Yapay Zekâ Destekli Isı Haritası (Heatmap) Yöntemiyle Temsil Kabiliyeti Düşük Hayvancılık Anket Verilerinin Görsel Analizi: Kırsal Bir Uygulama Örneği

Öz

Kırsal bölgelerde yürütülen hayvancılık anketlerinde, temsiliyetin düşük olduğu durumlar sıklıkla karşılaşılan bir sorundur. Bu tür verilerle geleneksel istatistiksel analizlerin yürütülmesi genellikle sınırlı geçerlilik ve güvenilirlik üretmektedir. Bu çalışma, saha koşullarının izin verdiği ölçüde toplanmış verilerin Yapay zekâ (YZ) destekli görselleştirme yöntemleri ile nasıl anlamlı hale getirilebileceğini göstermektedir. Heatmap tekniği kullanılarak, hem demografik hem de üretimsel örüntüler açık ve karşılaştırılabilir şekilde sunulmuştur. Bulgular, düşük temsiliyetli ve sınırlı veri yapılarında dahi güçlü görsel analiz çıktıları ile yönetsel ve mekânsal örüntülerin sezgisel biçimde analiz edilebileceğini göstermiştir.

Anahtar Kelimeler

• Hayvancılık anketleri
• Heatmap görselleştirme
• Sınırlı veri setleri
• Veri görselleştirme teknikleri
• Yapay zeka destekli analiz

Visual Analysis of Low-Representativeness Livestock Survey Data Using AI-Assisted Heatmap Methods: A Rural Case Study

Öz

In livestock surveys conducted in rural areas, low representativeness is a frequently encountered issue. Traditional statistical analyses performed on such data often yield limited validity and reliability. This study demonstrates how data collected under field constraints can be made meaningful using Artificial Intelligence (AI) assisted visualization techniques. By employing the heatmap method, both demographic and production patterns have been presented in a clear and comparable manner. The findings indicate that even with low representativeness and limited data structures, strong visual analysis outputs can facilitate intuitive interpretation of managerial and spatial patterns.

Anahtar Kelimeler

• Livestock surveys
• Heatmap visualization
• Limited datasets
• Data visualization techniques
• AI-assisted analysis

Kaynakça

1. Abdennur N., Fudenberg G., Flyamer IM., Galitsyna AA., Goloborodko A., Imakaev M., Venev S. Bioframe: Operations on genomic intervals in Pandas dataframes. Bioinformatics (Oxford, England) 2024; 40(2): btae088. https://doi.org/10.1093/bioinformatics/btae088
2. Alsufyani S., Forshaw M., Johansson Fernstad S. Visualization of missing data: A state of the art survey. arXiv. 2024. Available from: https://arxiv.org/abs/2410.03712
3. Azur MJ., Stuart EA., Frangakis C., Leaf PJ. Multiple imputation by chained equations: what is it and how does it work? International Journal of Methods in Psychiatric Research 2011; 20(1): 40-49. doi:10.1002/mpr.329
4. Babbie ER. The practice of social research. 13th ed. Boston: Cengage Learning 2013.
5. Bertin J. Semiology of graphics. 1st ed. Redlands, CA: ESRI Press 2010.
6. Borland D., Taylor RM II. Rainbow color map (still) considered harmful. IEEE Computer Graphics and Applications 2007; 27(2): 14–17.
7. Bryman A. Social research methods. 5th ed. Oxford: Oxford University Press 2016.
8. Chambers R. The origins and practice of participatory rural appraisal. World Development 1994; 22(7): 953–969. https://doi.org/10.1016/0305-750X(94)90141-4

