Konut Fiyatlarının Tahmini için Polinomsal Regresyon ve Yapay Sinir Ağları Yöntemlerinin Uygulamalı Karşılaştırılması

BARUT, Zeynep; Bilgin, Turgay Tugay

doi:10.19113/sdufenbed.1190150

Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi

2023

DOI: 10.19113/sdufenbed.1190150

|View full text |Cite

Konut Fiyatlarının Tahmini için Polinomsal Regresyon ve Yapay Sinir Ağları Yöntemlerinin Uygulamalı Karşılaştırılması

Zeynep BARUT

Turgay Tugay Bilgin

Abstract: Gayrimenkul sektörünün hızlı ekonomik büyümesi nedeniyle, konut fiyatlarının tahmini geleceğe yönelik planlamalar için önemlidir. Bu çalışmanın amacı makine öğrenmesi yöntemlerini kullanarak bir konutun potansiyel fiyatını tahmin etmektir. Makine öğrenmesi yöntemleri olarak Yapay sinir ağları ve Polinomsal regresyon kullanılarak bunların tahmin performansları karşılaştırılmıştır. Makine öğrenmesi yöntemlerinin uygulanabilmesi için KNIME veri analiz platformu kullanılmıştır. Yöntemlerin başarısını ölçmek için… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Article1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Exercise and resting periods: Thermal comfort dynamics in gym environments

Avci,

Balci,

Basaran

2024

Build. Simul.

View full text Add to dashboard Cite

Physical exercise spaces emerged as popular facilities due to recognizing the significance of physical well-being. This study investigates the relationship among physiological responses, human body energy transfer modes, and indoor environmental conditions in influencing thermal comfort perception within indoor physical exercise space. Seven male participants engaged in a 30 min constant-work-rate cycling exercise and a 20 min resting period in a climatic chamber. The physiological and environmental responses were recorded during the experiments, and the body’s energy transfer modes were calculated using the collected data. The dataset was prepared using the 2 min averages of the collected data and calculated parameters across the experiment phases, including the features of skin temperature, core temperature, skin relative humidity, heart rate, oxygen consumption, body’s heat transfer rates through convection, radiation, evaporation, and respiration, net metabolic heat production rate (metabolic rate minus external work rate), indoor air temperature, indoor relative humidity, air velocity, and radiant temperature. Gradient boosting regressor (GBR) was selected as the analyzing method to estimate predicted mean vote (PMV) and thermal sensation vote (TSV) indices during exercise and resting periods using features determined in the study. Thus, the four GBR models were defined as PMV-Exercise, PMV-Resting, TSV-Exercise, and TSV-Resting. In order to optimize the models’ performances, the hyperparameter tuning process was executed using the GridSearchCV method. A permutation feature importance analysis was performed, emphasizing the significance of net metabolic heat production rate (24.2%), radiant temperature (17.0%), and evaporative heat transfer rate (13.1%). According to the results, PMV-Exercise, PMV-Resting, and TSV-Resting GBR models performed better, while TSV-Exercise faced challenges in predicting exercise thermal sensations. Critically, this study addresses the need to understanding the interrelationship among physiological responses, environmental conditions, and human body energy transfer modes during both exercise and resting periods to optimize thermal comfort within indoor exercise spaces. The results of this study contribute to the operation of indoor gym environments to refine their indoor environmental parameters to optimize users’ thermal comfort and well-being. The study is limited to a small sample size consisting solely of male participants, which may restrict the generalizability of the findings. Future research could explore personalized thermal comfort control systems and synergies between comfort optimization and energy efficiency in indoor exercise spaces.

show abstract

Exercise and resting periods: Thermal comfort dynamics in gym environments

Avci,

Balci,

Basaran

2024

Build. Simul.

View full text Add to dashboard Cite

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

hi@scite.ai

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

Konut Fiyatlarının Tahmini için Polinomsal Regresyon ve Yapay Sinir Ağları Yöntemlerinin Uygulamalı Karşılaştırılması

Cited by 1 publication

References 9 publications

Exercise and resting periods: Thermal comfort dynamics in gym environments

Exercise and resting periods: Thermal comfort dynamics in gym environments

Contact Info

Product

Resources

About