Publications (193)
ARTICLE
Towards a More Generic and Elastic Metadata Management Model in a Data Lake Environment
Safiatou S Sore, T Frederic T Frédric Ouedraogo, Moustapha M Bikienga, Yaya Y Traore
The evolution of the vast amount of heterogeneous data sources is leading to the emergence of several new concepts. One of the best-known concepts that is emerging as a new and trending topic in the big data space is the data lake. This is a central repository that stores heterogeneous data sources in their native format, without any predefine(...)
Mots clés non renseignés
ARTICLE
Characterization of Malicious URLs Using Machine Learning and Feature Engineering
Nana, S.R., Bassolé, D., Dimitri Ouattara, J.S., Sié, O.
In this paper, we use Machine Learning models for malicious URL detection and classification by Feature Engineering techniques. These models were implemented with scikit-learn using Random Forest, Support Vector Machine and XGBoost classifier algorithms. Our models were trained, tested, and then optimized with a dataset of 641,125 URLs (benign(...)
Malicious URL, Characterization, Feature Engineering, Detection, Classification
ARTICLE
Fakipedia: Building and exploiting an AI model for detecting online fake news in Burkina Faso
Angelique Sidbewendin Yameogo, Aminata Sabané, Tégawendé F. Bissyandé, Rodrique Kafando, Abdoul-Kader Kabore
Misinformation poses a significant challenge, especially in developing countries with low literacy rates. The rapid spread on social media, coupled with their lack of robust verification mechanisms, makes distinguishing between credible and false information increasingly difficult. This document outlines our efforts to address this challenge i(...)
Fake News, Machine Learning, Text Classification, camemBERT, Artificial Intelligence
ARTICLE
Neural Machine Translation for Mooré, a Low-Resource Language
Hamed Joseph Ouily, Aminata Sabane, Delwende Eliane Birba, Rodrique Kafando, Abdoul Kader Kabore, Tegawende F. Bissyandé
Natural Language Processing (NLP) is a field of artificial intelligence with the goal of enabling machines to understand human language. Neural Machine Translation (NMT) is one of the many applications of NLP and allows for the translation of a source language into a target language. NMT has made significant progress in recent years. However,(...)
Natural Language Processing, Neural Machine Translation, Low-ressource Lan- guage
ARTICLE
Voice Interaction in Moore Language Study on Isolated Word Recognition in Audio Samples
Moumini Kabore, Rodrique Kafando, Aminata Sabane, Abdoul Kader Kabore, Tégawendé F. Bissyande
This paper explores the optimization of telephone functionalities through voice interaction in the
Moore language, prevalent in Burkina Faso. Data gathered from 492 individuals in Ouagadougou,
representing diverse dialects and vocal intensities across age groups, informs the study. Employing
K-Nearest Neighbor (KNN), Random Forest (RF), and(...)
Isolated Word Recognition, RNN
COMMUNICATION
Automédication à l’ère du numérique: enquête auprès de la population de la ville de Ouagadougou (Burkina Faso)
RA YAMEOGO, L BERE, P ZABSONRE, N MEDA
Introduction : L’automédication est un phénomène fréquent avec des conséquences telle que l’émergence des résistances bactériennes. Cette tendance pourrait être en pleine croissance avec l’ère du numérique avec l’amélioration de l’accès à internet et aux informations. L’objet de notre étude était de décrire l’impact d’internet sur la pratique(...)
Automédication, internet, Antibiotiques, Anti-inflammatoires
COMMUNICATION
Study and design of a multi-user detection based radio platform in vehicular ad hoc networks
Pegdwindé Justin Kouraogo , Zbigniew Dziong, Mohamad Haidar, François Gagnon
In this work we study a system and mechanism designed to enhance the throughput and the packet delivery ratio of a multiuser detection based vehicular ad hoc network (VANET), in two radios channels models. The first models we take into account is the wideband multipath channel and the second a vehicular-to-vehicular radio channel. We have used(...)
VANET, Multiuser detection, SDR plateform, channel prédiction
COMMUNICATION
Speed and Interference Effect Analysis in Multiuser Detection Based Radio Platform for Vehicular Ad Hoc Network
Pegdwindé Justin Kouraogo, Zbigniew Dziong, Mohamad Haidar, François Gagnon
This work presents the performance evaluation of the cross-layer prediction framework in the context of ad hoc network mobility and multiple access interference. Node mobility influences the quality of channel prediction and, obviously, packet reception. It also leads to varying levels of interference, depending on the scenario used and the nu(...)
