Papers by Sadouanouan Malo
Cause-of-death Certification in Africa: Analysis of a Model Implemented at the Teaching Hospital of Souro Sanou of Bobo-Dioulasso (Burkina Faso)
Studies in health technology and informatics, 2014
INTRODUCTION In Africa, mortality statistics are not reliable due to the low performance of the d... more INTRODUCTION In Africa, mortality statistics are not reliable due to the low performance of the death registering systems. Our aim is to implement an efficient system. In this article we make a comparison between the existing system model and the new system that will be set up. METHOD UML has been used as the modeling language based on the 2TUP analysis methods. RESULTS the new system for registering deaths and their causes was conceived and represented through activities, utilization cases and data model diagrams. DISCUSSION We have developed a tool for death registration taking into account African hospitals characteristics. The progressive deployment of this system at the CHUSS of Bobo-Dioulasso enables users and actors to appropriate it.
Extraction of Relevant Data from Social Media Based on Termino-Ontological Resources: Application to Meningitis Surveillance via Twitter
Innovations and Interdisciplinary Solutions for Underserved Areas, 2020
In this paper, we present a process for collecting and filtering relevant data for epidemiologica... more In this paper, we present a process for collecting and filtering relevant data for epidemiological surveillance of meningitis. We focus on the African meningitis belt stretching from Senegal to Ethiopia. This study aims to fill the data gap for the early detection of epidemics based on the analysis of social media. Our approach is based on previous work that showed that social media analysis contributes significantly to the surveillance of epidemics. It uses IDOMEN (Infectious Disease Ontology for MENingitis) a meningitis domain ontology and a SKOS resource meningVocab (meningitis vocabulary). IDOMEN is an extension of the Infectious Disease Ontology (IDO). The SKOS resource meningVocab is built from a corpus of meningitis tweets from social media. We align the IDOMEN ontology and the SKOS resource meningVocab for collection and filtering tweets containing data relevant to meningitis in a perspective of epidemiological surveillance. Tweets are collected via the Twitter API on the basis of a list of terms related to meningitis. They are then annotated using these two resources and filtered using the rules of the domain (for example, the rules characterizing situations suggestive of bacterial meningitis: fever AND purpura AND headache).
Implementation of E-health in Burkina Faso: A Status Report
Intelligent Sustainable Systems, 2022
An AI-based approach to the prediction of water points quality indicators for schistosomiasis prevention
2022 IEEE Multi-conference on Natural and Engineering Sciences for Sahel's Sustainable Development (MNE3SD), 2022
![Research paper thumbnail of Discovering frequent patterns guided by an ontology [Découverte de motifs fréquents guidée par une ontologie]](https://attachments.academia-assets.com/84488543/thumbnails/1.jpg)
ARIMA, 2016
L'extraction des motifs fréquents en fouille de données génère une quantité énorme de motifs fréq... more L'extraction des motifs fréquents en fouille de données génère une quantité énorme de motifs fréquents et requiert par conséquent la mise en place d'un post-traitement efficace afin de cibler les motifs fréquents les plus utiles. Cet article propose une approche de découverte de motifs fréquents utiles qui intègre les connaissances décrites par l'expert et représentées dans une ontologie associée aux données. L'approche utilise l'ontologie pour bénéficier de plus d'informations structurées afin d'éliminer certains motifs fréquents de l'analyse. Les expérimentations réalisées avec notre approche donnent des résultats satisfaisants. ABSTRACT. The frequent pattern mining generates a huge amount of patterns and therefore requires the establishment of an effective post-treatment to target the most useful. This paper proposes an approach to discover the useful frequent patterns that integrates knowledge described by the expert and represented in an ontology associated with the data. The approach uses the ontology for benefit from more structured information to remove some frequent patterns of the analysis. The experiments realized with our approach give satisfactory results.
International Journal of Advanced Computer Science and Applications, 2019
During these last few years, the problem of multilabel classification (ML) has been studied in se... more During these last few years, the problem of multilabel classification (ML) has been studied in several domains, such as text categorization. Multi-label classification is a main challenging task because each instance can be assigned to multiple classes simultaneously. This paper studies the problem of Multi-label classification in the context of web pages categorization. The categories are defined in an ontology. Among the weakness of the multi-label classification methods, exist the number of positive and negative examples used to build the training dataset of a specific label. So the challenge comes from the huge number of labels combinations that grows exponentially. In this paper, we present an ontology-based Multilabel classification which exploit dependence between the labels. In addition, our approach uses the ontology to take into account relationships between labels and to give the selection of positive and negative examples in the learning phase. In the prediction phase, if a label is not predicted, the ontology is used to prune the set of descendant labels. The results of experimental evaluation show the effectiveness of our approaches.
