Publications (258)
ARTICLE
Neural Machine Translation for French–Mooré: Adapting Large Language Models to Low-Resource Languages
Walker Stanislas Rocksane COMPAORE, Maimouna Ouattara, Rodrique Kafando, Tegawendé F. Bissyandé, Abdoul Kader Kaboré, Aminata Sabané
This work focuses on neural machine translation between French and Mooré, leveraging the capabilities of Large Language Models (LLMs) in a low-resource language context. Mooré is a local language widely spoken in Burkina Faso but remains underrepresented in digital resources. Alongside Mooré, French, now a working language, remains widely used(...)
Machine translation, Natural language, Translation (biology), Feature (linguistics), Artificial neural network
ARTICLE
Contributing to Speech-to-Speech Translation for African Low-Resource Languages : Study of French-Mooré Pair
Fayçal S. A. Ouedraogo, Maimouna Ouattara, Rodrique Kafando, Abdoul Kader Kaboré, Aminata Sabané, Tegawendé F. Bissyandé
Most of African low-resource languages are primarily spoken rather than written and lack large, standardized textual resources. In many communities, low literacy rates and limited access to formal education mean that text-based translation technologies alone are insufficient for effective communication. As a result, speech-to-speech translatio(...)
Translation (biology), Languages of Africa, Natural language, Context (archaeology)
ARTICLE
A Novel Reference Model for Intelligent and Comfortable Longitudinal Vehicle Control: Theory, Optimization, and Validation
Flavien H. Somda, Désiré Guel, Kisito K. Kaboré, Antoine Schorgen
This paper introduces a novel reference model for intelligent longitudinal vehicle control, designed to enhance both safety and passenger comfort. The proposed model dynamically adjusts the follower vehicle’s acceleration based on its penetration distance relative to the lead vehicle, ensuring smooth speed transitions and adaptive deceleration(...)
Longitudinal Vehicle Control, Nonlinear Control Model, Adaptive Deceleration, Safety Distance Optimization, Intelligent Transportation Systems, Advanced Driver Assistance Systems (ADAS)
COMMUNICATION
5G-NR PRACH Detection Using an AutoEncoder Under Interference
Ahmed Sawadogo, Désiré Guel, Boureima Zerbo
Efficient detection of the Physical Random Access Channel (PRACH) is vital for reliable initial access in 5G New Radio (5G-NR), yet it remains challenged by intra- and inter-cell interference. This paper proposes a deep learning-based solution leveraging an Autoencoder (AE) trained on synthetic PRACH data under noisy conditions. The model dete(...)
5G-NR, PRACH, Autoencoder, Interference, Machine Learning, Deep Learning
COMMUNICATION
Emergency Severity Index Protocol with Machine Learning
Manegaouindé Roland Tougma, Boureima Zerbo, Désiré Guel, Salah Idriss Seif Traore, Salifou Napon
Effective triage in emergency departments is vital for optimizing patient outcomes and resource use, especially in resource-limited contexts like Burkina Faso. This study presents an automated triage system using machine learning (ML) to predict patient priority levels and appropriate medical services based on the Emergency Severity Index (ESI(...)
Emergency triage, Machine learning, Emergency Severity Index (ESI)
COMMUNICATION
Vehicle Routing Optimization for Medical Product Distribution in Regional Capitals of Burkina Faso: A Linear Programming Approach with Gurobi
Saan-Nonnan Olivier Dabire, Boureima Zerbo, Désiré Guel
This study presents a MILP based approach to the Vehicle Routing Problem (VRP) for optimizing medical product distribution in Burkina Faso. The model accounts for critical real-world constraints including restricted areas and road inaccessibility while ensuring equitable service to priority healthcare centers. Implemented using the Gurobi solv(...)
Vehicle Routing Problem (VRP), Medical product distribution, Mixed-Integer Linear Programming (MILP)
COMMUNICATION
A Comparative Study of CDL/TDL Channel Models in 5G-mmWave Networks
Mahamadi Sogoba, Désiré Guel, Boureima Zerbo
Millimeter-wave (mmWave) bands play a key role in 5G New Radio (5G-NR). They provide wider bandwidth and support much higher data rates. However, these bands also bring serious challenges. Signal propagation is more complex and affects system performance. This study fills an important gap. It compares two standard 3GPP channel models: Clustere(...)
