Temperature, Humidity and CO2 Information Estimation of Indoor Sports Hall Environment by Using Artificial Neural Nets

Year 2016, Volume 4 (Special Issue 2), 547 - 556, 01.09.2016

Nail Altıntaş Oğuz Fındık

Abstract

In hot weather, humidity content affects adversely the human body. It causes body fatigue and slowness in metabolism by excessive sweating and increased body temperature. If the relative humidity rate is 100% , there won't be sweating and the body temperature will rise. The rise in body temperature can lead people to death. Moreover, high amounts of CO₂ in the air accelerate fatigue. Reach of indoor area temperature, humidity and CO₂ amounts to hazard level leads to very serious problems. In this study, totally seven features as the highest and lowest temperature of the day, the highest and lowest humidity content of the day, number of spectators, direction of wind, weather events on the day of match are obtained. During the match, a data pool is generated by taking temperature, humidity and CO₂ information of the environment. Humidity and temperature values of indoor environment are taken by DHT11 temperature and humidity sensor and CO₂ sensor, then they are transferred to Arduino Mega 2560. With the help of Arduino Mega 2560 card, humidity, temperature and CO₂ values have been measured in real time. Using this obtained data pool and artificial neural nets, an expert system has been designed. In this expert system; these ten obtained features have been used as input data, and temperature, humidity and CO₂ data have been used as output data. Through this system, temperature, humidity and CO₂  information of the environment during the match to be held have been estimated at very close value.  In addition, using this system, adverse conditions that may occur in indoor sports hall can be estimated and necessary measures can be taken.

Keywords

Estimation of temperature and humidity, artificial neural nets, expert systems, arduino, sensors

Field : Sports Technology Type : Research Article

Abstract

References

• Akyürek H A (2013). Yapay zeka teknikleri kullanarak akıllı iş gücü yönetimi.
• Çuhadar M, Kayacan C (2005). Yapay Sinir Ağları Kullanılarak Konaklama İşletmelerinde Doluluk Oranı Tahmini: Türkiye'deki Konaklama İşletmeleri Üzerine Bir Deneme. Anatolia Turizm Araştırmaları Dergisi, 16(1), 121-126.
• Daisey J M, Angell W J, Apte M G (2003). Indoor air quality, ventilation and health symptoms in schools: an analysis of existing information. Indoor air, 13(1), 53-64.
• Fridlund L (1987). Safety-health and working conditions. Joint Industrial Safety Council.
• Hayta A B (2007). Çalışma Ortamı Koşullarının işletme Verimliliği üzerine Etkisi. Ticaret ve Turizm Eğitim Fakültesi Dergisi Yı l, 21-41.
• Karaatlı M, Helvacıoğlu Ö C, Ömürbek N, Tokgöz G (2012). Yapay Sinir Ağları Yöntemi İle Otomobil Satış Tahmini. Uluslararası Yönetim İktisat ve İşletme Dergisi, 8(17), 87-100.
• Keleşoğlu Ö, Fırat A (2006). Tuğla Duvardaki ve Tesisattaki Isı Kaybının Yapay Sinir Ağları İle Belirlenmesi. Fırat Üniv. Fen ve Müh. Bil. Der, 18(1), 133-141.
• Kaya İ, Engin O (2011). Kalite İyileştirme Sürecinde Yapay Zekâ Tekniklerinin Kullanımı. Pamukkale University Journal of Engineering Sciences, 11(1).
• Kırlıoğlu H, Ceyhan İ F (2014). Mali Tablo Denetiminde Ön Analitik İnceleme Tekniği Olarak Veri Madenciliğinin Kullanımı: Borsa İstanbul Uygulaması. Akademik Yaklaşımlar Dergisi, 5(1).
• Terzi Ö (2006). Yapay Sinir Ağları Metodu ile Eğirdir Gölü Su Sıcaklığının Tahmini. SDÜ Fen Bilimleri Enstitüsü Dergisi, 10(2).
• Mitchell T M (1997). Machine learning. Computer Science Series (McGraw-Hill, Burr Ridge, 1997) Math.
• Narin A, İşler Y, Özer M (2014), Konjestif Kalp Yetmezliği Teşhisinde Kullanılan Çapraz Doğrulama Yöntemlerinin Sınıflandırıcı Performanslarının Belirlenmesine Olan Etkilerinin Karşılaştırılması, Dokuz Eylül Üniversitesi Mühendislik Fakültesi Mühendislik Bilimleri Dergisi, 16(48), 1-8
• Volkov O (2014). Indoor climate in air-supported structure.
• Yavuz S, Deveci M (2012). İstatiksel Normalizasyon Tekniklerinin Yapay Sinir Ağın Performansına Etkisi. Erciyes Üniversitesi İktisadi Ve İdari Bilimler Fakültesi Dergisi, (40), 167-187.
• http://www.robotistan.com/dht11-isi-ve-nem-sensoru-kart (05 May ,2016).
• http://sandboxelectronics.com/?product=mg-811-co2-gas-sensor-module (05 May, 2016).
• http://dca.iupr.com/lectures/lecture08-classification-with-neural-networks (05 May,2016) .
• http://www.solver.com/xlminer/help/neural-networks-classification-intro(01 May,2016).