ERIC NZIYUMVA

ERIC NZIYUMVA

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 March 2022 in Computers and Education: Artificial Intelligence
Verified
Journal Article
Open access
Jovial NiyogisubizoJovial Niyogisubizo
Jovial Niyogisubizo
LLLyuchao Liao
Lyuchao Liao
ERIC NZIYUMVAERIC NZIYUMVA
ERIC NZIYUMVA
EMEvariste Murwanashyaka
Evariste Murwanashyaka
PNPierre Claver Nshimyumukiza
Pierre Claver Nshimyumukiza

4 March 2023 in International Journal of Intelligent Transportation Systems Research
Verified
Journal Article
Closed access
PDF file
Jovial NiyogisubizoJovial Niyogisubizo
Jovial Niyogisubizo
LLLyuchao Liao
Lyuchao Liao
QSQi Sun
Qi Sun
ERIC NZIYUMVAERIC NZIYUMVA
ERIC NZIYUMVA
YWYongqiang Wang
Yongqiang Wang
EMEvariste Murwanashyaka
Evariste Murwanashyaka

30 January 2023 in Intelligent Data Analysis: An International Journal
Verified
Journal Article
Closed access
PDF file
JNJovial Niyogisubizo
Jovial Niyogisubizo
LLLyuchao Liao
Lyuchao Liao
FZFumin Zou
Fumin Zou
GHGuangjie Han
Guangjie Han
ERIC NZIYUMVAERIC NZIYUMVA
ERIC NZIYUMVA
YLYuyuan Lin
Yuyuan Lin
Accident severity prediction is a hot topic of research aimed at ensuring road safety as well as taking precautionary measures for anticipated future road crashes. In the past decades, both classical statistical methods and machine learning algorithms have been used to predict traffic crash severity. However, most of these models suffer from several drawbacks including low accuracy, and lack of interpretability for people. To address these issues, this paper proposed a hybrid of Balanced Bagging Classification (BBC) and Light Gradient Boosting Machine (LGBM) to improve the accuracy of crash severity prediction and eliminate the issues of bias and variance. To the best of the author’s knowledge, this is one of the pioneer studies which explores the application of BBC-LGBM to predict traffic crash severity. On the accident dataset of Great Britain (UK) from 2013 to 2019, the proposed model has demonstrated better performance when compared with other models such as Gaussian Naïve Bayes (GNB), Support vector machines (SVM), and Random Forest (RF). More specifically, the proposed model managed to achieve better performance among all metrics for the testing dataset (accuracy = 77.7%, precision = 75%, recall = 73%, F1-Score = 68%). Moreover, permutation importance is used to interpret the results and analyze the importance of each factor influencing crash severity. The accuracy-enhanced model is significant to several stakeholders including drivers for early alarm and government departments, insurance companies, and even hospitals for the services concerned about human lives and property damage in road crashes.

17 December 2021
Verified
Conference Paper
Closed access
JNJovial Niyogisubizo
Jovial Niyogisubizo
LLLyuchao Liao
Lyuchao Liao
YLYuyuan Lin
Yuyuan Lin
LLLinsen Luo
Linsen Luo
ERIC NZIYUMVAERIC NZIYUMVA
ERIC NZIYUMVA
EMEvariste Murwanashyaka
Evariste Murwanashyaka
Crash injury severity prediction is a promising area of interest in traffic safety and management. Recently, machine learning approaches are becoming popular due to their ability to enhance the prediction performance through the bias-variance trade-off-technique. However, some of these methods are criticized to perform like a ‘black box’ approach while predicting and analyzing crash injury severity and produce low accuracy. In this study, we propose a novel stacking framework based on a hybrid of Gradient Boosting (GB), Adaptive Boosting (AdaBoost), and Multilayer Perceptron (MLP) to predict accurately crash injury severity. On the traffic collision dataset provided by the Seattle City Department of Transportation from 2004 to 2021, the proposed model has demonstrated superior performance when compared with the base models. Furthermore, SHAP (SHapley Additive exPlanation) is used to interpret the contribution of every feature on model performance and provide recommendations to responsible authorities.


1 January 2022 in SSRN Electronic Journal
Verified
Preprint
Open access
PDF file
ERIC NZIYUMVAERIC NZIYUMVA
ERIC NZIYUMVA
RHRong Hu
Rong Hu
YXYong Xu
Yong Xu
Jovial NiyogisubizoJovial Niyogisubizo
Jovial Niyogisubizo
ZLZuoyong Li
Zuoyong Li
PNPierre Claver Nshimyumukiza
Pierre Claver Nshimyumukiza
Predicting solar radiance is an essential requirement for the authentic planning and efficient design of solar power systems. Machine learning models have been used to improve forecasting accuracy through the bias-variance trade-off technique. However, the accuracy of solar radiation cannot often fulfill our desired result due to natural weather intermittent affecting solar energy sources. This paper proposes a novel computational framework based on a stacked generalization approach to enhance the prediction performance of solar radiation. The proposed framework unifies three models, specifically, light gradient boosting machine (LGBM), gradient boosting (GB), and multilayer perceptron (MLP). The working principle of the stacked LGBM-GB-MLP model consists of aggregating the prediction of LGBM and GB to generate the final predictions using the MLP network. Several experiments to validate the performance of this model are carried out using the dataset provided by the National Aeronautics and Space Administration. The results prove the potential of the proposed approach compared with the existing benchmarks such as LGBM, GB, and MLP under the same conditions. This paper contributes mainly to the development of effective stacking ensemble-based algorithm to minimize the negative impacts of inaccurate solar radiation forecasting. Additionally, the utilization of solar energy under proper forecasting conditions is maximized which leads to the global warming issue handling.