Completed Research
Completed Research
Embedded Files
This project focuses on visual attention as an approach to solve captioning tasks with computer vision. We have studied the efficiency of different hyperparameter configurations on a state-of-the-art visual attention architecture composed of a pre-trained residual neural network encoder, and a long short-term memory decoder. Results show that the selection of both the cost function and the gradient-based optimizer have a significant impact on the captioning results. Our system considers the cross-entropy, Kullback-Leibler divergence, mean squared error, and the negative log-likelihood loss functions, as well as the adaptive momentum, AdamW, RMSprop, stochastic gradient descent, and Adadelta optimizers. Based on the performance metrics, a combination of cross-entropy with Adam is identified as the best alternative returning a Top-5 accuracy value of 73.092, and a BLEU-4 value of 0.201. Setting the cross-entropy as an independent variable, the first two optimization alternatives prove the best performance with a BLEU-4 metric value of 0.201. In terms of the inference loss, Adam outperforms AdamW with 3.413 over 3.418 and a Top-5 accuracy of 73.092 over 72.989.
The team:
Roberto Raul Castro Izurieta (Main Researcher - Yachay Tech University)
Israel Pineda (Yachay Tech University)
Wansu Lim (Kumoh National Institute of Technology)
Manuel Eugenio Morocho-Cayamcela (Yachay Tech University)
Results presented on:
Source code:
Slides:
Computer vision to identify the incorrect use of face masks for COVID-19 awareness
Computer vision to identify the incorrect use of face masks for COVID-19 awareness
Face mask detection has become a great challenge in computer vision, demanding the coalition of technology with COVID-19 awareness. Researchers have proposed deep learning models to detect the use of face masks. However, the incorrect use of a face mask can be as harmful as not wearing any protection at all. In this thesis, we propose a compound convolutional neural network (CNN) architecture based on two computer vision tasks: object localization to discover faces in images/videos, followed by an image classification CNN to categorize the faces and show if someone is using a face mask correctly, incorrectly, or not wearing any mask at all. The first CNN is built upon RetinaFace, a model to detect faces in images; whereas the second CNN uses a Resnet-152 architecture as a classification backbone. Our model enables an accurate identification of people who are not correctly following the COVID-19 healthcare recommendations on face masks use. We have released our proposed computer vision model to the public, and optimized it for embedded systems deployment, empowering a global use of our technology.
The team:
Jonnathan Fabricio Crespo Yaguana (Main Researcher - Yachay Tech University)
Luz Marina Sierra Martinez (Universidad del Cauca)
Diego Hernán Peluffo-Ordóñez (Mohammed VI Polytechnic University)
Manuel Eugenio Morocho-Cayamcela (Yachay Tech University)
Results presented on:
Source code:
Slides:
The Future of Agriculture: Detecting Tomato Maturity Levels with YOLOv8
The Future of Agriculture: Detecting Tomato Maturity Levels with YOLOv8
The team:
Jean Carlo Camacho Espín (Main Researcher - Yachay Tech University)
Manuel Eugenio Morocho-Cayamcela (Yachay Tech University)
Results presented on:
Source code:
Avaliable on GitHub soon
Slides:
Available soon (after Jean Carlo's thesis defense)
A web application to learn sign language with deep learning
A web application to learn sign language with deep learning
Deep learning and computer vision are used to create applications that facilitate a better interaction between humans and machines. In the educational domain, obtaining information about sign language is simple, but finding a platform that allows for intuitive interaction is quite challenging. A web app has been developed to address this issue by employing deep learning to assist users in learning sign language. In this study, two models for hand-gesture recognition were tested, utilizing 20,800 images; the models tested were Alexnet and GoogLeNet. The overfitting problem encountered in convolutional neural networks has been considered while training these models. Several techniques to minimize the overfitting and improve the overall accuracy have been employed in this study. AlexNet achieved an 87\% of accuracy rate when interpreting hand gestures whereas GoogLeNet achieved an 85\% accuracy rate. These results were incorporated into the web app, which aims to teach the alphabet of American sign language intuitively
The team:
Bryan Eduardo Jami Jami (Yachay Tech University)
Manuel Eugenio Morocho-Cayamcela (Yachay Tech University)
Results presented on:
To be submitted
Source code:
Avaliable soon
Slides:
Available soon
Deep reinforcement learning for efficient nucleus cell location in digital pap smears
Deep reinforcement learning for efficient nucleus cell location in digital pap smears
In August 2020, World Health Assembly (WHA) defined three main global targets for eliminating cervical cancer. Hopefully, they may eliminate cervical cancer by 2030 by following three targets. One of those targets is ``70\% coverage of screening". This target required experienced professionals to complete the analysis of Papanicolaou digital images. Pathologists carry out the analysis of the image which takes around 30 minutes. The lack of pathologists retard the goals of the target proposed by WHA. This thesis focuses on using a deep reinforcement learning agent that learns by itself, by rewards, penalties and pass experiences, to move toward cell nucleus in digital images, by following an optimal path.In principle this will create an agent whose input are raw pixels and its output is nucleus coordinates. This information will be used for other specialised future agents to detect deviated cells. The final idea is to construct high efficiency automatic Papanicolaou analyzing machine.
