Jovial Niyogisubizo

Jovial Niyogisubizo

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-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

21 May 2024 in Artificial Intelligence and Applications
Verified
Journal Article
Open access
PDF file
Jovial NiyogisubizoJovial Niyogisubizo
Jovial Niyogisubizo
JNJean de Dieu Ninteretse
Jean de Dieu Ninteretse
ENEric Nziyumva
Eric Nziyumva
MNMarc Nshimiyimana
Marc Nshimiyimana
EMEvariste Murwanashyaka
Evariste Murwanashyaka
EHErneste Habiyakare
Erneste Habiyakare
There is a growing concern among consumers and the wine industry regarding the quality of wine. Traditionally, wine experts determined its quality through tasting, which was time-consuming. Therefore, there is a need to predict wine quality based on specific key features to streamline these tasks. Technological developments like machine learning approaches have replaced human assessments with computational methods. However, some of these methods have faced criticism due to their low accuracy and lack of interpretability for humans. In this paper, a stacking ensemble method is introduced and demonstrates superior predictive performance when compared to other classification techniques like logistic regression, decision trees, gradient boosting, adaptive boosting (AdaBoost), and random forest. This evaluation is based on classification metrics such as accuracy, precision, recall, and F1-Score, all under the same conditions. Additionally, outlier detection algorithms were employed to identify exceptional or subpar wines, though their results did not match the accuracy of classification approaches. Lastly, a feature analysis study was conducted to assess the significance of each feature in the model’s performance. Received: 3 November 2023 | Revised: 21 February 2024 | Accepted: 28 April 2024 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available in UCI machine learning repository at https://archive.ics.uci.edu/ml/datasets/wine+quality. The technical details, code, and data can be accessed by visiting the link: https://github.com/jovialniyo93/red_wine_quality_prediction. Author Contribution Statement Jovial Niyogisubizo: Conceptualization, Methodology, Software, Validation, Formal analysis, Data curation, Writing - original draft, Writing - review & editing, Project administration. Jean de Dieu Ninteretse: Validation, Formal analysis, Writing - original draft, Writing - review & editing. Eric Nziyumva: Validation, Formal analysis, Resources, Writing - original draft, Writing - review & editing, Supervision. Marc Nshimiyimana: Validation, Formal analysis, Investigation, Writing - original draft, Writing - review & editing, Visualization. Evariste Murwanashyaka: Conceptualization, Methodology, Validation, Formal analysis, Investigation, Resources, Data curation, Writing - original draft, Writing - review & editing, Visualization, Supervision. Erneste Habiyakare: Validation, Formal analysis, Investigation, Resources, Writing - original draft, Writing - review & editing, Visualization, Supervision.

1 February 2025 in Journal of Computational Biology
Verified
Journal Article
Closed access
Jovial NiyogisubizoJovial Niyogisubizo
Jovial Niyogisubizo
KZKeliang Zhao
Keliang Zhao
JMJintao Meng
Jintao Meng
YPYi Pan
Yi Pan
RDRosiyadi Didi
Rosiyadi Didi
YWYanjie Wei
Yanjie Wei
Time-lapse microscopy imaging is a crucial technique in biomedical studies for observing cellular behavior over time, providing essential data on cell numbers, sizes, shapes, and interactions. Manual analysis of hundreds or thousands of cells is impractical, necessitating the development of automated cell segmentation approaches. Traditional image processing methods have made significant progress in this area, but the advent of deep learning methods, particularly those using U-Net-based networks, has further enhanced performance in medical and microscopy image segmentation. However, challenges remain, particularly in accurately segmenting touching cells in images with low signal-to-noise ratios. Existing methods often struggle with effectively integrating features across different levels of abstraction. This can lead to model confusion, particularly when important contextual information is lost or the features are not adequately distinguished. The challenge lies in appropriately combining these features to preserve critical details while ensuring robust and accurate segmentation. To address these issues, we propose a novel framework called RA-SE-ASPP-Net, which incorporates Residual Blocks, Attention Mechanism, Squeeze-and-Excitation connection, and Atrous Spatial Pyramid Pooling to achieve precise and robust cell segmentation. We evaluate our proposed architecture using an induced pluripotent stem cell reprogramming dataset, a challenging dataset that has received limited attention in this field. Additionally, we compare our model with different ablation experiments to demonstrate its robustness. The proposed architecture outperforms the baseline models in all evaluated metrics, providing the most accurate semantic segmentation results. Finally, we applied the watershed method to the semantic segmentation results to obtain precise segmentations with specific information for each cell.

