Browsing by Author "Drias, Yassine"

Now showing 1 - 7 of 7

AI-Driven Digital Soil Mapping: Leveraging Generative AI, Ensemble Learning and Geospatial Technologies for Data-Scarce Regions
(Springer Science and Business Media Deutschland GmbH, 2025) Drias, Yassine; Drias, Habiba; Belkadi, Widad Hassina; Cakar, Tuna; Abdelhamid, Zakaria; Bensemmane, Riad Yacine
This study presents a methodology for generating highresolution digital soil maps by integrating artificial intelligence (AI) with geospatial technologies. The research begins with comprehensive data collection and the extraction of relevant soil properties with the help of generative AI. To improve predictive accuracy, ensemble learning algorithms were employed due to their ability to capture complex relationships within soil characteristics. Additionally, a structured preprocessing pipeline was developed to refine and standardize the collected soil data, ensuring its suitability for modeling. The model's performance was evaluated using spatial cross-validation techniques to identify the most effective predictive approach. To validate the proposed methodology, experiments were conducted in northern Algeria, a region characterized by diverse landscapes ranging from arid zones to fertile plains. The results demonstrate the potential of AI-driven approaches to enhance soil mapping, particularly in regions where high-quality and up-to-date soil data are limited. This study underscores the efficacy of AI and geospatial technologies in advancing precision agriculture and land management.
İnternet Trafik Hızının Tahmininde Derin Öğrenme ve Ağaç Tabanlı Modellerin Karşılaştırılması
(Institute of Electrical and Electronics Engineers Inc., 2025) Filiz, Gozde; Altıntaş, Suat; Yıldız, Ayşenur; Kara, Erkan; Drias, Yassine; Çakar, Tuna
This study addresses the prediction of internet traffic speed using time-dependent data from an internet service provider through different modeling approaches. On an anonymized dataset, the performance of the moving average method, various deep learning models (N-BEATS, N-HITS, TimesNet, TSMixer, LSTM), and the XGBoost regression model enhanced with feature engineering was compared. Time series cross-validation and random hyperparameter search were used for model training. According to the results, the XGBoost model achieved the highest accuracy with 98.7% explained variance (R2), while among the deep learning models, N-BEATS and N-HITS achieved the best performance with R2 values around 90%. The findings indicate that tree-based methods supported by carefully selected features can offer higher accuracy and computational efficiency compared to complex deep learning models in internet traffic forecasting. © 2025 Elsevier B.V., All rights reserved.
Makine Öğrenimi ve Çok Boyutlu Anket Verileri Kullanılarak Öğrenci Başarısının Tahmini: Eğitim Programı Üzerine Bir Uygulama
(Institute of Electrical and Electronics Engineers Inc., 2025) Behsi, Zeynep; Dereli, Serhan; Çakar, Tuna ; Patel, Jay Nimish; Cicek, Gultekin; Drias, Yassine
This study develops a machine learning model integrating survey data and performance metrics to predict student success in the UpSchool education program. Students' personality traits assessed by DISC analysis, financial management, social, and emotional skills were clustered into "Successful,""Unsuccessful,"and "Moderately Successful"groups using K-means clustering. The SMOTE technique addressed data imbalance issues, and algorithms such as Logistic Regression, Random Forest, LightGBM, and AdaBoost were tested. After hyperparameter optimization, AdaBoost and LightGBM achieved the highest predictive performance. Results demonstrated the effectiveness of machine learning models in forecasting student success in educational programs. Future studies are recommended to enhance model performance through expanded datasets and to validate the model's applicability across diverse educational contexts. © 2025 Elsevier B.V., All rights reserved.
