Mühendislik, Mimarlık ve Tasarım Fakültesi

Permanent URI for this community

https://dspace.mudanya.edu.tr/handle/20.500.14362/73

Browse

Browsing Mühendislik, Mimarlık ve Tasarım Fakültesi by All Authors "222298"

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    A Comprehensive Review of Convolutional Neural Networks based Disease Detection Strategies in Potato Agriculture
    (Springer, 2024-09) Gülmez, Burak; 222298
    This review paper investigates the utilization of Convolutional Neural Networks (CNNs) for disease detection in potato agriculture, highlighting their pivotal role in efficiently analyzing large-scale agricultural datasets. The datasets used, preprocessing methodologies applied, specific data collection zones, and the efficacy of prominent algorithms like ResNet, VGG, and MobileNet variants for disease classification are scrutinized. Additionally, various hyperparameter optimization techniques such as grid search, random search, genetic algorithms, and Bayesian optimization are examined, and their impact on model performance is assessed. Challenges including dataset scarcity, variability in disease symptoms, and the generalization of models across diverse environmental conditions are addressed in the discussion section. Opportunities for advancing CNN-based disease detection, including the integration of multi-spectral imaging and remote sensing data, and the implementation of federated learning for collaborative model training, are explored. Future directions propose research into robust transfer learning techniques and the deployment of CNNs in real-time monitoring systems for proactive disease management in potato agriculture. Current knowledge is consolidated, research gaps are identified, and avenues for future research in CNN-based disease detection strategies to sustain potato farming effectively are proposed by this review. This study paves the way for future advancements in AI-driven disease detection, potentially revolutionizing agricultural practices and enhancing food security. Also, it aims to guide future research and development efforts in CNN-based disease detection for potato agriculture, potentially leading to improved crop management practices, increased yields, and enhanced food security.
  • No Thumbnail Available
    Item
    A novel hybrid MCDM framework combining TOPSIS, PROMETHEE II, and VIKOR for peach drying method selection
    (Elsevier, 2024-11) Gülmez, Burak; 222298
    The selection of optimal drying technologies for peach processing presents a complex decision-making challenge due to multiple conflicting criteria. This study introduces a novel hybrid multi-criteria decision-making (MCDM) framework combining TOPSIS, VIKOR, and PROMETHEE II methods to evaluate eight drying technologies. The evaluation was conducted across twelve criteria, encompassing product quality, operational efficiency, economic factors, and environmental impact. Data were collected from five industry experts through structured matrices. The results demonstrate that vacuum drying emerged as the optimal technology, maintaining the top position in 75 % of sensitivity scenarios. Freeze drying and heat pump drying consistently ranked among the top three alternatives across all methods. The correlation analysis revealed strong agreement between VIKOR and PROMETHEE II rankings (0.857), while TOPSIS provided complementary insights. Sensitivity analysis identified energy consumption, investment cost, and nutritional retention as the most critical factors influencing technology selection. The findings indicate that advanced drying technologies significantly outperform traditional methods in terms of overall performance. This research provides a comprehensive framework for evidence-based decision-making in food processing technology selection and establishes quantitative benchmarks for future technology evaluations in the fruit drying industry.
  • No Thumbnail Available
    Item
    Stock price prediction using the Sand Cat Swarm Optimization and an improved deep Long Short Term Memory network
    (Elsevier, 2025-01) Gülmez, Burak; 222298
    Stock price prediction remains a complex challenge in financial markets. This study introduces a novel Long Short-Term Memory (LSTM) model optimized by Sand Cat Swarm Optimization (SCSO) for stock price prediction. The research evaluates multiple algorithms including ANN, LSTM variants, Auto-ARIMA, Gradient Boosted Trees, DeepAR, N-BEATS, N-HITS, and the proposed LSTM-SCSO using DAX index data from 2018 to 2023. Model performance was assessed through Mean Squared Error, Mean Absolute Error, Mean Absolute Percentage Error, and out-of-sample R2 metrics. Statistical significance was validated using Model Confidence Set analysis with 5000 bootstrap replications. Results demonstrate LSTM-SCSO's superior performance across all evaluation metrics. The model achieved an annualized return of 66.25% compared to the DAX index's 47.45%, with a Sharpe ratio of 2.9091. The integration of technical indicators and macroeconomic variables enhanced the model's predictive capabilities. These findings establish LSTM-SCSO as an effective tool for stock price prediction, offering practical value for investment decision-making.