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
Ongoing Research
Ongoing Research
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
Open Research Calls for Yachay Students
Open Research Calls for Yachay Students
If you are a Final Graduation Project student, you can apply for supervision on the following topics. The students will be the main researchers supervised by one of the DeepARC teams.
Comprehensive AI Solutions for Enhancing Education, Environmental Sustainability, and Transportation Efficiency
Comprehensive AI Solutions for Enhancing Education, Environmental Sustainability, and Transportation Efficiency
Description:
The group is interested in a student to conduct research in any of the following topics:
Investigate how AI can facilitate collaborative learning between students, as well as between students and teachers, by creating virtual learning environments (Metaverses) and collaboration tools.
Investigate how artificial intelligence systems can provide personalized and adaptive tutoring to students in various ECC subjects for example in programming, AI, Data Science
Investigate how AI can improve solid waste sorting, recycling and management, using computer vision systems and optimization algorithms to reduce pollution and promote the circular economy.
Investigate how AI algorithms can optimize public and private transportation routes, considering factors such as traffic, weather conditions, user preferences, and energy efficiency goals.
Technical Requirements:
Basic knowledge of data mining, and machine learning.
Intermediate level in Python.
The team:
<Main Researcher>
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
Temperature/Climate Prediction Using Time Series Analysis in Ecuadorian Cities
Temperature/Climate Prediction Using Time Series Analysis in Ecuadorian Cities
Project Overview
We invite students to join a collaborative research project between Yachay Tech and the Universidad Internacional del Ecuador (UIDE). This project, suitable for a thesis or final project, will leverage historical climate data from various Ecuadorian cities to develop predictive algorithms for estimating future temperature and climate conditions.
Objective
The goal is to create a time series model to predict temperature and weather patterns based on historical data. Participants will have access to an extensive dataset and can utilize tools like PyCaret, Prophet, ARIMA, or any preferred time series tools to design and optimize their models.
Structure
Progress Meetings: Teams will participate in regular progress meetings with faculty from both universities, fostering an environment for feedback and collaborative problem-solving.
Inter-Institutional Collaboration: Students from Yachay Tech and UIDE will work together, sharing ideas and methodologies to enrich the learning experience.
Technical Requirements:
Basic knowledge of time-series forecasting.
Intermediate level in Python.
The team:
<This can be you!>
Paulina Vizcaino (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
Data Science and Business Intelligence with the Ecuadorian Stock Market (UDLA)
Data Science and Business Intelligence with the Ecuadorian Stock Market (UDLA)
Description:
This project ams to read the database from the "Bolsa de Valores del Ecuador". And create a time-series estimator to gain knowledge on when to buy/sell stocks.
Technical Requirements:
Basic knowledge of time-series forecasting.
Intermediate level in Python.
The team:
<This can be you!>
Andrés Navas (Universidad de las Américas - UDLA) - 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
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
Artificial intelligence-based model to help teachers grade academic pronunciation
Artificial intelligence-based model to help teachers grade academic pronunciation
Functional requirements:
The grading system should be able to identify grammar, punctuation, spelling, capitalization, and other kinds of language errors.
The grading system should be able to provide a score based on the previous criteria.
Non-functional requirements:
The model should have a website-based front-end, intuitive and friendly for the final user.
Notes:
The use of open source libraries is encouraged (OpenAI-based APIs).
The team:
<Main Researcher>
Gabriela Villavicencio (Yachay Tech University, Language Center) - Co-advisor
Hamilton Quezada (Yachay Tech University, Language Center) - Co-advisor
Rigoberto Fonseca (Yachay Tech University) - Co-advisor
Manuel Eugenio Morocho-Cayamcela (Yachay Tech University) - Advisor
Results presented on:
To be submitted
Source code:
Avaliable soon
An Evolutionary Approach for Deep Neural Network Parametrization
An Evolutionary Approach for Deep Neural Network Parametrization
The team:
<Main Researcher>
Erick Cuenca (Yachay Tech University) - Co-advisor
Rolando Armas (Yachay Tech University) - Co-advisor
Manuel Eugenio Morocho-Cayamcela (Yachay Tech University) - Advisor
Reading requisites:
Article: EvoDeep: a new Evolutionary approach for automatic Deep Neural Networks parametrisation
Code asociated with the article: Github
The dataset:
The student is free to select the application. That is, the imagery dataset to be used to train and test the DNN.
Results presented on:
To be submitted
Source code:
Avaliable soon
Machine learning as an enabler the next-generation WiFi networks
Machine learning as an enabler the next-generation WiFi networks
Technical requirements:
The student should have prior knowledge on wireless networks and machine learning.
