Classifying Apis mellifera Breeds Using Data Mining Techniques Based on Morphological Traits

Year 2025, Volume: 39 Issue: 1, 95 - 107

Mustafa Kibar , İnci Şahin Negiş , İbrahim Aytekin , İsmail Keskin

Abstract

Arı ırklarının sınıflandırılması, genetik çeşitliliğin sürdürülmesi, üretkenliğin artırılması ve arı kolonilerinin sağlığını korumak için önemlidir. Bu nedenle, bu çalışma, maliyet etkin ve basit olan veri madenciliği tekniklerini kullanarak farklı arı ırklarını morfolojik özelliklerine dayalı olarak sınıflandırmayı amaçlamaktadır. 2020 yılında, çalışma, morfometrik analiz için özel bir arı çiftliğinden toplamda 35 koloniyi içeren yedi farklı arı ırkı ve 404 arı örneği içermektedir. Arı ırklarının sınıflandırılması için çeşitli veri madenciliği teknikleri (Destek Vektör Makineleri (DVM), Rastgele Orman (RO), Yapay Sinir Ağları (YSA), Naive Bayes (NB) ve k-En Yakın Komşular (k-EYK)) ve model uyum kriterleri kullanılmıştır. Çalışma genel olarak farklı arı ırklarının morfolojik özelliklerinde önemli farklılıklar olduğunu ortaya koyarak, her arı ırkının çeşitliliğini ve farklı özelliklerini göstermektedir. Ayrıca, çalışma RF modelinin tüm kriterlerde üstün olduğunu ve bu nedenle bal arıları ırklarını sınıflandırmak için en etkili olduğunu göstermektedir. Buna karşılık, NB modeli sürekli olarak en kötü performansı sergilemektedir, tüm metriklerin sürekli minimum değerleri ile kanıtlanmıştır. Sonuç olarak, morfolojik özelliklere dayalı olarak arı ırklarının sınıflandırılmasında %99,8 başarı oranı gösteren RO modeli, gelecekteki sınıflandırma araştırmalarında kullanılabilirliğini destekleyerek ön plana çıkmaktadır.

Keywords

Arı ırkları, Sınıflandırma, Veri madenciliği, Morfolojik özellikler

Ethical Statement

Bu çalışma için etik kurul gerekmemektedir.

Supporting Institution

Bu çalışma herhangi bir kurum tarafından desteklenmemiştir.

Classifying Apis mellifera Breeds Using Data Mining Techniques Based on Morphological Traits

Abstract

The classification of bee breeds is significant for breeding, maintaining genetic diversity, increasing productivity and protecting the health of the bee colonies. Therefore, this study aims to classify different honeybee breeds based on their morphological traits using data mining techniques, which are cost-effective and straightforward. It were used a total of 35 colonies from a private bee farm for morphometric analysis in the study, which included seven different bee breeds and 404 bee samples. A range of data mining techniques (Support Vector Machines (SVM), Random Forest (RF), Artificial Neural Networks (ANN), Naive Bayes (NB) and k-Nearest Neighbors (k-NN)), and model fit criteria were used for the classification of bee breeds. Overall, the study shows significant differences in the morphological traits of different bee breeds, highlighting the diversity and different traits of each bee breed. In addition, the study shows that the RF model is superior in all criteria and therefore the most effective for classifying honeybee breeds. In contrast, the NB model consistently performs the worst, as evidenced by the consistently minimum values of all metrics. In conclusion, RF model exhibiting a 99.8% success rate, stands out as highly effective in the classification of bee breeds based on the morphological traits, supporting its applicability in future classification research.

Keywords

bee breeds, classification, data mining, morphological traits, performance metrics