VANET, SDR plateform, multiuser detection, interference
ARTICLE
Measures To Enhance The Characterization Of Internet Exchange Points
Y. Dabone, T. F. Ouedraogo, O. Sie
The reliability of data transport on the Internet is one of the objectives of researchers in the field of computer science. Data such as videos and audio is becoming increasingly large. Therefore, transporting them over the Internet is becoming difficult. It has therefore been important to establish a method of locally interconnecting autonomo(...)
Characteristic, Autonomous System, Internet Service Provider, Internet eXchange Point
ARTICLE
Evaluating Acoustic Parameters for DeepFake Audio Identification
Albérick Euraste Djiré; Aminata Sabané; Abdoul-Kader Kabore; Rodrique Kafando; Tégawendé F. Bissyandé
The progress made in the field of machine learning applied to signal processing offers interesting perspectives in terms of technological evolution but also causes some troubles in terms of ethics and security. For example, we are witnessing the emergence of audio deepFakes used to orchestrate scams. However, although the tools used in the gen(...)
Deep learning, deepFake audio, Deepfakes, detection, Ethics, Mel frequency cepstral coefficient, mel-spectogram, MFCC, Reliability, Security
COMMUNICATION
Enhancing Power Efficiency in NB-IoT Networks: PAPR Reduction in SC-FDMA
Désiré Guel, P. Justin Kouraogo, Boureima Zerbo, Modeste Dembele
NB-IoT, short for NarrowBand IoT, is a communication standard designed to enable the communication of a large number of connected objects over long distances. One of the research areas in NB-IoT systems is the Peak-to-Average Power Ratio (PAPR). NB-IoT, which is an extension of the LTE (Long Term Evolution) technology of 4G, uses the Single Ca(...)
Peak to Average Power Ratio (PAPR), Single-carrier FDMA (SC-FDMA), Narrowband { Internet of Things (NB-IoT) Networks
COMMUNICATION
Leveraging Conversational AI for Accelerating User-Driven Software Testing
Aminata Sabané, Laura Plein, Tegawendé F. Bissyandé
This work addresses a research challenge in automating the translation of natural language inputs into programming language specifications. We consider the case of bug reports, which are informally written by users, and that must be specifying into executable test cases for reproducing the bug on the target software. Software bugs are indeed l(...)
test generation, LLM, bug report
ARTICLE
Emergency Severity Index (ESI) a more suitable system for emergencies in Burkina Faso
Tougba Manegaouindé Roland, Zerbo Boureima, Guel, Désiré, Kouraogo Justin
The triage system an emergency department must prioritize the patients' needs above all else. Additionally, it enables improved care organization based on client type, institutional mission, and available resources. In order to conduct effective triage, the Orientation and Reception Nurse (ORN) should employ a reliable, valid, and reproducible(...)
Emergency Severity Index (ESI), ECG, SpO2, Healthcare, patient
ARTICLE
Emergency Severity Index (ESI), a more suitable system for emergencies in Burkina Faso
Roland M. TOUGMA, Boureima ZERBO, Désiré GUEL, P. Justin KOURAOGO
The triage system an emergency department must prioritize the patients' needs above all else. Additionally, it enables improved care organization based on client type, institutional mission, and available resources. In order to conduct effective triage, the Orientation and Reception Nurse (ORN) should employ a reliable, valid, and reproducible(...)
Emergency Severity Index (ESI), Electrocardiogram (ECG), Pulse Oxymetry, Healthcare, patient
ARTICLE
Enhancing Power Efficiency in NB-IoT Networks: PAPR Reduction in SC-FDMA
Désiré Guel, P. Justin Kouraogo, Boureima Zerbo, Modeste Dembele
NB-IoT, short for NarrowBand IoT, is a communication standard designed to enable the communication of a large number of connected objects over long distances. One of the research areas in NB-IoT systems is the Peak-to-Average Power Ratio (PAPR). NB-IoT, which is an extension of the LTE (Long Term Evolution) technology of 4G, uses the Single Ca(...)
Peak to Average Power Ratio (PAPR) Single-carrier FDMA (SC-FDMA) Narrowband { Internet of Things (NB-IoT) Networks