Application of genetic programming clustering in defining LOS criteria of urban street in Indian context

Patnaik, Ashish Kumar; Bhuyan, Prasanta Kumar

doi:10.1016/j.tbs.2015.08.003

Cited by 11 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In GP literature, the automatic problem solving ability of GP techniques is widely utilized in symbolic regression problems for datadriven modeling works (Dal Piccol Sotto and De Melo 2014). The GP method has been used extensively in many application areas, for example production scheduling (Nguyen et al 2017), optimal water reservoir-operating (Ashofteh et al 2015), energy of residential buildings (Castelli et al 2015;Kaboli et al 2017;Tahmassebi and Gandomi 2018), educational technologies (Zafra and Ventura 2012), urban planning (Patnaik and Bhuyan 2016), geotechnical design (Keshavarz and Mehramiri 2015), hydrology (Shoaib et al 2015), medicine (De Falco et al 2018). Also, GP has been widely utilized in many computer science problems such as classification problems (Tran et al 2016) (Kuo et al 2007), computer vision (Liu et al 2016), image processing (Shao et al 2014) (Liang et al 2020), signal processing (Feli and Abdali-Mohammadi 2019), artificial neural network design (Suganuma et al 2017).…”

Section: Genetic Programming Preliminaries and Gpols Algorithmmentioning

confidence: 99%

DEHypGpOls: A Genetic Programming with Evolutionary Hyper-Parameter Optimization and its Application for Stock Market Trend Prediction

Ari

Alagöz

2022

Preprint

View full text Add to dashboard Cite

Stock markets are one of the most popular financial markets since they can bring high revenues to their investors. In order to reduce the risk factor for investors, intelligent and automated stock market trend prediction tools are developed by using computational intelligence methods. This study presents a hyper-parameter optimal Genetic Programming (GP) model generation framework for a day-ahead prediction of stock market index trends. In order to obtain the best trend prediction model from the stock market data, a Differential Evolution (DE) algorithm is implemented to optimize hyper-parameters of a GP algorithm with Orthogonal Least Square (GpOls). Evolutions of GpOls agents within the hyper-parameter search space allow adaptation of GpOls algorithm for a given training dataset by enabling optimal autotuning of user-defined parameters. Authors demonstrated that this structure can significantly improve modeling performances of GpOls algorithms for data-driven modeling applications. In the study, the proposed DE based hyper GpOls (DEHypGpOls) algorithm is implemented for a day-ahead forecast problem of the Istanbul Stock Exchange 100 Index (ISE100) trends. In the experimental study, real trend data from ISE100 and seven other international stock markets are used to extract a day-ahead forecast model of daily ISE100 trends. The forecast model of the DEHypGpOls algorithm can provide 68% prediction accuracy for the test dataset. In ISE100 index market simulations, daily exchanges of ISE100 index according to buy or sell signal of the forecast model of DEHypGpOls provided about 273% more income compared to the income of a long-term investment strategy.

show abstract

Section: Genetic Programming Preliminaries and Gpols Algorithmmentioning

confidence: 99%

DEHypGpOls: A Genetic Programming with Evolutionary Hyper-Parameter Optimization and its Application for Stock Market Trend Prediction

Ari

Alagöz

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…To produce feasible solutions for efficiency and sustainability concerns, effective computational intelligence methods are needed to overcome such model complexity. Therefore, GP algorithms have found applications these problems such as energy efficiency in buildings [11], [101], the ground and soil analyzes [15], [102], urban transportation and infrastructure planning [14], [103] Financing, trade, and economy: The financial market introduces very complex, nonstationary and chaotic data models. To overcome this challenge, GP methods have been implemented and successful results have been reported.…”

Section: Urbanization and Buildingmentioning

confidence: 99%

“…Looking at the literature, it is seen that GP has been widely preferred in the problems that need symbolic regression for data modeling [6]. Accordingly, GP applications come out in many different disciplines such as classification problems [7], production scheduling [8], climate change analysis [9], energy and energy saving [10][11][12] besides educational technologies [13], urbanization [14], building [15], hydrology [16], medicine [17]. Additionally, GP has widely utilized in many computer sciences problems such as in computer vision [18], image processing [19], signal processing [20], artificial neural network design [21].…”

