Publications (18)
ARTICLE
Hybrid Feature Selection with a Meta-learner for Explainable IoT Intrusion Detection
Alphonse Sanou, Moustapha Bikienga, Poulmanogo Illy, Frédéric Tounwendnyam Ouedraogo
The heterogeneity and resource constraints of IoT networks make intrusion detection complex. High dimensionality, significant class imbalance, and a lack of model interpretability challenge the deployment of effective IDS models. This paper proposes a hybrid feature selection framework driven by a supervised meta-learner that aggregates six co(...)
hybrid feature selection, meta-learner, explainable AI, IoT intrusion detection, intrusion detection, feature selection
ARTICLE
A Case Study on Hyperparameter Optimization Methods in Scholarship Eligibility Prediction Using Neural Networks
Aminata Bagre, Moustapha Bikienga, Tclesphore B. Tiendrebeogo
Predicting scholarship eligibility is a key issue for higher education establishments wishing to ensure the fair and efficient allocation of grants. This prediction relies on the exploitation of academic and social data integrated into Decision Support Systems (DSS).
hyperparameter optimization, Bayesian optimization, artificial neural networks, decision support system, student performance data
ARTICLE
Preliminary Result in the Detection of Four Varieties of Mangoes with YOLOv11: Amélie, Kent, Mangot vert, Brooks
Moustapha Bikienga, Sanguirè Pascal Somda, Safiatou Soré, Tounwendyam Frédéric Ouédraogo, Corneille Drabo
The automatic detection of mango varieties using YOLOv11 was explored in order to evaluate the performance of this deep learning model in an agricultural context in Burkina Faso. The study focused on four representative varieties: Brooks(Retard), Mangot vert, Amélie, and Kent. Average Precision (AP) was chosen as the main metric, since it comb(...)
mango, YOLOv11, object detection, Amélie, Kent, orchard monitoring, fruit classification, Burkina Faso
ARTICLE
Analysis of the performance of the detection of cassava leaf diseases using YOLO versioning
Safiatou Sore, Moustapha Bikienga, Frédéric Ouédraogo
Early detection of cassava leaf diseases is important for preserving agricultural yields in regions where this crop is an essential food source, particularly in Sub-Saharan Africa, where losses reach 20-30% due to diseases such as Cassava Mosaic Disease (CMD), Brown Streak Disease (CBSD), Green Mites (CGM), and Bacterial Blight (CBB). This stu(...)
cassava leaf disease, plant disease detection, YOLO, object detection, detection performance evaluation
ARTICLE
Trickle-E: Enhanced Trickle Timer with Residual Energy Consideration
Mahamadi Boulou, Moustapha Bikienga, Tiguiane Yélémou
Trickle Timer protocol is widely used in IoT networks to regulate message delivery by minimising redundant transmissions. However, its static approach to transmission parameters leads to inefficiencies in dynamic network environments. To address these limitations, we propose Trickle-E which is an adaptive enhancement to the Trickle Timer. Than(...)
Internet of Things, energy efficiency, residual energy, packet delivery ratio, latency reduction
ARTICLE
A New Stegano-Watermarking Scheme for the Creation of Medical Image Datasets
Boureima Koussoube, Moustapha Bikienga, Telesphore Tiendrebeogo, Cheick Yacouba Rachid Coulibaly
Digitisation of medical images is improving diagnosis and clinical research, but poses major challenges in terms of security and traceability. This paper proposes a hybrid solution combining digital watermarking and steganography to securely trace these images, while enabling automatic watermarking detection via adapted neural networks. We eva(...)
medical image watermarking, steganography, digital watermarking, medical image dataset, data traceability, data security, artificial neural networks, discrete wavelet transform, singular value decomposition, discrete cosine transform, imperceptibility, file size
ARTICLE
New Robust Watermarking Scheme for a Distributed Database with Hyperbolic Structure
Boureima Koussoube, Moustapha Bikienga, Telesphore Tiendrebeogo
In this paper we propose a new robust water-marking scheme for medical images stored in a distributed database with a hyperbolic structure. Our approach is to first generate a watermark from the patient information and the statistical parameters of the image. The watermark is then inserted into the image and fragmented before being distributed(...)
