Public Transport Route Recommender Regarding Multiple Factors

Bozyiğit, Alican; Nasiboğlu, Efendi; Utku, Semih

doi:10.1109/ubmk.2018.8566432

Cited by 4 publications

(11 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this section, various pre-processing methods, feature extraction and selection processes on TurkishCyberBullying [16] dataset, and then the widely used classification algorithms are applied to determine cyberbullying.…”

Section: Methodsmentioning

confidence: 99%

“…In case of Turkish language based cyberbullying studies there are only one public dataset collected by Bozyigit et. al [16]. The authors have used Twitter as data source and produced a TurkishCyberBulling sample Turkish dataset for cyberbullying detection problem.…”

Section: Introductionmentioning

confidence: 99%

“…They also have experimented J48, NB and SVM in their study and the mentioned algorithms have produced 54%, 81%, and 74% in terms of F-measure. The second study in Turkish cyberbullying domain has been conducted in [16]. In their study, the authors evaluated a wide range of the algorithms such as SVM, NB, RF, KNN, Bagging, and J48 correspondingly.…”

Section: Introductionmentioning

confidence: 99%

“…Since the text data produces a high dimensional training space for machine learning algorithms, we have used Chi-Squared (CH2) feature selection strategy to obtain best subset of features. The parametertuned/optimized version of the proposed algorithm on top of reduced feature dimension has produced an F-measure value of 92.5% higher than the performance conducted in [16]. Finally, we also compared the results of the proposed algorithm with Naïve Bayes (NB), Support Vector Machine (SVM), C4.5, Random Forest (RF) and we provided the corresponding results in Section 3.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Grid Aramayla Optimize Edilmiş Bayes Lojistik Regresyon Algoritmasının Türkçe Mikro Blog Verilerinde Sanal Zorbalık Tespitinde Kullanılması

Özçift¹,

Kılınç²,

Bozyiğit³

2019

Academic Platform Journal of Engineering and Science

View full text Add to dashboard Cite

There is a huge interaction between users of various social media platforms. This communication produces enormous amount of user data worth to be analyzed from numerous aspects. One of the research area emerging from the user data is a major security issue known as cyberbullying. Since this problem has been recognized as the source of cybercrimes, design of a system to detect cyberbullying attacks/sources through the micro-blog texts is evident. Most of the academic search of this topic has been conducted in English language. The originality of this paper is that we develop an accurate cyberbullying detection system for Turkish language. We used data from Twitter to develop a supervised machine learning model on top of Bayesian Logistic Regression whose parameters are tuned with the use of grid-search algorithm. Since the text data produces a high dimensional training space for machine learning algorithms, we also used Chi-Squared (CH2) feature selection strategy to obtain best subset of features. The optimized version of the proposed algorithm on top of reduced feature dimension has produced an f-measure value of 0.925. Finally, we also compared the results of the proposed algorithm with the frequently used machine learning methods from literature and we provided the corresponding results in related sections.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Grid Aramayla Optimize Edilmiş Bayes Lojistik Regresyon Algoritmasının Türkçe Mikro Blog Verilerinde Sanal Zorbalık Tespitinde Kullanılması

Özçift¹,

Kılınç²,

Bozyiğit³

2019

Academic Platform Journal of Engineering and Science

View full text Add to dashboard Cite

show abstract

“…A. Bozyigit et al [1] proposed a similar system for public transport route recommendations. They focused and tested on the public transport network of Izmir, Turkey having 7,704 stations and 43,467 connections between these stations.…”

Section: Related Workmentioning

confidence: 99%

Multi-Modal Route Recommender System for Bangkok Public Transportation

Poonsilp*

2020

IJRTE

View full text Add to dashboard Cite

Currently, Bangkok has a 151 kilometers service of a rail line, whereas the total plan is 540 kilometers. More rail lines are now under construction and supposed to be done by a few years. Regarding a massive public transportation network, we need a route recommender system to make traveling more efficient. This paper proposes the route recommender system which supports multi modes of transportation in Bangkok, including BTS, MRT, ARL, BMTA bus, and Chaophraya Riverboat. Users can see suggested routes and sort routes by travel time, fare, number of transfer, and overall score. The A* algorithm with the Haversine formula as the heuristic function is used to calculate the possible routes. Then the best route is selected based on the score, which is calculated form four factors: travel time, fare, number of transfer, and distance. The database contains 13,510 stops, and the results show that the system can suggest accurate routes within a few seconds, which is fast enough for all use cases and achieved overall user satisfaction at 84.8% from our user experience survey.

show abstract

Toplu taşıma ağı mesafesine dayalı çok kriterli konum değerlendirme endeksi: İzmir örneği

Nasiboglu,

Balbal,

Rusiman

et al. 2024

GUMMFD

View full text Add to dashboard Cite

Konut ve kiralama piyasası ülke ekonomilerinde önemli bir ekonomik yere sahiptir. Konut fiyatları genel olarak evin alanı, oda sayısı, bulunduğu kat gibi özelliklere göre belirlenmektedir. Ancak evin bu özelliklerinin yanı sıra konumu da evin pazarlama değerlendirmesi üzerinde önemli bir etkiye sahiptir. Bu bakımdan subjektif fiyat spekülasyonlarının önüne geçebilmek için, konutun konumunu objektif kriterlere göre değerlendirebilmek oldukça önemlidir. Bu çalışmada bir nesnenin konumunun değerlendirilmesi, çok kriterli karar verme problemi olarak ele alınmıştır. Bu konumdan toplu taşıma araçlarıyla şehrin diğer noktalarına ulaşım kolaylığının yanı sıra metro istasyonları, hastaneler, alışveriş merkezleri, yeşil park alanları gibi önemli noktalara ulaşımın kolaylığını da göz önünde bulundurmaktadır. Bu bağlamda, bir toplu taşıma ağı (TTA) mesafe kavramı tanıtılmış ve Konum Değerlendirme Endeksi (KDE) adı verilen bir endeks önerilmiştir. Konutun konumuna göre piyasa değerinin tahmin edilmesinde bu endeksin önemi vurgulanmıştır. Önerilen model, Türkiye'nin üçüncü büyük metropol şehri olan İzmir şehrinin toplu ulaşım ağı verileri üzerinde çalıştırılmış ve şehrin KDE ısı haritası oluşturulmuştur.

show abstract

Public Transport Route Recommender Regarding Multiple Factors

Cited by 4 publications

References 11 publications

Grid Aramayla Optimize Edilmiş Bayes Lojistik Regresyon Algoritmasının Türkçe Mikro Blog Verilerinde Sanal Zorbalık Tespitinde Kullanılması

Grid Aramayla Optimize Edilmiş Bayes Lojistik Regresyon Algoritmasının Türkçe Mikro Blog Verilerinde Sanal Zorbalık Tespitinde Kullanılması

Multi-Modal Route Recommender System for Bangkok Public Transportation

Toplu taşıma ağı mesafesine dayalı çok kriterli konum değerlendirme endeksi: İzmir örneği

Contact Info

Product

Resources

About