Extraction of events and qualitative data from texts for the monitoring of infectious diseases: case of meningitis and COVID-19
2021 16th Iberian Conference on Information Systems and Technologies (CISTI), 2021
For decades, infectious diseases have been claiming many victims around the world. Even today, de... more For decades, infectious diseases have been claiming many victims around the world. Even today, despite technology and scientific advances, these diseases are still topical, evolving in the form of outbreaks that wreak havoc and take doctors and public health professionals by surprise. Discovered and treated in time can prevent possible epidemics or pandemics. One way of doing this is to make the many resources that are shared via the internet speak for themselves. This will consist of intelligently processing this massive resource of information, while taking into account the complexity linked to the fact that this information may be in various formats, sometimes described as non-standard, thus limiting the application of NLP techniques. In this document, we present our work which consists in extracting events and qualitative data from the text for the monitoring of infectious diseases. The extraction process will be based on Machine Learning techniques and guided by a domain ontology. Given the number of infectious diseases we will focus our study-on meningitis and COVID.
An Agent-Based Study of the Impact of Sensitization on the Spread of Covid 19 in Burkina Faso
Proceedings of the Future Technologies Conference (FTC) 2020, Volume 1
Emerging infectious diseases, such as severe acute respiratory syndrome (SARS), pose a major thre... more Emerging infectious diseases, such as severe acute respiratory syndrome (SARS), pose a major threat to public health. Despite intense research efforts on how, when and where these new diseases appear, they are still a source of considerable uncertainty. An outbreak of a new coronavirus, severe acute respiratory syndrome coronavirus 2 (SARS - CoV - 2), appeared in late December 2019 in the city of Wuhan, Hubei province in China and caused an atypical pneumonia called coronavirus 2019 (COVID - 19). On March 11, 2020, the World Health Organization officially declared that Covid-19 is a pandemic. As of April 15, 2020, at least 1,975 cases had been reported since the appearance of the first case on March 09, 2020. We have studied in this paper the dynamics of the spread of the pandemic in Burkina Faso as well as the cures when a good policy of awareness is put in place by the government. We use an agent-based approach. In this paper we are interested in the dynamics of propagation of the pandemic in Burkina Faso as well as the cures when a good awareness policy is implemented by the government. We use an agent-based approach. Awareness is simulated by the dissemination of information in a contact network. The results obtained show that the structure of contact networks has an influence on the information diffusion. As part of Covid-19, simulations show that awareness-raising contributes enormously to stopping the chain of contamination and death.
Approche de découverte de nouvelles catégories dans un wiki sémantique basée sur les motifs fréquents
Journées Francophones d'Ingénierie des Connaissances, 2015
In Africa, mortality statistics are not reliable due to the low performance of the death register... more In Africa, mortality statistics are not reliable due to the low performance of the death registering systems. Our aim is to implement an efficient system. In this article we make a comparison between the existing system model and the new system that will be set up. UML has been used as the modeling language based on the 2TUP analysis methods. the new system for registering deaths and their causes was conceived and represented through activities, utilization cases and data model diagrams. We have developed a tool for death registration taking into account African hospitals characteristics. The progressive deployment of this system at the CHUSS of Bobo-Dioulasso enables users and actors to appropriate it.
Fuzzy logic approach for knowledge modeling in an Ontology: A review
2020 IEEE 2nd International Conference on Smart Cities and Communities (SCCIC), 2020
Fuzzy logic is an extension of Boolean logic created by Lotfi Zadeh in 1965 based on his mathemat... more Fuzzy logic is an extension of Boolean logic created by Lotfi Zadeh in 1965 based on his mathematical theory of fuzzy sets, which is a generalization of classical set theory. By introducing the notion of degree or possibility, fuzzy logic confers very appreciable flexibility to the reasoning, which uses it, which makes it possible to take into account imprecision and uncertainties. Despite a beginning of reluctance and even rejection of the theory of fuzzy logic, it has been used in many fields. Today, its usefulness and its reputation are no longer to be demonstrated because more than 50 years after its appearance, it has been well adopted by engineers and part of the scientific world. In this paper, we present a state of the art on fuzzy logic and its use in the field of knowledge representation and more specifically in ontology modeling using OWL and SWRL.
Cashew Trees Detection And Yield Analysis Using UAV-Based Map
2021 16th Iberian Conference on Information Systems and Technologies (CISTI), 2021
In this study we developed a novel method to detect cashew trees in an orthophoto map derived fro... more In this study we developed a novel method to detect cashew trees in an orthophoto map derived from images collected by an unmanned aerial vehicle (UAV). We also suggest a way in which these detections can be used to analyze the yield of the cashew farm. The proposed method uses image analysis to find the tops of trees, to merge different tops located on the same tree, and to segment individual tree. The segmented trees are used in a deep learning framework to know the exact location of cashew trees. The preliminary cashew detection from UAV-based map is promising. This study can be interesting for developing countries where UAV system are nowadays gaining popularity in agriculture. Our method does not require any additional sensor other than the RGB camera onboard the UAV. This low-cost solution is suitable for small and medium cashew farmers. The developed method can also be extended to other types of trees, other than the cashew.