5G-NR, NR-PDSCH, CDL/TDL channels, mmWave bands, BLER, SNR
ARTICLE
Comparative study of the performance of ChatGPT-4, Claude, Gemini, Mistral, and perplexity on multiple-choice questions in cardiology
Martin Wendlassida Nacanabo, Yannick Laurent Tchenadoyo Bayala, André Arthur Taryètba Seghda, Anna Tall/Thiam, Aristide Relwendé Yaméogo, Nobila Valentin Yaméogo, André Koudnoaga Samadoulougou & Patrice Zabsonré
Objective
The objective of our study was to assess and compare the performance of five LLMs on multiple-choice questions (MCQs) in cardiology.
Materials and methods
This was a comparative study conducted in the cardiology department of the Bogodogo University Hospital, Ouagadougou, involving 83 MCQs derived from the 2020 French national c(...)
Artificial intelligence, Large language model, Cardiology, Medical education, Multiple-choice question, Ouagadougou, Burkina faso
ARTICLE
Recommendation of Documentary Units in a Progressively Intelligent City
Kiswendsida Kisito Kaboré, Désiré Guel, Yaya Traoré, Pegdwinde Justin Kouraogo, Didier Bassolé, Yacouba Kyelem, Tonguim Ferdinand Guinko, Oumarou Sié
The large cities and capitals of developing countries are becoming larger and more populated. These cities are modernizing day by day in order to increase the standard of living of their constantly growing population. To do this, they are equipping themselves with the latest generation of intelligent infrastructures that can make a city very a(...)
Smart City, Recommendation, IAAS, Documentary Unit
ARTICLE
Ouagadougou SUMO traffic scenarios for urban mobility.
Emile NANA, Ferdinand Tonguim GUINKO
In our work, we are attempting to predict urban traffic congestion in order to address issues related to urban mobility. We believe that congestion situations have upstream causes that significantly impact urban traffic flow. Thus, to resolve the problem of traffic congestion, there are intermediate steps that allow us to understand the traffi(...)
urban traffic simulation , road traffic prediction , road traffic engineering , SUMO , ontology , road traffic planning
ARTICLE
When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair
Wenqiang Luo, Jacky Wai Keung, Boyang Yang, He Ye, Claire Le Goues, Tegawendé F. Bissyandé, Haoye Tian, Bach Le
Software systems have been evolving rapidly and inevitably introducing bugs at an increasing rate, leading to significant maintenance costs. While large language models (LLMs) have demonstrated remarkable potential in enhancing software development and maintenance practices, particularly in automated program repair (APR), they rely heavily on(...)
Fine-Tuning, LLMs
ARTICLE
A Robust Crop Recommendation System Leveraging Soil and Climate Parameters
Desire Guel and Jimna Kongo
We present a benchmarking study of classical machine learning (ML) methods for crop recommendation from soil and climate parameters with an emphasis on methodological transparency, interpretability and deployability in low-resource contexts. We evaluate K-Nearest Neighbors (KNN), Random Forest (RF), Support Vector Classifier (SVC), Gaussian Na(...)
Crop Recommendation, Precision Agriculture, Ensemble Learning, Interpretability
ARTICLE
A Survey on Deep Learning Techniques for Malaria Detection: Datasets Architectures and Future Perspectives
Desire Guel, Kiswendsida Kisito Kabore, Flavien Herve Somda
Malaria remains a significant global health challenge that affects more than 200 million people each year and disproportionately burdens regions with limited resources. Precise and timely diagnosis is critical for effective treatment and control. Traditional diagnostic approaches, including microscopy and rapid diagnostic tests (RDTs), encount(...)
Malaria Detection, Deep Learning (DL), Convolutional Neural Networks (CNNs), Medical Imaging, Automated Diagnostics
ARTICLE
<scp>MORepair</scp> : Teaching LLMs to Repair Code via Multi-Objective Fine-Tuning
Boyang Yang, Haoye Tian, Jiadong Ren, Hongyu Zhang, Jacques Klein, Tegawendé F. Bissyandé, Claire Le Goues, Shunfu Jin
Within the realm of software engineering, specialized tasks on code, such as program repair, present unique challenges, necessitating fine-tuning Large language models (LLMs) to unlock state-of-the-art performance. Fine-tuning approaches proposed in the literature for LLMs on program repair tasks generally overlook the need to reason about the(...)
LLMs
ARTICLE
PriCod: Prioritizing Test Inputs for Compressed Deep Neural Networks
Yinghua Li, Xueqi Dang, Jacques Klein, Yves Le Traon, Tegawendé F. Bissyandé
The widespread adoption of Deep Neural Networks (DNNs) has brought remarkable advances in machine learning. However, the computational and memory demands of complex DNNs hinder their deployment in resource-constrained environments. To address this challenge, compressed DNN models have emerged, offering a compromise between efficiency and accur(...)
Prioritizing