Publications (280)
COMMUNICATION
Towards An Ecore-Based, Uncertainty-Aware Metamodel for Auditable Geopolitical Decision Support
Somda Flavien Hervé, Guel Désiré , Kangoye Sékou
We present GeoDepend-ML, a temporal, multiplex Ecore metamodel for representing geopolitical interdependence and influence with auditability. The model treats actors (states, blocs, enterprises, organizations), assets (resources, technologies, infrastructures, routes), and artifacts (e.g., treaties, licenses, sanctions) as first-class elements(...)
Multiplexing, Uncertainty, Sensitivity analysis, Semantics, Lithography, Licenses, Security, Risk analysis, Reliability, Sustainable development, Ecore, EMF, international relations, knowledge graphs, multiplex networks, decision support, provenance, uncertainty
ARTICLE
Towards an Ontology and Knowledge Graph-Based Recommendation Approach Enhanced with Large Language Models for Civil Service Recruitment in Burkina Faso
Wend-Panga Régis Cédric BÉRÉ, Yaya Traoré, P. Justin Kouraogo, Daouda Ouedraogo
Recruitment processes in the civil service often face challenges related to the management of competencies, complex regulatory rules, and the lack of explainability in selection decisions. To address these issues, we propose a hybrid recommendation approach that integrates a modular core ontology, a dynamic knowledge graph, and large language(...)
Knowledge engineering , Large language models , Systems architecture , Knowledge graphs , Ontologies , Resource management , Personnel , Sustainable development , Recommender systems , Recruitment
ARTICLE
Mapping the COVID-19 pandemic in Burkina Faso: spatial patterns, socioeconomic factors, and public health implications
Abdoul Azize Millogo, Aboubacar Karabinta, Emmanuel Kiendrebeogo, Bry Sylla, Abdoulaye DIABATÉ, Lassane Yameogo
The first case of COVID-19 in Burkina Faso was reported in March 2020. As of June 8, 2025, Burkina Faso reported 22,114 confirmed cases and 400 deaths. However, few studies have investigated the spatiotemporal dynamics of pandemics within the national boundaries. This study provides a retrospective spatial analysis of COVID-19 transmission in(...)
Public health, Pandemic, Spatial analysis, Geographic information system, Population, Health geography, Spatial epidemiology, Geographically Weighted Regression, Poverty, Socioeconomic status
ARTICLE
Resolving Conditional Implicit Calls to Improve Static and Dynamic Analysis in Android Apps
Jordan Samhi, René Just, Michael D. Ernst, Tegawendé F. Bissyandé, Jacques Klein
An implicit call is a mechanism that triggers the execution of a method m without a direct call to m in the code being analyzed. For instance, in Android apps the Thread.start() method implicitly executes the Thread.run() method. These implicit calls can be conditionally triggered by programmer-specified constraints that are evaluated at runti(...)
Resolving
PRéPUBLICATION
Optimizing the 4G--5G Migration: A Simulation-Driven Roadmap for Emerging Markets
Desire Guel and Justin Pegd-Windé Kouraogo and Kouka Kouakou Nakoulma
Deploying fifth-generation (5G) networks in emerging markets demands a balance between performance targets and constraints in budget, spectrum, and infrastructure. We use MATLAB simulations to quantify how radio and architectural levers - MIMO (beamforming, diversity, spatial multiplexing), carrier aggregation (CA), targeted spectrum refarming(...)
5G migration, emerging markets, MIMO, carrier aggregation, spectrum refarming, mmWave, NSA/SA, D2D, M2M
ARTICLE
Privacy-Preserving Android Malware Detection Using Deep Federated Learning
Rehanatou B. Coulibaly, Tegawende Bissyande, Aminata Sabané, Sabané Aminata, Abdoul Kader Kaboré
This work represents a major breakthrough in the fields of legal Technology, digital governance and mobile cybersecurity. Malware attacks on Android are increasing daily at a considerable volume, making Android users more vulnerable to cyberattacks. In response to this growing threat, researchers have developed numerous machine learning and de(...)
Android (operating system), Malware, Federated learning, Server, Mobile device
COMMUNICATION
AI4DVault: A Registry Architecture for Securing the AI4D Supply Chain
Aminata Sabane, Tegawendé F. Bissyande
As artificial intelligence for development initiatives expand, ensuring secure and transparent supply chains for AI artifacts has become a critical challenge in emerging countries. Recent incidents of malicious models on repositories like Hugging Face demonstrate that machine learning model platforms are increasingly vulnerable to the same sup(...)
