Charles Abdoulaye Ngom
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Charles Abdoulaye Ngom has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Alassane Bah
Ummisco-Sénégal
2 shared publications - Idy Diop
Cheikh Anta Diop University (UCAD)
2 shared publications - Mandicou Ba
Laboratoire dInformatique de Dakar (LID), Faculty of Science and Technology, University Cheikh Anta Diop of Dakar, Dakar, Senegal
2 shared publications - Etienne Delay
UMMISCO, Cheikh Anta Diop University
1 shared publication - Maboury Diao
Faculty of Medicine, Cheikh Anta Diop University, Dakar, Senegal;Cardiology Department, Aristide Le Dantec Hospital, Dakar, Senegal
1 shared publication - Pape Ibrahima Thiam
Cheikh Anta Diop University (UCAD), Polytechnic Higher School (ESP) Research Institute for Development (IRD), Unit of Mathematical Modeling and Computer Science of Complex Systems (UMI UMMISCO - UCAD), Senegal
1 shared publication
Latest Publications
- Open Access
- 12 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 60-68
Deep Learning-based Land Use and Land Cover Changes Detection from Satellite Imagery : a case study of the city of Richard Toll
In this paper, we propose the detection of land use and land cover changes from satellite imagery taken in Richard Toll. The Senegal River Valley, particularly the region encompassing Richard Toll, presents a significant research interest due to the prevalence of extensive agro-industrial activities. These activities induce profound alterations in the vegetative landscape, particularly evident upon their initiation or during expansion phases. Concurrently, these regions are obligated to reconcile the exigencies of pastoral sustainability. The identification of land use modifications through change detection in these areas is crucial for the prognostication and management of potential socio-environmental conflicts. Our approach is based on Deep Learning models applied to the analysis of satellite images, falling within the field of remote sensing where we automate the process of satellite images segmentation before tackling the generation of changes map. The methodology begins with the collection of geospatial-temporal data, 3-channel images taken at different points in time and in different spaces, of the area of interest via Google Earth Pro. The study region is divided into eight distinct classes, including cultivated fields, uncultivated fields, land, water, buildings, roads, football fields and vegetation. U-Net and FCN-8 deep learning architectures are used to achieve that goal by generating the segmented masks in order to highlight the changes areas by creating changes map during a post-process. We compare these two models and opt for the U-Net model, which offers the best performances.
- 12 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 60-68
Open AccessDeep Learning-based Land Use and Land Cover Changes Detection from Satellite Imagery : a case study of the city of Richard Toll
In this paper, we propose the detection of land use and land cover changes from satellite imagery taken in Richard Toll. The Senegal River Valley, particularly the region encompassing Richard Toll, presents a significant research interest due to the prevalence of extensive agro-industrial activities. These activities induce profound alterations in the vegetative landscape, particularly evident upon their initiation or during expansion phases. Concurrently, these regions are obligated to reconcile the exigencies of pastoral sustainability. The identification of land use modifications through change detection in these areas is crucial for the prognostication and management of potential socio-environmental conflicts. Our approach is based on Deep Learning models applied to the analysis of satellite images, falling within the field of remote sensing where we automate the process of satellite images segmentation before tackling the generation of changes map. The methodology begins with the collection of geospatial-temporal data, 3-channel images taken at different points in time and in different spaces, of the area of interest via Google Earth Pro. The study region is divided into eight distinct classes, including cultivated fields, uncultivated fields, land, water, buildings, roads, football fields and vegetation. U-Net and FCN-8 deep learning architectures are used to achieve that goal by generating the segmented masks in order to highlight the changes areas by creating changes map during a post-process. We compare these two models and opt for the U-Net model, which offers the best performances.
- 15 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-10
Data Generation Strategies for Enhanced Atrial Fibrillation Prediction in Pacemaker Patients
Atrial Fibrillation (AF) is a significant concern for patients with pacemakers, as it poses a heightened risk of cardiovascular complications, including strokes and limb ischemia. Accurate prediction of AF in this vulnerable population is crucial for early intervention and prevention of these serious outcomes. However, the scarcity of digitized and labeled electrocardiogram (ECG) data has presented a challenge for Deep Learning based prediction models. In this paper, we undertake a comprehensive exploration of innovative data generation strategies specifically tailored for pacemaker patients’ ECG data. Our study meticulously investigates conditional generation and standard augmentation techniques, systematically augmenting the dataset. Notably, the conditional DeepFake generation emerges as a standout technique, significantly improving data distribution, as evidenced by MMD = 8.10 −3 and MMD = 4.10 −4 . This augmentation approach yields data with acceptable FD, RMSE, and PRD scores when compared to a baseline. These compelling findings offer valuable insights into the enhancement of AF prediction in pacemaker wearers, underscoring the pivotal role of data augmentation in advancing cardiac risk assessment.
- 15 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-10
Data Generation Strategies for Enhanced Atrial Fibrillation Prediction in Pacemaker Patients
Atrial Fibrillation (AF) is a significant concern for patients with pacemakers, as it poses a heightened risk of cardiovascular complications, including strokes and limb ischemia. Accurate prediction of AF in this vulnerable population is crucial for early intervention and prevention of these serious outcomes. However, the scarcity of digitized and labeled electrocardiogram (ECG) data has presented a challenge for Deep Learning based prediction models. In this paper, we undertake a comprehensive exploration of innovative data generation strategies specifically tailored for pacemaker patients’ ECG data. Our study meticulously investigates conditional generation and standard augmentation techniques, systematically augmenting the dataset. Notably, the conditional DeepFake generation emerges as a standout technique, significantly improving data distribution, as evidenced by MMD = 8.10 −3 and MMD = 4.10 −4 . This augmentation approach yields data with acceptable FD, RMSE, and PRD scores when compared to a baseline. These compelling findings offer valuable insights into the enhancement of AF prediction in pacemaker wearers, underscoring the pivotal role of data augmentation in advancing cardiac risk assessment.