Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yousef Farhang has a total of 40 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Electric Vehicle Adoption Scenarios and Grid Electricity Requirements in Türkiye Through 2030

    by Yousef Farhang, Mehmet Akif Çifci, Hüseyin Çalık, Fazlı Yıldırım

    This study estimates how alternative electric vehicle (EV) adoption pathways translate into fleet stock and electricity requirements in Türkiye through 2030. The available sales record contains only 12 annual observations for 2014–2025, including sharp recent acceleration. This information is insufficient to establish the value of a high-capacity recurrent network. We therefore compare parsimonious extrapolations on a fixed 2022 origin and treat the previously reported LSTM-derived pathway solely as an unvalidated scenario input. Newly calculated linear-trend, drift, and last-increment benchmarks supplement persistence and the retained ARIMA evaluation. The last-increment rule and ARIMA have almost identical holdout RMSEs of 140,335 and 140,336 vehicles, respectively; all methods substantially underpredict 2023–2025 sales. Under the lower-adoption reference pathway, zero retirements, and explicit vehicle-use assumptions, the 2030 stock reaches 1,406,522 vehicles. Annualized grid-side energy is 3375.65 GWh, equivalent to 0.847% of the national demand reference; uniform within-year entry reduces the calendar-year estimate to 3125.55 GWh. The alternative ARIMA extrapolation yields 3,528,590 vehicles and 8468.62 GWh. Sensitivities examine adoption, mileage, efficiency, fleet composition, retirement, and charging timing. The contribution is a transparent conditional stock-to-energy assessment, not evidence of LSTM superiority or a validated national adoption forecast.

  • Open Access

    A Lightweight Hybrid Representation Learning Framework for Colorectal Lesion Classification in Colonoscopy Images

    by Mehmet Akif Cifci, Yousef Farhang

    Accurate colorectal lesion classification is important for computer-aided colonoscopy, yet many existing approaches require computationally intensive architectures. This study proposed and experimentally evaluated LHRF, which integrates BoVW encoding, SAE compression, TE-based metric refinement, optional HC augmentation, and FC-ResNet classification. Two configurations were investigated: LHRF-Core (BoVW → SAE → TE → FC-ResNet) and LHRF-HC, which additionally incorporates clustering-derived features. The experiments included three study-specific binary classification tasks constructed from CVC-ClinicDB, CVC-ColonDB, and a merged Kvasir/Kvasir-SEG collection. The CVC tasks used study-assigned sequence-level pathology categories, with sequence-grouped evaluation for CVC-ClinicDB and source-grouped evaluation for CVC-ColonDB. LHRF-HC achieved the highest accuracy on CVC-ClinicDB (96.24%, AUC 0.9741, MCC 0.9248), whereas LHRF-Core achieved the best results on CVC-ColonDB (95.88%, AUC 0.9698, MCC 0.9176) and Kvasir/Kvasir-SEG (98.74%, AUC 0.9908, MCC 0.9746). Five-fold cross-validation on CVC-ClinicDB yielded an accuracy of 97.43 ± 1.29%. Under matched experimental protocols, LHRF achieved higher classification accuracy than the evaluated lightweight baselines while requiring approximately 0.45–0.51 million trainable parameters. Measured post-decoding CPU throughput ranged from 351.67 to 2353.97 FPS, excluding image decoding and disk input/output. HC improved accuracy on CVC-ClinicDB but slightly reduced it on the other datasets, indicating a dataset-dependent contribution. The study also specified a gradient-based keypoint-attribution procedure, although its empirical faithfulness and clinical interpretability require further evaluation. Overall, the experimental findings highlight the potential of compact hybrid representation learning for colorectal lesion classification. Further evaluation using independently verified pathology annotations, patient-independent partitions, source-matched datasets, and external clinical collections would strengthen the assessment of robustness and clinical generalizability.