AI4D , AI artifacts , supply chain
ARTICLE
CallNavi, A challenge and empirical study on LLM function calling and routing
Yewei Song, Xunzhu Tang, Cedric Lothritz, Saad Ezzini, Jacques Klein, Tegawendé Bissyande, Andrey Boytsov, Ulrick Ble, Anne Goujon
API-driven chatbot systems are increasingly integral to software engineering applications, yet their effectiveness hinges on accurately generating and executing API calls. This is particularly challenging in scenarios requiring multi-step interactions with complex parameterization and nested API dependencies. Addressing these challenges, this(...)
challenge
COMMUNICATION
BF-WeakWeb-2025: A Novel Dataset and LLM Benchmark for Web Vulnerability Detection in Burkina Faso
Nana Sidwendluian Romaric and Bassolé Didier and Guel Désiré and Sié Oumarou
In a context of increasing digitalisation of administrative processes, cybersecurity has become a strategic issue for states, particularly Burkina Faso. Unfortunately, there is a lack of research into cybersecurity in Burkina Faso. In this article, we present an approach for identifying vulnerabilities in applications and websites from Burkina(...)
Knowledge engineering, Analytical models, Large language models, Cyberspace, Benchmark testing, Aging, Software, Data models, Communications technology, Computer security, OWASP Top 10, Web vulnerablity scanners, Fine-tuning, Large Language Model, Web application attacks
COMMUNICATION
Private Key Fragments Secure Recovery Approach in Passkeys System Based on Blockchain Technology and Error-Correcting Codes
Assane Ilboudo Didier Bassole and Desire Guel
In this paper, we propose an innovative approach to enhance the security and resilience of passkeys. this approach combines Shamir’s Secret Sharing Scheme, Reed–Solomon error-correcting codes, AES-GCM encryption, and decentralized storage systems such as blockchain and IPFS. In this approach, the adopted methodology is structured around three(...)
Solid modeling, Scalability, Computational modeling, Resists, Robustness, Error correction codes, Blockchains, Encryption, Secure storage, Resilience, Passkey System, Blockchain, Error-Correcting Codes, Security
ARTICLE
Big data analytics in healthcare: machine learning-based cardiac disease prediction in West Africa
Amédée W. DERA, Ferdinand T. GUINKO
This paper investigates the application of machine learning for cardiac disease prediction in resource constrained healthcare settings. This study conducts an empirical study evaluating four classification algorithms (Support Vector Machine, Random Forest, Logistic Regression, Decision Tree) on a real-world dataset. The results demonstrate tha(...)
Big Data Analytics, Data-driven healthcare, Data analytics in healthcare, Machine Learning in Healthcare, Disease Prediction
ARTICLE
Optimization and comparison of Deep Learning architectures for multi class classification of DDoS attacks in enterprise networks
Yacouba OUATTARA, Yaya TRAORE and Yves SAVADOGO
This article presents an in-depth study aimed at optimizing and comparing several deep learning architectures for multi-class classification of DDoS attacks in enterprise
networks, using the CIC-DDoS2019 dataset. The methodological approach includes rigorous data preprocessing (normalization, encoding, balancing, stratified split) as well as(...)
DDoS, intrusion detection, multi- class classification, Deep Learning, CNN-1D, CNN-LSTM, CNN-BiLSTM, CIC-DDoS2019.
ARTICLE
African digital health strategic plans analysis: key weaknesses in contextualization, intervention focus, and technological foresight
Bry Sylla; Ansiouonèkou Pascal Somda; Jean Noel Nikiema; Leon Gueswende Blaise Savadogo; Gayo Diallo; Nicolas Meda
Digital health strategies are increasingly being adopted in Africa, but their consistency with best practice planning is poorly documented. 54 countries were screened; 48 had a plan in the Global Digital Health Monitor, and 11 recent plans met the inclusion criteria. Using the “Ready, Extract, Analyze, Distill” methodology and a customized gri(...)
Health policy, Public health, Digital health
COMMUNICATION
A Metamodel for Simplifying Infrastructure Deployment Using Vagrant
Flavien Hervé Somda; Arnold Stéphane Kabore; Boureima Zerbo
We propose a metamodel–driven framework that replaces hand-written Ruby Vagrantfiles with validated EMF models capturing core Vagrant concepts (virtual machines, providers, networks, shares, plugins) and provisioners including Shell, Puppet, and Ansible. The framework raises the level of abstraction by allowing users to specify infrastructures(...)
Metamodeling , Infrastructure as Code , Vagrant , Virtualization , Code Generation , DevOps
ARTICLE
Deep learning models for binary ddos attack detection in enterprise environments
Yacouba OUATTARA Yaya TRAORE Yves SAVADOGO
This paper proposes an experimental methodology
based on the comparison of several deep learning models for the
detection of distributed denial of service (DDoS) attacks in
enterprise network environments. The CIC-DDoS2019 dataset,
recognized for the richness and realism of its attack scenarios,
served as a basis for the preparation, trai(...)
Cybersecurity, Deep Learning, Binary Classification, Intrusion Detection System (IDS), DDoS, CIC- DDoS2019 dataset