Methane Emissions Forecasting Using Hybrid Quantum-Classical Deep Learning Models: Case Study of North Africa
(Springer, 2025) Belkadi, Widad Hassina; Drias, Yassine; Drias, Habiba; Ferkous, Sarah; Khemissi, Maroua
This study explores climate change by predicting methane emissions in North Africa using classical and quantum deep learning methods. Using data from Sentinel-5P, we developed hybrid quantum-classical models, such as quantum long short-term memory (QLSTM) and quantum-gated recurrent unit networks (QGRUs), along with a novel hybrid architecture combining quantum convolutional neural networks (QCNNs) with LSTM and GRU, namely QCNN-LSTM and QCNN-GRU. The results show that these quantum models, especially the proposed hybrid architectures, outperform classical models by approximately seven percent in root-mean-squared error with fewer training epochs. These findings highlight the potential of quantum methodologies for enhancing environmental monitoring accuracy. Future research will aim to refine model performance, incorporate explainable AI techniques, and expand to forecasting other greenhouse gases, contributing to climate change mitigation efforts.
Quantum FP-Growth Algorithm Using GPU Simulation-Application to Digital Soil Mapping
(Elsevier, 2026) Belkadi, Widad Hassina; Drias, Yassine; Drias, Habiba
This study introduces a novel quantum version of the FP-growth algorithm for frequent itemset mining, leveraging the combined strengths of classical FP-growth and quantum machine learning. Key contributions include the theoretical and practical framework for Quantum FP-growth, along with a comprehensive analysis of its time and space complexity. We implemented Quantum FP-growth using IBM Qiskit and conducted a comparative evaluation of various quantum amplitude estimation (QAE) methods, including Canonical QAE, Faster QAE, Maximum Likelihood QAE, and Iterative QAE for support estimation. Our findings reveal that Iterative QAE surpasses the other methods in both accuracy and speed. Additionally, we explored the advantages of GPU simulation with IBM Qiskit and NVIDIA cuQuantum. Notably, this research marks the first application of a quantum frequent itemset mining algorithm to a real-world dataset in Digital Soil Mapping (DSM), pioneering the use of quantum technologies in soil science. This study underscores the potential of quantum computing to revolutionize data mining and promote sustainable soil management practices.
Toprak Özelliklerini ve İklim Değişikliğini Tahmin Etmek için Derin Öğrenme
(2025) Çelik, Nurçin; Drias, Yassine
Toprak, bitki büyümesi için gerekli olan temel besinleri, mineralleri ve elementleri sağlamakla kalmayıp aynı zamanda iklim düzenlemesinde ve daha geniş ekosistem işleyişinde hayati bir rol oynayan temel bir doğal kaynaktır. Bu yüksek lisans tezi, arazi örtüsü, topografya, iklim verileri ve diğer mekansal faktörler gibi temel çevresel değişkenleri entegre ederek Türkiye genelinde Dijital Toprak Haritalama (DSM) uygulamalarında modern Yapay Zeka (AI) metodolojilerinin uygulanmasını iyileştirmeyi amaçlamaktadır. Bu hedefe ulaşmak için, bu değişkenlere dayalı olarak toprak özelliklerini tahmin etme performanslarını değerlendirmek üzere yedi farklı makine öğrenimi modelinin karşılaştırmalı analizi yürütülmüştür.
Yapay Öğrenme Tabanlı Mikrofaktoring Skorlama Modeli ve Kredi Risk Yönetim Sistemi Geliştirilmesi
(Institute of Electrical and Electronics Engineers Inc., 2025) Sayar, Alperen; Ates, Yigit; Ertugrul, Seyit; Turan, Elif Naz; Drias, Yassine; Çakar, Tuna
Credit scoring systems are critical tools used by factoring institutions to assess the credit risks of SME businesses seeking microloans. This study presents a comprehensive predictive modeling framework that achieves 82.67% ROC-AUC with 65.34% Gini score on test data, demonstrating robust discriminative capability despite significant class imbalance. Our ensemble approach outperforms individual boosting models by leveraging their complementary strengths in payment behavior analysis and fraud detection. The raw data was cleaned, transformed, and optimized using the Polars library, with specialized features for detecting fraud patterns and time-based risk indicators. When implementing a score threshold of 950, our model significantly improves the detection of non-performing loans (NPL) compared to traditional rule-based approaches by reducing the net deficit from 6.59% to 2.62%. When applied to previously rejected applications, the model projects a potential 762.57% increase in transaction count and 747.05% growth in transaction volume. © 2025 Elsevier B.V., All rights reserved.