A5037840642- Animal Disease Management and Epidemiology
- Vector-Borne Animal Diseases
- Species Distribution and Climate Change
- Ecology and Vegetation Dynamics Studies
- Viral Infections and Outbreaks Research
- Agriculture and Rural Development Research
- Zoonotic diseases and public health
- Viral Infections and Vectors
- Wildlife Ecology and Conservation
- Rangeland Management and Livestock Ecology
- Air Quality Monitoring and Forecasting
- Economic and Environmental Valuation
- Animal Diversity and Health Studies
- Statistical Methods and Inference
- Genetic and phenotypic traits in livestock
- Urban Agriculture and Sustainability
- T-cell and Retrovirus Studies
- Forest ecology and management
- Flood Risk Assessment and Management
- Viral Infections and Immunology Research
- Agricultural Systems and Practices
- Animal Behavior and Welfare Studies
- Disaster Management and Resilience
- African Botany and Ecology Studies
- Hydrological Forecasting Using AI
Université d'Abomey-Calavi
2021-2024
Université Evangélique en Afrique
2019-2022
University of Pretoria
2022
Abstract Random forests (RF) have been widely used to predict spatial variables. Several studies shown that cross-validation (CV) methods consistently cause RF yield larger prediction errors compared standard CV methods. This study examined the impact of species characteristics and data features on performance approaches for predicting abundance distribution. It 5-fold CV, design-based validation, three different methods, such as buffering, environmental blocking, blocking. Validation...
This paper analyzes active fires from 2001 to 2019 in and around the Luki Biosphere Reserve, western DR Congo assess fire risks.In this study, we used descriptive statistics events, Getis-Ord G hotspot analysis define spatial patterns presented by events.Diagnostics for spatiotemporal clustering of location space-time interaction were assessed K function.MODIS data revealed 4602 events 150,132 ha burned, corresponding 42.6% study area.The results show that peak was recorded 2013 are mostly...
The present study aimed to assess the typology, production management, and smallholder farmer-preferred traits in selecting indigenous goats three agro-ecological zones (AEZs) Democratic Republic of Congo (DR Congo). Based on a structured survey, baseline data were recorded 320 adults unrelated does from 202 goat farms. Hierarchical clustering principal components revealed clusters studied well distinguished by double triple kidding. Prolific mostly clustered into cluster two more...
Pig farming plays an important role in farmers’ livelihoods many tropical countries. It contributes to food security of the poorest as well development rural economy through multiplier effects. In South Kivu province, pig farms are almost exclusively owned by smallholders. A few studies have attempted describe thoroughly systems this province. This study was undertaken characterise production systems, order better understand their current situation, namely constraints they face and...
Background African swine fever (ASF) is an infectious viral disease of domestic pigs that presents as a hemorrhagic fever, and for which no effective vaccine available. The has serious negative social economic impact on pig keepers. There limited information the potential risk factors responsible spread ASF in South Kivu. Objective aim this study was to determine associated with infection suspected virus (ASFV)-infected pigs. Methods We sampled whole blood from 391 Additionally, 300 farmers...
Machine learning algorithms, especially random forests (RFs), have become an integrated part of the modern scientific methodology and represent efficient alternative to conventional parametric algorithms. This study aimed assess influence data features overdispersion on RF regression performance. We assessed effect types predictors (100, 75, 50, 20% continuous, 100% categorical), number (p = 816 24), sample size (N 250, 1250) parameter settings. also compared performance that classical...
This study was conducted to assess the prevalence of calf fetal wastage and its economic implications at ELAKAT slaughterhouse, Bukavu, Democratic Republic Congo (DR Congo) fill research gap in relationship with this thematic. The investigations took place from May September 2018.A cross-sectional survey carried slaughterhouse. For each visit, number cattle slaughtered, pregnant cows gestational ages (stage pregnancy dam, estimated by crown-rump length) fetuses were recorded.Out 1035...
Objectives : The current study aims at understanding the state of Meleagris gallopavo turkey husbandry in Idjwi island, DRC. It stands as a preliminary that contributes to improvement production by focusing on breeding management terms feeding, housing, reproduction and disease management. Methodology Results: A survey 150 farming households Island, was conducted collect data related techniques main constraints. Results revealed majority farmers are involved agriculture (67.07%), including...
Le maraîchage est actuellement un secteur où certaines pratiques d’agriculture moderne comme la culture pure et l’utilisation des produits de synthèse se développent, mais sont plus en questionnées. L’évaluation durabilité ces n’a pas encore fait l’objet d’études dans les régions montagneuses du Sud-Kivu, à l’Est République démocratique Congo. Pour y remédier, 368 unités production maraîchère choisies manière aléatoire stratifiée a été évaluée grâce l’outil « Indicateur » (IPDM). Les...
Aim: In recent studies, three species of bat, Hypsignathus monstrosus, Myonycteris torquata and Epomops franqueti were identified as the most likely candidates to be reservoir for Ebolavirus. To help in epidemic preparedness surveillance, distribution modeling techniques are useful predicting where these occur DR Congo. Methods: MaxEnt software was used model current future Congo based on occurrence data collected from global biodiversity information facility environmental covariates...
This study aimed to evaluate the performance of resampling strategies in ensemble tree ML algorithms such a s random forest and conditional inference forests modelling overdispersed outcomes, considering complexity relationship between predictors outcome, overdispersion level, predictor type sample size. We used simulated data case tick <i>(Rhipicephalus appendiculatus)</i> abundance on pastures. Results show that choice approach affects learning algorithms' performances...
Aim: In recent studies, three species of bat, Hypsignathus monstrosus, Myonycteris torquata and Epomops franqueti were identified as the most likely candidates to be reservoir for Ebolavirus. To help in epidemic preparedness surveillance, distribution modeling techniques are useful predicting where these occur DR Congo. Methods: MaxEnt software was used model current future Congo based on occurrence data collected from global biodiversity information facility environmental covariates...
African swine fever (ASF) is a contagious viral disease of worldwide. ASF in South Africa has for many years been confined to controlled area the northeast country that was proclaimed 1935. Since 2012, outbreaks are more likely occur historically ASF-free area. This study aimed analyse spatial and spatiotemporal structure between 1993 2018. Global space-time clustering investigated by Diggle K-function while Kulldorff's scan statistic applied detect local cluster outbreaks. Globally, exhibit...
Species distribution models have become tools of great importance in ecology since the advanced knowledge suitable habitat species is needed process world's biodiversity conservation. Models that use presence-only data are interests and widely used due to their easy access. However, these do not estimate accurately true spatial based solely on they account for biases induced by sampling techniques imperfect detection. To address this gap, Hierarchical integrated been recently introduced....