Parçacık Sürüsü Optimizasyonu ile Optimize Edilmiş Yapay Sinir Ağı Modeli Kullanılarak Turizm Gelirlerinin Tahmini

Year 2025, Volume: 29 Issue: 3, 716 - 724, 25.12.2025

Ümmügülsüm Çelik , Aynur Yonar

https://doi.org/10.19113/sdufenbed.1657799

Abstract

Yapay sinir ağı (YSA), son yıllarda tahmin çalışmalarında yaygın olarak kullanılan makine öğrenme algoritmalarından biridir. YSA ile etkili tahmin sonuçları elde etmenin anahtarı, ağın eğitimi ve ayarlanabilir parametrelerinin tasarımına bağlıdır. Geri yayılım ve Levenberg-Marquardt (BP-LM) öğrenme algoritmaları, YSA'nın eğitimi için en çok kullanılan algoritmalardır. Ancak, bu algoritmalar yerel minimumlara takılma, hesaplama karmaşıklığı, başlangıç değerlerine duyarlılık, aşırı öğrenme ve sınırlı paralelleştirme gibi bazı dezavantajlara sahiptir. Bu çalışmada, YSA öğreniminde karşılaşılan bu sorunları ele almak amacıyla Parçacık Sürüsü Optimizasyonu (PSO) ile eğitilmiş bir YSA modeli önerilmiştir. PSO, en iyi çözüme ulaşabilme, az sayıda ayarlanabilir parametreye sahip olma, kolay paralelleştirme, sağlamlık ve hızlı yakınsama özellikleri sayesinde öğrenme sürecinde başarılı olabilen yapay zeka algoritmalarından biridir. Önerilen model, turizm geliri tahmini için farklı YSA yapıları ve parametre değerleri ile test edilmiştir. Sonuç olarak, önerilen PSO ile eğitilmiş YSA modelinin genel olarak BP-LM ile eğitilmiş YSA'ya kıyasla daha iyi tahmin sonuçları verdiği gözlemlenmiş ve turizm gelirlerinin tahmini için en uygun YSA yapısı belirlenmiştir. Ayrıca, belirlenen optimal YSA yapısı ile önümüzdeki 12 ay için turizm gelir tahmini gerçekleştirilmiştir.

Keywords

Yapay Zeka , Yapay Sinir Ağları , Makine Öğrenmesi , Parçacık Sürü Optimizasyonu

An Optimized Artificial Neural Network Model with Particle Swarm Optimization for Tourism Revenue Prediction

Abstract

Artificial neural network (ANN) is one of the machine learning algorithms widely used in prediction studies recently. The key to obtaining effective prediction results with ANN depends on its training and the design of its tunable parameters. The Backpropagation and Levenberg-Marquardt (BP-LM) learning algorithms are the most utilized algorithms for training ANN. However, these algorithms have some disadvantages such as local minima, computational complexity, sensitivity to initialization, overfitting, and limited parallelism. In this study, we proposed a Particle Swarm Optimization (PSO)-trained ANN model to deal with these problems in ANN learning. PSO is one of the well-utilized artificial intelligence algorithms and it can be successful in the learning process thanks to its features of finding global optima, having a few parameters to be tuned, being easily parallelized, robustness and convergence speed. The proposed model is tested with different ANN structures and parameter values for tourism revenue prediction. As a result, it was observed that the proposed PSO-trained ANN model generally gave better prediction results than BP-LM trained ANN and an optimal ANN structure was obtained for the prediction of tourism revenues. In addition, forecasting of tourism revenues for the next 12 months was obtained with a designed optimal ANN structure.

Keywords

Artificial intelligence , Artificial Neural Network , Machine Learning , Particle Swarm Optimization , Prediction of Tourism Revenues.