digital watermarking, medical image watermarking, distributed databases, hyperbolic structures, chaotic systems, robustness
ARTICLE
New Zero Watermarking Scheme Based on Hyper-catadioptric System Model and Hyperbolic Geometry
Boureima Koussoube, Moustapha Bikienga, Telesphore Tiendrebeogo, Armand Kodjo Atiampo, Boureima Zerbo
In this paper we propose a new digital watermarking scheme for securing DICOM images in a distributed database. This new technique introduces no distortion to the images and will serve as a means of authenticating them. The database has a hyperbolic structure and its model is based on the Poincaré disk model, in which a hyperbolic tree is buil(...)
digital watermarking, DICOM images, hyperbolic geometry, Poincaré disk model, hyperbolic tree, cryptographic signatures, image authentication, distributed image databases, watermark robustness
ARTICLE
New Medical Image Hybrid Watermarking
Boureima Koussoube, Moustapha Bikienga, Telesphore Tiendrebeogo
Digital watermarking is a mechanism for protecting digital documents as a complement to cryptography. Despite the many solutions proposed in the literature, to our knowledge there is no universal solution that can be applied everywhere. In this paper, we propose a new hybrid medical image watermarking approach that is based on two watermarks.(...)
medical image watermarking, hybrid watermarking, image signatures, Hu moments, co-occurrence matrix, image entropy, chaotic iteration, image encryption, image compression, image integrity, copyright protection
ARTICLE
Analysis, Design and Implementation of a Ripe Mango Detection Program in Burkina Faso
Moustapha Bikienga, Manegaouindé Roland Tougma, Soumaïla Ouedraogo
The analysis, concept, and implementation of a computer program capable of detecting ripe mangoes are at the core of this study. Traditional methods are often faced with calibration errors. Recently, deep learning has shown promising performance in visually guided agricultural applications. Faced with these constraints, it is necessary to esta(...)
YOLOv5, object detection, fruit counting, agricultural image analysis, Burkina Faso
ARTICLE
Study of the Rewiring Factor in an Unstructured P2P
Aminata Bagre, Moustapha Bikienga, Telesphore Tiendrebeogo
Social networking sites allow individuals to communicate and share information. Most of P2P systems assume that all peers cooperate for the benefit of the entire network. However, in practice, there is a significant portion of peers that extract resources from the system without contributing in return. Peer-to-peer applications can benefit fro(...)
peer-to-peer networks, friendship networks, selfish nodes, trust, cooperation, network topology, social networking sites
ARTICLE
Indexing And Searching Visual Content in a Data Lake Context
Safiatou Sore, Frédéric Ouédraogo, Yaya Traoré, Moustapha Bikienga
Nowadays, we are witnessing a steady increase in the number of available images, whether for experts or the general public, particularly in the age of Big Data, where data are distinguished by their volume, variety, authenticity and speed. Often, these vast databases contain numerous images, accompanied by texts and annotations more or less de(...)
image indexing, image search, data lakes, image database, color features, shape features, texture features, image similarity, big data
ARTICLE
An Architecture of a Data Lake for the Sharing, Agricultural Knowledge in Burkina Faso
Safiatou Sore, Yaya Traoré, Moustapha Bikienga, Frédéric Ouédraogo
With the advent of big data today, agricultural research institutes have stored enough data in databases at every level. This data contains a lot of knowledge that is often not well known by researchers and on the other hand, it may contain hidden semantic relationships. Therefore, it is important to find an adequate storage system for these d(...)
data lakes, agricultural data, data architecture, data sharing, agricultural knowledge, heterogeneous data storage, unstructured and semi-structured data, agricultural research institutions, Burkina Faso
ARTICLE
Design of a machine learning based model for academic performance prediction
Moustapha Bikienga, Ozias Bombiri, Emmanuel Sawadogo
Predicting and analyzing the performance of students is essential to design helpful guidance process that allows good success rates and raises the institution’s ranking as one of the criteria for a high-quality university. However the lack of adequate support and personalized guidance increases students failure rate. Nowadays, there are many r(...)
student performance prediction, student performance, university rankings, higher education
ARTICLE
Resources’s Optimisation in Pedagogical Activities Scheduling
Boureima Koussoube, Moustapha Bikienga, Telesphore Tiendrebeogo
The scheduling of pedagogical activities is a process that assigns a number of pedagogical activities to a limited set of resources and time slots, in accordance with a set of constraints. It is a complex and delicate task because it involves several educational activities and few resources, but also several constraints, some of which are cont(...)
resource optimization, time slot allocation, resource constraints