Abrham Mamu

Mr. Abrham Mamu

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
22 October 2025 in Discover Artificial Intelligence
Verified
Journal Article
Open access
PDF file
Dawit Teklu WeldeslasieDawit Teklu Weldeslasie
Dawit Teklu Weldeslasie
Mebrahatom YihdegoMebrahatom Yihdego
Mebrahatom Yihdego
Abrham MamuAbrham Mamu
Abrham Mamu
Kbrom Tekulu DestaKbrom Tekulu Desta
Kbrom Tekulu Desta
Early disease detection in crops remains an age-old problem in the quest for global food security. While deep learning has transformed image-based diagnosis, most existing models in maize leaf disease follow single-view approaches, offer limited validation, and neglect the accuracy-computational efficiency trade-off. In this regard, we suggest a robust framework to combat these issues with a heterogeneous stacking ensemble. Our suggested model combines four various convolutional neural networks DenseNet201, InceptionV3, NASNetMobile and VGG19 with a Vision Transformer. The model benefits from both local feature extraction and more global contextual analysis in trying to learn a more holistic representation of disease markers. We extensively evaluated this ensemble on a challenging dataset of 15,995 field images collected in Ethiopia and Kaggle dataset, utilizing stratified fivefold cross-validation for stable assessment. The model exhibited stable performance with a mean validation accuracy of 99.13% across validation folds a statistically significant improvement p < 0.05 over the best individual model, as assessed by a paired t-test. The ensemble recorded 99.15% accuracy on an independent test set, outperforming state-of-the-art lightweight models such as MobileNetV3 97.62%. The findings set a new baseline for maize leaf disease classification. The most important contribution of this work is the statistically validated excellence of the heterogeneous ensemble, along with transparent analysis of computational requirements and an extensive overfitting countermeasure. While the computational demands make this solution more amenable to server-side rather than edge device implementation, it is still incredibly reliable and generalizable as a diagnostic tool. A prototype was also developed and warmly received by users, further demonstrating its real-world applicability to drive data-driven sustainable agriculture.

23 December 2025 in Discover Applied Sciences
Verified
Journal Article
Open access
PDF file
Kbrom Tekulu DestaKbrom Tekulu Desta
Kbrom Tekulu Desta
Mebrahatom YihdegoMebrahatom Yihdego
Mebrahatom Yihdego
Abrham MamuAbrham Mamu
Abrham Mamu
GGGebrekiros Gebreyesus Gebremariam
Gebrekiros Gebreyesus Gebremariam
YNYemane Hailay Nega
Yemane Hailay Nega
The petroleum industry heavily relies on distillation as a key separation technique for product purification. However, controlling the petroleum distillation columns is challenging due to their highly nonlinear nature, interactions between variables, and operational disturbances. This study introduces a Model Reference Adaptive Controller (MRAC) utilizing the Lyapunov adaptation rule to overcome existing challenges. The MRAC is implemented on a decoupled model of a petroleum distillation column, and its effectiveness is evaluated against a traditional Proportional-Integral-Derivative (PID) controller. Simulation outcomes reveal that the MRAC outperforms the PID controller, exhibiting quicker response rates, minimized overshoot, and enhanced disturbance rejection capabilities. These findings suggest that the MRAC is a more efficient and robust control strategy for petroleum distillation column operations. For Liquefied petroleum gas (LPG) concentration, the MRAC improves rise time, settling time, and overshoot by 22.63%, 39.39%, and 34.23%, respectively, compared to the PID controller. Similarly, for gasoline concentration, improvements of 22.79%, 41.18%, and 40.26% are observed. Overall, MRAC outperforms PID controllers in stability and performance. When tested with a disturbance signal after settling time, MRAC demonstrates superior robustness and disturbance rejection capabilities.

26 September 2025 in Research Square
Verified
Preprint
Open access
PDF file
Kbrom Tekulu DestaKbrom Tekulu Desta
Kbrom Tekulu Desta
MMMebrahatom Yihdego Mekonen
Mebrahatom Yihdego Mekonen
Abrham MamuAbrham Mamu
Abrham Mamu
GGGebrekiros Gebreyesus Gebremariam
Gebrekiros Gebreyesus Gebremariam
YNYemane Hailay Nega
Yemane Hailay Nega
The petroleum industry heavily relies on distillation as a key separation technique for product purification. Distillation columns, which include components such as trays, reboilers, condensers, and reflux drums, are essential for achieving efficient separations. However, controlling these columns is challenging due to their highly nonlinear nature, interactions between variables, and operational disturbances. Traditional Proportional-Integral-Derivative (PID) controllers, while widely used, struggle with multiple inputs and outputs, lack adaptability, and fail to handle dynamic changes effectively. This study introduces a Model Reference Adaptive Controller (MRAC) utilizing the Lyapunov adaptation rule to overcome existing challenges. The MRAC is implemented on a decoupled model of a petroleum distillation column, and its effectiveness is evaluated against a traditional PID controller. Simulation outcomes reveal that the MRAC outperforms the PID controller, exhibiting quicker response rates, minimized overshoot, and enhanced disturbance rejection capabilities. These findings suggest that the MRAC is a more efficient and robust control strategy for petroleum distillation column operations. For Liquefied petroleum gas (LPG) concentration, the MRAC improves rise time, settling time, and overshoot by 22.63%, 39.39%, and 34.23%, respectively, compared to the PID controller. Similarly, for gasoline concentration, improvements of 22.79%, 41.18%, and 40.26% are observed. Overall, MRAC outperforms PID controllers in stability and performance. When tested with a disturbance signal after settling time, MRAC demonstrates superior robustness and disturbance rejection capabilities.