Publications (58)
ARTICLE
An ETL Method for Data Warehouse Design Driven by Ontology and LLM
Kientega, T.B., Traore, Y., Malo, S
The processes involved in feeding a warehouse require such a high level of expertise that they are generally entrusted to an IT specialist (data administrator). This requires, first, that decision-makers express their needs to the IT specialist and, second, that the data warehouse developed by this IT specialist be validated. In the era of ope(...)
Extract-Transform-Load (ETL); Large Language Models (LLMs) ; Ontology ; data warehousing ; Natural language; Requirements
COMMUNICATION
Improving Deep Learning Based UAV Thermal Images Classification By Taking Into Account Climate And Flight Parameters: The Case Of Fully Buried IEDs
Issaka Daouèga, Sadouanouan Malo, Frédéric Ouédraogo
Improvised explosive devices (IEDs) pose a serious threat to military operations. Previous studies have shown that thermal imaging can effectively distinguish between undisturbed soil, disturbed soil, and disturbed soil containing or not containing a buried IED, using batch-normalized VGG11 and VGG16 networks respectively. This study focuses o(...)
improvised explosive devices, infrared thermography, UAV imagery, thermal image classification, flight altitude, ambient temperature, sun exposure, VGG16, LSTM, time series modeling
COMMUNICATION
Extraction and Classification of Financial Documents: State of the Art, Methodology and Perspectives
Fousseni Seri, Sadouanouan Malo, Julie Thiombiano
Supreme Audit Institutions (SAIs) are crucial for transparency in public financial management but face major challenges when manually processing large volumes of multilingual, semi-structured, and heterogeneous financial documents. This paper reviews recent advances in multimodal Transformers and OCR-free models for document artificial intelli(...)
Financial Document Analysis, Supreme Audit Institutions, Multimodal Models, Document Classification, Information Extraction, OCR-free Models
COMMUNICATION
A Hybrid ABM-ML Framework for Simulating Climate Induced Migration in Burkina Faso
Soulama Zidama Adama, Belem Mahamadou, Hié kouvibana Aida, Sadouanouan Malo
The internal migration, influenced by intricate socioeconomic and climatic factors, presents a considerable obstacle to sustainable development in Burkina Faso. Although the factors influencing migration are generally comprehended, quantitative, long-term forecasts of migratory trends are lim-ited, obstructing proactive policy formulation. Thi(...)
climate-induced migration, internal migration, interprovincial migration, agent-based modeling, random forest, Shared Socioeconomic Pathways, migration forecasting, household migration decisions, spatially explicit simulation, GAMA platform, Burkina Faso
COMMUNICATION
Ontology Population and Maintenance Based on Web Scraping: Case of OntoSYSPARCOTCI
Téhia Kouaho N'Guessan Narcisse, Kaboré Ben Abdoul Nassire, Malanno Kouakou, Kouadio Kra Norbert Bini, Sadouanouan Malo
This paper discusses the populating of an ontology dedicated to the phytosanitary surveillance of cotton plants. This ontology was built with the aim of annotating the data from phytosanitary surveillance of cotton in Côte d’Ivoire and facilitating collaboration between actors with different skills. Its implementation led to the creation of a(...)
ontology population, ontology maintenance, web scraping, natural language processing, semantic wiki, phytosanitary surveillance, cotton, Côte d'Ivoire
COMMUNICATION
A RAG-Based LLM for Real-Time Cotton Diseases Prediction and Suitable Treatment Suggestion
Zakaria Kinda, Sadouanouan Malo
In Burkina Faso, farmers and plant pathologists remain with important challenges in treating cotton diseases. The development of natural language algorithms has advantages to the implementation of a tool for suggesting treatments for cotton diseases and the classification of cotton diseases using meteorological data. In order to propose a tool(...)
cotton diseases, disease classification, treatment guidelines, retrieval-augmented generation, large language models, Llama 2, BERT, meteorological observations, chatbots, plant pathology, Burkina Faso
COMMUNICATION
A Stacking-Based Model for Animal Disease Detection in Burkina Faso
Zakaria Cheick Oumar Keita, yaya Traore, Nouhoun Zampaligré, Sadouanouan Malo
Livestock farming in Burkina Faso faces numerous challenges, such as the reduction and degradation of grazing areas, difficulties in accessing pastoral and land resources, as well as the prevention and management of diseases, particularly epizootics. Although the number of qualified agents appears sufficient to address some of these issues, th(...)