References

• [1] Kumcu, E., Eğilmez M. 2002. Economic Policy, Theory and Practice in Türkiye.
• [2] Çımat, A., Bahar, O. 2003. An evaluation on the place and importance of the tourism sector in the Turkish economy.
• [3] Hepaktan CE., Çınar S. 2010 The effects of the tourism sector on the Turkish economy. Celal Bayar Univrsity, Journal of SBE, 8(2), 135-154.
• [4] Palmer A., Montano JJ., Sesé A. 2006. Designing an artificial neural network for forecasting tourism time series. Tourism Management, 27(5), 781-790.
• [5] Chen C. F., Lai M-C., Yeh C-C. 2012. Forecasting tourism demand based on empirical mode decomposition and neural network. Knowledge-Based Systems. 26, 281-287.
• [6] Constantino H., Fernandes PO., Teixeira JP. 2016. Tourism demand modelling and forecasting with artificial neural network models: The Mozambique case study. Tékhne. 14(2), 113-124.
• [7] Li S., Chen T., Wang L., Ming C. 2018. Effective tourist volume forecasting supported by PCA and improved BPNN using Baidu index. Tourism Management, 68, 116-126.
• [8] S.S. Deniz,. Veri Madenciliği Araçlari Kullanilarak Türkiye’nin Turizm Gelirlerinin Aylara Göre Yapay Sinir Ağlari İle Tahminlenmesi. Yüzüncü Yıl Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 241-255.
• [9] Höpken W., Eberle T., Fuchs M., Lexhagen M. 2021. Improving tourist arrival prediction: a big data and artificial neural network approach. Journal of Travel Research, 60(5), 998-1017.
• [10] Kang S.Y. 1991. An Investigation of the Use of Feedforward Neural Networks for Forecasting: Kent State University.Günay S., Eğrioğlu E., Aladağ ÇH. 2007. Introduction to Univariate Time Series Analysis.
• [11] Uğuz, S. 2019. An Artificial Intelligence School with Machine Learning Theoretical Aspects and Python Applications. Nobel Publishing. Ankara.
• [12] Ataseven, B. 2013 Yapay sinir ağlari ile öngörü modellemesi. Öneri Dergisi, 10(39), 101-115.
• [13] Narayanan, S.L., Kasiselvanathan, M., Gurumoorthy, K.B., Kiruthika, V. 2023. Particle swarm optimization based artificial neural network (PSO-ANN) model for effective k-barrier count intrusion detection system in WSN. Measurement: Sensors, 29, 100875.
• [14] Rauf, H.T., Bangyal, W.H., Ahmad, J., Bangyal, S.A. 2018. Training of artificial neural network using PSO with novel initialization technique. In: International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT), IEEE, Bahrain, pp. 1–8.
• [15] Yadav, A., Roy, S.M. 2023. An artificial neural network–particle swarm optimization (ANN-PSO) approach to predict the aeration efficiency of venturi aeration system. Smart Agricultural Technology, 4, 100230.
• [16] Kargı, V.S.A. 2013. Artificial Neural Network Models and Application in a Textile Company. Bursa Uludag University (Turkey),
• [17] Eberhart, R., Kennedy, J. 1995. A new Optimizer Using Particle SwarmTheory. Paper presented at the MHS'95. Proceedings of the sixth international symposium on micro machine and human science.
• [18] Acıtaş, Ş., Aladağ, Ç.H., Şenoğlu, B. 2019. A new approach for estimating the parameters of Weibull distribution via particle swarm optimization: an application to the strengths of glass fibre data. Reliability Engineering & System Safety, 183, 116-127.
• [19] Örkcü, H., Özsoy, V.S., Aksoy, E., Dogan, M.I. 2015. Estimating the parameters of 3-p Weibull distribution using particle swarm optimization: A comprehensive experimental comparison. Applied Mathematics and Computation, 268, 201-226.
• [20] Rezaee, Jordehi, A., Jasni, J. 2013. Parameter selection in particle swarm optimisation: a survey. Journal of Experimental & Theoretical Artificial Intelligence, 25(4), 527-542.
• [21] Talbi, E.G., 2009. Metaheuristics: from design to implementation: John Wiley & Sons.
• [22] Yang, X. S., 2014. Nature-inspired optimization algorithms: Elsevier.
• [23] Yonar, A,. 2020. Metaheuristic approaches for estimating parameters of univariate and multivariate distributions. Phd. Thesis, Selçuk University Institute of Science, Konya, 48–52.
• [24] Çarkıt, T. 2022. State of Charge and Voltage Prediction for Li-Ion Batteries by Using Neural Network Modeling and Artificial Bee Colony Algorithm.
• [25] Gulcu, Ş. 2020. Training of the Artificial Neural Networks Using States of Matter Search Algorithm. International Journal of Intelligent Systems and Applications in Engineering, 8(3), 131-136. This demonstrates
• [26] Irmak, B., Gülcü, Ş. 2021. Training of the Feed-Forward Artificial Neural Networks Using Butterfly Optimization Algorithm. Manas Journal of Engineering, 9(2), 160-168.
• [27] Kaya, E. 2022. Meta-Heuristic Approaches in Training Feed Forward Artificial Neural Network. Turkish Informatics Foundation Journal of Computer Science and Engineering, 15(1), 38-43.
• [28] Nawi, N. M., Khan, A,, Rehman, M. 2013. A New Levenberg Marquardt Based Back Propagation Algorithm Trained With Cuckoo Search. Procedia Technology, 11, 18-23.
• [29] Valian, E., Mohanna, S., Tavakoli, S. 2011. Improved Cuckoo Search Algorithm for Feedforward Neural Network Training. International Journal of Artificial Intelligence & Applications, 2(3), 36-43.
• [30] Zeydan, Ö. 2021. Evaluation of Particulate Matter (PM10) Pollution in Turkey in 2019. Journal of the Institute of Science and Technology, 11(1), 106-118.
• [31] Haklı, H., Uğuz, H. 2013. Levy Flight Distribution for Scout Bee in Artificial Bee Colony Algorithm. Lecture Notes on Software Engineering, 1(3), 254. [32] Hwang, C.L., Masud, A.S.M. 2012. Multiple Objective Decision Making—Methods and Applications: A State-of-the-Art Survey (Vol. 164): Springer Science & Business Media.
• [33] Shi, Y. 2001. Particle Swarm Optimization: Developments, Applications and Resources. Paper presented at the Proceedings of the congress on evolutionary computation. 2001. (IEEE Cat. No. 01TH8546).
• [34] Zhan, Z.H., Zhang, J., Li, Y., Chung, H.S.H. 2009. Adaptive particle swarm optimization. IEEE Transactions on Systems, Man, Cybernetics, Part B, 39(6), 1362-1381.
• [35] Akbay, R., Şahiner, A., Yılmaz, N. 2016. Determining of The Achievement of Students by Using Classical and Modern Optimization Techniques. Eurasian Journal of Physics & Chemistry Education, 8(1), 3–13.
• [36] Şahiner, A., Ucun, F., Koman, S. 2017. Continuous Energy Values of 3-Amino-4-Nitraminofurazan Molecule by Modern Optimization Techniques. Iranian Journal of Optimization, 9(2), 69–77.
• [37] Şahiner, A., Kapusuz, G., Yılmaz, N. 2017. A New Mathematical Modeling Approach for the Energy of Threonine Molecule. AIP Conference Proceedings, 1863, 250003.