Carlos Parra

Carlos Parra

Auto-generated profile, based on publicly available information

Carlos Parra

Pontificia Universidad Javeriana

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

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

Representative Publications

View All Publications
19 September 2024 in Drones
Verified
Journal Article
Open access
PDF file
RLRafael David Linero-Ramos
Rafael David Linero-Ramos
CPCarlos Parra-Rodríguez
Carlos Parra-Rodríguez
AEAlexander Esteban Espinosa
Alexander Esteban Espinosa
JGJorge Gomez-Rojas
Jorge Gomez-Rojas
MGMario Gongora
Mario Gongora
This paper presents an evaluation of different convolutional neural network (CNN) architectures using false-colour images obtained by multispectral sensors on drones for the detection of Black Sigatoka in banana crops. The objective is to use drones to improve the accuracy and efficiency of Black Sigatoka detection to reduce its impact on banana production and improve the sustainable management of banana crops, one of the most produced, traded, and important fruits for food security consumed worldwide. This study aims to improve the precision and accuracy in analysing the images and detecting the presence of the disease using deep learning algorithms. Moreover, we are using drones, multispectral images, and different CNNs, supported by transfer learning, to enhance and scale up the current approach using RGB images obtained by conventional cameras and even smartphone cameras, available in open datasets. The innovation of this study, compared to existing technologies for disease detection in crops, lies in the advantages offered by using drones for image acquisition of crops, in this case, constructing and testing our own datasets, which allows us to save time and resources in the identification of crop diseases in a highly scalable manner. The CNNs used are a type of artificial neural network widely utilised for machine training; they contain several specialised layers interconnected with each other in which the initial layers can detect lines and curves, and gradually become specialised until reaching deeper layers that recognise complex shapes. We use multispectral sensors to create false-colour images around the red colour spectra to distinguish infected leaves. Relevant results of this study include the construction of a dataset with 505 original drone images. By subdividing and converting them into false-colour images using the UAV’s multispectral sensors, we obtained 2706 objects of diseased leaves, 3102 objects of healthy leaves, and an additional 1192 objects of non-leaves to train classification algorithms. Additionally, 3640 labels of Black Sigatoka were generated by phytopathology experts, ideal for training algorithms to detect this disease in banana crops. In classification, we achieved a performance of 86.5% using false-colour images with red, red edge, and near-infrared composition through MobileNetV2 for three classes (healthy leaves, diseased leaves, and non-leaf extras). We obtained better results in identifying Black Sigatoka disease in banana crops using the classification approach with MobileNetV2 as well as our own datasets.

29 June 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JLJose-Luis Cabra Lopez
Jose-Luis Cabra Lopez
CPCarlos Parra
Carlos Parra
LGLibardo Gomez
Libardo Gomez
LTLuis Trujillo
Luis Trujillo
Physiological signals are strongly related to a person’s state of health and carry information about the human body. For example, by ECG, it is possible to obtain information about cardiac disease, emotions, personal identification, and the sex of a person, among others. This paper proposes the study of the heartbeat from a soft-biometric perspective to be applied to smartphone unlocking services. We employ the user heartbeat to classify the individual by sex (male, female) with the use of Deep Learning, reaching an accuracy of 94.4% ± 2.0%. This result was obtained with the RGB representation of the union of the time-frequency transformation from the pseudo-orthogonal X, Y, and Z bipolar signals. Evaluating each bipolar contribution, we found that the XYZ combination provides the best category distinction using GoogLeNet. The 24-h Holter database of the study contains 202 subjects with a female size of 49.5%. We propose an architecture for managing this signal that allows the use of a few samples to train the network. Due to the hidden nature of ECG, it does not present vulnerabilities like public trait exposition, light/noise sensibility, or learnability compared to fingerprint, facial, voice, or password verification methods. ECG may complement those gaps en route to a cooperative authentication ecosystem.

13 November 2023 in IEEE Sensors Journal
Verified
Journal Article
Closed access
ANAndres Eduardo Nieto
Andres Eduardo Nieto
CPCarlos Alberto Parra-Rodriguez
Carlos Alberto Parra-Rodriguez
OROmar Ramirez-Perez
Omar Ramirez-Perez
The classification of activities of daily living in the home of older adults makes it possible to identify risk situations and changes in behavior that may be associated with some type of problem. This information allows caregivers and health professionals to take action when these types of situations are detected. Although many machine learning classification techniques have been proposed, the effectiveness of the solution in a real-world context remains unclear in most cases due to the large number of sensors required, the type of sensors used which may pose privacy issues, and the assumption of considering only segmented sensor events for each activity before training the models. This paper presents an evaluation of different machine learning techniques using fixed time windows to extract spatio-temporal features and classify 10 human activities in a real smart home with unobtrusive sensors using the Aruba CASAS dataset. The three classification techniques that achieved better performance were Random Forest, XGBoost and Support Vector Machine, achieving an accuracy of 97% with our best model, outperforming other approaches from the literature that were using the same dataset under similar conditions. The proposed classification techniques were also evaluated under a more realistic scenario by reducing the amount of hardware required and using an additional class labeled "Other" to consider all raw sensor events, including those that do not belong to any specific activity, achieving an accuracy of 89%, outperforming other approaches from the literature using the same dataset under similar conditions.