9. Cheng L., Li X., Bing L. Is GPT 4 a good data analyst? 2023. arXiv preprint arXiv:2305.15038.
10. Chou WH., Feng Z., Li B., Liu F. A first look at financial data analysis using ChatGPT-4o. Journal of Risk and Financial Management 2025;18(2): 99. doi:10.3390/jrfm18020099
11. Cochran WG. Sampling techniques. 3rd ed. New York: John Wiley & Sons 1977.
12. Coşkun C. Veri madenciliği algoritmalarının karşılaştırılması (Yüksek lisans tezi). Diyarbakır: Dicle Üniversitesi, Fen Bilimleri Enstitüsü 2015. https://acikerisim.dicle.edu.tr/items/c1ed471a-30e2-442f-9439-bd5816f3272f
13. Davila F., Paz F., Moquillaza A. Usage and application of heatmap visualizations on usability user testing: A systematic literature review. In: Marcus A, editor. Design, User Experience, and Usability. Cham: Springer 2023: 3–17. doi:10.1007/978-3-031-35702-2_1
14. Dillman DA., Smyth JD., Christian LM. Internet, phone, mail, and mixed-mode surveys: The Tailored design method. 4th ed. Hoboken: Wiley 2014. https://content.e-bookshelf.de/media/reading/L-2753682-49f7ffb446.pdf
15. Few S. Now You See It: Simple Visualization Techniques for Quantitative Analysis. 1st ed. Oakland, CA: Analytics Press 2009.
16. Friendly M. Corrgrams: Exploratory displays for correlation matrices. The American Statistician 2002; 56(4): 316–324.
17. Godsey B. Think like a data scientist: Tackle the data science process step by step. Shelter Island, NY: Manning Publications 2017.
18. Gökmener H., Öztürk A. Erzurum ili Uzundere ilçesinde küçükbaş hayvancılık faaliyetleri ve genel sorunlar. Bahri Dağdaş Hayvancılık Araştırma Dergisi 2022; 11(1): 21–29. https://dergipark.org.tr/tr/pub/bdhad
19. Groves RM., Fowler FJ Jr., Couper MP., Lepkowski JM., Singer E., Tourangeau R. Survey Methodology. 2nd ed. Hoboken: Wiley 2009.
20. Haroz S., Whitney D. How capacity limits of attention influence information visualization effectiveness. IEEE Transactions on Visualization and Computer Graphics 2012;18(12): 2759–2768.
21. Hodges CB., Stone BM., Johnson PK., Carter JH 3rd., Sawyers CK., Roby PR., Lindsey HM. Researcher degrees of freedom in statistical software contribute to unreliable results: A comparison of nonparametric analyses conducted in SPSS, SAS, Stata, and R. Behavior Research Methods 2023; 55(6):2813–2832. doi:10.3758/s13428-022-01932-2
22. Huang Y., Wu R., He J., Xiang Y. Evaluating ChatGPT-4.0's data analytic proficiency in epidemiological studies: A comparative analysis with SAS, SPSS, and R. J Glob Health 2024; 14:04070. doi:10.7189/jogh.14.04070
23. Hunter JD. Matplotlib: A 2D graphics environment. Computing in Science & Engineering 2007; 9(3): 90–95. doi:10.1109/MCSE.2007.55
24. Jordan MI., Mitchell TM. Machine learning: Trends, perspectives, and prospects. Science 2015; 349(6245): 255–260. doi:10.1126/science.aaa8415
25. Kamoi R., Das SSS., Lou R., Ahn JJ., Zhao Y., Lu X., Zhang N., Zhang Y., Zhang RH., Vummanthala SR., Dave S., Qin S., Cohan A., Yin W., Zhang R. Evaluating LLMs at detecting errors in LLM responses (Version 2). arXiv. 2024. Available from: https://arxiv.org/abs/2404.02552
26. Kaul M., Küchler A., Banse C. A uniform representation of classical and quantum source code for static code analysis. arXiv. 2023. doi:10.48550/arXiv.2308.06113
27. Lee KJ., Tilling KM., Cornish RP., Little RJA., Bell ML., Goetghebeur E., Hogan JW., Carpenter JR., STRATOS initiative. Framework for the treatment and reporting of missing data in observational studies. Journal of clinical epidemiology 2021; 134: 79–88. doi:10.1016/j.jclinepi.2021.01.008
28. Little RJA., Rubin DB. Statistical Analysis with Missing Data. 2nd ed. Hoboken: Wiley 2019. doi:10.1002/9781119482260
29. Lohr SL. Sampling: Design and Analysis. 2nd ed. Boston: Brooks/Cole; 2009.
30. McKinney W. Python for Data Analysis: Data Wrangling with pandas, NumPy, and Jupyter (3rd ed.). O'Reilly Media 2022.
31. Meo AS., Shaikh N., Meo SA. Assessing the accuracy and efficiency of Chat GPT-4 Omni (GPT-4o) in biomedical statistics: Comparative study with traditional tools. Saudi medical journal. 2024; 45(12):1383–1390. doi:10.15537/smj.2024.45.12.20240454
32. Netek R., Brus J., Tomecka O. Performance testing on marker clustering and heatmap visualization techniques: A comparative study on JavaScript mapping libraries. ISPRS International Journal of Geo-Information 2019; 8(8): 348. doi:10.3390/ijgi8080348
33. Núñez JR., Anderton CR., Renslow RS. Optimizing colormaps with consideration for color vision deficiency to enable accurate interpretation of scientific data 2017. (arXiv:1712.01662). arXiv. https://doi.org/10.48550/arXiv.1712.01662
34. Panda SS., Terrill TH., Siddique A., Mahapatra AK., Morgan ER., Pech-Cervantes AA., Van Wyk JA. Development of a decision support system for animal health management using geo information technology: A novel approach to precision livestock management. Agriculture 2024; 14(5): 696. doi:10.3390/agriculture14050696
35. Shah AD., Bartlett JW., Carpenter J., Nicholas O., Hemingway H. Comparison of random forest and parametric imputation models for imputing missing data using Mice: A Caliber study. American journal of epidemiology 2014; 179(6): 764–774. doi:10.1093/aje/kwt312
36. Słomska-Przech K., Panecki T., Pokojski W. Heat maps: Perfect maps for quick reading? Comparing usability of heat maps with different levels of generalization. ISPRS International Journal of Geo-Information 2021; 10(8):562. doi:10.3390/ijgi10080562
37. Słomska Przech K., Panecki T., Pokojski W. User study of heat maps with different levels of generalisation. Abstracts of the ICA 2022; 5(1–2): 66. doi:10.5194/ica-abs-5-66-2022.
38. Slutsky DJ. Statistical errors in clinical studies. J Wrist Surg 2013; 2(4): 285–287. doi:10.1055/s-0033-1359421
39. Stekhoven DJ., Bühlmann P. MissForest nonparametric missing value imputation for mixed type data. Bioinformatics 2012; 28(1): 112–118. doi:10.1093/bioinformatics/btr597
40. Tang F., Ishwaran H. Random forest missing data algorithms. The ASA Data Science Journal 2017; 10(6): 363–377.
41. van Buuren S. Flexible Imputation of Missing Data. 2nd ed. Boca Raton: Chapman & Hall/CRC 2018. doi:10.1201/9780429492259
42. Waskom ML. seaborn: Statistical data visualization. Journal of Open Source Software 2021; 6(60): 3021. doi:10.21105/joss.03021
43. Wilkinson L., Friendly M. The history of the cluster heat map. Am Stat 2009; 63(2):179–184.
44. Zhu Y., Du S., Li B., Luo Y., Tang N. Are Large Language Models Good Statisticians? arXiv 2024. Available from: https://arxiv.org/abs/2406.07815