Section: Introductionmentioning

confidence: 99%

A Review of Genetic Programming: Popular Techniques, Fundamental Aspects, Software Tools and Applications

Ari

Alagöz

2021

Sakarya University Journal of Science

View full text Add to dashboard Cite

Genetic Programming (GP) is one of the evolutionary computation (EC) methods followed with great interest by many researchers. When GP first appeared, it has become a popular computational intelligence method because of its successful applications and its potentials to find effective solutions for difficult practical problems of many different disciplines. With the use of GP in a wide variety of areas, numerous variants of GP methods have emerged to provide more effective solutions for computation problems of diverse application fields. Therefore, GP has a very rich literature that is progressively growing. Many GP software tools developed along with process of GP algorithms. There is a need for an inclusive survey of GP literature from the beginning to today of GP in order to reveal the role of GP in the computational intelligence field. This survey study aims to provide an overview of the growing GP literature in a systematic way. The researchers, who need to implement GP methods, can gain insight of potentials in GP methods, their essential drawbacks and prevalent superiorities. Accordingly, taxonomy of GP methods is given by a systematic review of popular GP methods. In this manner, GP methods are analyzed according to two main categories, which consider the discrepancies in their program (chromosome) representation styles and their methodologies. Besides, GP applications in diverse problems are summarized. This literature survey is especially useful for new researchers to gain the required broad perspective before implementing a GP method in their problems.

show abstract

“…The authors have exposed the impact of physical and surrounding environmental characteristics of road segments while determining LOS. Patnaik and Bhuyan (2016) used an evolutionary algorithm, named Genetic Programming (GP) clustering to classify street and ranges of ATSs to define ranges of LOS categories (A-F) for mixed traffic flowsconditions. It was observed that the speed ranges corresponding to LOS categories in Indian context were lower compared to that was specified in Highway Capacity Manual (TRB 2010).…”

Section: Review Of Literaturementioning

confidence: 99%

Modelling automobile users’ response pattern in defining urban street level of service

2019

Self Cite

View full text Add to dashboard Cite

This paper presents a qualitative study on automobile users’ response pattern to assess the provided transportation service quality under heterogeneous traffic flow conditions. An Automobile Users’ Satisfaction index (AUSi) is established using data sets of questionnaire survey collected from 34 urban street segments of three midsized Indian cities. About 977 respondents with a suitable cross-section of gender, age, driving experience etc. were participated in travellers’ intercept survey. Rasch Model (RM) was applied to identify a set of quantitative measures to analyse the complex process of measuring perceived service quality and degree of drivers’ satisfaction together. The present study comprehends the multidimensional nature of users’ perception to evaluate AUSi with the help of six-dimensional variables such as roadway geometry, traffic facilities, traffic management, pavement condition, safety and aesthetics. RM offers a particular score to each user and each dimensional attribute along with a shared continuum. This way, the attributes those are more demanding to produce satisfaction as well as the variation in response of different modes of transport are evidently identified. The key findings indicate that the participants reported lower satisfaction level mainly due to the absence of separate bike/bus pull-out lanes, improper parking facilities and interruption by non-motorised vehicles/public transit or roadside commercial activities. Fuzzy C-Means (FCM) clustering was applied to classify AUSi scores into six auto Levels Of Service (LOS) categories (A–F) for each street segment. The model was well validated with a significant matching of predicted Automobile users’ LOS (ALOS) service categories with the users’ perceived Overall Satisfaction (OS) scores for fourteen randomly selected segments. This prediction model is new to mixed traffic flow condition, which uses linguistic information and real-life issues of drivers for the current state of services. Hence, the proposed method would be more credible than conventional models to support the decision makers for long term planning and designing road networks on a priority basis

show abstract

Application of genetic programming clustering in defining LOS criteria of urban street in Indian context

Cited by 11 publications

References 6 publications

DEHypGpOls: A Genetic Programming with Evolutionary Hyper-Parameter Optimization and its Application for Stock Market Trend Prediction

DEHypGpOls: A Genetic Programming with Evolutionary Hyper-Parameter Optimization and its Application for Stock Market Trend Prediction

A Review of Genetic Programming: Popular Techniques, Fundamental Aspects, Software Tools and Applications

Modelling automobile users’ response pattern in defining urban street level of service

Contact Info

Product

Resources

About