animal disease diagnosis, stacking ensemble, meta-model, livestock health, epizootic, veterinary practice
AUTRE
A Predictive Deep Learning Model for Educational Success Rate
Soilyhouna Kabore, Bole Wilfried Tienin, Julie Thiombiano, Sadouanouan Malo
Educational success rate prediction worldwide still faces fundamental challenge, such as data availability that varies across administrative regions. In this investigation, we address this challenge through a predictive deep learning approach applied to Burkina Faso’s primary education system, where some regions maintain consistent records whi(...)
student performance prediction, deep learning, educational data mining
PRéPUBLICATION
Evaluation of state-of-the-art models for improving the diagnosis of mango tree diseases through supervised learning of symptom images in Burkina Faso
Zoéyandé Oumarou DIANDA, Emile KABORE, Zakaria Cheick Oumar Keita, Issaka Zida, Zakaria Kinda, Lankoandé Benjamin, Sadouanouan Malo, Issa Wonni
Abstract
In Burkina Faso, the mango industry faces numerous phytosanitary constraints. This situation is exacerbated by producers' lack of knowledge about diseases and their symptoms, and the low uptake of control technologies. This study aims to develop a tool using artificial intelligence-based approaches for better integrat(...)
plant disease diagnosis, YOLOv11, mango anthracnose, bacterial diseases, dieback, phytosanitary management, integrated pest management, mobile application, Burkina Faso
ARTICLE
Fog-Enabled Modular Deep Learning Platform for Textual Data Mining in Healthcare for Pathology Detection in Burkina Faso.
Constantin Drabo, Sadouanouan Malo
In this paper, we propose an architecture for a deep-learning based medical diagnosis support platform in Burkina Faso. This model is built by merging the diagnosis and treatment guide with models derived from textual data recovered via optical character recognition (OCR) on handwritten prescriptions and data from electronic health records. Th(...)
Fog computing, text mining, pathology detection, healthcare platform
COMMUNICATION
A Framework for Cashew Yield Approximation Based on Remote Sensing Data
Thierry Roger Bayala, Sadouanouan Malo, Zakaria Kinda
Accurate yield prediction allows farmers to strengthen their relationships with their customers, as they are able to guarantee supply and deliver contracts on time. Neural networks have made it possible to build robust and accurate prediction models. However, Neural Nets are quite demanding in terms of quality training datasets. In addition, t(...)
crop yield prediction, tree height estimation, fully convolutional network, UAV imagery, RGB images, linear regression, remote sensing, explainable models, training data quality
COMMUNICATION
Classification of Buried IEDs and Buried IED Decoys Using Convolutional Neural Networks on Ground Images from Thermal Cameras Embarked on UAVs
Issaka Daouèga, Sadouanouan Malo, Frédéric Ouédraogo
Improvised explosive devices (IEDs) are used by Armed Terrorist Groups (GATs) to hinder the progress of the military forces. The burial of IEDs causes disturbances to the ground surface perceptible by thermal sensors. However, it happens that GATs dig the ground without burying an object in order to just simulate the presence of an IED. We ref(...)
improvised explosive devices, thermal imagery, convolutional neural networks, ResNet-18, VGG16, Inception, vision transformer
COMMUNICATION
An Ontology-Based System for Detecting and Repairing Road Potholes Through Community Involvement
Abdoul Azize Kindo, Lucien Kalmogo, Sadouanouan Malo
Potholes pose significant risks to road safety, endangering both human lives and vehicle integrity. Enhancing the safety of road infrastructure hinges on the prompt identification and repair of these potholes. This article introduces an affordable pothole detection system that engages citizens by utilizing smartphones to efficiently report the(...)
Semantic Web;Visualization;Soft sensorsOntologies, Road safety, Safety, Maintenance, Sustainable development, Smart phones;Interoperability, Pothole, Citizen Participation, Road Safety, Ontology, GPS Integration, Semantic Web
COMMUNICATION
Identification of Taurine Cattle Breed Based on Convolutional Neural Network
Fulbert Bembamba, Ozias Bombiri, Albert Soudré, Frédéric Ouédraogo, Sadouanouan Malo
Identifying West African taurine cattle breed has become vital since uncontrolled crossing with zebus is jeopardizing their genetic heritage and trypanoresistance capacity. In this study, a computer vision solution is proposed for lobi taurine cattle classification. We implemented a customized Convolutional Neural Network (CNN) on a dataset co(...)
zebu crossbreeding, transfer learning, VGG16, breed conservation
ARTICLE
Impact of Terrorism on the Use of Healthcare Services in Burkina Faso Between 2015 and 2022
S. M. Somda, Sadouanouan Malo
Burkina Faso has been facing a security crisis due to terrorism since 2015. This study aims to assess the impact of the attacks on the use of healthcare services. This is a secondary study on data from the country's health data warehouse and the ACLED security data warehouse. After a description, generalized additive models were used to assess(...)
Health Services, Terrorism, Burkina Faso