29 May 2023 in Data
Verified
Journal Article
Open access
PDF file
JLJose-Luis Cabra Lopez
Jose-Luis Cabra Lopez
CPCarlos Parra
Carlos Parra
GFGonzalo Forero
Gonzalo Forero
Human sex recognition with electrocardiogram signals is an emerging area in machine learning, mostly oriented toward neural network approaches. It might be the beginning of a field of heart behavior analysis focused on sex. However, a person’s heartbeat changes during daily activities, which could compromise the classification. In this paper, with the intention of capturing heartbeat dynamics, we divided the heart rate into different intervals, creating a specialized identification model for each interval. The sexual differentiation for each model was performed with a deep convolutional neural network from images that represented the RGB wavelet transformation of ECG pseudo-orthogonal X, Y, and Z signals, using sufficient samples to train the network. Our database included 202 people, with a female-to-male population ratio of 49.5–50.5% and an observation period of 24 h per person. As our main goal, we looked for periods of time during which the classification rate of sex recognition was higher and the process was faster; in fact, we identified intervals in which only one heartbeat was required. We found that for each heart rate interval, the best accuracy score varied depending on the number of heartbeats collected. Furthermore, our findings indicated that as the heart rate increased, fewer heartbeats were needed for analysis. On average, our proposed model reached an accuracy of 94.82% ± 1.96%. The findings of this investigation provide a heartbeat acquisition procedure for ECG sex recognition systems. In addition, our results encourage future research to include sex as a soft biometric characteristic in person identification scenarios and for cardiology studies, in which the detection of specific male or female anomalies could help autonomous learning machines move toward specialized health applications.

9 June 2021 in Electronics
Verified
Journal Article
Open access
PDF file
EGEduardo A. Gerlein
Eduardo A. Gerlein
GDGabriel Diaz-Guevara
Gabriel Diaz-Guevara
HCHenry Carrillo
Henry Carrillo
CPCarlos Parra
Carlos Parra
EGEnrique Gonzalez
Enrique Gonzalez
This paper discusses a novel embedded system-on-chip 3D localization and mapping (eSoC-LAM) implementation, that followed a co-design approach with the primary aim of being deployed in a small system on a programmable chip (SoPC), the Intel’s (a.k.a Altera) Cyclone V 5CSEMA5F31C6N, available in the Terasic’s board DE1-SoC. This computer board incorporates an 800 MHz Dual-core ARM Cortex-A9 and a Cyclone V FPGA with 85k programmable logic elements and 4450 Kbits of embedded memory running at 50 MHz. We report experiments of the eSoC-LAM implementation using a Robosense’s 3D LiDAR RS-16 sensor in a Robotis’ TurtleBot2 differential robot, both controlled by a Terasic’s board DE1-SoC. This paper presents a comprehensive description of the designed architecture, design constraints, resource optimization, HPS-FPGA exchange of information, and co-design results. The eSoC-LAM implementation reached an average speed-up of 6.5× when compared with a version of the algorithm running in a the hard processor system of the Cyclone V device, and a performance of nearly 32 fps, while keeping high map accuracy.

1 July 2020
Verified
Conference Paper
Open access
JFJohana Florez-Lozano
Johana Florez-Lozano
Fabio CaraffiniFabio Caraffini
Fabio Caraffini
CPCarlos Parra
Carlos Parra
MGMario Gongora
Mario Gongora
Real-world problems such as landmine detection require multiple sources of information to reduce the uncertainty of decision-making. A novel approach to solve these problems includes distributed systems, as presented in this work based on hardware and software multi-agent systems. To achieve a high rate of landmine detection, we evaluate the performance of a trained system over the distribution of samples between training and validation sets. Additionally, a general explanation of the data set is provided, presenting the samples gathered by a cooperative multi-agent system developed for detecting improvised explosive devices. The results show that input samples affect the performance of the output decisions, and a decision-making system can be less sensitive to sensor noise with intelligent systems obtained from a diverse and suitably organised training set.