Contribution à l'analyse d'ordonnançabilité des applications temps-réel multiprocesseurs
Les applications temps reel, le plus souvent dediees au controle de procede, sont soumises a des ... more Les applications temps reel, le plus souvent dediees au controle de procede, sont soumises a des contraintes temporelles strictes, destinees a garantir la securite et la coherence du procede controle. Les applications temps reel etant des applications multi tâches, elles doivent etre ordonnancees, le critere sine qua non de qualite de la strategie d'ordonnancement etant la garantie du respect des contraintes temporelles. Ces applications sont de plus en plus souvent deployees sur des architectures multiprocesseurs. Le probleme de l'ordonnancement doit donc etre pose dans ce contexte, ou de nombreux problemes doivent encore etre abordes. Notons tout d'abord que dans le cas multiprocesseur, il n'existe pas d'ordonnancement en ligne optimal dans le cas general, le probleme de l'ordonnancement est NP-complet, et des anomalies d'ordonnancement apparaissent meme lorsque l'on ne considere que des tâches independantes (une duree d'execution plus courte qu...
Semantic annotation of resources based on ontologies:application to a knowledge sharing platform on meningitis
2020 IEEE 2nd International Conference on Smart Cities and Communities (SCCIC), 2020
Semantic annotation of resources with ontologies plays a decisive role for semantic search, inter... more Semantic annotation of resources with ontologies plays a decisive role for semantic search, interoperability and data integration. In this paper, we focus on semi-automated web page annotation for a meningitis knowledge sharing platform. This web page annotation refers to the introduction of categories on a page or a set of tags on a page. Thus, we present a semantic web page annotation approach based on the use of an ontology. In this proposal, ontology is used to determine the categories on the web page. Our method extracts the relevant terms called keywords in the page to annotate. Our strategy for identifying the categories focus on ontology's concepts similarity with each keyword. The tags are identified among the keywords that are not mapped to the ontology's concepts. The results of simulation indicate the approach is feasible for practical use in semantic annotation of a new web page.
2018 IST-Africa Week Conference (IST-Africa), 2018
Although fish farming in Africa is developing in the last decade, it still has a big potential of... more Although fish farming in Africa is developing in the last decade, it still has a big potential of growth to meet the fish demand with growing population. One of the key parameters for a successful fish farm business is the water quality monitoring. Even though it is essential, it is often too expensive for African fish farmers to monitor their ponds. In the WAZIUP project, we deployed a low-cost and connected water monitoring system measuring pH, dissolved oxygen and temperature in a fish farm in Ghana. It has been collecting data since February 2017 and we present here the first conclusions of the water analysis and the impact it could have on fish farming. Based on these results, we aim to deploy several improved V2 prototypes in early 2018.
A Low-Cost IoT-Based Solution for an Integrated Farming Optimization in Nazi BONI University
An IoT-based solution for the improvement of the yield in a system of production in which one ass... more An IoT-based solution for the improvement of the yield in a system of production in which one associates vegetal and animal productions is related in this paper. We deployed a sensor network at the Research on Soil Fertility Laboratory (LERF) and at the Aquaculture and Aquatic Biodiversity Research Unit (UR-ABAQ) of Nazi BONI University. Through this network, we are able to check in real time and continue the pH, the dissolved oxygen and the water temperature of a hatchery of the UR-ABAQ. Also the soil moisture of banana, papaya, and maize is constantly checked, respectively, at UR-ABAQ and LERF sites. A weather station has been deployed to monitor the weather of these research units’ site. The equipment deployed is energy-efficient because of its solar panel and has a LoRa radio antenna for communication. The data collected is stored into a cloud platform by two gateways connected to the Internet via 3G MoDem and equipped with a LoRa antenna.
IDOMEN: An Extension of Infectious Disease Ontology for MENingitis
Studies in health technology and informatics, 2019
In sub-Saharan African countries the prevention and control of epidemic diseases requires the imp... more In sub-Saharan African countries the prevention and control of epidemic diseases requires the improvement of the surveillance system for these diseases. Biomedical ontologies are a growing field that can improve health information systems. Indeed biomedical ontologies allow semantic support, data integration, automated reasoning. We are building a meningitis ontology to assist filtering messages relevant to meningitis domain on social media in order to predict a possible epidemic. Indeed, the messages filtered are used for data and event extraction that serve as input for a meningitis surveillance system. In this paper we focused on the modeling and formalization of different perspectives of the meningitis disease such as biological perspective, clinical perspective, epidemiological and public health perspective. This paper presents the three modules in the global Infection Disease Ontology for Meningitis (IDOMEN) and at the end, we illustrate a case of reasoning with our ontology.
This paper concerns sets of periodic independent real-time tasks with hard deadlines, in a multip... more This paper concerns sets of periodic independent real-time tasks with hard deadlines, in a multiprocessor context. We address the cyclicity problem for global multiprocessor schedul- ing. Our aim is to prove the existence of a steady state after a transcient state in valid sched- ules. This could be helpfull for performing exact schedulability tests as well as for the sake of simulation. First, we underline the main differences between the uniprocessor and the multiprocessor cases. Then we consider the case of fixed-pri ority scheduling strategies, and finally, we extend our results to a wider class of scheduli ng algorithms. And finally, we present some amazing results as to the date of the begining of the steady state.
Architecture of a Platform on Sharing Endogenous Knowledge to Adapt to Climate Change
Approche de découverte de nouvelles catégories dans un wiki sémantique basée sur les motifs fréquents
Uploads
Papers by Sadouanouan Malo