References

• Abou-Shaara HF (2013). Wing venation characteristics of honey bees. Journal of Apicultural 28: 79-86.
• Abou-Shaara HF, Al-Ghamdi AA, Mohamed AA (2013). Body morphological characteristics of honey bees. Agricultura, 10: 45-49.
• Alpatov WW (1929). Biometrical studies on variation and races of the honey bee (Apis mellifera L.). The Quarterly Review of Biology, 4: 1-58. https://www.jstor.org/stable/2808231
• Anderson LE (1954). Hoyer's solution as a rapid permanent mounting medium for bryophytes. The Bryologist, 57: 242-244. https://doi.org/10.2307/3240091
• Antony JC, Pratheepa M (2018). A Bayesian classification approach for predicting Gesonia gemma Swinhoe population on soybean crop in relation to abiotic factors based on economic threshold level. Journal of Biological Chemistry, 32: 68-73. https://doi.org/10.18311/jbc/2018/16309
• Berlocher SH (1984). Insect molecular systematics. Annual Review of Entomology, 29: 403-433. https://doi.org/10.1146/annurev.en.29.010184.002155
• Bhavsar H, Ganatra A (2012). A comparative study of training algorithms for supervised machine learning. International Journal of Soft Computing and Engineering, 2: 74-81.
• Breiman L (2001). Random forests. Journal of Machine Learning Research, 45: 5-32. https://doi.org/10.1023/A:1010933404324
• Buco SM, Rinderer TE, Sylvester HA, Collins AM, Lancaster VA, Crewe RM (1987). Morphometric differences between South American Africanized and South African (Apis mellifera scutellata) honey bees. Apidologie, 18: 217-222. https://doi.org/10.1051/apido:19870301
• Cariveau DP, Nayak GK, Bartomeus I, Zientek J, Ascher JS, Gibbsand J, Winfree R (2018). The allometry of bee proboscis length and its uses in ecology. PloS One, 13: Article e0207900. https://doi.org/10.1371/journal.pone.0207900
• Cover T, Hart P (1967). Nearest neighbor pattern classification. IEEE Transactions on Information Theory, 13: 21-27. https://doi.org/10.1109/TIT.1967.1053964
• Crewe RM, Hepburn HR, Moritz RFA (1994). Morphometric analysis of 2 southern African races of honey bee. Apidologie, 25: 61-70. https://doi.org/10.1051/apido:19940107
• Demsar J, Curk T, Erjavec A, Gorup C, Hocevar T, Milutinovic M, Mozina M, Polajnar M, Toplak M, Staric A, Stajdohar M, Umek L, Zagar L, Zbontar J, Zitnik M, Zupan B (2013). Orange: Data Mining Toolbox in Python. Journal of Machine Learning Research, 14: 2349−2353.
• Diniz-Filho JAF, Malaspina O (1995). Evolution and population structure of Africanized honey bees in Brazil: Evidence from Spital analysis of morphometric data. Evolution, 49: 1172-1179. https://doi.org/10.1111/j.1558-5646.1995.tb04444.x
• Dodoloğlu A (2000). Kafkas ve Anadolu balarısı (Apis smellifera L.) ırkları ile karşılıklı melezlerinin morfolojik, fizyolojik ve davranış özellikleri (Publication No. 96437). PhD Thesis, Atatürk University (Unpublished), Türkiye.
• Estoup A, Garnery L, Solignac M, Cornuet JM (1995). Microsatellite variation in honey bee (Apis mellifera L.) populations: hierarchical genetic structure and test of the infinite allele and stepwise mutation models. Genetics, 140: 679-695. https://doi.org/10.1093/genetics/140.2.679
• Frunze O, Kim DW, Kang EJ, Kim K, Park BS, Choi YS (2022). The accuracy of morphometric characteristic analysis depends on the type of the assessed traits of honey bees (Apis cerana F. and Apis mellifera L.). Journal of Asia-Pacific Entomology, 25: Article 101991. https://doi.org/10.1016/j.aspen.2022.101991
• Ftayeh A, Meixner M, Fuchs S (1994). Morphometrical investigation in Syrian honey bees. Apidologie, 25: 396-401. https://doi.org/10.1051/apido:19940406
• Gençer HV (2004). The graphic evaluation of morphological characters in honey bees (Apis mellifera L.) by Chernoff Faces. Journal of Agricultural Sciences, 10: 245-249. https://doi.org/10.1501/Tarimbil_0000000901
• Gençer HV, Günbey B (2020). The morphological characteristics of distinctive honey bee (Apis mellifera L.) genotypes in Black Sea Region. Journal of Animal Science and Products, 3: 40-53.
• Guler A, Bek Y (2002). Forewing angles of honey bee (Apis mellifera) samples from different regions of Turkey. Journal of Apicultural Research, 41: 43-49. https://doi.org/10.1080/00218839.2002.11101067