The team:
Carlos Julio Macancela Bojorque (Main Researcher - Yachay Tech University)
Manuel Eugenio Morocho-Cayamcela (Yachay Tech University)
Oscar Chang (Yachay Tech University)
Results presented on:
To be submitted
Source code:
Avaliable soon
Slides:
Septorhinoplasty prediction with Denoising Diffusion Probabilistic Models
Septorhinoplasty prediction with Denoising Diffusion Probabilistic Models
Septorhinoplasty is a complex surgical procedure aimed at improving the functional and aesthetic aspects of the nose. In this study, we propose a novel approach for predicting post-septorhinoplasty outcomes using Denoising Diffusion Probabilistic Models (DDPM). The methodology involves generating synthetic post-surgery images from preoperative patient photos through the application of DDPM-induced noise. Subsequently, a U-Net architecture is employed to denoise the synthesized images and predict the potential postoperative appearance.
The first step of our framework involves training the DDPM on a large dataset of pre-septorhinoplasty patient images to learn the underlying distribution of natural nose variations. This trained model is then used to synthesize a diverse set of postoperative nose images by introducing diffusion-based noise to the original preoperative images. The introduction of noise helps capture the inherent uncertainty and variability present in real-world surgical outcomes.
Next, we employ a U-Net, a popular architecture for image denoising, to process the synthetic postoperative images generated by the DDPM. The U-Net is trained on paired data consisting of the original preoperative images and their corresponding noise-introduced counterparts. This supervised training process enables the U-Net to effectively remove the induced noise while preserving the essential features of the post-surgery nose appearance.
Technical requitements:
The student is expected to use a dataset of images from rhinoplasty surgeries and generate an image based on CGANs (Conditional Generative Adversarial Networks).
The new image will be generated from a photo of a patient before the surgery.
The team:
Jonathan Javier Loor Duque (Yachay Tech University)
Dra. Rosaura Yokasta Bravo Pita (Hospital Quito N1 Policía Nacional)
Dr. Freddy Raúl Guzmán Suarez (Hospital Quito N1 Policía Nacional)
Manuel Eugenio Morocho-Cayamcela (Yachay Tech University)
Results presented on:
To be submitted
Source code:
Avaliable soon
Slides:
Available soon
Decentralized-based blockchain system for enhancing the management of scientific publications
Decentralized-based blockchain system for enhancing the management of scientific publications
The peer review process by which a scientific research must go through to be reviewed and subsequently published or rejected has several positive and negative factors, among them is the factor that other scientists evaluate the quality of the work of other scientists to guarantee a rigorous and consistent work . Likewise, the identity of the evaluators is not revealed, in this way it is sought that the evaluation is not biased. However, the review process may lead to the publication to be delayed for more than one year. In some cases, investigators need to pay for the article processing charges. This is why the following proposal was born to improve this system by creating a decentralized version based on blockchain, which is used to review research managed by the scientific community through smart contracts. Since this new system will have a more secure anonymity factor, every step of the review process will be open and transparent. Reviewers will be rewarded with system tokens. The authors of the manuscripts with the highest impact will also be rewarded through tokens. In this way, the review process is expected to be faster, fairer, safer, and more transparent. In this graduation project, it is expected to write a white paper to document the proposed system.
The team:
Julio Rogers Cajas Guncay (Main Researcher - Yachay Tech University)
Juan Fernando Riofrio Valarezo (Yachay Tech University)
Manuel Eugenio Morocho-Cayamcela (Yachay Tech University)
Results presented on:
To be submitted
Source code:
Avaliable soon
Slides:
Avaliable soon
Knowledge Curation in the Digital Age: A Deep Learning-based Natural Language Processing Approach
Knowledge Curation in the Digital Age: A Deep Learning-based Natural Language Processing Approach
The team:
Leo Thomas Ramos (Main Researcher - Yachay Tech University)
Juan Sebastián Ochoa Zambrano (Universidad Politécnica de Madrid)
Juan Garbajosa (Universidad Politécnica de Madrid)
Manuel Eugenio Morocho Cayamcela (Yachay Tech University)
Hypothesis:
Does human interaction empower collective intelligence?