  • Open Access

    Weighting and Mileage Coding in Grouped Vehicle Emission Regression

    by Mehmet Akif Cifci, Yousef Farhang, Fazlı Yıldırım

    Weighting rules and mileage coding can change the apparent fit, uncertainty, and predictive performance of regression models built from grouped emission summaries. We examine these choices in a computational case study of 18 supplied age–mileage cells for carbon monoxide, non-methane hydrocarbons, and nitrogen oxides. Age-only, ordinal-mileage, and categorical-mileage specifications are compared using four weighting rules, cell deletion, robust regression, and cross-validation. Categorical mileage represents the lower middle-class means that ordinal coding cannot capture and improves prediction within the supplied grid, including when an entire age level is withheld. However, its advantage is conditional on the mean pattern and can reverse under a correctly specified ordinal model or contamination at the reference cell. Additional simulations with estimated cell dispersions show that interval coverage depends on covariance choice, contamination location, and model specification; small residual-based standard errors do not establish population precision. For practice, weights should reflect a stated estimation target, mileage coding should be checked against the observed shape, and fit should be assessed separately from prediction. The supplied counts sum to 1000, but their measurement lineage and disagreement with assignment frequencies remain unresolved. The findings therefore concern the computational behavior of supplied summaries and constructed scenarios, rather than causal effects or a verified vehicle population.

  • Wavelet-Enhanced Machine Learning Framework for Monthly Streamflow Prediction: A Comparative Assessment of Hybrid Models

    by Uğur Akbulut, Yousef Farhang, Mehmet Akif Cifci, Adem Özyavaş, Zafer Aslan, Kasım Koçak

    Accurate monthly streamflow prediction is essential for effective water-resource planning and basin-scale hydrological management. This study develops and evaluates a hybrid wavelet–machine learning framework for one-month-ahead streamflow prediction in the Karamandere Creek Basin, Türkiye. Multiresolution features derived from Discrete Wavelet Transform using Daubechies (db4) and Symlet (sym8) wavelets were integrated with five supervised learning algorithms, including Decision Tree, Linear Regression, Random Forest, Extra Trees, and Support Vector Regression. Daily streamflow, precipitation, and temperature observations collected from January 2005 to September 2020 were aggregated into 189 monthly records. After constructing the one-month lagged predictor and future streamflow target, the final supervised dataset consisted of 187 prediction cases. The cases were chronologically divided into 151 development observations and 36 independent test observations covering October 2017 to September 2020. Model development incorporated expanding-window walk-forward validation, while predictive performance was evaluated using the coefficient of determination (R²), root mean square error (RMSE), and mean absolute error (MAE). Across the independent test period, wavelet-derived representations improved predictive performance compared with corresponding raw-input configurations for all evaluated algorithms. Random Forest combined with sym8-derived features achieved the highest performance (R² = 0.92, RMSE = 1.72 m³/s, and MAE = 0.95 m³/s), followed by Extra Trees (R² = 0.91). Support Vector Regression exhibited the largest relative improvement, increasing its test R² from 0.65 with raw predictors to 0.88 with sym8-derived features. Although sym8-based representations provided better performance than db4 under the evaluated experimental conditions, this finding should be interpreted as evidence specific to the tested wavelet configurations rather than general superiority of the Symlet family. The results are limited by the single-basin application, relatively short monthly record, and absence of multi-site external validation. Further investigations using larger datasets, additional catchments, and broader wavelet comparisons are required to assess the transferability of the proposed framework.

  • Open Access

    Convergence bounds for fixed, adaptive, and stochastic gradient methods under Polyak–Łojasiewicz geometry

    by Yousef Farhang, Betül Öztel, Samet Yıldırım, Şaban Onur Viga, Mehmet Akif Cifci, Fazlı Yıldırım

  • Open Access

    Matematik tabanlı veri analizi ile özellik seçimi ve sınıflandırma: Akciğer kanseri evrelerinin belirlenmesi

