Browsing by Author "Kibirige, George William"

Now showing 1 - 3 of 3

Attacks in wireless sensor networks
(IGI Global, 2016) Kibirige, George William; Sanga, Camilius A.
Wireless Sensor Networks (WSN) consists of large number of low-cost, resource-constrained sensor nodes. The constraints of the WSN which make it to be vulnerable to attacks are based on their charac- teristics which include: low memory, low computation power, they are deployed in hostile area and left unattended, small range of communication capability and low energy capabilities. Examples of attacks which can occur in a WSN are sinkhole attack, selective forwarding attack and wormhole attack. One of the impacts of these attacks is that, one attack can be used to launch other attacks. This book chapter presents an exploration of the analysis of the existing solutions which are used to detect and identify passive and active attack in WSN. The analysis is based on advantages and limitations of the proposed solutions.
Influence of land-sea breeze on long-term PM2.5 prediction in central and southern Taiwan using composite neural network
(Research Square, 2022-09-08) Kibirige, George William; Huang, Chiao-Cheng; Liu, Chao-Lin; Chen, Meng-Chang
PM 2.5 prediction plays an important role for governments in establishing policies to control the emission of excessive atmospheric pollutants to protect the health of citizens. However, traditional machine learning methods that use data collected from ground- level monitoring stations have reached their limit with poor model generalization and insufficient data. We propose a composite neural network trained with aerosol optical depth (AOD) and weather data collected from satellites, as well as interpolated ocean wind features. We investigate the model outputs of different components of the composite neural network, concluding that the proposed composite neural network architecture yields significant improvements in overall performance compared to each component and the ensemble model benchmarks. The monthly analysis also demonstrates the overall superiority of the proposed architecture for the southern and central Taiwan stations in the months when land-sea breeze events frequently occur
Influence of land‐sea breeze On pm 2.5 prediction in central and Southern Taiwan using composite neural network
(Nature portfolio, 2023) Kibirige, George William; Huang, Chiao Cheng; Lin Liu, Chao; Chang Chen, Meng
PM 2.5 prediction plays an important role for governments in establishing policies to control the emission of excessive atmospheric pollutants to protect the health of citizens. However, traditional machine learning methods that use data collected from ground-level monitoring stations have reached their limit with poor model generalization and insufficient data. We propose a composite neural network trained with aerosol optical depth (AOD) and weather data collected from satellites, as well as interpolated ocean wind features. We investigate the model outputs of different components of the composite neural network, concluding that the proposed composite neural network architecture yields significant improvements in overall performance compared to each component and the ensemble model benchmarks. The monthly analysis also demonstrates the superiority of the proposed architecture for stations where land-sea breezes frequently occur in the southern and central Taiwan in the months when land-sea breeze dominates the accumulation of PM 2.5 .