Vol. 5 • Issue 2Current Issue3 Published Articles

Volume 5, Issue 2 (2026)

Published: August 30, 2026

The Intelligent Methods in Engineering Sciences (Vol. 5, No. 2, 2026) presents a collection of research studies demonstrating the application of machine learning, deep learning, and data-driven analysis methods to agricultural, industrial, and supply chain problems. This issue features a comparative performance analysis of machine learning algorithms for the classification of dry bean varieties, an experimental evaluation of YOLO12 and YOLO13 models for detecting surface defects in steel materials, and a machine learning-based approach for predicting processing times and delays across different operational stages of supply chains. Together, these contributions highlight the potential of intelligent methods to improve classification accuracy, quality control processes, operational planning, and decision-making in real-world engineering and industrial applications.

Table of Contents (3 Articles)

Full Text & Open Access

Performance Analysis of Machine Learning Methods for Classifying Types of Dry Beans

Research Articleslock_openOpen Access

pp. 49-54•Sep 2, 2026

Performance Analysis of Machine Learning Methods for Classifying Types of Dry Beans

Hasan Selim SındırYavuz Selim Taspinar

DOI:https://doi.org/10.58190/imiens.2026.174

Dry beans are a staple food of strategic importance worldwide and in our country due to their high protein content and nutritional value. In agricultural production, preserving seed quality and ensuring product standardization play a critical role in food safety and commercial sustainability. In this context, the accurate and rapid differentiation of morphologically similar bean varieties is essential for maintaining product purity. The main objective of this study is to enable the automatic and highly accurate classification of seven different dry bean varieties registered in Turkey using modern artificial intelligence technologies. Unlike traditional methods, the goal is to develop a decision support system that minimizes human-induced classification errors arising from physical similarities. The study utilized the Dry Bean Dataset obtained from open-source platforms. The dataset includes 16 different numerical morphological and shape features such as Area, Perimeter, Principal Axis Length, and Eccentricity, along with 7 different target classes: Seker, Barbunya, Bombay, Bush, Dermason, Horoz, and Sira. Decision Tree, Random Forest, Logistic Regression, and Artificial Neural Networks algorithms were used to solve the classification problem and perform performance analysis. As a result of the experimental analyses conducted, the highest classification success was achieved with the Artificial Neural Networks model, with a general accuracy rate of 93.4% and an AUC value of 0.995. In contrast, the lowest performance was observed in the Decision Tree algorithm, with an accuracy rate of 90.6%. This developed system has the potential to automate quality control processes in the food industry, thereby reducing manual sorting costs and increasing processing speed. Furthermore, it can provide industrial benefits as a reliable digital tool in seed certification processes and in verifying the purity of commercial products.

picture_as_pdfPDF Detailsarrow_forward

visibility34file_download10

YOLO12 and YOLO13 for Steel Surface Defect Detection: Experimental Evaluation

Research Articleslock_openOpen Access

pp. 55-68•Aug 31, 2026

YOLO12 and YOLO13 for Steel Surface Defect Detection: Experimental Evaluation

Adem Dilbaz

DOI:https://doi.org/10.58190/imiens.2026.175

Intelligent inspection and defect detection of steel surfaces are essential for ensuring product quality, minimizing production losses, and supporting quality control in modern manufacturing systems. In particular, the identification of defects on steel plates is an important step, as surface imperfections can significantly affect the mechanical performance and commercial value of the final product. This study presents a comparative evaluation of YOLO12 and YOLO13 architectures for steel surface defect detection using the NEU-DET dataset under different validation ratios and input image resolutions. Four models (YOLO12-S, YOLO12-L, YOLO13-S, and YOLO13-L) were evaluated under three experimental settings using standard object detection metrics and three different random seeds. Experimental results showed that YOLO13-S consistently demonstrated superior overall detection performance, reaching a best single-run mAP@50 value of 0.753 with seed 42 and a precision value of 0.848 with seed 44. In addition, it achieved the highest single-run mAP@50–95 value of 0.449, with seed 43. In contrast, YOLO12-L achieved the highest single-run recall (0.749), with seed 42, indicating its stronger capability for detecting positive defect instances. Overall, the results demonstrate that YOLO13-S provides the best balance between detection accuracy and computational efficiency, while YOLO12-L offers superior recall performance under the evaluated conditions.

picture_as_pdfPDF Detailsarrow_forward

visibility44file_download11

Data-Driven Prediction of Processing Times and Delays Across Supply Chain Operational Stages Using Machine Learning

Research Articleslock_openOpen Access

pp. 69-82•Aug 31, 2026

Data-Driven Prediction of Processing Times and Delays Across Supply Chain Operational Stages Using Machine Learning

Muhammed Yildiray SURMENOya KILCISelime Sinem BAHARMurat KOKLU

DOI:https://doi.org/10.58190/imiens.2026.176

This study proposes an ensemble learning framework to predict personnel data entry durations across six operational stages using transaction records collected from an operational supply chain information system. To accurately represent operational performance, processing times were calculated in working minutes by excluding nonworking periods, including nights and weekends. The dataset comprised 110,695 unique shipment records collected between 2022 and 2026 and underwent stage-specific data quality assessment and preprocessing. A median-based baseline predictor and three ensemble learning algorithms, HistGradientBoosting, XGBoost, and LightGBM, were evaluated for regression tasks. All models were trained on a log-transformed target (log1p), and predictions were back-transformed to working minutes using the inverse transformation (expm1). To prevent data leakage and better reflect real-world deployment, a year-based temporal split was adopted, with 2026 records reserved for testing. Model performance was evaluated using mean absolute error, root mean square error, coefficient of determination, accuracy, precision, recall, and F1-score. A single regression model was trained per stage, and binary labels (normal/slow) were derived by thresholding the predicted durations at a stage-specific cut-off optimized on the validation set. The results showed that predictive performance varied substantially across operational stages, with LightGBM achieving the best overall performance for the Loading Arrival stage, while lower performance in the Transport Entry and unloading stages suggested the influence of external operational factors not represented in the available data. For the Loading Arrival stage, LightGBM achieved an MAE of 285.989 working minutes and an R² of 0.371 on the test set. Overall, the findings demonstrate that ensemble learning provides an effective and computationally efficient approach for predicting personnel data entry durations and supports real-time decision-making, personnel performance monitoring, and process optimization in data-driven supply chain operations.

picture_as_pdfPDF Detailsarrow_forward

visibility38file_download20