno-ArmendarizMarco A. Moreno-Armendariz
Marco A. Moreno-Armendariz
Hiram CalvoHiram Calvo
Hiram Calvo
CDCarlos A. Duchanoy
Carlos A. Duchanoy
Anayantzin Lopez JuarezAnayantzin Lopez Juarez
Anayantzin Lopez Juarez
Israel Agustin MonroyIsrael Agustin Monroy
Israel Agustin Monroy
MSMiguel Santiago Suarez-Castanon
Miguel Santiago Suarez-Castanon
Nowadays, more than half of the world’s population lives in urban areas, and this number continues increasing. Consequently, there are more and more scientific publications that analyze health problems of people associated with living in these highly urbanized locations. In particular, some of the recent work has focused on relating people’s health to the quality and quantity of urban green areas. In this context, and considering the huge amount of land area in large cities that must be supervised, our work seeks to develop a deep learning-based solution capable of determining the level of health of the land and to assess whether it is contaminated. The main purpose is to provide health institutions with software capable of creating updated maps that indicate where these phenomena are presented, as this information could be very useful to guide public health goals in large cities. Our software is released as open source code, and the data used for the experiments presented in this paper are also freely available.

6 May 2019 in IEEE Access
Verified
Journal Article
Open access
Hiram CalvoHiram Calvo
Hiram Calvo
ARArturo P. Rocha-Ramirez
Arturo P. Rocha-Ramirez
Marco A. Moreno-ArmendarizMarco A. Moreno-Armendariz
Marco A. Moreno-Armendariz
CDCarlos A. Duchanoy
Carlos A. Duchanoy
Traditionally, approaches based on neural networks to solve the problem of disambiguation of the meaning of words (WSD) use a set of classifiers at the end, which results in a specialization in a single set of words—those for which they were trained. This makes impossible to apply the learned models to words not previously seen in the training corpus. This paper seeks to address a generalization of the problem of WSD in order to solve it through deep neural networks without limiting the method to a fixed set of words, with a performance close to the state of the art, and an acceptable computational cost. We explore different architectures based on multilayer perceptrons, recurrent cells (Long Short-Term Memory–LSTM and Gated Recurrent Units–GRU) and a classifier model. Different sources and dimensions of embeddings were tested as well. The main evaluation was performed on Senseval 3 English Lexical Sample. To evaluate the application to an unseen set of words, learned models are evaluated in the completely unseen words of a different corpus (Senseval 2 English Lexical Sample), overcoming the random baseline.

21 February 2022 in Sensors
Verified
Journal Article
Open access
PDF file
JVJosé Valdez
José Valdez
Hiram CalvoHiram Calvo
Hiram Calvo
EFEdgardo Manuel Felipe-Riverón
Edgardo Manuel Felipe-Riverón
Marco A. Moreno-ArmendarizMarco A. Moreno-Armendariz
Marco A. Moreno-Armendariz
Single image depth estimation works fail to separate foreground elements because they can easily be confounded with the background. To alleviate this problem, we propose the use of a semantic segmentation procedure that adds information to a depth estimator, in this case, a 3D Convolutional Neural Network (CNN)—segmentation is coded as one-hot planes representing categories of objects. We explore 2D and 3D models. Particularly, we propose a hybrid 2D–3D CNN architecture capable of obtaining semantic segmentation and depth estimation at the same time. We tested our procedure on the SYNTHIA-AL dataset and obtained σ3=0.95, which is an improvement of 0.14 points (compared with the state of the art of σ3=0.81) by using manual segmentation, and σ3=0.89 using automatic semantic segmentation, proving that depth estimation is improved when the shape and position of objects in a scene are known.