Verified
Journal Article
Open access
PDF file
HWHao Wu
Hao Wu
Jovial NiyogisubizoJovial Niyogisubizo
Jovial Niyogisubizo
KZKeliang Zhao
Keliang Zhao
JMJintao Meng
Jintao Meng
WXWenhui Xi
Wenhui Xi
YWYanjie Wei
Yanjie Wei
The automatic detection of cells in microscopy image sequences is a significant task in biomedical research. However, routine microscopy images with cells, which are taken during the process whereby constant division and differentiation occur, are notoriously difficult to detect due to changes in their appearance and number. Recently, convolutional neural network (CNN)-based methods have made significant progress in cell detection and tracking. However, these approaches require many manually annotated data for fully supervised training, which is time-consuming and often requires professional researchers. To alleviate such tiresome and labor-intensive costs, we propose a novel weakly supervised learning cell detection and tracking framework that trains the deep neural network using incomplete initial labels. Our approach uses incomplete cell markers obtained from fluorescent images for initial training on the Induced Pluripotent Stem (iPS) cell dataset, which is rarely studied for cell detection and tracking. During training, the incomplete initial labels were updated iteratively by combining detection and tracking results to obtain a model with better robustness. Our method was evaluated using two fields of the iPS cell dataset, along with the cell detection accuracy (DET) evaluation metric from the Cell Tracking Challenge (CTC) initiative, and it achieved 0.862 and 0.924 DET, respectively. The transferability of the developed model was tested using the public dataset FluoN2DH-GOWT1, which was taken from CTC; this contains two datasets with reference annotations. We randomly removed parts of the annotations in each labeled data to simulate the initial annotations on the public dataset. After training the model on the two datasets, with labels that comprise 10% cell markers, the DET improved from 0.130 to 0.903 and 0.116 to 0.877. When trained with labels that comprise 60% cell markers, the performance was better than the model trained using the supervised learning method. This outcome indicates that the model’s performance improved as the quality of the labels used for training increased.

1 January 2024 in Engineering Perspective
Verified
Journal Article
Closed access
JNJean de Dieu Ninteretse
Jean de Dieu Ninteretse
Jovial NiyogisubizoJovial Niyogisubizo
Jovial Niyogisubizo
MNMarc Nshimiyimana
Marc Nshimiyimana
JSJean Claude SUGIRA
Jean Claude SUGIRA
ANALAIN NIYONGABO
ALAIN NIYONGABO
The application of Self-Compacting Concrete (SCC) in the construction industry has been adopted over the years and its quality over normal concrete has been influential. The high-rise construction demands emphasize the necessity of concrete pumping technology due to limited working space. Concrete made from manufactured sand was produced and the variation of free fall height based on the experiment of SCC was studied. This study assesses both the mechanical properties of SCC cast after free fall from various heights and its applications in the CFST columns. The study specifically focuses on a varied height of free fall at 6m, 6.5m, 7m, 7.5m, and 8m. The workability performance of this SCC, batched from manufactured sand has been evaluated, and slump extension between 500-600 mm was obtained. The concrete cubes and prism specimens were tested for compressive and splitting, therefore the associate strength was obtained. Testing both normal and SCC reveals unfavourable effects in strength reduction with an increase in free fall height. At the final height of 8m, an observed decrease in strength of about 15%-20% using SCC was observed. At 6.5m, there is a 3% decrease in strength, and the reduction in cube-splitting strength ranges from 7% to 11% with SCC from natural sand. When the free fall height is 7m, the cubic compressive strength is reduced by about 4.3-5.4%, and its cube-splitting strength at a height of 7m decreases by approximately 7–11%. Despite the gradual decrease noted in this study, the application of SCC obtained at 7m in CFST has demonstrated reliable results in terms of combined strength, suggesting its use in columns not exceeding the same height.