    by Yousef Farhang, Betül Öztel, Gülfer Yildiz

    Arka Plan—Akciğer kanseri, dünya genelinde kansere bağlı ölümlerin önde gelen nedenlerinden biri olup, hastalığın prognozu büyük ölçüde tanı anındaki evreye bağlıdır. Erken evrede teşhis edilen vakalarda sağkalım oranları önemli ölçüde artarken, mevcut tanı yöntemleri akciğer adenokarsinomunun moleküler heterojenliğini yeterince yansıtamamaktadır. Yüksek kapasiteli dizileme teknolojilerindeki gelişmeler, genomik ve klinik verilerin entegrasyonunu mümkün kılarak kanser evreleme ve prognoz tahmini için yeni fırsatlar sunmaktadır. Bununla birlikte, çoklu veri kaynaklarını etkin biçimde birleştiren ve yüksek doğruluk ile yorumlanabilirlik sağlayan hesaplamalı yaklaşımlara olan ihtiyaç devam etmektedir.Amaç—Bu çalışmanın amacı, gen ekspresyon verileri ve klinik bilgileri kullanarak erken evre (Evre I–II) ve ileri evre (Evre III–IV) akciğer adenokarsinomu ayrımını gerçekleştiren bütünleşik bir hesaplamalı çerçeve geliştirmektir. Çalışma ile hem sınıflandırma performansının artırılması hem de hastalık progresyonuna ilişkin biyolojik olarak anlamlı çıkarımlar elde edilmesi hedeflenmektedir. Ayrıca, önerilen modelin klinik karar destek sistemlerine entegre edilerek erken teşhis ve tedavi planlamasına katkı sağlaması amaçlanmaktadır.Yöntem—Çalışmada, TCGA-LUAD veri setinden elde edilen 193 hastaya ait RNA-seq gen ekspresyon verileri ve klinik bilgiler kullanılmıştır. Önerilen yaklaşım; ANOVA tabanlı özellik seçimi ile ayırt edici genlerin belirlenmesini, protein-protein etkileşim (PPI) ağı analizi ile biyolojik yapıların incelenmesini ve Cox orantılı Hazard modeli ile sağkalım analizinin gerçekleştirilmesini içermektedir. Ardından lojistik regresyon, destek vektör makineleri (SVM), rastgele orman ve gradyan artırma algoritmaları kullanılarak sınıflandırma işlemi yapılmıştır. Model performansı, tabakalı 5 katlı çapraz doğrulama yöntemi ile doğruluk, AUC-ROC, duyarlılık ve özgüllük metrikleri kullanılarak değerlendirilmiştir.Bulgular—Lojistik regresyon modeli %94.9 doğruluk ve %98.6 AUC-ROC değeri ile en yüksek performansı göstermiş, SVM modeli ise benzer sonuçlar elde etmiştir. Sağkalım analizi, ileri evre hastalığın anlamlı derecede daha yüksek mortalite riski ile ilişkili olduğunu ortaya koymuştur (HR = 6.50; p < 0.001). PPI ağı analizi sonucunda TP53, EGFR, KRAS, AKT1 ve PIK3CA genlerinin ağda merkezi rol oynadığı belirlenmiştir. Elde edilen sonuçlar, genomik ve klinik verilerin entegrasyonunun tek modaliteli yaklaşımlara kıyasla daha yüksek sınıflandırma başarısı sağladığını göstermektedir.Sonuç—Bu çalışma, akciğer adenokarsinomu evreleme ve prognoz tahmini için etkili ve yorumlanabilir birçok modlu yaklaşım sunmaktadır. Gen ekspresyon verileri ile klinik değişkenlerin birlikte kullanılması hem tahmin doğruluğunu hem de biyolojik anlamlılığı artırmaktadır. Önerilen çerçeve, klinik karar destek sistemlerine katkı sağlayabilecek potansiyele sahiptir. Gelecek çalışmalarda, bağımsız veri setleri ile doğrulama yapılması ve farklı veri türlerinin entegrasyonu önerilmektedir.


  • Open Access

    A Scalarized Weighted-Sum Hybrid GA–PSO Decision-Support Framework for Constrained Water Resource Scheduling

    by Mehmet Akif Cifci, Yousef Farhang, Batuhan Öney, Ziya Gökalp Ersan, Fazlı Yıldırım, Uğur Akbulut

