User Guide
Why can I only view 3 results?
You can also view all results when you are connected from the network of member institutions only. For non-member institutions, we are opening a 1-month free trial version if institution officials apply.
So many results that aren't mine?
References in many bibliographies are sometimes referred to as "Surname, I", so the citations of academics whose Surname and initials are the same may occasionally interfere. This problem is often the case with citation indexes all over the world.
How can I see only citations to my article?
After searching the name of your article, you can see the references to the article you selected as soon as you click on the details section.
  Citation Number 11
 Views 10
 Downloands 4
Akıllı Durak Sistemindeki Araç Seyahat Sürelerinin Birleşik Yapay Sinir Ağları Kullanarak Tahmini
2020
Journal:  
Avrupa Bilim ve Teknoloji Dergisi
Author:  
Abstract:

Toplu taşımacılık özellikle nüfus yoğunluğunun fazla olduğu şehirlerde günlük yaşamda yoğun bir şekilde kullanılmaktadır. Toplu taşıma araçlarını kullanan birçok insan duraklarda beklemelerinden dolayı zaman kaybı yaşamaktadırlar. Bu nedenle toplu taşıma araçlarının duraklara geliş süresinin doğru şekilde hesaplanması veya tahmin edilmesi ve yolculara bildirilmesi önem arz etmektedir. Gerçek zamanlı trafik koşullarının ve trafik olaylarının karmaşıklığı ve çeşitliliği nedeniyle otobüslerin, duraklara geliş zamanlarını doğru bir şekilde tahmin etmek zor bir problemdir. Literatürde otobüs varış sürelerinin tahmin edilmesi için çeşitli teknikler ve parametreler kullanılmıştır. Bu çalışmada, toplu taşıma araçlarının duraklara varış zamanını doğru bir şekilde tahmin edebilmek için birleşik yapay sinir ağları (YSA) algoritması tabanlı bir sistem önerilmiştir. Birleşik YSA modeli birden fazla yapay sinir ağı modelinin çıktılarının ortaklaşa değerlendirilmesi ile YSA modellerinin performansını arttırabilmekte ve dolayısı ile daha doğru sonuçlar verebilmektedir. Bu nedenle birleşik YSA modelleri çeşitli uygulamalarda kullanılmaktadır. Önerilen birleşik YSA algoritması gerçek veriler üzerinde çalıştırılmıştır. Çalışmada Kayseri Büyükşehir Belediyesi akıllı otobüs durak verileri ve 800 adet farklı otobüs hattının GPS verisi kullanılmıştır. Önerilen sistemde akıllı duraklarda bulunan kare kodlar (QR) okutularak veya paylaşılan yolcu GPS (Küresel Konumlama Sistemi) verisini kullanılarak seçilen duraktan hangi otobüsün ne zaman geçeceği birleşik YSA modeli ile tahmin edilebilmekte ve yolculara bildirilmektedir. Çalışmada kullanılan YSA algoritmasının sonuçları lineer regresyon yöntemi sonuçları ile karşılaştırılmıştır. Deneysel sonuçlar önerilen birleşik YSA yaklaşımının lineer regresyon yaklaşımına göre daha doğru sonuçlar verdiğini göstermiştir. Çalışmada ayrıca geliştirilen birleşik YSA modelini kullanan mobil ve web uygulaması geliştirilmiştir. Geliştirilen uygulama ile yolcular akıllı duraklardaki kare kodları kullanarak sisteme bağlanmakta ve tahmini otobüs geliş sürelerini takip edebilmektedirler.

Keywords:

Prognosis of vehicle travel times in the smart stop system using a joint artificial nerve network
2020
Author:  
Abstract:

Public transportation is widely used in everyday life, especially in cities where the population is high. Many people who use public transportation experience a waste of time due to their waiting at stations. It is therefore important that the time of arrival of public transportation to the stations is correctly calculated or predicted and the passengers are informed. Due to the complexity and diversity of real-time traffic conditions and traffic events, it is difficult to correctly predict the times when buses arrive at stations. In literature, a variety of techniques and parameters have been used to predict bus arrival times. In this study, a system based on the unified artificial nervous networks (YSA) algorithm was proposed to be able to correctly predict the time of arrival of public transport vehicles to stations. The combined YSA model can improve the performance of the YSA models by joint assessment of the outcomes of multiple artificial nervous network models and thus deliver more accurate results. Therefore, the combined YSA models are used in various applications. The recommended combined YSA algorithm is run on real data. In the study, the Kayseri Metropolitan Municipality used the smart bus stop data and the GPS data of 800 different bus lines. In the recommended system, the square codes (QR) in the smart stations can be read or shared passenger GPS (Global Location System) data can be predicted and informed by the combined YSA model of which bus will pass from the selected station. The results of the YSA algorithm used in the study were compared with the results of the linear regression method. Experimental findings have shown that the proposed combined YSA approach provides more accurate results than the linear regression approach. The study also developed mobile and web applications using the unified YSA model developed. With the advanced application, passengers connect to the system using the square codes on the smart stations and can track the estimated bus arrival times.

Keywords:

Prediction Of Vehicle Arrival Times In The Smart Bus Stop System Using Ensemble Artificial Neural Networks
2020
Author:  
Abstract:

Public transportation is used extensively in daily life, especially in cities where the population density is high. Many people who use public transportation experience time loss due to waiting at the stops. For this reason, it is important to accurately calculate or estimate the arrival time of public transport to the stops and inform the passengers. Due to the complexity and diversity of real-time traffic conditions and traffic events, it is a difficult problem to accurately predict the arrival times of buses to the stops. Various techniques and parameters have been used in the literature to estimate bus arrival times. In this study, a system based on ensemble artificial neural networks (ANN) algorithm has been proposed in order to accurately predict the arrival time of public transport to the stops. The ensemble ANN model can increase the performance of ANN models and thus provide more accurate results by jointly evaluating the outputs of more than one neural network model. Therefore, ensemble ANN models are used in various applications. The proposed ensemble ANN algorithm was run on real data. In this study, Kayseri Metropolitan Municipality smart bus stop data and GPS data of 800 different bus lines were used. The proposed system predicts the arrival time of the public transportation vehicle when the QR codes of smart bus stops and or the shared GPS (Global Positioning System) of passengers were used. The experimental results show that the proposed ensemble ANN approach gives more accurate results than the LR approach. In the study, a mobile and web application using the combined ANN model was developed. With the developed application, passengers can connect to the system using square codes in smart stops and follow the estimated bus arrival times.

Keywords:

Citation Owners
Attention!
To view citations of publications, you must access Sobiad from a Member University Network. You can contact the Library and Documentation Department for our institution to become a member of Sobiad.
Off-Campus Access
If you are affiliated with a Sobiad Subscriber organization, you can use Login Panel for external access. You can easily sign up and log in with your corporate e-mail address.
Similar Articles






Avrupa Bilim ve Teknoloji Dergisi

Field :   Fen Bilimleri ve Matematik; Mühendislik

Journal Type :   Uluslararası

Metrics
Article : 3.175
Cite : 5.550
2023 Impact : 0.178
Avrupa Bilim ve Teknoloji Dergisi