Kural madenciliği, veri madenciliğinin önemli alt dallarından biri olup günümüzde hala üzerinde çalışılan sıcak bir çalışma alanıdır. Nicel nitelik içeren veri setleri üzerinde çalışan standart sınıflandırma yöntemleri genellikle ön işlem aşamalarına ihtiyaç duyarlar. Bu yapılan ayrıklaştırmalar ise başarım kaybına yol açabilmektedir. Buna ek olarak standart sınıflandırma algoritmalarının kara-kutu yapılarından dolayı kural açıklanabilirlikleri iyi değildir. Bu noktada, sürekli veriler ile çalışabilen optimizasyon algoritmaları, bu dezavantajların üstesinden gelebilir. Bu çalışmada, son yılların başarılı optimizasyon algoritmalarından olan Ayçiçeği Optimizasyon algoritmasını kullanarak verimli bir kural madenciliği gerçekleştirilmiştir. Bunun için, farklı bir temsil biçimi kullanan aday bitki yapısı, bu optimizasyon algoritmasına uyarlanmıştır. Arama uzayı olarak üç farklı disipline ait veri seti kullanılmış ve yöntemin başarımını gözlemlemek için iyi bilinen beş farklı sınıflandırma algoritmasına ait sonuçlar paylaşılmıştır. Elde edilen sonuçlar, optimizasyon temelli yaklaşım ile veri setleri üzerinde herhangi bir ön işlem yapmaya gerek kalmadan açıklanabilir kurallar üretilebileceğini ispatlamaktadır.

Uzun yıllardır metasezgisel algoritmalar güncelliğini korumakta, bu alanda farklı algoritmalar geliştirilmeye devam etmektedir. Son zamanlarda önerilen Ayçiçeği Optimizasyon Algoritması başarılı bir arama algoritması olarak öne çıkmaktadır. Bununla birlikte yeni bir algoritma olması nedeni ile geliştirilmeye açık ve kullandığı yöntem ile de esnek bir yapıdadır. Bu çalışma Ayçiçeği Optimizasyon algoritmasını esas alan ve farklı bir keşif yöntemi kullanan Salınımlı Kaotik Ayçiçeği Optimizasyon Algoritmasını önermektedir. Aynı zamanda, önerilen algoritmada birey üretimi ve algoritma yürütümü farklı kaotik haritalar kullanılarak gerçekleştirebilmektedir. Bunun için Chebyshev, Circle, Logistic, Sine ve Tent kaotik haritaları kullanılmıştır. Performans karşılaştırmaları için kısıtlı ve kısıtsız test fonksiyonları tercih edilmiş ve mukayeseli sonuçlar sunulmuştur. Yapılan bu deneysel çalışma sonucunda, Salınımlı Kaotik Ayçiçeği Algoritmasının, klasik ayçiçeği algoritması ile rekabet edebilir sonuçlar verdiği ispatlanmıştır.

Food drying is a widely used preservation technique; however, achieving high energy efficiency while maintaining product quality remains a significant challenge. This study aims to analyze comprehensive experimental data obtained during the hot-air drying process of the Paşa pear (regional pear) and the system’s autonomous control structure using an explainable artificial intelligence (XAI)-based method. The intelligent drying system, operating for approximately 17.5 h under two temperatures (50 °C and 65 °C) and two air speeds (0.63 m/s and 1.03 m/s), continuously adjusted the temperature and air speed using a PLC-based control mechanism; it ensured stable control throughout the process by monitoring parameters such as product weight, moisture, inlet–outlet temperatures, and air speed in real time. Experimental results showed that drying performance varied significantly with operating conditions, with product mass decreasing from 450 g to 103 g. The innovative aspect of the study is that it obtained quantitative, interpretable rules without discretization by applying the oscillatory chaotic sunflower optimization algorithm (OCSFO) to multidimensional control and process data for the first time. Thanks to its chaotic search mechanism, OCSFO accurately analyzed complex drying dynamics and created rules that achieved over 90% success for high, medium, and low performance classes. The obtained explainable rules clearly demonstrate that drying temperature and air velocity are the dominant determining parameters for drying efficiency, while energy consumption and cabin temperature distribution play a supporting role in distinguishing between efficiency classes. These rules clearly demonstrate how changes in controlled temperature and air velocity, combined with product weight and heat transfer, affect drying performance. Thus, the study offers a robust framework that identifies critical factors affecting drying performance through a transparent artificial intelligence approach that leverages both the autonomous control system and XAI-based rule mining.

