Mebrahatom Yihdego

Mr. Mebrahatom Yihdego

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.

10 November 2026 in Discover Artificial Intelligence
Verified
Journal Article
Open access
PDF file
Mebrahatom YihdegoMebrahatom Yihdego
Mebrahatom Yihdego
AAAbrham Mamu Abebe
Abrham Mamu Abebe
GGGebrekiros Gebreyesus Gebremariam
Gebrekiros Gebreyesus Gebremariam
YNYemane Hailay Nega
Yemane Hailay Nega
HBHailemariam Brhane Bitew
Hailemariam Brhane Bitew
AAAbrha Tareke Araya
Abrha Tareke Araya
Transformers have evolved from a sequence-to-sequence architecture for machine translation into a general computational framework underlying large language, vision, speech, multimodal, scientific, and decision-making systems. This critical narrative review synthesizes the field along four connected axes: architectural evolution and attention efficiency; neural scaling laws across parameters, data, compute, and inference-time computation; mechanisms and evaluation debates surrounding in-context learning and emergent reasoning; and the expansion of Transformer systems across modalities and application domains. We move beyond a paper-by-paper chronology by comparing architectural choices under explicit constraints of context length, memory bandwidth, training compute, inference latency, data availability, and task structure. Particular attention is given to sparse and IO-aware attention, multi-query and grouped-query attention, mixture-of-experts routing, multimodal integration, and Transformer–state-space hybrids. We reconcile the Kaplan and Chinchilla scaling formulations with later replication and inference-aware analyses, and distinguish training-time scaling from test-time compute scaling. For in-context learning, we synthesize evidence concerning induction heads, implicit task inference, pre-training data composition, and the debate over metric-dependent emergence. The review also broadens application coverage to speech and audio processing, UAVs and autonomous systems, cybersecurity and intrusion detection, communications and networking, and time-series forecasting, in addition to scientific discovery, software engineering, healthcare, and education. Quantitative comparison tables are restricted to studies reporting results on common datasets and metrics, while explicitly noting differences in training protocols and computational budgets. We conclude that progress is increasingly determined not by parameter count alone, but by joint optimization of architecture, data quality, inference compute, hardware efficiency, and deployment constraints.

27 September 2025
Verified
Dataset
Closed access
DWDawit Teklu Weldeslasie
Dawit Teklu Weldeslasie
Mebrahatom YihdegoMebrahatom Yihdego
Mebrahatom Yihdego
AMAbrham Mamu
Abrham Mamu
KTKibrom Tekulu
Kibrom Tekulu

21 September 2025
Verified
Dataset
Closed access
TDTeklu Weldeslasie Dawit
Teklu Weldeslasie Dawit
Mebrahatom YihdegoMebrahatom Yihdego
Mebrahatom Yihdego
MAMamu Abebe Abrham
Mamu Abebe Abrham
Kbrom Tekulu DestaKbrom Tekulu Desta
Kbrom Tekulu Desta