The team:
<Main Researcher>
Juan Pablo Astudillo León (Yachay Tech University) - Co-advisor
Christian Tipantuña (Escuela Politécnica Nacional) - Co-advisor
Manuel Eugenio Morocho-Cayamcela (Yachay Tech University) - Advisor
Results presented on:
To be submitted
Source code:
Avaliable soon
The Hidden Threats of Large Language Models: A Critical Security Review
The Hidden Threats of Large Language Models: A Critical Security Review
The team:
Luis Cedeño (Yachay Tech University)
Manuel Eugenio Morocho-Cayamcela (Yachay Tech University) - Advisor
General Objective:
The objective of this thesis is to analyze: How Secure Are Large Language Models in Handling Sensitive Data?, and building A Practical Guide to Secure LLM Deployment in Organizations.
Develop a chatbot powered by Meta Llama 3.2 to interact with enterprise databases, extract insights, and generate automated recommendations while ensuring data security.
Specific Objectives:
Conduct a systematic review of security risks associated with LLMs in enterprise environments.
Design and implement a system utilizing Meta Llama 3.2 to securely extract insights and automate report generation.
Evaluate potential vulnerabilities and implement mitigation strategies during the LLM integration process.
1st Semester: Systematic Review
1. Perform a comprehensive literature review on LLM security.
2. Identify key vulnerabilities (e.g., prompt injection, model poisoning, data leakage, unbounded consumption, adversarial attacks, etc.).
3. Draft and submit a survey paper highlighting critical findings.
Deliverable: An open access survey paper (IEEE Access) "Security in Large Language Models: A Systematic Review"
2nd Semester: Secure Chatbot Implementation
1. Train and deploy Meta Llama 3.2 locally to securely interact with enterprise databases.
2. Assess security risks during LLM interaction with sensitive data.
3. Design and implement an automated system for generating and emailing reports.
4. Write a research paper based on findings and proposed security improvements.
Deliverable: A technical paper "Secure Deployment of Local LLMs in Enterprise Settings"
Student Requirements:
Basic knowledge of how Meta LLaMA works (e.g., LLaMA 3.2-1B).
Familiarity with PyTorch ExecuTorch for on-device inference.
Foundational knowledge of cybersecurity principles in LLMs.
Intermediate Python programming skills.
Expected Impact:
1. Practical guidelines for the secure adoption of LLMs in enterprise contexts.
2. Contribution to the state of the art in generative AI security.
3. Publication of two high-impact scientific papers with strong citation potential.
Source code:
Available soon
Social media data to empower an AI-based sentiment analysis model
Social media data to empower an AI-based sentiment analysis model
Technical requirements:
Use the information of a mobile App API (e.g., Twitter, Spotify, Youtube, Facebook, etc.) to develop a sentiment analysis model using AI.
Analyze the social impact of the developed technology.
Potential applications:
Political tendency prediction.
Recognition of social behavior patterns.
The team:
<Main Researcher>
Silvana Escobar (Yachay Tech Uniersity) - Co-advisor
Erick Cuenca (Yachay Tech Uniersity) - Co-advisor
Manuel Eugenio Morocho-Cayamcela (Yachay Tech University) - Advisor
Results presented on:
To be submitted
Source code:
Avaliable soon
AI-based mass movement inventory model for early warning systems
AI-based mass movement inventory model for early warning systems
Technical requirements:
Estimation of mass movement inventory (using supervised learning techniques)
Principal component analysis (PCA).
Pearson/Spearman correlation coefficient.
Potential applications:
Early warning system for mass movement.
Available data:
Orthophoto (from MAGAP 2014) RGB
Intensity of RGB channels.
Digital terrain model (DTM) (resolution 3m/pixel).
Altitude over sea level.
Slope on each point.
Difference in altitude between points.
Estimation of rivers.
Geology (type of rock i.e., clay, etc.).
Edaphology/Pedology (type of soil until 2m).
Soil coverage (i.e., foliage, grass, corn, etc.).
True positive, true negative, false positive, false negative. -> Expert labeled data
Mass movement inventory (type of mass movement, i.e., flow, falls, topless, debris flow, etc.) -> Expert labeled data
The team:
<Main Researcher>
María Gabriela Cajamarca (Yachay Tech University) - Co-advisor
Raisa Ivanova Torres-Ramírez (Yachay Tech University) - Co-advisor
Manuel Eugenio Morocho-Cayamcela (Yachay Tech University) - Advisor
Results presented on:
To be submitted
Source code:
Avaliable soon
Feel free to contact us if you are interested in being part of any of our teams.If you are an external professor/researcher, we are happy to collaborate.You can bring your own ideas and we will build a tailored research team for you to work with.If you are a Yachay Tech student, you are required to have approved a related lecture with 8/10 or higher. The max. number of supervised students per semester is 4 (not including co-supervision).Student's applications are evaluated until the first week of the semester (as long as the max. number of students has not been reached).
Page updated
Google Sites
Report abuse