The European cherry fruit fly (Rhagoletis cerasi L.) poses a significant pest threat to cherry production due to its rapid reproduction and host specificity, causing substantial economic damage. This study presents a novel, explainable, and biologically inspired data-driven classification model based on fruit characteristics to support targeted and sustainable pest control strategies. In research conducted at four different locations in Elazığ province, three population classes were determined based on the number of adult individuals caught in traps, and 10 different fruit characteristics were measured in fruit samples belonging to each class. The data used in this study are original data obtained by the authors. To examine the relationship between pomological characteristics of cherry fruit and cherry fruit fly density, the Chaotic Rule-based–Strength Pareto Evolutionary Algorithm2 (CRb-SPEA2) method, developed as a multi-objective and chaos-integrated evolutionary rule mining framework, was adapted. The developed algorithm aimed for high performance, interpretability, and transparency. Accuracy, Precision, and Recall metrics, which are conflicting objectives, were optimized with Pareto-optimal solutions, yielding selectable results for domain experts. To increase population diversity and reduce the risk of early convergence and getting stuck in a local optimum, the Tent chaotic mapping mechanism was also integrated into the system. Furthermore, the model was trained without the need for predefined automatic discretization of the continuous value ranges of the attributes. The proposed model achieved superior results across all classes, with the highest accuracy rate of 82.6% recorded in the High class, demonstrating excellent sensitivity and recall values.

This study investigates the thermodynamic and drying performance of a greenhouse dryer integrated with a parabolic trough solar collector (PTSC) and develops interpretable operating rules using a bio-inspired explainable artificial intelligence framework. Outdoor apple-drying experiments were conducted, and system performance was evaluated in terms of energy, drying, and exergy efficiencies. The experimental results indicated that energy efficiency ranged from 17.7% to 29.2%, drying efficiency from 1.0% to 9.7%, and exergy efficiency from 5.6% to 8.4%. Measured variables, including temperature, relative humidity, product weight, and solar radiation, were used to classify the efficiencies into low, medium, and high categories using the Chaotic Rule-based Strength Pareto Evolutionary Algorithm 2 (CRb-SPEA2). As a bio-inspired evolutionary computing approach, CRb-SPEA2 employs population-based search, selection, Pareto dominance, and multi-objective optimization mechanisms inspired by natural evolutionary processes. In contrast to conventional black-box machine learning models, the proposed method extracts explicit decision rules that define physically meaningful operating ranges. The maximum recall values were 0.952, 1.000, and 0.971 for the high-energy-, drying-, and exergy-efficiency classes, respectively. The extracted rules identified solar radiation, temperature, relative humidity, and product weight as dominant factors affecting dryer performance.

Integrating low-global-warming-potential refrigerants, waste-heat recovery, and intelligent process monitoring offers a promising route to energy-efficient drying systems. This study experimentally compares the natural refrigerants R290 and R600a in a vapor-compression refrigeration system and utilizes condenser waste heat for apple drying. Refrigeration tests were conducted at an evaporator temperature of −16 °C and condenser temperatures of 25, 30, 35, and 40 °C. R290 provided 73% higher cooling capacity and 59% greater condenser heat rejection than R600a, while reducing the drying time from 300 to 265 min. Conversely, R600a exhibited lower specific energy consumption and a higher specific moisture extraction rate. To identify drying progress without continuous product weighing, a physics-guided bioinspired multi-objective evolutionary algorithm, termed Physics-Guided Ordinal Chaotic Rule-Based SPEA2 (P-CRb-SPEA2), was developed. The proposed framework integrates Pareto-based evolutionary search, chaotic initialization, ordinal error, physical consistency, and rule complexity to extract interpretable IF–THEN rules from six thermal and environmental features. Ten-fold cross-validation showed physically consistent, interpretable drying-stage classification, with T₁₀ and T₈ emerging as dominant features for R290 and R600a, respectively. The proposed approach demonstrates the potential of bioinspired evolutionary intelligence for explainable monitoring of integrated refrigeration–drying energy systems.