Research Article
Predicting Conflict Zones in Kenya Using a Point Process Model
Carol Ogira*,
Roselynn Kamau,
Shallom Kamau,
Bridgette Kerubo Bwoma,
Bonaya Kiinywi Komora,
Henry Athiany
Issue:
Volume 10, Issue 1, February 2024
Pages:
1-10
Received:
5 January 2024
Accepted:
23 January 2024
Published:
5 February 2024
Abstract: In the past decade, Kenya has continued to experience high levels of conflict, which has affected the country in various ways. This study presents a method for analyzing and predicting conflict zones in Kenya using a Point Process Model. Data utilized in the analysis was obtained from the Armed Conflict Location & Event Data (ACLED) Project and Open Data for Africa. The focus was to develop a point process model, test its predictive capability, and predict conflict zones in Kenya for a specified period of time. The study highlights the framework of the model, focusing on the intensity, and effects of covariates such as population density and spatial coordinates. Spatial data analysis was carried out using the spatstat package of the R Statistical Software, mapping the distribution of the conflict events and further developing the model using the Berman-Turner algorithm. Parameter estimates required for the prediction were obtained from the algorithm. For the 18-year period considered (2004 - 2021), the number of conflict events increased significantly as the election period drew near, during and after the election period. Geographically, the Central and Western parts of Kenya exhibited greater intensity of conflict events, spreading to their surroundings. The spike in the number of conflict events during the electioneering period can be explained by the political differences seen in the country which fuel violence among citizens. Furthermore, population density played a major role in the high cases of conflict as is evident from the many cases of conflict recorded in Nairobi County. Other high cases of conflict during some years in the study period were associated with counties with pastoral communities, such as Mandera. Evaluating the trend of the past conflict events, the model prediction indicates that the capital city of Kenya (Nairobi) and its environs would be more prone to conflict during elections.
Abstract: In the past decade, Kenya has continued to experience high levels of conflict, which has affected the country in various ways. This study presents a method for analyzing and predicting conflict zones in Kenya using a Point Process Model. Data utilized in the analysis was obtained from the Armed Conflict Location & Event Data (ACLED) Project and Ope...
Show More
Research Article
Deep Convolutional Neural Networks with Augmentation for Chest X-Ray Classification
Hannah Kariuki*,
Samuel Mwalili,
Anthony Waititu
Issue:
Volume 10, Issue 1, February 2024
Pages:
11-19
Received:
23 October 2023
Accepted:
6 March 2024
Published:
19 March 2024
DOI:
10.11648/j.ijdsa.20241001.12
Downloads:
Views:
Abstract: The recent release of large amounts of Chest radiographs (CXR) has prompted the research of automated analysis of Chest X-rays to improve health care services. DCNNs are well suited for image classification because they can learn to extract features from images that are relevant to the task at hand. However, class imbalance is a common problem in chest X-ray imaging, where the number of samples for some disease category is much lower than the number of samples in other categories. This can occur as a result of rarity of some diseases being studied or the fact that only a subset of patients with a particular disease may undergo imaging. Class imbalance can make it difficult for Deep Convolutional Neural networks (DCNNs) to learn and make accurate predictions on the minority classes. Obtaining more data for minority groups is not feasible in medical research. Therefore, there is a need for a suitable method that can address class imbalance. To address class imbalance in DCNNs, this study proposes, Deep Convolutional Neural Networks with Augmentation. The results show that data augmentation can be applied to imbalanced dataset to increase the representation of the minority class by generating new images that are a slight variation of the original CXR images. This study further evaluates identifiability and consistency of the proposed model.
Abstract: The recent release of large amounts of Chest radiographs (CXR) has prompted the research of automated analysis of Chest X-rays to improve health care services. DCNNs are well suited for image classification because they can learn to extract features from images that are relevant to the task at hand. However, class imbalance is a common problem in c...
Show More