• Han J, Pei J, Tong H (2022). Data mining: concepts and techniques. Morgan kaufmann. Amsterdam, Elsevier, p.735.
• Jadhav SD, Channe HP (2016). Comparative study of K-NN, naive Bayes and decision tree classification techniques. International Journal of Science and Research, 5: 1842-1845. https://www.ijsr.net/getabstract.php?paperid=NOV153131
• Kambur M, Kekeçoğlu M (2018). The current situation of Turkey Honey Bee (Apis mellifera L.) biodiversity and conservations studies. Biological Diversity and Conservation, 11: 105-119. https://doi.org/10.13140/RG.2.2.12203.54568
• Kekeçoğlu M, Bir S, Acar MK (2023). Determination of Anatolian honeybee biodiversity by wing characters. Sociobiology, 70: Article e8333. https://doi.org/10.13102/sociobiology.v70i3.8333
• Khan SN, Khan SU, Aznaoui H, Şahin CB, Dinler ÖB (2023). Generalization of linear and non-linear support vector machine in multiple fields: a review. Computer Science and Information Technology, 4: 226-239. https://doi.org/10.11591/csit.v4i3.p226-239
• Li F, Xiong Y (2018). Automatic identification of butterfly species based on HoMSC and GLCMoIB. The Visual Computer, 34: 1525-1533. https://doi.org/10.1007/s00371-017-1426-1
• Liaw A, Wiener M (2002). Classification and regression by random Forest. R News, 2: 18-22. http://CRAN.R-project.org/doc/Rnews/
• Özbakır GÖ (2011). Morphological characterization of honey bee populations (Apis mellifera L.) along the southeast border of Turkey (Publication No. 299725). PhD Thesis, Ankara University(Unpublished), Türkiye.
• Pan X, Wang Y, Qi Y (2023). Artificial neural network model and its application in signal processing. Asian Journal of Advanced Research and Reports, 17: 1-8. https://doi.org/10.9734/AJARR/2023/v17i1459
• Potts SG, Biesmeijer JC, Kremen C, Neumann P, Schweiger O, Kunin WE (2010). Global pollinator declines: trends, impacts and drivers. Trends in Ecology and Evolution, 25: 345-353. https://doi.org/10.1016/j.tree.2010.01.007
• Rinderer TE, Buco SM, Rubink WL, Daly HV, Stelszer JA, Rigio RM, Baptista C (1993). Morphometric identification of Africanized and European honey bees using large reference populations. Apidologie, 24: 569-585. https://doi.org/10.1051/apido:19930605
• Rodrigues PJ, Gomes W, Pinto MA (2022). DeepWings©: automatic wing geometric morphometrics classification of honey bee (Apis mellifera) subspecies using deep learning for detecting landmarks. Big Data and Cognitive Computing, 6: 70. https://doi.org/10.3390/bdcc6030070
• Ruttner F, Tassencourt L, Louveaux J (1978). Biometrical-statistical analysis of the geographic variability of Apis mellifera L. I. Material and methods. Apidologie, 9: 363-381. https://doi.org/10.1051/apido:19780408
• Souza D, Cruz CD, Campos L, Regazzi AJ (2002). Correlation between honey production and some morphological traits in africanized honey bees (Apis melifera). Ciência Rural, 32: 869-872. https://doi.org/10.1590/S0103-84782002000500020
• Szymula J, Skowronek W, Bienkowska M (2010). Use of various morphological traits measured by microscope or by computer methods in the honeybee taxonomy. Journal of Apicultural Science, 54: 91-97.
• Tapkan P, Özbakır L, Kulluk S, Baykasoğlu A (2016). A cost-sensitive classification algorithm: BEE-Miner. Knowledge-Based Systems, 95: 99-113. https://doi.org/10.1016/j.knosys.2015.12.010
• Trevethan R (2017). Sensitivity, specificity, and predictive values: foundations, pliabilities, and pitfalls in research and practice. Frontiers in Public Health, 5: 307. https://doi.org/10.3389/fpubh.2017.00307
• Vapnik V (1999). The nature of statistical learning theory. Springer Science and Business Media, pp.314. https://doi.org/10.1007/978-1-4757-3264-1
• Wickramasinghe I, Kalutarage H (2021). Naive Bayes: applications, variations and vulnerabilities: a review of literature with code snippets for implementation. Soft Computing, 25: 2277-2293. https://doi.org/10.1007/s00500-020-05297-6
• Yegnanarayana B (1999). Artificial neural networks. PHI Learning Pvt. Ltd.: New Delhi, India, pp. 476.
• Zemskova NE, Sattarov VN, Skvortsov AI, Semenov VG (2020). Morphological characteristics of honey bees of the Volga region. BIO Web Conf 17, 35. EDP Sciences. https://doi.org/10.1051/bioconf/20201700035