Resources:
Results:
To be submitted
Source code:
Avaliable soon
Slides:
Available soon
Boosting Image Captioning Using ConvNeXt Deep Neural Networks
Boosting Image Captioning Using ConvNeXt Deep Neural Networks
The team:
Leo Thomas Ramos (Main Researcher - Yachay Tech University)
Francklin Iván Rivas Echeverría (Yachay Tech University)
Manuel Eugenio Morocho Cayamcela (Yachay Tech University)
Results:
Under review
Source code:
Avaliable soon
Slides:
Available soon
Deep reinforcement learning for dynamic electromagnetic spectrum access
Deep reinforcement learning for dynamic electromagnetic spectrum access
Required knowledge:
The team:
Mateo Sebastián Lomas (Main Researcher - Yachay Tech University)
Oscar Chang (Yachay Tech University)
Wansu Lim (Kumoh National Institute of Technology)
Manuel Eugenio Morocho-Cayamcela (Yachay Tech University)
Results presented on:
To be submitted
Source code:
Avaliable soon
Slides:
Available soon
Deep learning hyperparameter optimization via genetic algorithms
Deep learning hyperparameter optimization via genetic algorithms
The team:
Krishna Román (Main Researcher - Yachay Tech University)
Paola Quiloango (Yachay Tech University)
Manuel Eugenio Morocho-Cayamcela (Yachay Tech University)
Rolando Armas (Yachay Tech University)
Results presented on:
To be submitted
Source code:
Avaliable soon
Slides:
Available soon
Development of a Generative Language Model-Based Supplementary Tool for High School and College Students Using META Language Models
Development of a Generative Language Model-Based Supplementary Tool for High School and College Students Using META Language Models
EDUAI chatbot powered by Llama-2-7b-chat-hf, based on the model developed by Meta, uses Pinecone as its vector database and employs cosine similarity calculation to identify and provide the most appropriate answers to user queries. This chatbot stands out for its educational approach, as it draws from an extensive database that includes exercises, audiovisual material, formulas and theorems essential for university and college level students. Its ability to contextualize answers within the database allows users to efficiently access valuable educational resources, making it a powerful tool for learning and teaching.
The team:
Darío Sebastián Cabezas Erazo (Main Researcher - Yachay Tech University)
Rigoberto Fonseca Delgado (Yachay Tech University)
Paulina Vizcaino (Universidad Internacional del Ecuador - UIDE) - Co-advisor
Iván Reyes (Universidad Internacional del Ecuador - UIDE) - Co-advisor
Manuel Eugenio Morocho-Cayamcela (Yachay Tech University)
Results presented on:
To be submitted
Source code:
Slides:
End-to-end Sign Language Translation with Stochastic and Natural Language Processing Transformers (BERT)
End-to-end Sign Language Translation with Stochastic and Natural Language Processing Transformers (BERT)
The team:
Andrés Fabricio Quelal Flores (Main Researcher - Yachay Tech University)
Manuel Eugenio Morocho-Cayamcela (Yachay Tech University)
Results presented on:
Slides:
CNNLENGUAJESIGNOS.pdf
Artificial intelligence-based eye-tracking algorithm as a neuro-scientific instrument
Artificial intelligence-based eye-tracking algorithm as a neuro-scientific instrument
Technical requirements:
Develop and optimize an eye-tracking algorithm using artificial intelligence.
Analyze the social impact of the developed technology.
Potential applications:
Marketing focalization in websites. Political message analysis.
Introduction: Hypothesis (define dependent -reaction-, and independent variables -action-)
Hypothesis: website (communication channel).
Independent variable: Publicity placement in the website, content placement in the website.
Independent co-variables: Color, typography, grid divisions (right, left, top, bottom, etc.).
Co-variables: Social status (different universities -public universities-), gender, age, political view.
Dependent variable: Emotions, facial expression, etc.
Theoretical Framework: (Eye tracking + Social impact)
State of the Art: Eye tracking for marketing focalization (Technical + Social impact). Find Metric.
The team:
Saul Figueroa (Yachay Tech Uniersity)
Andrés Tirado (Yachay Tech Uniersity)
Manuel Eugenio Morocho-Cayamcela (Yachay Tech University)
Results presented on:
To be submitted
Source code:
Avaliable soon
Slides:
Available soon
Plague pattern recognition based on inspection data collected in Galápagos
Plague pattern recognition based on inspection data collected in Galápagos
Description:
This project ams to read the database from the "Agencia de Regulación y Control de la Bioseguridad y Cuarentena para Galápagos". This database contains the information gathered by the units of inspection, which inspect all the ships,planes, etc. that enters the Galápagos Islands.
The plan:
Titulación I: The aim of this study is to find patters in the database that can help us to locate the ships,planes, etc. that introduce plagues to the islands. The hypothetical characteristics can be: the country of origin of the plane, the month of the year, the visiting motive, etc.
Titulación II: With the extracted patterns, the next step is to visualize the information (ARCGIS, etc), to help the units of inspection to optimize the inspection process.
Technical Requirements:
Basic knowledge of data mining, and machine learning.
Intermediate level in Python.
The team:
Jonathan Javier Loor Duque (Yachay Tech University)
Ariana Deyaneira Jiménez Narváez (Yachay Tech University)
Juan David Moromenacho (Universidad Internacional del Ecuador - UIDE)
Paulina Vizcaino (Universidad Internacional del Ecuador - UIDE) - Co-advisor
Iván Reyes (Universidad Internacional del Ecuador - UIDE) - Co-advisor
Manuel Eugenio Morocho-Cayamcela (Yachay Tech University) - Advisor
Results presented on:
To be submitted in an SCOPUS indexed conference/journal
Source code:
Avaliable soon on GitHub
Page updated
Google Sites
Report abuse