    Water resource management increasingly requires allocation methods that address rising demand, climate variability, and operational inefficiency. This study proposes an elite-transfer hybrid Genetic Algorithm–Particle Swarm Optimization framework for constrained water allocation under a weighted-sum scalarization model. The model combines four normalized objectives: minimizing water shortage, an operational cost coefficient, and allocation imbalance while maximizing utilization efficiency through an equivalent minimization term. A bidirectional elite-transfer mechanism links GA-based global exploration with PSO-based local refinement. The framework was evaluated using two capacity-constrained surrogate scenarios anchored to hydrometeorological records from Türkiye: Melekbahçe station (E21A033) in the Upper Euphrates Basin and Beşdeğirmen station (E12A003) in the Sakarya Basin. Daily streamflow records supported scenario construction, while precipitation and air-temperature data characterized local conditions. The proposed method was compared with standalone GA and standalone PSO, Differential Evolution, Grey Wolf Optimizer, a scalarized NSGA-II, adapted Kao–Zahara and Garg GA–PSO hybrids, and a no-elite ablation. All methods used the same objective formulation, normalization bounds, constraint-repair procedure, equal objective weights, tuning protocol, paired random seeds, and a budget of 10,000 objective-function evaluations. Performance was assessed through 30 paired runs per scenario. The proposed framework achieved the lowest mean scalar fitness values—0.1670 for Melekbahçe and 0.1752 for Beşdeğirmen—and reached the predefined convergence region after averages of 4587 and 4780 evaluations, respectively. All fitness and convergence improvements remained significant after Holm correction. Paired rank-biserial correlations ranged from 0.957 to 1.000 against the seven general comparators and were 0.824 and 0.781 against the no-elite ablation. The findings support the framework under the tested surrogate scenarios but do not establish Pareto-front dominance or universal superiority. Future work should examine measured operational data, additional basins, dynamic scheduling, alternative weights, and Pareto-based extensions.


  • Open Access

    Benchmarking a standard genetic algorithm for real-world university class timetabling

    by Yousef Farhang, Saman Tarighpeyma Aghbolagh, Ülker Başar

    The university class timetabling is known to be a classic example of a problem in combinatorial optimization, where an allocation of classes to time periods, classrooms, and tutors is needed. Although modern works mostly concentrate on designing various hybrid or specialized algorithms and metaheuristics, one should also examine the performance of the original algorithm to obtain a baseline metric for future comparisons. This paper considers a simple application of the unaltered SGA on Dataset A that has 38 subjects, 8 tutors, 8 classrooms, five days of operation, and two types of classes (theoretical and practical). As far as scalability was concerned, we have tested several population sizes for the algorithm, namely 15, 30, 60, and 120. Performance metrics such as fitness and the rate of convergence were measured according to the value of the fitness function and runtime as well as memory usage. It could be demonstrated that despite being extremely simple, classical SGA produces valid solutions for this problem but is quite sensitive to changes in population size. To make the analysis more robust, the paper also includes a very basic comparison experiment involving Simulated Annealing as another basis of evaluation.

  • Open Access

    Concepts of Machine Learning

    by Yousef Farhang, Ülker Başar, İbrahim Öztürk, Gökhan Halimoğlu, David M. Halliday, Nigar Tuğbagül Altan Gülgün, Havva Gül Koçer, Birkan Büyükarıkan, Esin Ayşe Zaimoğlu

    This chapter introduces the fundamental concepts and principles of machine learning, serving as a theoretical foundation for the subsequent chapters of the book. It provides a comprehensive overview of the main learning paradigms, including supervised, unsupervised, semi-supervised, and reinforcement learning, along with essential terminology and notations commonly used in machine learning research and applications. Key topics such as data representation, preprocessing techniques, feature engineering, and the learning process are discussed to highlight how raw data is transformed into meaningful knowledge through computational models. The chapter also explains core concepts related to model training, generalization, overfitting, and the bias–variance tradeoff, which are critical for understanding model performance and reliability. In addition, fundamental ideas in optimization and model evaluation are presented, including cost functions, gradient-based learning, and standard performance metrics. Ethical and practical considerations, such as data bias, interpretability, and privacy, are briefly addressed to emphasize responsible use of machine learning technologies. Overall, this chapter establishes a conceptual framework that enables readers to better understand, design, and critically evaluate machine learning systems.


  • Open Access

    A Novel Deep Learning Model for Diabetes Diagnosis

    by Haniyeh Fattahi, Yousef Farhang

    The SETSCI Conference Proceedings is an Open Access publication created for the storage and indexing of proceedings | Diabetes is a chronic disease affecting millions worldwide, necessitating early and accurate diagnosis for effective management. Traditional diagnostic methods, while reliable, often struggle with efficiency and early-stage detection. Deep learning has emerged as a powerful tool in medical diagnostics, offering improved accuracy and predictive capabilities. This paper introduces a novel deep learning model for diabetes diagnosis, leveraging advanced neural network architectures. Trained and evaluated on standard datasets, the model outperforms conventional methods, demonstrating superior diagnostic accuracy and reliability. Our findings underscore the potential of deep learning to enhance diabetes detection and patient outcomes.